2024 Server CPUs

2 x Intel Xeon 6780E testing with a Quanta Cloud QuantaGrid D55Q-2U S7Q-MB-MPS-MDP (2A05.QCT001 BIOS) and ASPEED on Ubuntu 24.04 via the Phoronix Test Suite.

Compare your own system(s) to this result file with the Phoronix Test Suite by running the command: phoronix-test-suite benchmark 2406049-NE-2024SERVE17
Jump To Table - Results

View

Do Not Show Noisy Results
Do Not Show Results With Incomplete Data
Do Not Show Results With Little Change/Spread
List Notable Results
Show Result Confidence Charts

Limit displaying results to tests within:

AV1 2 Tests
BLAS (Basic Linear Algebra Sub-Routine) Tests 4 Tests
C++ Boost Tests 5 Tests
Chess Test Suite 2 Tests
Timed Code Compilation 8 Tests
C/C++ Compiler Tests 16 Tests
Compression Tests 3 Tests
CPU Massive 25 Tests
Creator Workloads 23 Tests
Cryptography 5 Tests
Database Test Suite 5 Tests
Encoding 7 Tests
Fortran Tests 7 Tests
Game Development 5 Tests
HPC - High Performance Computing 29 Tests
Imaging 3 Tests
Common Kernel Benchmarks 3 Tests
LAPACK (Linear Algebra Pack) Tests 3 Tests
Linear Algebra 2 Tests
Machine Learning 7 Tests
Molecular Dynamics 10 Tests
MPI Benchmarks 10 Tests
Multi-Core 44 Tests
NVIDIA GPU Compute 3 Tests
Intel oneAPI 7 Tests
OpenMPI Tests 18 Tests
Programmer / Developer System Benchmarks 12 Tests
Python 2 Tests
Raytracing 2 Tests
Renderers 5 Tests
Scientific Computing 15 Tests
Software Defined Radio 2 Tests
Server 7 Tests
Server CPU Tests 17 Tests
Single-Threaded 2 Tests
Video Encoding 7 Tests
Common Workstation Benchmarks 3 Tests

Statistics

Show Overall Harmonic Mean(s)
Show Overall Geometric Mean
Show Geometric Means Per-Suite/Category
Show Wins / Losses Counts (Pie Chart)
Normalize Results
Remove Outliers Before Calculating Averages

Graph Settings

Force Line Graphs Where Applicable
Convert To Scalar Where Applicable
Disable Color Branding
Prefer Vertical Bar Graphs
No Box Plots
On Line Graphs With Missing Data, Connect The Line Gaps

Additional Graphs

Show Perf Per Core/Thread Calculation Graphs Where Applicable
Show Perf Per Clock Calculation Graphs Where Applicable
Show Perf Per RAM Channel Calculation Graphs Where Applicable

Multi-Way Comparison

Condense Multi-Option Tests Into Single Result Graphs
Condense Test Profiles With Multiple Version Results Into Single Result Graphs

Table

Show Detailed System Result Table

Run Management

Highlight
Result
Hide
Result
Result
Identifier
View Logs
Performance Per
Dollar
Date
Run
  Test
  Duration
Xeon Platinum 8490H
April 16
  22 Hours, 19 Minutes
Xeon Platinum 8490H 2P
April 17
  23 Hours
Xeon Platinum 8592+
April 11
  22 Hours, 9 Minutes
Xeon Platinum 8592+ 2P
April 08
  23 Hours, 49 Minutes
Xeon Max 9468
April 21
  1 Day, 3 Hours, 43 Minutes
Xeon Max 9468 2P
April 22
  1 Day, 34 Minutes
Xeon Max 9480
April 26
  1 Day, 1 Hour, 37 Minutes
Xeon Max 9480 2P
April 27
  1 Day, 6 Hours, 26 Minutes
Xeon Platinum 8380 2P
May 07
  1 Day, 5 Hours, 29 Minutes
Xeon Platinum 8380
May 09
  1 Day, 7 Hours, 15 Minutes
EPYC 9684X 2P
May 11
  1 Day, 4 Hours, 57 Minutes
EPYC 9684X
May 12
  1 Day, 27 Minutes
EPYC 9654
May 13
  1 Day, 1 Hour, 48 Minutes
EPYC 9654 2P
May 14
  1 Day, 6 Hours, 48 Minutes
EPYC 9754
May 15
  1 Day, 6 Hours
EPYC 9754 2P
May 17
  1 Day, 9 Hours, 52 Minutes
EPYC 8534P
May 18
  1 Day, 3 Hours, 8 Minutes
EPYC 8534PN
May 19
  1 Day, 3 Hours, 48 Minutes
Xeon 6766E 2P
May 24
  1 Day, 3 Hours, 18 Minutes
Xeon 6766E
May 25
  18 Hours, 24 Minutes
Xeon 6780E
May 26
  17 Hours, 33 Minutes
Xeon 6780E 2P
May 27
  23 Hours, 13 Minutes
Invert Hiding All Results Option
  1 Day, 2 Hours, 10 Minutes

Only show results where is faster than
Only show results matching title/arguments (delimit multiple options with a comma):
Do not show results matching title/arguments (delimit multiple options with a comma):


2024 Server CPUsProcessorMotherboardChipsetMemoryDiskGraphicsNetworkMonitorOSKernelCompilerFile-SystemScreen ResolutionXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380 2PXeon Platinum 8380EPYC 9684X 2PEPYC 9684XEPYC 9654EPYC 9654 2PEPYC 9754EPYC 9754 2PEPYC 8534PEPYC 8534PNXeon 6766E 2PXeon 6766EXeon 6780EXeon 6780E 2PIntel Xeon Platinum 8490H @ 3.50GHz (60 Cores / 120 Threads)Quanta Cloud QuantaGrid D54Q-2U S6Q-MB-MPS (3B05.TEL4P1 BIOS)Intel Device 1bce512GB2 x 1920GB KIOXIA KCD8XPUG1T92ASPEEDUbuntu 24.046.9.0-060900rc3-generic (x86_64)GCC 13.2.0ext41920x12002 x Intel Xeon Platinum 8490H @ 3.50GHz (120 Cores / 240 Threads)1008GB2 x Intel X710 for 10GBASE-TINTEL XEON PLATINUM 8592+ @ 3.90GHz (64 Cores / 128 Threads)512GB2 x INTEL XEON PLATINUM 8592+ @ 3.90GHz (128 Cores / 256 Threads)1008GB2 x Intel X710 for 10GBASE-TIntel Xeon Max 9468 @ 3.50GHz (48 Cores / 96 Threads)576GB2 x Intel Xeon Max 9468 @ 3.50GHz (96 Cores / 192 Threads)1136GB2 x Intel X710 for 10GBASE-TIntel Xeon Max 9480 @ 3.50GHz (56 Cores / 112 Threads)576GB2 x Intel Xeon Max 9480 @ 3.50GHz (112 Cores / 224 Threads)1136GB2 x Intel X710 for 10GBASE-T2 x Intel Xeon Platinum 8380 @ 3.40GHz (80 Cores / 160 Threads)Intel M50CYP2SB2U (SE5C6200.86B.0022.D08.2103221623 BIOS)Intel Ice Lake IEH512GBVE2282 x Intel X710 for 10GBASE-T + 2 x Intel E810-C for QSFP1920x1080Intel Xeon Platinum 8380 @ 3.40GHz (40 Cores / 80 Threads)256GB2 x AMD EPYC 9684X 96-Core @ 2.55GHz (192 Cores / 384 Threads)AMD Titanite_4G (RTI1007B BIOS)AMD Device 14a41520GBBroadcom NetXtreme BCM5720 PCIe1920x1200AMD EPYC 9684X 96-Core @ 2.55GHz (96 Cores / 192 Threads)12 x 64GB DDR5-4800MT/s Samsung M321R8GA0BB0-CQKEGAMD EPYC 9654 96-Core @ 2.40GHz (96 Cores / 192 Threads)2 x AMD EPYC 9654 96-Core @ 2.40GHz (192 Cores / 384 Threads)1520GBAMD EPYC 9754 128-Core @ 2.25GHz (128 Cores / 256 Threads)12 x 64GB DDR5-4800MT/s Samsung M321R8GA0BB0-CQKEG2 x AMD EPYC 9754 128-Core @ 2.25GHz (256 Cores / 512 Threads)1520GBAMD EPYC 8534P 64-Core @ 2.30GHz (64 Cores / 128 Threads)AMD Cinnabar (RCB1009C BIOS)6 x 32GB DDR5-4800MT/s Samsung M321R4GA0BB0-CQKMG2 x 1920GB KIOXIA KCD8XPUG1T92 + 2000GB Corsair MP700 PRO2 x Broadcom NetXtreme BCM5720 PCIeAMD EPYC 8534PN 64-Core @ 2.00GHz (64 Cores / 128 Threads)2 x 1920GB KIOXIA KCD8XPUG1T922 x Intel Xeon 6766E @ 2.70GHz (288 Cores)Quanta Cloud QuantaGrid D55Q-2U S7Q-MB-MPS-MDP (2A05.QCT001 BIOS)Intel Ice Lake IEH512GB3201GB Micron_7450_MTFDKCB3T2TFS + 2 x 1920GB KIOXIA KCD8XPUG1T922 x Broadcom BCM57416 NetXtreme-E Dual-Media 10G RDMAIntel Xeon 6766E @ 2.70GHz (144 Cores)256GB2 x 1920GB KIOXIA KCD8XPUG1T92 + 3201GB Micron_7450_MTFDKCB3T2TFSIntel Xeon 6780E @ 3.00GHz (144 Cores)3201GB Micron_7450_MTFDKCB3T2TFS + 2 x 1920GB KIOXIA KCD8XPUG1T922 x Intel Xeon 6780E @ 3.00GHz (288 Cores)512GBOpenBenchmarking.orgKernel Details- Transparent Huge Pages: madviseCompiler Details- --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-backtrace --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-13-OiuXZC/gcc-13-13.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-13-OiuXZC/gcc-13-13.2.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -vProcessor Details- Xeon Platinum 8490H: Scaling Governor: intel_pstate performance (EPP: performance) - CPU Microcode: 0x2b000590- Xeon Platinum 8490H 2P: Scaling Governor: intel_pstate performance (EPP: performance) - CPU Microcode: 0x2b000590- Xeon Platinum 8592+: Scaling Governor: intel_pstate performance (EPP: performance) - CPU Microcode: 0x21000200- Xeon Platinum 8592+ 2P: Scaling Governor: intel_pstate performance (EPP: performance) - CPU Microcode: 0x21000200- Xeon Max 9468: Scaling Governor: intel_pstate performance (EPP: performance) - CPU Microcode: 0x2c000290- Xeon Max 9468 2P: Scaling Governor: intel_pstate performance (EPP: performance) - CPU Microcode: 0x2c000290- Xeon Max 9480: Scaling Governor: intel_pstate performance (EPP: performance) - CPU Microcode: 0x2c000290- Xeon Max 9480 2P: Scaling Governor: intel_pstate performance (EPP: performance) - CPU Microcode: 0x2c000290- Xeon Platinum 8380 2P: Scaling Governor: intel_pstate performance (EPP: performance) - CPU Microcode: 0xd0003d1- Xeon Platinum 8380: Scaling Governor: intel_pstate performance (EPP: performance) - CPU Microcode: 0xd0003d1- EPYC 9684X 2P: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa101144- EPYC 9684X: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa101144- EPYC 9654: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa101144- EPYC 9654 2P: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa101144- EPYC 9754: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xaa00116- EPYC 9754 2P: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xaa00116- EPYC 8534P: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xaa00213- EPYC 8534PN: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xaa00213- Xeon 6766E 2P: Scaling Governor: intel_pstate performance (EPP: performance) - CPU Microcode: 0x13000131- Xeon 6766E: Scaling Governor: intel_pstate performance (EPP: performance) - CPU Microcode: 0x13000131- Xeon 6780E: Scaling Governor: intel_pstate performance (EPP: performance) - CPU Microcode: 0x13000131- Xeon 6780E 2P: Scaling Governor: intel_pstate performance (EPP: performance) - CPU Microcode: 0x13000131Java Details- OpenJDK Runtime Environment (build 21.0.3-ea+7-Ubuntu-1build1)Python Details- Python 3.12.2Security Details- Xeon Platinum 8490H: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + reg_file_data_sampling: Not affected + retbleed: Not affected + spec_rstack_overflow: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS IBPB: conditional RSB filling PBRSB-eIBRS: SW sequence + srbds: Not affected + tsx_async_abort: Not affected- Xeon Platinum 8490H 2P: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + reg_file_data_sampling: Not affected + retbleed: Not affected + spec_rstack_overflow: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS IBPB: conditional RSB filling PBRSB-eIBRS: SW sequence + srbds: Not affected + tsx_async_abort: Not affected- Xeon Platinum 8592+: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + reg_file_data_sampling: Not affected + retbleed: Not affected + spec_rstack_overflow: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS IBPB: conditional RSB filling PBRSB-eIBRS: SW sequence + srbds: Not affected + tsx_async_abort: Not affected- Xeon Platinum 8592+ 2P: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + reg_file_data_sampling: Not affected + retbleed: Not affected + spec_rstack_overflow: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS IBPB: conditional RSB filling PBRSB-eIBRS: SW sequence + srbds: Not affected + tsx_async_abort: Not affected- Xeon Max 9468: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + reg_file_data_sampling: Not affected + retbleed: Not affected + spec_rstack_overflow: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS IBPB: conditional RSB filling PBRSB-eIBRS: SW sequence + srbds: Not affected + tsx_async_abort: Not affected- Xeon Max 9468 2P: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + reg_file_data_sampling: Not affected + retbleed: Not affected + spec_rstack_overflow: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS IBPB: conditional RSB filling PBRSB-eIBRS: SW sequence + srbds: Not affected + tsx_async_abort: Not affected- Xeon Max 9480: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + reg_file_data_sampling: Not affected + retbleed: Not affected + spec_rstack_overflow: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS IBPB: conditional RSB filling PBRSB-eIBRS: SW sequence + srbds: Not affected + tsx_async_abort: Not affected- Xeon Max 9480 2P: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + reg_file_data_sampling: Not affected + retbleed: Not affected + spec_rstack_overflow: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS IBPB: conditional RSB filling PBRSB-eIBRS: SW sequence + srbds: Not affected + tsx_async_abort: Not affected- Xeon Platinum 8380 2P: gather_data_sampling: Mitigation of Microcode + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Mitigation of Clear buffers; SMT vulnerable + reg_file_data_sampling: Not affected + retbleed: Not affected + spec_rstack_overflow: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS IBPB: conditional RSB filling PBRSB-eIBRS: SW sequence + srbds: Not affected + tsx_async_abort: Not affected- Xeon Platinum 8380: gather_data_sampling: Mitigation of Microcode + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Mitigation of Clear buffers; SMT vulnerable + reg_file_data_sampling: Not affected + retbleed: Not affected + spec_rstack_overflow: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS IBPB: conditional RSB filling PBRSB-eIBRS: SW sequence + srbds: Not affected + tsx_async_abort: Not affected- EPYC 9684X 2P: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + reg_file_data_sampling: Not affected + retbleed: Not affected + spec_rstack_overflow: Mitigation of Safe RET + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS IBPB: conditional STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected- EPYC 9684X: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + reg_file_data_sampling: Not affected + retbleed: Not affected + spec_rstack_overflow: Mitigation of Safe RET + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS IBPB: conditional STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected- EPYC 9654: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + reg_file_data_sampling: Not affected + retbleed: Not affected + spec_rstack_overflow: Mitigation of Safe RET + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS IBPB: conditional STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected- EPYC 9654 2P: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + reg_file_data_sampling: Not affected + retbleed: Not affected + spec_rstack_overflow: Mitigation of Safe RET + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS IBPB: conditional STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected- EPYC 9754: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + reg_file_data_sampling: Not affected + retbleed: Not affected + spec_rstack_overflow: Mitigation of Safe RET + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS IBPB: conditional STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected- EPYC 9754 2P: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + reg_file_data_sampling: Not affected + retbleed: Not affected + spec_rstack_overflow: Mitigation of Safe RET + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS IBPB: conditional STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected- EPYC 8534P: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + reg_file_data_sampling: Not affected + retbleed: Not affected + spec_rstack_overflow: Mitigation of Safe RET + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS IBPB: conditional STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected- EPYC 8534PN: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + reg_file_data_sampling: Not affected + retbleed: Not affected + spec_rstack_overflow: Mitigation of Safe RET + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS IBPB: conditional STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected- Xeon 6766E 2P: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + reg_file_data_sampling: Not affected + retbleed: Not affected + spec_rstack_overflow: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS IBPB: conditional RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected- Xeon 6766E: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + reg_file_data_sampling: Not affected + retbleed: Not affected + spec_rstack_overflow: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS IBPB: conditional RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected- Xeon 6780E: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + reg_file_data_sampling: Not affected + retbleed: Not affected + spec_rstack_overflow: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS IBPB: conditional RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected- Xeon 6780E 2P: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + reg_file_data_sampling: Not affected + retbleed: Not affected + spec_rstack_overflow: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS IBPB: conditional RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected

Xeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380 2PXeon Platinum 8380EPYC 9684X 2PEPYC 9684XEPYC 9654EPYC 9654 2PEPYC 9754EPYC 9754 2PEPYC 8534PEPYC 8534PNXeon 6766E 2PXeon 6766EXeon 6780EXeon 6780E 2PLogarithmic Result OverviewPhoronix Test SuiteNAMDStockfishASTC EncoderRocksDBCoremarkJohn The RipperminiBUDEOpenSSLSpeedbBlenderACES DGEMMHelsingPrimesievem-queensOSPRayOSPRay StudioLlamafileMemcached7-Zip CompressionOpenVKLOpenVINOEmbreePyTorchLULESHoneDNNONNX RuntimeTimed Node.js CompilationKvazaarTimed LLVM CompilationLuxCoreRenderPostgreSQLminiFEParallel BZIP2 CompressionIntel Open Image Denoiseuvg266QuantLibTimed Linux Kernel CompilationGraphicsMagickCloverLeafY-CruncherLiquid-DSPsrsRAN ProjectNumpy BenchmarkTensorFlowFFmpegx265ClickHouseBRL-CADXmriglibavif avifencTimed FFmpeg CompilationTimed Godot Game Engine CompilationGNU Octave BenchmarkApache IoTDBSVT-AV1Timed ImageMagick CompilationTimed Gem5 CompilationZstd CompressionWebP Image EncodePyBenchGoogle SynthMarkTimed Mesa CompilationSecureMark

Xeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380 2PXeon Platinum 8380EPYC 9684X 2PEPYC 9684XEPYC 9654EPYC 9654 2PEPYC 9754EPYC 9754 2PEPYC 8534PEPYC 8534PNXeon 6766E 2PXeon 6766EXeon 6780EXeon 6780E 2PLogarithmic Per Watt Result OverviewPhoronix Test SuiteminiFEMemcachedWebP Image EncodeZstd CompressionSVT-AV1PyTorchFFmpegASTC EncodersrsRAN ProjectNumpy Benchmarkx265Google SynthMarkminiBUDESecureMarkCoremarkACES DGEMM7-Zip CompressionKvazaarClickHouseXmrigSpeedbTensorFlowuvg266LuxCoreRenderRocksDBGraphicsMagickLiquid-DSPEmbreeOpenVKLQuantLibOSPRayLULESHJohn The RipperStockfishBRL-CADOpenSSLIntel Open Image DenoiseLlamafileNAMDP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.M

2024 Server CPUsopenvino: Person Vehicle Bike Detection FP16 - CPUopenssl: SHA512openssl: RSA4096llamafile: llava-v1.5-7b-q4 - CPUtensorflow: CPU - 1 - GoogLeNetpennant: sedovbigopenfoam: drivaerFastback, Medium Mesh Size - Execution Timequantlib: Multi-Threadedopenvino: Handwritten English Recognition FP16-INT8 - CPUjohn-the-ripper: WPA PSKopenvino: Machine Translation EN To DE FP16 - CPUminibude: OpenMP - BM2minibude: OpenMP - BM2astcenc: Thoroughrelion: Basic - CPUopenssl: ChaCha20-Poly1305blender: Classroom - CPU-Onlyopenvino: Person Detection FP16 - CPUopenssl: ChaCha20john-the-ripper: Blowfishjohn-the-ripper: bcryptcompress-7zip: Decompression Ratingprimesieve: 1e13blender: Barbershop - CPU-Onlyblender: Pabellon Barcelona - CPU-Onlycoremark: CoreMark Size 666 - Iterations Per Secondopenradioss: Chrysler Neon 1Mopenvino: Face Detection Retail FP16-INT8 - CPUospray-studio: 1 - 4K - 16 - Path Tracer - CPUblender: BMW27 - CPU-Onlyopenvino: Person Re-Identification Retail FP16 - CPUincompact3d: input.i3d 193 Cells Per Directionopenssl: RSA4096ospray-studio: 3 - 4K - 16 - Path Tracer - CPUopenvino: Road Segmentation ADAS FP16-INT8 - CPUmt-dgemm: Sustained Floating-Point Ratehelsing: 14 digitamg: ospray-studio: 1 - 4K - 32 - Path Tracer - CPUblender: Fishy Cat - CPU-Onlym-queens: Time To Solveospray-studio: 3 - 4K - 32 - Path Tracer - CPUminibude: OpenMP - BM1minibude: OpenMP - BM1openvino: Vehicle Detection FP16-INT8 - CPUnpb: LU.Cospray: particle_volume/scivis/real_timeopenssl: AES-128-GCMospray: particle_volume/ao/real_timellamafile: wizardcoder-python-34b-v1.0.Q6_K - CPUospray-studio: 1 - 4K - 1 - Path Tracer - CPUospray-studio: 3 - 4K - 1 - Path Tracer - CPUopenssl: AES-256-GCMprimesieve: 1e12blender: Junkshop - CPU-Onlyopenvino: Road Segmentation ADAS FP16-INT8 - CPUnpb: IS.Dospray: gravity_spheres_volume/dim_512/pathtracer/real_timeopenvino: Vehicle Detection FP16-INT8 - CPUopenvino: Person Vehicle Bike Detection FP16 - CPUpytorch: CPU - 1 - ResNet-50pgbench: 100 - 1000 - Read Only - Average Latencypgbench: 100 - 1000 - Read Onlyspeedb: Read While Writingonnx: T5 Encoder - CPU - Parallelliquid-dsp: 256 - 256 - 57embree: Pathtracer ISPC - Crownmemcached: 1:100openvino: Age Gender Recognition Retail 0013 FP16-INT8 - CPUpytorch: CPU - 256 - ResNet-50graphics-magick: Sharpensrsran: PUSCH Processor Benchmark, Throughput Totalgromacs: MPI CPU - water_GMX50_bareopenvkl: vklBenchmarkCPU ISPCpytorch: CPU - 64 - ResNet-50pytorch: CPU - 512 - ResNet-50onnx: yolov4 - CPU - Parallelnpb: CG.Caskap: tConvolve MT - Griddingembree: Pathtracer ISPC - Asian Dragon Objliquid-dsp: 256 - 256 - 512onnx: super-resolution-10 - CPU - Standardliquid-dsp: 256 - 256 - 32astcenc: Mediumwrf: conus 2.5kmnpb: MG.Connx: GPT-2 - CPU - Parallelpytorch: CPU - 1 - ResNet-152lulesh: embree: Pathtracer ISPC - Asian Dragononnx: ResNet50 v1-12-int8 - CPU - Standardkvazaar: Bosphorus 4K - Slowkvazaar: Bosphorus 4K - Mediumpytorch: CPU - 256 - ResNet-152pytorch: CPU - 512 - ResNet-152pytorch: CPU - 64 - ResNet-152onednn: Deconvolution Batch shapes_3d - CPUopenvino: Noise Suppression Poconet-Like FP16 - CPUuvg266: Bosphorus 4K - Slowonnx: super-resolution-10 - CPU - Parallelonnx: fcn-resnet101-11 - CPU - Parallelaircrack-ng: openvino: Face Detection Retail FP16-INT8 - CPUbuild-nodejs: Time To Compileonnx: T5 Encoder - CPU - Standarduvg266: Bosphorus 4K - Mediumonnx: yolov4 - CPU - Standardbuild-linux-kernel: allmodconfigtensorflow: CPU - 1 - AlexNetopenvino: Face Detection FP16-INT8 - CPUincompact3d: X3D-benchmarking input.i3dhpcg: 144 144 144 - 60build-llvm: Ninjagraphics-magick: Enhancedopenfoam: drivaerFastback, Small Mesh Size - Execution Timeonnx: CaffeNet 12-int8 - CPU - Standardcompress-7zip: Compression Ratingcompress-pbzip2: FreeBSD-13.0-RELEASE-amd64-memstick.img Compressiongpaw: Carbon Nanotubeonnx: GPT-2 - CPU - Standardopenvino: Age Gender Recognition Retail 0013 FP16-INT8 - CPUliquid-dsp: 128 - 256 - 57oidn: RT.ldr_alb_nrm.3840x2160 - CPU-Onlytensorflow: CPU - 512 - AlexNetoidn: RTLightmap.hdr.4096x4096 - CPU-Onlyliquid-dsp: 1 - 256 - 512oidn: RT.hdr_alb_nrm.3840x2160 - CPU-Onlyonnx: bertsquad-12 - CPU - Parallellammps: 20k Atomsluxcorerender: LuxCore Benchmark - CPUtensorflow: CPU - 256 - AlexNetliquid-dsp: 128 - 256 - 512cloverleaf: clover_bm64_shortlammps: Rhodopsin Proteinpgbench: 100 - 1000 - Read Write - Average Latencypgbench: 100 - 1000 - Read Writesrsran: PUSCH Processor Benchmark, Throughput Threadsrsran: PDSCH Processor Benchmark, Throughput Threadopenradioss: INIVOL and Fluid Structure Interaction Drop Containerliquid-dsp: 64 - 256 - 512nwchem: C240 Buckyballkvazaar: Bosphorus 4K - Very Fastgraphics-magick: Swirlliquid-dsp: 128 - 256 - 32cloverleaf: clover_bm16avifenc: 0avifenc: 2svt-av1: Preset 4 - Bosphorus 4Kuvg266: Bosphorus 4K - Very Fastaskap: tConvolve MT - Degriddingtensorflow: CPU - 64 - GoogLeNettensorflow: CPU - 64 - AlexNety-cruncher: 1By-cruncher: 500Mliquid-dsp: 1 - 256 - 57build-linux-kernel: defconfigopenradioss: Cell Phone Drop Testtensorflow: CPU - 512 - GoogLeNetnumpy: ffmpeg: libx265 - Video On Demandffmpeg: libx265 - Platformsvt-av1: Preset 8 - Bosphorus 4Kquantlib: Single-Threadedtensorflow: CPU - 256 - GoogLeNetapache-iotdb: 800 - 100 - 800 - 100clickhouse: 100M Rows Hits Dataset, Second Runapache-iotdb: 800 - 100 - 800 - 100clickhouse: 100M Rows Hits Dataset, Third Runx265: Bosphorus 4Konnx: ArcFace ResNet-100 - CPU - Parallelaskap: tConvolve MPI - Degriddingbrl-cad: VGR Performance Metricopenvino: Person Detection FP16 - CPUaskap: tConvolve MPI - Griddingxmrig: GhostRider - 1Mopenvino: Weld Porosity Detection FP16-INT8 - CPUonnx: ArcFace ResNet-100 - CPU - Standardonnx: ResNet50 v1-12-int8 - CPU - Parallelopenssl: SHA256openvino: Face Detection FP16-INT8 - CPUopenvino: Noise Suppression Poconet-Like FP16 - CPUopenvino: Machine Translation EN To DE FP16 - CPUopenvino: Person Re-Identification Retail FP16 - CPUopenvino: Weld Porosity Detection FP16-INT8 - CPUastcenc: Exhaustivenpb: SP.Connx: CaffeNet 12-int8 - CPU - Parallelastcenc: Very Thoroughspeedb: Rand Readrocksdb: Rand Readtensorflow: CPU - 1 - ResNet-50openvino: Handwritten English Recognition FP16-INT8 - CPUffmpeg: libx265 - Uploadclickhouse: 100M Rows Hits Dataset, First Run / Cold Cachebuild-ffmpeg: Time To Compiletensorflow: CPU - 64 - ResNet-50build-godot: Time To Compileoctave-benchmark: appleseed: Disney Materialliquid-dsp: 64 - 256 - 57compress-zstd: 19 - Decompression Speedtensorflow: CPU - 512 - ResNet-50onnx: Faster R-CNN R-50-FPN-int8 - CPU - Parallelcompress-zstd: 19, Long Mode - Decompression Speedapache-iotdb: 500 - 100 - 800 - 400vvenc: Bosphorus 4K - Fasttensorflow: CPU - 256 - ResNet-50build-imagemagick: Time To Compileavifenc: 10, Losslessapache-iotdb: 500 - 100 - 800 - 400qmcpack: Li2_STO_aeavifenc: 6, Losslessavifenc: 6build-gem5: Time To Compilecompress-zstd: 19, Long Mode - Compression Speedwebp: Quality 100, Lossless, Highest Compressioncompress-zstd: 19 - Compression Speedsvt-av1: Preset 12 - Bosphorus 4Kgraphics-magick: Noise-Gaussianvvenc: Bosphorus 4K - Fasterwebp: Quality 100, Highest Compressionopenfoam: drivaerFastback, Medium Mesh Size - Mesh Timepybench: Total For Average Test Timessynthmark: VoiceMark_100build-mesa: Time To Compilesecuremark: SecureMark-TLSopenfoam: drivaerFastback, Small Mesh Size - Mesh Timeliquid-dsp: 64 - 256 - 32liquid-dsp: 1 - 256 - 32stockfish: Chess Benchmarkonnx: T5 Encoder - CPU - Parallelonnx: T5 Encoder - CPU - Standardonnx: Faster R-CNN R-50-FPN-int8 - CPU - Parallelonnx: Faster R-CNN R-50-FPN-int8 - CPU - Standardonnx: Faster R-CNN R-50-FPN-int8 - CPU - Standardonnx: CaffeNet 12-int8 - CPU - Parallelonnx: CaffeNet 12-int8 - CPU - Standardonnx: ResNet50 v1-12-int8 - CPU - Parallelonnx: ResNet50 v1-12-int8 - CPU - Standardonnx: ArcFace ResNet-100 - CPU - Parallelonnx: ArcFace ResNet-100 - CPU - Standardonnx: GPT-2 - CPU - Parallelonnx: GPT-2 - CPU - Standardonnx: bertsquad-12 - CPU - Parallelonnx: bertsquad-12 - CPU - Standardonnx: bertsquad-12 - CPU - Standardonnx: super-resolution-10 - CPU - Parallelonnx: super-resolution-10 - CPU - Standardonnx: fcn-resnet101-11 - CPU - Parallelonnx: fcn-resnet101-11 - CPU - Standardonnx: fcn-resnet101-11 - CPU - Standardonnx: yolov4 - CPU - Parallelonnx: yolov4 - CPU - Standardsrsran: PDSCH Processor Benchmark, Throughput Totalsvt-av1: Preset 13 - Bosphorus 4Kluxcorerender: Orange Juice - CPUluxcorerender: DLSC - CPUnpb: EP.Dpennant: leblancbignamd: STMV with 1,066,628 Atomsnamd: ATPase with 327,506 Atomsminife: Smallrocksdb: Read While WritingXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380 2PXeon Platinum 8380EPYC 9684X 2PEPYC 9684XEPYC 9654EPYC 9654 2PEPYC 9754EPYC 9754 2PEPYC 8534PEPYC 8534PNXeon 6766E 2PXeon 6766EXeon 6780EXeon 6780E 2P3606.122221992772327431.120.9533.5616.03080420.6467179647.536.20401278477.7786.9672174.19251.2971373.18222503885073068.61100.39316126421173945139455128786251.820261.9787.922194630.600449207.209004.233138025.899.7912.9293413974189.9366491068.4323.54370593.34816050970005802634.8315.2116800682.8482071.1893325.90135125.1521.893276880469369721.93245.85165719777002393527174.57635.9655.992865.7224.644517.8416.5051.460.572174814610695360326.143350083333370.05404481667.950.4354.841572616.98.762173456.0156.4418.141333811.638088.1179.38051020833333227.4233243800000333.990211980.80683448.70191.56219.4123072.30291.9925315.41020.2320.9720.2520.4620.131.0774313.9515.71205.5253.03922147469.3286.43254.003357.35517.8519.8593362.45456.53356.38357.00971231.0738187.01721642.219419852.3263881902.14485747.776222.029115106.3031812666672.711278.451.29168823332.7116.095634.8927.101205.3091856666739.4828.71614.04071227129.7680.2140.437444100002070.350.035023200600000328.4769.93137.7527.06149.42380.14969.627.0473.2676707466739.45031.49461.23455.5749.8449.7970.9083209.6448.4685.16486.0590871770481.6637.8646.849117891.6833892298.5621314.25808.83.5852.8167313.10061806994523167.834209.1062.465943.6615943.174.268971245.26784.3047.088527617961726536617010.531643.4324.97465.5024.056120.93140.2337.53253.49027625392000001032.0148.4532.34331069.1877972066.719143.6714.7244.923294.33109.306.2783.169210.9347.940.5214.6164.25015815.0603.08160.72685765711.37819.22627720531.384585189056666736506000968874793.065002.7969430.916529.408034.00211.273681.172923.192983.1700221.343618.93195.215204.4997662.127649.637620.14534.866044.39649329.036116.3158.5971955.120450.352224688.5162.47413.468.727562.804.9558651.052742.9702135230.178417387862.584284625447754601.110.4413.5011.28438196.49644350187.525.12793253793.64140.8283520.70586.9845203.40744220253297735.9145.7862440297294718358318360355705427.107141.5446.383902076.243612115.8920937.581413813.747.726.391698171916162.9168371843.6145.96595550.83131244026673341119.137.88138813133.6283340.6945483.81261127.0938.2269153302630072738.22353.82894106313695343284702.32521.1565.023960.2842.818821.7315.0435.531.29377814117297027246.3355361266667124.70843245908.400.2937.442654853.615.450271637.0837.5512.754658128.247630.06132.28061616966667212.9246116566667484.54996674.12163333.21144.64015.7743724.062152.7472177.76331.2432.0414.0814.5914.030.73617015.9624.71188.8902.8349853914.9335.72172.990288.47127.6515.5555218.57037.57283.11196.80811660.8515122.31434228.556037696.9805927291.46921041.563180.032189893.3137236666674.481899.642.18168433334.4114.528050.5218.821730.25112646666726.5842.28114.85667315129.7675.5107.367994966671960.967.646173558600000214.8067.37537.3116.69854.88331.76996.475.0082.3646699133329.98128.22576.08456.1848.7748.7665.2243210.1528.9392.23507.5683651785501.6337.0429.148734614.14136969654.8441773.011263.22.5036.2493156.461119106802107423.187356.6337.5815519.9247654.958.3701147311.14566.37713.75185512869585250499984.394744.0524.56485.6319.506115.47118.5728.03648.564182655500000963.6174.9530.0368992.1801696206.480161.0613.2625.074317.36101.6296.1723.044178.2828.160.5115.2156.51618212.5363.07162.02669767712.69718.29327547235.6040972025000000364610001877617694.058813.4657133.289929.753633.60821.763531.435736.390315.6251734.305427.59446.906195.5510168.829960.358916.57055.292874.72530352.73892.347310.8362378.398964.285830108.7154.50218.7011.1214946.762.5298071.109002.2194846877.5123213005725.032388605477031594.416.6121.6716.96910302.0641195648.821.87428116592.20108.1242703.08854.4547290.44822362573801363.6139.6234415091693710583110578133814648.406236.7380.292369998.356940157.5612317.942312523.726.7210.19670661036735.6319931159.6629.14107889.07018147600005079831.9114.25759522106.3952659.8834656.92232012.7730.679988956750654030.84044.08144117097443876836704.25032.0855.074059.7027.101013.7311.1777.520.589169904612168413462.855380683333382.96634752673.790.4963.601673088.710.477200463.0663.3020.879563760.455062.0797.18611178766667259.1863167200000327.782910602.408107321.89248.68227.2138433.973112.6611314.05724.2324.8023.3323.4123.490.9071619.4016.06234.5403.30836153584.2035.19214.431460.77516.6422.9689316.90235.50224.64323.24569735.1361165.04822833.065393908.1874416361.84753743.048270.32981279.7935032000003.321486.121.58187743333.3119.677337.4608.061277.46115293333339.3834.30113.26475396129.5742.9128.747837700001878.338.025293148233333410.5964.47534.7917.87635.10319.76819.896.7013.3917314066734.59127.90462.78520.2253.9953.9279.4373600.5423.5981.73455.7994616807458.2338.9360.409431177.2916904403.2037265.98378.32.3666.5162308.80166573957920284.646757.2626.859515.8626943.424.6303109416.42830.7257.62403151783812975179466.432924.6626.93437.2021.35791.51122.7186.45848.42505124755000001221.8140.5333.37971242.6927097517.392129.0212.5954.456280.26105.985.7842.971187.5079.800.6018.0177.86117115.9663.47148.40248691799.71717.25830989631.7049051927766667402440001097663452.159802.1696629.956629.018534.45951.202981.100423.237803.1839216.553415.03764.016873.6964950.830739.745125.15914.263523.85774302.266109.6709.1188547.895343.535526378.1174.83214.749.388089.144.1827071.437874.6481431830.2892689310934.174652076070761499.67.4912.699.964526137.03802380867.522.967970931128.78191.8184795.46297.9383155.74144409914427033.6143.4168428438276020549920677857341025.021125.8741.854966250.77798386.9324676.861212412.766.955.391259672057021.6143582237.6958.25334048.09136096463332424917.297.40233391199.7344993.3438719.37455312.0953.9348176931314601354.11953.0575989814975299393772.18718.3157.137437.8148.757614.6711.6945.691.14988188117585737354.7546284300000153.16223780240.560.4641.452845493.418.540322240.7740.8314.198098764.936038.92173.22082027000000251.3056077300000550.01685601.101220893.78195.45317.5770826.734199.6089171.23140.9241.5816.0016.1716.250.62425013.1527.11214.8123.0508564181.2935.18145.413356.76430.3716.9672189.73930.76234.24171.37577869.2976106.81537423.558932754.8056742391.43236238.049236.648128566.8144505250005.092039.632.40182005335.0315.434156.4008.881681.44149383333331.9055.49630.20333110129.5755.5100.008837012501809.765.386893520766667378.0560.52633.6507.36053.66291.37858.845.1102.6597049900025.87226.88577.76519.8953.2953.2270.4263586.3501.3982.73443.5892771639438.6039.3131.458959139.25186677736.2372004.016324.72.4838.4240153.922131976050120545.219360.8928.1718375.6348122.168.9091228184.68605.58914.63345861478715783928003.855570.6326.80423.3017.38994.66103.3766.85643.69539926200666671165.8169.7531.71091189.7892318506.960150.3311.4934.579286.7897.9115.6132.805157.3639.670.5917.8165.49519413.2563.46139.61713692799.49116.18330843429.3251252154633333389506002226103782.817392.8026331.532428.848134.66281.649191.324546.496935.8395431.790726.08665.109484.2953164.789144.599622.42514.654313.98013327.875100.7389.9268470.437758.939430547.6162.97919.9112.7416004.072.1594592.254225.8526742114.6124255193802.611619926127722861.07.6736.1321.02112440.83113143755.323.12286552415.9670.2131755.33337.0051412.37116132105821386.6741.93226597354153678936787520773867.324320.11106.961614763.703237228.749087.123705531.667.1313.9692376697707.242837860.6419.768930123.83215884966676897342.7821.0308074263.6201590.5012935.47126171.5216.086964120084817016.05021.47198823575074567280876.16042.8555.743050.1619.910216.3312.5450.990.55917926368795408337.004284893333358.42304384040.520.3352.971142170.77.545124351.5551.0516.174235116.553375.3264.9597838530000217.8802381800000247.297913273.69485910.95191.11119.9923848.54075.4690330.10417.5218.1319.2019.4719.011.2640711.3713.36195.7052.62544117588.9925.27270.380219.53215.1718.2179428.38748.28236.52407.58940625.2423212.48216045.947435728.4693147162.63207754.376176.333135075.0726700333332.271047.961.08169063332.2616.325128.2786.30986.0480018666741.4327.62914.29269969129.7702.6160.566323966672530.540.233942351900000351.2976.91541.1256.49039.56333.73841.688.3003.7816713033343.42133.75383.57461.6147.3447.3262.7503225.7375.7390.02465.0685744542470.0229.0540.728918522713937285.9521766.55446.82.5047.2703319.04344439185187202.594208.4928.736717.6519183.833.120458815.36687.6715.134221145704820534615411.292074.3023.33446.4026.458104.23149.3787.62258.37911621387666671126.4117.5328.51641131.1824556646.324119.7316.0754.916314.44121.196.8363.730220.5697.760.5514.4146.09715014.1013.10153.12467763711.10120.17527764731.781874164026666736537667680190882.970944.5758135.066533.334129.99731.452801.378313.133663.0289724.553521.21795.227815.6770061.254747.241721.17025.109144.58912380.902139.0967.2418761.825654.959921286.6144.69811.867.465366.695.9309571.452235.9713020091.174396637127.283230422299345531.07.7718.2413.21125201.10956288129.124.00562875795.63127.8453196.12372.3297214.41632039672044744.7142.1644990849492713456213386640170733.921169.4455.262993136.601832125.1517252.271664516.557.327.293491171395446.4197011691.7939.34573265.02631562616673892623.1710.84045211108.3972709.9305576.86246822.5229.3496127758338275729.50181.771049123710118989933233.12124.9956.713816.7035.932417.1913.3446.491.02797603513859254246.6804825133333107.62993373323.920.2841.681993787.013.392177642.3541.6513.086965396.223347.93104.84251444066667205.8854670966667441.65187157.961172614.10135.97617.9152102.668125.7494174.67726.0026.6916.3016.6815.840.94507517.1519.75173.9092.1746383665.7585.55175.625199.07922.2514.4831246.93637.76256.63189.68611654.4054134.41926928.993119604.7554917291.98293242.873141.954174862.5635964000003.491604.111.72169046673.5113.736646.7056.811479.53109146000032.2547.51216.96358952129.7651.9114.29732560000178551.915093254033333263.3369.64738.6535.99144.75341.51932.596.3343.1106706400032.14327.51467.91435.2145.2945.9554.8233207.0447.5094.84499.1880770465501.0727.2632.814136900.53658790568.8142939.210975.82.5340.5671166.48588635753413373.505565.2329.9813102.2837710.606.2126135939.25492.88510.20514199435704055331735.113998.0222.34491.8920.788111.71123.88212.61751.24589824940500001040.2145.2924.72741041.8775012486.023141.9514.4025.317328.41102.127.1213.776184.2987.620.5413.8122.08915011.8973.09134.78213763710.91618.47427758932.4819931963233333364976671379772034.052705.0226740.453436.228327.60742.026591.652706.005255.7449130.473324.65107.348487.0411172.801860.112016.63945.749214.85818460.673121.6708.3996276.422769.450130236.0122.61716.9110.1710970.452.8810991.886797.3006519876.596244174093.731889398078325441.58.1331.4719.88246410.29005162727.424.94334076467.0878.1051952.60642.9834384.38418779617444076.8759.69263740690067791527914424334758.159290.5697.801855135.326098212.999686.393379028.497.7612.7997582813667.639238894.8722.539990107.23715979933336254038.4818.1027336670.8431771.0652877.32131606.8618.485174771070266018.55331.54179221235920141154535.33239.1762.533076.6622.362519.4413.5948.590.62216074249988176346.213322253333365.33184315467.170.3751.561302514.08.282135651.3551.8616.389835234.063406.9671.8253944550000213.9852769066667284.333612410.2986407.46188.93018.0725831.83883.4921296.79918.2418.8419.5819.2919.241.1964312.7213.89190.0632.61721134048.9645.77252.648215.12715.6816.9166384.06343.67257.50351.64416530.5872197.84418141.746192705.6063423632.28776648.487168.859140144.0129724000002.391108.951.14168853332.3815.739432.1576.821058.9988220000042.2230.84313.84572225129.7705.5146.036890033332245.241.344322739633333357.5773.06039.8766.57240.82335.58852.367.9593.7046712766740.50131.92398.40464.7248.1448.3565.3593229.1386.0089.53474.6886354518476.9131.4042.271120561.4767812301.3023250.26122.32.6742.2747301.13651840436763217.114386.4838.507207.7420910.533.627669776.41678.4835.97022440706742344699399.992243.8423.77461.6224.840103.56143.8087.74856.40169823089666671127.5125.1428.47981133.3834756456.501123.6915.3764.867309.03117.816.6053.550215.4967.720.5514.5151.71815814.3623.10150.66848762712.01319.65027726031.998248167970000036539000735922302.887344.6475735.111033.987729.42501.472491.416623.320303.3703423.656523.66255.290275.9196163.535349.974020.01035.260754.67269382.109155.7886.5496561.010759.179515081.0149.99612.508.006445.095.1141611.502145.9250118621.273665007689.323756452205348534.87.2614.6712.10690186.32539316359.225.72657889889.18133.9903349.75683.3395201.38237273521529740.3864.9152291240334715665815595946913130.196156.7051.293279262.530349117.9118561.911535715.297.976.663875101627941.4181111801.8944.66830258.24832051610003617921.459.28541971114.9022872.5625525.56257384.5533.1275148466962705033.11251.54961114311811489573532.69123.4562.113819.8339.338920.2414.4235.461.09892072515354400252.6715036000000116.60533392842.380.3037.912274386.614.127185238.3037.8412.597466492.444382.97112.72311518933333199.8965367033333483.10496840.057171436.47136.68914.8653269.469129.7482161.88628.9629.6214.9214.7414.960.86435818.7222.14169.8502.1048065663.8236.02171.174185.4624.6514.4583231.03333.21278.52187.22400462.6357128.06630127.577291581.7695255141.71129643.911132.712176900.3238965000003.661677.621.74168840003.6513.519051.8167.411528.41120606666732.4452.24416.65560046129.7663.8110.567571766671873.152.235583337066667269.2068.43738.1366.05246.25308.95940.406.2662.9616626600030.53027.63477.33439.8446.7946.5955.9793222.8449.9195.39467.9680139566471.7927.9029.195540368.64075342569.6045195.112115.02.7933.9621153.407103382860113401.455933.6541.5714033.9440032.817.2075141954.15478.46711.88754979074904737559464.374351.5923.30460.6620.008107.30122.70412.57849.13617524913400001039.2138.3924.68181046.0780577286.077135.2814.0945.311325.97106.277.0383.738181.6297.460.5413.3127.54616411.9673.09159.31171763712.08518.13827729828.8401572090466667365213331494090823.958195.3912340.517836.003927.77722.087801.718756.517446.1779634.250729.44487.308227.5325973.968455.901917.98735.886285.00222475.254121.7808.2601679.377069.201411866.7124.26316.6410.4412793.012.5273631.767782.5631921583.2112233292030.972207953990036371.612.2929.1815.24719362.5935182366.960.90491583281.3697.0752426.88130.0309368.21929350212241362.54113.7042545119006311322311321936653440.444235.3176.101839444.396311185.0313467.283044223.6724.3911.24980161099481.5348661186.2424.97410482.9597231535335524730.7512.3906418885.2892132.2354390.81185954.5417.622280722926530017.82693.10155318337124854114473.36633.2016.843345.4522.50814.549.8242.640.525193000611795318249.484303710000082.91954814941.530.4536.971443288.48.964152737.7537.4514.216938906.135279.0784.80101061033333192.8103572233333216.967814030.513110742.15153.53816.6821389.82399.2430222.52219.7120.3314.8814.7615.110.86706526.3313.79178.6152.89253159709.7475.93303.421292.51716.1916.4123356.98737.26207.84292.03031430.1110194.38221540.286404701.7243917192.18145548.453194.149151627.4226890333333.101470.461.48135990003.0814.946035.7016.431340.3498109000035.2933.54413.69373042112.3490.3135.56646513333217044.114033044700000295.3088.06547.5055.43740.699893.32347.72904.367.7443.7245393033339.41031.17411.05394.7143.8043.5559.0972558.6402.78102.67295.4375178480295.0630.8038.502512800.42300947175.7214497.35230.98.2745.5414192.9935453070057696.082963.8270.953263.039657.082.647190420.25641.0014.29352591364662512341039.131313.3921.73285.1725.939108.32151.5379.69458.3767321999266667900.5127.9725.9606912.9746530075.877125.9116.3345.919349.42131.377.3883.528219.6697.830.4914.3140.75615313.0232.81162.32335971548.36221.43723107636.8621161731166667319920001045972004.006753.4312538.517929.764533.60271.558211.428495.180704.4931725.981321.95646.507475.1648066.913654.283218.42225.597635.29844345.938110.9709.0336770.340960.928218943.6138.72214.318.988880.824.7025571.612326.7266331046.598366891100.181098094009318389.319.1153.3825.78945798.3498691036.562.64248066156.1349.2031230.08015.5038705.584146156212950124.63236.81212294883830569395693918834581.355456.81150.391218453.342873343.165913.045445646.3223.2523.9708284587354.863035642.4413.494557165.785107362766710346159.1524.17512173447.2601181.4942120.3398557.169.700223995268154279.777644.41305236163560620408836.67361.2231.052266.3211.86389.2618.0861.320.58117207627147120282.252161046666743.67334826284.800.5648.89791770.04.81386948.9948.9917.674722655.325172.9647.6437542606667197.8521823566667126.440718998.81657317.66180.22522.2717348.42955.4208335.15215.0915.5117.7017.5517.731.4221325.9110.93176.2922.75242101665.4696.56423.626298.67312.5620.2495612.78242.05415.89558.38486820.4129298.40912374.956584849.5592437323.39318976.175207.93461956.9315546666671.81883.000.86136083331.8116.686321.3794.29852.1453922666760.8921.16216.34161233112.3484.8204.215032533333576.431.252781797400000512.36100.46152.2275.43830.177425.22282.50690.0910.7124.8745408966755.73843.45290.16400.6444.1344.0155.2382534.5290.27100.29339.6776729495342.9929.7644.27488429.1343088584.309623.772593.28.5851.0172315.0302785850449047.991525.57127.891698.054502.741.331937567.61767.4762.159613035914512558495317.82637.7621.96326.6534.28990.72187.8759.10479.83239814691666671032.491.7528.08861018.3788231125.58391.6518.8445.906326.53163.758.2014.093275.7147.520.5013.7134.07212113.1002.82182.23572973555.59723.65823135739.117914156176666731995000510995453.542423.3496635.604928.018135.68751.301731.175613.173602.9830622.585419.60355.543794.8041859.935348.470020.87235.671755.05427363.351160.5276.2474056.580249.386213537.7133.1888.825.634479.2811.852131.110563.6047922957.355398709752.899145597120098237.014.2912.833.08110893.568115644091.033.1812940001110.49309.2197730.471116.122693.16876765271954718.6743.771086618191950374589376268111646512.13067.5223.848448083.72998049.5535809.5989167.753.783.753199013214376.3105144013.9678.49615830.69444672813331785510.164.13320893236.6105915.25311735.42551955.5555.2576199035205996755.33825.2456166017140617610871.19911.4711.9512296.2760.37484.084.9119.840.289348090933307574276.2078012700000214.01788683410.790.3516.972976999.722.525390617.2816.826.3182888487.9114185.1210.43672394333333119.55857935266667508.09264431.344244738.81110.1688.3554678.485231.4272141.83062.8263.487.027.077.081.00191422.2043.3987.25790.8576855.34114.912263.52445.267.24869181.99519.92233.63167.12816444.950289.27540822.707989446.8057413661.10944624.134161.947178488.0347593666673.471897.641.64130831333.458.7597162.00010.611560.56139473333322.8353.77118.15955272112.2664.779.428493400001429.974.035834407900000223.5463.40435.3168.51355.0516906.2248.03738.318.9924.5105541566725.87222.52464.78540.9655.0155.1187.8243125.4391.4061.46528.21124947288526.3631.9515.051612348061939211095.79121976.931157.89.2523.4960100.4600276267766403205.038231.7243.1712665.6220550.9311.9107390520.93310.59119.4052105954653310312091513.925766.6227.43513.9217.83986.0896.1616.95527728000001392.5137.5024.05401321.4106778379120.1111.7204.943246.0891.9665.9502.890161.9368.420.5616.8163.7951793.62135.5163818783.20016.40130174026.8236272279300000360400003991242233.617923.8079241.569622.788644.06353.217812.246459.952457.0968266.435542.88799.066076.17190114.15890.062111.270711.45808.399691165.93182.2685.49711158.265137.98925977.4161.33933.0822.5822166.602.0768356.3834320.7525959466.6198516645608.074586513191348996.825.3834.205.460660178.25382319827.232.00671322576.98187.6844692.10673.3796176.42238392565207735.66110.9154490408477319257419289871606523.265123.9044.874152864.87538077.3217230.351660314.296.936.881212791613828.7195352212.4145.24579456.91223761490003864518.366.95044349151.9483798.6956017.19362511.4332.523299600710926732.51888.48103712258597205999631.98418.6521.636346.1534.64477.858.4841.170.251398935819595777446.3035811900000130.78748634258.390.4534.902015656.915.222239634.7134.699.8000862071.1014955.6133.47691570400000122.9485862466667500.76737885.16134994.14161.49715.8627287.261155.1208243.34040.0040.5014.0813.9513.891.1192313.5229.18108.8681.25179206619.2925.41147.837279.64132.749.73685290.34126.23471.98309.84765327.5824124.45530028.325594672.9165791121.36906330.001162.092138605.5247553333332.661392.911.28133873332.6412.280746.89112.431301.26136873333342.1739.99812.58079492112.2680.794.768505866671450.578.155464353533333245.8261.62934.0448.59562.7014143.1330.26868.547.4714.3125545533332.88920.45425.25542.1555.5655.3886.2983114.2406.5852.93597.73144760448595.1932.1229.849364260.23122574433.0674389.015786.69.4241.4745178.698138409588983101.516963.3183.116846.799997.896.3027225311.82590.70710.32245376330345233100918.962986.3327.61566.3119.991104.52103.3526.85740.91896128620000001385.3121.9628.72501324.91261610287.547123.3712.1994.770209.6897.0045.7572.723176.8768.450.5717.2165.75316517.0163.61118.54229818783.42216.66830083325.9316462287466667360660002145246592.239223.5754334.812621.578446.87641.693071.485965.594914.1091433.499424.10976.184786.1666881.431971.556413.97459.185248.13326801.961178.0325.66508102.035102.73429384.9162.47524.6916.2111424.053.3604533.410859.3353453167.8141584195024.323962757549735964.925.7532.805.916458325.42331294183.234.92643475525.88171.7714294.28365.3025238.88135096099835740.26157.4550331102112316654116654164262624.237139.2548.883926265.277120176.1416038.901889615.967.238.253835111436324.9223051743.4939.08626262.17322828020004329020.157.73850019136.9453423.6345528.15269047.2828.068989728843612328.09568.35118013917676965536672.05821.0227.465229.4130.60738.589.4740.450.278360326118024993374.7455266466667110.52538220895.450.4834.901735239.612.514207735.0134.659.7851653182.7712394.6113.27831362166667122.6835271933333449.114110176.864116725.04156.61015.5726082.711132.4918225.30838.9039.5813.9514.0513.841.1548716.3228.01109.9981.25135186675.4325.85164.021187.01231.449.86018311.82532.56510.10466.54801428.3185135.66626432.591783604.0455495001.42295434.866126.816133779.6242563000002.731363.331.31133946672.7312.254942.50711.341278.58115816666746.5036.15112.50279987112.2684.7100.248113733331575.576.835114032733333334.3061.99234.1488.42262.0214217.1354.59942.196.7433.8505542533334.56722.53470.95529.8055.5955.6187.9933105.9447.6153.77562.50142102254559.5531.7229.269042172.43161216306.2746233.714207.710.0939.2586190.38212647513769093.995697.5191.166554.129356.715.6301125191.11586.1789.18444285570544092729499.012739.0127.66536.8220.494114.63111.6887.52843.45405128598333331388.9140.0129.83811328.51255620607.431138.1113.4714.792211.85108.025.7992.756185.3008.380.5717.2178.51616016.7303.62136.39912818783.77816.96329834128.0310222282766667360683331977083502.667115.3465633.520923.919842.06921.705791.660465.253214.4613534.163625.47896.377807.8858481.604172.123213.86479.089558.15092800.231182.0175.55018102.191101.468627695.2172.87521.3214.2910652.033.7548352.878778.1827550909.6146085449203.197882225738371942.014.4712.423.408337124.29946593246.936.901253333990.16291.2787281.958105.4052145.64769892582222321.1263.981001502634860316492320527103327712.63179.0526.357975907.45064977.6431974.88104288.613.984.260785962861959.8124273353.7368.86850533.67543249303332075011.254.60927943217.8465446.16110708.91472931.0447.5267178500687906747.61435.2466178015265054658131.24212.8714.3010139.6952.67414.465.2019.340.293342273130324596271.6207411866667176.20618498306.780.3517.412626835.720.234333517.0716.246.3489184477.7212708.5175.5971212953333395.83727513333333491.53446918.021194942.32109.4648.2748760.815185.7110133.48561.0761.117.147.207.041.00947323.1240.9686.92300.9170435.98118.902167.10742.036.41229197.63019.88253.63248.86731542.515894.81036825.005632444.8477617341.12632925.844102.572172688.5042809333333.491862.791.67133906673.488.8093057.09910.561524.74119996666730.0550.12118.05955505112.2673.485.898245833331558.472.685534063333333266.1062.88735.4028.34953.4411941.3227.22727.778.1964.3295495466727.67823.53525.84529.0352.8152.7986.3413098.5401.8461.07529.80125595607525.2328.8115.008281025.86162228750.1186757.726702.710.1723.5786100.3586251645629887188.747810.6548.4312024.1818666.1610.6018256584.67315.35517.00988576871798151451103.665178.2926.41504.8418.08982.94102.5837.64527302333331382.1161.9025.62651324.6108821580133.8712.7494.829240.43102.985.8462.810164.8998.300.5717.0171.2181783.62140.48261822782.32216.40929961027.7377122282066667360330003707515303.680015.9843639.017625.317139.80353.170642.250209.962457.5555866.628542.51379.124529.74614113.51793.834010.661511.502410.43441094.256220.3514.53817157.505155.96022931.8167.22329.6117.8919414.942.3129775.2783917.8110543531.0201082895594.815274663411353966.920.6421.005.147658449.46597374413.538.85803187621.42232.7495818.73686.0139360.20745703974887031.65230.2465639632938722018822018878087121.762114.7639.834525288.003014231.9619917.541528612.868.038.872259141872096.1181291671.2344.97082648.84922753526673738316.586.35042945229.9135747.8235778.51279397.4535.1464116722114187035.24617.4795411309975390078731.92117.7038.215702.1337.738110.9711.3531.620.292342249222829426319.4526401366667126.14567736018.740.7327.782075973.813.242250827.6827.538.6359443799.7812731.8133.92971744700000106.1306588200000527.799711895.407125567.07137.19313.0524218.831156.3909160.90438.4739.0811.0110.9110.880.94362122.6729.0094.73653.13156177989.8916.25186.103131.00432.448.29533337.68535.08551.07534.05942823.6266146.76130433.814223382.1035754401.35573733.12089.7350132973.4347145000003.161620.531.50111745003.129.6529647.98612.411454.71136980000048.3640.38613.84372244112.1596.2106.54709650000170068.565353791566667400.5273.27140.3517.28354.469839.64314.67924.806.9283.9684627000038.52623.69450.61425.4647.3347.3178.7392596.1462.7958.11450.12131781309458.9628.1624.609528476.63484477283.1828854.39320.510.9230.8572153.246161269162280115.785310.07102.847862.6511508.197.5573127519.37452.32312.31875899510705732354526.193280.2523.36433.7923.217106.14128.2798.80145.07808724449333331139.9135.1727.44711102.21166853266.465125.7616.3885.662227.40110.806.8533.251212.5466.680.4813.8169.23015114.7853.04167.40625974655.79519.90625069530.3813721898766667299073331897637993.129047.6333736.446026.445837.95852.210202.616536.523676.2279140.633032.47447.2808711.1392103.59787.655211.418210.55379.42177319.348166.7936.01164115.790120.55625194.6163.41323.7616.7912575.303.6543032.888697.9975650139.91577618610182.16104776633047107830.610.948.102.940456137.11385759922.139.8615510001127.05288.5377213.433121.3017201.26590602860899016.8285.861306928507573415412412723134022611.55765.5821.668171241.70851293.9938546.6684137.174.374.510618933729470.8100154032.6684.68859426.7762783039083169609.713.98120071214.6175365.42112750.59588329.3256.4485231661194528356.69364.6353163019831030267001.35911.2115.849771.4163.845956.2714.900.329304462036593204250.6346316266667190.08397645325.700.4113.113108396.721.305401213.6813.765.5576763265.0111208.7200.1612173480000098.63746439000000462.23827365.863245447.7299.21826.6446126.080208.3131117.61754.8854.575.715.755.790.82965328.1037.1378.06762.517096.6147.735127.53738.126.74977210.19718.59275.53253.31855341.8727101.56140324.570122316.1137769681.06839827.14586.6864166151.4246265666673.571876.661.71112736673.597.9840258.8399.651403.46134980000027.7451.62916.88459228112.1576.890.857093933331712.659.015673794133333349.6774.68941.9167.15346.0013455.0176.00658.977.9154.1004622966730.68027.86588.43422.7647.1447.1377.5962590.8397.4466.54420.35115317834427.9528.1111.938252639.55861750750.9654066.017873.111.2018.013388.3741320258686237231.836513.3656.7314601.5222499.0314.1038214017.18270.63122.0023116994738511352065642.476400.9423.28411.2621.22467.08126.1128.84823747666671139.0174.9326.32571104.2103630483131.3815.8105.740253.13111.156.9863.341192.9776.640.4813.7168.7791643.03192.41705972655.04619.55825107529.4744841894966667298933333012022323.987357.8406538.000027.897535.87123.696023.1644111.31488.5180883.766055.915810.066611.5774125.24493.636010.7518812.809310.23106397.429203.5714.91420179.989148.20829877.1159.74632.2622.0022017.752.0843845.8360618.9745442113.5229001522830.122437846082025894.621.0036.6611.36964691.64224172566.841.38386212317.38107.7152692.87341.0225468.68821118566172767.67161.4830706893837710219810222236798945.953240.1385.122274636.131544297.259256.113881127.128.5920.9379139881480.845377998.0921.817577105.67611500526677205134.3513.25084261107.3532683.8312943.08133284.4617.944853978493137317.96685.16204324214623097505303.80135.8231.992746.2018.470510.7811.2241.110.384260650012053901255.671311693333362.18666198256.720.5333.681123193.06.499126633.4933.768.7581422229.945826.4464.3253821013333106.5263062200000294.620916146.99763930.64128.98215.2516949.59175.2149219.05823.7124.3113.2613.2813.191.4983517.3017.0497.05082.57278153818.0316.77277.525127.08519.258.87446406.41434.51592.22567.28694722.1972205.01417258.169235443.0583313572.20049763.79689.208187511.1129828000001.80875.230.86112900001.799.800927.5327.38843.6380991666757.3824.24616.32161272112.1557.9176.876338600002024.754.603793047066667495.2575.86441.6576.93950.047382.43276.93673.4210.2055.0774621066744.27633.23313.50421.9946.8846.8768.1882593.3308.4665.66337.32116879799338.8428.1327.312816704.4851997197.9116573.24660.011.7830.3743207.3367458472100753.893636.33100.673692.675366.793.514652745.64547.5245.742027409177826618653710.791542.6123.25323.5927.53687.31154.0108.92956.41751821868333331118.8101.1727.93621101.41054328626.11898.7017.9175.735251.47137.237.1823.484242.9316.760.4813.9165.08912313.9683.03163.69864976655.23921.03525002433.673162187133333329899667991981443.910067.8732535.794327.928136.07721.824432.257164.825064.5702936.611932.92017.7452111.2047102.050380.723212.388410.30269.38681388.743216.7034.66491114.174112.72819375.9160.78513.819.396416.346.5417681.519015.7067224526.093336452506.102219447097321047.520.6536.4812.15132690.73503153920.845.71339998293.0797.9782449.45437.9597496.24119330509364375.26156.59282053327077934739347233835554.389263.7694.412069432.528093300.698279.634251330.079.4621.1780307810291.848844918.5320.997732120.56011471080007809338.0414.4939164398.2072455.1632763.48130839.1216.450548896539085716.45045.11224026494158939632074.54538.8634.762718.9416.920011.4812.6740.970.414241637511882103254.727279370000058.27765820618.180.633.301052818.56.246117733.2333.188.4728321684.805821.4663.3433741740000102.9662789600000273.670316609.78162449.55129.64615.1116855.89173.9073211.18722.4623.0213.1813.2813.151.7974918.4915.7796.16792.25453141831.7767.60288.118127.20817.808.75233438.16834.35654.83568.25404922.1341215.92516359.266377446.6893190942.32119566.70588.568878334.9226870666671.69796.820.80112363331.698.8714425.3346.93771.4773175666757.5421.93518.05355395112.1563.6187.035772633332224.651.513632767933333498.2278.24142.6056.72744.927421.23256.79617.0310.4275.1654548633346.35235.95295.29418.8946.9346.8664.7872593.0287.4264.93337.44117884977335.4627.7426.247515903.4771352204.0516399.74564.313.1131.0644203.0556780673038748.733405.94109.003355.734830.013.199352684.93553.4715.240624294011023499263610.701396.7823.27322.6928.42080.86159.6248.94861.36246320263333331144.895.6327.87031096.51051385516.00092.8218.1755.734251.05151.277.3013.623251.6066.740.4813.8157.36212013.6143.03188.37105974656.25021.53025016236.823441177686666729899333906581563.924557.8601535.883126.829037.53021.805732.238684.926534.7422138.102732.22947.7051111.2864112.76086.651511.544710.39779.71131443.961226.6264.46533118.023114.31119485.8153.41713.008.485745.046.8527121.461635.4497124548.889341762743.397859939523022587.42.835.88456271.0180.29367657243.7678.2351955.88171.024724000513515327.41293.0235282682165336330036313376731329.385106.4835.116575205.53864614551.123822810.5618.751479879.0439061731.5031.47855758.9576244916.526.0457158376.6021915.0414376.0932.7979109608219971332.96632.56149718329794193887972.60518.7041.5021.222716.2826.1216.450.81512296492763078192.50836800900000121.43201783869.961.2014.673363067.0202014.8414.814.58960125.1146130673333359.49836821533333338.146858.57676.4742946.258138.849980.419929.1529.156.116.336.152.49734340.2620.4660.28801.6467419.23187.654178.113122.037.49940192.09816.24719.83138.566350276.2355918351.857642136.39175761.5037121333332.97979.891.5162807672.986.667186.41857.2070705333328.9928.8073471649.8293.134974666736.404743607900000226.60143.79779.2003.71027.33168.10464.807.9673.6293343933335.546354.81258.4926.8926.9042.8571760.8301.46107.28320.1771664005320.8722.073.497852239294245.2710431.628.245.5824127.472725633034977799.72843.92294.693787.9410020.917.129181.257211.3573115849654611157207421.761593.8813.90311.6325.71161.48160.46212.2451852366667721.4113.4217.6172701.267599793103.2220.5888.094380.339.9604.829252.9685.600.3510.6108.4951182.231119494.37925.87919729817805333333170566723544549910.80666.1432756.773447.197721.198212.30213.6192036.400912.4345285.988179.14417.05537.32610149.994155.9006.6047116.582816.8062608.094194.1075.15166217.929133.35631677.2108.29316.887.710.707572.5540039580.9244661431414.864060513792311348.58.5612.40233836.3172.72188925138.5339.348983.70740.692412059178725752.47283.8317724906218319020919005842106357.713191.2065.672915609.7473687721.005208319.8517.81743282.757657924.9015.941604115.4628857929.5511.47910144439.171979.2792366.8319.425156572076778319.51595.39231827315063013746234.80629.0638.8712.173715.1125.3332.450.572174865817548934237.803425943333373.95582299150.511.3626.822531953.1126726.8926.917.1358776.529284837666759.29894301166667284.4616131.53613.3926024.60284.7057130.06218.8619.3411.8811.7411.952.2971282.1213.7769.06831.77809114715.78918.20246.848207.94215.6512.7015274.85529.56692.79184.202270445.6234138512.504621139.45484584.1337363000001.93677.400.9862843001.938.572867.90609.6771962666738.0112.6287919149.8299.435957666741.865043671966667314.88140.85976.4743.97240.73214.14443.7411.1985.1773344466741.095278.05261.1927.1727.1746.4831765.6260.8390.31381.0585117897379.9220.226.245211508453126.645315.727.019.3729455.862212997599473351.851747.50259.662006.005278.463.6505176.6435.86325969554945747495524.67832.2914.01365.6227.85071.41165.40910.99658.3067151906266667743.591.9623.3078739.1819004774.05287.1720.9087.507312.329.1884.243267.9515.650.3510.6115.34514510.3912.231117494.04625.8851967401841400000317260001227942464.203554.8072542.901641.083324.33945.664262.2432317.90007.68977160.128106.6887.595897.16440116.644124.0648.0601314.476116.8631562.398188.3005.31050140.14478.730227281.9114.54215.909.400.523573.7681140441.0113403891525.264508875564012610.89.6013.14262432.6153.76209803149.6343.7281093.20645.210013403303909048.07266.9119692068327021144921131146376852.074174.4960.113340274.0343098536.394687517.6116.36826049.5525011018.1817.853682103.8638100326.5210.3019217543.5531088.8332553.5521.514763845320376321.62225.58209024725689375783134.32426.4935.3013.401814.0123.4935.850.542184608017945745246.037471470000081.83402339570.281.2530.862812118.6139130.6930.877.6958383.732194027000066.19714799133333314.6232140.02614.5326864.11092.8784143.35520.8721.3913.6413.6113.002.0491075.2215.2475.86501.94144116716.40116.41228.571217.44517.2913.8295251.19531.99618.97169.447299482.2094380482.279971148.10791273.0241367666672.11732.791.0769839332.119.503538.47668.3379634000038.0111.5378667752.5333.239856666746.185664102200000313.50126.96669.3434.35044.44232.51482.0610.3864.7703719566737.640298.16284.3329.9529.9450.8221960.7281.6284.59403.9690973414400.5221.306.813301640921134.775753.924.2510.342564.158414416302728058.061906.99240.382179.995866.634.0574190.7826.51666731592176453094835.02934.9715.47388.2925.23576.37152.22910.24352.3213812099033333816.797.6726.0268797.7871903974.44092.4219.2036.849296.368.3593.872238.4326.190.3911.5126.58515511.1812.491007540.24023.4052200512057300000352590001251940664.062724.5970338.419736.783427.18445.240512.0728815.58566.97509146.77996.68707.135356.74630105.223111.8748.9383313.178915.1057515.079174.1405.74234129.94072.312029804.4124.59715.8310.090.567173.7634840626.4118648152957.698919441685725098.02.996.72519392.2157.28407256264.6686.8842172.10379.285226658385788724.61274.5239191122548040473940227584633526.46297.1831.287302247.13820616394.06350819.7116.731644363.7392831933.0835.19669253.0155608215.165.5126648784.3472108.6754992.7836.2464126688286665336.50432.671342163111253730411732.33716.8937.1723.116314.3024.2417.910.77512921222765777694.42477597566667133.41501821144.001.0916.223813414.2222816.1015.974.56278136.2218143710000066.17727546366667363.384460.38837.1044136.525151.248187.086731.8531.706.616.656.592.24526293.3621.6365.43201.7036516.98173.087210.36522.598.14615174.27218.34630.23125.274389292.7916112001.718022103.894776895.2940686666673.311064.181.6869699673.317.139176.741010.9377794000028.9226.2883804352.6323.738440666738.925174021033333236.81129.91071.9684.04028.43190.80520.017.4683.4113712133332.655378.79283.5228.3928.3947.2531954.2335.38101.49339.5075740139337.7519.553.760032449334261.6411147.224.775.9528328.3969287035041140113.68978.46271.144259.9911390.047.906082.442112.6220132416334012729075611.991826.8214.87333.0623.32368.52148.99311.6192036733333774.4124.6018.4295753.268320800115.1218.8517.603377.589.3514.486233.2056.100.3811.6117.6811262.471005538.90823.45621753619893000003519066726691982510.58834.7485954.254343.806822.828912.12683.4153735.226611.4820266.104167.97416.541810.58571140.07141.5747.3128515.278415.1274587.000182.3615.48343219.173122.75133010.5116.61817.457.990.576942.3977037461.127059786OpenBenchmarking.org

