AMD EPYC Genoa Zen 4 Linux Review

Tests for a future article on Phoronix.

Compare your own system(s) to this result file with the Phoronix Test Suite by running the command: phoronix-test-suite benchmark 2211101-PTS-GENOAREV10
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:

BLAS (Basic Linear Algebra Sub-Routine) Tests 4 Tests
C++ Boost Tests 5 Tests
Chess Test Suite 3 Tests
Timed Code Compilation 10 Tests
C/C++ Compiler Tests 12 Tests
Compression Tests 2 Tests
CPU Massive 26 Tests
Creator Workloads 19 Tests
Cryptography 2 Tests
Encoding 2 Tests
Fortran Tests 5 Tests
Game Development 5 Tests
HPC - High Performance Computing 23 Tests
Imaging 2 Tests
Common Kernel Benchmarks 2 Tests
LAPACK (Linear Algebra Pack) Tests 2 Tests
Linear Algebra 2 Tests
Machine Learning 5 Tests
Molecular Dynamics 7 Tests
MPI Benchmarks 7 Tests
Multi-Core 40 Tests
NVIDIA GPU Compute 5 Tests
Intel oneAPI 6 Tests
OpenMPI Tests 16 Tests
Programmer / Developer System Benchmarks 16 Tests
Python 3 Tests
Raytracing 5 Tests
Renderers 7 Tests
Scientific Computing 10 Tests
Software Defined Radio 2 Tests
Server 6 Tests
Server CPU Tests 19 Tests
Single-Threaded 4 Tests
Texture Compression 2 Tests
Video Encoding 2 Tests
Common Workstation Benchmarks 4 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

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
EPYC 75F3
October 28 2022
  18 Hours, 49 Minutes
EPYC 75F3 2P
October 27 2022
  17 Hours
EPYC 7713
September 10 2022
  15 Hours
EPYC 7713 2P
September 06 2022
  12 Hours, 30 Minutes
EPYC 7763
September 16 2022
  15 Hours, 2 Minutes
EPYC 7763 2P
September 18 2022
  12 Hours, 35 Minutes
EPYC 7773X
September 19 2022
  14 Hours, 30 Minutes
EPYC 7773X 2P
September 22 2022
  12 Hours, 20 Minutes
EPYC 9554
November 02 2022
  14 Hours, 5 Minutes
EPYC 9554 - Power
November 02 2022
  13 Hours, 22 Minutes
EPYC 9554 2P
October 31 2022
  12 Hours, 54 Minutes
EPYC 9554 2P - Power
November 01 2022
  12 Hours, 39 Minutes
EPYC 9654
October 15 2022
  13 Hours, 12 Minutes
EPYC 9654 - Power
October 16 2022
  13 Hours, 17 Minutes
EPYC 9654 2P
October 22 2022
  9 Hours, 53 Minutes
EPYC 9654 2P - Power
October 23 2022
  9 Hours, 58 Minutes
Xeon Platinum 8362
October 04 2022
  18 Hours, 50 Minutes
Xeon Platinum 8362 2P
October 05 2022
  13 Hours, 47 Minutes
Xeon Platinum 8380
September 30 2022
  17 Hours, 51 Minutes
Xeon Platinum 8380 2P
November 04 2022
  17 Hours, 50 Minutes
Invert Hiding All Results Option
  14 Hours, 16 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):


AMD EPYC Genoa Zen 4 Linux ReviewProcessorMotherboardChipsetMemoryDiskGraphicsMonitorNetworkOSKernelDesktopDisplay ServerVulkanCompilerFile-SystemScreen ResolutionEPYC 7713 2PEPYC 7713EPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P2 x AMD EPYC 7713 64-Core @ 2.00GHz (128 Cores / 256 Threads)AMD DAYTONA_X (RYM1009B BIOS)AMD Starship/Matisse512GB3841GB Micron_9300_MTFDHAL3T8TDPASPEEDVE2282 x Mellanox MT27710Ubuntu 22.106.0.0-060000rc3daily20220904-generic (x86_64)GNOME ShellX Server 1.21.1.31.3.211GCC 12.2.0ext41920x1080AMD EPYC 7713 64-Core @ 2.00GHz (64 Cores / 128 Threads)256GBAMD EPYC 7763 64-Core @ 2.45GHz (64 Cores / 128 Threads)2 x AMD EPYC 7763 64-Core @ 2.45GHz (128 Cores / 256 Threads)512GBAMD EPYC 7773X 64-Core @ 2.20GHz (64 Cores / 128 Threads)256GB2 x AMD EPYC 7773X 64-Core @ 2.20GHz (128 Cores / 256 Threads)512GBIntel Xeon Platinum 8380 @ 3.40GHz (40 Cores / 80 Threads)Intel M50CYP2SB2U (SE5C6200.86B.0022.D08.2103221623 BIOS)Intel Ice Lake IEH256GB2 x Intel X710 for 10GBASE-T + 2 x Intel E810-C for QSFPIntel Xeon Platinum 8362 @ 3.60GHz (32 Cores / 64 Threads)2 x Intel Xeon Platinum 8362 @ 3.60GHz (64 Cores / 128 Threads)512GBAMD EPYC 9654 96-Core @ 3.71GHz (96 Cores / 192 Threads)AMD Titanite_4G (RTI1002E BIOS)AMD Device 14a4768GBVGA HDMIBroadcom NetXtreme BCM5720 PCIe2 x AMD EPYC 9654 96-Core @ 3.71GHz (192 Cores / 384 Threads)1520GB2 x AMD EPYC 75F3 32-Core @ 2.95GHz (64 Cores / 128 Threads)AMD DAYTONA_X (RYM1009B BIOS)AMD Starship/Matisse512GBVE2282 x Mellanox MT27710AMD EPYC 75F3 32-Core @ 2.95GHz (32 Cores / 64 Threads)256GB2 x AMD EPYC 9554 64-Core @ 3.76GHz (128 Cores / 256 Threads)AMD Titanite_4G (RTI1002E BIOS)AMD Device 14a41520GBVGA HDMIBroadcom NetXtreme BCM5720 PCIeAMD EPYC 9554 64-Core @ 3.76GHz (64 Cores / 128 Threads)768GB2 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 QSFPOpenBenchmarking.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-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-12-Wbc0TK/gcc-12-12.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-12-Wbc0TK/gcc-12-12.2.0/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- EPYC 7713 2P: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa001173- EPYC 7713: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa001173- EPYC 7763: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa001173- EPYC 7763 2P: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa001173- EPYC 7773X: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa001229- EPYC 7773X 2P: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa001229- Xeon Platinum 8380: Scaling Governor: intel_pstate performance (EPP: performance) - CPU Microcode: 0xd000375- Xeon Platinum 8362: Scaling Governor: intel_pstate performance (EPP: performance) - CPU Microcode: 0xd000375- Xeon Platinum 8362 2P: Scaling Governor: intel_pstate performance (EPP: performance) - CPU Microcode: 0xd000375- EPYC 9654: Scaling Governor: amd-pstate performance (Boost: Enabled) - CPU Microcode: 0xa10110d- EPYC 9654 - Power: Scaling Governor: amd-pstate performance (Boost: Enabled) - CPU Microcode: 0xa10110d- EPYC 9654 2P: Scaling Governor: amd-pstate performance (Boost: Enabled) - CPU Microcode: 0xa10110d- EPYC 9654 2P - Power: Scaling Governor: amd-pstate performance (Boost: Enabled) - CPU Microcode: 0xa10110d- EPYC 75F3 2P: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa001173- EPYC 75F3: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa001173- EPYC 9554 2P: Scaling Governor: amd-pstate performance (Boost: Enabled) - CPU Microcode: 0xa10110d- EPYC 9554 2P - Power: Scaling Governor: amd-pstate performance (Boost: Enabled) - CPU Microcode: 0xa10110d- EPYC 9554 - Power: Scaling Governor: amd-pstate performance (Boost: Enabled) - CPU Microcode: 0xa10110d- EPYC 9554: Scaling Governor: amd-pstate performance (Boost: Enabled) - CPU Microcode: 0xa10110d- Xeon Platinum 8380 2P: Scaling Governor: intel_pstate performance (EPP: performance) - CPU Microcode: 0xd000375Java Details- OpenJDK Runtime Environment (build 11.0.16+8-post-Ubuntu-0ubuntu1)Python Details- Python 3.10.6Security Details- EPYC 7713 2P: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: 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 Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected- EPYC 7713: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: 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 Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected- EPYC 7763: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: 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 Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected- EPYC 7763 2P: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: 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 Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected- EPYC 7773X: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: 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 Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected- EPYC 7773X 2P: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: 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 Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected- Xeon Platinum 8380: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Mitigation of Clear buffers; SMT vulnerable + retbleed: 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 IBRS IBPB: conditional RSB filling PBRSB-eIBRS: SW sequence + srbds: Not affected + tsx_async_abort: Not affected- Xeon Platinum 8362: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Mitigation of Clear buffers; SMT vulnerable + retbleed: 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 IBRS IBPB: conditional RSB filling PBRSB-eIBRS: SW sequence + srbds: Not affected + tsx_async_abort: Not affected- Xeon Platinum 8362 2P: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Mitigation of Clear buffers; SMT vulnerable + retbleed: 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 IBRS IBPB: conditional RSB filling PBRSB-eIBRS: SW sequence + srbds: Not affected + tsx_async_abort: Not affected- EPYC 9654: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: 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 Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected- EPYC 9654 - Power: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: 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 Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected- EPYC 9654 2P: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: 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 Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected- EPYC 9654 2P - Power: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: 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 Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected- EPYC 75F3 2P: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: 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 Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected- EPYC 75F3: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: 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 Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected- EPYC 9554 2P: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: 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 Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected- EPYC 9554 2P - Power: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: 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 Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected- EPYC 9554 - Power: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: 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 Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected- EPYC 9554: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: 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 Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected- Xeon Platinum 8380 2P: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Mitigation of Clear buffers; SMT vulnerable + retbleed: 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 IBRS IBPB: conditional RSB filling PBRSB-eIBRS: SW sequence + srbds: Not affected + tsx_async_abort: Not affected

EPYC 7713 2PEPYC 7713EPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2PLogarithmic Result OverviewPhoronix Test SuiteSysbenchLeelaChessZeroOSPRayCoremarkOpenSSLXmrigOSPRay StudioPennantC-Raym-queensBlenderTachyonACES DGEMMOpenVINORELIONebizzyRodinia7-Zip CompressionEmbreeASTC EncoderNAMDasmFishWRFXcompact3d Incompact3dNAS Parallel BenchmarksHigh Performance Conjugate GradientGROMACSAlgebraic Multi-Grid BenchmarkLuxCoreRenderLiquid-DSPGraphicsMagickGPAWoneDNNTimed Linux Kernel CompilationIntel Open Image DenoiseLULESHPOV-RayPJSIPNWChemGraph500Timed Node.js CompilationKvazaarTimed LLVM CompilationTimed MPlayer CompilationWebP2 Image EncodeASKAPTimed Godot Game Engine CompilationEtcpakTimed Gem5 CompilationNode.js Express HTTP Load TestBuild2Timed Mesa CompilationsimdjsonNumpy BenchmarkPyPerformanceZstd CompressionDaCapo BenchmarkTimed Wasmer CompilationsrsRANPHPBenchTimed CPython CompilationPyBenchQuantLib

EPYC 7713 2PEPYC 7713EPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2PLogarithmic Per Watt Result OverviewPhoronix Test SuiteLeelaChessZeroPJSIPASKAPEtcpakebizzyACES DGEMMNumpy BenchmarkNode.js Express HTTP Load TestSysbenchXmrigZstd CompressionsrsRANOSPRayKvazaarASTC EncodersimdjsonQuantLibNAS Parallel BenchmarksEmbree7-Zip CompressionOpenSSLPHPBenchCoremarkWebP2 Image EncodeLuxCoreRenderLiquid-DSPAlgebraic Multi-Grid BenchmarkGraph500Intel Open Image DenoiseGraphicsMagickasmFishGROMACSHigh Performance Conjugate GradientLULESHP.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