OpenVINO

This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Person Vehicle Bike Detection FP16 - Device: CPUEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P2K4K6K8K10KSE +/- 2.97, N = 3SE +/- 3.87, N = 3SE +/- 25.68, N = 3SE +/- 6.56, N = 3SE +/- 18.02, N = 3SE +/- 10.88, N = 3SE +/- 54.09, N = 3SE +/- 4.91, N = 3SE +/- 2.55, N = 3SE +/- 5.02, N = 3SE +/- 2.87, N = 3SE +/- 3.86, N = 3SE +/- 7.17, N = 3SE +/- 4.05, N = 3SE +/- 9.37, N = 3SE +/- 3.66, N = 3SE +/- 0.24, N = 3SE +/- 1.00, N = 3SE +/- 4.52, N = 3SE +/- 8.98, N = 3SE +/- 4.97, N = 3SE +/- 3.37, N = 32830.122506.105024.329203.195608.079752.895594.8110182.161414.862743.391525.262957.693802.617127.284093.737689.321100.182030.973606.127862.585725.0310934.171. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenSSL

OpenSSL is an open-source toolkit that implements SSL (Secure Sockets Layer) and TLS (Transport Layer Security) protocols. This test profile makes use of the built-in "openssl speed" benchmarking capabilities. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgbyte/s, More Is BetterOpenSSL 3.3Algorithm: SHA512EPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P20000M40000M60000M80000M100000MSE +/- 15082903.45, N = 3SE +/- 9990938.84, N = 3SE +/- 6285194.15, N = 3SE +/- 37307640.51, N = 3SE +/- 55712209.05, N = 3SE +/- 44023374.36, N = 3SE +/- 5822493.86, N = 3SE +/- 17716195.81, N = 3SE +/- 14430784.68, N = 3SE +/- 66704467.17, N = 3SE +/- 24045021.87, N = 3SE +/- 64065176.93, N = 3SE +/- 500176.69, N = 3SE +/- 3500318.33, N = 3SE +/- 1250834.62, N = 3SE +/- 14339684.98, N = 3SE +/- 6313493.56, N = 3SE +/- 20492408.59, N = 3SE +/- 203213936.42, N = 3SE +/- 481040738.21, N = 3SE +/- 37654528.63, N = 3SE +/- 14734422.48, N = 32437846082022194470973396275754977882225738345865131913914559712005274663411310477663304740605137923785993952304508875564089194416857161992612773230422299318893980783375645220531098094009322079539900222199277234284625447723886054770465207607071. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl

OpenBenchmarking.orgsign/s, More Is BetterOpenSSL 3.3Algorithm: RSA4096EPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P20K40K60K80K100KSE +/- 22.17, N = 3SE +/- 12.56, N = 3SE +/- 29.11, N = 3SE +/- 81.38, N = 3SE +/- 98.71, N = 3SE +/- 247.60, N = 3SE +/- 27.42, N = 3SE +/- 80.37, N = 3SE +/- 1.37, N = 3SE +/- 8.25, N = 3SE +/- 1.63, N = 3SE +/- 8.20, N = 3SE +/- 19.45, N = 3SE +/- 6.92, N = 3SE +/- 20.13, N = 3SE +/- 83.09, N = 3SE +/- 40.37, N = 3SE +/- 108.70, N = 3SE +/- 9.84, N = 3SE +/- 14.34, N = 3SE +/- 15.15, N = 3SE +/- 56.68, N = 325894.621047.535964.971942.048996.898237.053966.9107830.611348.522587.412610.825098.022861.045531.025441.548534.818389.336371.627431.154601.131594.461499.61. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl

Llamafile

Mozilla's Llamafile allows distributing and running large language models (LLMs) as a single file. Llamafile aims to make open-source LLMs more accessible to developers and users. Llamafile supports a variety of models, CPUs and GPUs, and other options. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgTokens Per Second, More Is BetterLlamafile 0.7Test: llava-v1.5-7b-q4 - Acceleration: CPUEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P612182430SE +/- 0.11, N = 4SE +/- 0.07, N = 4SE +/- 0.02, N = 5SE +/- 0.07, N = 4SE +/- 0.10, N = 5SE +/- 0.02, N = 4SE +/- 0.05, N = 4SE +/- 0.08, N = 4SE +/- 0.08, N = 3SE +/- 0.02, N = 3SE +/- 0.30, N = 15SE +/- 0.04, N = 3SE +/- 0.10, N = 3SE +/- 0.05, N = 3SE +/- 0.02, N = 3SE +/- 0.04, N = 3SE +/- 0.11, N = 3SE +/- 0.10, N = 15SE +/- 0.15, N = 4SE +/- 0.09, N = 15SE +/- 0.17, N = 4SE +/- 1.08, N = 1221.0020.6525.7514.4725.3814.2920.6410.948.562.839.602.997.677.778.137.2619.1112.2920.9510.4416.617.49

TensorFlow

This is a benchmark of the TensorFlow deep learning framework using the TensorFlow reference benchmarks (tensorflow/benchmarks with tf_cnn_benchmarks.py). Note with the Phoronix Test Suite there is also pts/tensorflow-lite for benchmarking the TensorFlow Lite binaries if desired for complementary metrics. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.16.1Device: CPU - Batch Size: 1 - Model: GoogLeNetEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P1224364860SE +/- 0.30, N = 15SE +/- 0.14, N = 6SE +/- 0.41, N = 15SE +/- 0.14, N = 15SE +/- 0.33, N = 15SE +/- 0.17, N = 15SE +/- 0.27, N = 15SE +/- 0.04, N = 3SE +/- 0.04, N = 4SE +/- 0.05, N = 7SE +/- 0.09, N = 4SE +/- 0.06, N = 9SE +/- 0.27, N = 7SE +/- 0.20, N = 15SE +/- 0.27, N = 6SE +/- 0.23, N = 12SE +/- 0.24, N = 7SE +/- 0.34, N = 15SE +/- 0.19, N = 6SE +/- 0.23, N = 15SE +/- 0.21, N = 6SE +/- 0.12, N = 636.6636.4832.8012.4234.2012.8321.008.1012.405.8813.146.7236.1318.2431.4714.6753.3829.1833.5613.5021.6712.69

Pennant

Pennant is an application focused on hydrodynamics on general unstructured meshes in 2D. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgHydro Cycle Time - Seconds, Fewer Is BetterPennant 1.0.1Test: sedovbigEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P612182430SE +/- 0.024479, N = 4SE +/- 0.029749, N = 4SE +/- 0.052975, N = 7SE +/- 0.040626, N = 15SE +/- 0.080453, N = 15SE +/- 0.041359, N = 15SE +/- 0.074320, N = 15SE +/- 0.037087, N = 15SE +/- 0.001847, N = 3SE +/- 0.003237, N = 4SE +/- 0.013353, N = 3SE +/- 0.003253, N = 4SE +/- 0.034794, N = 3SE +/- 0.052953, N = 3SE +/- 0.002987, N = 3SE +/- 0.016400, N = 4SE +/- 0.002400, N = 3SE +/- 0.018471, N = 411.36964012.1513205.9164583.4083375.4606603.0811085.1476582.94045621.02112013.21125019.88246012.10690025.78945015.24719016.03080011.28438016.9691009.9645261. (CXX) g++ options: -fopenmp -lmpi_cxx -lmpi

OpenFOAM

OpenFOAM is the leading free, open-source software for computational fluid dynamics (CFD). This test profile currently uses the drivaerFastback test case for analyzing automotive aerodynamics or alternatively the older motorBike input. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterOpenFOAM 10Input: drivaerFastback, Medium Mesh Size - Execution TimeEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P2004006008001000691.64690.74325.42124.30178.2593.57449.47137.11440.83201.11410.29186.33798.35362.59420.65196.50302.06137.041. (CXX) g++ options: -std=c++14 -m64 -O3 -ftemplate-depth-100 -fPIC -fuse-ld=bfd -Xlinker --add-needed --no-as-needed -lfiniteVolume -lmeshTools -lparallel -llagrangian -lregionModels -lgenericPatchFields -lOpenFOAM -ldl -lm

QuantLib

QuantLib is an open-source library/framework around quantitative finance for modeling, trading and risk management scenarios. QuantLib is written in C++ with Boost and its built-in benchmark used reports the QuantLib Benchmark Index benchmark score. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMFLOPS, More Is BetterQuantLib 1.32Configuration: Multi-ThreadedEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P160K320K480K640K800KSE +/- 82.80, N = 3SE +/- 86.28, N = 3SE +/- 86.78, N = 3SE +/- 713.18, N = 3SE +/- 412.72, N = 3SE +/- 1065.76, N = 3SE +/- 156.35, N = 3SE +/- 804.57, N = 3SE +/- 306.14, N = 3SE +/- 1610.78, N = 3SE +/- 846.02, N = 3SE +/- 1647.70, N = 3SE +/- 155.19, N = 3SE +/- 286.86, N = 3SE +/- 40.48, N = 3SE +/- 160.59, N = 3SE +/- 395.04, N = 3SE +/- 457.00, N = 3SE +/- 105.60, N = 3SE +/- 362.38, N = 3SE +/- 63.14, N = 3SE +/- 248.00, N = 3172566.8153920.8294183.2593246.9319827.2644091.0374413.5759922.1233836.3456271.0262432.6519392.2143755.3288129.1162727.4316359.291036.5182366.9179647.5350187.5195648.8380867.51. (CXX) g++ options: -O3 -march=native -fPIE -pie

OpenVINO

This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Handwritten English Recognition FP16-INT8 - Device: CPUEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P4080120160200SE +/- 0.09, N = 3SE +/- 0.02, N = 3SE +/- 0.06, N = 3SE +/- 0.07, N = 3SE +/- 0.05, N = 3SE +/- 0.07, N = 3SE +/- 0.09, N = 3SE +/- 0.08, N = 3SE +/- 0.34, N = 3SE +/- 0.13, N = 3SE +/- 0.10, N = 3SE +/- 0.33, N = 3SE +/- 0.04, N = 3SE +/- 0.01, N = 3SE +/- 0.05, N = 3SE +/- 0.02, N = 3SE +/- 0.46, N = 3SE +/- 0.45, N = 15SE +/- 0.04, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 341.3845.7134.9236.9032.0033.1838.8539.86172.72180.29153.76157.2823.1224.0024.9425.7262.6460.9036.2025.1221.8722.961. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

John The Ripper

This is a benchmark of John The Ripper, which is a password cracker. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgReal C/S, More Is BetterJohn The Ripper 2023.03.14Test: WPA PSKEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P300K600K900K1200K1500KSE +/- 321.00, N = 3SE +/- 79.20, N = 3SE +/- 921.74, N = 3SE +/- 1333.33, N = 3SE +/- 2683.36, N = 3SE +/- 5291.50, N = 3SE +/- 478.70, N = 3SE +/- 4358.90, N = 3SE +/- 30.00, N = 3SE +/- 187.67, N = 3SE +/- 66.16, N = 3SE +/- 394.40, N = 3SE +/- 987.33, N = 3SE +/- 5122.51, N = 3SE +/- 1274.00, N = 3SE +/- 788.50, N = 3SE +/- 177.03, N = 3SE +/- 1491.72, N = 3SE +/- 1599.31, N = 3SE +/- 2519.00, N = 3SE +/- 864.17, N = 3SE +/- 15579.94, N = 153862123399986434751253333671322129400080318715510001889253676572098034072562865525628753340766578892480664915834012787932534281167970931. (CC) gcc options: -m64 -lssl -lcrypto -fopenmp -lgmp -lm -lrt -lz -ldl -lcrypt -lbz2

OpenVINO

This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Machine Translation EN To DE FP16 - Device: CPUEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P2004006008001000SE +/- 0.39, N = 3SE +/- 0.13, N = 3SE +/- 4.59, N = 7SE +/- 8.96, N = 3SE +/- 4.29, N = 11SE +/- 0.37, N = 3SE +/- 6.34, N = 5SE +/- 11.78, N = 3SE +/- 0.25, N = 3SE +/- 2.30, N = 15SE +/- 0.03, N = 3SE +/- 3.00, N = 3SE +/- 1.21, N = 3SE +/- 1.99, N = 3SE +/- 4.09, N = 3SE +/- 1.13, N = 3SE +/- 0.45, N = 3SE +/- 0.17, N = 3SE +/- 0.17, N = 3SE +/- 3.48, N = 3SE +/- 0.54, N = 3SE +/- 0.85, N = 3317.38293.07525.88990.16576.981110.49621.421127.05138.53243.76149.63264.66415.96795.63467.08889.18156.13281.36477.77793.64592.201128.781. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

miniBUDE

MiniBUDE is a mini application for the the core computation of the Bristol University Docking Engine (BUDE). This test profile currently makes use of the OpenMP implementation of miniBUDE for CPU benchmarking. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgBillion Interactions/s, More Is BetterminiBUDE 20210901Implementation: OpenMP - Input Deck: BM2EPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P70140210280350SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.93, N = 3SE +/- 0.08, N = 3SE +/- 1.71, N = 3SE +/- 2.28, N = 3SE +/- 0.01, N = 3SE +/- 3.85, N = 3SE +/- 0.00, N = 3SE +/- 0.03, N = 3SE +/- 0.00, N = 3SE +/- 0.08, N = 3SE +/- 0.31, N = 3SE +/- 1.48, N = 3SE +/- 0.96, N = 4SE +/- 0.93, N = 3SE +/- 0.11, N = 3SE +/- 0.75, N = 3SE +/- 0.31, N = 3SE +/- 0.99, N = 3SE +/- 0.03, N = 3SE +/- 1.93, N = 15107.7297.98171.77291.28187.68309.22232.75288.5439.3578.2443.7386.8870.21127.8578.11133.9949.2097.0886.97140.83108.12191.821. (CC) gcc options: -std=c99 -Ofast -ffast-math -fopenmp -march=native -lm

OpenBenchmarking.orgGFInst/s, More Is BetterminiBUDE 20210901Implementation: OpenMP - Input Deck: BM2EPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P17003400510068008500SE +/- 0.13, N = 3SE +/- 0.10, N = 3SE +/- 23.15, N = 3SE +/- 2.03, N = 3SE +/- 42.85, N = 3SE +/- 57.10, N = 3SE +/- 0.20, N = 3SE +/- 96.25, N = 3SE +/- 0.03, N = 3SE +/- 0.82, N = 3SE +/- 0.09, N = 3SE +/- 1.96, N = 3SE +/- 7.81, N = 3SE +/- 36.96, N = 3SE +/- 23.93, N = 4SE +/- 23.14, N = 3SE +/- 2.69, N = 3SE +/- 18.66, N = 3SE +/- 7.77, N = 3SE +/- 24.63, N = 3SE +/- 0.70, N = 3SE +/- 48.20, N = 152692.872449.454294.287281.964692.117730.475818.747213.43983.711955.881093.212172.101755.333196.121952.613349.761230.082426.882174.193520.712703.094795.461. (CC) gcc options: -std=c99 -Ofast -ffast-math -fopenmp -march=native -lm

ASTC Encoder

ASTC Encoder (astcenc) is for the Adaptive Scalable Texture Compression (ASTC) format commonly used with OpenGL, OpenGL ES, and Vulkan graphics APIs. This test profile does a coding test of both compression/decompression. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMT/s, More Is BetterASTC Encoder 4.7Preset: ThoroughEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P306090120150SE +/- 0.02, N = 4SE +/- 0.02, N = 3SE +/- 0.01, N = 4SE +/- 0.73, N = 15SE +/- 0.06, N = 5SE +/- 1.46, N = 12SE +/- 0.01, N = 5SE +/- 1.20, N = 5SE +/- 0.00, N = 3SE +/- 0.42, N = 4SE +/- 0.01, N = 3SE +/- 0.85, N = 4SE +/- 0.01, N = 3SE +/- 0.05, N = 4SE +/- 0.03, N = 4SE +/- 0.03, N = 5SE +/- 0.03, N = 3SE +/- 0.04, N = 3SE +/- 0.01, N = 4SE +/- 0.19, N = 5SE +/- 0.05, N = 4SE +/- 0.55, N = 541.0237.9665.30105.4173.38116.1286.01121.3040.6971.0245.2179.2937.0172.3342.9883.3415.5030.0351.3086.9854.4597.941. (CXX) g++ options: -O3 -flto -pthread

RELION

RELION - REgularised LIkelihood OptimisatioN - is a stand-alone computer program for Maximum A Posteriori refinement of (multiple) 3D reconstructions or 2D class averages in cryo-electron microscopy (cryo-EM). It is developed in the research group of Sjors Scheres at the MRC Laboratory of Molecular Biology. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterRELION 4.0.1Test: Basic - Device: CPUEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P150300450600750SE +/- 4.63, N = 3SE +/- 6.20, N = 3SE +/- 2.95, N = 3SE +/- 2.11, N = 12SE +/- 2.17, N = 3SE +/- 1.27, N = 15SE +/- 7.69, N = 9SE +/- 4.04, N = 12SE +/- 2.98, N = 3SE +/- 3.24, N = 12SE +/- 4.65, N = 9SE +/- 2.66, N = 12SE +/- 7.86, N = 9SE +/- 0.35, N = 3SE +/- 7.14, N = 9SE +/- 2.65, N = 3SE +/- 2.68, N = 7SE +/- 1.41, N = 3468.69496.24238.88145.65176.4293.17360.21201.27412.37214.42384.38201.38705.58368.22373.18203.41290.45155.741. (CXX) g++ options: -fopenmp -std=c++11 -O3 -rdynamic -ldl -ltiff -lfftw3f -lfftw3 -lpng -ljpeg -lmpi_cxx -lmpi

OpenSSL

OpenSSL is an open-source toolkit that implements SSL (Secure Sockets Layer) and TLS (Transport Layer Security) protocols. This test profile makes use of the built-in "openssl speed" benchmarking capabilities. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgbyte/s, More Is BetterOpenSSL 3.3Algorithm: ChaCha20-Poly1305EPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P200000M400000M600000M800000M1000000MSE +/- 24234601.89, N = 3SE +/- 65233629.47, N = 3SE +/- 29295317.86, N = 3SE +/- 6119305.11, N = 3SE +/- 4478378.70, N = 3SE +/- 558033954.71, N = 3SE +/- 151303743.70, N = 3SE +/- 19082587.00, N = 3SE +/- 2360978.39, N = 3SE +/- 37182497.08, N = 3SE +/- 18243420.30, N = 3SE +/- 38565703.74, N = 3SE +/- 6370607.14, N = 3SE +/- 4148679.28, N = 3SE +/- 37795783.50, N = 3SE +/- 36941390.18, N = 3SE +/- 255765711.98, N = 3SE +/- 31274617.76, N = 3SE +/- 766713911.50, N = 3SE +/- 132227134.30, N = 3SE +/- 120899798.30, N = 3SE +/- 82161991.11, N = 32111856617271933050936433509609983576989258222233839256520777676527195474570397488709060286089901205917872572400051351531340330390902665838578871613210582133203967204471877961744403727352152971461562129502935021224132250388507304422025329772236257380134440991442701. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl

Blender

Blender is an open-source 3D creation and modeling software project. This test is of Blender's Cycles performance with various sample files. GPU computing via NVIDIA OptiX and NVIDIA CUDA is currently supported as well as HIP for AMD Radeon GPUs and Intel oneAPI for Intel Graphics. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.1Blend File: Classroom - Compute: CPU-OnlyEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P306090120150SE +/- 0.04, N = 3SE +/- 0.18, N = 3SE +/- 0.11, N = 3SE +/- 0.05, N = 3SE +/- 0.14, N = 3SE +/- 0.03, N = 3SE +/- 0.04, N = 3SE +/- 0.05, N = 3SE +/- 0.05, N = 3SE +/- 0.09, N = 3SE +/- 0.67, N = 3SE +/- 0.05, N = 3SE +/- 0.20, N = 3SE +/- 0.38, N = 3SE +/- 0.40, N = 3SE +/- 0.25, N = 3SE +/- 0.38, N = 3SE +/- 0.16, N = 3SE +/- 0.04, N = 3SE +/- 0.05, N = 3SE +/- 0.11, N = 3SE +/- 0.22, N = 367.6775.2640.2621.1235.6618.6731.6516.8252.4727.4148.0724.6186.6744.7176.8740.38124.6362.5468.6135.9163.6133.61

OpenVINO

This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Person Detection FP16 - Device: CPUEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P60120180240300SE +/- 0.19, N = 3SE +/- 0.41, N = 3SE +/- 2.90, N = 15SE +/- 0.44, N = 15SE +/- 1.22, N = 15SE +/- 0.09, N = 3SE +/- 6.97, N = 15SE +/- 1.90, N = 15SE +/- 0.25, N = 3SE +/- 0.07, N = 3SE +/- 0.15, N = 3SE +/- 0.34, N = 3SE +/- 0.18, N = 3SE +/- 0.10, N = 3SE +/- 0.10, N = 3SE +/- 0.06, N = 3SE +/- 0.92, N = 3SE +/- 0.14, N = 3SE +/- 0.01, N = 3SE +/- 0.05, N = 3SE +/- 0.09, N = 3SE +/- 0.09, N = 3161.48156.59157.4563.98110.9143.77230.2485.86283.83293.02266.91274.5241.9342.1659.6964.91236.81113.70100.3945.7839.6243.411. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenSSL

OpenSSL is an open-source toolkit that implements SSL (Secure Sockets Layer) and TLS (Transport Layer Security) protocols. This test profile makes use of the built-in "openssl speed" benchmarking capabilities. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgbyte/s, More Is BetterOpenSSL 3.3Algorithm: ChaCha20EPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P300000M600000M900000M1200000M1500000MSE +/- 9570566.28, N = 3SE +/- 71110585.03, N = 3SE +/- 151272595.84, N = 3SE +/- 80233613.02, N = 3SE +/- 94935214.36, N = 3SE +/- 874940734.18, N = 3SE +/- 170968063.89, N = 3SE +/- 63368290.15, N = 3SE +/- 11028602.79, N = 3SE +/- 11835135.62, N = 3SE +/- 39095934.62, N = 3SE +/- 63366974.35, N = 3SE +/- 415487944.57, N = 3SE +/- 329510485.23, N = 3SE +/- 312824840.64, N = 3SE +/- 863978337.15, N = 3SE +/- 151152302.42, N = 3SE +/- 352722951.98, N = 3SE +/- 232288636.76, N = 3SE +/- 271318554.29, N = 3SE +/- 3335467.26, N = 3SE +/- 303075210.03, N = 33070689383772820533270775033110211231001502634860544904084773108661819195065639632938713069285075731772490621833528268216531969206832703919112254802265973541534499084949272637406900675229124033472122948838304254511900633161264211736244029729473441509169376842843827601. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl

John The Ripper

This is a benchmark of John The Ripper, which is a password cracker. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgReal C/S, More Is BetterJohn The Ripper 2023.03.14Test: BlowfishEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P90K180K270K360K450KSE +/- 13.72, N = 3SE +/- 20.54, N = 3SE +/- 38.33, N = 3SE +/- 3455.48, N = 3SE +/- 98.33, N = 3SE +/- 454.86, N = 3SE +/- 1.33, N = 3SE +/- 2397.15, N = 3SE +/- 174.44, N = 3SE +/- 353.58, N = 3SE +/- 14.67, N = 3SE +/- 482.17, N = 3SE +/- 17.33, N = 3SE +/- 116.69, N = 3SE +/- 8.67, N = 3SE +/- 169.28, N = 3SE +/- 6.33, N = 3SE +/- 14.62, N = 3SE +/- 11.39, N = 3SE +/- 348.45, N = 3SE +/- 79.75, N = 3SE +/- 649.08, N = 310219893473166541316492192574374589220188415412190209363300211449404739678931345627915215665856939113223945131835831058312054991. (CC) gcc options: -m64 -lssl -lcrypto -fopenmp -lgmp -lm -lrt -lz -ldl -lcrypt -lbz2

OpenBenchmarking.orgReal C/S, More Is BetterJohn The Ripper 2023.03.14Test: bcryptEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P90K180K270K360K450KSE +/- 22.28, N = 3SE +/- 0.00, N = 3SE +/- 20.00, N = 3SE +/- 710.46, N = 3SE +/- 154.46, N = 3SE +/- 1315.55, N = 3SE +/- 1.33, N = 3SE +/- 4958.68, N = 4SE +/- 32.84, N = 3SE +/- 801.76, N = 3SE +/- 87.49, N = 3SE +/- 2096.39, N = 3SE +/- 8.84, N = 3SE +/- 866.68, N = 3SE +/- 8.67, N = 3SE +/- 576.80, N = 3SE +/- 6.33, N = 3SE +/- 12.67, N = 3SE +/- 10.67, N = 3SE +/- 292.24, N = 3SE +/- 46.28, N = 3SE +/- 288.38, N = 310222293472166541320527192898376268220188412723190058363133211311402275678751338667914415595956939113219945511836031057812067781. (CC) gcc options: -m64 -lssl -lcrypto -fopenmp -lgmp -lm -lrt -lz -ldl -lcrypt -lbz2

7-Zip Compression

This is a test of 7-Zip compression/decompression with its integrated benchmark feature. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMIPS, More Is Better7-Zip Compression 22.01Test: Decompression RatingEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P300K600K900K1200K1500KSE +/- 120.28, N = 3SE +/- 81.21, N = 3SE +/- 111.53, N = 3SE +/- 15794.26, N = 3SE +/- 1085.99, N = 3SE +/- 38431.24, N = 3SE +/- 291.68, N = 3SE +/- 14188.09, N = 3SE +/- 343.82, N = 3SE +/- 2333.15, N = 3SE +/- 258.19, N = 3SE +/- 903.01, N = 3SE +/- 916.22, N = 3SE +/- 2598.93, N = 3SE +/- 374.59, N = 3SE +/- 6276.88, N = 3SE +/- 309.57, N = 3SE +/- 559.82, N = 3SE +/- 61.74, N = 3SE +/- 185.14, N = 3SE +/- 119.21, N = 3SE +/- 28320.74, N = 33679893383556426261033277716065111646578087113402264210637673134637688463352077384017072433474691311883453665342878625570543381465734101. (CXX) g++ options: -lpthread -ldl -O2 -fPIC

Primesieve

Primesieve generates prime numbers using a highly optimized sieve of Eratosthenes implementation. Primesieve primarily benchmarks the CPU's L1/L2 cache performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterPrimesieve 12.1Length: 1e13EPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P20406080100SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 4SE +/- 0.02, N = 3SE +/- 0.02, N = 4SE +/- 0.02, N = 3SE +/- 0.01, N = 4SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.04, N = 3SE +/- 0.07, N = 3SE +/- 0.04, N = 3SE +/- 0.04, N = 3SE +/- 0.07, N = 3SE +/- 0.25, N = 3SE +/- 0.10, N = 3SE +/- 0.04, N = 3SE +/- 0.01, N = 3SE +/- 0.04, N = 3SE +/- 0.04, N = 345.9554.3924.2412.6323.2712.1321.7611.5657.7129.3952.0726.4667.3233.9258.1630.2081.3640.4451.8227.1148.4125.021. (CXX) g++ options: -O3

Blender

Blender is an open-source 3D creation and modeling software project. This test is of Blender's Cycles performance with various sample files. GPU computing via NVIDIA OptiX and NVIDIA CUDA is currently supported as well as HIP for AMD Radeon GPUs and Intel oneAPI for Intel Graphics. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.1Blend File: Barbershop - Compute: CPU-OnlyEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P100200300400500SE +/- 0.06, N = 3SE +/- 0.07, N = 3SE +/- 0.25, N = 3SE +/- 0.02, N = 3SE +/- 0.12, N = 3SE +/- 0.11, N = 3SE +/- 0.03, N = 3SE +/- 0.07, N = 3SE +/- 0.33, N = 3SE +/- 0.41, N = 3SE +/- 0.08, N = 3SE +/- 0.17, N = 3SE +/- 0.12, N = 3SE +/- 0.23, N = 3SE +/- 1.09, N = 3SE +/- 0.06, N = 3SE +/- 0.03, N = 3SE +/- 0.25, N = 3SE +/- 0.18, N = 3SE +/- 0.42, N = 3SE +/- 0.69, N = 3SE +/- 0.21, N = 3240.13263.76139.2579.05123.9067.52114.7665.58191.20106.48174.4997.18320.11169.44290.56156.70456.81235.31261.97141.54236.73125.87

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.1Blend File: Pabellon Barcelona - Compute: CPU-OnlyEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P306090120150SE +/- 0.16, N = 3SE +/- 0.05, N = 3SE +/- 0.04, N = 3SE +/- 0.10, N = 3SE +/- 0.16, N = 3SE +/- 0.11, N = 3SE +/- 0.13, N = 3SE +/- 0.13, N = 3SE +/- 0.13, N = 3SE +/- 0.29, N = 3SE +/- 0.25, N = 3SE +/- 0.17, N = 3SE +/- 0.31, N = 3SE +/- 0.08, N = 3SE +/- 0.44, N = 3SE +/- 0.20, N = 3SE +/- 0.15, N = 3SE +/- 0.26, N = 3SE +/- 0.15, N = 3SE +/- 0.26, N = 3SE +/- 0.09, N = 3SE +/- 0.06, N = 385.1294.4148.8826.3544.8723.8439.8321.6665.6735.1160.1131.28106.9655.2697.8051.29150.3976.1087.9246.3880.2941.85

Coremark

This is a test of EEMBC CoreMark processor benchmark. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgIterations/Sec, More Is BetterCoremark 1.0CoreMark Size 666 - Iterations Per SecondEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P2M4M6M8M10MSE +/- 1374.66, N = 3SE +/- 11678.22, N = 3SE +/- 10132.66, N = 3SE +/- 2306.54, N = 3SE +/- 54326.71, N = 3SE +/- 76743.24, N = 3SE +/- 4775.53, N = 3SE +/- 54771.53, N = 3SE +/- 10294.77, N = 3SE +/- 9906.84, N = 3SE +/- 40214.40, N = 15SE +/- 7619.10, N = 3SE +/- 1747.99, N = 3SE +/- 7219.73, N = 3SE +/- 5202.86, N = 3SE +/- 20649.43, N = 3SE +/- 927.64, N = 3SE +/- 30163.42, N = 15SE +/- 9256.47, N = 3SE +/- 12743.41, N = 3SE +/- 4635.95, N = 3SE +/- 9700.21, N = 32274636.132069432.533926265.287975907.454152864.888448083.734525288.008171241.712915609.756575205.543340274.037302247.141614763.702993136.601855135.333279262.531218453.341839444.402194630.603902076.242369998.364966250.781. (CC) gcc options: -O2 -lrt" -lrt

OpenRadioss

OpenRadioss is an open-source AGPL-licensed finite element solver for dynamic event analysis OpenRadioss is based on Altair Radioss and open-sourced in 2022. This open-source finite element solver is benchmarked with various example models available from https://www.openradioss.org/models/ and https://github.com/OpenRadioss/ModelExchange/tree/main/Examples. This test is currently using a reference OpenRadioss binary build offered via GitHub. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterOpenRadioss 2023.09.15Model: Chrysler Neon 1MEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P70140210280350SE +/- 0.47, N = 3SE +/- 0.50, N = 3SE +/- 1.51, N = 8SE +/- 0.71, N = 12SE +/- 0.49, N = 3SE +/- 0.46, N = 3SE +/- 1.11, N = 3SE +/- 1.00, N = 10SE +/- 0.08, N = 3SE +/- 0.13, N = 3SE +/- 0.18, N = 3SE +/- 0.14, N = 3SE +/- 0.13, N = 3SE +/- 0.78, N = 3SE +/- 0.15, N = 3SE +/- 0.11, N = 3SE +/- 0.20, N = 3SE +/- 0.14, N = 3297.25300.69176.1477.6477.3249.55231.9693.99228.74125.15212.99117.91343.16185.03207.20115.89157.5686.93

OpenVINO

This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Face Detection Retail FP16-INT8 - Device: CPUEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P8K16K24K32K40KSE +/- 2.45, N = 3SE +/- 7.49, N = 3SE +/- 2.59, N = 3SE +/- 46.87, N = 3SE +/- 7.70, N = 3SE +/- 15.46, N = 3SE +/- 8.57, N = 3SE +/- 10.72, N = 3SE +/- 2.54, N = 3SE +/- 30.29, N = 3SE +/- 0.67, N = 3SE +/- 41.98, N = 3SE +/- 18.13, N = 3SE +/- 12.64, N = 3SE +/- 7.39, N = 3SE +/- 3.89, N = 3SE +/- 15.90, N = 3SE +/- 16.45, N = 3SE +/- 5.45, N = 3SE +/- 12.64, N = 3SE +/- 4.30, N = 3SE +/- 17.69, N = 39256.118279.6316038.9031974.8817230.3535809.5919917.5438546.667721.0014551.128536.3916394.069087.1217252.279686.3918561.915913.0413467.289004.2320937.5812317.9424676.861. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OSPRay Studio

Intel OSPRay Studio is an open-source, interactive visualization and ray-tracing software package. OSPRay Studio makes use of Intel OSPRay, a portable ray-tracing engine for high-performance, high-fidelity visualizations. OSPRay builds off Intel's Embree and Intel SPMD Program Compiler (ISPC) components as part of the oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 1.0Camera: 1 - Resolution: 4K - Samples Per Pixel: 16 - Renderer: Path Tracer - Acceleration: CPUEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P12K24K36K48K60KSE +/- 250.73, N = 3SE +/- 31.02, N = 3SE +/- 44.33, N = 3SE +/- 32.74, N = 3SE +/- 39.30, N = 3SE +/- 17.16, N = 3SE +/- 33.33, N = 3SE +/- 12.34, N = 3SE +/- 199.93, N = 3SE +/- 409.89, N = 15SE +/- 371.33, N = 3SE +/- 429.71, N = 4SE +/- 28.06, N = 3SE +/- 72.42, N = 3SE +/- 83.47, N = 3SE +/- 51.39, N = 3SE +/- 148.46, N = 3SE +/- 53.03, N = 3SE +/- 62.46, N = 3SE +/- 34.10, N = 3SE +/- 37.49, N = 3SE +/- 7.13, N = 3388114251318896104281660389161528684135208338228468753508137055166453379015357544563044231380141382312512124

Blender

Blender is an open-source 3D creation and modeling software project. This test is of Blender's Cycles performance with various sample files. GPU computing via NVIDIA OptiX and NVIDIA CUDA is currently supported as well as HIP for AMD Radeon GPUs and Intel oneAPI for Intel Graphics. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.1Blend File: BMW27 - Compute: CPU-OnlyEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P1122334455SE +/- 0.04, N = 3SE +/- 0.05, N = 3SE +/- 0.07, N = 4SE +/- 0.02, N = 5SE +/- 0.04, N = 4SE +/- 0.03, N = 6SE +/- 0.01, N = 4SE +/- 0.02, N = 6SE +/- 0.17, N = 8SE +/- 0.06, N = 5SE +/- 0.05, N = 3SE +/- 0.09, N = 5SE +/- 0.11, N = 3SE +/- 0.03, N = 3SE +/- 0.24, N = 3SE +/- 0.08, N = 4SE +/- 0.11, N = 3SE +/- 0.03, N = 3SE +/- 0.15, N = 3SE +/- 0.08, N = 4SE +/- 0.04, N = 3SE +/- 0.03, N = 427.1230.0715.968.6114.297.7512.867.1719.8510.5617.619.7131.6616.5528.4915.2946.3223.6725.8913.7423.7212.76

OpenVINO

This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Person Re-Identification Retail FP16 - Device: CPUEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P612182430SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.16, N = 3SE +/- 0.02, N = 3SE +/- 0.08, N = 3SE +/- 0.02, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 38.599.467.233.986.933.788.034.3717.8118.7516.3616.737.137.327.767.9723.2524.399.797.726.726.951. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

Xcompact3d Incompact3d

Xcompact3d Incompact3d is a Fortran-MPI based, finite difference high-performance code for solving the incompressible Navier-Stokes equation and as many as you need scalar transport equations. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterXcompact3d Incompact3d 2021-03-11Input: input.i3d 193 Cells Per DirectionEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P612182430SE +/- 0.01040414, N = 3SE +/- 0.10237421, N = 3SE +/- 0.06577912, N = 5SE +/- 0.04312156, N = 5SE +/- 0.05847189, N = 6SE +/- 0.00891960, N = 5SE +/- 0.03951909, N = 5SE +/- 0.01633300, N = 4SE +/- 0.04445674, N = 4SE +/- 0.01741826, N = 5SE +/- 0.01708632, N = 4SE +/- 0.05695382, N = 15SE +/- 0.01216869, N = 3SE +/- 0.02691998, N = 4SE +/- 0.01004100, N = 4SE +/- 0.04312801, N = 5SE +/- 0.02923582, N = 4SE +/- 0.03329814, N = 520.9379139021.178030708.253835114.260785966.881212793.753199018.872259144.5106189313.969237607.2934911712.799758206.6638751023.9708284011.2498016012.929341306.3916981710.196706605.391259671. (F9X) gfortran options: -cpp -O2 -funroll-loops -floop-optimize -fcray-pointer -fbacktrace -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz

OpenSSL

OpenSSL is an open-source toolkit that implements SSL (Secure Sockets Layer) and TLS (Transport Layer Security) protocols. This test profile makes use of the built-in "openssl speed" benchmarking capabilities. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgverify/s, More Is BetterOpenSSL 3.3Algorithm: RSA4096EPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P800K1600K2400K3200K4000KSE +/- 126.84, N = 3SE +/- 136.07, N = 3SE +/- 149.48, N = 3SE +/- 5.26, N = 3SE +/- 1576.96, N = 3SE +/- 6125.37, N = 3SE +/- 444.74, N = 3SE +/- 2222.55, N = 3SE +/- 9.55, N = 3SE +/- 37.76, N = 3SE +/- 23.84, N = 3SE +/- 205.33, N = 3SE +/- 165.80, N = 3SE +/- 355.69, N = 3SE +/- 200.66, N = 3SE +/- 277.84, N = 3SE +/- 198.68, N = 3SE +/- 40228.60, N = 3SE +/- 92.46, N = 3SE +/- 862.96, N = 3SE +/- 92.62, N = 3SE +/- 6745.42, N = 3881480.8810291.81436324.92861959.81613828.73214376.31872096.13729470.8743282.71479879.0826049.51644363.7697707.21395446.4813667.61627941.4587354.81099481.5974189.91916162.91036735.62057021.61. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl

OSPRay Studio

Intel OSPRay Studio is an open-source, interactive visualization and ray-tracing software package. OSPRay Studio makes use of Intel OSPRay, a portable ray-tracing engine for high-performance, high-fidelity visualizations. OSPRay builds off Intel's Embree and Intel SPMD Program Compiler (ISPC) components as part of the oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 1.0Camera: 3 - Resolution: 4K - Samples Per Pixel: 16 - Renderer: Path Tracer - Acceleration: CPUEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P14K28K42K56K70KSE +/- 111.72, N = 3SE +/- 197.99, N = 3SE +/- 5.55, N = 3SE +/- 27.79, N = 3SE +/- 24.66, N = 3SE +/- 32.79, N = 3SE +/- 21.05, N = 3SE +/- 16.90, N = 3SE +/- 500.31, N = 3SE +/- 51.90, N = 3SE +/- 26.58, N = 3SE +/- 301.00, N = 12SE +/- 36.47, N = 3SE +/- 25.12, N = 3SE +/- 74.33, N = 3SE +/- 10.97, N = 3SE +/- 62.75, N = 3SE +/- 28.75, N = 3SE +/- 61.20, N = 3SE +/- 29.96, N = 3SE +/- 26.00, N = 3SE +/- 8.00, N = 345377488442230512427195351051418129100155765743906525013928342837197013923818111630353486636649168373199314358

OpenVINO

This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Road Segmentation ADAS FP16-INT8 - Device: CPUEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P9001800270036004500SE +/- 0.65, N = 3SE +/- 0.81, N = 3SE +/- 6.85, N = 3SE +/- 3.90, N = 3SE +/- 1.09, N = 3SE +/- 5.33, N = 3SE +/- 11.41, N = 15SE +/- 5.40, N = 3SE +/- 2.69, N = 3SE +/- 2.08, N = 3SE +/- 2.82, N = 3SE +/- 2.23, N = 3SE +/- 2.29, N = 3SE +/- 1.56, N = 3SE +/- 2.94, N = 3SE +/- 1.74, N = 3SE +/- 0.62, N = 3SE +/- 3.75, N = 3SE +/- 2.65, N = 3SE +/- 0.66, N = 3SE +/- 0.47, N = 3SE +/- 11.53, N = 3998.09918.531743.493353.732212.414013.961671.234032.66924.901731.501018.181933.08860.641691.79894.871801.89642.441186.241068.431843.611159.662237.691. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

ACES DGEMM

This is a multi-threaded DGEMM benchmark. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGFLOP/s, More Is BetterACES DGEMM 1.0Sustained Floating-Point RateEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P20406080100SE +/- 0.16, N = 5SE +/- 0.10, N = 5SE +/- 0.22, N = 7SE +/- 0.10, N = 9SE +/- 0.40, N = 7SE +/- 0.39, N = 9SE +/- 0.17, N = 7SE +/- 0.19, N = 10SE +/- 0.01, N = 4SE +/- 0.03, N = 6SE +/- 0.01, N = 4SE +/- 0.04, N = 6SE +/- 0.04, N = 4SE +/- 0.06, N = 7SE +/- 0.09, N = 5SE +/- 0.04, N = 7SE +/- 0.01, N = 3SE +/- 0.09, N = 5SE +/- 0.09, N = 5SE +/- 0.28, N = 7SE +/- 0.08, N = 6SE +/- 0.11, N = 821.8221.0039.0968.8745.2578.5044.9784.6915.9431.4817.8535.2019.7739.3522.5444.6713.4924.9723.5445.9729.1458.251. (CC) gcc options: -O3 -march=native -fopenmp

Helsing

Helsing is an open-source POSIX vampire number generator. This test profile measures the time it takes to generate vampire numbers between varying numbers of digits. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterHelsing 1.0-betaDigit Range: 14 digitEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P4080120160200SE +/- 0.27, N = 3SE +/- 0.06, N = 3SE +/- 0.10, N = 3SE +/- 0.38, N = 5SE +/- 0.14, N = 3SE +/- 0.42, N = 3SE +/- 0.02, N = 3SE +/- 0.32, N = 3SE +/- 0.12, N = 3SE +/- 0.11, N = 3SE +/- 0.10, N = 3SE +/- 0.01, N = 3SE +/- 0.53, N = 3SE +/- 0.11, N = 3SE +/- 0.12, N = 3SE +/- 0.42, N = 3SE +/- 0.08, N = 3SE +/- 0.09, N = 3SE +/- 0.26, N = 3SE +/- 0.06, N = 3SE +/- 0.08, N = 3SE +/- 0.07, N = 3105.68120.5662.1733.6856.9130.6948.8526.78115.4658.96103.8653.02123.8365.03107.2458.25165.7982.9693.3550.8389.0748.091. (CC) gcc options: -O2 -pthread

Algebraic Multi-Grid Benchmark

AMG is a parallel algebraic multigrid solver for linear systems arising from problems on unstructured grids. The driver provided with AMG builds linear systems for various 3-dimensional problems. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFigure Of Merit, More Is BetterAlgebraic Multi-Grid Benchmark 1.2EPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P1000M2000M3000M4000M5000MSE +/- 2902028.33, N = 3SE +/- 291866.98, N = 3SE +/- 1066998.75, N = 3SE +/- 8808919.44, N = 3SE +/- 4963892.66, N = 3SE +/- 6340323.98, N = 3SE +/- 433397.56, N = 3SE +/- 235140242.43, N = 12SE +/- 3359086.30, N = 3SE +/- 7233468.75, N = 3SE +/- 1778769.08, N = 3SE +/- 9164253.67, N = 3SE +/- 971797.70, N = 3SE +/- 467864.03, N = 3SE +/- 468935.32, N = 3SE +/- 2438223.49, N = 3SE +/- 4000850.45, N = 3SE +/- 9014927.20, N = 3115005266711471080002282802000432493033323761490004467281333227535266727830390831588496667315626166715979933333205161000107362766772315353316050970003124402667181476000036096463331. (CC) gcc options: -lparcsr_ls -lparcsr_mv -lseq_mv -lIJ_mv -lkrylov -lHYPRE_utilities -lm -fopenmp -lmpi

OSPRay Studio

Intel OSPRay Studio is an open-source, interactive visualization and ray-tracing software package. OSPRay Studio makes use of Intel OSPRay, a portable ray-tracing engine for high-performance, high-fidelity visualizations. OSPRay builds off Intel's Embree and Intel SPMD Program Compiler (ISPC) components as part of the oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 1.0Camera: 1 - Resolution: 4K - Samples Per Pixel: 32 - Renderer: Path Tracer - Acceleration: CPUEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P20K40K60K80K100KSE +/- 172.59, N = 3SE +/- 346.19, N = 3SE +/- 42.05, N = 3SE +/- 109.43, N = 3SE +/- 193.23, N = 3SE +/- 14.62, N = 3SE +/- 312.83, N = 12SE +/- 47.34, N = 3SE +/- 541.85, N = 3SE +/- 739.02, N = 15SE +/- 424.84, N = 3SE +/- 605.82, N = 15SE +/- 134.33, N = 3SE +/- 37.55, N = 3SE +/- 64.91, N = 3SE +/- 13.86, N = 3SE +/- 175.68, N = 3SE +/- 152.29, N = 3SE +/- 102.40, N = 3SE +/- 64.24, N = 3SE +/- 90.37, N = 3SE +/- 16.05, N = 3720517809343290207503864517855373831696088579624498100356082689733892662540361791034615524758026334115079824249

Blender

Blender is an open-source 3D creation and modeling software project. This test is of Blender's Cycles performance with various sample files. GPU computing via NVIDIA OptiX and NVIDIA CUDA is currently supported as well as HIP for AMD Radeon GPUs and Intel oneAPI for Intel Graphics. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.1Blend File: Fishy Cat - Compute: CPU-OnlyEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P1326395265SE +/- 0.23, N = 3SE +/- 0.07, N = 3SE +/- 0.11, N = 3SE +/- 0.05, N = 4SE +/- 0.07, N = 3SE +/- 0.02, N = 5SE +/- 0.13, N = 3SE +/- 0.04, N = 5SE +/- 0.37, N = 3SE +/- 0.05, N = 3SE +/- 0.08, N = 3SE +/- 0.01, N = 4SE +/- 0.17, N = 3SE +/- 0.13, N = 3SE +/- 0.04, N = 3SE +/- 0.18, N = 3SE +/- 0.15, N = 3SE +/- 0.27, N = 3SE +/- 0.11, N = 3SE +/- 0.08, N = 3SE +/- 0.06, N = 3SE +/- 0.04, N = 334.3538.0420.1511.2518.3610.1616.589.7129.5516.5226.5215.1642.7823.1738.4821.4559.1530.7534.8319.1331.9117.29

m-queens

A solver for the N-queens problem with multi-threading support via the OpenMP library. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is Betterm-queens 1.2Time To SolveEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P612182430SE +/- 0.019, N = 4SE +/- 0.029, N = 4SE +/- 0.019, N = 6SE +/- 0.093, N = 15SE +/- 0.025, N = 6SE +/- 0.064, N = 15SE +/- 0.021, N = 6SE +/- 0.031, N = 8SE +/- 0.039, N = 5SE +/- 0.035, N = 7SE +/- 0.032, N = 5SE +/- 0.034, N = 7SE +/- 0.031, N = 3SE +/- 0.021, N = 5SE +/- 0.035, N = 3SE +/- 0.028, N = 5SE +/- 0.023, N = 3SE +/- 0.066, N = 4SE +/- 0.025, N = 4SE +/- 0.021, N = 6SE +/- 0.030, N = 4SE +/- 0.028, N = 613.25014.4937.7384.6096.9504.1336.3503.98111.4796.04510.3015.51221.03010.84018.1029.28524.17512.39015.2117.88114.2577.4021. (CXX) g++ options: -fopenmp -O2 -march=native

OSPRay Studio

Intel OSPRay Studio is an open-source, interactive visualization and ray-tracing software package. OSPRay Studio makes use of Intel OSPRay, a portable ray-tracing engine for high-performance, high-fidelity visualizations. OSPRay builds off Intel's Embree and Intel SPMD Program Compiler (ISPC) components as part of the oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 1.0Camera: 3 - Resolution: 4K - Samples Per Pixel: 32 - Renderer: Path Tracer - Acceleration: CPUEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P30K60K90K120K150KSE +/- 29.36, N = 3SE +/- 13.58, N = 3SE +/- 231.95, N = 3SE +/- 756.08, N = 15SE +/- 89.57, N = 3SE +/- 27.74, N = 3SE +/- 50.97, N = 3SE +/- 28.11, N = 3SE +/- 365.52, N = 3SE +/- 900.17, N = 15SE +/- 189.03, N = 3SE +/- 176.25, N = 3SE +/- 41.33, N = 3SE +/- 155.80, N = 3SE +/- 65.97, N = 3SE +/- 141.04, N = 3SE +/- 623.29, N = 3SE +/- 32.38, N = 3SE +/- 58.68, N = 3SE +/- 125.33, N = 3SE +/- 162.52, N = 3SE +/- 47.16, N = 38426191643500192794344349208934294520071101444715839217566487807424521173366419711217346418868006388135952233391

miniBUDE

MiniBUDE is a mini application for the the core computation of the Bristol University Docking Engine (BUDE). This test profile currently makes use of the OpenMP implementation of miniBUDE for CPU benchmarking. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgBillion Interactions/s, More Is BetterminiBUDE 20210901Implementation: OpenMP - Input Deck: BM1EPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P50100150200250SE +/- 0.04, N = 6SE +/- 0.03, N = 6SE +/- 1.18, N = 7SE +/- 2.97, N = 13SE +/- 3.27, N = 13SE +/- 6.15, N = 12SE +/- 0.70, N = 9SE +/- 3.98, N = 15SE +/- 0.02, N = 3SE +/- 0.05, N = 5SE +/- 0.01, N = 3SE +/- 0.46, N = 15SE +/- 0.12, N = 4SE +/- 1.28, N = 12SE +/- 0.84, N = 15SE +/- 1.85, N = 12SE +/- 0.38, N = 9SE +/- 1.19, N = 15SE +/- 0.61, N = 5SE +/- 0.81, N = 7SE +/- 0.20, N = 6SE +/- 1.02, N = 8107.3598.21136.95217.85151.95236.61229.91214.6239.1776.6043.5584.3563.62108.4070.84114.9047.2685.2982.85133.63106.40199.731. (CC) gcc options: -std=c99 -Ofast -ffast-math -fopenmp -march=native -lm

OpenBenchmarking.orgGFInst/s, More Is BetterminiBUDE 20210901Implementation: OpenMP - Input Deck: BM1EPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P13002600390052006500SE +/- 0.97, N = 6SE +/- 0.82, N = 6SE +/- 29.52, N = 7SE +/- 74.36, N = 13SE +/- 81.83, N = 13SE +/- 153.85, N = 12SE +/- 17.54, N = 9SE +/- 99.42, N = 15SE +/- 0.46, N = 3SE +/- 1.36, N = 5SE +/- 0.29, N = 3SE +/- 11.58, N = 15SE +/- 2.91, N = 4SE +/- 32.01, N = 12SE +/- 21.10, N = 15SE +/- 46.19, N = 12SE +/- 9.38, N = 9SE +/- 29.84, N = 15SE +/- 15.23, N = 5SE +/- 20.15, N = 7SE +/- 5.07, N = 6SE +/- 25.44, N = 82683.832455.163423.635446.163798.705915.255747.825365.42979.281915.041088.832108.681590.502709.931771.072872.561181.492132.242071.193340.692659.884993.341. (CC) gcc options: -std=c99 -Ofast -ffast-math -fopenmp -march=native -lm

OpenVINO

This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Vehicle Detection FP16-INT8 - Device: CPUEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P3K6K9K12K15KSE +/- 2.22, N = 3SE +/- 2.89, N = 3SE +/- 8.39, N = 3SE +/- 4.21, N = 3SE +/- 3.54, N = 3SE +/- 4.04, N = 3SE +/- 66.33, N = 15SE +/- 1.24, N = 3SE +/- 1.12, N = 3SE +/- 8.74, N = 3SE +/- 2.61, N = 3SE +/- 5.08, N = 3SE +/- 8.09, N = 3SE +/- 4.11, N = 3SE +/- 5.68, N = 3SE +/- 8.70, N = 3SE +/- 1.06, N = 3SE +/- 2.84, N = 3SE +/- 0.81, N = 3SE +/- 11.51, N = 3SE +/- 0.73, N = 3SE +/- 6.25, N = 32943.082763.485528.1510708.916017.1911735.425778.5112750.592366.834376.092553.554992.782935.475576.862877.325525.562120.334390.813325.905483.814656.928719.371. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

NAS Parallel Benchmarks

NPB, NAS Parallel Benchmarks, is a benchmark developed by NASA for high-end computer systems. This test profile currently uses the MPI version of NPB. This test profile offers selecting the different NPB tests/problems and varying problem sizes. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: LU.CEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P130K260K390K520K650KSE +/- 314.42, N = 4SE +/- 274.93, N = 3SE +/- 789.76, N = 5SE +/- 4162.49, N = 6SE +/- 1849.65, N = 6SE +/- 1879.23, N = 6SE +/- 2566.89, N = 15SE +/- 5800.63, N = 15SE +/- 71.37, N = 3SE +/- 441.66, N = 5SE +/- 37.04, N = 4SE +/- 411.20, N = 5SE +/- 123.65, N = 3SE +/- 155.95, N = 4SE +/- 130.20, N = 4SE +/- 398.40, N = 5SE +/- 213.44, N = 5SE +/- 726.00, N = 5133284.46130839.12269047.28472931.04362511.43551955.55279397.45588329.32126171.52246822.52131606.86257384.5598557.16185954.54135125.15261127.09232012.77455312.091. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz 2. Open MPI 4.1.6

OSPRay

Intel OSPRay is a portable ray-tracing engine for high-performance, high-fidelity scientific visualizations. OSPRay builds off Intel's Embree and Intel SPMD Program Compiler (ISPC) components as part of the oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgItems Per Second, More Is BetterOSPRay 3.1Benchmark: particle_volume/scivis/real_timeEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P1326395265SE +/- 0.01395, N = 3SE +/- 0.00583, N = 3SE +/- 0.01265, N = 3SE +/- 0.04960, N = 3SE +/- 0.01858, N = 3SE +/- 0.01792, N = 3SE +/- 0.02252, N = 3SE +/- 0.01106, N = 3SE +/- 0.00610, N = 3SE +/- 0.04097, N = 3SE +/- 0.01460, N = 3SE +/- 0.02131, N = 3SE +/- 0.00932, N = 3SE +/- 0.05872, N = 3SE +/- 0.03593, N = 3SE +/- 0.04134, N = 3SE +/- 0.00909, N = 3SE +/- 0.03711, N = 3SE +/- 0.00525, N = 3SE +/- 0.02499, N = 3SE +/- 0.04057, N = 3SE +/- 0.04682, N = 317.9448016.4505028.0689047.5267032.5232055.2576035.1464056.4485019.4251032.7979021.5147036.2464016.0869029.3496018.4851033.127509.7002217.6222021.8932038.2269030.6799053.93480

OpenSSL

OpenSSL is an open-source toolkit that implements SSL (Secure Sockets Layer) and TLS (Transport Layer Security) protocols. This test profile makes use of the built-in "openssl speed" benchmarking capabilities. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgbyte/s, More Is BetterOpenSSL 3.3Algorithm: AES-128-GCMEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P500000M1000000M1500000M2000000M2500000MSE +/- 530918594.60, N = 3SE +/- 409615403.40, N = 3SE +/- 164763342.54, N = 3SE +/- 337702856.52, N = 3SE +/- 570058274.06, N = 3SE +/- 1428966819.54, N = 3SE +/- 49279694.68, N = 3SE +/- 1841260363.24, N = 3SE +/- 195953395.92, N = 3SE +/- 429428665.34, N = 3SE +/- 129279575.06, N = 3SE +/- 333650111.34, N = 3SE +/- 43545680.66, N = 3SE +/- 268465891.11, N = 3SE +/- 56355870.99, N = 3SE +/- 697208281.49, N = 3SE +/- 706172241.68, N = 3SE +/- 266669781.18, N = 3SE +/- 28627701.54, N = 3SE +/- 159598753.20, N = 3SE +/- 1253503549.61, N = 3SE +/- 1622921637.03, N = 353978493137348896539085789728843612317850068790679960071092671990352059967116722114187023166119452835657207677831096082199713638453203763126688286665364120084817012775833827577477107026601484669627050399526815427807229265300768804693697153302630072788956750654017693131460131. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl

OSPRay

Intel OSPRay is a portable ray-tracing engine for high-performance, high-fidelity scientific visualizations. OSPRay builds off Intel's Embree and Intel SPMD Program Compiler (ISPC) components as part of the oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgItems Per Second, More Is BetterOSPRay 3.1Benchmark: particle_volume/ao/real_timeEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P1326395265SE +/- 0.02190, N = 3SE +/- 0.04390, N = 3SE +/- 0.01424, N = 3SE +/- 0.01406, N = 3SE +/- 0.01754, N = 3SE +/- 0.02899, N = 3SE +/- 0.03039, N = 3SE +/- 0.01800, N = 3SE +/- 0.02488, N = 3SE +/- 0.03817, N = 3SE +/- 0.01225, N = 3SE +/- 0.03595, N = 3SE +/- 0.03513, N = 3SE +/- 0.01945, N = 3SE +/- 0.01050, N = 3SE +/- 0.00297, N = 3SE +/- 0.05948, N = 3SE +/- 0.03319, N = 3SE +/- 0.00975, N = 3SE +/- 0.02269, N = 3SE +/- 0.01144, N = 3SE +/- 0.07203, N = 317.9668016.4504028.0956047.6143032.5188055.3382035.2461056.6936019.5159032.9663021.6222036.5043016.0502029.5018018.5533033.112509.7776417.8269021.9324038.2235030.8404054.11950

Llamafile

Mozilla's Llamafile allows distributing and running large language models (LLMs) as a single file. Llamafile aims to make open-source LLMs more accessible to developers and users. Llamafile supports a variety of models, CPUs and GPUs, and other options. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgTokens Per Second, More Is BetterLlamafile 0.7Test: wizardcoder-python-34b-v1.0.Q6_K - Acceleration: CPUEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P246810SE +/- 0.02, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.03, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.12, N = 6SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 35.165.118.355.248.485.247.474.635.392.565.582.671.471.771.541.544.413.105.853.824.083.05

OSPRay Studio

Intel OSPRay Studio is an open-source, interactive visualization and ray-tracing software package. OSPRay Studio makes use of Intel OSPRay, a portable ray-tracing engine for high-performance, high-fidelity visualizations. OSPRay builds off Intel's Embree and Intel SPMD Program Compiler (ISPC) components as part of the oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 1.0Camera: 1 - Resolution: 4K - Samples Per Pixel: 1 - Renderer: Path Tracer - Acceleration: CPUEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P7001400210028003500SE +/- 0.58, N = 3SE +/- 1.20, N = 3SE +/- 0.58, N = 3SE +/- 0.58, N = 3SE +/- 1.15, N = 3SE +/- 1.20, N = 3SE +/- 1.20, N = 3SE +/- 0.88, N = 3SE +/- 7.84, N = 3SE +/- 21.79, N = 12SE +/- 11.06, N = 3SE +/- 24.01, N = 12SE +/- 0.33, N = 3SE +/- 1.76, N = 3SE +/- 0.58, N = 3SE +/- 0.58, N = 3SE +/- 4.62, N = 3SE +/- 0.33, N = 3SE +/- 0.58, N = 3SE +/- 0.58, N = 3SE +/- 0.88, N = 3SE +/- 0.88, N = 3204322401180661103756195453123181497209013421988104917929613052155316578941441759

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 1.0Camera: 3 - Resolution: 4K - Samples Per Pixel: 1 - Renderer: Path Tracer - Acceleration: CPUEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P8001600240032004000SE +/- 1.00, N = 3SE +/- 3.06, N = 3SE +/- 1.00, N = 3SE +/- 0.58, N = 3SE +/- 1.53, N = 3SE +/- 1.45, N = 3SE +/- 0.88, N = 3SE +/- 0.67, N = 3SE +/- 6.23, N = 3SE +/- 4.67, N = 3SE +/- 3.51, N = 3SE +/- 16.65, N = 5SE +/- 1.20, N = 3SE +/- 2.65, N = 3SE +/- 1.20, N = 3SE +/- 0.33, N = 3SE +/- 3.79, N = 3SE +/- 2.73, N = 3SE +/- 0.88, N = 3SE +/- 0.88, N = 3SE +/- 1.45, N = 3SE +/- 0.00, N = 3242126491391780122566011306302731183224721631235712372123114336161833197710631709898

OpenSSL

OpenSSL is an open-source toolkit that implements SSL (Secure Sockets Layer) and TLS (Transport Layer Security) protocols. This test profile makes use of the built-in "openssl speed" benchmarking capabilities. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgbyte/s, More Is BetterOpenSSL 3.3Algorithm: AES-256-GCMEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P400000M800000M1200000M1600000M2000000MSE +/- 148092414.72, N = 3SE +/- 3442274884.66, N = 3SE +/- 818689705.82, N = 3SE +/- 2225250504.62, N = 3SE +/- 671752057.50, N = 3SE +/- 1859275059.09, N = 3SE +/- 290015345.25, N = 3SE +/- 1791964708.17, N = 3SE +/- 34244051.67, N = 3SE +/- 252081360.30, N = 3SE +/- 317370827.95, N = 3SE +/- 301551944.80, N = 3SE +/- 119857064.56, N = 3SE +/- 108288170.03, N = 3SE +/- 63026881.96, N = 3SE +/- 112278705.55, N = 3SE +/- 81945775.93, N = 3SE +/- 116420153.53, N = 3SE +/- 2848140790.67, N = 3SE +/- 1397764228.85, N = 3SE +/- 3966858436.56, N = 3SE +/- 1320809584.03, N = 3462309750530415893963207767696553667152650546581385972059996317140617610879975390078731983103026700506301374623979419388797568937578313112537304117350745672808710118989933235920141154531181148957353356062040883712485411447700239352717136953432847074438768367014975299393771. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl

Primesieve

Primesieve generates prime numbers using a highly optimized sieve of Eratosthenes implementation. Primesieve primarily benchmarks the CPU's L1/L2 cache performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterPrimesieve 12.1Length: 1e12EPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P246810SE +/- 0.006, N = 8SE +/- 0.003, N = 8SE +/- 0.003, N = 11SE +/- 0.005, N = 12SE +/- 0.004, N = 11SE +/- 0.003, N = 12SE +/- 0.002, N = 11SE +/- 0.010, N = 15SE +/- 0.003, N = 8SE +/- 0.012, N = 10SE +/- 0.003, N = 8SE +/- 0.008, N = 10SE +/- 0.006, N = 7SE +/- 0.004, N = 9SE +/- 0.010, N = 7SE +/- 0.005, N = 10SE +/- 0.006, N = 6SE +/- 0.003, N = 9SE +/- 0.019, N = 8SE +/- 0.006, N = 10SE +/- 0.007, N = 8SE +/- 0.008, N = 113.8014.5452.0581.2421.9841.1991.9211.3594.8062.6054.3242.3376.1603.1215.3322.6916.6733.3664.5762.3254.2502.1871. (CXX) g++ options: -O3

Blender

Blender is an open-source 3D creation and modeling software project. This test is of Blender's Cycles performance with various sample files. GPU computing via NVIDIA OptiX and NVIDIA CUDA is currently supported as well as HIP for AMD Radeon GPUs and Intel oneAPI for Intel Graphics. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.1Blend File: Junkshop - Compute: CPU-OnlyEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P1428425670SE +/- 0.06, N = 3SE +/- 0.03, N = 3SE +/- 0.06, N = 3SE +/- 0.02, N = 4SE +/- 0.13, N = 3SE +/- 0.08, N = 4SE +/- 0.08, N = 3SE +/- 0.02, N = 4SE +/- 0.08, N = 3SE +/- 0.11, N = 3SE +/- 0.03, N = 3SE +/- 0.14, N = 3SE +/- 0.04, N = 3SE +/- 0.06, N = 3SE +/- 0.10, N = 3SE +/- 0.19, N = 3SE +/- 0.09, N = 3SE +/- 0.10, N = 3SE +/- 0.24, N = 3SE +/- 0.04, N = 3SE +/- 0.10, N = 3SE +/- 0.09, N = 335.8238.8621.0212.8718.6511.4717.7011.2129.0618.7026.4916.8942.8524.9939.1723.4561.2233.2035.9621.1532.0818.31

OpenVINO

This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Road Segmentation ADAS FP16-INT8 - Device: CPUEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P1530456075SE +/- 0.02, N = 3SE +/- 0.03, N = 3SE +/- 0.11, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.26, N = 15SE +/- 0.02, N = 3SE +/- 0.11, N = 3SE +/- 0.05, N = 3SE +/- 0.10, N = 3SE +/- 0.04, N = 3SE +/- 0.15, N = 3SE +/- 0.05, N = 3SE +/- 0.21, N = 3SE +/- 0.06, N = 3SE +/- 0.03, N = 3SE +/- 0.05, N = 3SE +/- 0.14, N = 3SE +/- 0.03, N = 3SE +/- 0.02, N = 3SE +/- 0.28, N = 331.9934.7627.4614.3021.6311.9538.2115.8438.8741.5035.3037.1755.7456.7162.5362.1131.0516.8455.9965.0255.0757.131. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

NAS Parallel Benchmarks

NPB, NAS Parallel Benchmarks, is a benchmark developed by NASA for high-end computer systems. This test profile currently uses the MPI version of NPB. This test profile offers selecting the different NPB tests/problems and varying problem sizes. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: IS.DEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P3K6K9K12K15KSE +/- 9.85, N = 4SE +/- 14.39, N = 4SE +/- 17.53, N = 5SE +/- 76.70, N = 10SE +/- 29.95, N = 5SE +/- 119.22, N = 6SE +/- 35.67, N = 5SE +/- 85.04, N = 8SE +/- 15.55, N = 4SE +/- 12.99, N = 4SE +/- 18.08, N = 4SE +/- 4.96, N = 4SE +/- 11.05, N = 3SE +/- 8.35, N = 4SE +/- 6.56, N = 3SE +/- 23.92, N = 4SE +/- 8.92, N = 4SE +/- 155.00, N = 152746.202718.945229.4110139.696346.1512296.275702.139771.413050.163816.703076.663819.832266.323345.452865.723960.284059.707437.811. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz 2. Open MPI 4.1.6

OSPRay

Intel OSPRay is a portable ray-tracing engine for high-performance, high-fidelity scientific visualizations. OSPRay builds off Intel's Embree and Intel SPMD Program Compiler (ISPC) components as part of the oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgItems Per Second, More Is BetterOSPRay 3.1Benchmark: gravity_spheres_volume/dim_512/pathtracer/real_timeEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P1428425670SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.07, N = 3SE +/- 0.04, N = 3SE +/- 0.14, N = 3SE +/- 0.02, N = 3SE +/- 0.05, N = 3SE +/- 0.00, N = 3SE +/- 0.23, N = 3SE +/- 0.01, N = 3SE +/- 0.03, N = 3SE +/- 0.01, N = 3SE +/- 0.09, N = 3SE +/- 0.03, N = 3SE +/- 0.16, N = 3SE +/- 0.04, N = 3SE +/- 0.03, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.03, N = 3SE +/- 0.04, N = 318.4716.9230.6152.6734.6460.3737.7463.8512.1721.2213.4023.1219.9135.9322.3639.3411.8622.5124.6442.8227.1048.76

OpenVINO

This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Vehicle Detection FP16-INT8 - Device: CPUEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P510152025SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.12, N = 15SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.03, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.05, N = 3SE +/- 0.01, N = 3SE +/- 0.04, N = 3SE +/- 0.03, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.04, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 310.7811.488.584.467.854.0810.975.0015.1116.2814.0114.3016.3317.1919.4420.249.264.5417.8421.7313.7314.671. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Person Vehicle Bike Detection FP16 - Device: CPUEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P612182430SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.05, N = 3SE +/- 0.00, N = 3SE +/- 0.03, N = 3SE +/- 0.01, N = 3SE +/- 0.11, N = 3SE +/- 0.00, N = 3SE +/- 0.04, N = 3SE +/- 0.05, N = 3SE +/- 0.05, N = 3SE +/- 0.03, N = 3SE +/- 0.02, N = 3SE +/- 0.00, N = 3SE +/- 0.03, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 311.2212.679.475.208.484.9111.356.2725.3326.1223.4924.2412.5413.3413.5914.4218.089.8216.5015.0411.1711.691. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

PyTorch

This is a benchmark of PyTorch making use of pytorch-benchmark [https://github.com/LukasHedegaard/pytorch-benchmark]. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.2.1Device: CPU - Batch Size: 1 - Model: ResNet-50EPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P20406080100SE +/- 0.12, N = 3SE +/- 0.30, N = 3SE +/- 0.15, N = 3SE +/- 0.28, N = 15SE +/- 0.15, N = 3SE +/- 0.37, N = 12SE +/- 0.12, N = 3SE +/- 0.06, N = 3SE +/- 0.12, N = 3SE +/- 0.20, N = 3SE +/- 0.45, N = 4SE +/- 0.22, N = 4SE +/- 0.28, N = 3SE +/- 0.38, N = 8SE +/- 0.36, N = 3SE +/- 0.44, N = 3SE +/- 0.22, N = 3SE +/- 0.20, N = 3SE +/- 0.03, N = 3SE +/- 0.49, N = 3SE +/- 0.16, N = 3SE +/- 0.52, N = 341.1140.9740.4519.3441.1719.8431.6214.9032.4516.4535.8517.9150.9946.4948.5935.4661.3242.6451.4635.5377.5245.69

PostgreSQL

This is a benchmark of PostgreSQL using the integrated pgbench for facilitating the database benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL 16Scaling Factor: 100 - Clients: 1000 - Mode: Read Only - Average LatencyEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P0.29090.58180.87271.16361.4545SE +/- 0.002, N = 3SE +/- 0.001, N = 3SE +/- 0.003, N = 3SE +/- 0.004, N = 12SE +/- 0.002, N = 3SE +/- 0.006, N = 12SE +/- 0.001, N = 3SE +/- 0.001, N = 3SE +/- 0.007, N = 3SE +/- 0.009, N = 12SE +/- 0.006, N = 5SE +/- 0.008, N = 12SE +/- 0.008, N = 12SE +/- 0.017, N = 9SE +/- 0.007, N = 3SE +/- 0.038, N = 9SE +/- 0.005, N = 3SE +/- 0.022, N = 9SE +/- 0.007, N = 3SE +/- 0.030, N = 12SE +/- 0.005, N = 12SE +/- 0.040, N = 120.3840.4140.2780.2930.2510.2890.2920.3290.5720.8150.5420.7750.5591.0270.6221.0980.5810.5250.5721.2930.5891.1491. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL 16Scaling Factor: 100 - Clients: 1000 - Mode: Read OnlyEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P900K1800K2700K3600K4500KSE +/- 11512.67, N = 3SE +/- 4774.62, N = 3SE +/- 39970.22, N = 3SE +/- 41074.86, N = 12SE +/- 27594.68, N = 3SE +/- 71870.42, N = 12SE +/- 15503.17, N = 3SE +/- 13473.87, N = 3SE +/- 20221.52, N = 3SE +/- 13874.42, N = 12SE +/- 19583.16, N = 5SE +/- 13233.94, N = 12SE +/- 24978.23, N = 12SE +/- 16726.04, N = 9SE +/- 17697.00, N = 3SE +/- 36627.33, N = 9SE +/- 13469.59, N = 3SE +/- 74539.48, N = 9SE +/- 20350.34, N = 3SE +/- 18635.21, N = 12SE +/- 13863.97, N = 12SE +/- 30933.90, N = 122606500241637536032613422731398935834809093422492304462017486581229649184608012921221792636976035160742492072517207621930006174814677814116990468818811. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