AMD EPYC Genoa Zen 4 Linux Reviewopenvino: Vehicle Detection FP16-INT8 - CPUopenvino: Person Vehicle Bike Detection FP16 - CPUopenvino: Face Detection FP16 - CPUsysbench: CPUospray: gravity_spheres_volume/dim_512/ao/real_timepennant: sedovbiglczero: Eigenliquid-dsp: 256 - 256 - 57xmrig: Monero - 1Mopenvino: Weld Porosity Detection FP16 - CPUcompress-7zip: Decompression Ratingcoremark: CoreMark Size 666 - Iterations Per Secondopenvino: Person Detection FP16 - CPUopenvino: Person Detection FP32 - CPUopenfoam: drivaerFastback, Medium Mesh Size - Execution Timeblender: Classroom - CPU-Onlyonednn: Convolution Batch Shapes Auto - u8s8f32 - CPUospray-studio: 1 - 4K - 16 - Path Tracerospray-studio: 2 - 4K - 16 - Path Tracerospray-studio: 3 - 4K - 16 - Path Tracerc-ray: Total Time - 4K, 16 Rays Per Pixelnpb: SP.Cblender: Barbershop - CPU-Onlym-queens: Time To Solveospray-studio: 2 - 4K - 32 - Path Tracerospray-studio: 1 - 4K - 32 - Path Traceropenvino: Age Gender Recognition Retail 0013 FP16 - CPUblender: Pabellon Barcelona - CPU-Onlyospray: gravity_spheres_volume/dim_512/pathtracer/real_timeospray-studio: 3 - 4K - 32 - Path Traceropenvino: Vehicle Detection FP16 - CPUdeepsparse: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Asynchronous Multi-Streamospray-studio: 2 - 4K - 1 - Path Tracerxmrig: Wownero - 1Mtachyon: Total Timeliquid-dsp: 128 - 256 - 57ospray-studio: 1 - 4K - 1 - Path Traceropenvino: Machine Translation EN To DE FP16 - CPUospray-studio: 3 - 4K - 1 - Path Tracerastcenc: Exhaustiveblender: BMW27 - CPU-Onlymt-dgemm: Sustained Floating-Point Rateopenssl: RSA4096embree: Pathtracer - Crownopenssl: RSA4096blender: Fishy Cat - CPU-Onlydeepsparse: CV Classification, ResNet-50 ImageNet - Asynchronous Multi-Streamincompact3d: input.i3d 193 Cells Per Directionastcenc: Thoroughrelion: Basic - CPUrodinia: OpenMP LavaMDembree: Pathtracer - Asian Dragonnpb: EP.Cnpb: BT.Cembree: Pathtracer ISPC - Crowndeepsparse: CV Detection,YOLOv5s COCO - Asynchronous Multi-Streamembree: Pathtracer ISPC - Asian Dragonopenvino: Person Detection FP32 - CPUdeepsparse: NLP Text Classification, BERT base uncased SST2 - Asynchronous Multi-Streamopenvino: Person Detection FP16 - CPUdeepsparse: NLP Text Classification, DistilBERT mnli - Asynchronous Multi-Streamnamd: ATPase Simulation - 327,506 Atomsnpb: LU.Conednn: Convolution Batch Shapes Auto - f32 - CPUasmfish: 1024 Hash Memory, 26 Depthonednn: Deconvolution Batch shapes_3d - f32 - CPUonednn: Convolution Batch Shapes Auto - f32 - CPUwrf: conus 2.5kmincompact3d: X3D-benchmarking input.i3dnpb: SP.Bopenvino: Person Vehicle Bike Detection FP16 - CPUbuild-linux-kernel: allmodconfigluxcorerender: DLSC - CPUhpcg: gromacs: MPI CPU - water_GMX50_baregraphics-magick: Sharpenamg: openvino: Age Gender Recognition Retail 0013 FP16-INT8 - CPUnpb: MG.Cincompact3d: input.i3d 129 Cells Per Directionopenvino: Age Gender Recognition Retail 0013 FP16 - CPUnpb: FT.Castcenc: Mediumcompress-7zip: Compression Ratingopenfoam: drivaerFastback, Small Mesh Size - Execution Timegpaw: Carbon Nanotubeluxcorerender: Orange Juice - CPUbuild-llvm: Ninjanpb: CG.Cgraphics-magick: Enhancedpgbench: 100 - 500 - Read Only - Average Latencypgbench: 100 - 500 - Read Onlypgbench: 100 - 250 - Read Only - Average Latencyliquid-dsp: 64 - 256 - 57pgbench: 1 - 500 - Read Onlypgbench: 1 - 500 - Read Only - Average Latencypgbench: 100 - 250 - Read Onlypgbench: 1 - 250 - Read Onlyoidn: RT.hdr_alb_nrm.3840x2160pgbench: 1 - 250 - Read Only - Average Latencyoidn: RT.ldr_alb_nrm.3840x2160webp2: Quality 95, Compression Effort 7oidn: RTLightmap.hdr.4096x4096lulesh: graph500: 26openvino: Age Gender Recognition Retail 0013 FP16-INT8 - CPUpovray: Trace Timepjsip: OPTIONS, Statelessgraph500: 26webp2: Quality 75, Compression Effort 7deepsparse: NLP Token Classification, BERT base uncased conll2003 - Asynchronous Multi-Streamnwchem: C240 Buckyballdeepsparse: NLP Document Classification, oBERT base uncased on IMDB - Asynchronous Multi-Streambuild-nodejs: Time To Compilegraph500: 26kvazaar: Bosphorus 4K - Very Fastgraph500: 26deepsparse: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Synchronous Single-Streamdeepsparse: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Synchronous Single-Streambuild-linux-kernel: defconfigbuild-mplayer: Time To Compiledeepsparse: CV Detection,YOLOv5s COCO - Synchronous Single-Streamdeepsparse: CV Detection,YOLOv5s COCO - Synchronous Single-Streamopenradioss: Cell Phone Drop Testdeepsparse: NLP Token Classification, BERT base uncased conll2003 - Synchronous Single-Streamdeepsparse: NLP Token Classification, BERT base uncased conll2003 - Synchronous Single-Streamdeepsparse: NLP Document Classification, oBERT base uncased on IMDB - Synchronous Single-Streamdeepsparse: NLP Document Classification, oBERT base uncased on IMDB - Synchronous Single-Streamopenradioss: INIVOL and Fluid Structure Interaction Drop Containerdeepsparse: NLP Text Classification, DistilBERT mnli - Synchronous Single-Streamdeepsparse: NLP Text Classification, DistilBERT mnli - Synchronous Single-Streamdeepsparse: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Asynchronous Multi-Streambuild-llvm: Unix Makefilesopenvino: Face Detection FP16 - CPUopenvino: Vehicle Detection FP16 - CPUbrl-cad: VGR Performance Metricopenvino: Weld Porosity Detection FP16 - CPUonednn: Convolution Batch Shapes Auto - bf16bf16bf16 - CPUopenvino: Weld Porosity Detection FP16-INT8 - CPUaskap: tConvolve MPI - Degriddingopenvino: Face Detection FP16-INT8 - CPUopenvino: Machine Translation EN To DE FP16 - CPUaskap: tConvolve MPI - Griddingopenssl: SHA256openradioss: Rubber O-Ring Seal Installationbuild-godot: Time To Compiledeepsparse: NLP Text Classification, BERT base uncased SST2 - Synchronous Single-Streamdeepsparse: NLP Text Classification, BERT base uncased SST2 - Synchronous Single-Streamdeepsparse: CV Classification, ResNet-50 ImageNet - Synchronous Single-Streamdeepsparse: CV Classification, ResNet-50 ImageNet - Synchronous Single-Streamopenfoam: drivaerFastback, Small Mesh Size - Mesh Timeopenfoam: drivaerFastback, Medium Mesh Size - Mesh Timeetcpak: Multi-Threaded - ETC2build-gem5: Time To Compilesimdjson: TopTweetdeepsparse: CV Classification, ResNet-50 ImageNet - Asynchronous Multi-Streamsimdjson: DistinctUserIDsimdjson: PartialTweetssrsran: 5G PHY_DL_NR Test 52 PRB SISO 64-QAMnode-express-loadtest: deepsparse: NLP Text Classification, BERT base uncased SST2 - Asynchronous Multi-Streambuild2: Time To Compilebuild-mesa: Time To Compileaom-av1: Speed 0 Two-Pass - Bosphorus 4Kdeepsparse: NLP Text Classification, DistilBERT mnli - Asynchronous Multi-Streamopenradioss: Bird Strike on Windshieldnumpy: liquid-dsp: 32 - 256 - 57pyperformance: regex_compilesimdjson: Kostyaaom-av1: Speed 4 Two-Pass - Bosphorus 4Ksrsran: 4G PHY_DL_Test 100 PRB MIMO 64-QAMdeepsparse: CV Detection,YOLOv5s COCO - Asynchronous Multi-Streamsrsran: 4G PHY_DL_Test 100 PRB SISO 64-QAMopenradioss: Bumper Beamcompress-zstd: 19, Long Mode - Decompression Speedaom-av1: Speed 4 Two-Pass - Bosphorus 1080ppyperformance: json_loadscompress-zstd: 19 - Compression Speedsrsran: 4G PHY_DL_Test 100 PRB MIMO 256-QAMdacapobench: Jythonbuild-wasmer: Time To Compilesimdjson: LargeRandsrsran: OFDM_Testpyperformance: crypto_pyaesbuild-python: Defaultsrsran: 5G PHY_DL_NR Test 52 PRB SISO 64-QAMphpbench: PHP Benchmark Suitepybench: Total For Average Test Timessrsran: 4G PHY_DL_Test 100 PRB SISO 256-QAMpyperformance: django_templatequantlib: build-python: Released Build, PGO + LTO Optimizedwebp2: Defaultebizzy: onednn: Convolution Batch Shapes Auto - u8s8f32 - CPUnpb: IS.Dnpb: EP.Dpennant: leblancbigEPYC 7713 2PEPYC 7713EPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P3317.722682.292018.73500770.9413.41805.6917784184538386666751273.316.666338473659583.24065113.0112.8441.292228722769268526.357113107.52171.986.659457014489459879.3453.9921.38875338616.78142241903.716.335651059333331397143.1816496.052917.0032.62643824998.089.47331633628.122.0311.014796357.7938296.12726.91668.65588241.13232312.4782.571767.30082453.372425.010.26727258224.352468888543.742470.6322108626.671298.322428134888.0611.91184.69412.7437.25158.3187601917570000101816.87100065.123.089436212.11116524.99379.485052565444.22918.49121.47847508.34128931847000002.252.270.341.1137996.4874510230001.097.689683143362480000.632079.6141.32172849900055.7771301600026.12210.396212.67015.801904.6732441031909.815276.7939243.650.20223.1541026.912861663690043.5266628.311162.2254.294.453.7262.5501960.77324.617479.5315949333331562.98134.6145.13492.221.582.2142.2407651.3511.0313649333398.218.12127.8730528970151.839.82830.5283.8668.2531514250.7938244763.449336.773.6316281694.531520.033554.86252327.027.8548411.318453596278140000028571.831.073511781824524.4760626.796.7877.1139631400954714712.35051976.91300.1012.794856068520232070.1296.2012.24069977533.82249437205.631.160027205000002464273.2829343.206830.4120.73428012612.151.8896823890.539.0421.849405330.1262572.30946.15863.11174531.17127746.6647.918156.86814633.474623.960.45521135885.311383779603.202410.93628816938.433602.44484490065.5721.03312.9388.3319.12655.164511101425400051141.5757128.295.039292201.9861089.33233.060135850573.43012.49186.43323979.7993425780333331.411.410.240.7019643.9182971590001.0410.506743892336760000.482314.2203.22654631400037.0553172500035.86313.623258.7538.97945.347089431029.062458.7220056.124.58116.9120855.86520601457747.9206694.850196.9254.294.453.7462.8543867.29027.752486.4215916000001562.98135.4146.03538.021.384.8143.3408852.0161.0313455714310118.75127.5730550969152.639.92827.5286.2279.2123939171.595742672.584871.166.1009381901.211637.963238.66252773.249.0504010.1609303898309316666731459.228.383852051876249.1449077.597.58627.9694968.1735029353724153810.95351889.31264.8712.304771087620033814.3885.5113.86828923030.14219542583.627.786930333000002171243.2625823.618926.9623.48245013287.563.1869867678.434.5121.809558933.8884566.37742.24471.14844982.82133198.1658.169766.08784147.584151.950.38226144112.861591202973.178910.86359316544.816603.53564588708.7519.51267.4999.4719.12155.772582101444500055150.3257200.165.179966771.8860945.14262.031838641148.35220169.89413.91167.05424379.67103628104000001.651.650.240.8119943.0853410420000.989.695723332658680000.482203.9186.25068680200039.0867655500032.61112.594244.6139.741060.637445331126.902756.7622333.227.67131.2723153.27435824956745.39834.493903161.854596689.606188.6314.044.243.5659.6523665.55826.865466.8915900000001642.84128.1137.33328.422.585.0135.8412552.9000.9813010666710319.015121.67022911018142.842.22684.7298.3669.1423453951.577662695.005300.775.8128083748.342914.321982.52503926.6016.40955.5003174598604713333357031.014.887193233706923.16193114.3914.38277.1275935.061831918614217185.576114669.27142.266.443372323662564899.7144.0825.94824341514.70115849895.414.165255938666671137125.8013507.239214.2738.90578826521.8111.94321728763.718.4911.008701866.2779293.34223.95073.60719241.56252416.39101.568768.26432191.712191.230.22418287345.282915950663.832660.6279698372.93297.434947136460.4410.96160.01513.7637.318510.0728581929891667106094.9898920.033.131475111.95118231.73450.109358238435.33596542.51121.76112.58246814.82144631870000002.562.570.351.2638255.5074745520001.017.298664153568570000.641999.1135.21072568900056.9869695500024.67310.097210.12316.012173.4929625932136.935931.5544039.557.38254.0344983.214879714113043.07431.557736154.213016678.397161.4354.064.243.5459.5491260.85524.953455.6815980666671632.84128.5138.03336.622.380.1136.0421753.1130.9812748000010518.865121.86916551016143.841.82689.6298.9018.3230610510.7965954729.6310333.193.4843251864.661876.123059.08265046.149.147109.5187815286304043333336431.426.754121501987443.3294467.978.02365.7619670.5734169344244055611.01089188.95266.6411.281748337455035966.8087.4013.81148693026.55214040297.228.503629637333332125227.7725173.627127.5329.46084313762.368.8597902005.334.9716.875356134.1055276.58943.77980.64594968.98166563.2163.473972.23043931.313956.740.37636255823.481565073443.217710.83635915435.544573.313762135254.1217.04263.2899.4519.71187.165595105705066757873.6860128.524.382258621.7764733.33264.501740371840.0517859.85413.43159.22240140.36103928449333331.651.660.260.8222729.5943669230000.909.667712082886580000.522053.3177.62873247100041.7571637600031.91912.204232.08110.361204.497775641195.392664.4932294.827.04140.1934048.47401393060042.81428.9386126.710186989.997178.7944.084.243.5659.8517563.12626.375492.4316793333331632.84129.8138.63378.422.3103.6136.4405349.6800.9812876666710318.748121.76970591016144.242.12694.3292.429.5525853160.9338182838.045491.625.4197123659.993202.241821.21528491.5716.39695.1245295808585290000043442.813.277481093867411.27185515.2615.12166.2967336.391760518019208765.782230050.33140.205.915360253527068270.4145.2225.68204190713.68113449905.714.696655973333331101116.1913037.140714.6151.04691327127.8127.84971780874.618.709.5077899365.6141147.36325.193100.04069285.18369239.47116.075594.10022084.772067.020.22366392397.672917606043.759780.5932357410.731265.938090163786.889.98155.91013.7238.239711.2168751998897333108150.75123247.082.246857121.85127733.49452.173354738530.35077238.20321.23108.52451069.45145633380000001.941.960.360.9543886.0003753050000.967.183671282989870000.661866.5130.04161117200055.0859151300024.1489.939201.37017.412336.7729929452407.715735.0562354.454.96275.0366651.414645641199038.99130.640099147.740936926.204154.9294.084.243.5459.9489959.36924.5390.43488.6116709333331642.8410.61128.4138.33343.319.7622.5107.6137.0424850.3270.9813034444410318.792121.96962031018144.342.12668.0292.8048.5631301760.7148565165.199921.733.3005782255.591127.831645.06107244.8210.840026.161184458156186666714460.632.351876421177693.0596356.896.74794.72984120.921.4046541655419404961022.18637710.58471.4524.578893858902028673.99150.5913.379910521336.22262222902.949.331514913666672603142.3731052.262945.6013.4969468462.535.0865588480.560.8423.966153522.4801716.74878.72041.97494390.98115359.2043.063955.86762916.122868.210.5444297758.151.47433879745781.561991.4794718689.213556.32509449434.6917.70409.1495.6320.66894.980348108113100056565.0157809.355.330262321.3756704.82167.018224246674.86430177.7948.79239.57622812.4361716116666671.741.740.150.8318563.4812731510000.6315.841434492044730000.323453.2257.11871713200027.5570370000043.37916.645295.90312.05551.201234.664.101214465.688766.0942.69140.2410092.12853888308759.19935.639242173.541055532.148211.9505.695.694.7472.6667174.71631.0070.35398.5815524666671692.919.75110.2118.12815.919.1522.682.4135.2383048.6850.9713523333311019.699113.18167431042142.344.32521.7306.348.1611185821.403062274.134636.7212.006821976.25984.421466.5299997.319.5576627.341181682140546666712857.128.571662271055949.5628986.186.08864.64243136.411.5187248204486136289625.07735288.04538.8127.39110206810149224550.40170.4711.992111998930.56303619709.155.557713318666673003129.3735951.997851.4212.1269687690.330.9409519444.768.0826.453769719.9438763.19686.92035.79963979.0895180.7238.763249.56692594.302557.140.6033597670.641.61193769998771.639831.5968520075.501588.06294848063.4016.22461.5384.9220.17634.388317106780633348059.0155604.705.991757151.2956879.46148.596221626385.97064583.2797.79267.73222162.9456013095000001.591.600.140.7618713.2722633810000.6017.434446051973860000.283956.7279.47968002600029.3664676400046.66618.012324.08210.82522.873844081118.624.708864023.357391.6738.48123.568603.522515103964763.04537.18473177.058356170.389225.7366.106.045.0378.0708575.89030.7950.34415.9915683333331603.069.57133.7126.42982.519.8821.483.7137.3364647.4101.0214316666710418.917122.0859511983146.641.82664.8293.0839.019734631.499962191.664181.1313.754943873.021727.84730.17200101.4018.783016.740796643272223333323539.929.083317462006324.37607711.8811.67399.3336667.572.0058223834240582843212.55489186.77274.8813.522483494773851258.5484.5523.19106254515.55150935545.427.47182636866667149277.5517814.099825.8023.02898516041.557.65421068009.034.3412.247636140.3136383.38748.11469.98607622.71194987.4968.364389.09841359.691336.050.30429188856.062.263501448183131.0055952.2568610633.825312.028646111259.339.22250.8867.9839.96218.6565792067115333108301.83116706.642.901793351.2397993.30289.379336473044.50603348.87412.67159.49137782.1699829861000002.712.720.261.3035