Speedb

Speedb is a next-generation key value storage engine that is RocksDB compatible and aiming for stability, efficiency, and performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgOp/s, More Is BetterSpeedb 2.7Test: Read While WritingEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P8M16M24M32M40MSE +/- 88013.69, N = 15SE +/- 86788.79, N = 3SE +/- 170909.18, N = 3SE +/- 746932.76, N = 15SE +/- 118870.12, N = 3SE +/- 651901.79, N = 15SE +/- 172052.60, N = 3SE +/- 803844.71, N = 15SE +/- 45758.35, N = 3SE +/- 138092.00, N = 3SE +/- 75416.94, N = 3SE +/- 223786.94, N = 15SE +/- 88257.34, N = 3SE +/- 171807.74, N = 3SE +/- 93731.24, N = 7SE +/- 197596.27, N = 3SE +/- 48302.92, N = 15SE +/- 48351.08, N = 3SE +/- 62510.72, N = 3SE +/- 239363.92, N = 3SE +/- 143570.67, N = 4SE +/- 195912.00, N = 15120539011188210318024993303245961959577733307574228294263659320417548934276307811794574527657776879540813859254998817615354400714712011795318106953601729702712168413175857371. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread

ONNX Runtime

ONNX Runtime is developed by Microsoft and partners as a open-source, cross-platform, high performance machine learning inferencing and training accelerator. This test profile runs the ONNX Runtime with various models available from the ONNX Model Zoo. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.17Model: T5 Encoder - Device: CPU - Executor: ParallelEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P100200300400500SE +/- 2.24, N = 3SE +/- 1.96, N = 3SE +/- 0.55, N = 3SE +/- 2.43, N = 3SE +/- 3.58, N = 3SE +/- 0.65, N = 3SE +/- 3.02, N = 3SE +/- 0.64, N = 3SE +/- 0.65, N = 3SE +/- 1.08, N = 3SE +/- 0.69, N = 3SE +/- 1.28, N = 3SE +/- 3.48, N = 15SE +/- 2.44, N = 3SE +/- 1.74, N = 3SE +/- 1.67, N = 15SE +/- 2.25, N = 3SE +/- 1.11, N = 3SE +/- 0.86, N = 3SE +/- 2.94, N = 3SE +/- 3.84, N = 3SE +/- 1.73, N = 3255.67254.73374.75271.62446.30276.21319.45250.63237.8092.51246.0494.42337.00246.68346.21252.67282.25249.48326.14246.34462.86354.751. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

Liquid-DSP

LiquidSDR's Liquid-DSP is a software-defined radio (SDR) digital signal processing library. This test profile runs a multi-threaded benchmark of this SDR/DSP library focused on embedded platform usage. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 1.6Threads: 256 - Buffer Length: 256 - Filter Length: 57EPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P2000M4000M6000M8000M10000MSE +/- 1959875.28, N = 3SE +/- 4481443.22, N = 3SE +/- 2618735.91, N = 3SE +/- 60380193.59, N = 3SE +/- 8144527.82, N = 3SE +/- 50144890.07, N = 3SE +/- 12739745.33, N = 3SE +/- 8069352.17, N = 3SE +/- 8015887.00, N = 3SE +/- 28436830.58, N = 3SE +/- 6906036.01, N = 3SE +/- 30821331.00, N = 3SE +/- 4088330.28, N = 3SE +/- 17558125.69, N = 3SE +/- 1976810.00, N = 3SE +/- 28453880.81, N = 3SE +/- 2935605.18, N = 3SE +/- 3572580.77, N = 3SE +/- 5292237.50, N = 3SE +/- 2331189.49, N = 3SE +/- 3555434.03, N = 3SE +/- 61971606.40, N = 331169333332793700000526646666774118666675811900000801270000064013666676316266667425943333368009000004714700000759756666728489333334825133333322253333350360000001610466667303710000035008333335361266667380683333362843000001. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

Embree

Intel Embree is a collection of high-performance ray-tracing kernels for execution on CPUs (and GPUs via SYCL) and supporting instruction sets such as SSE, AVX, AVX2, and AVX-512. Embree also supports making use of the Intel SPMD Program Compiler (ISPC). Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 4.3Binary: Pathtracer ISPC - Model: CrownEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P50100150200250SE +/- 0.04, N = 4SE +/- 0.07, N = 4SE +/- 0.08, N = 6SE +/- 0.43, N = 7SE +/- 0.20, N = 7SE +/- 1.23, N = 8SE +/- 0.64, N = 6SE +/- 1.04, N = 7SE +/- 0.05, N = 5SE +/- 0.11, N = 6SE +/- 0.02, N = 5SE +/- 0.14, N = 6SE +/- 0.05, N = 4SE +/- 0.14, N = 6SE +/- 0.02, N = 4SE +/- 0.48, N = 6SE +/- 0.07, N = 3SE +/- 0.08, N = 5SE +/- 0.07, N = 5SE +/- 0.12, N = 6SE +/- 0.05, N = 5SE +/- 0.07, N = 762.1958.28110.53176.21130.79214.02126.15190.0873.96121.4381.83133.4258.42107.6365.33116.6143.6782.9270.05124.7182.97153.16

Memcached

Memcached is a high performance, distributed memory object caching system. This Memcached test profiles makes use of memtier_benchmark for excuting this CPU/memory-focused server benchmark. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgOps/sec, More Is BetterMemcached 1.6.19Set To Get Ratio: 1:100EPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P2M4M6M8M10MSE +/- 36366.89, N = 3SE +/- 41123.40, N = 3SE +/- 29027.89, N = 3SE +/- 83562.82, N = 3SE +/- 58081.25, N = 3SE +/- 27143.58, N = 3SE +/- 38372.96, N = 3SE +/- 14591.70, N = 3SE +/- 19070.02, N = 15SE +/- 16910.46, N = 15SE +/- 19998.04, N = 15SE +/- 16926.98, N = 15SE +/- 21428.06, N = 3SE +/- 26891.33, N = 3SE +/- 52575.97, N = 3SE +/- 24083.78, N = 3SE +/- 38410.91, N = 15SE +/- 101903.23, N = 15SE +/- 25335.31, N = 3SE +/- 50660.01, N = 15SE +/- 35182.67, N = 3SE +/- 35300.21, N = 36198256.725820618.188220895.458498306.788634258.398683410.797736018.747645325.702299150.511783869.962339570.281821144.004384040.523373323.924315467.173392842.384826284.804814941.534481667.953245908.404752673.793780240.561. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre

OpenVINO

This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPUEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P0.3060.6120.9181.2241.53SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 15SE +/- 0.00, N = 3SE +/- 0.00, N = 7SE +/- 0.00, N = 3SE +/- 0.00, N = 9SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 15SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 30.530.600.480.350.450.350.730.411.361.201.251.090.330.280.370.300.560.450.430.290.490.461. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

PyTorch

This is a benchmark of PyTorch making use of pytorch-benchmark [https://github.com/LukasHedegaard/pytorch-benchmark]. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.2.1Device: CPU - Batch Size: 256 - Model: ResNet-50EPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P1428425670SE +/- 0.18, N = 3SE +/- 0.13, N = 3SE +/- 0.21, N = 3SE +/- 0.37, N = 12SE +/- 0.09, N = 3SE +/- 0.32, N = 12SE +/- 0.08, N = 3SE +/- 0.28, N = 12SE +/- 0.12, N = 3SE +/- 0.11, N = 3SE +/- 0.13, N = 3SE +/- 0.12, N = 3SE +/- 0.76, N = 3SE +/- 0.52, N = 3SE +/- 0.62, N = 3SE +/- 0.45, N = 3SE +/- 0.04, N = 3SE +/- 0.23, N = 3SE +/- 0.52, N = 3SE +/- 0.49, N = 3SE +/- 0.64, N = 3SE +/- 0.29, N = 333.6833.3034.9017.4134.9016.9727.7813.1126.8214.6730.8616.2252.9741.6851.5637.9148.8936.9754.8437.4463.6041.45

GraphicsMagick

This is a test of GraphicsMagick with its OpenMP implementation that performs various imaging tests on a sample high resolution (currently 15400 x 6940) JPEG image. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.43Operation: SharpenEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P80160240320400SE +/- 0.00, N = 3SE +/- 0.33, N = 3SE +/- 0.00, N = 3SE +/- 1.20, N = 3SE +/- 0.00, N = 3SE +/- 0.88, N = 3SE +/- 0.33, N = 3SE +/- 3.00, N = 3SE +/- 0.00, N = 3SE +/- 0.88, N = 3SE +/- 0.00, N = 3SE +/- 0.67, N = 3SE +/- 0.00, N = 3SE +/- 1.20, N = 3SE +/- 0.00, N = 3SE +/- 0.33, N = 3SE +/- 0.33, N = 3SE +/- 0.33, N = 3SE +/- 0.33, N = 3SE +/- 1.67, N = 3SE +/- 0.00, N = 3SE +/- 1.67, N = 3112105173262201297207310253336281381114199130227791441572651672841. (CC) gcc options: -fopenmp -O2 -ltiff -ljbig -lsharpyuv -lwebp -lwebpmux -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -lxml2 -lzstd -llzma -lbz2 -lz -lm -lpthread -lgomp

srsRAN Project

srsRAN Project is a complete ORAN-native 5G RAN solution created by Software Radio Systems (SRS). The srsRAN Project radio suite was formerly known as srsLTE and can be used for building your own software-defined radio (SDR) 4G/5G mobile network. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMbps, More Is BettersrsRAN Project 23.10.1-20240325Test: PUSCH Processor Benchmark, Throughput TotalEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P2K4K6K8K10KSE +/- 25.25, N = 3SE +/- 19.02, N = 13SE +/- 0.20, N = 3SE +/- 74.95, N = 4SE +/- 55.17, N = 3SE +/- 2.29, N = 3SE +/- 63.64, N = 5SE +/- 76.45, N = 3SE +/- 8.17, N = 3SE +/- 36.60, N = 3SE +/- 0.00, N = 3SE +/- 14.40, N = 3SE +/- 0.09, N = 3SE +/- 26.47, N = 3SE +/- 18.30, N = 3SE +/- 0.15, N = 3SE +/- 0.07, N = 3SE +/- 0.17, N = 3SE +/- 18.43, N = 3SE +/- 47.68, N = 6SE +/- 18.09, N = 3SE +/- 0.12, N = 33193.02818.55239.66835.75656.96999.75973.88396.71953.13067.02118.63414.22170.73787.02514.04386.61770.03288.42616.94853.63088.75493.41. (CXX) g++ options: -O3 -march=native -mavx2 -mavx -msse4.1 -mfma -fno-trapping-math -fno-math-errno -ldl

GROMACS

The GROMACS (GROningen MAchine for Chemical Simulations) molecular dynamics package testing with the water_GMX50 data. This test profile allows selecting between CPU and GPU-based GROMACS builds. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgNs Per Day, More Is BetterGROMACS 2024Implementation: MPI CPU - Input: water_GMX50_bareEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P510152025SE +/- 0.004, N = 3SE +/- 0.004, N = 3SE +/- 0.034, N = 3SE +/- 0.189, N = 6SE +/- 0.052, N = 3SE +/- 0.224, N = 14SE +/- 0.032, N = 3SE +/- 0.067, N = 3SE +/- 0.019, N = 3SE +/- 0.025, N = 3SE +/- 0.007, N = 3SE +/- 0.032, N = 3SE +/- 0.018, N = 3SE +/- 0.036, N = 3SE +/- 0.010, N = 3SE +/- 0.019, N = 3SE +/- 0.009, N = 3SE +/- 0.046, N = 36.4996.24612.51420.23415.22222.52513.24221.3057.54513.3928.28214.1274.8138.9648.76215.45010.47718.5401. (CXX) g++ options: -O3 -lm

OpenVKL

OpenVKL is the Intel Open Volume Kernel Library that offers high-performance volume computation kernels and part of the Intel oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgItems / Sec, More Is BetterOpenVKL 2.0.0Benchmark: vklBenchmarkCPU ISPCEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P9001800270036004500SE +/- 1.20, N = 3SE +/- 8.17, N = 3SE +/- 1.20, N = 3SE +/- 8.67, N = 3SE +/- 1.00, N = 3SE +/- 5.36, N = 3SE +/- 0.88, N = 3SE +/- 26.33, N = 3SE +/- 0.58, N = 3SE +/- 7.31, N = 3SE +/- 0.67, N = 3SE +/- 3.61, N = 3SE +/- 6.66, N = 3SE +/- 8.62, N = 3SE +/- 13.96, N = 3SE +/- 4.36, N = 3SE +/- 6.81, N = 3SE +/- 12.02, N = 3SE +/- 1.53, N = 3SE +/- 6.74, N = 3SE +/- 2.08, N = 3SE +/- 13.62, N = 3126611772077333523963906250840121267202013912228124317761356185286915271734271620043222

PyTorch

This is a benchmark of PyTorch making use of pytorch-benchmark [https://github.com/LukasHedegaard/pytorch-benchmark]. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.2.1Device: CPU - Batch Size: 64 - Model: ResNet-50EPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P1428425670SE +/- 0.06, N = 3SE +/- 0.18, N = 3SE +/- 0.26, N = 3SE +/- 0.35, N = 12SE +/- 0.10, N = 3SE +/- 0.37, N = 12SE +/- 0.10, N = 3SE +/- 0.23, N = 9SE +/- 0.14, N = 3SE +/- 0.06, N = 3SE +/- 0.33, N = 5SE +/- 0.11, N = 3SE +/- 0.71, N = 3SE +/- 0.51, N = 3SE +/- 0.62, N = 3SE +/- 0.46, N = 4SE +/- 0.14, N = 3SE +/- 0.40, N = 15SE +/- 0.24, N = 3SE +/- 0.50, N = 3SE +/- 0.12, N = 3SE +/- 0.12, N = 333.4933.2335.0117.0734.7117.2827.6813.6826.8914.8430.6916.1051.5542.3551.3538.3048.9937.7556.0137.0863.0640.77

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.2.1Device: CPU - Batch Size: 512 - Model: ResNet-50EPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P1428425670SE +/- 0.08, N = 3SE +/- 0.11, N = 3SE +/- 0.10, N = 3SE +/- 0.23, N = 3SE +/- 0.19, N = 3SE +/- 0.29, N = 12SE +/- 0.04, N = 3SE +/- 0.22, N = 12SE +/- 0.24, N = 3SE +/- 0.03, N = 3SE +/- 0.02, N = 3SE +/- 0.13, N = 9SE +/- 0.72, N = 3SE +/- 0.26, N = 3SE +/- 0.43, N = 15SE +/- 0.34, N = 15SE +/- 0.17, N = 3SE +/- 0.38, N = 15SE +/- 0.12, N = 3SE +/- 0.21, N = 3SE +/- 0.19, N = 3SE +/- 0.30, N = 1533.7633.1834.6516.2434.6916.8227.5313.7626.9114.8130.8715.9751.0541.6551.8637.8448.9937.4556.4437.5563.3040.83

ONNX Runtime

ONNX Runtime is developed by Microsoft and partners as a open-source, cross-platform, high performance machine learning inferencing and training accelerator. This test profile runs the ONNX Runtime with various models available from the ONNX Model Zoo. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.17Model: yolov4 - Device: CPU - Executor: ParallelEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P510152025SE +/- 0.00112, N = 3SE +/- 0.03807, N = 3SE +/- 0.01934, N = 3SE +/- 0.02467, N = 3SE +/- 0.00491, N = 3SE +/- 0.00606, N = 3SE +/- 0.01474, N = 3SE +/- 0.07368, N = 3SE +/- 0.04609, N = 3SE +/- 0.05214, N = 3SE +/- 0.03075, N = 3SE +/- 0.02942, N = 3SE +/- 0.05802, N = 3SE +/- 0.12795, N = 3SE +/- 0.00279, N = 3SE +/- 0.02010, N = 3SE +/- 0.11211, N = 3SE +/- 0.09305, N = 3SE +/- 0.01672, N = 3SE +/- 0.01439, N = 3SE +/- 0.13074, N = 3SE +/- 0.11392, N = 38.758148.472839.785166.348919.800086.318288.635945.557677.135874.589607.695834.5627816.1742013.0869016.3898012.5974017.6747014.2169018.1413012.7546020.8795014.198001. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

NAS Parallel Benchmarks

NPB, NAS Parallel Benchmarks, is a benchmark developed by NASA for high-end computer systems. This test profile currently uses the MPI version of NPB. This test profile offers selecting the different NPB tests/problems and varying problem sizes. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: CG.CEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P20K40K60K80K100KSE +/- 126.79, N = 6SE +/- 207.19, N = 6SE +/- 393.67, N = 15SE +/- 779.47, N = 7SE +/- 386.70, N = 9SE +/- 661.05, N = 7SE +/- 480.71, N = 15SE +/- 545.82, N = 5SE +/- 313.88, N = 7SE +/- 545.92, N = 15SE +/- 260.16, N = 15SE +/- 560.41, N = 15SE +/- 34.34, N = 6SE +/- 28.62, N = 7SE +/- 243.41, N = 12SE +/- 178.23, N = 8SE +/- 328.18, N = 8SE +/- 271.54, N = 622229.9421684.8053182.7784477.7262071.1088487.9143799.7863265.0135116.5565396.2235234.0666492.4422655.3238906.1333811.6358128.2463760.4598764.931. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz 2. Open MPI 4.1.6

ASKAP

ASKAP is a set of benchmarks from the Australian SKA Pathfinder. The principal ASKAP benchmarks are the Hogbom Clean Benchmark (tHogbomClean) and Convolutional Resamping Benchmark (tConvolve) as well as some previous ASKAP benchmarks being included as well for OpenCL and CUDA execution of tConvolve. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMillion Grid Points Per Second, More Is BetterASKAP 1.0Test: tConvolve MT - GriddingEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P3K6K9K12K15KSE +/- 0.88, N = 3SE +/- 0.88, N = 3SE +/- 59.24, N = 3SE +/- 141.43, N = 5SE +/- 262.30, N = 12SE +/- 204.28, N = 3SE +/- 2.09, N = 3SE +/- 21.01, N = 3SE +/- 87.89, N = 12SE +/- 23.56, N = 3SE +/- 32.87, N = 12SE +/- 195.28, N = 8SE +/- 6.18, N = 3SE +/- 19.36, N = 3SE +/- 4.15, N = 3SE +/- 75.19, N = 5SE +/- 54.27, N = 5SE +/- 60.72, N = 35826.445821.4612394.6012708.5014955.6014185.1012731.8011208.703375.323347.933406.964382.975172.965279.078088.117630.065062.076038.921. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp

Embree

Intel Embree is a collection of high-performance ray-tracing kernels for execution on CPUs (and GPUs via SYCL) and supporting instruction sets such as SSE, AVX, AVX2, and AVX-512. Embree also supports making use of the Intel SPMD Program Compiler (ISPC). Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 4.3Binary: Pathtracer ISPC - Model: Asian Dragon ObjEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P50100150200250SE +/- 0.04, N = 3SE +/- 0.04, N = 3SE +/- 0.02, N = 4SE +/- 1.58, N = 15SE +/- 0.11, N = 4SE +/- 1.72, N = 15SE +/- 0.07, N = 4SE +/- 3.26, N = 12SE +/- 0.03, N = 3SE +/- 0.22, N = 3SE +/- 0.09, N = 3SE +/- 0.09, N = 3SE +/- 0.08, N = 3SE +/- 0.76, N = 3SE +/- 0.09, N = 3SE +/- 0.89, N = 15SE +/- 0.03, N = 3SE +/- 0.10, N = 3SE +/- 0.09, N = 3SE +/- 0.22, N = 4SE +/- 0.35, N = 3SE +/- 0.29, N = 464.3363.34113.28175.60133.48210.44133.93200.1676.53125.1183.73136.2264.96104.8471.83112.7247.6484.8079.38132.2897.19173.22

Liquid-DSP

LiquidSDR's Liquid-DSP is a software-defined radio (SDR) digital signal processing library. This test profile runs a multi-threaded benchmark of this SDR/DSP library focused on embedded platform usage. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 1.6Threads: 256 - Buffer Length: 256 - Filter Length: 512EPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P500M1000M1500M2000M2500MSE +/- 776881.23, N = 3SE +/- 170391.71, N = 3SE +/- 520683.31, N = 3SE +/- 11753202.87, N = 3SE +/- 2676440.42, N = 3SE +/- 14870701.99, N = 3SE +/- 1300000.00, N = 3SE +/- 1650252.51, N = 3SE +/- 320537.74, N = 3SE +/- 2198737.01, N = 3SE +/- 409267.64, N = 3SE +/- 6411708.04, N = 3SE +/- 569766.03, N = 3SE +/- 4238841.56, N = 3SE +/- 740202.67, N = 3SE +/- 6728628.72, N = 3SE +/- 4629652.01, N = 3SE +/- 11053858.05, N = 3SE +/- 1722723.94, N = 3SE +/- 5630373.98, N = 3SE +/- 240370.09, N = 3SE +/- 14465476.14, N = 38210133337417400001362166667212953333315704000002394333333174470000017348000008483766671306733333940270000143710000083853000014440666679445500001518933333542606667106103333310208333331616966667117876666720270000001. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

ONNX Runtime

ONNX Runtime is developed by Microsoft and partners as a open-source, cross-platform, high performance machine learning inferencing and training accelerator. This test profile runs the ONNX Runtime with various models available from the ONNX Model Zoo. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.17Model: super-resolution-10 - Device: CPU - Executor: StandardEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P60120180240300SE +/- 0.30, N = 3SE +/- 0.30, N = 3SE +/- 0.67, N = 3SE +/- 0.61, N = 3SE +/- 0.58, N = 3SE +/- 2.15, N = 12SE +/- 0.26, N = 3SE +/- 2.46, N = 15SE +/- 0.31, N = 3SE +/- 0.27, N = 3SE +/- 0.32, N = 3SE +/- 0.60, N = 15SE +/- 0.09, N = 3SE +/- 2.30, N = 4SE +/- 0.25, N = 3SE +/- 1.02, N = 3SE +/- 1.75, N = 3SE +/- 6.83, N = 12SE +/- 0.16, N = 3SE +/- 4.15, N = 15SE +/- 0.03, N = 3SE +/- 3.39, N = 3106.53102.97122.6895.84122.95119.56106.1398.6459.3059.5066.2066.18217.88205.89213.99199.90197.85192.81227.42212.92259.19251.311. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

Liquid-DSP

LiquidSDR's Liquid-DSP is a software-defined radio (SDR) digital signal processing library. This test profile runs a multi-threaded benchmark of this SDR/DSP library focused on embedded platform usage. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 1.6Threads: 256 - Buffer Length: 256 - Filter Length: 32EPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P2000M4000M6000M8000M10000MSE +/- 1501110.70, N = 3SE +/- 1928730.15, N = 3SE +/- 1419311.26, N = 3SE +/- 46730658.51, N = 3SE +/- 11426625.83, N = 3SE +/- 34610274.65, N = 3SE +/- 3768731.00, N = 3SE +/- 2936551.27, N = 3SE +/- 821245.67, N = 3SE +/- 32054242.22, N = 3SE +/- 2601495.30, N = 3SE +/- 20501246.57, N = 3SE +/- 1320353.49, N = 3SE +/- 2447674.63, N = 3SE +/- 1338323.99, N = 3SE +/- 895048.11, N = 3SE +/- 1266666.67, N = 3SE +/- 7369833.41, N = 3SE +/- 4021608.30, N = 3SE +/- 10496401.50, N = 3SE +/- 2516611.48, N = 3SE +/- 6711433.03, N = 330622000002789600000527193333375133333335862466667793526666765882000006439000000430116666768215333334799133333754636666723818000004670966667276906666753670333331823566667357223333332438000006116566667316720000060773000001. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

ASTC Encoder

ASTC Encoder (astcenc) is for the Adaptive Scalable Texture Compression (ASTC) format commonly used with OpenGL, OpenGL ES, and Vulkan graphics APIs. This test profile does a coding test of both compression/decompression. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMT/s, More Is BetterASTC Encoder 4.7Preset: MediumEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P120240360480600SE +/- 0.07, N = 6SE +/- 0.07, N = 6SE +/- 0.20, N = 7SE +/- 3.54, N = 6SE +/- 0.63, N = 7SE +/- 3.11, N = 7SE +/- 0.39, N = 7SE +/- 0.52, N = 6SE +/- 0.18, N = 5SE +/- 1.77, N = 5SE +/- 0.13, N = 6SE +/- 2.01, N = 5SE +/- 0.03, N = 6SE +/- 0.52, N = 6SE +/- 0.08, N = 6SE +/- 0.77, N = 6SE +/- 0.32, N = 4SE +/- 2.26, N = 5SE +/- 0.16, N = 6SE +/- 2.79, N = 6SE +/- 1.17, N = 6SE +/- 1.56, N = 7294.62273.67449.11491.53500.77508.09527.80462.24284.46338.15314.62363.38247.30441.65284.33483.10126.44216.97333.99484.55327.78550.021. (CXX) g++ options: -O3 -flto -pthread

WRF

WRF, the Weather Research and Forecasting Model, is a "next-generation mesoscale numerical weather prediction system designed for both atmospheric research and operational forecasting applications. It features two dynamical cores, a data assimilation system, and a software architecture supporting parallel computation and system extensibility." Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterWRF 4.2.2Input: conus 2.5kmEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P4K8K12K16K20K16147.0016609.7810176.866918.027885.164431.3411895.417365.8613273.697157.9612410.296840.0618998.8214030.5111980.816674.1210602.415601.101. (F9X) gfortran options: -O2 -ftree-vectorize -funroll-loops -ffree-form -fconvert=big-endian -frecord-marker=4 -fallow-invalid-boz -lesmf_time -lwrfio_nf -lnetcdff -lnetcdf -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz

NAS Parallel Benchmarks

NPB, NAS Parallel Benchmarks, is a benchmark developed by NASA for high-end computer systems. This test profile currently uses the MPI version of NPB. This test profile offers selecting the different NPB tests/problems and varying problem sizes. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: MG.CEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P50K100K150K200K250KSE +/- 167.65, N = 8SE +/- 301.54, N = 8SE +/- 1153.71, N = 15SE +/- 2707.72, N = 14SE +/- 1372.89, N = 15SE +/- 7207.31, N = 15SE +/- 884.47, N = 9SE +/- 1776.37, N = 11SE +/- 436.97, N = 10SE +/- 1415.96, N = 9SE +/- 382.59, N = 10SE +/- 1298.67, N = 9SE +/- 53.56, N = 9SE +/- 233.83, N = 9SE +/- 152.92, N = 9SE +/- 1262.04, N = 9SE +/- 406.29, N = 9SE +/- 1422.07, N = 763930.6462449.55116725.04194942.32134994.14244738.81125567.07245447.7285910.95172614.1086407.46171436.4757317.66110742.1583448.70163333.21107321.89220893.781. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz 2. Open MPI 4.1.6

ONNX Runtime

ONNX Runtime is developed by Microsoft and partners as a open-source, cross-platform, high performance machine learning inferencing and training accelerator. This test profile runs the ONNX Runtime with various models available from the ONNX Model Zoo. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.17Model: GPT-2 - Device: CPU - Executor: ParallelEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P50100150200250SE +/- 0.64, N = 3SE +/- 0.43, N = 3SE +/- 0.08, N = 3SE +/- 0.35, N = 3SE +/- 0.64, N = 3SE +/- 0.48, N = 3SE +/- 0.17, N = 3SE +/- 0.19, N = 3SE +/- 0.09, N = 3SE +/- 0.40, N = 3SE +/- 0.23, N = 3SE +/- 0.04, N = 3SE +/- 1.04, N = 3SE +/- 1.53, N = 3SE +/- 2.63, N = 3SE +/- 0.26, N = 3SE +/- 0.64, N = 3SE +/- 1.59, N = 3SE +/- 0.53, N = 3SE +/- 0.78, N = 3SE +/- 0.27, N = 3SE +/- 0.81, N = 3128.98129.65156.61109.46161.50110.17137.1999.22131.5458.58140.0360.39191.11135.98188.93136.69180.23153.54191.56144.64248.68195.451. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

PyTorch

This is a benchmark of PyTorch making use of pytorch-benchmark [https://github.com/LukasHedegaard/pytorch-benchmark]. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.2.1Device: CPU - Batch Size: 1 - Model: ResNet-152EPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P612182430SE +/- 0.17, N = 3SE +/- 0.06, N = 3SE +/- 0.09, N = 3SE +/- 0.27, N = 9SE +/- 0.01, N = 3SE +/- 0.20, N = 12SE +/- 0.04, N = 3SE +/- 0.15, N = 12SE +/- 0.12, N = 3SE +/- 0.17, N = 9SE +/- 0.06, N = 3SE +/- 0.07, N = 3SE +/- 0.26, N = 3SE +/- 0.18, N = 3SE +/- 0.16, N = 3SE +/- 0.13, N = 8SE +/- 0.12, N = 3SE +/- 0.10, N = 3SE +/- 0.09, N = 3SE +/- 0.16, N = 4SE +/- 0.08, N = 3SE +/- 0.19, N = 515.2515.1115.578.2715.868.3513.056.6413.396.4714.537.1019.9917.9118.0714.8622.2716.6819.4115.7727.2117.57

LULESH

LULESH is the Livermore Unstructured Lagrangian Explicit Shock Hydrodynamics. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgz/s, More Is BetterLULESH 2.0.3EPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P15K30K45K60K75KSE +/- 372.63, N = 12SE +/- 373.78, N = 12SE +/- 372.12, N = 3SE +/- 349.39, N = 15SE +/- 194.65, N = 15SE +/- 675.87, N = 3SE +/- 244.17, N = 3SE +/- 427.75, N = 3SE +/- 254.25, N = 6SE +/- 55.60, N = 3SE +/- 314.85, N = 4SE +/- 91.45, N = 3SE +/- 211.12, N = 6SE +/- 206.20, N = 5SE +/- 217.67, N = 6SE +/- 207.54, N = 5SE +/- 53.94, N = 5SE +/- 188.07, N = 8SE +/- 182.38, N = 15SE +/- 272.44, N = 4SE +/- 437.51, N = 4SE +/- 359.29, N = 316949.5916855.8926082.7148760.8227287.2654678.4924218.8346126.0826024.6042946.2626864.1144136.5323848.5452102.6725831.8453269.4717348.4321389.8223072.3043724.0638433.9770826.731. (CXX) g++ options: -O3 -fopenmp -lm -lmpi_cxx -lmpi

Embree

Intel Embree is a collection of high-performance ray-tracing kernels for execution on CPUs (and GPUs via SYCL) and supporting instruction sets such as SSE, AVX, AVX2, and AVX-512. Embree also supports making use of the Intel SPMD Program Compiler (ISPC). Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 4.3Binary: Pathtracer ISPC - Model: Asian DragonEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P50100150200250SE +/- 0.03, N = 5SE +/- 0.05, N = 5SE +/- 0.03, N = 6SE +/- 1.54, N = 8SE +/- 0.07, N = 7SE +/- 2.04, N = 8SE +/- 0.12, N = 7SE +/- 1.88, N = 7SE +/- 0.04, N = 5SE +/- 0.10, N = 6SE +/- 0.05, N = 5SE +/- 0.16, N = 7SE +/- 0.04, N = 5SE +/- 0.63, N = 6SE +/- 0.11, N = 5SE +/- 1.20, N = 15SE +/- 0.04, N = 4SE +/- 0.29, N = 6SE +/- 0.05, N = 5SE +/- 0.13, N = 7SE +/- 0.13, N = 6SE +/- 0.26, N = 875.2173.91132.49185.71155.12231.43156.39208.3184.71138.8592.88151.2575.47125.7583.49129.7555.4299.2491.99152.75112.66199.61

ONNX Runtime

ONNX Runtime is developed by Microsoft and partners as a open-source, cross-platform, high performance machine learning inferencing and training accelerator. This test profile runs the ONNX Runtime with various models available from the ONNX Model Zoo. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.17Model: ResNet50 v1-12-int8 - Device: CPU - Executor: StandardEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P70140210280350SE +/- 2.24, N = 15SE +/- 2.40, N = 15SE +/- 4.35, N = 15SE +/- 3.84, N = 12SE +/- 0.95, N = 3SE +/- 3.21, N = 15SE +/- 2.12, N = 15SE +/- 1.44, N = 15SE +/- 1.47, N = 3SE +/- 0.44, N = 3SE +/- 0.67, N = 3SE +/- 0.05, N = 3SE +/- 2.40, N = 3SE +/- 2.72, N = 15SE +/- 3.31, N = 5SE +/- 1.78, N = 3SE +/- 1.65, N = 3SE +/- 0.64, N = 3SE +/- 1.80, N = 3SE +/- 1.01, N = 3SE +/- 2.52, N = 3SE +/- 0.40, N = 3219.06211.19225.31133.49243.34141.83160.90117.62130.0680.42143.3687.09330.10174.68296.80161.89335.15222.52315.41177.76314.06171.231. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

Kvazaar

This is a test of Kvazaar as a CPU-based H.265/HEVC video encoder written in the C programming language and optimized in Assembly. Kvazaar is the winner of the 2016 ACM Open-Source Software Competition and developed at the Ultra Video Group, Tampere University, Finland. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.2Video Input: Bosphorus 4K - Video Preset: SlowEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P1428425670SE +/- 0.04, N = 3SE +/- 0.05, N = 3SE +/- 0.01, N = 4SE +/- 0.50, N = 5SE +/- 0.07, N = 4SE +/- 0.26, N = 5SE +/- 0.05, N = 4SE +/- 0.47, N = 8SE +/- 0.07, N = 3SE +/- 0.09, N = 3SE +/- 0.07, N = 3SE +/- 0.18, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.00, N = 3SE +/- 0.05, N = 3SE +/- 0.03, N = 3SE +/- 0.08, N = 3SE +/- 0.07, N = 3SE +/- 0.04, N = 423.7122.4638.9061.0740.0062.8238.4754.8818.8629.1520.8731.8517.5226.0018.2428.9615.0919.7120.2331.2424.2340.921. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt

OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.2Video Input: Bosphorus 4K - Video Preset: MediumEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P1428425670SE +/- 0.05, N = 3SE +/- 0.03, N = 3SE +/- 0.07, N = 4SE +/- 0.56, N = 5SE +/- 0.01, N = 4SE +/- 0.40, N = 5SE +/- 0.04, N = 4SE +/- 0.52, N = 15SE +/- 0.00, N = 3SE +/- 0.21, N = 3SE +/- 0.01, N = 3SE +/- 0.23, N = 3SE +/- 0.04, N = 3SE +/- 0.08, N = 3SE +/- 0.02, N = 3SE +/- 0.07, N = 3SE +/- 0.01, N = 3SE +/- 0.03, N = 3SE +/- 0.02, N = 3SE +/- 0.06, N = 3SE +/- 0.03, N = 3SE +/- 0.27, N = 424.3123.0239.5861.1140.5063.4839.0854.5719.3429.1521.3931.7018.1326.6918.8429.6215.5120.3320.9732.0424.8041.581. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt

PyTorch

This is a benchmark of PyTorch making use of pytorch-benchmark [https://github.com/LukasHedegaard/pytorch-benchmark]. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.2.1Device: CPU - Batch Size: 256 - Model: ResNet-152EPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P612182430SE +/- 0.06, N = 3SE +/- 0.04, N = 3SE +/- 0.11, N = 3SE +/- 0.13, N = 9SE +/- 0.20, N = 3SE +/- 0.13, N = 9SE +/- 0.15, N = 3SE +/- 0.12, N = 9SE +/- 0.04, N = 3SE +/- 0.06, N = 9SE +/- 0.19, N = 3SE +/- 0.04, N = 3SE +/- 0.15, N = 3SE +/- 0.09, N = 3SE +/- 0.15, N = 3SE +/- 0.18, N = 4SE +/- 0.05, N = 3SE +/- 0.08, N = 3SE +/- 0.08, N = 3SE +/- 0.13, N = 7SE +/- 0.29, N = 3SE +/- 0.16, N = 313.2613.1813.957.1414.087.0211.015.7111.886.1113.646.6119.2016.3019.5814.9217.7014.8820.2514.0823.3316.00

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.2.1Device: CPU - Batch Size: 512 - Model: ResNet-152EPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P612182430SE +/- 0.11, N = 3SE +/- 0.09, N = 3SE +/- 0.18, N = 3SE +/- 0.14, N = 9SE +/- 0.12, N = 3SE +/- 0.13, N = 9SE +/- 0.02, N = 3SE +/- 0.11, N = 9SE +/- 0.14, N = 3SE +/- 0.07, N = 3SE +/- 0.19, N = 3SE +/- 0.07, N = 3SE +/- 0.18, N = 7SE +/- 0.09, N = 3SE +/- 0.18, N = 7SE +/- 0.16, N = 3SE +/- 0.13, N = 3SE +/- 0.17, N = 3SE +/- 0.04, N = 3SE +/- 0.09, N = 3SE +/- 0.16, N = 3SE +/- 0.18, N = 313.2813.2814.057.2013.957.0710.915.7511.746.3313.616.6519.4716.6819.2914.7417.5514.7620.4614.5923.4116.17

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.2.1Device: CPU - Batch Size: 64 - Model: ResNet-152EPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P612182430SE +/- 0.16, N = 3SE +/- 0.03, N = 3SE +/- 0.17, N = 3SE +/- 0.13, N = 9SE +/- 0.10, N = 3SE +/- 0.15, N = 9SE +/- 0.02, N = 3SE +/- 0.03, N = 3SE +/- 0.04, N = 3SE +/- 0.07, N = 3SE +/- 0.13, N = 3SE +/- 0.05, N = 3SE +/- 0.19, N = 5SE +/- 0.21, N = 3SE +/- 0.17, N = 12SE +/- 0.05, N = 3SE +/- 0.05, N = 3SE +/- 0.12, N = 3SE +/- 0.18, N = 3SE +/- 0.17, N = 3SE +/- 0.34, N = 3SE +/- 0.15, N = 1213.1913.1513.847.0413.897.0810.885.7911.956.1513.006.5919.0115.8419.2414.9617.7315.1120.1314.0323.4916.25

oneDNN

This is a test of the Intel oneDNN as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Intel oneDNN was formerly known as DNNL (Deep Neural Network Library) and MKL-DNN before being rebranded as part of the Intel oneAPI toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.4Harness: Deconvolution Batch shapes_3d - Engine: CPUEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P0.56191.12381.68572.24762.8095SE +/- 0.000791, N = 9SE +/- 0.001685, N = 9SE +/- 0.001484, N = 9SE +/- 0.001921, N = 9SE +/- 0.001272, N = 9SE +/- 0.002070, N = 9SE +/- 0.001089, N = 9SE +/- 0.003127, N = 9SE +/- 0.001097, N = 9SE +/- 0.001467, N = 9SE +/- 0.002181, N = 9SE +/- 0.001365, N = 9SE +/- 0.000508, N = 9SE +/- 0.000806, N = 9SE +/- 0.000927, N = 9SE +/- 0.001240, N = 9SE +/- 0.006599, N = 9SE +/- 0.001091, N = 9SE +/- 0.000805, N = 9SE +/- 0.001274, N = 9SE +/- 0.000392, N = 9SE +/- 0.000902, N = 91.4983501.7974901.1548701.0094731.1192301.0019140.9436210.8296532.2971202.4973402.0491002.2452601.2640700.9450751.1964300.8643581.4221300.8670651.0774300.7361700.9071610.6242501. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread

OpenVINO

This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Noise Suppression Poconet-Like FP16 - Device: CPUEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P70140210280350SE +/- 0.00, N = 3SE +/- 0.02, N = 3SE +/- 0.16, N = 14SE +/- 0.08, N = 3SE +/- 0.00, N = 3SE +/- 0.04, N = 3SE +/- 0.45, N = 12SE +/- 0.10, N = 3SE +/- 0.66, N = 3SE +/- 4.48, N = 3SE +/- 0.65, N = 3SE +/- 0.86, N = 3SE +/- 0.04, N = 3SE +/- 0.12, N = 3SE +/- 0.02, N = 3SE +/- 0.09, N = 3SE +/- 0.03, N = 3SE +/- 0.07, N = 3SE +/- 0.00, N = 3SE +/- 0.05, N = 3SE +/- 0.01, N = 3SE +/- 0.04, N = 317.3018.4916.3223.1213.5222.2022.6728.1082.12340.2675.22293.3611.3717.1512.7218.7225.9126.3313.9515.969.4013.151. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

uvg266

uvg266 is an open-source VVC/H.266 (Versatile Video Coding) encoder based on Kvazaar as part of the Ultra Video Group, Tampere University, Finland. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is Betteruvg266 0.4.1Video Input: Bosphorus 4K - Video Preset: SlowEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P1020304050SE +/- 0.04, N = 3SE +/- 0.02, N = 3SE +/- 0.04, N = 3SE +/- 0.21, N = 4SE +/- 0.04, N = 3SE +/- 0.12, N = 4SE +/- 0.04, N = 3SE +/- 0.23, N = 4SE +/- 0.04, N = 3SE +/- 0.02, N = 3SE +/- 0.03, N = 3SE +/- 0.18, N = 3SE +/- 0.02, N = 3SE +/- 0.04, N = 3SE +/- 0.01, N = 3SE +/- 0.04, N = 3SE +/- 0.01, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.04, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 317.0415.7728.0140.9629.1843.3929.0037.1313.7720.4615.2421.6313.3619.7513.8922.1410.9313.7915.7124.7116.0627.11

ONNX Runtime

ONNX Runtime is developed by Microsoft and partners as a open-source, cross-platform, high performance machine learning inferencing and training accelerator. This test profile runs the ONNX Runtime with various models available from the ONNX Model Zoo. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.17Model: super-resolution-10 - Device: CPU - Executor: ParallelEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P50100150200250SE +/- 0.54, N = 3SE +/- 0.72, N = 3SE +/- 0.36, N = 3SE +/- 0.53, N = 3SE +/- 0.99, N = 3SE +/- 0.41, N = 3SE +/- 0.26, N = 3SE +/- 0.83, N = 3SE +/- 0.04, N = 3SE +/- 0.23, N = 3SE +/- 0.04, N = 3SE +/- 0.11, N = 3SE +/- 0.98, N = 3SE +/- 1.17, N = 3SE +/- 0.61, N = 3SE +/- 0.62, N = 3SE +/- 0.40, N = 3SE +/- 0.90, N = 3SE +/- 2.34, N = 3SE +/- 0.74, N = 3SE +/- 1.98, N = 3SE +/- 1.38, N = 397.0596.17110.0086.92108.8787.2694.7478.0769.0760.2975.8765.43195.71173.91190.06169.85176.29178.62205.53188.89234.54214.811. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.17Model: fcn-resnet101-11 - Device: CPU - Executor: ParallelEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P0.74441.48882.23322.97763.722SE +/- 0.023203, N = 3SE +/- 0.018603, N = 15SE +/- 0.013875, N = 12SE +/- 0.016597, N = 12SE +/- 0.020352, N = 15SE +/- 0.001170, N = 3SE +/- 0.018814, N = 3SE +/- 0.034519, N = 3SE +/- 0.001935, N = 3SE +/- 0.016386, N = 15SE +/- 0.002384, N = 3SE +/- 0.009611, N = 3SE +/- 0.011894, N = 3SE +/- 0.027020, N = 13SE +/- 0.015170, N = 3SE +/- 0.026516, N = 3SE +/- 0.019473, N = 3SE +/- 0.019617, N = 15SE +/- 0.008707, N = 3SE +/- 0.007683, N = 3SE +/- 0.008053, N = 3SE +/- 0.038257, N = 32.5727802.2545301.2513500.9170431.2517900.8576853.1315602.5170901.7780901.6467401.9414401.7036502.6254402.1746302.6172102.1048002.7524202.8925303.0392202.8349803.3083603.0508501. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

Aircrack-ng

Aircrack-ng is a tool for assessing WiFi/WLAN network security. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgk/s, More Is BetterAircrack-ng 1.7EPYC 8534PEPYC 8534PNEPYC 9654EPYC 9684XEPYC 9754Xeon 6766EXeon 6780EXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P40K80K120K160K200KSE +/- 338.71, N = 3SE +/- 319.60, N = 3SE +/- 207.11, N = 3SE +/- 1622.56, N = 3SE +/- 714.86, N = 3SE +/- 1379.58, N = 4SE +/- 888.98, N = 3SE +/- 36.42, N = 3SE +/- 1027.07, N = 15SE +/- 122.31, N = 3SE +/- 1131.21, N = 15SE +/- 728.55, N = 3SE +/- 1234.47, N = 15SE +/- 1953.08, N = 3SE +/- 1197.41, N = 15SE +/- 840.59, N = 3SE +/- 773.70, N = 3153818.03141831.78186675.43206619.29177989.89114715.79116716.40117588.9983665.76134048.9665663.82101665.47159709.75147469.3353914.93153584.2064181.291. (CXX) g++ options: -std=gnu++17 -O3 -fvisibility=hidden -fcommon -rdynamic -lnl-3 -lnl-genl-3 -lpcre -lsqlite3 -lpthread -lz -lssl -lcrypto -lhwloc -ldl -lm -pthread

EPYC 9684X 2P: The test run did not produce a result.

EPYC 9654 2P: The test run did not produce a result.

EPYC 9754 2P: The test run did not produce a result.

Xeon 6766E 2P: The test run did not produce a result.

Xeon 6780E 2P: The test run did not produce a result.

OpenVINO

This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Face Detection Retail FP16-INT8 - Device: CPUEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P510152025SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.02, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 36.777.605.855.985.415.346.256.6018.2019.2316.4116.985.275.555.776.026.565.936.435.725.195.181. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

Timed Node.js Compilation

This test profile times how long it takes to build/compile Node.js itself from source. Node.js is a JavaScript run-time built from the Chrome V8 JavaScript engine while itself is written in C/C++. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Node.js Compilation 21.7.2Time To CompileEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P90180270360450SE +/- 0.17, N = 3SE +/- 0.19, N = 3SE +/- 0.59, N = 3SE +/- 0.18, N = 3SE +/- 0.50, N = 3SE +/- 1.19, N = 3SE +/- 0.72, N = 3SE +/- 1.51, N = 3SE +/- 0.15, N = 3SE +/- 1.20, N = 3SE +/- 0.51, N = 3SE +/- 0.60, N = 3SE +/- 0.53, N = 3SE +/- 0.84, N = 3SE +/- 0.74, N = 3SE +/- 0.52, N = 3SE +/- 0.22, N = 3SE +/- 0.68, N = 3SE +/- 0.71, N = 3SE +/- 0.48, N = 3SE +/- 0.52, N = 3SE +/- 0.12, N = 3277.53288.12164.02118.90147.84114.91186.10147.74246.85187.65228.57173.09270.38175.63252.65171.17423.63303.42254.00172.99214.43145.41

ONNX Runtime

ONNX Runtime is developed by Microsoft and partners as a open-source, cross-platform, high performance machine learning inferencing and training accelerator. This test profile runs the ONNX Runtime with various models available from the ONNX Model Zoo. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.17Model: T5 Encoder - Device: CPU - Executor: StandardEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P100200300400500SE +/- 0.98, N = 13SE +/- 0.54, N = 3SE +/- 1.08, N = 3SE +/- 1.86, N = 3SE +/- 1.35, N = 3SE +/- 4.17, N = 15SE +/- 1.16, N = 3SE +/- 1.15, N = 3SE +/- 0.35, N = 3SE +/- 11.98, N = 15SE +/- 0.17, N = 3SE +/- 1.00, N = 3SE +/- 3.95, N = 15SE +/- 1.31, N = 3SE +/- 0.51, N = 3SE +/- 0.89, N = 3SE +/- 2.62, N = 15SE +/- 4.93, N = 15SE +/- 0.84, N = 3SE +/- 0.26, N = 3SE +/- 1.00, N = 3SE +/- 3.01, N = 3127.09127.21187.01167.11279.64263.52131.00127.54207.94178.11217.45210.37219.53199.08215.13185.46298.67292.52357.36288.47460.78356.761. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

uvg266

uvg266 is an open-source VVC/H.266 (Versatile Video Coding) encoder based on Kvazaar as part of the Ultra Video Group, Tampere University, Finland. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is Betteruvg266 0.4.1Video Input: Bosphorus 4K - Video Preset: MediumEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P1020304050SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.23, N = 4SE +/- 0.03, N = 3SE +/- 0.46, N = 4SE +/- 0.05, N = 3SE +/- 0.28, N = 11SE +/- 0.01, N = 3SE +/- 0.23, N = 5SE +/- 0.01, N = 3SE +/- 0.16, N = 15SE +/- 0.02, N = 3SE +/- 0.03, N = 3SE +/- 0.02, N = 3SE +/- 0.03, N = 3SE +/- 0.00, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.04, N = 3SE +/- 0.16, N = 3SE +/- 0.05, N = 319.2517.8031.4442.0332.7445.2632.4438.1215.6522.0317.2922.5915.1722.2515.6824.6512.5616.1917.8527.6516.6430.37

ONNX Runtime

ONNX Runtime is developed by Microsoft and partners as a open-source, cross-platform, high performance machine learning inferencing and training accelerator. This test profile runs the ONNX Runtime with various models available from the ONNX Model Zoo. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.17Model: yolov4 - Device: CPU - Executor: StandardEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P612182430SE +/- 0.10588, N = 4SE +/- 0.09781, N = 5SE +/- 0.08554, N = 8SE +/- 0.04207, N = 3SE +/- 0.12519, N = 3SE +/- 0.08454, N = 3SE +/- 0.05314, N = 3SE +/- 0.09575, N = 3SE +/- 0.05969, N = 3SE +/- 0.06011, N = 3SE +/- 0.09768, N = 3SE +/- 0.01654, N = 3SE +/- 0.16821, N = 15SE +/- 0.29451, N = 15SE +/- 0.15263, N = 15SE +/- 0.09595, N = 14SE +/- 0.15605, N = 3SE +/- 0.06818, N = 3SE +/- 0.04802, N = 3SE +/- 0.06825, N = 3SE +/- 0.05084, N = 3SE +/- 0.09991, N = 38.874468.752339.860186.412299.736857.248698.295336.7497712.701507.4994013.829508.1461518.2179014.4831016.9166014.4583020.2495016.4123019.8593015.5555022.9689016.967201. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

Timed Linux Kernel Compilation

This test times how long it takes to build the Linux kernel in a default configuration (defconfig) for the architecture being tested or alternatively an allmodconfig for building all possible kernel modules for the build. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Linux Kernel Compilation 6.8Build: allmodconfigEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P130260390520650SE +/- 0.91, N = 3SE +/- 0.78, N = 3SE +/- 0.49, N = 3SE +/- 0.49, N = 3SE +/- 0.37, N = 3SE +/- 0.98, N = 3SE +/- 1.05, N = 3SE +/- 1.31, N = 3SE +/- 0.76, N = 3SE +/- 0.81, N = 3SE +/- 0.67, N = 3SE +/- 0.90, N = 3SE +/- 0.61, N = 3SE +/- 0.56, N = 3SE +/- 0.67, N = 3SE +/- 0.73, N = 3SE +/- 0.35, N = 3SE +/- 0.92, N = 3SE +/- 0.80, N = 3SE +/- 0.86, N = 3SE +/- 0.72, N = 3SE +/- 0.56, N = 3406.41438.17311.83197.63290.34182.00337.69210.20274.86192.10251.20174.27428.39246.94384.06231.03612.78356.99362.45218.57316.90189.74

TensorFlow

This is a benchmark of the TensorFlow deep learning framework using the TensorFlow reference benchmarks (tensorflow/benchmarks with tf_cnn_benchmarks.py). Note with the Phoronix Test Suite there is also pts/tensorflow-lite for benchmarking the TensorFlow Lite binaries if desired for complementary metrics. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.16.1Device: CPU - Batch Size: 1 - Model: AlexNetEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P1326395265SE +/- 0.05, N = 7SE +/- 0.04, N = 7SE +/- 0.18, N = 7SE +/- 0.17, N = 15SE +/- 0.07, N = 7SE +/- 0.10, N = 6SE +/- 0.48, N = 15SE +/- 0.15, N = 9SE +/- 0.07, N = 6SE +/- 0.12, N = 15SE +/- 0.08, N = 7SE +/- 0.19, N = 5SE +/- 0.76, N = 15SE +/- 0.57, N = 15SE +/- 1.22, N = 15SE +/- 0.52, N = 15SE +/- 0.05, N = 7SE +/- 0.33, N = 15SE +/- 0.08, N = 8SE +/- 0.44, N = 15SE +/- 0.66, N = 15SE +/- 0.45, N = 1534.5134.3532.5619.8826.2319.9235.0818.5929.5616.2431.9918.3448.2837.7643.6733.2142.0537.2656.5337.5735.5030.76

OpenVINO

This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Face Detection FP16-INT8 - Device: CPUEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P160320480640800SE +/- 0.18, N = 3SE +/- 0.12, N = 3SE +/- 0.07, N = 3SE +/- 0.02, N = 3SE +/- 0.43, N = 3SE +/- 0.43, N = 3SE +/- 0.18, N = 3SE +/- 0.03, N = 3SE +/- 0.99, N = 3SE +/- 1.58, N = 3SE +/- 1.47, N = 3SE +/- 1.63, N = 3SE +/- 0.15, N = 3SE +/- 0.40, N = 3SE +/- 0.47, N = 3SE +/- 0.35, N = 3SE +/- 3.13, N = 3SE +/- 0.22, N = 3SE +/- 0.28, N = 3SE +/- 0.00, N = 3SE +/- 0.69, N = 3SE +/- 0.33, N = 3592.22654.83510.10253.63471.98233.63551.07275.53692.79719.83618.97630.23236.52256.63257.50278.52415.89207.84356.38283.11224.64234.241. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

Xcompact3d Incompact3d

Xcompact3d Incompact3d is a Fortran-MPI based, finite difference high-performance code for solving the incompressible Navier-Stokes equation and as many as you need scalar transport equations. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterXcompact3d Incompact3d 2021-03-11Input: X3D-benchmarking input.i3dEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P120240360480600SE +/- 0.92, N = 3SE +/- 0.22, N = 3SE +/- 4.73, N = 3SE +/- 3.26, N = 9SE +/- 3.06, N = 9SE +/- 2.20, N = 12SE +/- 5.39, N = 3SE +/- 9.13, N = 9SE +/- 1.25, N = 3SE +/- 0.04, N = 3SE +/- 0.14, N = 3SE +/- 0.01, N = 3SE +/- 0.13, N = 3SE +/- 1.19, N = 3SE +/- 3.88, N = 4SE +/- 0.05, N = 3SE +/- 2.51, N = 3SE +/- 0.37, N = 3567.29568.25466.55248.87309.85167.13534.06253.32407.59189.69351.64187.22558.38292.03357.01196.81323.25171.381. (F9X) gfortran options: -cpp -O2 -funroll-loops -floop-optimize -fcray-pointer -fbacktrace -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz

High Performance Conjugate Gradient

HPCG is the High Performance Conjugate Gradient and is a new scientific benchmark from Sandia National Lans focused for super-computer testing with modern real-world workloads compared to HPCC. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGFLOP/s, More Is BetterHigh Performance Conjugate Gradient 3.1X Y Z: 144 144 144 - RT: 60EPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P1530456075SE +/- 0.03, N = 3SE +/- 0.02, N = 3SE +/- 0.05, N = 3SE +/- 0.05, N = 3SE +/- 0.28, N = 5SE +/- 0.51, N = 3SE +/- 0.04, N = 3SE +/- 0.02, N = 3SE +/- 0.08, N = 3SE +/- 0.29, N = 3SE +/- 0.37, N = 3SE +/- 0.07, N = 3SE +/- 0.01, N = 3SE +/- 0.34, N = 9SE +/- 0.02, N = 3SE +/- 0.03, N = 3SE +/- 0.08, N = 3SE +/- 0.94, N = 322.2022.1328.3242.5227.5844.9523.6341.8725.2454.4130.5962.6420.4130.1131.0760.8535.1469.301. (CXX) g++ options: -O3 -ffast-math -ftree-vectorize -lmpi_cxx -lmpi

Timed LLVM Compilation

This test times how long it takes to compile/build the LLVM compiler stack. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed LLVM Compilation 16.0Build System: NinjaEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P60120180240300SE +/- 0.20, N = 3SE +/- 0.10, N = 3SE +/- 0.31, N = 3SE +/- 0.08, N = 3SE +/- 0.27, N = 3SE +/- 0.09, N = 3SE +/- 0.74, N = 3SE +/- 0.45, N = 3SE +/- 0.20, N = 3SE +/- 1.52, N = 3SE +/- 0.06, N = 3SE +/- 0.05, N = 3SE +/- 0.19, N = 3SE +/- 0.17, N = 3SE +/- 0.36, N = 3SE +/- 0.79, N = 3SE +/- 1.03, N = 3SE +/- 0.37, N = 3SE +/- 0.07, N = 3SE +/- 0.15, N = 3SE +/- 0.12, N = 3SE +/- 0.27, N = 3205.01215.93135.6794.81124.4689.28146.76101.56184.20138.57169.45125.27212.48134.42197.84128.07298.41194.38187.02122.31165.05106.82

GraphicsMagick

This is a test of GraphicsMagick with its OpenMP implementation that performs various imaging tests on a sample high resolution (currently 15400 x 6940) JPEG image. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.43Operation: EnhancedEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P90180270360450SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.33, N = 3SE +/- 1.20, N = 3SE +/- 0.67, N = 3SE +/- 0.33, N = 3SE +/- 0.33, N = 3SE +/- 0.33, N = 3SE +/- 0.00, N = 3SE +/- 0.33, N = 3SE +/- 0.33, N = 3SE +/- 1.53, N = 3SE +/- 0.00, N = 3SE +/- 2.60, N = 3SE +/- 0.00, N = 3SE +/- 1.00, N = 3SE +/- 0.00, N = 3SE +/- 1.45, N = 3SE +/- 0.00, N = 3SE +/- 0.33, N = 3SE +/- 0.00, N = 3SE +/- 1.15, N = 31721632643683004083044032703502993891602691813011232152163422283741. (CC) gcc options: -fopenmp -O2 -ltiff -ljbig -lsharpyuv -lwebp -lwebpmux -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -lxml2 -lzstd -llzma -lbz2 -lz -lm -lpthread -lgomp

OpenFOAM

OpenFOAM is the leading free, open-source software for computational fluid dynamics (CFD). This test profile currently uses the drivaerFastback test case for analyzing automotive aerodynamics or alternatively the older motorBike input. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterOpenFOAM 10Input: drivaerFastback, Small Mesh Size - Execution TimeEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P2040608010058.1759.2732.5925.0128.3322.7133.8124.5745.9528.9941.7527.5874.9640.2942.2228.5633.0723.561. (CXX) g++ options: -std=c++14 -m64 -O3 -ftemplate-depth-100 -fPIC -fuse-ld=bfd -Xlinker --add-needed --no-as-needed -lfiniteVolume -lmeshTools -lparallel -llagrangian -lregionModels -lgenericPatchFields -lOpenFOAM -ldl -lm

ONNX Runtime

ONNX Runtime is developed by Microsoft and partners as a open-source, cross-platform, high performance machine learning inferencing and training accelerator. This test profile runs the ONNX Runtime with various models available from the ONNX Model Zoo. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.17Model: CaffeNet 12-int8 - Device: CPU - Executor: StandardEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P2004006008001000SE +/- 4.84, N = 4SE +/- 6.13, N = 3SE +/- 9.50, N = 15SE +/- 4.37, N = 15SE +/- 6.60, N = 3SE +/- 7.76, N = 15SE +/- 2.19, N = 3SE +/- 2.36, N = 11SE +/- 0.67, N = 3SE +/- 0.86, N = 3SE +/- 0.28, N = 3SE +/- 3.37, N = 3SE +/- 12.91, N = 15SE +/- 1.83, N = 3SE +/- 7.34, N = 3SE +/- 6.21, N = 5SE +/- 1.66, N = 3SE +/- 10.46, N = 15SE +/- 11.46, N = 3SE +/- 6.50, N = 15SE +/- 2.43, N = 3SE +/- 8.88, N = 3443.06446.69604.05444.85672.92446.81382.10316.11445.62276.24482.21292.79728.47604.76705.61581.77849.56701.72852.33696.98908.19754.811. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

7-Zip Compression

This is a test of 7-Zip compression/decompression with its integrated benchmark feature. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMIPS, More Is Better7-Zip Compression 22.01Test: Compression RatingEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P170K340K510K680K850KSE +/- 268.94, N = 3SE +/- 206.69, N = 3SE +/- 719.89, N = 3SE +/- 6869.20, N = 3SE +/- 1520.59, N = 3SE +/- 3075.95, N = 3SE +/- 1188.96, N = 3SE +/- 2500.52, N = 3SE +/- 610.46, N = 3SE +/- 7384.79, N = 3SE +/- 933.46, N = 3SE +/- 1102.28, N = 3SE +/- 1836.55, N = 3SE +/- 5127.15, N = 3SE +/- 2258.81, N = 3SE +/- 3924.87, N = 3SE +/- 248.73, N = 3SE +/- 1785.84, N = 3SE +/- 1535.53, N = 3SE +/- 4200.62, N = 3SE +/- 1982.97, N = 3SE +/- 709.87, N = 33313573190945495007617345791127413665754407769684138515918354380486112003147164917293423635255142437323917193881905927294416366742391. (CXX) g++ options: -lpthread -ldl -O2 -fPIC

Parallel BZIP2 Compression

This test measures the time needed to compress a file (FreeBSD-13.0-RELEASE-amd64-memstick.img) using Parallel BZIP2 compression. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterParallel BZIP2 Compression 1.1.13FreeBSD-13.0-RELEASE-amd64-memstick.img CompressionEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P0.76351.5272.29053.0543.8175SE +/- 0.023387, N = 15SE +/- 0.016947, N = 15SE +/- 0.014512, N = 15SE +/- 0.019468, N = 15SE +/- 0.015384, N = 15SE +/- 0.015217, N = 15SE +/- 0.010826, N = 15SE +/- 0.012053, N = 15SE +/- 0.012826, N = 10SE +/- 0.015355, N = 15SE +/- 0.014326, N = 10SE +/- 0.015943, N = 15SE +/- 0.023295, N = 15SE +/- 0.030907, N = 15SE +/- 0.020941, N = 15SE +/- 0.028863, N = 15SE +/- 0.048155, N = 15SE +/- 0.026496, N = 15SE +/- 0.007749, N = 10SE +/- 0.017240, N = 15SE +/- 0.023842, N = 15SE +/- 0.024402, N = 152.2004972.3211951.4229541.1263291.3690631.1094461.3557371.0683982.5046211.8576422.2799711.7180222.6320771.9829322.2877661.7112963.3931892.1814552.1448571.4692101.8475371.4323621. (CXX) g++ options: -O2 -pthread -lbz2 -lpthread

GPAW

GPAW is a density-functional theory (DFT) Python code based on the projector-augmented wave (PAW) method and the atomic simulation environment (ASE). Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterGPAW 23.6Input: Carbon NanotubeEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P20406080100SE +/- 0.07, N = 3SE +/- 0.01, N = 3SE +/- 0.21, N = 3SE +/- 0.29, N = 15SE +/- 0.11, N = 3SE +/- 0.30, N = 15SE +/- 0.14, N = 3SE +/- 0.18, N = 3SE +/- 0.03, N = 3SE +/- 0.08, N = 3SE +/- 0.08, N = 3SE +/- 0.27, N = 3SE +/- 0.12, N = 3SE +/- 0.60, N = 3SE +/- 0.24, N = 3SE +/- 0.55, N = 3SE +/- 0.12, N = 3SE +/- 0.10, N = 363.8066.7134.8725.8430.0024.1333.1227.1554.3842.8748.4943.9176.1848.4547.7841.5643.0538.051. (CC) gcc options: -shared -lxc -lblas -lmpi

ONNX Runtime

ONNX Runtime is developed by Microsoft and partners as a open-source, cross-platform, high performance machine learning inferencing and training accelerator. This test profile runs the ONNX Runtime with various models available from the ONNX Model Zoo. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.17Model: GPT-2 - Device: CPU - Executor: StandardEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P60120180240300SE +/- 0.28, N = 3SE +/- 0.63, N = 3SE +/- 1.37, N = 5SE +/- 0.13, N = 3SE +/- 0.70, N = 3SE +/- 0.46, N = 3SE +/- 0.15, N = 3SE +/- 1.43, N = 15SE +/- 0.47, N = 3SE +/- 0.47, N = 3SE +/- 0.44, N = 3SE +/- 8.91, N = 15SE +/- 2.01, N = 15SE +/- 0.58, N = 3SE +/- 1.88, N = 3SE +/- 1.08, N = 3SE +/- 1.97, N = 3SE +/- 3.16, N = 15SE +/- 1.50, N = 3SE +/- 1.05, N = 3SE +/- 1.19, N = 3SE +/- 8.14, N = 1589.2188.57126.82102.57162.09161.9589.7486.69139.45136.39148.11103.89176.33141.95168.86132.71207.93194.15222.03180.03270.33236.651. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenVINO

This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPUEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P40K80K120K160K200KSE +/- 86.99, N = 3SE +/- 55.52, N = 3SE +/- 205.87, N = 3SE +/- 1922.38, N = 15SE +/- 162.47, N = 3SE +/- 1640.61, N = 7SE +/- 89.35, N = 3SE +/- 1374.23, N = 9SE +/- 68.06, N = 3SE +/- 1048.23, N = 3SE +/- 100.17, N = 3SE +/- 1067.91, N = 3SE +/- 383.22, N = 3SE +/- 18.38, N = 3SE +/- 1761.33, N = 3SE +/- 1422.88, N = 15SE +/- 95.54, N = 3SE +/- 696.52, N = 3SE +/- 75.30, N = 3SE +/- 2494.14, N = 3SE +/- 988.12, N = 3SE +/- 1158.60, N = 387511.1178334.92133779.62172688.50138605.52178488.03132973.43166151.4284584.1375761.5091273.0276895.29135075.07174862.56140144.01176900.3261956.93151627.42115106.30189893.3181279.79128566.811. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

Liquid-DSP

LiquidSDR's Liquid-DSP is a software-defined radio (SDR) digital signal processing library. This test profile runs a multi-threaded benchmark of this SDR/DSP library focused on embedded platform usage. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 1.6Threads: 128 - Buffer Length: 256 - Filter Length: 57EPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P1000M2000M3000M4000M5000MSE +/- 3527510.93, N = 3SE +/- 6398003.16, N = 3SE +/- 20120967.50, N = 3SE +/- 4098915.85, N = 3SE +/- 6778479.02, N = 3SE +/- 11892621.43, N = 3SE +/- 18691531.06, N = 3SE +/- 14606429.33, N = 3SE +/- 6887912.12, N = 3SE +/- 2709448.49, N = 3SE +/- 1909915.65, N = 3SE +/- 13354940.83, N = 3SE +/- 2030052.00, N = 3SE +/- 25888414.40, N = 3SE +/- 3119294.79, N = 3SE +/- 14772609.79, N = 3SE +/- 1549551.91, N = 3SE +/- 11686221.71, N = 3SE +/- 3116800.35, N = 3SE +/- 13655808.69, N = 3SE +/- 5260228.13, N = 3SE +/- 51282832.98, N = 429828000002687066667425630000042809333334755333333475936666747145000004626566667373630000037121333334136766667406866666726700333333596400000297240000038965000001554666667268903333331812666673723666667350320000044505250001. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

Intel Open Image Denoise

Open Image Denoise is a denoising library for ray-tracing and part of the Intel oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgImages / Sec, More Is BetterIntel Open Image Denoise 2.2Run: RT.ldr_alb_nrm.3840x2160 - Device: CPU-OnlyEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P1.14532.29063.43594.58125.7265SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 4SE +/- 0.01, N = 5SE +/- 0.02, N = 4SE +/- 0.00, N = 5SE +/- 0.03, N = 6SE +/- 0.01, N = 5SE +/- 0.00, N = 4SE +/- 0.01, N = 4SE +/- 0.00, N = 4SE +/- 0.00, N = 5SE +/- 0.00, N = 4SE +/- 0.02, N = 5SE +/- 0.00, N = 4SE +/- 0.02, N = 5SE +/- 0.00, N = 3SE +/- 0.00, N = 5SE +/- 0.00, N = 4SE +/- 0.01, N = 6SE +/- 0.00, N = 5SE +/- 0.03, N = 61.801.692.733.492.663.473.163.571.932.972.113.312.273.492.393.661.813.102.714.483.325.09

TensorFlow

This is a benchmark of the TensorFlow deep learning framework using the TensorFlow reference benchmarks (tensorflow/benchmarks with tf_cnn_benchmarks.py). Note with the Phoronix Test Suite there is also pts/tensorflow-lite for benchmarking the TensorFlow Lite binaries if desired for complementary metrics. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.16.1Device: CPU - Batch Size: 512 - Model: AlexNetEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P400800120016002000SE +/- 0.35, N = 3SE +/- 0.57, N = 3SE +/- 0.67, N = 3SE +/- 12.71, N = 3SE +/- 0.49, N = 3SE +/- 23.15, N = 4SE +/- 4.07, N = 3SE +/- 7.97, N = 3SE +/- 2.03, N = 3SE +/- 20.10, N = 12SE +/- 0.86, N = 3SE +/- 38.99, N = 12SE +/- 3.89, N = 3SE +/- 17.88, N = 4SE +/- 5.13, N = 3SE +/- 8.55, N = 3SE +/- 1.47, N = 3SE +/- 5.91, N = 3SE +/- 0.51, N = 3SE +/- 18.52, N = 3SE +/- 1.84, N = 3SE +/- 19.23, N = 3875.23796.821363.331862.791392.911897.641620.531876.66677.40979.89732.791064.181047.961604.111108.951677.62883.001470.461278.451899.641486.122039.63

Intel Open Image Denoise

Open Image Denoise is a denoising library for ray-tracing and part of the Intel oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgImages / Sec, More Is BetterIntel Open Image Denoise 2.2Run: RTLightmap.hdr.4096x4096 - Device: CPU-OnlyEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P0.541.081.622.162.7SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.02, N = 4SE +/- 0.00, N = 3SE +/- 0.02, N = 3SE +/- 0.00, N = 3SE +/- 0.02, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 4SE +/- 0.00, N = 3SE +/- 0.01, N = 40.860.801.311.671.281.641.501.710.981.511.071.681.081.721.141.740.861.481.292.181.582.40

Liquid-DSP

LiquidSDR's Liquid-DSP is a software-defined radio (SDR) digital signal processing library. This test profile runs a multi-threaded benchmark of this SDR/DSP library focused on embedded platform usage. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 1.6Threads: 1 - Buffer Length: 256 - Filter Length: 512EPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P4M8M12M16M20MSE +/- 3464.10, N = 3SE +/- 31571.79, N = 3SE +/- 121304.48, N = 3SE +/- 124115.99, N = 3SE +/- 134727.30, N = 3SE +/- 234395.65, N = 15SE +/- 120841.84, N = 4SE +/- 11050.39, N = 3SE +/- 115.47, N = 3SE +/- 33.33, N = 3SE +/- 88.19, N = 3SE +/- 133.33, N = 3SE +/- 5238.74, N = 3SE +/- 17457.89, N = 3SE +/- 30179.10, N = 3SE +/- 7571.88, N = 3SE +/- 18478.22, N = 3SE +/- 11150.49, N = 3SE +/- 8685.88, N = 3SE +/- 38670.98, N = 3SE +/- 9492.69, N = 3SE +/- 162096.41, N = 1511290000112363331339466713390667133873331308313311174500112736676284300628076769839336969967169063331690466716885333168840001360833313599000168823331684333318774333182005331. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

Intel Open Image Denoise

Open Image Denoise is a denoising library for ray-tracing and part of the Intel oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgImages / Sec, More Is BetterIntel Open Image Denoise 2.2Run: RT.hdr_alb_nrm.3840x2160 - Device: CPU-OnlyEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P1.13182.26363.39544.52725.659SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 4SE +/- 0.01, N = 5SE +/- 0.00, N = 4SE +/- 0.00, N = 5SE +/- 0.02, N = 5SE +/- 0.01, N = 5SE +/- 0.00, N = 4SE +/- 0.00, N = 4SE +/- 0.00, N = 4SE +/- 0.03, N = 5SE +/- 0.00, N = 4SE +/- 0.01, N = 5SE +/- 0.00, N = 4SE +/- 0.04, N = 5SE +/- 0.00, N = 3SE +/- 0.01, N = 5SE +/- 0.00, N = 4SE +/- 0.03, N = 6SE +/- 0.00, N = 5SE +/- 0.03, N = 61.791.692.733.482.643.453.123.591.932.982.113.312.263.512.383.651.813.082.714.413.315.03

ONNX Runtime

ONNX Runtime is developed by Microsoft and partners as a open-source, cross-platform, high performance machine learning inferencing and training accelerator. This test profile runs the ONNX Runtime with various models available from the ONNX Model Zoo. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.17Model: bertsquad-12 - Device: CPU - Executor: ParallelEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P510152025SE +/- 0.10485, N = 3SE +/- 0.10146, N = 4SE +/- 0.09004, N = 3SE +/- 0.05052, N = 3SE +/- 0.08493, N = 3SE +/- 0.04604, N = 3SE +/- 0.05587, N = 3SE +/- 0.01907, N = 3SE +/- 0.00728, N = 3SE +/- 0.03979, N = 3SE +/- 0.02804, N = 3SE +/- 0.01071, N = 3SE +/- 0.06023, N = 3SE +/- 0.09371, N = 3SE +/- 0.07567, N = 3SE +/- 0.04124, N = 3SE +/- 0.13407, N = 3SE +/- 0.12404, N = 3SE +/- 0.04566, N = 3SE +/- 0.02421, N = 3SE +/- 0.21736, N = 3SE +/- 0.02832, N = 39.800908.8714412.254908.8093012.280708.759719.652967.984028.572866.667189.503537.1391716.3251013.7366015.7394013.5190016.6863014.9460016.0956014.5280019.6773015.434101. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

LAMMPS Molecular Dynamics Simulator

LAMMPS is a classical molecular dynamics code, and an acronym for Large-scale Atomic/Molecular Massively Parallel Simulator. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgns/day, More Is BetterLAMMPS Molecular Dynamics Simulator 23Jun2022Model: 20k AtomsEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P1428425670SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.12, N = 3SE +/- 0.13, N = 3SE +/- 0.30, N = 3SE +/- 0.12, N = 3SE +/- 0.19, N = 3SE +/- 0.13, N = 3SE +/- 0.01, N = 3SE +/- 0.07, N = 3SE +/- 0.01, N = 3SE +/- 0.05, N = 3SE +/- 0.04, N = 3SE +/- 0.03, N = 3SE +/- 0.04, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.04, N = 327.5325.3342.5157.1046.8962.0047.9958.8428.2846.7132.1651.8221.3835.7034.8950.5237.4656.401. (CXX) g++ options: -O3 -lm -ldl

LuxCoreRender

LuxCoreRender is an open-source 3D physically based renderer formerly known as LuxRender. LuxCoreRender supports CPU-based rendering as well as GPU acceleration via OpenCL, NVIDIA CUDA, and NVIDIA OptiX interfaces. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender 2.6Scene: LuxCore Benchmark - Acceleration: CPUEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P3691215SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.10, N = 7SE +/- 0.11, N = 15SE +/- 0.04, N = 3SE +/- 0.12, N = 15SE +/- 0.16, N = 3SE +/- 0.08, N = 15SE +/- 0.06, N = 3SE +/- 0.10, N = 15SE +/- 0.06, N = 3SE +/- 0.08, N = 15SE +/- 0.03, N = 3SE +/- 0.22, N = 12SE +/- 0.05, N = 3SE +/- 0.16, N = 15SE +/- 0.06, N = 15SE +/- 0.07, N = 15SE +/- 0.04, N = 3SE +/- 0.12, N = 3SE +/- 0.11, N = 3SE +/- 0.17, N = 127.386.9311.3410.5612.4310.6112.419.657.906.418.476.746.306.816.827.414.296.437.108.828.068.88

TensorFlow

This is a benchmark of the TensorFlow deep learning framework using the TensorFlow reference benchmarks (tensorflow/benchmarks with tf_cnn_benchmarks.py). Note with the Phoronix Test Suite there is also pts/tensorflow-lite for benchmarking the TensorFlow Lite binaries if desired for complementary metrics. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.16.1Device: CPU - Batch Size: 256 - Model: AlexNetEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P400800120016002000SE +/- 0.99, N = 3SE +/- 0.41, N = 3SE +/- 2.58, N = 3SE +/- 6.01, N = 3SE +/- 1.54, N = 3SE +/- 15.82, N = 3SE +/- 4.01, N = 3SE +/- 10.23, N = 15SE +/- 1.03, N = 3SE +/- 19.06, N = 15SE +/- 2.12, N = 3SE +/- 10.51, N = 4SE +/- 1.21, N = 3SE +/- 1.15, N = 3SE +/- 6.82, N = 3SE +/- 5.81, N = 3SE +/- 1.28, N = 3SE +/- 3.03, N = 3SE +/- 0.54, N = 3SE +/- 5.06, N = 3SE +/- 4.27, N = 3SE +/- 1.86, N = 3843.63771.471278.581524.741301.261560.561454.711403.46609.67857.20668.331010.93986.041479.531058.991528.41852.141340.341205.301730.251277.461681.44

Liquid-DSP

LiquidSDR's Liquid-DSP is a software-defined radio (SDR) digital signal processing library. This test profile runs a multi-threaded benchmark of this SDR/DSP library focused on embedded platform usage. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 1.6Threads: 128 - Buffer Length: 256 - Filter Length: 512EPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P300M600M900M1200M1500MSE +/- 390953.25, N = 3SE +/- 431058.13, N = 3SE +/- 1047748.91, N = 3SE +/- 2338327.99, N = 3SE +/- 2412697.89, N = 3SE +/- 3901424.24, N = 3SE +/- 814452.78, N = 3SE +/- 503322.30, N = 3SE +/- 305632.31, N = 3SE +/- 1072572.19, N = 3SE +/- 287923.60, N = 3SE +/- 866544.86, N = 3SE +/- 681281.47, N = 3SE +/- 11560043.25, N = 5SE +/- 1345523.44, N = 3SE +/- 2123152.79, N = 3SE +/- 912164.70, N = 3SE +/- 8061118.62, N = 3SE +/- 1740596.96, N = 3SE +/- 6842108.19, N = 3SE +/- 2313246.88, N = 3SE +/- 4790383.89, N = 3809916667731756667115816666711999666671368733333139473333313698000001349800000719626667707053333796340000777940000800186667109146000088220000012060666675392266679810900009185666671126466667115293333314938333331. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

CloverLeaf

CloverLeaf is a Lagrangian-Eulerian hydrodynamics benchmark. This test profile currently makes use of CloverLeaf's OpenMP version. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterCloverLeaf 1.3Input: clover_bm64_shortEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P1428425670SE +/- 0.04, N = 3SE +/- 0.04, N = 3SE +/- 2.15, N = 15SE +/- 1.11, N = 12SE +/- 1.81, N = 15SE +/- 0.23, N = 3SE +/- 2.07, N = 12SE +/- 0.30, N = 3SE +/- 0.03, N = 3SE +/- 0.33, N = 3SE +/- 0.04, N = 3SE +/- 0.33, N = 3SE +/- 0.15, N = 3SE +/- 0.31, N = 15SE +/- 0.17, N = 3SE +/- 0.40, N = 4SE +/- 0.03, N = 3SE +/- 0.31, N = 3SE +/- 0.02, N = 3SE +/- 0.24, N = 3SE +/- 0.03, N = 3SE +/- 0.45, N = 357.3857.5446.5030.0542.1722.8348.3627.7438.0128.9938.0128.9241.4332.2542.2232.4460.8935.2939.4826.5839.3831.901. (F9X) gfortran options: -O3 -march=native -funroll-loops -fopenmp

LAMMPS Molecular Dynamics Simulator

LAMMPS is a classical molecular dynamics code, and an acronym for Large-scale Atomic/Molecular Massively Parallel Simulator. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgns/day, More Is BetterLAMMPS Molecular Dynamics Simulator 23Jun2022Model: Rhodopsin ProteinEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P1224364860SE +/- 0.29, N = 15SE +/- 0.30, N = 15SE +/- 0.14, N = 11SE +/- 0.39, N = 7SE +/- 0.35, N = 15SE +/- 0.43, N = 7SE +/- 0.29, N = 10SE +/- 0.24, N = 5SE +/- 0.05, N = 11SE +/- 0.11, N = 9SE +/- 0.04, N = 11SE +/- 0.09, N = 8SE +/- 0.28, N = 15SE +/- 0.53, N = 15SE +/- 0.36, N = 15SE +/- 0.33, N = 8SE +/- 0.29, N = 15SE +/- 0.97, N = 1524.2521.9436.1550.1240.0053.7740.3951.6327.6347.5130.8452.2421.1633.5428.7242.2834.3055.501. (CXX) g++ options: -O3 -lm -ldl

PostgreSQL

This is a benchmark of PostgreSQL using the integrated pgbench for facilitating the database benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL 16Scaling Factor: 100 - Clients: 1000 - Mode: Read Write - Average LatencyEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P714212835SE +/- 0.05, N = 3SE +/- 0.10, N = 3SE +/- 0.04, N = 3SE +/- 0.25, N = 12SE +/- 0.01, N = 3SE +/- 0.32, N = 12SE +/- 0.05, N = 3SE +/- 0.02, N = 3SE +/- 0.03, N = 3SE +/- 0.14, N = 3SE +/- 0.03, N = 3SE +/- 0.15, N = 3SE +/- 0.02, N = 3SE +/- 0.06, N = 3SE +/- 0.03, N = 3SE +/- 0.12, N = 3SE +/- 0.12, N = 12SE +/- 0.12, N = 3SE +/- 0.02, N = 3SE +/- 0.03, N = 3SE +/- 0.04, N = 3SE +/- 0.10, N = 316.3218.0512.5018.0612.5818.1613.8416.8812.6328.8111.5426.2914.2916.9613.8516.6616.3413.6914.0414.8613.2630.201. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL 16Scaling Factor: 100 - Clients: 1000 - Mode: Read WriteEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P20K40K60K80K100KSE +/- 175.33, N = 3SE +/- 299.71, N = 3SE +/- 232.97, N = 3SE +/- 865.71, N = 12SE +/- 87.23, N = 3SE +/- 1059.49, N = 12SE +/- 242.45, N = 3SE +/- 58.85, N = 3SE +/- 186.80, N = 3SE +/- 163.06, N = 3SE +/- 232.81, N = 3SE +/- 221.82, N = 3SE +/- 95.84, N = 3SE +/- 195.77, N = 3SE +/- 143.25, N = 3SE +/- 440.63, N = 3SE +/- 434.11, N = 12SE +/- 656.63, N = 3SE +/- 78.02, N = 3SE +/- 137.82, N = 3SE +/- 198.41, N = 3SE +/- 106.16, N = 3612725539579987555057949255272722445922879191347168667738043699695895272225600466123373042712276731575396331101. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

srsRAN Project

srsRAN Project is a complete ORAN-native 5G RAN solution created by Software Radio Systems (SRS). The srsRAN Project radio suite was formerly known as srsLTE and can be used for building your own software-defined radio (SDR) 4G/5G mobile network. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMbps, More Is BettersrsRAN Project 23.10.1-20240325Test: PUSCH Processor Benchmark, Throughput ThreadEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P306090120150SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.07, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3112.1112.1112.2112.2112.2112.2112.1112.149.849.852.552.6129.7129.7129.7129.7112.3112.3129.7129.7129.5129.51. (CXX) g++ options: -O3 -march=native -mavx2 -mavx -msse4.1 -mfma -fno-trapping-math -fno-math-errno -ldl

OpenBenchmarking.orgMbps, More Is BettersrsRAN Project 23.10.1-20240325Test: PDSCH Processor Benchmark, Throughput ThreadEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P160320480640800SE +/- 3.14, N = 7SE +/- 1.24, N = 7SE +/- 1.71, N = 8SE +/- 3.72, N = 8SE +/- 3.13, N = 8SE +/- 5.52, N = 8SE +/- 0.80, N = 7SE +/- 4.48, N = 7SE +/- 0.32, N = 5SE +/- 0.32, N = 5SE +/- 0.24, N = 5SE +/- 0.66, N = 5SE +/- 1.64, N = 8SE +/- 3.86, N = 8SE +/- 1.27, N = 8SE +/- 5.02, N = 8SE +/- 3.57, N = 7SE +/- 2.08, N = 7SE +/- 1.17, N = 8SE +/- 2.57, N = 8SE +/- 1.34, N = 8SE +/- 1.89, N = 8557.9563.6684.7673.4680.7664.7596.2576.8299.4293.1333.2323.7702.6651.9705.5663.8484.8490.3680.2675.5742.9755.51. (CXX) g++ options: -O3 -march=native -mavx2 -mavx -msse4.1 -mfma -fno-trapping-math -fno-math-errno -ldl

OpenRadioss

OpenRadioss is an open-source AGPL-licensed finite element solver for dynamic event analysis OpenRadioss is based on Altair Radioss and open-sourced in 2022. This open-source finite element solver is benchmarked with various example models available from https://www.openradioss.org/models/ and https://github.com/OpenRadioss/ModelExchange/tree/main/Examples. This test is currently using a reference OpenRadioss binary build offered via GitHub. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterOpenRadioss 2023.09.15Model: INIVOL and Fluid Structure Interaction Drop ContainerEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P4080120160200SE +/- 0.37, N = 3SE +/- 0.63, N = 3SE +/- 0.57, N = 3SE +/- 0.14, N = 3SE +/- 0.93, N = 3SE +/- 0.43, N = 3SE +/- 0.46, N = 3SE +/- 0.12, N = 3SE +/- 0.08, N = 3SE +/- 0.07, N = 3SE +/- 0.06, N = 3SE +/- 0.09, N = 3SE +/- 0.23, N = 3SE +/- 0.50, N = 3SE +/- 0.19, N = 3SE +/- 0.17, N = 3SE +/- 0.12, N = 3SE +/- 0.30, N = 3176.87187.03100.2485.8994.7679.42106.5490.85160.56114.29146.03110.56204.21135.56140.43107.36128.74100.00

Liquid-DSP

LiquidSDR's Liquid-DSP is a software-defined radio (SDR) digital signal processing library. This test profile runs a multi-threaded benchmark of this SDR/DSP library focused on embedded platform usage. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 1.6Threads: 64 - Buffer Length: 256 - Filter Length: 512EPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P200M400M600M800M1000MSE +/- 822739.33, N = 3SE +/- 2292977.20, N = 3SE +/- 1678355.68, N = 3SE +/- 2261241.06, N = 3SE +/- 752558.60, N = 3SE +/- 3039034.93, N = 3SE +/- 673003.22, N = 3SE +/- 958772.36, N = 3SE +/- 271682.00, N = 3SE +/- 584646.14, N = 3SE +/- 124677.36, N = 3SE +/- 3610015.39, N = 3SE +/- 1611276.24, N = 3SE +/- 4432294.36, N = 3SE +/- 1289603.73, N = 3SE +/- 6141471.96, N = 3SE +/- 147685.85, N = 3SE +/- 749718.47, N = 3SE +/- 940265.92, N = 3SE +/- 3717554.45, N = 3SE +/- 1515552.70, N = 3SE +/- 7562646.32, N = 86338600005772633338113733338245833338505866678493400007096500007093933333595766673497466673985666673844066676323966677325600006890033337571766675032533336465133337444100007994966677837700008837012501. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

NWChem

NWChem is an open-source high performance computational chemistry package. Per NWChem's documentation, "NWChem aims to provide its users with computational chemistry tools that are scalable both in their ability to treat large scientific computational chemistry problems efficiently, and in their use of available parallel computing resources from high-performance parallel supercomputers to conventional workstation clusters." Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterNWChem 7.0.2Input: C240 BuckyballEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P80016002400320040002024.72224.61575.51558.41450.51429.91700.01712.62530.51785.02245.21873.13576.42170.02070.31960.91878.31809.71. (F9X) gfortran options: -lnwctask -lccsd -lmcscf -lselci -lmp2 -lmoints -lstepper -ldriver -loptim -lnwdft -lgradients -lcphf -lesp -lddscf -ldangchang -lguess -lhessian -lvib -lnwcutil -lrimp2 -lproperty -lsolvation -lnwints -lprepar -lnwmd -lnwpw -lofpw -lpaw -lpspw -lband -lnwpwlib -lcafe -lspace -lanalyze -lqhop -lpfft -ldplot -ldrdy -lvscf -lqmmm -lqmd -letrans -ltce -lbq -lmm -lcons -lperfm -ldntmc -lccca -ldimqm -lga -larmci -lpeigs -l64to32 -lopenblas -lpthread -lrt -llapack -lnwcblas -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz -lcomex -m64 -ffast-math -std=legacy -fdefault-integer-8 -finline-functions -O2

Kvazaar

This is a test of Kvazaar as a CPU-based H.265/HEVC video encoder written in the C programming language and optimized in Assembly. Kvazaar is the winner of the 2016 ACM Open-Source Software Competition and developed at the Ultra Video Group, Tampere University, Finland. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.2Video Input: Bosphorus 4K - Video Preset: Very FastEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P20406080100SE +/- 0.07, N = 5SE +/- 0.07, N = 4SE +/- 0.62, N = 6SE +/- 0.71, N = 6SE +/- 0.32, N = 6SE +/- 0.28, N = 6SE +/- 0.21, N = 5SE +/- 0.63, N = 15SE +/- 0.04, N = 4SE +/- 0.36, N = 15SE +/- 0.00, N = 4SE +/- 0.50, N = 15SE +/- 0.06, N = 4SE +/- 0.33, N = 4SE +/- 0.08, N = 4SE +/- 0.29, N = 4SE +/- 0.06, N = 3SE +/- 0.18, N = 4SE +/- 0.08, N = 4SE +/- 0.45, N = 5SE +/- 0.04, N = 4SE +/- 0.36, N = 554.6051.5176.8372.6878.1574.0368.5659.0141.8636.4046.1838.9240.2351.9141.3452.2331.2544.1150.0367.6438.0265.381. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt

GraphicsMagick

This is a test of GraphicsMagick with its OpenMP implementation that performs various imaging tests on a sample high resolution (currently 15400 x 6940) JPEG image. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.43Operation: SwirlEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P150300450600750SE +/- 0.33, N = 3SE +/- 0.88, N = 3SE +/- 0.33, N = 3SE +/- 0.33, N = 3SE +/- 0.00, N = 3SE +/- 0.67, N = 3SE +/- 0.33, N = 3SE +/- 0.33, N = 3SE +/- 4.91, N = 3SE +/- 2.33, N = 3SE +/- 1.15, N = 3SE +/- 3.00, N = 3SE +/- 0.58, N = 3SE +/- 1.33, N = 3SE +/- 0.67, N = 3SE +/- 0.67, N = 3SE +/- 0.33, N = 3SE +/- 4.41, N = 3SE +/- 1.15, N = 3SE +/- 1.76, N = 3SE +/- 0.88, N = 3SE +/- 0.58, N = 33793635115535465835355675044745665173945094325582784035026175296891. (CC) gcc options: -fopenmp -O2 -ltiff -ljbig -lsharpyuv -lwebp -lwebpmux -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -lxml2 -lzstd -llzma -lbz2 -lz -lm -lpthread -lgomp

Liquid-DSP

LiquidSDR's Liquid-DSP is a software-defined radio (SDR) digital signal processing library. This test profile runs a multi-threaded benchmark of this SDR/DSP library focused on embedded platform usage. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 1.6Threads: 128 - Buffer Length: 256 - Filter Length: 32EPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P900M1800M2700M3600M4500MSE +/- 3138116.92, N = 3SE +/- 2003607.86, N = 3SE +/- 2714365.08, N = 3SE +/- 3186603.90, N = 3SE +/- 841295.30, N = 3SE +/- 4250882.26, N = 3SE +/- 4056818.68, N = 3SE +/- 384418.75, N = 3SE +/- 920748.49, N = 3SE +/- 3194265.70, N = 3SE +/- 2023198.79, N = 3SE +/- 517472.49, N = 3SE +/- 400000.00, N = 3SE +/- 4598671.31, N = 3SE +/- 1342054.81, N = 3SE +/- 2403700.85, N = 3SE +/- 3178574.10, N = 3SE +/- 3557152.42, N = 3SE +/- 1858314.65, N = 3SE +/- 26633124.74, N = 3SE +/- 2236316.42, N = 3SE +/- 13813198.20, N = 330470666672767933333403273333340633333334353533333440790000037915666673794133333367196666736079000004102200000402103333323519000003254033333273963333333370666671797400000304470000032006000003558600000314823333335207666671. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

CloverLeaf

CloverLeaf is a Lagrangian-Eulerian hydrodynamics benchmark. This test profile currently makes use of CloverLeaf's OpenMP version. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterCloverLeaf 1.3Input: clover_bm16EPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P110220330440550SE +/- 0.79, N = 3SE +/- 1.08, N = 3SE +/- 3.79, N = 9SE +/- 0.12, N = 3SE +/- 2.24, N = 3SE +/- 0.59, N = 3SE +/- 4.99, N = 9SE +/- 1.02, N = 3SE +/- 0.11, N = 3SE +/- 1.60, N = 12SE +/- 0.00, N = 3SE +/- 2.04, N = 3SE +/- 1.43, N = 3SE +/- 1.56, N = 3SE +/- 2.03, N = 3SE +/- 2.11, N = 9SE +/- 1.58, N = 3SE +/- 3.41, N = 3SE +/- 0.13, N = 3SE +/- 0.74, N = 3SE +/- 0.54, N = 3SE +/- 2.02, N = 3495.25498.22334.30266.10245.82223.54400.52349.67314.88226.60313.50236.81351.29263.33357.57269.20512.36295.30328.47214.80410.59378.051. (F9X) gfortran options: -O3 -march=native -funroll-loops -fopenmp

libavif avifenc

This is a test of the AOMedia libavif library testing the encoding of a JPEG image to AV1 Image Format (AVIF). Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 1.0Encoder Speed: 0EPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P306090120150SE +/- 0.19, N = 3SE +/- 0.18, N = 3SE +/- 0.01, N = 3SE +/- 0.11, N = 3SE +/- 0.12, N = 3SE +/- 0.01, N = 3SE +/- 0.13, N = 3SE +/- 0.06, N = 3SE +/- 0.03, N = 3SE +/- 0.22, N = 3SE +/- 0.12, N = 3SE +/- 0.18, N = 3SE +/- 0.15, N = 3SE +/- 0.29, N = 3SE +/- 0.22, N = 3SE +/- 0.32, N = 3SE +/- 0.52, N = 3SE +/- 0.18, N = 3SE +/- 0.32, N = 3SE +/- 0.05, N = 3SE +/- 0.08, N = 3SE +/- 0.03, N = 375.8678.2461.9962.8961.6363.4073.2774.69140.86143.80126.97129.9176.9269.6573.0668.44100.4688.0769.9367.3864.4860.531. (CXX) g++ options: -O3 -fPIC -lm

OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 1.0Encoder Speed: 2EPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P20406080100SE +/- 0.03, N = 3SE +/- 0.10, N = 3SE +/- 0.02, N = 3SE +/- 0.43, N = 3SE +/- 0.02, N = 3SE +/- 0.03, N = 3SE +/- 0.06, N = 3SE +/- 0.13, N = 3SE +/- 0.01, N = 3SE +/- 0.07, N = 3SE +/- 0.41, N = 3SE +/- 0.09, N = 3SE +/- 0.21, N = 3SE +/- 0.22, N = 3SE +/- 0.31, N = 3SE +/- 0.06, N = 3SE +/- 0.04, N = 3SE +/- 0.25, N = 3SE +/- 0.04, N = 3SE +/- 0.16, N = 3SE +/- 0.05, N = 3SE +/- 0.09, N = 341.6642.6134.1535.4034.0435.3240.3541.9276.4779.2069.3471.9741.1338.6539.8838.1452.2347.5137.7537.3134.7933.651. (CXX) g++ options: -O3 -fPIC -lm