687.8993403680000.579.930438072693030000.512176.3178.61983869300040.1080655100030.62611.910223.50721.841027.016427112186.182.387438569.8514994.573.30205.8417349.35141716797744.67630.940326156.83066238.490183.3956.16.105.0377.4677862.48226.0910.44412.1617703000001603.019.85132.3125.22828.919.4321.487.1138.9365946.7391.0014326666710418.243123.0866491986147.141.92666.3290.6338.0516398891.981632891.848264.366.4883746003.735763.31955.51446395.2226.53205.8462309258519346666758736.19.586529703753920.39294327.7427.55246.6607838.720.2907281697117162202286.662125438.45143.317.9883432333978112325.8248.8931.16644049213.99401.1991107175830.916.75865174800000106087.5212635.956815.6339.14968022205.3102.97191463630.720.471014.61518.2262027756.1994247.08728.609120.75828633.62267319.17109.9161447.5468136.10561722.48316.55671714.98626.04230.24798274263.370.6698032491758791.143180.6709707676.327254.854207162758.978.32173.10514.3145.223911.1478432333430333149560.47120349.962.289035300.65121799.77422.019865892328.51894735.83421.49105.19254251.0214290.16031204140.080405450000032360190.154313562632861363.040.0763.050.411.4429508.5905277510000.457.178878984176480000.7842.6917155042.5205123.42690661300076.678873140009.8328101.653923.6058.7655.1960192.305623.0935.573228.105235.663628.0351103.59189.87505.2631119.4099171.12050.063426.6931239905004.250.3944569842.9342366.796.87547.9847485.212597944460766.8133.25887.517111.42045.1998192.242025.942655131.293129257.884146.3126.5747.25066.825.6792.27829151.396550.60220.77076.6033119.94585.0622688000001164.10158.5107.0059166.673.763798.116.6106.1166.2324040.4531.2516200000088.215.585139.4843665855172.836.33028.2254.58511.6042872000.2858204888.5211335.943.7630216582.286138.92890.80457526.5530.55605.21123210155614026666763045.59.007415364111551.58132729.7429.68237.9374833.390.2751941472214926175695.804126790.36127.116.9532971529445118385.5843.0336.32033505914.04428.442692682117.114.6145618290000091681.2710957.036813.5943.95339525901.8115.54321689673.118.051133.40958.0777998065.3992245.02524.489137.93179551.94274024.34123.6227499.7481154.63571598.26336.60011597.31666.25000.22157272077.940.6101192803138231.089590.6116007370.388253.414098168014.137.81158.31817.0744.479312.9569992341996333159812.84121727.312.241371100.62125326.19480.188570008525.13794632.55123.6297.62455458.3916650.13537003950.067454753333338181310.131370146238724733.330.0653.330.451.5830521.1185229330000.436.578877284127410000.8349.0994139148.9753117.06288172900077.058633680009.7375102.648822.5098.4145.0062199.584520.4037.253526.837537.151726.911190.85196.19685.0933111.7465167.35153.513414.6231794575329.570.37518410601.8346081.4103.49590.0851341.314316347005761.5232.44789.498511.16745.1923192.516223.190278120.417829335.755141.4396.5542.28576.835.6694.57780142.325349.52720.37771.9609111.28583.5022843000001164.11158.495.8519166.669.373852.816.7107.3166.4321940.4051.2516123636487.415.626139.8843411864172.136.53043.0254.61312.0646705620.2811044941.7512299.793.38251611178.659010.78468.17896449.8143.96433.512603900910334333333103903.14.7911663597536121.00623938.0437.95111.5674520.120.38215992569375110553.780257843.1681.564.2171882318567144811.6725.7154.2093220836.44600126187.48.8633804840000057949.2669311.73948.4370.48275444516.7175.90092936111.911.504.36289297106.6224127.52416.625193.251916424.61500990.52182.4798213.25261256.411253.980.12797490393.910.5298383689198630.9847340.5254584070.107125.387578219454.015.32107.13617.6686.023818.68611834358309667166269.03197332.181.481720700.54215057.58571.608987144022.87893923.15029.1374.64879107.08192345648000003.573.570.461.6958017.0687378890000.366.035867495398620000.83153498.508143757000071.57134254000018.9977.697158.694102.387435.7257937509979.660.44156719812.0983966.6194.03973.4593531.725151127385333.77831.670367129.436819305.670137.0846.496.865.6794.9750848.77620.2500.52586.8622820666671164.1013.17158.6165.23797.624.9616.5108.4166.1338041.0931.2515863333390.115.64139.3847129864173.236.13049.8255.7489.9652503160.3811557694.9320121.232.42226412490.179661.33435.80910333.6451.70713.0533261038712204333333111088.84.4113320568413564.07808941.7441.2117.660.3511828043817295973.361263182.4873.393.7381635616134166260.6223.4864.1441192155.93510137480.47.9829910703333350346.2360313.69987.5080.40437451406.6202.58483369633.310.544.29938201122.1151127.04214.676210.036518773.11543554.45212.1716232.40081157.041142.240.11211507823.130.4887213970465390.9387070.4762413940.075124.231038238644.034.9698.28423.0187.159519.83413934414763333173823.44202432.691.448108470.52222687.11601.361489088921.01030.7971.32582256.89208045518666673.703.690.451.7759160.8998381590000.365.673830076009060000.831355.895.414159485000071.57147959000018.2297.493157.879109.788084.61582092910858.900.38656121859.0288708.8212.431037.2898935.028449981860733.3379232.749135.2576.576.875.6794.4747448.72619.9390.52584.2622815000001174.1112.78158.1166.33779.624.8316.6107.8166.7339541.4421.2516376666789.515.707138.8846790862173.136.23030.6255.69510.2157310490.3418068041.3821722.652.1467662400.262023.851432.86307896.2710.41377.6520957022410163333337718.910.734713782438301.7507539.829.81310.6760355.600.9670212963430313352218.808113978.98222.689.793664696529143222.9969.4816.47187588610.67185.5587190141290.021.42874030766667185391.8422054.630622.1321.43122416807.973.10851093482.128.14534.957211.313880743.4562228.07433.00068.03976159.65199380.3367.2069268.008664.55801616.40200.01041613.85394.16440.30850267834.170.6874951829589602.089180.69839213011.194383.386047159375.747.89219.4559.7437.85967.601643192536266779094.25102839.193.288719031.47105557.99321.907041664435.194955.17015.76135.10242579.3210930.25619502760.128368620000020110810.249195670820565121.880.1221.890.310.9430531.6133292870000.798.233294452681360000.5947.42611696.847.5579152.41959756500050.0157613700026.652837.506127.69410.38411.813384.598227.6916.015062.427916.012062.4394138.7292.600910.7861171.9144199.53911.101497.628743851488.563788.7139616.337.01174.0643745.39097400932399.4140.66849.035020.37887.0245142.280224.441328131.086727726.462157.734.6659.71944.844.0668.15280159.542656.15522.7510.4881.0147128.95525.0319492333331433.2410.59147.5119.1089158.5100.543727.820.9519.594.7154.9370645.8151.1214770000091.216.638139.1802341887164.336.93094.0263.8738.7728682781.298434413.496374.824.3964251257.261128.762386.41154204.565.7457814.199921165216586666724666.220.752472501218318.3130945.295.28666.22446106.721.6033961287620927215317.15450624.72417.9919.18211925611743622886.83130.998.8411113803420.5898.9355355826562.442.455920459666673478177.9141402.322741.5011.7884368401.640.9110546929.952.40269.457323.306477922.2007456.68060.44545.93043230.6998277.9937.3229136.869741.48583000.17102.66332995.55202.66470.58459121293.261.17455948580952.949201.1752618209.6624.49837283421.8814.16390.3946.1519.62434.358387102302233341209.6556330.805.635620121.3961146.13177.156127682956.0596979.5549.19219.94430040.207030.48410321950.237202403333310867080.460105717711060441.120.2261.120.180.5619112.5622681600000.7713.369428302036440000.3724.25543144.724.2212229.16555037000037.4653802500025.302539.506340.41514.41911.740485.142738.9316.373361.068816.349161.1590198.1295.399410.4761161.3668274.0286.67776.79462318770.451811.3420316.218.3589.8222500.14549934136768.3052.23851.464419.42416.9706143.408528.288449143.309727919.456188.0334.6759.31474.834.0568.15971155.471064.88926.1560.4178.8554141.46529.0718560000001433.2411.46147.0116.7721157.890.793754.722.4919.695.1156.1356646.0771.1214806666791.917.001138.2793816901165.936.83047.1264.13310.3020166271.604202641.003238.918.2772379148.557395.02389.27615405.6437.04643.8320939699871366666781468.53.949432736009403.02148836.2235.97129.8052724.430.2942291145411646136904.723241831.0797.975.0162330922971161378.1031.1146.0312274385.27629.113273197269.410.4833854596666771740.348599.641810.0154.66623434900.0141.63802282702.113.491615.51024.9669620790.5512131.59518.721160.238212851.16463499.49149.0219710.8981176.3458884.80509.1313878.55996.36080.17214471697.130.4394043684628010.7597540.4391754329.903134.334381222846.944.32113.17217.6883.610017.10411024258717333175383.10233220.371.498298300.51234088.25548.847975260820.98016624.65125.8283.33882493.4017560.15432564420.074461416666734390450.145336007034443403.840.0733.820.461.8159398.7866318190000.355.851836614549260000.8570.04511341.869.6170100.258119287000073.37111518000010.920991.504119.1397.7955.3134188.038517.4826.109038.294626.140138.248487.78167.07245.9782101.5081159.73982.016063.8440066678090.580.35996516203.4160853.9156.27792.5371171.820540803781380.0632.59788.201811.33093.8941256.651721.930327109.417158902.847135.9926.6639.54986.925.7093.47453125.418348.32019.8060.5264.1208165.94592.1323174000001144.1512.56160.189.8065168.073.133870.925.1716.5103.3168.5330240.7231.2716666666786.615.472141.7876214844174.035.83106.4253.33510.3453938820.2897087690.0716197.052.3743829215.527429.47383.87615220.3037.95243.81692910188969636666782034.83.899475666023637.43113237.1637.60129.1737722.300.2841251064010889127894.491239623.8389.465.0292177621323161750.1128.5748.0591255615.06694.617868398131.49.8306922673333366739.5679910.70699.2654.56747935088.9147.84602282801.712.321739.25954.9566047598.4021130.64517.089163.833912962.47462177.87157.1718776.2980178.9679846.31557.5457855.641090.98670.15564473377.170.4386933734668570.7452650.4426354503.415133.955037214561.414.30109.23921.5358.173218.38211144279539333171196.42232995.131.515555210.51234367.13613.639876277721.19528723.50126.8581.68081468.9517370.15133147900.074462540000034648650.144341143434603453.910.0723.890.461.8460173.8696707210000.355.733847454881300000.8473.51331309.873.116999.650129753000074.70123854000010.990390.942518.7917.6765.2659189.730616.6426.394337.880926.284838.038888.54168.25315.936991.9435159.93283.266310.0141367848198.280.35299016421.6762047.3158.29808.1674093.320533872744779.9932.96988.054311.35003.9080255.744122.286281106.444648825.794134.8326.6536.73376.935.7295.67500114.560948.49119.7960.5258.5344166.46591.0823118666671154.1612.74159.682.2592168.772.593843.525.3716.4102.9168.9332140.8641.2716416666787.315.446141.0849730846175.535.73059.9253.27310.1558209480.2820148001.1216347.892.3756195429.944936.15744.44309102.1122.02306.9364309607494816666748786.07.475244762930510.78947123.9023.84298.3941543.270.2600691989820230237828.572120312.32164.669.566404063977799729.0654.7626.44814763811.10358.4294126261774.218.80634854166667124067.8914835.382417.4530.12665817546.189.30901141575.622.59879.22109.5988208850.9369250.95229.781100.15946940.40237735.4296.7897388.3238116.10401330.39281.83391326.74557.25810.26207253395.110.5859132125988231.115740.5862758828.5268.650238167629.486.48179.86013.6045.304510.3457042355505667133585.43128432.872.481463910.51127498.51388.567355139530.31923639.22018.63115.77146439.6012390.19126147700.095461293333327227940.183264065427544092.730.0912.730.361.2930428.0934440310000.367.145898343549050000.7236.97881441.536.9625132.31681707500062.1379739400010.706193.343023.8788.9475.2608189.927522.7826.579137.618126.490537.7443117.81172.25895.799489.1254178.75342.872880.4812479604279.780.3971868512.5831335.583.27470.9137265.910374592021350.2834.20089.096011.21793.9067255.829322.85391110.843988976.889148.9696.6036.35036.915.7295.97884113.407450.70620.5680.5357.3992108.19593.1323082000001144.1713.98160.982.2885169.071.043837.026.3816.3102.1169.1317140.1751.2616680000086.815.496141.6862102849175.636.03089.5251.21111.6947691060.2610294895.848887.573.9191484978.424762.61766.80309133.8821.52237.0655428996451260000048513.87.675235312950220.28209523.0723.12297.8689146.000.2818452062320946246078.541119972.76172.189.619417384131697379.5658.1825.69804915211.23329.1167131060490.219.96884435766667128971.0815375.029518.3930.03472717536.085.55881141402.424.00843.37459.5690528947.5400256.40632.55398.43767198.90235197.7591.7173364.7039111.69931372.74262.96331373.83520.75000.28101254430.040.5976982095331411.120080.5951168834.711268.578237164817.946.71185.80512.8642.81239.6416972353380000132051.79125660.142.546472790.52124561.13360.554754572831.21106140.29118.50117.75645631.3412160.19226010260.094434973333327178720.184264837527601672.670.0912.670.361.2630166.9164415220000.377.445897333516070000.7235.66151456.135.6897133.19982226500062.3379986900010.783392.677724.7309.1625.2790189.263623.1326.437837.819126.444837.8098117.49172.18435.802097.0949180.47841.632847.3911963754165.020.4005318228.7031647.380.62449.7637485.110369096473750.1434.52989.033611.22573.9577252.549122.837682102.783958966.411150.7666.6537.89066.955.7095.97846121.434650.86320.7890.5361.3817109.32592.8923192666671154.1713.91160.487.5625168.171.103926.026.6016.3103.3169.3320540.0981.2716456666787.015.462141.9855637849175.136.03075.1251.67911.7640131930.2802374878.238634.104.0234704360.682007.14831.48214410.5920.861915.720775899297036666726408.332.973624662375492.46301613.1812.97362.692561.321.1622421309215252543711.26490535.96243.7512.571431264275359056.8276.2425.33285089117.94217.4148135041319.424.89883079533333133386.6015944.513823.7124.63977117391.561.89771180376.631.34824.347811.146017144.6877367.12344.82479.57337976.70193069.4873.7839333.6070105.21001527.18219.67551502.67450.62230.28669185454.541.420481632690370.9289171.5264210128.151296.317108119784.289.94229.4868.8040.76699.0216282065741000118721.53118435.742.616581811.3399537.68320.084539753441.02351746.77614.23149.59639249.4710640.26618821110.134293003333319936750.252187142520759262.890.1202.890.271.3834993.4683704010000.599.544430532844440000.5347.46972190.647.5562173.99187729200039.8284403000012.965877.078729.95011.8358.3483119.634533.2719.621250.96019.587751.0470147.10100.38999.9536183.8840222.62323.931112.3822506312408.312.127889597.9317075.882.00230.2219582.55726722181382.6345.76551.592419.37734.4379224.922639.474281175.080165779.840183.9495.7348.47095.694.7371.46245181.746564.54726.8250.4188.6710141.93389.8916963333331692.839.56120.7119.7508116.186.212731.219.0922.686.2125.7385548.3280.9613616666711119.073111.38169681052140.944.32514.7307.7577.9618725411.227512798.308647.744.845815OpenBenchmarking.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 2022.2.devModel: Vehicle Detection FP16-INT8 - Device: CPUEPYC 7713 2PEPYC 7713EPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P3K6K9K12K15KSE +/- 4.40, N = 3SE +/- 1.18, N = 3SE +/- 2.45, N = 3SE +/- 0.83, N = 3SE +/- 2.25, N = 3SE +/- 1.40, N = 3SE +/- 1.28, N = 3SE +/- 3.26, N = 3SE +/- 3.31, N = 3SE +/- 5.49, N = 3SE +/- 7.76, N = 3SE +/- 5.13, N = 3SE +/- 3.81, N = 3SE +/- 0.65, N = 3SE +/- 0.72, N = 3SE +/- 3.55, N = 3SE +/- 11.42, N = 3SE +/- 16.12, N = 3SE +/- 9.84, N = 3SE +/- 14.36, N = 33317.721694.531901.213748.341864.663659.992255.591976.253873.026003.736582.2811178.6512490.172400.261257.269148.559215.525429.944978.424360.681. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.2.devModel: Person Vehicle Bike Detection FP16 - Device: CPUEPYC 7713 2PEPYC 7713EPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P2K4K6K8K10KSE +/- 5.98, N = 3SE +/- 0.76, N = 3SE +/- 0.54, N = 3SE +/- 0.68, N = 3SE +/- 0.30, N = 3SE +/- 1.92, N = 3SE +/- 1.06, N = 3SE +/- 2.38, N = 3SE +/- 5.47, N = 3SE +/- 5.10, N = 3SE +/- 8.43, N = 3SE +/- 3.74, N = 3SE +/- 0.76, N = 3SE +/- 0.14, N = 3SE +/- 0.72, N = 3SE +/- 6.11, N = 3SE +/- 5.54, N = 3SE +/- 12.97, N = 3SE +/- 2.56, N = 3SE +/- 8.28, N = 32682.291520.031637.962914.321876.123202.241127.83984.421727.845763.316138.929010.789661.332023.851128.767395.027429.474936.154762.612007.141. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.2.devModel: Face Detection FP16 - Device: CPUEPYC 7713 2PEPYC 7713EPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P8001600240032004000SE +/- 9.94, N = 3SE +/- 5.55, N = 3SE +/- 3.86, N = 3SE +/- 2.80, N = 3SE +/- 1.12, N = 3SE +/- 5.57, N = 3SE +/- 4.78, N = 3SE +/- 2.14, N = 3SE +/- 0.65, N = 3SE +/- 0.29, N = 3SE +/- 0.45, N = 3SE +/- 0.05, N = 3SE +/- 1.05, N = 3SE +/- 1.37, N = 3SE +/- 4.30, N = 3SE +/- 0.37, N = 3SE +/- 0.12, N = 3SE +/- 0.26, N = 3SE +/- 0.18, N = 3SE +/- 5.16, N = 32018.733554.863238.661982.523059.081821.211645.061466.52730.17955.51890.80468.17435.801432.862386.41389.27383.87744.44766.80831.481. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv

Sysbench

This is a benchmark of Sysbench with the built-in CPU and memory sub-tests. Sysbench is a scriptable multi-threaded benchmark tool based on LuaJIT. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgEvents Per Second, More Is BetterSysbench 1.0.20Test: CPUEPYC 7713 2PEPYC 7713EPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P200K400K600K800K1000KSE +/- 661.98, N = 3SE +/- 35.68, N = 3SE +/- 16.30, N = 3SE +/- 171.45, N = 3SE +/- 64.96, N = 3SE +/- 738.28, N = 3SE +/- 3.27, N = 3SE +/- 28.31, N = 3SE +/- 19.61, N = 3SE +/- 1162.56, N = 3SE +/- 28.32, N = 3SE +/- 1204.93, N = 3SE +/- 1525.81, N = 3SE +/- 153.88, N = 3SE +/- 5.76, N = 3SE +/- 284.53, N = 3SE +/- 425.17, N = 3SE +/- 51.83, N = 3SE +/- 24.46, N = 3SE +/- 2.38, N = 3500770.94252327.02252773.24503926.60265046.14528491.57107244.8299997.31200101.40446395.22457526.55896449.81910333.64307896.27154204.56615405.64615220.30309102.11309133.88214410.591. (CC) gcc options: -O2 -funroll-loops -rdynamic -ldl -laio -lm

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 2.10Benchmark: gravity_spheres_volume/dim_512/ao/real_timeEPYC 7713 2PEPYC 7713EPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P1224364860SE +/- 0.00705, N = 3SE +/- 0.00239, N = 3SE +/- 0.01245, N = 3SE +/- 0.01650, N = 3SE +/- 0.00528, N = 3SE +/- 0.00542, N = 3SE +/- 0.05149, N = 3SE +/- 0.00577, N = 3SE +/- 0.13341, N = 3SE +/- 0.01091, N = 3SE +/- 0.18329, N = 3SE +/- 0.03899, N = 3SE +/- 0.07975, N = 3SE +/- 0.01491, N = 3SE +/- 0.01042, N = 3SE +/- 0.02772, N = 3SE +/- 0.04942, N = 3SE +/- 0.00729, N = 3SE +/- 0.05480, N = 3SE +/- 0.04916, N = 313.418007.854849.0504016.409509.1471016.3969010.840009.5576618.7830026.5320030.5560043.9643051.7071010.413705.7457837.0464037.9524022.0230021.5223020.86190

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 7713 2PEPYC 7713EPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P612182430SE +/- 0.049975, N = 15SE +/- 0.062388, N = 4SE +/- 0.071304, N = 5SE +/- 0.063855, N = 15SE +/- 0.073072, N = 10SE +/- 0.041035, N = 7SE +/- 0.051396, N = 3SE +/- 0.069582, N = 3SE +/- 0.010884, N = 3SE +/- 0.049036, N = 15SE +/- 0.084204, N = 15SE +/- 0.044883, N = 15SE +/- 0.035923, N = 15SE +/- 0.030410, N = 6SE +/- 0.030708, N = 4SE +/- 0.066125, N = 12SE +/- 0.057833, N = 15SE +/- 0.036194, N = 6SE +/- 0.064993, N = 6SE +/- 0.032603, N = 45.69177811.31845010.1609305.5003179.5187815.12452926.16118027.34118016.7407905.8462305.2112323.5126033.0533267.65209514.1999203.8320933.8169296.9364307.06554215.7207701. (CXX) g++ options: -fopenmp -lmpi_cxx -lmpi

LeelaChessZero

LeelaChessZero (lc0 / lczero) is a chess engine automated vian neural networks. This test profile can be used for OpenCL, CUDA + cuDNN, and BLAS (CPU-based) benchmarking. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgNodes Per Second, More Is BetterLeelaChessZero 0.28Backend: EigenEPYC 7713 2PEPYC 7713EPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P2K4K6K8K10KSE +/- 39.68, N = 3SE +/- 40.72, N = 3SE +/- 27.81, N = 3SE +/- 32.87, N = 3SE +/- 13.96, N = 3SE +/- 62.77, N = 3SE +/- 37.69, N = 3SE +/- 15.30, N = 3SE +/- 88.45, N = 3SE +/- 107.55, N = 4SE +/- 7.94, N = 3SE +/- 125.11, N = 3SE +/- 125.50, N = 4SE +/- 81.86, N = 9SE +/- 9.29, N = 3SE +/- 22.88, N = 3SE +/- 83.80, N = 3SE +/- 109.97, N = 3SE +/- 105.96, N = 3SE +/- 31.21, N = 3418435963898459852865808445816826643925810155900910387702211659699101889607899658991. (CXX) g++ options: -flto -pthread

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 2021.01.31Threads: 256 - Buffer Length: 256 - Filter Length: 57EPYC 7713 2PEPYC 7713EPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P3000M6000M9000M12000M15000MSE +/- 1471205.10, N = 3SE +/- 4246174.75, N = 3SE +/- 1083717.88, N = 3SE +/- 1437976.97, N = 3SE +/- 1549551.91, N = 3SE +/- 3023794.53, N = 3SE +/- 9781672.20, N = 3SE +/- 4336793.49, N = 3SE +/- 12187197.29, N = 3SE +/- 6811836.10, N = 3SE +/- 9056182.66, N = 3SE +/- 4841946.35, N = 3SE +/- 11259563.84, N = 3SE +/- 1593040.42, N = 3SE +/- 2331189.49, N = 3SE +/- 2940710.42, N = 3SE +/- 3352776.63, N = 3SE +/- 3002406.44, N = 3SE +/- 8467191.58, N = 3SE +/- 968389.27, N = 353838666672781400000309316666760471333333040433333585290000015618666671405466667272223333351934666676140266667103343333331220433333341016333332165866667871366666796963666674948166667451260000029703666671. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

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 Xmlrig CPU mining performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgH/s, More Is BetterXmrig 6.12.1Variant: Monero - Hash Count: 1MEPYC 7713 2PEPYC 7713EPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P20K40K60K80K100KSE +/- 32.01, N = 3SE +/- 91.06, N = 3SE +/- 83.10, N = 3SE +/- 33.60, N = 3SE +/- 55.66, N = 3SE +/- 155.40, N = 3SE +/- 15.93, N = 3SE +/- 13.24, N = 3SE +/- 4.72, N = 3SE +/- 55.16, N = 3SE +/- 124.44, N = 4SE +/- 111.70, N = 5SE +/- 454.82, N = 5SE +/- 37.10, N = 3SE +/- 68.14, N = 3SE +/- 112.63, N = 4SE +/- 97.02, N = 4SE +/- 136.28, N = 3SE +/- 130.07, N = 3SE +/- 63.40, N = 351273.328571.831459.257031.036431.443442.814460.612857.123539.958736.163045.5103903.1111088.837718.924666.281468.582034.848786.048513.826408.31. (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 2022.2.devModel: Weld Porosity Detection FP16 - Device: CPUEPYC 7713 2PEPYC 7713EPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P816243240SE +/- 0.03, N = 3SE +/- 0.02, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.04, N = 3SE +/- 0.05, N = 3SE +/- 0.02, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.04, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.04, N = 316.6631.0728.3814.8826.7513.2732.3528.5729.089.589.004.794.4110.7320.753.943.897.477.6732.971. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv

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 7713 2PEPYC 7713EPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P300K600K900K1200K1500KSE +/- 4163.69, N = 3SE +/- 450.42, N = 3SE +/- 1349.13, N = 3SE +/- 6731.38, N = 4SE +/- 1089.17, N = 3SE +/- 3553.28, N = 3SE +/- 310.55, N = 3SE +/- 458.21, N = 3SE +/- 947.19, N = 3SE +/- 105.81, N = 3SE +/- 2286.04, N = 3SE +/- 14710.35, N = 3SE +/- 6319.46, N = 3SE +/- 1532.17, N = 3SE +/- 523.94, N = 3SE +/- 2445.95, N = 3SE +/- 14137.94, N = 3SE +/- 950.26, N = 3SE +/- 388.18, N = 3SE +/- 809.22, N = 3633847351178385205719323412150748109187642166227331746652970741536116635913320564713782472509432739475665244765235313624661. (CXX) g++ options: -lpthread -ldl -O2 -fPIC