SVT-AV1

This is a benchmark of the SVT-AV1 open-source video encoder/decoder. SVT-AV1 was originally developed by Intel as part of their Open Visual Cloud / Scalable Video Technology (SVT). Development of SVT-AV1 has since moved to the Alliance for Open Media as part of upstream AV1 development. SVT-AV1 is a CPU-based multi-threaded video encoder for the AV1 video format with a sample YUV video file. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 2.0Encoder Mode: Preset 4 - Input: Bosphorus 4KEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P246810SE +/- 0.007, N = 3SE +/- 0.015, N = 3SE +/- 0.019, N = 3SE +/- 0.046, N = 3SE +/- 0.021, N = 3SE +/- 0.040, N = 3SE +/- 0.024, N = 3SE +/- 0.004, N = 3SE +/- 0.002, N = 3SE +/- 0.023, N = 3SE +/- 0.003, N = 3SE +/- 0.041, N = 3SE +/- 0.027, N = 3SE +/- 0.015, N = 3SE +/- 0.047, N = 3SE +/- 0.042, N = 3SE +/- 0.014, N = 3SE +/- 0.014, N = 3SE +/- 0.030, N = 3SE +/- 0.049, N = 3SE +/- 0.005, N = 3SE +/- 0.044, N = 36.9396.7278.4228.3498.5958.5137.2837.1533.9723.7104.3504.0406.4905.9916.5726.0525.4385.4377.0616.6987.8767.3601. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

uvg266

uvg266 is an open-source VVC/H.266 (Versatile Video Coding) encoder based on Kvazaar as part of the Ultra Video Group, Tampere University, Finland. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is Betteruvg266 0.4.1Video Input: Bosphorus 4K - Video Preset: Very FastEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P1428425670SE +/- 0.08, N = 4SE +/- 0.06, N = 4SE +/- 0.13, N = 5SE +/- 0.55, N = 5SE +/- 0.13, N = 5SE +/- 0.12, N = 5SE +/- 0.18, N = 5SE +/- 0.43, N = 15SE +/- 0.01, N = 4SE +/- 0.34, N = 15SE +/- 0.06, N = 4SE +/- 0.43, N = 15SE +/- 0.12, N = 4SE +/- 0.39, N = 4SE +/- 0.02, N = 4SE +/- 0.38, N = 9SE +/- 0.06, N = 3SE +/- 0.18, N = 4SE +/- 0.01, N = 4SE +/- 0.50, N = 5SE +/- 0.08, N = 3SE +/- 0.16, N = 550.0444.9262.0253.4462.7055.0554.4646.0040.7327.3344.4428.4339.5644.7540.8246.2530.1740.6949.4254.8835.1053.66

ASKAP

ASKAP is a set of benchmarks from the Australian SKA Pathfinder. The principal ASKAP benchmarks are the Hogbom Clean Benchmark (tHogbomClean) and Convolutional Resamping Benchmark (tConvolve) as well as some previous ASKAP benchmarks being included as well for OpenCL and CUDA execution of tConvolve. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMillion Grid Points Per Second, More Is BetterASKAP 1.0Test: tConvolve MT - DegriddingEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon Platinum 8380Xeon Platinum 8380 2P4K8K12K16K20KSE +/- 34.17, N = 3SE +/- 0.54, N = 3SE +/- 128.32, N = 3SE +/- 267.65, N = 5SE +/- 212.00, N = 12SE +/- 889.21, N = 3SE +/- 25.80, N = 3SE +/- 345.37, N = 3SE +/- 3.76, N = 3SE +/- 322.56, N = 37382.437421.2314217.1011941.3014143.1016906.209839.6413455.007425.229893.321. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp

TensorFlow

This is a benchmark of the TensorFlow deep learning framework using the TensorFlow reference benchmarks (tensorflow/benchmarks with tf_cnn_benchmarks.py). Note with the Phoronix Test Suite there is also pts/tensorflow-lite for benchmarking the TensorFlow Lite binaries if desired for complementary metrics. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.16.1Device: CPU - Batch Size: 64 - Model: GoogLeNetEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P80160240320400SE +/- 0.30, N = 3SE +/- 0.44, N = 3SE +/- 4.22, N = 3SE +/- 2.41, N = 3SE +/- 1.66, N = 3SE +/- 2.47, N = 3SE +/- 3.84, N = 4SE +/- 1.18, N = 3SE +/- 0.29, N = 3SE +/- 2.29, N = 3SE +/- 0.64, N = 3SE +/- 0.21, N = 3SE +/- 1.94, N = 3SE +/- 3.52, N = 5SE +/- 0.83, N = 3SE +/- 2.38, N = 3SE +/- 0.49, N = 3SE +/- 1.42, N = 3SE +/- 1.62, N = 3SE +/- 2.37, N = 3SE +/- 1.12, N = 3SE +/- 0.21, N = 3276.93256.79354.59227.22330.26248.03314.67176.00214.14168.10232.51190.80333.73341.51335.58308.95282.50347.72380.14331.76319.76291.37

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.16.1Device: CPU - Batch Size: 64 - Model: AlexNetEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P2004006008001000SE +/- 0.45, N = 4SE +/- 0.16, N = 4SE +/- 1.31, N = 5SE +/- 8.87, N = 4SE +/- 1.37, N = 5SE +/- 7.66, N = 5SE +/- 2.99, N = 5SE +/- 7.43, N = 15SE +/- 0.70, N = 3SE +/- 5.44, N = 15SE +/- 0.97, N = 3SE +/- 5.91, N = 15SE +/- 1.95, N = 5SE +/- 6.39, N = 13SE +/- 2.31, N = 5SE +/- 7.35, N = 5SE +/- 0.27, N = 4SE +/- 3.70, N = 5SE +/- 0.51, N = 5SE +/- 7.98, N = 5SE +/- 6.22, N = 5SE +/- 2.22, N = 5673.42617.03942.19727.77868.54738.31924.80658.97443.74464.80482.06520.01841.68932.59852.36940.40690.09904.36969.62996.47819.89858.84

Y-Cruncher

Y-Cruncher is a multi-threaded Pi benchmark capable of computing Pi to trillions of digits. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterY-Cruncher 0.8.3Pi Digits To Calculate: 1BEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P3691215SE +/- 0.005, N = 4SE +/- 0.001, N = 4SE +/- 0.008, N = 5SE +/- 0.012, N = 4SE +/- 0.008, N = 4SE +/- 0.012, N = 4SE +/- 0.007, N = 4SE +/- 0.049, N = 4SE +/- 0.018, N = 4SE +/- 0.007, N = 4SE +/- 0.020, N = 4SE +/- 0.002, N = 4SE +/- 0.045, N = 5SE +/- 0.122, N = 15SE +/- 0.026, N = 5SE +/- 0.142, N = 12SE +/- 0.011, N = 4SE +/- 0.010, N = 5SE +/- 0.005, N = 5SE +/- 0.007, N = 6SE +/- 0.030, N = 5SE +/- 0.010, N = 610.20510.4276.7438.1967.4718.9926.9287.91511.1987.96710.3867.4688.3006.3347.9596.26610.7127.7447.0475.0086.7015.110

OpenBenchmarking.orgSeconds, Fewer Is BetterY-Cruncher 0.8.3Pi Digits To Calculate: 500MEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P1.16482.32963.49444.65925.824SE +/- 0.006, N = 6SE +/- 0.008, N = 6SE +/- 0.003, N = 6SE +/- 0.003, N = 5SE +/- 0.003, N = 6SE +/- 0.007, N = 5SE +/- 0.005, N = 6SE +/- 0.015, N = 5SE +/- 0.005, N = 6SE +/- 0.004, N = 6SE +/- 0.007, N = 6SE +/- 0.004, N = 6SE +/- 0.010, N = 7SE +/- 0.064, N = 15SE +/- 0.023, N = 15SE +/- 0.074, N = 15SE +/- 0.003, N = 6SE +/- 0.006, N = 7SE +/- 0.003, N = 7SE +/- 0.002, N = 8SE +/- 0.008, N = 7SE +/- 0.004, N = 75.0775.1653.8504.3294.3124.5103.9684.1005.1773.6294.7703.4113.7813.1103.7042.9614.8743.7243.2672.3643.3912.659

Liquid-DSP

LiquidSDR's Liquid-DSP is a software-defined radio (SDR) digital signal processing library. This test profile runs a multi-threaded benchmark of this SDR/DSP library focused on embedded platform usage. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 1.6Threads: 1 - Buffer Length: 256 - Filter Length: 57EPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P16M32M48M64M80MSE +/- 4807.40, N = 3SE +/- 393224.42, N = 3SE +/- 12719.19, N = 3SE +/- 486361.09, N = 3SE +/- 7423.69, N = 3SE +/- 34724.31, N = 3SE +/- 7937.25, N = 3SE +/- 8089.77, N = 3SE +/- 20835.33, N = 3SE +/- 2185.81, N = 3SE +/- 5206.83, N = 3SE +/- 11392.00, N = 3SE +/- 4910.31, N = 3SE +/- 4163.33, N = 3SE +/- 5364.49, N = 3SE +/- 822374.71, N = 4SE +/- 15982.63, N = 3SE +/- 178712.37, N = 3SE +/- 666.67, N = 3SE +/- 3844.19, N = 3SE +/- 599433.09, N = 9SE +/- 68119.99, N = 3462106674548633355425333549546675545533355415667462700004622966733444667334393333719566737121333671303336706400067127667662660005408966753930333670746676699133373140667704990001. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

Timed Linux Kernel Compilation

This test times how long it takes to build the Linux kernel in a default configuration (defconfig) for the architecture being tested or alternatively an allmodconfig for building all possible kernel modules for the build. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Linux Kernel Compilation 6.8Build: defconfigEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P1326395265SE +/- 0.50, N = 4SE +/- 0.54, N = 4SE +/- 0.43, N = 3SE +/- 0.33, N = 3SE +/- 0.46, N = 3SE +/- 0.17, N = 13SE +/- 0.44, N = 3SE +/- 0.28, N = 7SE +/- 0.39, N = 6SE +/- 0.22, N = 14SE +/- 0.37, N = 6SE +/- 0.28, N = 8SE +/- 0.59, N = 3SE +/- 0.40, N = 4SE +/- 0.57, N = 3SE +/- 0.31, N = 5SE +/- 0.33, N = 3SE +/- 0.42, N = 5SE +/- 0.55, N = 3SE +/- 0.43, N = 3SE +/- 0.39, N = 4SE +/- 0.23, N = 744.2846.3534.5727.6832.8925.8738.5330.6841.1035.5537.6432.6643.4232.1440.5030.5355.7439.4139.4529.9834.5925.87

OpenRadioss

OpenRadioss is an open-source AGPL-licensed finite element solver for dynamic event analysis OpenRadioss is based on Altair Radioss and open-sourced in 2022. This open-source finite element solver is benchmarked with various example models available from https://www.openradioss.org/models/ and https://github.com/OpenRadioss/ModelExchange/tree/main/Examples. This test is currently using a reference OpenRadioss binary build offered via GitHub. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterOpenRadioss 2023.09.15Model: Cell Phone Drop TestEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P1020304050SE +/- 0.18, N = 3SE +/- 0.35, N = 3SE +/- 0.26, N = 3SE +/- 0.05, N = 3SE +/- 0.19, N = 3SE +/- 0.05, N = 3SE +/- 0.26, N = 3SE +/- 0.05, N = 3SE +/- 0.08, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.05, N = 3SE +/- 0.21, N = 3SE +/- 0.07, N = 3SE +/- 0.08, N = 3SE +/- 0.10, N = 3SE +/- 0.18, N = 3SE +/- 0.32, N = 333.2335.9522.5323.5320.4522.5223.6927.8633.7527.5131.9227.6343.4531.1731.4928.2227.9026.88

TensorFlow

This is a benchmark of the TensorFlow deep learning framework using the TensorFlow reference benchmarks (tensorflow/benchmarks with tf_cnn_benchmarks.py). Note with the Phoronix Test Suite there is also pts/tensorflow-lite for benchmarking the TensorFlow Lite binaries if desired for complementary metrics. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.16.1Device: CPU - Batch Size: 512 - Model: GoogLeNetEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P130260390520650SE +/- 0.06, N = 3SE +/- 0.03, N = 3SE +/- 4.02, N = 10SE +/- 5.11, N = 3SE +/- 3.05, N = 12SE +/- 1.60, N = 3SE +/- 12.03, N = 12SE +/- 5.63, N = 6SE +/- 0.26, N = 3SE +/- 1.19, N = 3SE +/- 0.19, N = 3SE +/- 1.26, N = 3SE +/- 0.41, N = 3SE +/- 1.14, N = 3SE +/- 0.37, N = 3SE +/- 2.46, N = 3SE +/- 0.12, N = 3SE +/- 0.25, N = 3SE +/- 0.34, N = 3SE +/- 2.62, N = 3SE +/- 3.68, N = 3SE +/- 1.52, N = 3313.50295.29470.95525.84425.25464.78450.61588.43278.05354.81298.16378.79383.57467.91398.40477.33290.16411.05461.23576.08462.78577.76

Numpy Benchmark

This is a test to obtain the general Numpy performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgScore, More Is BetterNumpy BenchmarkEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P120240360480600SE +/- 0.72, N = 3SE +/- 1.34, N = 3SE +/- 2.28, N = 3SE +/- 0.38, N = 3SE +/- 1.85, N = 3SE +/- 0.60, N = 3SE +/- 0.96, N = 3SE +/- 0.25, N = 3SE +/- 0.37, N = 3SE +/- 0.30, N = 3SE +/- 2.24, N = 3SE +/- 0.47, N = 3SE +/- 0.60, N = 3SE +/- 1.13, N = 3SE +/- 0.79, N = 3SE +/- 1.30, N = 3SE +/- 2.23, N = 3SE +/- 1.52, N = 3SE +/- 0.33, N = 3SE +/- 0.26, N = 3SE +/- 1.84, N = 3SE +/- 1.42, N = 3421.99418.89529.80529.03542.15540.96425.46422.76261.19258.49284.33283.52461.61435.21464.72439.84400.64394.71455.57456.18520.22519.89

FFmpeg

This is a benchmark of the FFmpeg multimedia framework. The FFmpeg test profile is making use of a modified version of vbench from Columbia University's Architecture and Design Lab (ARCADE) [http://arcade.cs.columbia.edu/vbench/] that is a benchmark for video-as-a-service workloads. The test profile offers the options of a range of vbench scenarios based on freely distributable video content and offers the options of using the x264 or x265 video encoders for transcoding. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterFFmpeg 7.0Encoder: libx265 - Scenario: Video On DemandEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P1224364860SE +/- 0.02, N = 3SE +/- 0.05, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.07, N = 3SE +/- 0.03, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.04, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.10, N = 3SE +/- 0.43, N = 3SE +/- 0.07, N = 3SE +/- 0.13, N = 3SE +/- 0.07, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.14, N = 346.8846.9355.5952.8155.5655.0147.3347.1427.1726.8929.9528.3947.3445.2948.1446.7944.1343.8049.8448.7753.9953.291. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma

OpenBenchmarking.orgFPS, More Is BetterFFmpeg 7.0Encoder: libx265 - Scenario: PlatformEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P1224364860SE +/- 0.02, N = 3SE +/- 0.03, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.04, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.00, N = 3SE +/- 0.03, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.03, N = 3SE +/- 0.09, N = 3SE +/- 0.08, N = 3SE +/- 0.27, N = 3SE +/- 0.08, N = 3SE +/- 0.05, N = 3SE +/- 0.16, N = 3SE +/- 0.12, N = 3SE +/- 0.14, N = 3SE +/- 0.15, N = 346.8746.8655.6152.7955.3855.1147.3147.1327.1726.9029.9428.3947.3245.9548.3546.5944.0143.5549.7948.7653.9253.221. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma

SVT-AV1

This is a benchmark of the SVT-AV1 open-source video encoder/decoder. SVT-AV1 was originally developed by Intel as part of their Open Visual Cloud / Scalable Video Technology (SVT). Development of SVT-AV1 has since moved to the Alliance for Open Media as part of upstream AV1 development. SVT-AV1 is a CPU-based multi-threaded video encoder for the AV1 video format with a sample YUV video file. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 2.0Encoder Mode: Preset 8 - Input: Bosphorus 4KEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P20406080100SE +/- 0.11, N = 4SE +/- 0.67, N = 4SE +/- 0.56, N = 5SE +/- 0.40, N = 5SE +/- 0.42, N = 5SE +/- 0.63, N = 5SE +/- 0.38, N = 5SE +/- 0.31, N = 4SE +/- 0.03, N = 4SE +/- 0.35, N = 15SE +/- 0.02, N = 4SE +/- 0.34, N = 3SE +/- 0.26, N = 4SE +/- 0.58, N = 5SE +/- 0.29, N = 4SE +/- 0.44, N = 15SE +/- 0.09, N = 4SE +/- 0.52, N = 7SE +/- 0.20, N = 5SE +/- 0.46, N = 4SE +/- 0.22, N = 5SE +/- 0.79, N = 568.1964.7987.9986.3486.3087.8278.7477.6046.4842.8650.8247.2562.7554.8265.3655.9855.2459.1070.9165.2279.4470.431. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

QuantLib

QuantLib is an open-source library/framework around quantitative finance for modeling, trading and risk management scenarios. QuantLib is written in C++ with Boost and its built-in benchmark used reports the QuantLib Benchmark Index benchmark score. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMFLOPS, More Is BetterQuantLib 1.32Configuration: Single-ThreadedEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P8001600240032004000SE +/- 18.64, N = 3SE +/- 14.40, N = 3SE +/- 24.27, N = 3SE +/- 19.83, N = 3SE +/- 22.39, N = 3SE +/- 1.14, N = 3SE +/- 14.83, N = 3SE +/- 19.30, N = 3SE +/- 4.87, N = 3SE +/- 4.34, N = 3SE +/- 6.88, N = 3SE +/- 7.35, N = 3SE +/- 22.17, N = 3SE +/- 28.11, N = 3SE +/- 25.35, N = 3SE +/- 28.57, N = 3SE +/- 14.88, N = 3SE +/- 2.82, N = 3SE +/- 28.42, N = 3SE +/- 25.40, N = 3SE +/- 33.58, N = 3SE +/- 30.36, N = 122593.32593.03105.93098.53114.23125.42596.12590.81765.61760.81960.71954.23225.73207.03229.13222.82534.52558.63209.63210.13600.53586.31. (CXX) g++ options: -O3 -march=native -fPIE -pie

TensorFlow

This is a benchmark of the TensorFlow deep learning framework using the TensorFlow reference benchmarks (tensorflow/benchmarks with tf_cnn_benchmarks.py). Note with the Phoronix Test Suite there is also pts/tensorflow-lite for benchmarking the TensorFlow Lite binaries if desired for complementary metrics. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.16.1Device: CPU - Batch Size: 256 - Model: GoogLeNetEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P110220330440550SE +/- 0.04, N = 3SE +/- 0.07, N = 3SE +/- 3.87, N = 15SE +/- 1.02, N = 3SE +/- 2.76, N = 15SE +/- 0.51, N = 3SE +/- 10.93, N = 12SE +/- 1.11, N = 3SE +/- 0.31, N = 3SE +/- 3.73, N = 4SE +/- 0.07, N = 3SE +/- 2.49, N = 3SE +/- 1.67, N = 3SE +/- 2.29, N = 3SE +/- 1.91, N = 3SE +/- 4.80, N = 3SE +/- 0.16, N = 3SE +/- 0.69, N = 3SE +/- 0.24, N = 3SE +/- 4.87, N = 3SE +/- 2.30, N = 3SE +/- 2.68, N = 3308.46287.42447.61401.84406.58391.40462.79397.44260.83301.46281.62335.38375.73447.50386.00449.91290.27402.78448.46528.93423.59501.39

Apache IoTDB

Apache IotDB is a time series database and this benchmark is facilitated using the IoT Benchmaark [https://github.com/thulab/iot-benchmark/]. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgAverage Latency, Fewer Is BetterApache IoTDB 1.2Device Count: 800 - Batch Size Per Write: 100 - Sensor Count: 800 - Client Number: 100EPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P20406080100SE +/- 0.31, N = 3SE +/- 0.03, N = 3SE +/- 0.31, N = 3SE +/- 0.65, N = 12SE +/- 0.23, N = 3SE +/- 0.59, N = 12SE +/- 0.10, N = 3SE +/- 0.79, N = 12SE +/- 0.11, N = 3SE +/- 1.37, N = 3SE +/- 0.15, N = 3SE +/- 0.65, N = 3SE +/- 0.48, N = 3SE +/- 1.01, N = 3SE +/- 0.87, N = 3SE +/- 1.11, N = 4SE +/- 0.43, N = 3SE +/- 0.53, N = 3SE +/- 0.15, N = 3SE +/- 1.18, N = 3SE +/- 0.68, N = 3SE +/- 0.80, N = 765.6664.9353.7761.0752.9361.4658.1166.5490.31107.2884.59101.4990.0294.8489.5395.39100.29102.6785.1692.2381.7382.73

ClickHouse

ClickHouse is an open-source, high performance OLAP data management system. This test profile uses ClickHouse's standard benchmark recommendations per https://clickhouse.com/docs/en/operations/performance-test/ / https://github.com/ClickHouse/ClickBench/tree/main/clickhouse with the 100 million rows web analytics dataset. The reported value is the query processing time using the geometric mean of all separate queries performed as an aggregate. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgQueries Per Minute, Geo Mean, More Is BetterClickHouse 22.12.3.5100M Rows Hits Dataset, Second RunEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P130260390520650SE +/- 2.99, N = 3SE +/- 5.72, N = 3SE +/- 3.14, N = 3SE +/- 8.37, N = 3SE +/- 0.42, N = 3SE +/- 6.78, N = 3SE +/- 9.26, N = 3SE +/- 4.85, N = 5SE +/- 3.34, N = 3SE +/- 1.53, N = 3SE +/- 2.12, N = 3SE +/- 3.25, N = 3SE +/- 1.94, N = 3SE +/- 0.19, N = 3SE +/- 4.95, N = 3SE +/- 3.17, N = 12SE +/- 0.73, N = 3SE +/- 3.61, N = 3SE +/- 2.93, N = 3SE +/- 3.26, N = 3SE +/- 2.86, N = 6SE +/- 3.10, N = 5337.32337.44562.50529.80597.73528.21450.12420.35381.05320.17403.96339.50465.06499.18474.68467.96339.67295.43486.05507.56455.79443.58

Apache IoTDB

Apache IotDB is a time series database and this benchmark is facilitated using the IoT Benchmaark [https://github.com/thulab/iot-benchmark/]. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgpoint/sec, More Is BetterApache IoTDB 1.2Device Count: 800 - Batch Size Per Write: 100 - Sensor Count: 800 - Client Number: 100EPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P30M60M90M120M150MSE +/- 576868.09, N = 3SE +/- 41021.96, N = 3SE +/- 665173.47, N = 3SE +/- 1249999.63, N = 12SE +/- 538692.55, N = 3SE +/- 1058559.19, N = 12SE +/- 263772.09, N = 3SE +/- 1225528.40, N = 12SE +/- 84917.07, N = 3SE +/- 769517.20, N = 3SE +/- 174748.00, N = 3SE +/- 207721.96, N = 3SE +/- 435900.66, N = 3SE +/- 594234.55, N = 3SE +/- 782176.98, N = 3SE +/- 872659.60, N = 4SE +/- 306106.55, N = 3SE +/- 365828.34, N = 3SE +/- 276414.35, N = 3SE +/- 928557.10, N = 3SE +/- 739343.51, N = 3SE +/- 862582.24, N = 71168797991178849771421022541255956071447604481249472881317813091153178348511789771664005909734147574013985744542807704658635451880139566767294957517848090871770836517859461680792771639

ClickHouse

ClickHouse is an open-source, high performance OLAP data management system. This test profile uses ClickHouse's standard benchmark recommendations per https://clickhouse.com/docs/en/operations/performance-test/ / https://github.com/ClickHouse/ClickBench/tree/main/clickhouse with the 100 million rows web analytics dataset. The reported value is the query processing time using the geometric mean of all separate queries performed as an aggregate. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgQueries Per Minute, Geo Mean, More Is BetterClickHouse 22.12.3.5100M Rows Hits Dataset, Third RunEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P130260390520650SE +/- 1.77, N = 3SE +/- 5.23, N = 3SE +/- 4.03, N = 3SE +/- 10.00, N = 3SE +/- 4.34, N = 3SE +/- 2.03, N = 3SE +/- 3.32, N = 3SE +/- 6.21, N = 5SE +/- 2.14, N = 3SE +/- 1.59, N = 3SE +/- 1.22, N = 3SE +/- 3.52, N = 3SE +/- 6.03, N = 3SE +/- 3.08, N = 3SE +/- 3.60, N = 3SE +/- 3.54, N = 12SE +/- 4.79, N = 3SE +/- 1.27, N = 3SE +/- 3.45, N = 3SE +/- 2.55, N = 3SE +/- 3.62, N = 6SE +/- 5.39, N = 5338.84335.46559.55525.23595.19526.36458.96427.95379.92320.87400.52337.75470.02501.07476.91471.79342.99295.06481.66501.63458.23438.60

x265

This is a simple test of the x265 encoder run on the CPU with 1080p and 4K options for H.265 video encode performance with x265. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is Betterx265 3.6Video Input: Bosphorus 4KEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P918273645SE +/- 0.06, N = 3SE +/- 0.06, N = 3SE +/- 0.08, N = 3SE +/- 0.09, N = 3SE +/- 0.11, N = 3SE +/- 0.10, N = 3SE +/- 0.02, N = 3SE +/- 0.06, N = 3SE +/- 0.11, N = 3SE +/- 0.22, N = 6SE +/- 0.13, N = 3SE +/- 0.17, N = 3SE +/- 0.08, N = 3SE +/- 0.12, N = 3SE +/- 0.39, N = 3SE +/- 0.10, N = 3SE +/- 0.13, N = 3SE +/- 0.05, N = 3SE +/- 0.11, N = 4SE +/- 0.20, N = 4SE +/- 0.06, N = 4SE +/- 0.09, N = 428.1327.7431.7228.8132.1231.9528.1628.1120.2222.0721.3019.5529.0527.2631.4027.9029.7630.8037.8637.0438.9339.311. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma

ONNX Runtime

ONNX Runtime is developed by Microsoft and partners as a open-source, cross-platform, high performance machine learning inferencing and training accelerator. This test profile runs the ONNX Runtime with various models available from the ONNX Model Zoo. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.17Model: ArcFace ResNet-100 - Device: CPU - Executor: ParallelEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P1428425670SE +/- 0.12474, N = 3SE +/- 0.23936, N = 3SE +/- 0.03174, N = 3SE +/- 0.05569, N = 3SE +/- 0.04145, N = 3SE +/- 0.05013, N = 3SE +/- 0.07716, N = 3SE +/- 0.06474, N = 3SE +/- 0.03255, N = 3SE +/- 0.04782, N = 3SE +/- 0.04131, N = 3SE +/- 0.02474, N = 15SE +/- 0.27882, N = 3SE +/- 0.11901, N = 3SE +/- 0.20934, N = 3SE +/- 0.11212, N = 3SE +/- 0.10899, N = 3SE +/- 0.55506, N = 3SE +/- 0.09731, N = 3SE +/- 0.09239, N = 3SE +/- 0.27014, N = 3SE +/- 0.27122, N = 327.3128026.2475029.2690015.0082029.8493015.0516024.6095011.938206.245213.497856.813303.7600340.7289032.8141042.2711029.1955044.2748038.5025046.8491029.1487060.4094031.458901. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

ASKAP

ASKAP is a set of benchmarks from the Australian SKA Pathfinder. The principal ASKAP benchmarks are the Hogbom Clean Benchmark (tHogbomClean) and Convolutional Resamping Benchmark (tConvolve) as well as some previous ASKAP benchmarks being included as well for OpenCL and CUDA execution of tConvolve. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMpix/sec, More Is BetterASKAP 1.0Test: tConvolve MPI - DegriddingEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P30K60K90K120K150KSE +/- 44.43, N = 3SE +/- 69.57, N = 3SE +/- 189.10, N = 3SE +/- 882.91, N = 4SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 598.81, N = 12SE +/- 1077.92, N = 14SE +/- 0.00, N = 3SE +/- 143.60, N = 3SE +/- 76.47, N = 3SE +/- 0.00, N = 3SE +/- 64.71, N = 3SE +/- 62.13, N = 3SE +/- 93.91, N = 3SE +/- 378.22, N = 4SE +/- 153.57, N = 3SE +/- 480.95, N = 316704.4015903.4042172.4081025.8064260.20123480.0028476.6052639.5018522.0036900.5020561.4040368.608429.1312800.4017891.6034614.1031177.2059139.201. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp

BRL-CAD

BRL-CAD is a cross-platform, open-source solid modeling system with built-in benchmark mode. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgVGR Performance Metric, More Is BetterBRL-CAD 7.38.2VGR Performance MetricEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P1.3M2.6M3.9M5.2M6.5M8519977713523161216616222831225746193921348447758617501508453223929416409212449334713937365879076781240753424308852300947833892413696991690451866771. (CXX) g++ options: -std=c++17 -pipe -fvisibility=hidden -fno-strict-aliasing -fno-common -fexceptions -ftemplate-depth-128 -m64 -ggdb3 -O3 -fipa-pta -fstrength-reduce -finline-functions -flto -ltcl8.6 -lnetpbm -lregex_brl -lz_brl -lassimp -ldl -lm -ltk8.6

OpenVINO

This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Person Detection FP16 - Device: CPUEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P2004006008001000SE +/- 0.25, N = 3SE +/- 0.56, N = 3SE +/- 7.13, N = 15SE +/- 5.47, N = 15SE +/- 5.20, N = 15SE +/- 2.17, N = 3SE +/- 13.40, N = 15SE +/- 20.94, N = 15SE +/- 0.09, N = 3SE +/- 0.07, N = 3SE +/- 0.05, N = 3SE +/- 0.34, N = 3SE +/- 1.23, N = 3SE +/- 1.28, N = 3SE +/- 0.52, N = 3SE +/- 0.55, N = 3SE +/- 0.34, N = 3SE +/- 0.23, N = 3SE +/- 0.04, N = 3SE +/- 0.69, N = 3SE +/- 0.95, N = 3SE +/- 1.42, N = 3197.91204.05306.27750.11433.061095.79283.18750.96126.64245.27134.77261.64285.95568.81301.30569.6084.30175.72298.56654.84403.20736.231. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

ASKAP

ASKAP is a set of benchmarks from the Australian SKA Pathfinder. The principal ASKAP benchmarks are the Hogbom Clean Benchmark (tHogbomClean) and Convolutional Resamping Benchmark (tConvolve) as well as some previous ASKAP benchmarks being included as well for OpenCL and CUDA execution of tConvolve. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMpix/sec, More Is BetterASKAP 1.0Test: tConvolve MPI - GriddingEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P30K60K90K120K150KSE +/- 86.77, N = 3SE +/- 0.00, N = 3SE +/- 1853.72, N = 3SE +/- 2386.93, N = 4SE +/- 581.17, N = 3SE +/- 19579.11, N = 3SE +/- 685.49, N = 12SE +/- 1180.69, N = 14SE +/- 99.83, N = 3SE +/- 194.30, N = 3SE +/- 0.00, N = 3SE +/- 802.88, N = 3SE +/- 47.29, N = 3SE +/- 46.25, N = 3SE +/- 76.67, N = 3SE +/- 412.68, N = 4SE +/- 219.20, N = 3SE +/- 1080.03, N = 316573.2016399.7046233.7086757.7074389.00121976.9028854.3054066.0021766.5042939.2023250.2045195.109623.7714497.3021314.2041773.0037265.9072004.001. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp

Xmrig

Xmrig is an open-source cross-platform CPU/GPU miner for RandomX, KawPow, CryptoNight and AstroBWT. This test profile is setup to measure the Xmrig CPU mining performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgH/s, More Is BetterXmrig 6.21Variant: GhostRider - Hash Count: 1MEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P7K14K21K28K35KSE +/- 30.53, N = 3SE +/- 41.94, N = 3SE +/- 117.32, N = 3SE +/- 290.50, N = 3SE +/- 10.36, N = 3SE +/- 95.10, N = 3SE +/- 61.27, N = 3SE +/- 46.94, N = 3SE +/- 19.74, N = 3SE +/- 53.95, N = 3SE +/- 43.00, N = 3SE +/- 43.14, N = 3SE +/- 12.93, N = 3SE +/- 14.02, N = 3SE +/- 14.78, N = 3SE +/- 7.44, N = 3SE +/- 32.20, N = 2SE +/- 49.14, N = 12SE +/- 23.16, N = 3SE +/- 4.03, N = 3SE +/- 44.68, N = 3SE +/- 64.69, N = 34660.04564.314207.726702.715786.631157.89320.517873.15315.710431.65753.911147.25446.810975.86122.312115.02593.25230.95808.811263.28378.316324.71. (CXX) g++ options: -fexceptions -fno-rtti -maes -O3 -Ofast -static-libgcc -static-libstdc++ -rdynamic -lssl -lcrypto -luv -lpthread -lrt -ldl -lhwloc

OpenVINO

This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Weld Porosity Detection FP16-INT8 - Device: CPUEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P714212835SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.08, N = 3SE +/- 0.01, N = 3SE +/- 0.04, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.04, N = 3SE +/- 0.05, N = 3SE +/- 0.03, N = 3SE +/- 0.05, N = 3SE +/- 0.03, N = 4SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 311.7813.1110.0910.179.429.2510.9211.2027.0128.2424.2524.772.502.532.672.798.588.273.582.502.362.481. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

ONNX Runtime

ONNX Runtime is developed by Microsoft and partners as a open-source, cross-platform, high performance machine learning inferencing and training accelerator. This test profile runs the ONNX Runtime with various models available from the ONNX Model Zoo. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.17Model: ArcFace ResNet-100 - Device: CPU - Executor: StandardEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P1530456075SE +/- 0.06539, N = 3SE +/- 0.29092, N = 15SE +/- 0.42374, N = 4SE +/- 0.31646, N = 15SE +/- 0.05911, N = 3SE +/- 0.56636, N = 15SE +/- 0.38216, N = 15SE +/- 0.40826, N = 15SE +/- 0.02972, N = 3SE +/- 0.03571, N = 3SE +/- 0.03724, N = 3SE +/- 0.00992, N = 3SE +/- 0.69010, N = 15SE +/- 0.34209, N = 3SE +/- 0.58786, N = 3SE +/- 0.20595, N = 3SE +/- 0.54692, N = 3SE +/- 0.18826, N = 3SE +/- 0.16471, N = 3SE +/- 0.47575, N = 3SE +/- 0.82440, N = 3SE +/- 0.50579, N = 1330.3743031.0644039.2586023.5786041.4745023.4960030.8572018.013309.372945.5824110.342505.9528347.2703040.5671042.2747033.9621051.0172045.5414052.8167036.2493066.5162038.424001. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.17Model: ResNet50 v1-12-int8 - Device: CPU - Executor: ParallelEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P70140210280350SE +/- 1.54, N = 15SE +/- 1.50, N = 15SE +/- 2.31, N = 4SE +/- 0.54, N = 3SE +/- 1.50, N = 3SE +/- 0.54, N = 3SE +/- 0.53, N = 3SE +/- 0.66, N = 3SE +/- 0.27, N = 3SE +/- 0.26, N = 3SE +/- 0.32, N = 3SE +/- 0.27, N = 6SE +/- 1.74, N = 3SE +/- 0.47, N = 3SE +/- 2.72, N = 3SE +/- 0.73, N = 3SE +/- 1.73, N = 3SE +/- 1.30, N = 3SE +/- 0.53, N = 3SE +/- 0.73, N = 3SE +/- 2.50, N = 3SE +/- 1.63, N = 3207.34203.06190.38100.36178.70100.46153.2588.3755.8627.4764.1628.40319.04166.49301.14153.41315.03192.99313.10156.46308.80153.921. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenSSL

OpenSSL is an open-source toolkit that implements SSL (Secure Sockets Layer) and TLS (Transport Layer Security) protocols. This test profile makes use of the built-in "openssl speed" benchmarking capabilities. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgbyte/s, More Is BetterOpenSSL 3.3Algorithm: SHA256EPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P70000M140000M210000M280000M350000MSE +/- 10642001.84, N = 3SE +/- 64797308.82, N = 3SE +/- 38601729.93, N = 3SE +/- 210407867.05, N = 3SE +/- 146384349.91, N = 3SE +/- 160246527.97, N = 3SE +/- 34182873.86, N = 3SE +/- 80639802.67, N = 3SE +/- 34216643.88, N = 3SE +/- 97765007.32, N = 3SE +/- 242095363.59, N = 3SE +/- 228931567.43, N = 3SE +/- 27466135.54, N = 3SE +/- 126029257.64, N = 3SE +/- 33334799.97, N = 3SE +/- 70647143.49, N = 3SE +/- 8534071.27, N = 3SE +/- 919807437.76, N = 12SE +/- 159515825.53, N = 3SE +/- 66583540.43, N = 3SE +/- 23323764.84, N = 3SE +/- 29142783.86, N = 37458472100767806730387126475137690251645629887138409588983276267766403161269162280320258686237129975994733256330349777144163027280287035041140444391851878863575341351840436763103382860113278585044905453070057661806994523119106802107665739579201319760501201. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl

OpenVINO

This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Face Detection FP16-INT8 - Device: CPUEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P120240360480600SE +/- 0.01, N = 3SE +/- 0.06, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.12, N = 3SE +/- 0.41, N = 3SE +/- 0.03, N = 3SE +/- 0.04, N = 3SE +/- 0.07, N = 3SE +/- 0.18, N = 3SE +/- 0.15, N = 3SE +/- 0.18, N = 3SE +/- 0.14, N = 3SE +/- 0.58, N = 3SE +/- 0.41, N = 3SE +/- 0.54, N = 3SE +/- 0.36, N = 3SE +/- 0.10, N = 3SE +/- 0.12, N = 3SE +/- 0.01, N = 3SE +/- 0.69, N = 3SE +/- 0.77, N = 353.8948.7393.99188.74101.51205.03115.78231.8351.8599.7258.06113.68202.59373.50217.11401.4547.9996.08167.83423.18284.64545.211. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Noise Suppression Poconet-Like FP16 - Device: CPUEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P2K4K6K8K10KSE +/- 0.64, N = 3SE +/- 3.67, N = 3SE +/- 67.22, N = 14SE +/- 77.59, N = 3SE +/- 1.84, N = 3SE +/- 59.51, N = 3SE +/- 139.41, N = 12SE +/- 27.90, N = 3SE +/- 13.67, N = 3SE +/- 11.12, N = 3SE +/- 16.46, N = 3SE +/- 2.88, N = 3SE +/- 15.13, N = 3SE +/- 37.79, N = 3SE +/- 7.60, N = 3SE +/- 28.98, N = 3SE +/- 1.70, N = 3SE +/- 6.96, N = 3SE +/- 1.87, N = 3SE +/- 13.31, N = 3SE +/- 10.14, N = 3SE +/- 24.76, N = 33636.333405.945697.517810.656963.318231.725310.076513.361747.50843.921906.99978.464208.495565.234386.485933.651525.572963.824209.107356.636757.269360.891. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Machine Translation EN To DE FP16 - Device: CPUEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P60120180240300SE +/- 0.13, N = 3SE +/- 0.05, N = 3SE +/- 0.77, N = 7SE +/- 0.44, N = 3SE +/- 0.60, N = 11SE +/- 0.01, N = 3SE +/- 1.05, N = 5SE +/- 0.59, N = 3SE +/- 0.48, N = 3SE +/- 2.84, N = 15SE +/- 0.06, N = 3SE +/- 3.14, N = 3SE +/- 0.12, N = 3SE +/- 0.07, N = 3SE +/- 0.34, N = 3SE +/- 0.05, N = 3SE +/- 0.39, N = 3SE +/- 0.05, N = 3SE +/- 0.03, N = 3SE +/- 0.16, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 3100.67109.0091.1648.4383.1143.17102.8456.73259.66294.69240.38271.1428.7329.9838.5041.57127.8970.9562.4637.5826.8528.171. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Person Re-Identification Retail FP16 - Device: CPUEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P4K8K12K16K20KSE +/- 3.18, N = 3SE +/- 1.89, N = 3SE +/- 4.14, N = 3SE +/- 7.03, N = 3SE +/- 4.58, N = 3SE +/- 7.99, N = 3SE +/- 4.98, N = 3SE +/- 10.13, N = 3SE +/- 20.57, N = 3SE +/- 6.55, N = 3SE +/- 11.75, N = 3SE +/- 4.90, N = 3SE +/- 3.72, N = 3SE +/- 3.67, N = 3SE +/- 0.46, N = 3SE +/- 7.22, N = 3SE +/- 1.47, N = 3SE +/- 2.06, N = 3SE +/- 3.97, N = 3SE +/- 4.14, N = 3SE +/- 5.57, N = 3SE +/- 7.74, N = 33692.673355.736554.1212024.186846.7912665.627862.6514601.522006.003787.942179.994259.996717.6513102.287207.7414033.941698.053263.035943.6615519.929515.8618375.631. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Weld Porosity Detection FP16-INT8 - Device: CPUEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P10K20K30K40K50KSE +/- 0.41, N = 3SE +/- 1.69, N = 3SE +/- 4.46, N = 3SE +/- 147.69, N = 3SE +/- 11.71, N = 3SE +/- 110.20, N = 3SE +/- 5.50, N = 3SE +/- 11.27, N = 3SE +/- 7.59, N = 3SE +/- 12.93, N = 3SE +/- 6.61, N = 3SE +/- 19.55, N = 3SE +/- 234.43, N = 4SE +/- 80.58, N = 3SE +/- 21.27, N = 3SE +/- 233.95, N = 3SE +/- 5.62, N = 3SE +/- 6.41, N = 3SE +/- 2.71, N = 3SE +/- 53.98, N = 3SE +/- 47.41, N = 3SE +/- 39.08, N = 35366.794830.019356.7118666.169997.8920550.9311508.1922499.035278.4610020.915866.6311390.0419183.8337710.6020910.5340032.814502.749657.0815943.1747654.9526943.4248122.161. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

ASTC Encoder

ASTC Encoder (astcenc) is for the Adaptive Scalable Texture Compression (ASTC) format commonly used with OpenGL, OpenGL ES, and Vulkan graphics APIs. This test profile does a coding test of both compression/decompression. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMT/s, More Is BetterASTC Encoder 4.7Preset: ExhaustiveEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P48121620SE +/- 0.0010, N = 3SE +/- 0.0006, N = 3SE +/- 0.0002, N = 3SE +/- 0.0218, N = 3SE +/- 0.0086, N = 3SE +/- 0.0170, N = 3SE +/- 0.0025, N = 3SE +/- 0.1160, N = 3SE +/- 0.0007, N = 3SE +/- 0.0040, N = 3SE +/- 0.0000, N = 3SE +/- 0.0118, N = 3SE +/- 0.0003, N = 3SE +/- 0.0033, N = 3SE +/- 0.0011, N = 3SE +/- 0.0016, N = 3SE +/- 0.0016, N = 3SE +/- 0.0029, N = 3SE +/- 0.0024, N = 3SE +/- 0.0164, N = 3SE +/- 0.0072, N = 3SE +/- 0.0157, N = 33.51463.19935.630110.60186.302711.91077.557314.10383.65057.12914.05747.90603.12046.21263.62767.20751.33192.64714.26898.37014.63038.90911. (CXX) g++ options: -O3 -flto -pthread

NAS Parallel Benchmarks

NPB, NAS Parallel Benchmarks, is a benchmark developed by NASA for high-end computer systems. This test profile currently uses the MPI version of NPB. This test profile offers selecting the different NPB tests/problems and varying problem sizes. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: SP.CEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P80K160K240K320K400KSE +/- 23.20, N = 3SE +/- 14.31, N = 3SE +/- 72.03, N = 4SE +/- 1929.89, N = 5SE +/- 1178.78, N = 6SE +/- 1666.53, N = 6SE +/- 126.50, N = 4SE +/- 2064.71, N = 6SE +/- 67.02, N = 3SE +/- 679.14, N = 4SE +/- 9.58, N = 3SE +/- 420.81, N = 4SE +/- 11.99, N = 3SE +/- 33.85, N = 3SE +/- 150.79, N = 3SE +/- 560.20, N = 4SE +/- 31.76, N = 4SE +/- 1528.09, N = 552745.6452684.93125191.11256584.67225311.82390520.93127519.37214017.1858815.36135939.2569776.41141954.1537567.6190420.2571245.26147311.14109416.42228184.681. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz 2. Open MPI 4.1.6

ONNX Runtime

ONNX Runtime is developed by Microsoft and partners as a open-source, cross-platform, high performance machine learning inferencing and training accelerator. This test profile runs the ONNX Runtime with various models available from the ONNX Model Zoo. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.17Model: CaffeNet 12-int8 - Device: CPU - Executor: ParallelEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P2004006008001000SE +/- 0.91, N = 3SE +/- 5.34, N = 6SE +/- 4.99, N = 15SE +/- 2.35, N = 15SE +/- 5.53, N = 15SE +/- 4.10, N = 3SE +/- 3.02, N = 15SE +/- 2.41, N = 15SE +/- 1.50, N = 15SE +/- 0.53, N = 3SE +/- 1.57, N = 3SE +/- 0.77, N = 3SE +/- 4.16, N = 3SE +/- 1.77, N = 3SE +/- 4.87, N = 3SE +/- 1.98, N = 3SE +/- 1.09, N = 3SE +/- 3.90, N = 3SE +/- 5.72, N = 3SE +/- 4.81, N = 3SE +/- 10.06, N = 4SE +/- 2.57, N = 3547.52553.47586.18315.36590.71310.59452.32270.63176.6481.26190.7882.44687.67492.89678.48478.47767.48641.00784.30566.38830.73605.591. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

ASTC Encoder

ASTC Encoder (astcenc) is for the Adaptive Scalable Texture Compression (ASTC) format commonly used with OpenGL, OpenGL ES, and Vulkan graphics APIs. This test profile does a coding test of both compression/decompression. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMT/s, More Is BetterASTC Encoder 4.7Preset: Very ThoroughEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P510152025SE +/- 0.0007, N = 3SE +/- 0.0012, N = 3SE +/- 0.0006, N = 3SE +/- 0.1965, N = 3SE +/- 0.0254, N = 3SE +/- 0.1284, N = 3SE +/- 0.0006, N = 3SE +/- 0.1961, N = 15SE +/- 0.0005, N = 3SE +/- 0.0386, N = 3SE +/- 0.0005, N = 3SE +/- 0.0314, N = 3SE +/- 0.0016, N = 3SE +/- 0.0055, N = 3SE +/- 0.0016, N = 3SE +/- 0.0022, N = 3SE +/- 0.0075, N = 3SE +/- 0.0026, N = 3SE +/- 0.0054, N = 3SE +/- 0.0379, N = 3SE +/- 0.0294, N = 3SE +/- 0.0007, N = 35.74205.24069.184417.009810.322419.405212.318722.00235.863211.35736.516612.62205.134210.20515.970211.88752.15964.29357.088513.75187.624014.63341. (CXX) g++ options: -O3 -flto -pthread

Speedb

Speedb is a next-generation key value storage engine that is RocksDB compatible and aiming for stability, efficiency, and performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgOp/s, More Is BetterSpeedb 2.7Test: Random ReadEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P300M600M900M1200M1500MSE +/- 109015.29, N = 3SE +/- 70537.88, N = 3SE +/- 66268.38, N = 3SE +/- 955915.20, N = 3SE +/- 205170.43, N = 3SE +/- 5954964.38, N = 3SE +/- 1606748.01, N = 3SE +/- 2399164.12, N = 3SE +/- 998087.60, N = 3SE +/- 1272758.30, N = 3SE +/- 1322733.50, N = 3SE +/- 2674444.99, N = 3SE +/- 3698537.65, N = 15SE +/- 8491098.40, N = 15SE +/- 2763560.64, N = 13SE +/- 2955608.21, N = 3SE +/- 232538.80, N = 3SE +/- 706582.63, N = 3SE +/- 168680.90, N = 3SE +/- 5393159.45, N = 3SE +/- 242146.75, N = 3SE +/- 5399265.88, N = 1527409177824294011042855705485768717953763303410595465335899510701169947385596955494115849654667315921713241633402114570484199435702440706744979074901303591452591364662761796175512869583151783815861478711. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread