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 7713 2PEPYC 7713EPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P2M4M6M8M10MSE +/- 1100.55, N = 3SE +/- 4825.91, N = 3SE +/- 8067.73, N = 3SE +/- 1745.40, N = 3SE +/- 8411.66, N = 3SE +/- 1391.68, N = 3SE +/- 10749.57, N = 3SE +/- 640.30, N = 3SE +/- 8718.18, N = 3SE +/- 4348.78, N = 3SE +/- 17803.94, N = 3SE +/- 75759.77, N = 3SE +/- 58302.36, N = 3SE +/- 341.38, N = 3SE +/- 1838.99, N = 3SE +/- 6330.65, N = 3SE +/- 9387.28, N = 3SE +/- 13633.41, N = 3SE +/- 16091.05, N = 3SE +/- 4774.22, N = 33659583.241824524.481876249.143706923.161987443.333867411.271177693.061055949.562006324.383753920.394111551.587536121.018413564.082438301.751218318.316009403.026023637.432930510.792950220.282375492.461. (CC) gcc options: -O2 -lrt" -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 2022.2.devModel: Person Detection FP16 - Device: CPUEPYC 7713 2PEPYC 7713EPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P1020304050SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.03, N = 3SE +/- 0.01, N = 3SE +/- 0.04, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.03, N = 3SE +/- 0.09, N = 3SE +/- 0.43, N = 4SE +/- 0.19, N = 3SE +/- 0.07, N = 3SE +/- 0.01, N = 3SE +/- 0.15, N = 3SE +/- 0.09, N = 3SE +/- 0.08, N = 3SE +/- 0.06, N = 3SE +/- 0.04, N = 313.016.797.5914.397.9715.266.896.1811.8827.7429.7438.0441.749.825.2936.2237.1623.9023.0713.181. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.2.devModel: Person Detection FP32 - Device: CPUEPYC 7713 2PEPYC 7713EPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P918273645SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.04, N = 3SE +/- 0.05, N = 3SE +/- 0.01, N = 3SE +/- 0.10, N = 3SE +/- 0.01, N = 3SE +/- 0.03, N = 3SE +/- 0.01, N = 3SE +/- 0.17, N = 3SE +/- 0.11, N = 3SE +/- 0.20, N = 3SE +/- 0.22, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.16, N = 3SE +/- 0.36, N = 3SE +/- 0.04, N = 3SE +/- 0.10, N = 3SE +/- 0.02, N = 312.846.787.5814.388.0215.126.746.0811.6727.5529.6837.9541.219.815.2835.9737.6023.8423.1212.971. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv

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 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P2004006008001000627.97277.13365.76166.30794.73864.64399.33246.66237.94111.57310.68666.22129.81129.17298.39297.87362.69-lfoamToVTK -ldynamicMesh -lfileFormats-lfoamToVTK -ldynamicMesh -lfileFormats-lfoamToVTK -ldynamicMesh -lfileFormats-lfoamToVTK -ldynamicMesh -lfileFormats-lfiniteVolume -lmeshTools -lparallel -lregionModels-lfiniteVolume -lmeshTools -lparallel -lregionModels-lfiniteVolume -lmeshTools -lparallel -lregionModels-lfiniteVolume -lmeshTools -lparallel -lregionModels-lfiniteVolume -lmeshTools -lparallel -lregionModels-lfiniteVolume -lmeshTools -lparallel -lregionModels-lfiniteVolume -lmeshTools -lparallel -lregionModels-lfiniteVolume -lmeshTools -lparallel -lregionModels-lfiniteVolume -lmeshTools -lparallel -lregionModels-lfiniteVolume -lmeshTools -lparallel -lregionModels-lfiniteVolume -lmeshTools -lparallel -lregionModels-lfoamToVTK -ldynamicMesh -lfileFormats1. (CXX) g++ options: -std=c++14 -m64 -O3 -ftemplate-depth-100 -fPIC -fuse-ld=bfd -Xlinker --add-needed --no-as-needed -llagrangian -lgenericPatchFields -lOpenFOAM -ldl -lm

Blender

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 3.3Blend File: Classroom - Compute: CPU-OnlyEPYC 7713 2PEPYC 7713EPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P306090120150SE +/- 0.36, N = 3SE +/- 0.07, N = 3SE +/- 0.18, N = 3SE +/- 0.04, N = 3SE +/- 0.08, N = 3SE +/- 0.11, N = 3SE +/- 0.26, N = 3SE +/- 0.20, N = 3SE +/- 0.07, N = 3SE +/- 0.06, N = 3SE +/- 0.05, N = 3SE +/- 0.02, N = 3SE +/- 0.03, N = 3SE +/- 0.21, N = 3SE +/- 0.08, N = 3SE +/- 0.02, N = 3SE +/- 0.03, N = 3SE +/- 0.01, N = 3SE +/- 0.05, N = 3SE +/- 0.10, N = 341.2977.1168.1735.0670.5736.39120.92136.4167.5738.7233.3920.1217.6655.60106.7224.4322.3043.2746.0061.32

oneDNN

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.7Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPUXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P0.45130.90261.35391.80522.2565SE +/- 0.000570, N = 7SE +/- 0.001673, N = 7SE +/- 0.002951, N = 7SE +/- 0.001445, N = 7SE +/- 0.001337, N = 7SE +/- 0.002791, N = 7SE +/- 0.003853, N = 15SE +/- 0.057585, N = 15SE +/- 0.003190, N = 7SE +/- 0.001079, N = 7SE +/- 0.002431, N = 15SE +/- 0.000585, N = 7SE +/- 0.000785, N = 7SE +/- 0.002890, N = 71.4046501.5187202.0058200.2907280.2751940.3821590.3511820.9670211.6033900.2942290.2841250.2600690.2818451.162240MIN: 1.3MIN: 1.37MIN: 1.91MIN: 0.28MIN: 0.48MIN: 1.54MIN: 11. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread

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 0.11Camera: 1 - Resolution: 4K - Samples Per Pixel: 16 - Renderer: Path TracerEPYC 7713 2PEPYC 7713EPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P13K26K39K52K65KSE +/- 21.40, N = 3SE +/- 6.36, N = 3SE +/- 43.02, N = 3SE +/- 67.34, N = 3SE +/- 77.82, N = 3SE +/- 24.26, N = 3SE +/- 20.67, N = 3SE +/- 51.07, N = 3SE +/- 41.65, N = 3SE +/- 11.92, N = 3SE +/- 20.21, N = 3SE +/- 6.17, N = 3SE +/- 13.35, N = 3SE +/- 51.24, N = 3SE +/- 11.61, N = 3SE +/- 13.62, N = 3SE +/- 8.50, N = 3SE +/- 7.06, N = 3SE +/- 7.54, N = 3SE +/- 129.10, N = 3222873963135029183193416917605416554820423834169711472292568043296346128711454106401989820623213091. (CXX) g++ options: -O3 -ldl

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.11Camera: 2 - Resolution: 4K - Samples Per Pixel: 16 - Renderer: Path TracerEPYC 7713 2PEPYC 7713EPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P13K26K39K52K65KSE +/- 21.23, N = 3SE +/- 34.59, N = 3SE +/- 38.76, N = 3SE +/- 35.24, N = 3SE +/- 81.80, N = 3SE +/- 49.96, N = 3SE +/- 44.86, N = 3SE +/- 54.60, N = 3SE +/- 13.45, N = 3SE +/- 9.61, N = 3SE +/- 40.04, N = 3SE +/- 14.38, N = 3SE +/- 11.98, N = 3SE +/- 26.54, N = 3SE +/- 82.30, N = 3SE +/- 5.69, N = 3SE +/- 12.91, N = 3SE +/- 14.57, N = 3SE +/- 16.33, N = 3SE +/- 99.88, N = 3227694009535372186143442418019419404861324058171621492693758172303136209211646108892023020946215251. (CXX) g++ options: -O3 -ldl

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.11Camera: 3 - Resolution: 4K - Samples Per Pixel: 16 - Renderer: Path TracerEPYC 7713 2PEPYC 7713EPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P15K30K45K60K75KSE +/- 132.07, N = 3SE +/- 66.46, N = 3SE +/- 26.14, N = 3SE +/- 27.62, N = 3SE +/- 121.66, N = 3SE +/- 17.36, N = 3SE +/- 123.33, N = 3SE +/- 112.43, N = 3SE +/- 41.79, N = 3SE +/- 5.61, N = 3SE +/- 30.02, N = 3SE +/- 16.26, N = 3SE +/- 10.97, N = 3SE +/- 41.34, N = 3SE +/- 111.69, N = 3SE +/- 14.85, N = 3SE +/- 3.06, N = 3SE +/- 8.19, N = 3SE +/- 19.97, N = 3SE +/- 140.36, N = 32685247147415382171840556208764961062896284322022817569110559597352217215313690127892378224607254371. (CXX) g++ options: -O3 -ldl

C-Ray

This is a test of C-Ray, a simple raytracer designed to test the floating-point CPU performance. This test is multi-threaded (16 threads per core), will shoot 8 rays per pixel for anti-aliasing, and will generate a 1600 x 1200 image. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterC-Ray 1.1Total Time - 4K, 16 Rays Per PixelEPYC 7713 2PEPYC 7713EPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P612182430SE +/- 0.033, N = 6SE +/- 0.014, N = 4SE +/- 0.017, N = 5SE +/- 0.023, N = 7SE +/- 0.010, N = 5SE +/- 0.044, N = 7SE +/- 0.065, N = 3SE +/- 0.079, N = 3SE +/- 0.034, N = 4SE +/- 0.012, N = 6SE +/- 0.022, N = 7SE +/- 0.063, N = 15SE +/- 0.084, N = 15SE +/- 0.012, N = 5SE +/- 0.037, N = 3SE +/- 0.057, N = 15SE +/- 0.054, N = 15SE +/- 0.021, N = 5SE +/- 0.016, N = 5SE +/- 0.058, N = 46.35712.35010.9535.57611.0105.78222.18625.07712.5546.6625.8043.7803.3618.80817.1544.7234.4918.5728.54111.2641. (CC) gcc options: -lm -lpthread -O3

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 7713 2PEPYC 7713EPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P60K120K180K240K300KSE +/- 369.61, N = 4SE +/- 29.35, N = 3SE +/- 21.43, N = 3SE +/- 290.00, N = 4SE +/- 208.16, N = 3SE +/- 1083.89, N = 6SE +/- 4.44, N = 3SE +/- 22.24, N = 3SE +/- 117.02, N = 3SE +/- 300.99, N = 4SE +/- 276.27, N = 4SE +/- 951.51, N = 6SE +/- 1129.41, N = 6SE +/- 202.53, N = 4SE +/- 51.11, N = 3SE +/- 525.61, N = 6SE +/- 1312.27, N = 6SE +/- 114.35, N = 4SE +/- 341.83, N = 4SE +/- 121.52, N = 3113107.5251976.9151889.31114669.2789188.95230050.3337710.5835288.0489186.77125438.45126790.36257843.16263182.48113978.9850624.72241831.07239623.83120312.32119972.7690535.961. (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 4.1.4

Blender

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 3.3Blend File: Barbershop - Compute: CPU-OnlyEPYC 7713 2PEPYC 7713EPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P120240360480600SE +/- 0.45, N = 3SE +/- 0.70, N = 3SE +/- 0.21, N = 3SE +/- 0.36, N = 3SE +/- 0.21, N = 3SE +/- 0.14, N = 3SE +/- 0.14, N = 3SE +/- 0.29, N = 3SE +/- 0.15, N = 3SE +/- 0.09, N = 3SE +/- 0.38, N = 3SE +/- 0.37, N = 3SE +/- 0.72, N = 3SE +/- 0.19, N = 3SE +/- 0.05, N = 3SE +/- 0.20, N = 3SE +/- 0.11, N = 3SE +/- 0.18, N = 3SE +/- 0.07, N = 3SE +/- 0.23, N = 3171.98300.10264.87142.26266.64140.20471.45538.81274.88143.31127.1181.5673.39222.68417.9997.9789.46164.66172.18243.75

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 7713 2PEPYC 7713EPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P612182430SE +/- 0.017, N = 6SE +/- 0.024, N = 4SE +/- 0.041, N = 4SE +/- 0.016, N = 6SE +/- 0.017, N = 5SE +/- 0.008, N = 7SE +/- 0.050, N = 3SE +/- 0.031, N = 3SE +/- 0.025, N = 4SE +/- 0.033, N = 6SE +/- 0.014, N = 6SE +/- 0.023, N = 8SE +/- 0.014, N = 9SE +/- 0.026, N = 5SE +/- 0.005, N = 3SE +/- 0.028, N = 7SE +/- 0.026, N = 7SE +/- 0.024, N = 5SE +/- 0.036, N = 5SE +/- 0.126, N = 46.65912.79412.3046.44311.2815.91524.57827.39113.5227.9886.9534.2173.7389.79319.1825.0165.0299.5669.61912.5711. (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 0.11Camera: 2 - Resolution: 4K - Samples Per Pixel: 32 - Renderer: Path TracerEPYC 7713 2PEPYC 7713EPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P30K60K90K120K150KSE +/- 132.40, N = 3SE +/- 107.07, N = 3SE +/- 72.64, N = 3SE +/- 85.62, N = 3SE +/- 88.52, N = 3SE +/- 73.14, N = 3SE +/- 425.81, N = 3SE +/- 503.46, N = 3SE +/- 73.98, N = 3SE +/- 75.68, N = 3SE +/- 52.88, N = 3SE +/- 47.26, N = 3SE +/- 9.49, N = 3SE +/- 134.17, N = 3SE +/- 189.04, N = 3SE +/- 24.88, N = 3SE +/- 12.86, N = 3SE +/- 60.79, N = 3SE +/- 34.87, N = 3SE +/- 93.72, N = 34570185606771083723274833360258938510206848349343232971518823163566646911925623309217764040641738431261. (CXX) g++ options: -O3 -ldl

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.11Camera: 1 - Resolution: 4K - Samples Per Pixel: 32 - Renderer: Path TracerEPYC 7713 2PEPYC 7713EPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P30K60K90K120K150KSE +/- 112.83, N = 3SE +/- 307.61, N = 3SE +/- 88.75, N = 3SE +/- 102.80, N = 3SE +/- 173.71, N = 3SE +/- 69.38, N = 3SE +/- 220.19, N = 3SE +/- 529.70, N = 3SE +/- 41.00, N = 3SE +/- 53.67, N = 3SE +/- 57.52, N = 3SE +/- 50.75, N = 3SE +/- 32.54, N = 3SE +/- 326.00, N = 3SE +/- 246.64, N = 3SE +/- 43.24, N = 3SE +/- 33.62, N = 3SE +/- 55.41, N = 3SE +/- 31.01, N = 3SE +/- 30.38, N = 34489485202762003662574550352708902010149247738339782944518567161346529111743622971213233977741316427531. (CXX) g++ options: -O3 -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 2022.2.devModel: Age Gender Recognition Retail 0013 FP16 - Device: CPUEPYC 7713 2PEPYC 7713EPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P40K80K120K160K200KSE +/- 135.49, N = 3SE +/- 26.93, N = 3SE +/- 6.50, N = 3SE +/- 25.85, N = 3SE +/- 39.91, N = 3SE +/- 23.57, N = 3SE +/- 13.80, N = 3SE +/- 19.72, N = 3SE +/- 14.05, N = 3SE +/- 105.34, N = 3SE +/- 7.87, N = 3SE +/- 625.00, N = 3SE +/- 462.02, N = 3SE +/- 34.76, N = 3SE +/- 13.32, N = 3SE +/- 1226.28, N = 3SE +/- 1059.23, N = 3SE +/- 52.00, N = 3SE +/- 69.14, N = 3SE +/- 187.68, N = 359879.3432070.1233814.3864899.7135966.8068270.4128673.9924550.4051258.54112325.82118385.58144811.67166260.6243222.9922886.83161378.10161750.1199729.0697379.5659056.821. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv

Blender

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 3.3Blend File: Pabellon Barcelona - Compute: CPU-OnlyEPYC 7713 2PEPYC 7713EPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P4080120160200SE +/- 0.19, N = 3SE +/- 0.09, N = 3SE +/- 0.05, N = 3SE +/- 0.06, N = 3SE +/- 0.02, N = 3SE +/- 0.03, N = 3SE +/- 0.20, N = 3SE +/- 0.36, N = 3SE +/- 0.14, N = 3SE +/- 0.07, N = 3SE +/- 0.12, N = 3SE +/- 0.02, N = 3SE +/- 0.20, N = 3SE +/- 0.07, N = 3SE +/- 0.09, N = 3SE +/- 0.10, N = 3SE +/- 0.33, N = 3SE +/- 0.28, N = 3SE +/- 0.08, N = 3SE +/- 0.25, N = 353.9996.2085.5144.0887.4045.22150.59170.4784.5548.8943.0325.7123.4869.48130.9931.1128.5754.7658.1876.24

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 2.10Benchmark: gravity_spheres_volume/dim_512/pathtracer/real_timeEPYC 7713 2PEPYC 7713EPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P1428425670SE +/- 0.00831, N = 3SE +/- 0.00883, N = 3SE +/- 0.00699, N = 3SE +/- 0.01341, N = 3SE +/- 0.00386, N = 3SE +/- 0.01802, N = 3SE +/- 0.02171, N = 3SE +/- 0.02192, N = 3SE +/- 0.06779, N = 3SE +/- 0.02040, N = 3SE +/- 0.03060, N = 3SE +/- 0.09801, N = 3SE +/- 0.10304, N = 3SE +/- 0.00771, N = 3SE +/- 0.00228, N = 3SE +/- 0.01513, N = 3SE +/- 0.02681, N = 3SE +/- 0.01551, N = 3SE +/- 0.01023, N = 3SE +/- 0.04257, N = 321.3887012.2406013.8682025.9482013.8114025.6820013.3799011.9921023.1910031.1664036.3203054.2093064.1441016.471808.8411146.0312048.0591026.4481025.6980025.33280

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 0.11Camera: 3 - Resolution: 4K - Samples Per Pixel: 32 - Renderer: Path TracerEPYC 7713 2PEPYC 7713EPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P30K60K90K120K150KSE +/- 168.11, N = 3SE +/- 132.46, N = 3SE +/- 64.26, N = 3SE +/- 75.07, N = 3SE +/- 132.68, N = 3SE +/- 141.78, N = 3SE +/- 406.86, N = 3SE +/- 279.04, N = 3SE +/- 63.56, N = 3SE +/- 80.97, N = 3SE +/- 70.57, N = 3SE +/- 20.98, N = 3SE +/- 26.91, N = 3SE +/- 70.43, N = 3SE +/- 218.50, N = 3SE +/- 32.90, N = 3SE +/- 30.95, N = 3SE +/- 21.43, N = 3SE +/- 30.66, N = 3SE +/- 44.01, N = 353386997758923043415869304190710521311998962545404923505922083192157588613803427438255614763849152508911. (CXX) g++ options: -O3 -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.orgms, Fewer Is BetterOpenVINO 2022.2.devModel: Vehicle Detection FP16 - Device: CPUEPYC 7713 2PEPYC 7713EPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P816243240SE +/- 0.02, N = 3SE +/- 0.04, N = 3SE +/- 0.04, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.04, N = 3SE +/- 0.02, 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 +/- 0.05, N = 3SE +/- 0.01, N = 3SE +/- 0.04, N = 316.7833.8230.1414.7026.5513.6836.2230.5615.5513.9914.046.445.9310.6720.585.275.0611.1011.2317.941. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv

Neural Magic DeepSparse

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.1Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Asynchronous Multi-StreamEPYC 9654EPYC 9654 - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P150300450600750SE +/- 0.33, N = 3SE +/- 0.50, N = 3SE +/- 0.41, N = 3SE +/- 0.23, N = 3SE +/- 0.32, N = 3SE +/- 0.55, N = 3SE +/- 0.30, N = 3SE +/- 0.26, N = 3SE +/- 1.45, N = 3401.20428.44185.5698.94629.11694.62358.43329.12217.41

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 0.11Camera: 2 - Resolution: 4K - Samples Per Pixel: 1 - Renderer: Path TracerEPYC 7713 2PEPYC 7713EPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P8001600240032004000SE +/- 2.40, N = 3SE +/- 3.28, N = 3SE +/- 1.33, N = 3SE +/- 2.19, N = 3SE +/- 1.20, N = 3SE +/- 0.33, N = 3SE +/- 4.16, N = 3SE +/- 6.64, N = 3SE +/- 1.00, N = 3SE +/- 0.33, N = 3SE +/- 0.67, N = 3SE +/- 1.53, N = 3SE +/- 1.53, N = 3SE +/- 1.73, N = 3SE +/- 2.65, N = 3SE +/- 0.67, N = 3SE +/- 1.15, N = 3SE +/- 1.53, N = 3SE +/- 1.86, N = 3SE +/- 4.10, N = 31422249421951158214011342622303615091071926600510190135587316831262131013501. (CXX) g++ options: -O3 -ldl

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 Xmlrig CPU mining performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgH/s, More Is BetterXmrig 6.12.1Variant: Wownero - Hash Count: 1MEPYC 7713 2PEPYC 7713EPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P30K60K90K120K150KSE +/- 49.46, N = 3SE +/- 206.18, N = 3SE +/- 59.15, N = 3SE +/- 212.72, N = 3SE +/- 22.36, N = 3SE +/- 236.60, N = 3SE +/- 91.33, N = 3SE +/- 76.21, N = 3SE +/- 76.17, N = 3SE +/- 23.53, N = 4SE +/- 49.38, N = 4SE +/- 196.84, N = 5SE +/- 156.60, N = 5SE +/- 35.95, N = 3SE +/- 128.10, N = 3SE +/- 83.46, N = 4SE +/- 164.95, N = 4SE +/- 46.14, N = 3SE +/- 86.61, N = 3SE +/- 99.58, N = 341903.737205.642583.649895.440297.249905.722902.919709.135545.475830.982117.1126187.4137480.441290.026562.497269.498131.461774.260490.241319.41. (CXX) g++ options: -fexceptions -fno-rtti -maes -O3 -Ofast -static-libgcc -static-libstdc++ -rdynamic -lssl -lcrypto -luv -lpthread -lrt -ldl -lhwloc

Tachyon

This is a test of the threaded Tachyon, a parallel ray-tracing system, measuring the time to ray-trace a sample scene. The sample scene used is the Teapot scene ray-traced to 8K x 8K with 32 samples. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTachyon 0.99.2Total TimeEPYC 7713 2PEPYC 7713EPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P1224364860SE +/- 0.1158, N = 3SE +/- 0.0206, N = 3SE +/- 0.0274, N = 3SE +/- 0.0272, N = 4SE +/- 0.0033, N = 3SE +/- 0.0692, N = 4SE +/- 0.0916, N = 3SE +/- 0.0267, N = 3SE +/- 0.0251, N = 3SE +/- 0.0101, N = 3SE +/- 0.0145, N = 4SE +/- 0.0823, N = 7SE +/- 0.0339, N = 6SE +/- 0.0327, N = 3SE +/- 0.0355, N = 3SE +/- 0.0786, N = 5SE +/- 0.0480, N = 5SE +/- 0.0045, N = 3SE +/- 0.0168, N = 3SE +/- 0.1125, N = 316.335631.160027.786914.165228.503614.696649.331555.557727.471816.758614.61458.86337.982921.428742.455910.48339.830618.806319.968824.89881. (CC) gcc options: -m64 -O3 -fomit-frame-pointer -ffast-math -ltachyon -lm -lpthread

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 2021.01.31Threads: 128 - Buffer Length: 256 - Filter Length: 57EPYC 7713 2PEPYC 7713EPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P2000M4000M6000M8000M10000MSE +/- 11583657.07, N = 3SE +/- 264575.13, N = 3SE +/- 2645751.31, N = 3SE +/- 1058825.34, N = 3SE +/- 3002406.44, N = 3SE +/- 7366666.67, N = 3SE +/- 1596175.99, N = 3SE +/- 6982199.59, N = 3SE +/- 3240541.79, N = 3SE +/- 1556705.92, N = 3SE +/- 2200000.00, N = 3SE +/- 3501904.24, N = 3SE +/- 9653036.37, N = 3SE +/- 2061013.77, N = 3SE +/- 2772083.05, N = 3SE +/- 7408178.66, N = 3SE +/- 11228881.41, N = 3SE +/- 2027587.51, N = 3SE +/- 1467802.59, N = 3SE +/- 16840460.54, N = 3510593333327205000003033300000559386666729637333335597333333149136666713318666672636866667517480000061829000008048400000910703333340307666672045966667854596666792267333334854166667443576666730795333331. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

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 0.11Camera: 1 - Resolution: 4K - Samples Per Pixel: 1 - Renderer: Path TracerEPYC 7713 2PEPYC 7713EPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P7001400210028003500SE +/- 4.26, N = 3SE +/- 5.24, N = 3SE +/- 1.76, N = 3SE +/- 2.52, N = 3SE +/- 0.33, N = 3SE +/- 1.86, N = 3SE +/- 2.33, N = 3SE +/- 6.94, N = 3SE +/- 0.88, N = 3SE +/- 0.33, N = 3SE +/- 0.88, N = 3SE +/- 0.67, N = 3SE +/- 0.33, N = 3SE +/- 1.45, N = 3SE +/- 3.51, N = 3SE +/- 0.67, N = 3SE +/- 0.33, N = 3SE +/- 0.88, N = 3SE +/- 0.67, N = 3SE +/- 2.85, N = 31397246421711137212511012603300314921060916579503185334787176671240128913331. (CXX) g++ options: -O3 -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.orgms, Fewer Is BetterOpenVINO 2022.2.devModel: Machine Translation EN To DE FP16 - Device: CPUEPYC 7713 2PEPYC 7713EPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P60120180240300SE +/- 0.77, N = 3SE +/- 0.44, N = 3SE +/- 0.48, N = 3SE +/- 0.53, N = 3SE +/- 0.07, N = 3SE +/- 0.28, N = 3SE +/- 0.13, N = 3SE +/- 0.25, N = 3SE +/- 0.38, N = 3SE +/- 0.09, N = 3SE +/- 0.06, N = 3SE +/- 0.03, N = 3SE +/- 0.05, N = 3SE +/- 0.21, N = 3SE +/- 0.40, N = 3SE +/- 0.03, N = 3SE +/- 0.07, N = 3SE +/- 0.03, N = 3SE +/- 0.12, N = 3SE +/- 0.47, N = 3143.18273.28243.26125.80227.77116.19142.37129.3777.5587.5281.2749.2646.2391.84177.9140.3439.5667.8971.0886.601. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv

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 0.11Camera: 3 - Resolution: 4K - Samples Per Pixel: 1 - Renderer: Path TracerEPYC 7713 2PEPYC 7713EPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P9001800270036004500SE +/- 1.53, N = 3SE +/- 2.03, N = 3SE +/- 4.33, N = 3SE +/- 2.33, N = 3SE +/- 1.00, N = 3SE +/- 1.20, N = 3SE +/- 4.67, N = 3SE +/- 7.94, N = 3SE +/- 0.88, N = 3SE +/- 0.58, N = 3SE +/- 1.20, N = 3SE +/- 1.45, N = 3SE +/- 1.76, N = 3SE +/- 2.33, N = 3SE +/- 7.37, N = 3SE +/- 0.88, N = 3SE +/- 0.58, N = 3SE +/- 1.33, N = 3SE +/- 1.15, N = 3SE +/- 5.90, N = 316492934258213502517130331053595178112631095693603220541408597991483153715941. (CXX) g++ options: -O3 -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 4.0Preset: ExhaustiveEPYC 7713 2PEPYC 7713EPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P48121620SE +/- 0.0540, N = 15SE +/- 0.0012, N = 3SE +/- 0.0004, N = 3SE +/- 0.0017, N = 5SE +/- 0.0013, N = 3SE +/- 0.0027, N = 5SE +/- 0.0026, N = 3SE +/- 0.0023, N = 3SE +/- 0.0047, N = 4SE +/- 0.0016, N = 4SE +/- 0.0031, N = 5SE +/- 0.0146, N = 6SE +/- 0.0373, N = 6SE +/- 0.0024, N = 4SE +/- 0.0005, N = 3SE +/- 0.0052, N = 5SE +/- 0.0010, N = 6SE +/- 0.0021, N = 4SE +/- 0.0005, N = 4SE +/- 0.0066, N = 46.05293.20683.61897.23923.62717.14072.26291.99784.09985.95687.036811.739413.69984.63062.32279.641810.70695.38245.02954.51381. (CXX) g++ options: -O3 -flto -pthread

Blender

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 3.3Blend File: BMW27 - Compute: CPU-OnlyEPYC 7713 2PEPYC 7713EPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P1224364860SE +/- 0.17, N = 3SE +/- 0.14, N = 3SE +/- 0.05, N = 3SE +/- 0.04, N = 4SE +/- 0.03, N = 3SE +/- 0.01, N = 4SE +/- 0.11, N = 3SE +/- 0.06, N = 3SE +/- 0.08, N = 3SE +/- 0.15, N = 4SE +/- 0.04, N = 4SE +/- 0.03, N = 5SE +/- 0.02, N = 6SE +/- 0.03, N = 3SE +/- 0.12, N = 3SE +/- 0.02, N = 5SE +/- 0.02, N = 5SE +/- 0.08, N = 3SE +/- 0.05, N = 3SE +/- 0.22, N = 317.0030.4126.9614.2727.5314.6145.6051.4225.8015.6313.598.437.5022.1341.5010.019.2617.4518.3923.71

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 7713 2PEPYC 7713EPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P20406080100SE +/- 0.22, N = 6SE +/- 0.14, N = 5SE +/- 0.20, N = 5SE +/- 0.34, N = 8SE +/- 0.20, N = 15SE +/- 0.35, N = 8SE +/- 0.02, N = 3SE +/- 0.03, N = 3SE +/- 0.04, N = 5SE +/- 0.28, N = 7SE +/- 0.17, N = 7SE +/- 0.07, N = 9SE +/- 0.08, N = 9SE +/- 0.11, N = 5SE +/- 0.12, N = 6SE +/- 0.04, N = 8SE +/- 0.06, N = 8SE +/- 0.25, N = 6SE +/- 0.26, N = 6SE +/- 0.16, N = 532.6320.7323.4838.9129.4651.0513.5012.1323.0339.1543.9570.4880.4021.4311.7954.6754.5730.1330.0324.641. (CC) gcc options: -O3 -march=native -fopenmp

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.orgsign/s, More Is BetterOpenSSL 3.0Algorithm: RSA4096EPYC 7713 2PEPYC 7713EPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P11K22K33K44K55KSE +/- 9.34, N = 3SE +/- 1.23, N = 3SE +/- 3.42, N = 3SE +/- 22.46, N = 3SE +/- 25.24, N = 3SE +/- 13.15, N = 3SE +/- 8.67, N = 3SE +/- 94.29, N = 3SE +/- 89.52, N = 3SE +/- 0.35, N = 3SE +/- 27.29, N = 3SE +/- 25.12, N = 3SE +/- 95.15, N = 3SE +/- 0.22, N = 3SE +/- 7.57, N = 3SE +/- 19.62, N = 3SE +/- 12.09, N = 3SE +/- 10.36, N = 3SE +/- 21.02, N = 3SE +/- 173.15, N = 324998.012612.113287.526521.813762.327127.88462.57690.316041.522205.325901.844516.751406.616807.98401.634900.035088.917546.117536.017391.51. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl

Embree

Intel Embree is a collection of high-performance ray-tracing kernels for execution on CPUs 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 3.13Binary: Pathtracer - Model: CrownEPYC 7713 2PEPYC 7713EPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P4080120160200SE +/- 0.10, N = 6SE +/- 0.06, N = 4SE +/- 0.10, N = 5SE +/- 0.24, N = 7SE +/- 0.12, N = 5SE +/- 0.14, N = 7SE +/- 0.05, N = 3SE +/- 0.07, N = 3SE +/- 0.14, N = 5SE +/- 0.14, N = 6SE +/- 0.08, N = 7SE +/- 0.38, N = 8SE +/- 0.43, N = 8SE +/- 0.11, N = 5SE +/- 0.09, N = 4SE +/- 0.36, N = 7SE +/- 0.31, N = 7SE +/- 0.09, N = 6SE +/- 0.09, N = 6SE +/- 0.09, N = 589.4751.8963.19111.9468.86127.8535.0930.9457.65102.97115.54175.90202.5873.1140.91141.64147.8589.3185.5661.90

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 3.0Algorithm: RSA4096EPYC 7713 2PEPYC 7713EPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P700K1400K2100K2800K3500KSE +/- 296.25, N = 3SE +/- 70.93, N = 3SE +/- 79.21, N = 3SE +/- 3081.20, N = 3SE +/- 1242.31, N = 3SE +/- 180.37, N = 3SE +/- 1367.77, N = 3SE +/- 438.19, N = 3SE +/- 1640.19, N = 3SE +/- 93.24, N = 3SE +/- 137.73, N = 3SE +/- 457.50, N = 3SE +/- 708.03, N = 3SE +/- 130.95, N = 3SE +/- 27.52, N = 3SE +/- 160.33, N = 3SE +/- 169.85, N = 3SE +/- 60.43, N = 3SE +/- 79.86, N = 3SE +/- 5774.79, N = 31633628.1823890.5867678.41728763.7902005.31780874.6588480.5519444.71068009.01463630.71689673.12936111.93369633.31093482.1546929.92282702.12282801.71141575.61141402.41180376.61. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl

Blender

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 3.3Blend File: Fishy Cat - Compute: CPU-OnlyEPYC 7713 2PEPYC 7713EPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P1530456075SE +/- 0.09, N = 3SE +/- 0.04, N = 3SE +/- 0.10, N = 3SE +/- 0.18, N = 3SE +/- 0.15, N = 3SE +/- 0.10, N = 3SE +/- 0.36, N = 3SE +/- 0.28, N = 3SE +/- 0.06, N = 3SE +/- 0.13, N = 3SE +/- 0.02, N = 3SE +/- 0.05, N = 4SE +/- 0.06, N = 5SE +/- 0.18, N = 3SE +/- 0.03, N = 3SE +/- 0.06, N = 4SE +/- 0.06, N = 4SE +/- 0.04, N = 3SE +/- 0.07, N = 3SE +/- 0.11, N = 322.0339.0434.5118.4934.9718.7060.8468.0834.3420.4718.0511.5010.5428.1452.4013.4912.3222.5924.0031.34

Neural Magic DeepSparse

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.1Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-StreamEPYC 9654EPYC 9654 - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P400800120016002000SE +/- 0.42, N = 3SE +/- 0.46, N = 3SE +/- 0.95, N = 3SE +/- 0.32, N = 3SE +/- 0.15, N = 3SE +/- 1.89, N = 3SE +/- 0.74, N = 3SE +/- 0.93, N = 3SE +/- 0.94, N = 31014.621133.41534.96269.461615.511739.26879.22843.37824.35

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 7713 2PEPYC 7713EPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P612182430SE +/- 0.03902515, N = 4SE +/- 0.14874204, N = 3SE +/- 0.17583211, N = 3SE +/- 0.03743001, N = 4SE +/- 0.05294615, N = 3SE +/- 0.09231981, N = 15SE +/- 0.00677335, N = 3SE +/- 0.09921822, N = 3SE +/- 0.02271047, N = 4SE +/- 0.05206844, N = 5SE +/- 0.02766243, N = 5SE +/- 0.01966452, N = 7SE +/- 0.01984368, N = 7SE +/- 0.03398896, N = 4SE +/- 0.03504156, N = 3SE +/- 0.03372817, N = 7SE +/- 0.02752118, N = 7SE +/- 0.02649159, N = 5SE +/- 0.04408610, N = 5SE +/- 0.01369263, N = 411.0147963021.8494053021.8095589011.0087018016.875356109.5077899323.9661535026.4537697012.247636108.226202778.077799804.362892974.2993820111.3138807023.306477904.966962074.956604759.598820889.5690528911.146017101. (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

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 4.0Preset: ThoroughEPYC 7713 2PEPYC 7713EPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P306090120150SE +/- 0.04, N = 5SE +/- 0.01, N = 4SE +/- 0.04, N = 5SE +/- 0.02, N = 6SE +/- 0.01, N = 5SE +/- 0.02, N = 6SE +/- 0.06, N = 4SE +/- 0.03, N = 3SE +/- 0.02, N = 5SE +/- 0.01, N = 6SE +/- 0.04, N = 6SE +/- 0.05, N = 7SE +/- 0.08, N = 7SE +/- 0.07, N = 5SE +/- 0.03, N = 4SE +/- 0.01, N = 6SE +/- 0.02, N = 7SE +/- 0.01, N = 5SE +/- 0.01, N = 5SE +/- 0.05, N = 557.7930.1333.8966.2834.1165.6122.4819.9440.3156.2065.40106.62122.1243.4622.2090.5598.4050.9447.5444.691. (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 3.1.1Test: Basic - Device: CPUEPYC 7713 2PEPYC 7713EPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P160320480640800SE +/- 3.65, N = 4SE +/- 4.48, N = 3SE +/- 4.68, N = 3SE +/- 3.63, N = 4SE +/- 3.13, N = 4SE +/- 1.24, N = 12SE +/- 2.68, N = 3SE +/- 2.68, N = 3SE +/- 3.97, N = 3SE +/- 2.71, N = 5SE +/- 2.38, N = 6SE +/- 0.19, N = 3SE +/- 1.23, N = 12SE +/- 0.08, N = 3SE +/- 3.73, N = 3SE +/- 0.15, N = 3SE +/- 1.24, N = 12SE +/- 2.75, N = 5SE +/- 2.72, N = 5SE +/- 3.95, N = 3296.13572.31566.38293.34276.59147.36716.75763.20383.39247.09245.03127.52127.04228.07456.68131.60130.65250.95256.41367.121. (CXX) g++ options: -fopenmp -std=c++0x -O3 -rdynamic -ldl -ltiff -lfftw3f -lfftw3 -lpng -lmpi_cxx -lmpi

Rodinia

Rodinia is a suite focused upon accelerating compute-intensive applications with accelerators. CUDA, OpenMP, and OpenCL parallel models are supported by the included applications. This profile utilizes select OpenCL, NVIDIA CUDA and OpenMP test binaries at the moment. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 3.1Test: OpenMP LavaMDEPYC 7713 2PEPYC 7713EPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P20406080100SE +/- 0.11, N = 3SE +/- 0.02, N = 3SE +/- 0.09, N = 3SE +/- 0.20, N = 3SE +/- 0.07, N = 3SE +/- 0.30, N = 3SE +/- 0.28, N = 3SE +/- 0.04, N = 3SE +/- 0.08, N = 3SE +/- 0.05, N = 3SE +/- 0.06, N = 3SE +/- 0.04, N = 4SE +/- 0.03, N = 4SE +/- 0.07, N = 3SE +/- 0.13, N = 3SE +/- 0.02, N = 3SE +/- 0.05, N = 3SE +/- 0.03, N = 3SE +/- 0.02, N = 3SE +/- 0.15, N = 326.9246.1642.2423.9543.7825.1978.7286.9248.1128.6124.4916.6314.6833.0060.4518.7217.0929.7832.5544.821. (CXX) g++ options: -O2 -lOpenCL

Embree

Intel Embree is a collection of high-performance ray-tracing kernels for execution on CPUs 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 3.13Binary: Pathtracer - Model: Asian DragonEPYC 7713 2PEPYC 7713EPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P50100150200250SE +/- 0.64, N = 5SE +/- 0.27, N = 5SE +/- 0.10, N = 5SE +/- 0.51, N = 5SE +/- 0.18, N = 6SE +/- 1.00, N = 6SE +/- 0.20, N = 4SE +/- 0.09, N = 3SE +/- 0.36, N = 5SE +/- 0.26, N = 7SE +/- 0.14, N = 7SE +/- 0.20, N = 8SE +/- 0.29, N = 9SE +/- 0.13, N = 5SE +/- 0.16, N = 4SE +/- 0.23, N = 8SE +/- 0.18, N = 8SE +/- 0.12, N = 6SE +/- 0.36, N = 6SE +/- 0.27, N = 568.6663.1171.1573.6180.65100.0441.9735.8069.99120.76137.93193.25210.0468.0445.93160.24163.83100.1698.4479.57

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: EP.CEPYC 7713 2PEPYC 7713EPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P4K8K12K16K20KSE +/- 117.79, N = 15SE +/- 31.46, N = 15SE +/- 49.37, N = 15SE +/- 26.79, N = 11SE +/- 92.00, N = 15SE +/- 128.91, N = 15SE +/- 32.11, N = 11SE +/- 28.44, N = 15SE +/- 67.04, N = 15SE +/- 86.35, N = 15SE +/- 39.65, N = 15SE +/- 112.63, N = 12SE +/- 97.05, N = 15SE +/- 46.76, N = 15SE +/- 11.53, N = 9SE +/- 108.53, N = 15SE +/- 23.76, N = 12SE +/- 140.16, N = 15SE +/- 131.05, N = 15SE +/- 86.42, N = 158241.134531.174982.829241.564968.989285.184390.983979.087622.718633.629551.9416424.6118773.116159.653230.6912851.1612962.476940.407198.907976.701. (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 4.1.4

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: BT.CEPYC 7713 2PEPYC 7713EPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P120K240K360K480K600KSE +/- 1004.45, N = 4SE +/- 363.87, N = 3SE +/- 218.03, N = 3SE +/- 401.49, N = 4SE +/- 269.58, N = 3SE +/- 1679.40, N = 5SE +/- 356.18, N = 3SE +/- 152.73, N = 3SE +/- 706.35, N = 4SE +/- 1212.90, N = 4SE +/- 1011.25, N = 5SE +/- 2523.78, N = 6SE +/- 3150.15, N = 6SE +/- 179.20, N = 4SE +/- 44.90, N = 3SE +/- 3154.34, N = 6SE +/- 4145.25, N = 6SE +/- 649.68, N = 4SE +/- 455.33, N = 4SE +/- 520.33, N = 4232312.47127746.66133198.16252416.39166563.21369239.47115359.2095180.72194987.49267319.17274024.34500990.52543554.45199380.3398277.99463499.49462177.87237735.42235197.75193069.481. (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 4.1.4

Embree

Intel Embree is a collection of high-performance ray-tracing kernels for execution on CPUs 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 3.13Binary: Pathtracer ISPC - Model: CrownEPYC 7713 2PEPYC 7713EPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P50100150200250SE +/- 0.09, N = 6SE +/- 0.20, N = 4SE +/- 0.08, N = 5SE +/- 0.13, N = 6SE +/- 0.08, N = 5SE +/- 0.26, N = 7SE +/- 0.04, N = 4SE +/- 0.06, N = 4SE +/- 0.10, N = 5SE +/- 0.16, N = 7SE +/- 0.12, N = 7SE +/- 0.38, N = 8SE +/- 0.25, N = 8SE +/- 0.01, N = 5SE +/- 0.03, N = 3SE +/- 0.35, N = 8SE +/- 0.24, N = 8SE +/- 0.23, N = 6SE +/- 0.09, N = 6SE +/- 0.15, N = 582.5747.9258.17101.5763.47116.0843.0638.7668.36109.92123.62182.48212.1767.2137.32149.02157.1796.7991.7273.78

Neural Magic DeepSparse

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.1Model: CV Detection,YOLOv5s COCO - Scenario: Asynchronous Multi-StreamEPYC 9654EPYC 9654 - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P2004006008001000SE +/- 0.82, N = 3SE +/- 0.57, N = 3SE +/- 0.52, N = 3SE +/- 0.11, N = 3SE +/- 1.74, N = 3SE +/- 2.55, N = 3SE +/- 0.23, N = 3SE +/- 0.64, N = 3SE +/- 0.70, N = 3447.55499.75268.01136.87710.90776.30388.32364.70333.61

Embree

Intel Embree is a collection of high-performance ray-tracing kernels for execution on CPUs 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 3.13Binary: Pathtracer ISPC - Model: Asian DragonEPYC 7713 2PEPYC 7713EPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P50100150200250SE +/- 0.61, N = 15SE +/- 0.10, N = 5SE +/- 0.04, N = 5SE +/- 0.55, N = 15SE +/- 0.24, N = 5SE +/- 0.75, N = 15SE +/- 0.59, N = 5SE +/- 0.16, N = 4SE +/- 0.50, N = 6SE +/- 0.07, N = 7SE +/- 0.21, N = 8SE +/- 0.22, N = 9SE +/- 0.42, N = 9SE +/- 0.10, N = 5SE +/- 0.17, N = 4SE +/- 0.39, N = 8SE +/- 0.35, N = 8SE +/- 0.21, N = 7SE +/- 0.15, N = 7SE +/- 0.32, N = 667.3056.8766.0968.2672.2394.1055.8749.5789.10136.11154.64213.25232.4064.5641.49176.35178.97116.10111.70105.21