RocksDB

This is a benchmark of Meta/Facebook's RocksDB as an embeddable persistent key-value store for fast storage based on Google's LevelDB. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgOp/s, More Is BetterRocksDB 9.0Test: Random ReadEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P300M600M900M1200M1500MSE +/- 206014.27, N = 3SE +/- 211259.57, N = 3SE +/- 610621.13, N = 3SE +/- 599126.55, N = 3SE +/- 326038.01, N = 3SE +/- 2927744.32, N = 3SE +/- 153963.59, N = 3SE +/- 1154820.73, N = 3SE +/- 1336933.52, N = 3SE +/- 4448269.22, N = 3SE +/- 2130676.22, N = 3SE +/- 1897433.73, N = 3SE +/- 81327.78, N = 3SE +/- 1120857.00, N = 3SE +/- 86315.43, N = 3SE +/- 785893.13, N = 3SE +/- 744772.41, N = 3SE +/- 704022.38, N = 3SE +/- 3338569.32, N = 3SE +/- 1411218.60, N = 3SE +/- 1119855.47, N = 3SE +/- 82996.27, N = 326618653723499263640927294981514511052331009110312091515732354521135206564574749552111572074264530948312729075612053461544055331732344699394737559461255849532512341032653661705250499982975179465783928001. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread

TensorFlow

This is a benchmark of the TensorFlow deep learning framework using the TensorFlow reference benchmarks (tensorflow/benchmarks with tf_cnn_benchmarks.py). Note with the Phoronix Test Suite there is also pts/tensorflow-lite for benchmarking the TensorFlow Lite binaries if desired for complementary metrics. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.16.1Device: CPU - Batch Size: 1 - Model: ResNet-50EPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P48121620SE +/- 0.08, N = 15SE +/- 0.08, N = 15SE +/- 0.01, N = 4SE +/- 0.06, N = 15SE +/- 0.09, N = 15SE +/- 0.01, N = 3SE +/- 0.05, N = 15SE +/- 0.03, N = 15SE +/- 0.04, N = 3SE +/- 0.01, N = 15SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.09, N = 4SE +/- 0.07, N = 3SE +/- 0.10, N = 4SE +/- 0.04, N = 15SE +/- 0.08, N = 5SE +/- 0.13, N = 15SE +/- 0.05, N = 4SE +/- 0.06, N = 15SE +/- 0.05, N = 9SE +/- 0.03, N = 1510.7910.709.013.668.963.926.192.474.671.765.021.9911.295.119.994.3717.829.1310.534.396.433.85

OpenVINO

This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Handwritten English Recognition FP16-INT8 - Device: CPUEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P14002800420056007000SE +/- 3.51, N = 3SE +/- 0.47, N = 3SE +/- 4.84, N = 3SE +/- 9.83, N = 3SE +/- 4.06, N = 3SE +/- 13.59, N = 3SE +/- 7.27, N = 3SE +/- 14.68, N = 3SE +/- 1.73, N = 3SE +/- 1.20, N = 3SE +/- 0.61, N = 3SE +/- 3.81, N = 3SE +/- 3.41, N = 3SE +/- 1.09, N = 3SE +/- 4.55, N = 3SE +/- 2.81, N = 3SE +/- 4.60, N = 3SE +/- 9.58, N = 15SE +/- 1.46, N = 3SE +/- 2.46, N = 3SE +/- 0.73, N = 3SE +/- 3.43, N = 31542.611396.782739.015178.292986.335766.623280.256400.94832.291593.88934.971826.822074.303998.022243.844351.59637.761313.391643.434744.052924.665570.631. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

FFmpeg

This is a benchmark of the FFmpeg multimedia framework. The FFmpeg test profile is making use of a modified version of vbench from Columbia University's Architecture and Design Lab (ARCADE) [http://arcade.cs.columbia.edu/vbench/] that is a benchmark for video-as-a-service workloads. The test profile offers the options of a range of vbench scenarios based on freely distributable video content and offers the options of using the x264 or x265 video encoders for transcoding. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterFFmpeg 7.0Encoder: libx265 - Scenario: UploadEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P714212835SE +/- 0.04, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.04, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.04, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.12, N = 3SE +/- 0.07, N = 3SE +/- 0.07, N = 3SE +/- 0.07, N = 3SE +/- 0.06, N = 3SE +/- 0.04, N = 3SE +/- 0.10, N = 3SE +/- 0.05, N = 3SE +/- 0.04, N = 323.2523.2727.6626.4127.6127.4323.3623.2814.0113.9015.4714.8723.3322.3423.7723.3021.9621.7324.9724.5626.9326.801. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma

ClickHouse

ClickHouse is an open-source, high performance OLAP data management system. This test profile uses ClickHouse's standard benchmark recommendations per https://clickhouse.com/docs/en/operations/performance-test/ / https://github.com/ClickHouse/ClickBench/tree/main/clickhouse with the 100 million rows web analytics dataset. The reported value is the query processing time using the geometric mean of all separate queries performed as an aggregate. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgQueries Per Minute, Geo Mean, More Is BetterClickHouse 22.12.3.5100M Rows Hits Dataset, First Run / Cold CacheEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P120240360480600SE +/- 1.57, N = 3SE +/- 1.88, N = 3SE +/- 5.33, N = 3SE +/- 6.05, N = 3SE +/- 7.88, N = 3SE +/- 4.34, N = 3SE +/- 2.78, N = 3SE +/- 4.49, N = 5SE +/- 2.21, N = 3SE +/- 1.51, N = 3SE +/- 1.12, N = 3SE +/- 3.71, N = 3SE +/- 2.85, N = 3SE +/- 1.35, N = 3SE +/- 5.88, N = 3SE +/- 3.85, N = 12SE +/- 1.56, N = 3SE +/- 1.56, N = 3SE +/- 3.41, N = 3SE +/- 4.37, N = 3SE +/- 4.18, N = 6SE +/- 4.12, N = 5323.59322.69536.82504.84566.31513.92433.79411.26365.62311.63388.29333.06446.40491.89461.62460.66326.65285.17465.50485.63437.20423.30

Timed FFmpeg Compilation

This test times how long it takes to build the FFmpeg multimedia library. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed FFmpeg Compilation 7.0Time To CompileEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P816243240SE +/- 0.05, N = 3SE +/- 0.04, N = 3SE +/- 0.03, N = 3SE +/- 0.05, N = 3SE +/- 0.02, N = 3SE +/- 0.03, N = 3SE +/- 0.11, N = 3SE +/- 0.30, N = 3SE +/- 0.03, N = 3SE +/- 0.06, N = 3SE +/- 0.01, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.09, N = 3SE +/- 0.09, N = 3SE +/- 0.03, N = 3SE +/- 0.06, N = 3SE +/- 0.03, N = 3SE +/- 0.04, N = 3SE +/- 0.01, N = 3SE +/- 0.07, N = 3SE +/- 0.05, N = 327.5428.4220.4918.0919.9917.8423.2221.2227.8525.7125.2423.3226.4620.7924.8420.0134.2925.9424.0619.5121.3617.39

TensorFlow

This is a benchmark of the TensorFlow deep learning framework using the TensorFlow reference benchmarks (tensorflow/benchmarks with tf_cnn_benchmarks.py). Note with the Phoronix Test Suite there is also pts/tensorflow-lite for benchmarking the TensorFlow Lite binaries if desired for complementary metrics. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.16.1Device: CPU - Batch Size: 64 - Model: ResNet-50EPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P306090120150SE +/- 0.05, N = 3SE +/- 0.11, N = 3SE +/- 0.64, N = 3SE +/- 0.91, N = 5SE +/- 0.08, N = 3SE +/- 1.04, N = 4SE +/- 0.60, N = 3SE +/- 0.88, N = 3SE +/- 0.04, N = 3SE +/- 0.56, N = 3SE +/- 0.14, N = 3SE +/- 0.76, N = 3SE +/- 0.13, N = 3SE +/- 0.39, N = 3SE +/- 0.93, N = 3SE +/- 1.28, N = 3SE +/- 0.36, N = 3SE +/- 1.42, N = 3SE +/- 0.04, N = 3SE +/- 1.12, N = 3SE +/- 0.50, N = 3SE +/- 0.70, N = 387.3180.86114.6382.94104.5286.08106.1467.0871.4161.4876.3768.52104.23111.71103.56107.3090.72108.32120.93115.4791.5194.66

Timed Godot Game Engine Compilation

This test times how long it takes to compile the Godot Game Engine. Godot is a popular, open-source, cross-platform 2D/3D game engine and is built using the SCons build system and targeting the X11 platform. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Godot Game Engine Compilation 4.0Time To CompileEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P4080120160200SE +/- 0.32, N = 3SE +/- 0.16, N = 3SE +/- 0.16, N = 3SE +/- 0.06, N = 3SE +/- 0.12, N = 3SE +/- 0.62, N = 3SE +/- 0.20, N = 3SE +/- 0.55, N = 3SE +/- 0.16, N = 3SE +/- 0.64, N = 3SE +/- 0.73, N = 3SE +/- 1.40, N = 3SE +/- 0.18, N = 3SE +/- 0.56, N = 3SE +/- 0.32, N = 3SE +/- 1.69, N = 3SE +/- 0.22, N = 3SE +/- 0.69, N = 3SE +/- 0.76, N = 3SE +/- 0.56, N = 3SE +/- 0.91, N = 3SE +/- 0.29, N = 3154.01159.62111.69102.58103.3596.16128.28126.11165.41160.46152.23148.99149.38123.88143.81122.70187.88151.54140.23118.57122.72103.38

GNU Octave Benchmark

This test profile measures how long it takes to complete several reference GNU Octave files via octave-benchmark. GNU Octave is used for numerical computations and is an open-source alternative to MATLAB. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterGNU Octave Benchmark 8.4.0EPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P3691215SE +/- 0.011, N = 5SE +/- 0.007, N = 5SE +/- 0.009, N = 6SE +/- 0.004, N = 6SE +/- 0.018, N = 6SE +/- 0.007, N = 6SE +/- 0.014, N = 5SE +/- 0.025, N = 5SE +/- 0.035, N = 5SE +/- 0.023, N = 5SE +/- 0.051, N = 5SE +/- 0.108, N = 7SE +/- 0.015, N = 6SE +/- 0.096, N = 5SE +/- 0.024, N = 6SE +/- 0.082, N = 5SE +/- 0.017, N = 5SE +/- 0.052, N = 5SE +/- 0.015, N = 6SE +/- 0.019, N = 6SE +/- 0.020, N = 6SE +/- 0.019, N = 68.9298.9487.5287.6456.8576.9558.8018.84810.99612.24510.24311.6197.62212.6177.74812.5789.1049.6947.5328.0366.4586.856

Appleseed

Appleseed is an open-source production renderer focused on physically-based global illumination rendering engine primarily designed for animation and visual effects. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterAppleseed 2.0 BetaScene: Disney MaterialEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9684XEPYC 9754Xeon 6766EXeon 6780EXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P2040608010056.4261.3643.4540.9245.0858.3152.3258.3851.2556.4049.1479.8358.3853.4948.5648.4343.70

Scene: Disney Material

EPYC 9684X 2P: The test run did not produce a result.

EPYC 9654 2P: The test run did not produce a result.

EPYC 9754 2P: The test run did not produce a result.

Xeon 6766E 2P: The test run did not produce a result.

Xeon 6780E 2P: The test run did not produce a result.

Liquid-DSP

LiquidSDR's Liquid-DSP is a software-defined radio (SDR) digital signal processing library. This test profile runs a multi-threaded benchmark of this SDR/DSP library focused on embedded platform usage. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 1.6Threads: 64 - Buffer Length: 256 - Filter Length: 57EPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P600M1200M1800M2400M3000MSE +/- 4914717.13, N = 3SE +/- 7776531.65, N = 3SE +/- 3786085.64, N = 3SE +/- 10590929.03, N = 3SE +/- 8476044.68, N = 3SE +/- 8732315.46, N = 3SE +/- 8567444.84, N = 3SE +/- 17457503.96, N = 3SE +/- 1953913.45, N = 3SE +/- 4223873.95, N = 3SE +/- 1361779.88, N = 3SE +/- 7523814.04, N = 3SE +/- 2629533.12, N = 3SE +/- 28812627.44, N = 4SE +/- 5493127.02, N = 3SE +/- 27382304.50, N = 5SE +/- 4885465.97, N = 3SE +/- 25737283.81, N = 3SE +/- 7076957.92, N = 3SE +/- 28500058.48, N = 3SE +/- 11426868.92, N = 3SE +/- 32405829.38, N = 321868333332026333333285983333327302333332862000000277280000024449333332374766667190626666718523666672099033333203673333321387666672494050000230896666724913400001469166667199926666725392000002655500000247550000026200666671. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

Zstd Compression

This test measures the time needed to compress/decompress a sample file (silesia.tar) using Zstd (Zstandard) compression with options for different compression levels / settings. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.4Compression Level: 19 - Decompression SpeedEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P30060090012001500SE +/- 21.23, N = 3SE +/- 1.58, N = 3SE +/- 0.46, N = 3SE +/- 2.20, N = 3SE +/- 7.31, N = 3SE +/- 1.73, N = 3SE +/- 0.83, N = 3SE +/- 1.83, N = 3SE +/- 2.22, N = 3SE +/- 5.06, N = 3SE +/- 5.13, N = 3SE +/- 2.25, N = 3SE +/- 2.12, N = 3SE +/- 0.66, N = 15SE +/- 1.08, N = 15SE +/- 0.65, N = 15SE +/- 1.75, N = 3SE +/- 1.74, N = 4SE +/- 4.45, N = 3SE +/- 4.96, N = 3SE +/- 3.01, N = 4SE +/- 1.88, N = 31118.81144.81388.91382.11385.31392.51139.91139.0743.5721.4816.7774.41126.41040.21127.51039.21032.4900.51032.0963.61221.81165.81. (CC) gcc options: -O3 -pthread -lz -llzma

TensorFlow

This is a benchmark of the TensorFlow deep learning framework using the TensorFlow reference benchmarks (tensorflow/benchmarks with tf_cnn_benchmarks.py). Note with the Phoronix Test Suite there is also pts/tensorflow-lite for benchmarking the TensorFlow Lite binaries if desired for complementary metrics. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.16.1Device: CPU - Batch Size: 512 - Model: ResNet-50EPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P4080120160200SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.34, N = 3SE +/- 1.83, N = 3SE +/- 1.42, N = 4SE +/- 0.31, N = 3SE +/- 1.62, N = 4SE +/- 0.81, N = 3SE +/- 0.01, N = 3SE +/- 0.93, N = 9SE +/- 0.04, N = 3SE +/- 1.22, N = 3SE +/- 1.17, N = 3SE +/- 0.79, N = 3SE +/- 0.61, N = 3SE +/- 1.80, N = 3SE +/- 0.08, N = 3SE +/- 0.21, N = 3SE +/- 0.01, N = 3SE +/- 1.39, N = 3SE +/- 0.48, N = 3SE +/- 0.61, N = 3101.1795.63140.01161.90121.96137.50135.17174.9391.96113.4297.67124.60117.53145.29125.14138.3991.75127.97148.45174.95140.53169.75

ONNX Runtime

ONNX Runtime is developed by Microsoft and partners as a open-source, cross-platform, high performance machine learning inferencing and training accelerator. This test profile runs the ONNX Runtime with various models available from the ONNX Model Zoo. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.17Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: ParallelEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P816243240SE +/- 0.14, N = 3SE +/- 0.25, N = 3SE +/- 0.36, N = 3SE +/- 0.05, N = 3SE +/- 0.19, N = 3SE +/- 0.08, N = 3SE +/- 0.33, N = 4SE +/- 0.24, N = 7SE +/- 0.03, N = 3SE +/- 0.22, N = 3SE +/- 0.05, N = 3SE +/- 0.04, N = 3SE +/- 0.10, N = 3SE +/- 0.34, N = 3SE +/- 0.07, N = 3SE +/- 0.19, N = 3SE +/- 0.24, N = 3SE +/- 0.05, N = 3SE +/- 0.07, N = 3SE +/- 0.06, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 327.9427.8729.8425.6328.7324.0527.4526.3323.3117.6226.0318.4328.5224.7328.4824.6828.0925.9632.3430.0433.3831.711. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

Zstd Compression

This test measures the time needed to compress/decompress a sample file (silesia.tar) using Zstd (Zstandard) compression with options for different compression levels / settings. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.4Compression Level: 19, Long Mode - Decompression SpeedEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P30060090012001500SE +/- 2.09, N = 3SE +/- 0.92, N = 3SE +/- 1.17, N = 3SE +/- 1.87, N = 3SE +/- 1.99, N = 3SE +/- 2.93, N = 3SE +/- 1.95, N = 3SE +/- 0.19, N = 3SE +/- 3.99, N = 3SE +/- 4.61, N = 3SE +/- 1.05, N = 3SE +/- 1.54, N = 3SE +/- 0.56, N = 3SE +/- 1.00, N = 3SE +/- 1.45, N = 3SE +/- 1.78, N = 15SE +/- 4.15, N = 3SE +/- 0.30, N = 3SE +/- 0.43, N = 3SE +/- 3.69, N = 3SE +/- 0.84, N = 3SE +/- 1.60, N = 31101.41096.51328.51324.61324.91321.41102.21104.2739.1701.2797.7753.21131.11041.81133.31046.01018.3912.91069.1992.11242.61189.71. (CC) gcc options: -O3 -pthread -lz -llzma

Apache IoTDB

Apache IotDB is a time series database and this benchmark is facilitated using the IoT Benchmaark [https://github.com/thulab/iot-benchmark/]. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgpoint/sec, More Is BetterApache IoTDB 1.2Device Count: 500 - Batch Size Per Write: 100 - Sensor Count: 800 - Client Number: 400EPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P30M60M90M120M150MSE +/- 13050.78, N = 3SE +/- 412757.79, N = 3SE +/- 255887.16, N = 3SE +/- 1152766.29, N = 3SE +/- 371659.60, N = 3SE +/- 353097.82, N = 3SE +/- 68559.13, N = 3SE +/- 666882.79, N = 15SE +/- 111181.55, N = 3SE +/- 531367.14, N = 12SE +/- 441557.52, N = 3SE +/- 796440.21, N = 3SE +/- 662950.65, N = 3SE +/- 565297.90, N = 12SE +/- 1037167.36, N = 3SE +/- 574699.97, N = 12SE +/- 88241.50, N = 3SE +/- 661234.22, N = 3SE +/- 308756.34, N = 3SE +/- 692701.79, N = 8SE +/- 746822.47, N = 3SE +/- 761276.42, N = 121054328621051385511255620601088215801261610281067783791166853261036304838190047767599793871903976832080082455664775012488347564578057728788231127465300787797206801696209270975189231850

VVenC

VVenC is the Fraunhofer Versatile Video Encoder as a fast/efficient H.266/VVC encoder. The vvenc encoder makes use of SIMD Everywhere (SIMDe). The vvenc software is published under the Clear BSD License. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterVVenC 1.11Video Input: Bosphorus 4K - Video Preset: FastEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9684XEPYC 9754Xeon 6766EXeon 6780EXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P246810SE +/- 0.038, N = 3SE +/- 0.041, N = 3SE +/- 0.048, N = 3SE +/- 0.057, N = 3SE +/- 0.045, N = 3SE +/- 0.008, N = 3SE +/- 0.007, N = 3SE +/- 0.010, N = 3SE +/- 0.081, N = 3SE +/- 0.033, N = 3SE +/- 0.043, N = 15SE +/- 0.010, N = 3SE +/- 0.028, N = 3SE +/- 0.022, N = 3SE +/- 0.047, N = 3SE +/- 0.023, N = 3SE +/- 0.038, N = 36.1186.0007.4317.5476.4654.0524.4406.3246.0236.5016.0775.5835.8776.7196.4807.3926.9601. (CXX) g++ options: -O3 -flto=auto -fno-fat-lto-objects

Video Input: Bosphorus 4K - Video Preset: Fast

EPYC 9684X 2P: The test quit with a non-zero exit status. E: Parameter Check Error: Number of threads out of range (-1

EPYC 9654 2P: The test quit with a non-zero exit status. E: Parameter Check Error: Number of threads out of range (-1

EPYC 9754 2P: The test quit with a non-zero exit status. E: Parameter Check Error: Number of threads out of range (-1

Xeon 6766E 2P: The test quit with a non-zero exit status. E: Parameter Check Error: Number of threads out of range (-1

Xeon 6780E 2P: The test quit with a non-zero exit status. E: Parameter Check Error: Number of threads out of range (-1

TensorFlow

This is a benchmark of the TensorFlow deep learning framework using the TensorFlow reference benchmarks (tensorflow/benchmarks with tf_cnn_benchmarks.py). Note with the Phoronix Test Suite there is also pts/tensorflow-lite for benchmarking the TensorFlow Lite binaries if desired for complementary metrics. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.16.1Device: CPU - Batch Size: 256 - Model: ResNet-50EPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P4080120160200SE +/- 0.05, N = 3SE +/- 0.06, N = 3SE +/- 0.66, N = 3SE +/- 0.57, N = 3SE +/- 1.39, N = 4SE +/- 0.50, N = 3SE +/- 2.00, N = 12SE +/- 0.18, N = 3SE +/- 0.01, N = 3SE +/- 0.48, N = 3SE +/- 0.04, N = 3SE +/- 0.54, N = 3SE +/- 0.14, N = 3SE +/- 1.40, N = 3SE +/- 0.63, N = 3SE +/- 1.04, N = 12SE +/- 0.02, N = 3SE +/- 0.46, N = 3SE +/- 0.03, N = 3SE +/- 1.57, N = 3SE +/- 0.58, N = 3SE +/- 0.21, N = 398.7092.82138.11133.87123.37120.11125.76131.3887.17103.2292.42115.12119.73141.95123.69135.2891.65125.91143.67161.06129.02150.33

Timed ImageMagick Compilation

This test times how long it takes to build ImageMagick. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed ImageMagick Compilation 6.9.0Time To CompileEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P510152025SE +/- 0.04, N = 3SE +/- 0.04, N = 3SE +/- 0.09, N = 4SE +/- 0.04, N = 4SE +/- 0.06, N = 4SE +/- 0.04, N = 4SE +/- 0.08, N = 4SE +/- 0.02, N = 4SE +/- 0.08, N = 3SE +/- 0.08, N = 3SE +/- 0.05, N = 3SE +/- 0.11, N = 3SE +/- 0.15, N = 4SE +/- 0.11, N = 4SE +/- 0.06, N = 4SE +/- 0.07, N = 4SE +/- 0.03, N = 3SE +/- 0.13, N = 4SE +/- 0.10, N = 4SE +/- 0.13, N = 4SE +/- 0.10, N = 4SE +/- 0.03, N = 417.9218.1813.4712.7512.2011.7216.3915.8120.9120.5919.2018.8516.0814.4015.3814.0918.8416.3314.7213.2612.6011.49

libavif avifenc

This is a test of the AOMedia libavif library testing the encoding of a JPEG image to AV1 Image Format (AVIF). Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 1.0Encoder Speed: 10, LosslessEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P246810SE +/- 0.006, N = 7SE +/- 0.010, N = 7SE +/- 0.006, N = 8SE +/- 0.006, N = 8SE +/- 0.002, N = 8SE +/- 0.003, N = 7SE +/- 0.004, N = 7SE +/- 0.006, N = 7SE +/- 0.009, N = 6SE +/- 0.021, N = 6SE +/- 0.003, N = 6SE +/- 0.016, N = 6SE +/- 0.005, N = 7SE +/- 0.019, N = 7SE +/- 0.015, N = 7SE +/- 0.028, N = 7SE +/- 0.008, N = 7SE +/- 0.011, N = 7SE +/- 0.006, N = 7SE +/- 0.014, N = 7SE +/- 0.008, N = 8SE +/- 0.015, N = 85.7355.7344.7924.8294.7704.9435.6625.7407.5078.0946.8497.6034.9165.3174.8675.3115.9065.9194.9235.0744.4564.5791. (CXX) g++ options: -O3 -fPIC -lm

Apache IoTDB

Apache IotDB is a time series database and this benchmark is facilitated using the IoT Benchmaark [https://github.com/thulab/iot-benchmark/]. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgAverage Latency, Fewer Is BetterApache IoTDB 1.2Device Count: 500 - Batch Size Per Write: 100 - Sensor Count: 800 - Client Number: 400EPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P80160240320400SE +/- 0.38, N = 3SE +/- 0.82, N = 3SE +/- 1.96, N = 3SE +/- 3.49, N = 3SE +/- 1.71, N = 3SE +/- 1.87, N = 3SE +/- 1.41, N = 3SE +/- 2.16, N = 15SE +/- 1.12, N = 3SE +/- 3.93, N = 12SE +/- 4.45, N = 3SE +/- 5.20, N = 3SE +/- 5.15, N = 3SE +/- 2.59, N = 12SE +/- 5.07, N = 3SE +/- 3.74, N = 12SE +/- 4.06, N = 3SE +/- 3.47, N = 3SE +/- 2.20, N = 3SE +/- 3.79, N = 8SE +/- 3.41, N = 3SE +/- 3.40, N = 12251.47251.05211.85240.43209.68246.08227.40253.13312.32380.33296.36377.58314.44328.41309.03325.97326.53349.42294.33317.36280.26286.78

QMCPACK

QMCPACK is a modern high-performance open-source Quantum Monte Carlo (QMC) simulation code making use of MPI for this benchmark of the H20 example code. QMCPACK is an open-source production level many-body ab initio Quantum Monte Carlo code for computing the electronic structure of atoms, molecules, and solids. QMCPACK is supported by the U.S. Department of Energy. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgTotal Execution Time - Seconds, Fewer Is BetterQMCPACK 3.17.1Input: Li2_STO_aeEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P4080120160200SE +/- 1.13, N = 3SE +/- 0.40, N = 3SE +/- 0.54, N = 3SE +/- 0.23, N = 3SE +/- 1.06, N = 3SE +/- 0.06, N = 3SE +/- 0.63, N = 3SE +/- 0.42, N = 3SE +/- 1.20, N = 3SE +/- 0.88, N = 3SE +/- 1.04, N = 3SE +/- 1.11, N = 5SE +/- 1.47, N = 7SE +/- 0.50, N = 3SE +/- 0.89, N = 3SE +/- 1.11, N = 3SE +/- 1.03, N = 3SE +/- 0.93, N = 3137.23151.27108.02102.9897.0091.97110.80111.15121.19102.12117.81106.27163.75131.37109.30101.63105.9897.911. (CXX) g++ options: -fopenmp -foffload=disable -finline-limit=1000 -fstrict-aliasing -funroll-all-loops -ffast-math -march=native -O3 -lm -ldl

libavif avifenc

This is a test of the AOMedia libavif library testing the encoding of a JPEG image to AV1 Image Format (AVIF). Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 1.0Encoder Speed: 6, LosslessEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P3691215SE +/- 0.009, N = 6SE +/- 0.011, N = 6SE +/- 0.010, N = 7SE +/- 0.020, N = 7SE +/- 0.014, N = 7SE +/- 0.015, N = 7SE +/- 0.007, N = 6SE +/- 0.025, N = 6SE +/- 0.012, N = 5SE +/- 0.054, N = 5SE +/- 0.010, N = 6SE +/- 0.038, N = 5SE +/- 0.045, N = 6SE +/- 0.027, N = 6SE +/- 0.033, N = 6SE +/- 0.035, N = 6SE +/- 0.016, N = 6SE +/- 0.027, N = 6SE +/- 0.013, N = 7SE +/- 0.022, N = 7SE +/- 0.025, N = 7SE +/- 0.031, N = 77.1827.3015.7995.8465.7575.9506.8536.9869.1889.9608.3599.3516.8367.1216.6057.0388.2017.3886.2786.1725.7845.6131. (CXX) g++ options: -O3 -fPIC -lm

OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 1.0Encoder Speed: 6EPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P1.08652.1733.25954.3465.4325SE +/- 0.016, N = 9SE +/- 0.011, N = 9SE +/- 0.011, N = 10SE +/- 0.008, N = 10SE +/- 0.005, N = 10SE +/- 0.005, N = 9SE +/- 0.002, N = 9SE +/- 0.026, N = 9SE +/- 0.003, N = 8SE +/- 0.023, N = 8SE +/- 0.004, N = 8SE +/- 0.034, N = 8SE +/- 0.017, N = 9SE +/- 0.029, N = 8SE +/- 0.011, N = 9SE +/- 0.022, N = 9SE +/- 0.010, N = 8SE +/- 0.023, N = 15SE +/- 0.022, N = 9SE +/- 0.008, N = 9SE +/- 0.016, N = 9SE +/- 0.009, N = 103.4843.6232.7562.8102.7232.8903.2513.3414.2434.8293.8724.4863.7303.7763.5503.7384.0933.5283.1693.0442.9712.8051. (CXX) g++ options: -O3 -fPIC -lm

Timed Gem5 Compilation

This test times how long it takes to compile Gem5. Gem5 is a simulator for computer system architecture research. Gem5 is widely used for computer architecture research within the industry, academia, and more. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Gem5 Compilation 23.0.1Time To CompileEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P60120180240300SE +/- 1.99, N = 9SE +/- 0.97, N = 3SE +/- 2.24, N = 4SE +/- 0.72, N = 3SE +/- 2.15, N = 3SE +/- 1.16, N = 3SE +/- 1.88, N = 3SE +/- 1.73, N = 3SE +/- 3.60, N = 3SE +/- 0.78, N = 3SE +/- 1.47, N = 3SE +/- 2.61, N = 3SE +/- 2.59, N = 4SE +/- 1.72, N = 3SE +/- 2.11, N = 6SE +/- 1.01, N = 3SE +/- 3.88, N = 3SE +/- 1.04, N = 3SE +/- 0.92, N = 3SE +/- 0.58, N = 3SE +/- 2.17, N = 3SE +/- 0.89, N = 3242.93251.61185.30164.90176.88161.94212.55192.98267.95252.97238.43233.21220.57184.30215.50181.63275.71219.67210.93178.28187.51157.36

Zstd Compression

This test measures the time needed to compress/decompress a sample file (silesia.tar) using Zstd (Zstandard) compression with options for different compression levels / settings. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.4Compression Level: 19, Long Mode - Compression SpeedEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P3691215SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.03, N = 3SE +/- 0.02, N = 3SE +/- 0.03, N = 3SE +/- 0.02, N = 3SE +/- 0.05, N = 3SE +/- 0.00, N = 3SE +/- 0.04, N = 3SE +/- 0.01, N = 3SE +/- 0.03, N = 3SE +/- 0.04, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.06, N = 15SE +/- 0.03, N = 3SE +/- 0.05, N = 3SE +/- 0.03, N = 3SE +/- 0.05, N = 3SE +/- 0.05, N = 3SE +/- 0.04, N = 36.766.748.388.308.458.426.686.645.655.606.196.107.767.627.727.467.527.837.948.169.809.671. (CC) gcc options: -O3 -pthread -lz -llzma

WebP Image Encode

This is a test of Google's libwebp with the cwebp image encode utility and using a sample 6000x4000 pixel JPEG image as the input. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMP/s, More Is BetterWebP Image Encode 1.2.4Encode Settings: Quality 100, Lossless, Highest CompressionEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P0.1350.270.4050.540.675SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 30.480.480.570.570.570.560.480.480.350.350.390.380.550.540.550.540.500.490.520.510.600.591. (CC) gcc options: -fvisibility=hidden -O2 -lm

Zstd Compression

This test measures the time needed to compress/decompress a sample file (silesia.tar) using Zstd (Zstandard) compression with options for different compression levels / settings. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.4Compression Level: 19 - Compression SpeedEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P48121620SE +/- 0.00, N = 3SE +/- 0.03, N = 3SE +/- 0.00, N = 3SE +/- 0.09, N = 3SE +/- 0.03, N = 3SE +/- 0.22, N = 3SE +/- 0.06, N = 3SE +/- 0.03, N = 3SE +/- 0.00, N = 3SE +/- 0.07, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.15, N = 3SE +/- 0.09, N = 15SE +/- 0.11, N = 15SE +/- 0.13, N = 15SE +/- 0.03, N = 3SE +/- 0.17, N = 4SE +/- 0.06, N = 3SE +/- 0.12, N = 3SE +/- 0.21, N = 4SE +/- 0.03, N = 313.913.817.217.017.216.813.813.710.610.611.511.614.413.814.513.313.714.314.615.218.017.81. (CC) gcc options: -O3 -pthread -lz -llzma

SVT-AV1

This is a benchmark of the SVT-AV1 open-source video encoder/decoder. SVT-AV1 was originally developed by Intel as part of their Open Visual Cloud / Scalable Video Technology (SVT). Development of SVT-AV1 has since moved to the Alliance for Open Media as part of upstream AV1 development. SVT-AV1 is a CPU-based multi-threaded video encoder for the AV1 video format with a sample YUV video file. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 2.0Encoder Mode: Preset 12 - Input: Bosphorus 4KEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P4080120160200SE +/- 0.71, N = 6SE +/- 0.78, N = 6SE +/- 0.80, N = 7SE +/- 1.88, N = 15SE +/- 0.43, N = 7SE +/- 0.88, N = 6SE +/- 1.32, N = 6SE +/- 1.41, N = 6SE +/- 0.08, N = 6SE +/- 0.88, N = 5SE +/- 0.15, N = 6SE +/- 1.07, N = 6SE +/- 0.61, N = 7SE +/- 0.83, N = 5SE +/- 0.40, N = 7SE +/- 0.97, N = 6SE +/- 0.48, N = 6SE +/- 1.28, N = 6SE +/- 0.41, N = 7SE +/- 0.25, N = 7SE +/- 0.20, N = 7SE +/- 0.42, N = 7165.09157.36178.52171.22165.75163.80169.23168.78115.35108.50126.59117.68146.10122.09151.72127.55134.07140.76164.25156.52177.86165.501. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

GraphicsMagick

This is a test of GraphicsMagick with its OpenMP implementation that performs various imaging tests on a sample high resolution (currently 15400 x 6940) JPEG image. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.43Operation: Noise-GaussianEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P4080120160200SE +/- 0.33, N = 3SE +/- 0.00, N = 3SE +/- 0.58, N = 3SE +/- 0.67, N = 3SE +/- 0.00, N = 3SE +/- 0.67, N = 3SE +/- 0.58, N = 3SE +/- 0.58, N = 3SE +/- 0.33, N = 3SE +/- 0.33, N = 3SE +/- 0.58, N = 3SE +/- 1.44, N = 4SE +/- 0.33, N = 3SE +/- 0.58, N = 3SE +/- 0.33, N = 3SE +/- 0.33, N = 3SE +/- 0.67, N = 3SE +/- 0.00, N = 3SE +/- 0.33, N = 3SE +/- 1.15, N = 3SE +/- 0.00, N = 3SE +/- 0.88, N = 31231201601781651791511641451181551261501501581641211531581821711941. (CC) gcc options: -fopenmp -O2 -ltiff -ljbig -lsharpyuv -lwebp -lwebpmux -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -lxml2 -lzstd -llzma -lbz2 -lz -lm -lpthread -lgomp

VVenC

VVenC is the Fraunhofer Versatile Video Encoder as a fast/efficient H.266/VVC encoder. The vvenc encoder makes use of SIMD Everywhere (SIMDe). The vvenc software is published under the Clear BSD License. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterVVenC 1.11Video Input: Bosphorus 4K - Video Preset: FasterEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9684XEPYC 9754Xeon 6766EXeon 6780EXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P48121620SE +/- 0.06, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.03, N = 3SE +/- 0.05, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.05, N = 3SE +/- 0.11, N = 3SE +/- 0.13, N = 3SE +/- 0.13, N = 3SE +/- 0.01, N = 3SE +/- 0.13, N = 6SE +/- 0.02, N = 3SE +/- 0.16, N = 3SE +/- 0.08, N = 3SE +/- 0.12, N = 313.9713.6116.7317.0214.7910.3911.1814.1011.9014.3611.9713.1013.0215.0612.5415.9713.261. (CXX) g++ options: -O3 -flto=auto -fno-fat-lto-objects

Video Input: Bosphorus 4K - Video Preset: Faster

EPYC 9684X 2P: The test quit with a non-zero exit status. E: Parameter Check Error: Number of threads out of range (-1

EPYC 9654 2P: The test quit with a non-zero exit status. E: Parameter Check Error: Number of threads out of range (-1

EPYC 9754 2P: The test quit with a non-zero exit status. E: Parameter Check Error: Number of threads out of range (-1

Xeon 6766E 2P: The test quit with a non-zero exit status. E: Parameter Check Error: Number of threads out of range (-1

Xeon 6780E 2P: The test quit with a non-zero exit status. E: Parameter Check Error: Number of threads out of range (-1

WebP Image Encode

This is a test of Google's libwebp with the cwebp image encode utility and using a sample 6000x4000 pixel JPEG image as the input. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMP/s, More Is BetterWebP Image Encode 1.2.4Encode Settings: Quality 100, Highest CompressionEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P0.81451.6292.44353.2584.0725SE +/- 0.00, N = 6SE +/- 0.00, N = 6SE +/- 0.00, N = 6SE +/- 0.00, N = 6SE +/- 0.00, N = 6SE +/- 0.00, N = 6SE +/- 0.00, N = 6SE +/- 0.00, N = 6SE +/- 0.00, N = 5SE +/- 0.00, N = 5SE +/- 0.00, N = 5SE +/- 0.00, N = 5SE +/- 0.00, N = 6SE +/- 0.00, N = 6SE +/- 0.00, N = 6SE +/- 0.00, N = 6SE +/- 0.00, N = 5SE +/- 0.00, N = 5SE +/- 0.00, N = 6SE +/- 0.00, N = 6SE +/- 0.00, N = 6SE +/- 0.00, N = 63.033.033.623.623.613.623.043.032.232.232.492.473.103.093.103.092.822.813.083.073.473.461. (CC) gcc options: -fvisibility=hidden -O2 -lm

OpenFOAM

OpenFOAM is the leading free, open-source software for computational fluid dynamics (CFD). This test profile currently uses the drivaerFastback test case for analyzing automotive aerodynamics or alternatively the older motorBike input. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterOpenFOAM 10Input: drivaerFastback, Medium Mesh Size - Mesh TimeEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P4080120160200163.70188.37136.40140.48118.54135.52167.41192.42153.12134.78150.67159.31182.24162.32160.73162.03148.40139.621. (CXX) g++ options: -std=c++14 -m64 -O3 -ftemplate-depth-100 -fPIC -fuse-ld=bfd -Xlinker --add-needed --no-as-needed -lfiniteVolume -lmeshTools -lparallel -llagrangian -lregionModels -lgenericPatchFields -lOpenFOAM -ldl -lm

PyBench

This test profile reports the total time of the different average timed test results from PyBench. PyBench reports average test times for different functions such as BuiltinFunctionCalls and NestedForLoops, with this total result providing a rough estimate as to Python's average performance on a given system. This test profile runs PyBench each time for 20 rounds. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyBench 2018-02-16Total For Average Test TimesEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P2004006008001000SE +/- 1.45, N = 3SE +/- 2.40, N = 3SE +/- 2.19, N = 3SE +/- 1.86, N = 3SE +/- 2.08, N = 3SE +/- 1.20, N = 3SE +/- 0.58, N = 3SE +/- 1.33, N = 3SE +/- 1.15, N = 3SE +/- 0.33, N = 3SE +/- 0.88, N = 3SE +/- 0.58, N = 3SE +/- 0.33, N = 3SE +/- 0.67, N = 3SE +/- 0.58, N = 3SE +/- 0.67, N = 3SE +/- 2.85, N = 3SE +/- 0.33, N = 3SE +/- 0.33, N = 3SE +/- 1.15, N = 3SE +/- 0.41, N = 4SE +/- 0.48, N = 49769748188228188189749721117111910071005763763762763973971765767691692

Google SynthMark

SynthMark is a cross platform tool for benchmarking CPU performance under a variety of real-time audio workloads. It uses a polyphonic synthesizer model to provide standardized tests for latency, jitter and computational throughput. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgVoices, More Is BetterGoogle SynthMark 20201109Test: VoiceMark_100EPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P2004006008001000SE +/- 0.14, N = 3SE +/- 0.60, N = 3SE +/- 0.55, N = 3SE +/- 0.56, N = 3SE +/- 0.69, N = 3SE +/- 0.72, N = 3SE +/- 0.45, N = 3SE +/- 0.88, N = 3SE +/- 0.58, N = 3SE +/- 0.33, N = 3SE +/- 0.18, N = 3SE +/- 0.06, N = 3SE +/- 0.26, N = 3SE +/- 0.30, N = 3SE +/- 0.24, N = 3SE +/- 0.48, N = 3SE +/- 7.09, N = 3SE +/- 0.53, N = 3SE +/- 0.22, N = 3SE +/- 1.51, N = 3SE +/- 0.13, N = 3SE +/- 0.38, N = 3655.24656.25783.78782.32783.42783.20655.80655.05494.05494.38540.24538.91711.10710.92712.01712.09555.60548.36711.38712.70799.72799.491. (CXX) g++ options: -lm -lpthread -std=c++11 -Ofast

Timed Mesa Compilation

This test profile times how long it takes to compile Mesa with Meson/Ninja. For minimizing build dependencies and avoid versioning conflicts, test this is just the core Mesa build without LLVM or the extra Gallium3D/Mesa drivers enabled. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Mesa Compilation 24.0Time To CompileEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P612182430SE +/- 0.04, N = 3SE +/- 0.02, N = 3SE +/- 0.03, N = 3SE +/- 0.02, N = 4SE +/- 0.02, N = 3SE +/- 0.08, N = 4SE +/- 0.03, N = 3SE +/- 0.12, N = 3SE +/- 0.06, N = 3SE +/- 0.08, N = 3SE +/- 0.05, N = 3SE +/- 0.06, N = 3SE +/- 0.03, N = 3SE +/- 0.07, N = 3SE +/- 0.08, N = 3SE +/- 0.17, N = 3SE +/- 0.05, N = 3SE +/- 0.05, N = 3SE +/- 0.07, N = 3SE +/- 0.12, N = 3SE +/- 0.07, N = 3SE +/- 0.05, N = 421.0421.5316.9616.4116.6716.4019.9119.5625.8925.8823.4123.4620.1818.4719.6518.1423.6621.4419.2318.2917.2616.18

SecureMark

SecureMark is an objective, standardized benchmarking framework for measuring the efficiency of cryptographic processing solutions developed by EEMBC. SecureMark-TLS is benchmarking Transport Layer Security performance with a focus on IoT/edge computing. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgmarks, More Is BetterSecureMark 1.0.4Benchmark: SecureMark-TLSEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P70K140K210K280K350KSE +/- 372.96, N = 3SE +/- 542.88, N = 3SE +/- 361.20, N = 3SE +/- 389.81, N = 3SE +/- 415.71, N = 3SE +/- 809.90, N = 3SE +/- 457.42, N = 3SE +/- 553.62, N = 3SE +/- 553.57, N = 3SE +/- 722.69, N = 3SE +/- 406.59, N = 3SE +/- 1219.44, N = 3SE +/- 256.85, N = 3SE +/- 384.08, N = 3SE +/- 670.43, N = 3SE +/- 196.24, N = 3SE +/- 372.88, N = 3SE +/- 285.52, N = 3SE +/- 625.56, N = 3SE +/- 330.95, N = 3SE +/- 209.97, N = 3SE +/- 411.11, N = 32500242501622983412996103008333017402506952510751967401972982200512175362776472775892772602772982313572310762772052754723098963084341. (CC) gcc options: -pedantic -O3

OpenFOAM

OpenFOAM is the leading free, open-source software for computational fluid dynamics (CFD). This test profile currently uses the drivaerFastback test case for analyzing automotive aerodynamics or alternatively the older motorBike input. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterOpenFOAM 10Input: drivaerFastback, Small Mesh Size - Mesh TimeEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P91827364533.6736.8228.0327.7425.9326.8230.3829.4731.7832.4832.0028.8439.1236.8631.3835.6031.7029.331. (CXX) g++ options: -std=c++14 -m64 -O3 -ftemplate-depth-100 -fPIC -fuse-ld=bfd -Xlinker --add-needed --no-as-needed -lfiniteVolume -lmeshTools -lparallel -llagrangian -lregionModels -lgenericPatchFields -lOpenFOAM -ldl -lm

Liquid-DSP

LiquidSDR's Liquid-DSP is a software-defined radio (SDR) digital signal processing library. This test profile runs a multi-threaded benchmark of this SDR/DSP library focused on embedded platform usage. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 1.6Threads: 64 - Buffer Length: 256 - Filter Length: 32EPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P500M1000M1500M2000M2500MSE +/- 3090487.20, N = 3SE +/- 3256958.36, N = 3SE +/- 2810891.52, N = 3SE +/- 1567730.14, N = 3SE +/- 3000185.18, N = 3SE +/- 2510644.01, N = 3SE +/- 1550627.11, N = 3SE +/- 1462114.15, N = 3SE +/- 1379613.47, N = 3SE +/- 1003881.36, N = 3SE +/- 808290.38, N = 3SE +/- 4028647.42, N = 3SE +/- 688799.28, N = 3SE +/- 2206304.10, N = 3SE +/- 692820.32, N = 3SE +/- 3017909.50, N = 3SE +/- 3209534.41, N = 3SE +/- 9052685.30, N = 3SE +/- 3167192.94, N = 3SE +/- 3300505.01, N = 3SE +/- 27191440.65, N = 3SE +/- 17236814.61, N = 318713333331776866667228276666722820666672287466667227930000018987666671894966667184140000017805333332057300000198930000016402666671963233333167970000020904666671561766667173116666718905666672025000000192776666721546333331. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 1.6Threads: 1 - Buffer Length: 256 - Filter Length: 32EPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P9M18M27M36M45MSE +/- 2333.33, N = 3SE +/- 881.92, N = 3SE +/- 7753.14, N = 3SE +/- 13503.09, N = 3SE +/- 7023.77, N = 3SE +/- 19139.84, N = 3SE +/- 6984.11, N = 3SE +/- 2185.81, N = 3SE +/- 0.00, N = 3SE +/- 881.92, N = 3SE +/- 1527.53, N = 3SE +/- 881.92, N = 3SE +/- 1666.67, N = 3SE +/- 1201.85, N = 3SE +/- 3000.00, N = 3SE +/- 1452.97, N = 3SE +/- 1000.00, N = 3SE +/- 577.35, N = 3SE +/- 1527.53, N = 3SE +/- 1154.70, N = 3SE +/- 417042.80, N = 5SE +/- 419600.12, N = 5298996672989933336068333360330003606600036040000299073332989333331726000317056673525900035190667365376673649766736539000365213333199500031992000365060003646100040244000389506001. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

ONNX Runtime

OpenBenchmarking.orgWatts, Fewer Is BetterONNX Runtime 1.17CPU Power Consumption MonitorEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Platinum 8380Xeon Platinum 8380 2P90180270360450Min: 18.14 / Avg: 109.41 / Max: 118.96Min: 16.01 / Avg: 98.3 / Max: 106.86Min: 26.28 / Avg: 211.37 / Max: 231.46Min: 54.43 / Avg: 417.34 / Max: 450.65Min: 31.9 / Avg: 250.92 / Max: 275.39Min: 60.67 / Avg: 475.62 / Max: 514.58Min: 19.69 / Avg: 171.56 / Max: 188.27Min: 40.25 / Avg: 308.06 / Max: 331.38Min: 43.64 / Avg: 132.23 / Max: 144.22Min: 104.4 / Avg: 226.53 / Max: 245.57Min: 43.52 / Avg: 154.49 / Max: 168.64Min: 106.43 / Avg: 248.46 / Max: 271.28Min: 53.43 / Avg: 226.19 / Max: 247.32Min: 103.45 / Avg: 419.57 / Max: 461.32

OpenBenchmarking.orgWatts, Fewer Is BetterONNX Runtime 1.17CPU Power Consumption MonitorEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Platinum 8380Xeon Platinum 8380 2P90180270360450Min: 16.8 / Avg: 119.38 / Max: 129.78Min: 16.97 / Avg: 101.89 / Max: 112.56Min: 29.64 / Avg: 222.91 / Max: 240.57Min: 56.36 / Avg: 405.91 / Max: 434.32Min: 33.42 / Avg: 261.74 / Max: 283.2Min: 63.67 / Avg: 460.32 / Max: 497.92Min: 20.33 / Avg: 188.2 / Max: 202.92Min: 38.39 / Avg: 302.95 / Max: 323.86Min: 43.62 / Avg: 139.52 / Max: 148.88Min: 104.06 / Avg: 210.79 / Max: 227.9Min: 43.51 / Avg: 163.29 / Max: 175Min: 106.24 / Avg: 233.19 / Max: 250.31Min: 51.89 / Avg: 246.13 / Max: 266.29Min: 95.98 / Avg: 424.24 / Max: 455.9

OpenBenchmarking.orgWatts, Fewer Is BetterONNX Runtime 1.17CPU Power Consumption MonitorEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Platinum 8380Xeon Platinum 8380 2P120240360480600Min: 19.31 / Avg: 140.51 / Max: 154.48Min: 17.45 / Avg: 121.04 / Max: 134.63Min: 27.94 / Avg: 273.66 / Max: 300.92Min: 60.03 / Avg: 522.44 / Max: 571.64Min: 33.76 / Avg: 321.88 / Max: 360.42Min: 64.5 / Avg: 611.91 / Max: 674.71Min: 21.08 / Avg: 240.98 / Max: 267.52Min: 41.83 / Avg: 453.96 / Max: 496.3Min: 43.7 / Avg: 200.72 / Max: 216.16Min: 105.71 / Avg: 414.92 / Max: 451.7Min: 43.58 / Avg: 243.68 / Max: 263.63Min: 108.32 / Avg: 473.62 / Max: 514.95Min: 53.6 / Avg: 252.85 / Max: 280.59Min: 100.08 / Avg: 498.61 / Max: 537.57

CPU Power Consumption Monitor

OpenBenchmarking.orgWattsCPU Power Consumption MonitorPhoronix Test Suite System MonitoringEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P170340510680850Min: 8.43 / Avg: 128.7 / Max: 184.62Min: 9.26 / Avg: 114.13 / Max: 155.71Min: 14.69 / Avg: 244.69 / Max: 373.1Min: 35.7 / Avg: 464.49 / Max: 751.79Min: 17.06 / Avg: 290.08 / Max: 413.51Min: 33.66 / Avg: 525.49 / Max: 837.69Min: 10.09 / Avg: 225.05 / Max: 397.44Min: 20.22 / Avg: 375.51 / Max: 735.74Min: 21.86 / Avg: 142.1 / Max: 271.22Min: 52.85 / Avg: 291.05 / Max: 542.48Min: 21.7 / Avg: 169.1 / Max: 357.69Min: 53.44 / Avg: 321.01 / Max: 713.33Min: 38.11 / Avg: 291.53 / Max: 379.76Min: 102.49 / Avg: 566.6 / Max: 756.48Min: 38.16 / Avg: 295.53 / Max: 384.53Min: 95.52 / Avg: 569.8 / Max: 760.61Min: 26.31 / Avg: 237.91 / Max: 292.14Min: 51.38 / Avg: 437.37 / Max: 583.47Min: 30.38 / Avg: 278.1 / Max: 383.24Min: 87.48 / Avg: 517.33 / Max: 758.17Min: 17.77 / Avg: 260.08 / Max: 405.42Min: 39.72 / Avg: 455.07 / Max: 946.96

Stockfish

OpenBenchmarking.orgWatts, Fewer Is BetterStockfish 16.1CPU Power Consumption MonitorEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P140280420560700Min: 17.26 / Avg: 174.36 / Max: 184.62Min: 16.19 / Avg: 145.98 / Max: 155.71Min: 30.05 / Avg: 347.3 / Max: 373.1Min: 57.4 / Avg: 686.5 / Max: 751.79Min: 35.5 / Avg: 386.38 / Max: 410.66Min: 70.77 / Avg: 766.5 / Max: 822.06Min: 21.51 / Avg: 332.06 / Max: 363.69Min: 37.25 / Avg: 640.56 / Max: 735.74Min: 43.78 / Avg: 240.94 / Max: 270.17Min: 105.79 / Avg: 474.56 / Max: 541.15Min: 43.61 / Avg: 310.08 / Max: 337.09Min: 109.43 / Avg: 618.97 / Max: 701.47Min: 71.31 / Avg: 341.39 / Max: 379.06Min: 203.83 / Avg: 679.75 / Max: 756.48Min: 74.29 / Avg: 341.12 / Max: 366.15Min: 195.85 / Avg: 680.45 / Max: 758.53Min: 53.05 / Avg: 263.42 / Max: 290.77Min: 100.78 / Avg: 519.4 / Max: 581.59Min: 56.83 / Avg: 339.56 / Max: 379.91Min: 166.29 / Avg: 678.39 / Max: 758.17Min: 22.35 / Avg: 337.72 / Max: 370.84Min: 78.55 / Avg: 672.28 / Max: 755.5

OpenBenchmarking.orgNodes Per Second Per Watt, More Is BetterStockfish 16.1Chess BenchmarkEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P130K260K390K520K650K568916.36621037.11569277.48540060.41555213.84520707.98571475.98470216.10509643.71496138.40403742.35431231.39199243.06202981.45215737.78219573.26193986.52201379.09285328.34276776.39325017.74331127.60

OpenBenchmarking.orgNodes Per Second, More Is BetterStockfish 16.1Chess BenchmarkEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P90M180M270M360M450MSE +/- 2397455.91, N = 12SE +/- 2147688.02, N = 12SE +/- 3170744.86, N = 15SE +/- 2356843.91, N = 3SE +/- 2268830.04, N = 3SE +/- 919073.22, N = 3SE +/- 4652276.19, N = 12SE +/- 7961094.38, N = 12SE +/- 3565305.92, N = 15SE +/- 2692064.58, N = 4SE +/- 1441726.26, N = 3SE +/- 3095674.84, N = 3SE +/- 1751369.24, N = 12SE +/- 4344961.90, N = 10SE +/- 629927.17, N = 3SE +/- 2925715.37, N = 11SE +/- 1466028.98, N = 9SE +/- 1325249.25, N = 3SE +/- 1304590.97, N = 3SE +/- 2148606.38, N = 4SE +/- 2966712.90, N = 9SE +/- 2482737.87, N = 39919814490658156197708350370751530214524659399124223189763799301202232122794246235445499125194066266919825680190881379772037359223014940908251099545104597200968874791877617691097663452226103781. (CXX) g++ options: -lgcov -m64 -lpthread -fno-exceptions -std=c++17 -fno-peel-loops -fno-tracer -pedantic -O3 -funroll-loops -msse -msse3 -mpopcnt -mavx2 -mbmi -msse4.1 -mssse3 -msse2 -mbmi2 -flto -flto-partition=one -flto=jobserver

ONNX Runtime

ONNX Runtime is developed by Microsoft and partners as a open-source, cross-platform, high performance machine learning inferencing and training accelerator. This test profile runs the ONNX Runtime with various models available from the ONNX Model Zoo. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: StandardEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P1122334455SE +/- 0.63, N = 15SE +/- 0.61, N = 15SE +/- 0.50, N = 15SE +/- 0.61, N = 15SE +/- 0.61, N = 15SE +/- 0.40, N = 15SE +/- 0.45, N = 15SE +/- 0.23, N = 15SE +/- 0.08, N = 3SE +/- 0.36, N = 11SE +/- 0.06, N = 3SE +/- 0.35, N = 3SE +/- 0.11, N = 3SE +/- 0.40, N = 3SE +/- 0.31, N = 3SE +/- 0.33, N = 3SE +/- 0.01, N = 3SE +/- 0.35, N = 3SE +/- 0.04, N = 3SE +/- 0.12, N = 3SE +/- 0.09, N = 3SE +/- 0.09, N = 327.9326.8323.9225.3221.5822.7926.4527.9041.0847.2036.7843.8133.3336.2333.9936.0028.0229.7629.4129.7529.0228.851. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.17Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: StandardEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P1122334455SE +/- 0.87, N = 15SE +/- 0.82, N = 15SE +/- 0.91, N = 15SE +/- 0.92, N = 15SE +/- 1.36, N = 15SE +/- 0.76, N = 15SE +/- 0.63, N = 15SE +/- 0.27, N = 15SE +/- 0.05, N = 3SE +/- 0.16, N = 11SE +/- 0.05, N = 3SE +/- 0.18, N = 3SE +/- 0.09, N = 3SE +/- 0.31, N = 3SE +/- 0.27, N = 3SE +/- 0.26, N = 3SE +/- 0.01, N = 3SE +/- 0.40, N = 3SE +/- 0.05, N = 3SE +/- 0.13, N = 3SE +/- 0.10, N = 3SE +/- 0.11, N = 336.0837.5342.0739.8046.8844.0637.9635.8724.3421.2027.1822.8330.0027.6129.4327.7835.6933.6034.0033.6134.4634.661. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: bertsquad-12 - Device: CPU - Executor: StandardEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P306090120150SE +/- 0.51, N = 3SE +/- 1.26, N = 3SE +/- 0.17, N = 3SE +/- 0.90, N = 6SE +/- 0.18, N = 3SE +/- 2.80, N = 15SE +/- 0.70, N = 15SE +/- 2.33, N = 12SE +/- 0.05, N = 3SE +/- 6.85, N = 15SE +/- 0.06, N = 3SE +/- 6.88, N = 15SE +/- 0.44, N = 3SE +/- 0.68, N = 3SE +/- 0.23, N = 3SE +/- 1.12, N = 15SE +/- 1.84, N = 12SE +/- 0.29, N = 3SE +/- 0.17, N = 3SE +/- 0.62, N = 3SE +/- 0.04, N = 3SE +/- 0.44, N = 380.7286.6572.1293.8371.5690.0687.6693.64124.06155.90111.87141.5747.2460.1149.9755.9048.4754.2849.6460.3639.7544.601. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.17Model: bertsquad-12 - Device: CPU - Executor: StandardEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P612182430SE +/- 0.07825, N = 3SE +/- 0.16639, N = 3SE +/- 0.03352, N = 3SE +/- 0.10002, N = 6SE +/- 0.03564, N = 3SE +/- 0.38561, N = 15SE +/- 0.09294, N = 15SE +/- 0.26635, N = 12SE +/- 0.00331, N = 3SE +/- 0.31004, N = 15SE +/- 0.00509, N = 3SE +/- 0.36771, N = 15SE +/- 0.19764, N = 3SE +/- 0.18711, N = 3SE +/- 0.09194, N = 3SE +/- 0.35497, N = 15SE +/- 0.58074, N = 12SE +/- 0.09869, N = 3SE +/- 0.07031, N = 3SE +/- 0.16743, N = 3SE +/- 0.02370, N = 3SE +/- 0.21982, N = 312.3884011.5447013.8647010.6615013.9745011.2707011.4182010.751888.060136.604718.938337.3128521.1702016.6394020.0103017.9873020.8723018.4222020.1453016.5705025.1591022.425101. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: fcn-resnet101-11 - Device: CPU - Executor: StandardEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P50100150200250SE +/- 6.87, N = 12SE +/- 7.19, N = 15SE +/- 4.84, N = 15SE +/- 0.35, N = 3SE +/- 4.76, N = 12SE +/- 2.18, N = 15SE +/- 2.29, N = 15SE +/- 2.91, N = 3SE +/- 0.09, N = 3SE +/- 0.06, N = 3SE +/- 0.21, N = 3SE +/- 0.13, N = 3SE +/- 3.36, N = 15SE +/- 5.82, N = 12SE +/- 6.41, N = 15SE +/- 2.59, N = 15SE +/- 2.32, N = 15SE +/- 1.55, N = 15SE +/- 0.09, N = 3SE +/- 0.69, N = 15SE +/- 0.71, N = 3SE +/- 0.44, N = 3216.70226.63182.02220.35178.03182.27166.79203.57188.30194.11174.14182.36139.10121.67155.79121.78160.53110.97116.3292.35109.67100.741. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.17Model: fcn-resnet101-11 - Device: CPU - Executor: StandardEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P3691215SE +/- 0.14467, N = 12SE +/- 0.11914, N = 15SE +/- 0.15150, N = 15SE +/- 0.00718, N = 3SE +/- 0.16422, N = 12SE +/- 0.06453, N = 15SE +/- 0.08489, N = 15SE +/- 0.07023, N = 3SE +/- 0.00241, N = 3SE +/- 0.00154, N = 3SE +/- 0.00692, N = 3SE +/- 0.00381, N = 3SE +/- 0.15651, N = 15SE +/- 0.34632, N = 12SE +/- 0.22869, N = 15SE +/- 0.16487, N = 15SE +/- 0.08940, N = 15SE +/- 0.11577, N = 15SE +/- 0.00664, N = 3SE +/- 0.07619, N = 15SE +/- 0.05824, N = 3SE +/- 0.04271, N = 34.664914.465335.550184.538175.665085.497116.011644.914205.310505.151665.742345.483437.241878.399626.549658.260166.247409.033678.5971910.836239.118859.926841. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

srsRAN Project

OpenBenchmarking.orgWatts, Fewer Is BettersrsRAN Project 23.10.1-20240325CPU Power Consumption MonitorEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P130260390520650Min: 17.85 / Avg: 136.58 / Max: 166.81Min: 16.71 / Avg: 117.93 / Max: 142.26Min: 28.12 / Avg: 276.24 / Max: 341.73Min: 55.25 / Avg: 559.64 / Max: 633.66Min: 32.26 / Avg: 321.41 / Max: 408.75Min: 65.52 / Avg: 632.5 / Max: 723.62Min: 21.57 / Avg: 261.04 / Max: 306.84Min: 41.23 / Avg: 514.74 / Max: 612.62Min: 43.55 / Avg: 205.11 / Max: 263.97Min: 103.72 / Avg: 426.81 / Max: 506.19Min: 43.52 / Avg: 245.99 / Max: 312.37Min: 104.56 / Avg: 509.97 / Max: 630.46Min: 74.5 / Avg: 281.29 / Max: 379.76Min: 195.95 / Avg: 604.92 / Max: 745.23Min: 74.87 / Avg: 289.12 / Max: 373.87Min: 189.97 / Avg: 617.8 / Max: 721.97Min: 51.25 / Avg: 229.96 / Max: 288.72Min: 100.98 / Avg: 470 / Max: 560.27Min: 60.24 / Avg: 283.1 / Max: 369.61Min: 148.45 / Avg: 589.02 / Max: 721.35Min: 25.9 / Avg: 266.9 / Max: 379.06Min: 68.27 / Avg: 537.03 / Max: 710

OpenBenchmarking.orgMbps Per Watt, More Is BettersrsRAN Project 23.10.1-20240325Test: PDSCH Processor Benchmark, Throughput TotalEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P4080120160200141.87165.23100.2640.9891.4241.0796.5258.04133.0174.22121.1664.7375.6849.9852.1619.2158.8740.3187.2151.1298.8356.88

OpenBenchmarking.orgMbps, More Is BettersrsRAN Project 23.10.1-20240325Test: PDSCH Processor Benchmark, Throughput TotalEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P7K14K21K28K35KSE +/- 207.19, N = 5SE +/- 58.21, N = 3SE +/- 357.13, N = 12SE +/- 526.01, N = 15SE +/- 348.28, N = 4SE +/- 343.97, N = 3SE +/- 237.63, N = 3SE +/- 2115.57, N = 15SE +/- 150.02, N = 4SE +/- 319.61, N = 3SE +/- 134.28, N = 4SE +/- 242.64, N = 3SE +/- 938.95, N = 15SE +/- 175.78, N = 4SE +/- 281.72, N = 15SE +/- 490.54, N = 15SE +/- 44.42, N = 3SE +/- 308.01, N = 15SE +/- 236.27, N = 4SE +/- 312.17, N = 3SE +/- 298.34, N = 15SE +/- 356.81, N = 1519375.919485.827695.222931.829384.925977.425194.629877.127281.931677.229804.433010.521286.630236.015081.011866.713537.718943.624688.530108.726378.130547.61. (CXX) g++ options: -O3 -march=native -mavx2 -mavx -msse4.1 -mfma -fno-trapping-math -fno-math-errno -ldl

SVT-AV1

OpenBenchmarking.orgWatts, Fewer Is BetterSVT-AV1 2.0CPU Power Consumption MonitorEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P100200300400500Min: 16.06 / Avg: 60.52 / Max: 126.9Min: 14.1 / Avg: 55.32 / Max: 107.14Min: 25.79 / Avg: 105.15 / Max: 208.71Min: 56.44 / Avg: 206.94 / Max: 347.98Min: 31.67 / Avg: 118.98 / Max: 227.28Min: 60.69 / Avg: 231.16 / Max: 380.35Min: 19.23 / Avg: 84.14 / Max: 169.24Min: 38.31 / Avg: 171.31 / Max: 283.81Min: 43.57 / Avg: 69.02 / Max: 130.57Min: 104.02 / Avg: 131.43 / Max: 193.79Min: 43.43 / Avg: 73.7 / Max: 142.81Min: 106.17 / Avg: 142.03 / Max: 219.81Min: 73.18 / Avg: 187.24 / Max: 299.74Min: 196.97 / Avg: 398.41 / Max: 555.31Min: 69.14 / Avg: 187.17 / Max: 307.31Min: 193.69 / Avg: 401.02 / Max: 565.3Min: 49.33 / Avg: 128.89 / Max: 223.87Min: 96.21 / Avg: 219.64 / Max: 381.28Min: 59.06 / Avg: 155.98 / Max: 273.08Min: 160.44 / Avg: 317.58 / Max: 460.42Min: 26.49 / Avg: 131.08 / Max: 275.44Min: 70.69 / Avg: 247.31 / Max: 459.08

OpenBenchmarking.orgFrames Per Second Per Watt, More Is BetterSVT-AV1 2.0Encoder Mode: Preset 13 - Input: Bosphorus 4KEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P0.62391.24781.87172.49563.11952.6572.7731.6440.8081.3660.6981.9420.9331.6600.8241.6910.8210.7730.3080.8010.3101.0330.6321.0420.4861.3340.659

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 2.0Encoder Mode: Preset 13 - Input: Bosphorus 4KEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P4080120160200SE +/- 4.25, N = 15SE +/- 3.84, N = 15SE +/- 4.38, N = 15SE +/- 4.23, N = 15SE +/- 3.81, N = 15SE +/- 1.54, N = 15SE +/- 4.48, N = 15SE +/- 4.46, N = 15SE +/- 1.01, N = 8SE +/- 0.80, N = 15SE +/- 1.12, N = 7SE +/- 1.79, N = 15SE +/- 1.44, N = 15SE +/- 1.63, N = 15SE +/- 1.62, N = 15SE +/- 1.67, N = 15SE +/- 1.11, N = 15SE +/- 3.34, N = 15SE +/- 2.31, N = 15SE +/- 2.18, N = 15SE +/- 2.83, N = 15SE +/- 2.84, N = 15160.79153.42172.88167.22162.48161.34163.41159.75114.54108.29124.60116.62144.70122.62150.00124.26133.19138.72162.47154.50174.83162.981. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

LuxCoreRender

OpenBenchmarking.orgWatts, Fewer Is BetterLuxCoreRender 2.6CPU Power Consumption MonitorEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P150300450600750Min: 19.16 / Avg: 150.1 / Max: 167.85Min: 17.62 / Avg: 128.09 / Max: 142.09Min: 27.54 / Avg: 296.6 / Max: 330.72Min: 57.15 / Avg: 586.21 / Max: 670.16Min: 33.09 / Avg: 373.72 / Max: 411.13Min: 66.69 / Avg: 722.97 / Max: 825.83Min: 22.04 / Avg: 298.61 / Max: 336.88Min: 41.55 / Avg: 551.09 / Max: 677.8Min: 43.68 / Avg: 191.46 / Max: 222.84Min: 104.86 / Avg: 321.3 / Max: 495.12Min: 43.49 / Avg: 223.98 / Max: 283.31Min: 107.87 / Avg: 364.17 / Max: 576.89Min: 75.77 / Avg: 326.79 / Max: 375.2Min: 204.79 / Avg: 656.04 / Max: 751.44Min: 83.75 / Avg: 327.46 / Max: 377.5Min: 201.92 / Avg: 656.25 / Max: 748.81Min: 53 / Avg: 249.69 / Max: 290.48Min: 100.16 / Avg: 499.14 / Max: 582.6Min: 61.77 / Avg: 323.08 / Max: 377.72Min: 172.79 / Avg: 646.27 / Max: 748.56Min: 34.75 / Avg: 320.73 / Max: 377.48Min: 82.44 / Avg: 639.12 / Max: 751.58

OpenBenchmarking.orgM samples/sec Per Watt, More Is BetterLuxCoreRender 2.6Scene: Orange Juice - Acceleration: CPUEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P0.02270.04540.06810.09080.11350.0920.1010.0720.0510.0660.0460.0800.0590.0830.0530.0710.0480.0360.0260.0380.0250.0350.0290.0420.0290.0460.031

OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender 2.6Scene: Orange Juice - Acceleration: CPUEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P816243240SE +/- 0.05, N = 3SE +/- 0.05, N = 3SE +/- 0.18, N = 15SE +/- 0.84, N = 15SE +/- 0.28, N = 5SE +/- 1.06, N = 15SE +/- 0.07, N = 3SE +/- 1.12, N = 15SE +/- 0.19, N = 3SE +/- 0.46, N = 12SE +/- 0.06, N = 3SE +/- 0.46, N = 15SE +/- 0.10, N = 3SE +/- 0.16, N = 15SE +/- 0.04, N = 3SE +/- 0.28, N = 15SE +/- 0.03, N = 3SE +/- 0.06, N = 3SE +/- 0.07, N = 3SE +/- 0.12, N = 3SE +/- 0.05, N = 3SE +/- 0.30, N = 1513.8113.0021.3229.6124.6933.0823.7632.2615.9016.8815.8317.4511.8616.9112.5016.648.8214.3113.4618.7014.7419.91

OpenBenchmarking.orgWatts, Fewer Is BetterLuxCoreRender 2.6CPU Power Consumption MonitorEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P150300450600750Min: 18.62 / Avg: 156.14 / Max: 171.55Min: 18.19 / Avg: 128.95 / Max: 140.58Min: 29.9 / Avg: 299.39 / Max: 326.71Min: 59.66 / Avg: 573.93 / Max: 661.76Min: 34.75 / Avg: 384.12 / Max: 412.45Min: 65.89 / Avg: 739.45 / Max: 837.69Min: 20.73 / Avg: 311.89 / Max: 340.37Min: 42.95 / Avg: 561.1 / Max: 675.69Min: 43.65 / Avg: 180.3 / Max: 223.44Min: 104.02 / Avg: 295.99 / Max: 409.35Min: 43.51 / Avg: 225.44 / Max: 288.32Min: 79.88 / Avg: 341.83 / Max: 482.57Min: 74.56 / Avg: 331.26 / Max: 374.04Min: 195.7 / Avg: 665.76 / Max: 753.2Min: 72.86 / Avg: 330.29 / Max: 377.65Min: 203.55 / Avg: 668.4 / Max: 754.98Min: 51.32 / Avg: 255.3 / Max: 289.97Min: 101.11 / Avg: 511.71 / Max: 580Min: 59.67 / Avg: 330.53 / Max: 373.83Min: 173.98 / Avg: 664.56 / Max: 753.01Min: 24.28 / Avg: 326.43 / Max: 375.69Min: 76.68 / Avg: 654.92 / Max: 755.35

OpenBenchmarking.orgM samples/sec Per Watt, More Is BetterLuxCoreRender 2.6Scene: DLSC - Acceleration: CPUEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P0.01490.02980.04470.05960.07450.0600.0660.0480.0310.0420.0310.0540.0390.0520.0260.0450.0230.0230.0150.0240.0160.0220.0180.0260.0170.0290.019

OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender 2.6Scene: DLSC - Acceleration: CPUEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P510152025SE +/- 0.06, N = 15SE +/- 0.03, N = 3SE +/- 0.13, N = 3SE +/- 0.12, N = 3SE +/- 0.18, N = 15SE +/- 0.91, N = 15SE +/- 0.28, N = 15SE +/- 1.02, N = 15SE +/- 0.02, N = 3SE +/- 0.22, N = 12SE +/- 0.06, N = 3SE +/- 0.22, N = 15SE +/- 0.08, N = 3SE +/- 0.12, N = 3SE +/- 0.10, N = 3SE +/- 0.20, N = 15SE +/- 0.05, N = 3SE +/- 0.04, N = 3SE +/- 0.06, N = 15SE +/- 0.23, N = 15SE +/- 0.02, N = 3SE +/- 0.24, N = 159.398.4814.2917.8916.2122.5816.7922.009.407.7110.097.997.4610.178.0010.445.638.988.7211.129.3812.74

NAS Parallel Benchmarks

OpenBenchmarking.orgWatts, Fewer Is BetterNAS Parallel Benchmarks 3.4CPU Power Consumption MonitorEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P140280420560700Min: 18.8 / Avg: 129.08 / Max: 158.73Min: 17.1 / Avg: 113.27 / Max: 135.62Min: 26.47 / Avg: 242.89 / Max: 334.43Min: 56.44 / Avg: 416.97 / Max: 683.16Min: 31.93 / Avg: 307.77 / Max: 409.54Min: 65.8 / Avg: 495.73 / Max: 819.01Min: 21.19 / Avg: 234.01 / Max: 336.9Min: 40.5 / Avg: 379.03 / Max: 677.9Min: 73.35 / Avg: 254.67 / Max: 351.04Min: 200.97 / Avg: 537.97 / Max: 722.6Min: 76.21 / Avg: 270.13 / Max: 345.76Min: 196.31 / Avg: 561.84 / Max: 754.16Min: 51.37 / Avg: 242.36 / Max: 290.59Min: 100.12 / Avg: 440.29 / Max: 581.61Min: 57.58 / Avg: 291.31 / Max: 376.98Min: 155.56 / Avg: 520.43 / Max: 752.57Min: 26.35 / Avg: 276.68 / Max: 375.06Min: 68.69 / Avg: 471.7 / Max: 753.27

OpenBenchmarking.orgTotal Mop/s Per Watt, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: EP.DEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P132639526549.7150.7243.8646.5637.1244.7253.7458.0921.0720.3923.8622.7718.4820.1725.9628.7229.2433.93

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: EP.DEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P5K10K15K20K25KSE +/- 14.68, N = 3SE +/- 50.01, N = 8SE +/- 122.47, N = 15SE +/- 530.31, N = 15SE +/- 309.03, N = 15SE +/- 602.37, N = 15SE +/- 367.88, N = 12SE +/- 1274.85, N = 12SE +/- 155.10, N = 12SE +/- 4.83, N = 4SE +/- 6.53, N = 3SE +/- 10.93, N = 4SE +/- 13.82, N = 3SE +/- 17.53, N = 3SE +/- 6.77, N = 3SE +/- 100.23, N = 4SE +/- 22.33, N = 3SE +/- 30.19, N = 46416.345745.0410652.0319414.9411424.0522166.6012575.3022017.755366.6910970.456445.0912793.014479.288880.827562.8014946.768089.1416004.071. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz 2. Open MPI 4.1.6

Pennant

OpenBenchmarking.orgWatts, Fewer Is BetterPennant 1.0.1CPU Power Consumption MonitorEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P140280420560700Min: 18.14 / Avg: 107.18 / Max: 164.25Min: 16.11 / Avg: 95.67 / Max: 145.23Min: 27.07 / Avg: 170.76 / Max: 330.73Min: 54.46 / Avg: 322.18 / Max: 670.5Min: 33.15 / Avg: 196.35 / Max: 409.53Min: 63.33 / Avg: 370.49 / Max: 818.97Min: 20.01 / Avg: 156.67 / Max: 328.66Min: 41.42 / Avg: 291.74 / Max: 665.7Min: 71.8 / Avg: 241.62 / Max: 375.61Min: 187.85 / Avg: 448.22 / Max: 752.01Min: 74.45 / Avg: 234.93 / Max: 375.6Min: 191.18 / Avg: 450.17 / Max: 753.29Min: 52.7 / Avg: 215.77 / Max: 289.7Min: 100.92 / Avg: 344.84 / Max: 581.63Min: 57.31 / Avg: 222.1 / Max: 377.34Min: 144.69 / Avg: 414.55 / Max: 753.5Min: 25.17 / Avg: 191.11 / Max: 377.76Min: 64.47 / Avg: 342.65 / Max: 753.04

OpenBenchmarking.orgHydro Cycle Time - Seconds, Fewer Is BetterPennant 1.0.1Test: leblancbigEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P3691215SE +/- 0.057580, N = 6SE +/- 0.045713, N = 13SE +/- 0.115723, N = 15SE +/- 0.063684, N = 15SE +/- 0.115724, N = 15SE +/- 0.055800, N = 15SE +/- 0.115702, N = 15SE +/- 0.022246, N = 15SE +/- 0.025580, N = 6SE +/- 0.010204, N = 7SE +/- 0.023904, N = 7SE +/- 0.008354, N = 7SE +/- 0.010812, N = 4SE +/- 0.037316, N = 9SE +/- 0.022393, N = 7SE +/- 0.019069, N = 15SE +/- 0.022698, N = 7SE +/- 0.013568, N = 66.5417686.8527123.7548352.3129773.3604532.0768353.6543032.0843845.9309572.8810995.1141612.52736311.8521304.7025574.9558652.5298074.1827072.1594591. (CXX) g++ options: -fopenmp -lmpi_cxx -lmpi

NAMD

OpenBenchmarking.orgWatts, Fewer Is BetterNAMD 3.0b6CPU Power Consumption MonitorEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P140280420560700Min: 18.33 / Avg: 130.18 / Max: 164.25Min: 15.81 / Avg: 114.62 / Max: 140.3Min: 28.55 / Avg: 235.77 / Max: 330Min: 57.51 / Avg: 289.28 / Max: 672.46Min: 32.28 / Avg: 274.76 / Max: 406.72Min: 65.49 / Avg: 343.59 / Max: 811.63Min: 21.48 / Avg: 206.2 / Max: 309.47Min: 42.36 / Avg: 249.94 / Max: 651.86Min: 43.64 / Avg: 119.15 / Max: 229.24Min: 104.7 / Avg: 241.31 / Max: 387.86Min: 43.54 / Avg: 140.31 / Max: 283.29Min: 62.83 / Avg: 273.53 / Max: 463.21Min: 71.79 / Avg: 281.33 / Max: 364.12Min: 192.28 / Avg: 560.13 / Max: 714.79Min: 72.24 / Avg: 295.54 / Max: 371.41Min: 194.25 / Avg: 565.07 / Max: 686.05Min: 51.87 / Avg: 233.31 / Max: 276.8Min: 103.57 / Avg: 411.33 / Max: 527.15Min: 55.23 / Avg: 273.91 / Max: 344.33Min: 163.14 / Avg: 552.42 / Max: 653.46Min: 33.09 / Avg: 260.62 / Max: 349.3Min: 73.13 / Avg: 510.74 / Max: 686.96

OpenBenchmarking.orgns/day Per Watt, More Is BetterNAMD 3.0b6Input: STMV with 1,066,628 AtomsEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P0.00520.01040.01560.02080.0260.0120.0130.0120.0180.0120.0190.0140.0230.0040.0030.0040.0020.0050.0030.0050.0030.0050.0040.0040.0020.0060.004

OpenBenchmarking.orgns/day, More Is BetterNAMD 3.0b6Input: STMV with 1,066,628 AtomsEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P246810SE +/- 0.00440, N = 3SE +/- 0.00540, N = 3SE +/- 0.00537, N = 3SE +/- 0.02927, N = 3SE +/- 0.00206, N = 3SE +/- 0.01739, N = 3SE +/- 0.00847, N = 3SE +/- 0.00332, N = 3SE +/- 0.00423, N = 3SE +/- 0.04439, N = 8SE +/- 0.00540, N = 3SE +/- 0.03216, N = 9SE +/- 0.05087, N = 15SE +/- 0.05644, N = 12SE +/- 0.05862, N = 15SE +/- 0.05463, N = 15SE +/- 0.00653, N = 3SE +/- 0.00911, N = 3SE +/- 0.01396, N = 15SE +/- 0.04403, N = 15SE +/- 0.02648, N = 15SE +/- 0.08185, N = 131.519011.461632.878775.278393.410856.383432.888695.836060.523570.707570.567170.576941.452231.886791.502141.767781.110561.612321.052741.109001.437872.25422

OpenBenchmarking.orgWatts, Fewer Is BetterNAMD 3.0b6CPU Power Consumption MonitorEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P140280420560700Min: 17 / Avg: 109.51 / Max: 166.07Min: 16.45 / Avg: 96.77 / Max: 141.98Min: 27.01 / Avg: 187.68 / Max: 312.41Min: 58.84 / Avg: 262.91 / Max: 648.62Min: 29.28 / Avg: 180.85 / Max: 379.02Min: 62.44 / Avg: 326.5 / Max: 779.77Min: 20.68 / Avg: 165.67 / Max: 289.24Min: 40.88 / Avg: 225.05 / Max: 615.88Min: 43.66 / Avg: 112.28 / Max: 262.76Min: 72.63 / Avg: 236.64 / Max: 427.46Min: 43.48 / Avg: 132.04 / Max: 342.42Min: 106.87 / Avg: 266.5 / Max: 492.66Min: 73.54 / Avg: 248.99 / Max: 374.54Min: 194.24 / Avg: 522.05 / Max: 693.75Min: 73.99 / Avg: 269.88 / Max: 376.76Min: 190.7 / Avg: 550.3 / Max: 686.19Min: 54.68 / Avg: 216.04 / Max: 281.76Min: 101.59 / Avg: 389.17 / Max: 564.97Min: 55.01 / Avg: 258.53 / Max: 352.06Min: 165.98 / Avg: 533.68 / Max: 633.47Min: 33.34 / Avg: 236.13 / Max: 373.62Min: 75.47 / Avg: 484.77 / Max: 671.95

OpenBenchmarking.orgns/day Per Watt, More Is BetterNAMD 3.0b6Input: ATPase with 327,506 AtomsEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P0.01890.03780.05670.07560.09450.0520.0560.0440.0680.0520.0640.0480.0840.0340.0110.0290.0090.0240.0140.0220.0050.0170.0170.0110.0040.0200.012

OpenBenchmarking.orgns/day, More Is BetterNAMD 3.0b6Input: ATPase with 327,506 AtomsEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P510152025SE +/- 0.04338, N = 5SE +/- 0.00431, N = 4SE +/- 0.01368, N = 5SE +/- 0.04751, N = 3SE +/- 0.02148, N = 6SE +/- 0.08771, N = 3SE +/- 0.04917, N = 5SE +/- 0.02125, N = 3SE +/- 0.02593, N = 3SE +/- 0.19805, N = 15SE +/- 0.17734, N = 15SE +/- 0.20408, N = 12SE +/- 0.16058, N = 15SE +/- 0.26203, N = 15SE +/- 0.14537, N = 15SE +/- 0.44989, N = 15SE +/- 0.02582, N = 3SE +/- 0.07204, N = 4SE +/- 0.21567, N = 12SE +/- 0.17435, N = 15SE +/- 0.54361, N = 15SE +/- 0.34017, N = 125.706725.449718.1827517.811059.3353420.752597.9975618.974543.768112.554003.763482.397705.971307.300655.925012.563193.604796.726632.970212.219484.648145.85267

miniFE

OpenBenchmarking.orgWatts, Fewer Is BetterminiFE 2.2CPU Power Consumption MonitorEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P130260390520650Min: 19.07 / Avg: 96.36 / Max: 147.72Min: 15.16 / Avg: 86.83 / Max: 132.07Min: 28.79 / Avg: 152.24 / Max: 300.13Min: 53.09 / Avg: 309.09 / Max: 579.88Min: 33.7 / Avg: 177.88 / Max: 364.34Min: 63.04 / Avg: 330.55 / Max: 718.24Min: 21.36 / Avg: 127.63 / Max: 261.53Min: 40.05 / Avg: 258.88 / Max: 518.97Min: 43.59 / Avg: 108.34 / Max: 211.25Min: 104.71 / Avg: 215.79 / Max: 487.65Min: 43.53 / Avg: 119.29 / Max: 232.16Min: 106.66 / Avg: 225.73 / Max: 522.28Min: 75.77 / Avg: 253.53 / Max: 365.64Min: 189.32 / Avg: 498.77 / Max: 730.29Min: 73.91 / Avg: 260.35 / Max: 366.7Min: 199.32 / Avg: 500.61 / Max: 723.88Min: 53.33 / Avg: 190.48 / Max: 282.32Min: 99.06 / Avg: 326.82 / Max: 539.95Min: 61.92 / Avg: 224.98 / Max: 377.92Min: 168.8 / Avg: 424.3 / Max: 732.03Min: 31.62 / Avg: 198.71 / Max: 331.13Min: 73.08 / Avg: 366.83 / Max: 700.4

OpenBenchmarking.orgCG Mflops Per Watt, More Is BetterminiFE 2.2Problem Size: SmallEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P90180270360450254.52282.72334.41140.84298.90179.90392.87162.67373.28183.43340.56165.9679.2439.8571.5243.11120.5295.00156.59110.48160.18114.81

OpenBenchmarking.orgCG Mflops, More Is BetterminiFE 2.2Problem Size: SmallEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P13K26K39K52K65KSE +/- 49.20, N = 4SE +/- 42.17, N = 4SE +/- 42.89, N = 5SE +/- 1510.37, N = 15SE +/- 92.04, N = 5SE +/- 2182.93, N = 15SE +/- 53.07, N = 5SE +/- 2087.13, N = 15SE +/- 19.87, N = 4SE +/- 1039.71, N = 15SE +/- 8.42, N = 4SE +/- 712.94, N = 12SE +/- 601.03, N = 12SE +/- 1097.75, N = 15SE +/- 572.00, N = 12SE +/- 283.44, N = 3SE +/- 54.57, N = 4SE +/- 366.08, N = 4SE +/- 11.14, N = 4SE +/- 467.78, N = 4SE +/- 135.77, N = 4SE +/- 1633.92, N = 1524526.024548.850909.643531.053167.859466.650139.942113.540441.039580.940626.437461.120091.119876.518621.221583.222957.331046.535230.146877.531830.242114.61. (CXX) g++ options: -O3 -fopenmp -lmpi_cxx -lmpi

RocksDB

OpenBenchmarking.orgWatts, Fewer Is BetterRocksDB 9.0CPU Power Consumption MonitorEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P140280420560700Min: 17.34 / Avg: 155.39 / Max: 168.8Min: 17.36 / Avg: 134 / Max: 149.2Min: 24.6 / Avg: 300.55 / Max: 337.2Min: 56.63 / Avg: 576.34 / Max: 690.47Min: 34.3 / Avg: 383.63 / Max: 411.02Min: 67.1 / Avg: 671.28 / Max: 820.11Min: 22 / Avg: 301.4 / Max: 339.84Min: 43.23 / Avg: 505.19 / Max: 682.09Min: 43.66 / Avg: 179.48 / Max: 270.38Min: 107.56 / Avg: 350.26 / Max: 540.44Min: 43.57 / Avg: 208.52 / Max: 356.32Min: 108.91 / Avg: 400.79 / Max: 709.44Min: 72.31 / Avg: 332.58 / Max: 376.04Min: 200.41 / Avg: 651.38 / Max: 755.47Min: 74.89 / Avg: 331.82 / Max: 375.82Min: 185.7 / Avg: 663.3 / Max: 752.58Min: 55.14 / Avg: 255.9 / Max: 290.56Min: 98.57 / Avg: 510.9 / Max: 583.45Min: 52.65 / Avg: 330.54 / Max: 376.66Min: 157.04 / Avg: 656.04 / Max: 755.91Min: 33.11 / Avg: 323.9 / Max: 378.14Min: 67.94 / Avg: 558.28 / Max: 752.93

OpenBenchmarking.orgOp/s Per Watt, More Is BetterRocksDB 9.0Test: Read While WritingEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P15K30K45K60K75K60067.2166672.7048605.6934889.6536906.8329572.8952342.4645330.1863183.0369851.7556900.6267516.2922369.2614775.4922200.6216920.4621648.9919253.5223723.7618781.2727560.2822256.95

OpenBenchmarking.orgOp/s, More Is BetterRocksDB 9.0Test: Read While WritingEPYC 8534PEPYC 8534PNEPYC 9654EPYC 9654 2PEPYC 9684XEPYC 9684X 2PEPYC 9754EPYC 9754 2PXeon 6766EXeon 6766E 2PXeon 6780EXeon 6780E 2PXeon Max 9468Xeon Max 9468 2PXeon Max 9480Xeon Max 9480 2PXeon Platinum 8380Xeon Platinum 8380 2PXeon Platinum 8490HXeon Platinum 8490H 2PXeon Platinum 8592+Xeon Platinum 8592+ 2P6M12M18M24M30MSE +/- 28098.62, N = 3SE +/- 81998.56, N = 3SE +/- 36524.26, N = 3SE +/- 506458.47, N = 15SE +/- 93669.97, N = 15SE +/- 236709.61, N = 3SE +/- 109424.14, N = 3SE +/- 273109.47, N = 3SE +/- 45015.86, N = 3SE +/- 426084.70, N = 15SE +/- 136761.19, N = 4SE +/- 726178.20, N = 12SE +/- 83772.27, N = 13SE +/- 218479.19, N = 15SE +/- 26369.56, N = 3SE +/- 254193.37, N = 15SE +/- 23120.76, N = 3SE +/- 113154.86, N = 4SE +/- 61518.27, N = 10SE +/- 343737.14, N = 15SE +/- 28201.44, N = 3SE +/- 215352.04, N = 15933364589341761460854420108289141584191985166415776186229001521134038924466143118648152705978674396639624417736650011223329553987098366897841738123213008926893124255191. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread

271 Results Shown

OpenVINO
OpenSSL:
  SHA512
  RSA4096
Llamafile
TensorFlow
Pennant
OpenFOAM
QuantLib
OpenVINO
John The Ripper
OpenVINO
miniBUDE:
  OpenMP - BM2:
    Billion Interactions/s
    GFInst/s
ASTC Encoder
RELION
OpenSSL
Blender
OpenVINO
OpenSSL
John The Ripper:
  Blowfish
  bcrypt
7-Zip Compression
Primesieve
Blender:
  Barbershop - CPU-Only
  Pabellon Barcelona - CPU-Only
Coremark
OpenRadioss
OpenVINO
OSPRay Studio
Blender
OpenVINO
Xcompact3d Incompact3d
OpenSSL
OSPRay Studio
OpenVINO
ACES DGEMM
Helsing
Algebraic Multi-Grid Benchmark
OSPRay Studio
Blender
m-queens
OSPRay Studio
miniBUDE:
  OpenMP - BM1:
    Billion Interactions/s
    GFInst/s
OpenVINO
NAS Parallel Benchmarks
OSPRay
OpenSSL
OSPRay
Llamafile
OSPRay Studio:
  1 - 4K - 1 - Path Tracer - CPU
  3 - 4K - 1 - Path Tracer - CPU
OpenSSL
Primesieve
Blender
OpenVINO
NAS Parallel Benchmarks
OSPRay
OpenVINO:
  Vehicle Detection FP16-INT8 - CPU
  Person Vehicle Bike Detection FP16 - CPU
PyTorch
PostgreSQL:
  100 - 1000 - Read Only - Average Latency
  100 - 1000 - Read Only
Speedb
ONNX Runtime
Liquid-DSP
Embree
Memcached
OpenVINO
PyTorch
GraphicsMagick
srsRAN Project
GROMACS
OpenVKL
PyTorch:
  CPU - 64 - ResNet-50
  CPU - 512 - ResNet-50
ONNX Runtime
NAS Parallel Benchmarks
ASKAP
Embree
Liquid-DSP
ONNX Runtime
Liquid-DSP
ASTC Encoder
WRF
NAS Parallel Benchmarks
ONNX Runtime
PyTorch
LULESH
Embree
ONNX Runtime
Kvazaar:
  Bosphorus 4K - Slow
  Bosphorus 4K - Medium
PyTorch:
  CPU - 256 - ResNet-152
  CPU - 512 - ResNet-152
  CPU - 64 - ResNet-152
oneDNN
OpenVINO
uvg266
ONNX Runtime:
  super-resolution-10 - CPU - Parallel
  fcn-resnet101-11 - CPU - Parallel
Aircrack-ng
OpenVINO
Timed Node.js Compilation
ONNX Runtime
uvg266
ONNX Runtime
Timed Linux Kernel Compilation
TensorFlow
OpenVINO
Xcompact3d Incompact3d
High Performance Conjugate Gradient
Timed LLVM Compilation
GraphicsMagick
OpenFOAM
ONNX Runtime
7-Zip Compression
Parallel BZIP2 Compression
GPAW
ONNX Runtime
OpenVINO
Liquid-DSP
Intel Open Image Denoise
TensorFlow
Intel Open Image Denoise
Liquid-DSP
Intel Open Image Denoise
ONNX Runtime
LAMMPS Molecular Dynamics Simulator
LuxCoreRender
TensorFlow
Liquid-DSP
CloverLeaf
LAMMPS Molecular Dynamics Simulator
PostgreSQL:
  100 - 1000 - Read Write - Average Latency
  100 - 1000 - Read Write
srsRAN Project:
  PUSCH Processor Benchmark, Throughput Thread
  PDSCH Processor Benchmark, Throughput Thread
OpenRadioss
Liquid-DSP
NWChem
Kvazaar
GraphicsMagick
Liquid-DSP
CloverLeaf
libavif avifenc:
  0
  2
SVT-AV1
uvg266
ASKAP
TensorFlow:
  CPU - 64 - GoogLeNet
  CPU - 64 - AlexNet
Y-Cruncher:
  1B
  500M
Liquid-DSP
Timed Linux Kernel Compilation
OpenRadioss
TensorFlow
Numpy Benchmark
FFmpeg:
  libx265 - Video On Demand
  libx265 - Platform
SVT-AV1
QuantLib
TensorFlow
Apache IoTDB
ClickHouse
Apache IoTDB
ClickHouse
x265
ONNX Runtime
ASKAP
BRL-CAD
OpenVINO
ASKAP
Xmrig
OpenVINO
ONNX Runtime:
  ArcFace ResNet-100 - CPU - Standard
  ResNet50 v1-12-int8 - CPU - Parallel
OpenSSL
OpenVINO:
  Face Detection FP16-INT8 - CPU
  Noise Suppression Poconet-Like FP16 - CPU
  Machine Translation EN To DE FP16 - CPU
  Person Re-Identification Retail FP16 - CPU
  Weld Porosity Detection FP16-INT8 - CPU
ASTC Encoder
NAS Parallel Benchmarks
ONNX Runtime
ASTC Encoder
Speedb
RocksDB
TensorFlow
OpenVINO
FFmpeg
ClickHouse
Timed FFmpeg Compilation
TensorFlow
Timed Godot Game Engine Compilation
GNU Octave Benchmark
Appleseed
Liquid-DSP
Zstd Compression
TensorFlow
ONNX Runtime
Zstd Compression
Apache IoTDB
VVenC
TensorFlow
Timed ImageMagick Compilation
libavif avifenc
Apache IoTDB
QMCPACK
libavif avifenc:
  6, Lossless
  6
Timed Gem5 Compilation
Zstd Compression
WebP Image Encode
Zstd Compression
SVT-AV1
GraphicsMagick
VVenC
WebP Image Encode
OpenFOAM
PyBench
Google SynthMark
Timed Mesa Compilation
SecureMark
OpenFOAM
Liquid-DSP:
  64 - 256 - 32
  1 - 256 - 32
ONNX Runtime:
  CPU Power Consumption Monitor:
    Watts
    Watts
    Watts
  Phoronix Test Suite System Monitoring:
    Watts
  CPU Power Consumption Monitor:
    Watts
  Chess Benchmark:
    Nodes Per Second Per Watt
Stockfish
ONNX Runtime:
  Faster R-CNN R-50-FPN-int8 - CPU - Standard:
    Inference Time Cost (ms)
    Inferences Per Second
  bertsquad-12 - CPU - Standard:
    Inference Time Cost (ms)
    Inferences Per Second
  fcn-resnet101-11 - CPU - Standard:
    Inference Time Cost (ms)
    Inferences Per Second
srsRAN Project:
  CPU Power Consumption Monitor
  PDSCH Processor Benchmark, Throughput Total
srsRAN Project
SVT-AV1:
  CPU Power Consumption Monitor
  Preset 13 - Bosphorus 4K
SVT-AV1
LuxCoreRender:
  CPU Power Consumption Monitor
  Orange Juice - CPU
LuxCoreRender
LuxCoreRender:
  CPU Power Consumption Monitor
  DLSC - CPU
LuxCoreRender
NAS Parallel Benchmarks:
  CPU Power Consumption Monitor
  EP.D
NAS Parallel Benchmarks
Pennant
Pennant
NAMD:
  CPU Power Consumption Monitor
  STMV with 1,066,628 Atoms
NAMD
NAMD:
  CPU Power Consumption Monitor
  ATPase with 327,506 Atoms
NAMD
miniFE:
  CPU Power Consumption Monitor
  Small
miniFE
RocksDB:
  CPU Power Consumption Monitor
  Read While Writing
RocksDB