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 2022.2.devModel: Person Detection FP32 - Device: CPUEPYC 7713 2PEPYC 7713EPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P10002000300040005000SE +/- 3.97, N = 3SE +/- 5.69, N = 3SE +/- 10.19, N = 3SE +/- 7.70, N = 3SE +/- 7.16, N = 3SE +/- 12.20, N = 3SE +/- 3.45, N = 3SE +/- 4.22, N = 3SE +/- 1.83, N = 3SE +/- 9.11, N = 3SE +/- 6.56, N = 3SE +/- 7.07, N = 3SE +/- 6.16, N = 3SE +/- 1.82, N = 3SE +/- 6.44, N = 3SE +/- 4.19, N = 3SE +/- 8.23, N = 3SE +/- 2.35, N = 3SE +/- 5.54, N = 3SE +/- 2.36, N = 32453.374633.474147.582191.713931.312084.772916.122594.301359.691722.481598.261256.411157.041616.403000.17884.80846.311330.391372.741527.181. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv

Neural Magic DeepSparse

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.1Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-StreamEPYC 9654EPYC 9654 - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P120240360480600SE +/- 1.28, N = 3SE +/- 1.13, N = 3SE +/- 0.29, N = 3SE +/- 0.06, N = 3SE +/- 0.61, N = 3SE +/- 2.06, N = 3SE +/- 0.48, N = 3SE +/- 0.57, N = 3SE +/- 0.10, N = 3316.56336.60200.01102.66509.13557.55281.83262.96219.68

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 2022.2.devModel: Person Detection FP16 - Device: CPUEPYC 7713 2PEPYC 7713EPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P10002000300040005000SE +/- 4.14, N = 3SE +/- 1.50, N = 3SE +/- 4.63, N = 3SE +/- 5.23, N = 3SE +/- 4.41, N = 3SE +/- 6.50, N = 3SE +/- 3.72, N = 3SE +/- 4.45, N = 3SE +/- 0.67, N = 3SE +/- 2.17, N = 3SE +/- 4.15, N = 3SE +/- 13.83, N = 4SE +/- 5.11, N = 3SE +/- 10.93, N = 3SE +/- 7.45, N = 3SE +/- 3.73, N = 3SE +/- 1.97, N = 3SE +/- 3.90, N = 3SE +/- 2.15, N = 3SE +/- 4.07, N = 32425.014623.964151.952191.233956.742067.022868.212557.141336.051714.981597.311253.981142.241613.852995.55878.55855.641326.741373.831502.671. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv

Neural Magic DeepSparse

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.1Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-StreamEPYC 9654EPYC 9654 - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P2004006008001000SE +/- 2.07, N = 3SE +/- 1.04, N = 3SE +/- 0.23, N = 3SE +/- 0.39, N = 3SE +/- 0.91, N = 3SE +/- 3.40, N = 3SE +/- 1.32, N = 3SE +/- 0.71, N = 3SE +/- 0.95, N = 3626.04666.25394.16202.66996.361090.99557.26520.75450.62

NAMD

NAMD is a parallel molecular dynamics code designed for high-performance simulation of large biomolecular systems. NAMD was developed by the Theoretical and Computational Biophysics Group in the Beckman Institute for Advanced Science and Technology at the University of Illinois at Urbana-Champaign. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgdays/ns, Fewer Is BetterNAMD 2.14ATPase Simulation - 327,506 AtomsEPYC 7713 2PEPYC 7713EPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P0.13580.27160.40740.54320.679SE +/- 0.00094, N = 3SE +/- 0.00055, N = 3SE +/- 0.00059, N = 3SE +/- 0.00135, N = 4SE +/- 0.00050, N = 3SE +/- 0.00076, N = 4SE +/- 0.00094, N = 3SE +/- 0.00127, N = 3SE +/- 0.00027, N = 3SE +/- 0.00061, N = 3SE +/- 0.00029, N = 4SE +/- 0.00008, N = 3SE +/- 0.00027, N = 3SE +/- 0.00184, N = 3SE +/- 0.00096, N = 3SE +/- 0.00088, N = 3SE +/- 0.00089, N = 5SE +/- 0.00035, N = 4SE +/- 0.00012, N = 4SE +/- 0.00024, N = 30.267270.455210.382260.224180.376360.223660.544420.603350.304290.247980.221570.127970.112110.308500.584590.172140.155640.262070.281010.28669

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 7713 2PEPYC 7713EPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P110K220K330K440K550KSE +/- 2085.69, N = 5SE +/- 304.31, N = 4SE +/- 382.95, N = 4SE +/- 886.34, N = 6SE +/- 1813.78, N = 5SE +/- 2945.88, N = 10SE +/- 277.89, N = 3SE +/- 206.77, N = 3SE +/- 188.68, N = 5SE +/- 1225.90, N = 6SE +/- 741.37, N = 6SE +/- 3747.09, N = 7SE +/- 4645.52, N = 7SE +/- 895.16, N = 6SE +/- 666.33, N = 3SE +/- 3622.62, N = 7SE +/- 3515.49, N = 7SE +/- 1412.50, N = 5SE +/- 702.52, N = 5SE +/- 263.39, N = 4258224.35135885.31144112.86287345.28255823.48392397.6797758.1597670.64188856.06274263.37272077.94490393.91507823.13267834.17121293.26471697.13473377.17253395.11254430.04185454.541. (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 4.1.4

oneDNN

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.7Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPUXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P0.50931.01861.52792.03722.5465SE +/- 0.000937, N = 7SE +/- 0.002168, N = 7SE +/- 0.001727, N = 7SE +/- 0.000897, N = 7SE +/- 0.001009, N = 7SE +/- 0.003944, N = 15SE +/- 0.003698, N = 15SE +/- 0.002087, N = 7SE +/- 0.000614, N = 7SE +/- 0.002491, N = 7SE +/- 0.003117, N = 7SE +/- 0.000630, N = 7SE +/- 0.001014, N = 7SE +/- 0.004482, N = 71.4743301.6119302.2635000.6698030.6101190.5298380.4887210.6874951.1745500.4394040.4386930.5859130.5976981.420480MIN: 1.43MIN: 1.56MIN: 2.13MIN: 0.6MIN: 0.58MIN: 0.44MIN: 0.41MIN: 0.62MIN: 1.13MIN: 0.37MIN: 0.36MIN: 0.57MIN: 0.56MIN: 1.261. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread

asmFish

This is a test of asmFish, an advanced chess benchmark written in Assembly. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgNodes/second, More Is BetterasmFish 2018-07-231024 Hash Memory, 26 DepthEPYC 7713 2PEPYC 7713EPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P90M180M270M360M450MSE +/- 611665.63, N = 3SE +/- 809742.81, N = 3SE +/- 1045666.18, N = 3SE +/- 451407.56, N = 3SE +/- 348426.38, N = 3SE +/- 2388608.17, N = 9SE +/- 478355.71, N = 3SE +/- 654954.01, N = 3SE +/- 1526020.25, N = 3SE +/- 2828612.84, N = 3SE +/- 1169064.32, N = 3SE +/- 2695071.60, N = 3SE +/- 1520548.58, N = 3SE +/- 1101907.90, N = 3SE +/- 868554.02, N = 3SE +/- 1040134.87, N = 3SE +/- 3711493.29, N = 5SE +/- 835429.68, N = 3SE +/- 1373257.95, N = 3SE +/- 692156.92, N = 3246888854138377960159120297291595066156507344291760604879745787699987714481831324917587928031382336891986339704653918295896094858095368462801373466857212598823209533141163269037

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 Intel oneAPI. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.6Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPUEPYC 7713 2PEPYC 7713EPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P0.86231.72462.58693.44924.3115SE +/- 0.036406, N = 15SE +/- 0.019741, N = 9SE +/- 0.004502, N = 9SE +/- 0.026880, N = 9SE +/- 0.017156, N = 9SE +/- 0.017848, N = 9SE +/- 0.003420, N = 9SE +/- 0.002798, N = 9SE +/- 0.001612, N = 9SE +/- 0.000926, N = 9SE +/- 0.000988, N = 9SE +/- 0.001925, N = 9SE +/- 0.002404, N = 9SE +/- 0.018693, N = 15SE +/- 0.012562, N = 9SE +/- 0.001947, N = 9SE +/- 0.001619, N = 9SE +/- 0.000782, N = 9SE +/- 0.000646, N = 9SE +/- 0.001547, N = 93.7424703.2024103.1789103.8326603.2177103.7597801.5619901.6398301.0055951.1431801.0895900.9847340.9387072.0891802.9492000.7597540.7452651.1157401.1200800.9289171. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl -lpthread

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.6Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPUEPYC 7713 2PEPYC 7713EPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P0.50781.01561.52342.03122.539SE +/- 0.002779, N = 7SE +/- 0.000772, N = 7SE +/- 0.000743, N = 7SE +/- 0.003588, N = 7SE +/- 0.001090, N = 7SE +/- 0.003100, N = 7SE +/- 0.000989, N = 7SE +/- 0.001429, N = 7SE +/- 0.002078, N = 7SE +/- 0.002654, N = 7SE +/- 0.001657, N = 7SE +/- 0.004050, N = 7SE +/- 0.004281, N = 7SE +/- 0.004918, N = 12SE +/- 0.001361, N = 7SE +/- 0.001952, N = 7SE +/- 0.002336, N = 7SE +/- 0.001196, N = 7SE +/- 0.000621, N = 7SE +/- 0.009335, N = 150.6322100.9362880.8635930.6279690.8363590.5932351.4794701.5968502.2568600.6709700.6116000.5254580.4762410.6983921.1752600.4391750.4426350.5862750.5951161.5264201. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl -lpthread

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 7713 2PEPYC 7713EPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P4K8K12K16K20K8626.6716938.4316544.828372.9315435.547410.7318689.2120075.5010633.837676.337370.394070.113940.0813011.1918209.604329.904503.428828.508834.7110128.151. (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

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 7713 2PEPYC 7713EPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P130260390520650SE +/- 0.26, N = 3SE +/- 0.28, N = 3SE +/- 0.30, N = 3SE +/- 0.05, N = 3SE +/- 0.13, N = 3SE +/- 0.17, N = 3SE +/- 2.89, N = 3SE +/- 0.82, N = 3SE +/- 4.12, N = 3SE +/- 0.87, N = 3SE +/- 0.89, N = 3SE +/- 0.17, N = 3SE +/- 0.23, N = 3SE +/- 0.87, N = 3SE +/- 2.85, N = 3SE +/- 0.18, N = 3SE +/- 0.14, N = 3SE +/- 0.71, N = 3SE +/- 0.14, N = 3SE +/- 0.51, N = 3298.32602.44603.54297.43573.31265.94556.33588.06312.03254.85253.41125.39124.23383.39624.50134.33133.96268.65268.58296.321. (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

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.BEPYC 7713 2PEPYC 7713EPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P50K100K150K200K250KSE +/- 1364.07, N = 15SE +/- 564.25, N = 8SE +/- 677.41, N = 10SE +/- 1060.57, N = 9SE +/- 2164.09, N = 15SE +/- 1611.06, N = 15SE +/- 36.55, N = 6SE +/- 46.80, N = 6SE +/- 509.59, N = 8SE +/- 1433.38, N = 15SE +/- 2245.97, N = 15SE +/- 1703.57, N = 15SE +/- 2791.46, N = 15SE +/- 1204.13, N = 15SE +/- 208.44, N = 8SE +/- 3991.38, N = 15SE +/- 3716.81, N = 15SE +/- 2022.23, N = 15SE +/- 1837.39, N = 15SE +/- 114.69, N = 9134888.0690065.5788708.75136460.44135254.12163786.8849434.6948063.40111259.33162758.97168014.13219454.01238644.03159375.7483421.88222846.94214561.41167629.48164817.94119784.281. (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 4.1.4

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 2022.2.devModel: Person Vehicle Bike Detection FP16 - Device: CPUEPYC 7713 2PEPYC 7713EPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P510152025SE +/- 0.03, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.04, N = 3SE +/- 0.03, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.04, N = 311.9121.0319.5110.9617.049.9817.7016.229.228.327.815.324.967.8914.164.324.306.486.719.941. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv

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 5.18Build: allmodconfigEPYC 7713 2PEPYC 7713EPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P100200300400500SE +/- 0.51, N = 3SE +/- 0.64, N = 3SE +/- 0.62, N = 3SE +/- 0.39, N = 3SE +/- 0.45, N = 3SE +/- 0.69, N = 3SE +/- 0.49, N = 3SE +/- 0.63, N = 3SE +/- 0.29, N = 3SE +/- 0.43, N = 3SE +/- 0.49, N = 3SE +/- 0.47, N = 3SE +/- 0.08, N = 3SE +/- 0.60, N = 3SE +/- 0.39, N = 3SE +/- 0.36, N = 3SE +/- 0.39, N = 3SE +/- 0.42, N = 3SE +/- 0.52, N = 3SE +/- 0.43, N = 3184.69312.94267.50160.02263.29155.91409.15461.54250.89173.11158.32107.1498.28219.46390.39113.17109.24179.86185.81229.49

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: DLSC - Acceleration: CPUEPYC 7713 2PEPYC 7713EPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P612182430SE +/- 0.20, N = 15SE +/- 0.07, N = 3SE +/- 0.03, N = 3SE +/- 0.12, N = 3SE +/- 0.08, N = 3SE +/- 0.07, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.09, N = 15SE +/- 0.02, N = 3SE +/- 0.21, N = 15SE +/- 0.07, N = 3SE +/- 1.00, N = 15SE +/- 0.09, N = 3SE +/- 0.01, N = 3SE +/- 0.47, N = 15SE +/- 0.15, N = 3SE +/- 0.11, N = 10SE +/- 0.05, N = 3SE +/- 0.07, N = 1012.748.339.4713.769.4513.725.634.927.9814.3117.0717.6623.019.746.1517.6821.5313.6012.868.80

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 3.1EPYC 7713 2PEPYC 7713EPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P20406080100SE +/- 0.05, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.08, N = 3SE +/- 0.00, N = 3SE +/- 0.12, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.05, N = 3SE +/- 0.02, N = 3SE +/- 0.45, N = 3SE +/- 0.49, N = 3SE +/- 0.13, N = 3SE +/- 0.17, N = 3SE +/- 0.01, N = 3SE +/- 2.93, N = 10SE +/- 0.37, N = 3SE +/- 0.03, N = 3SE +/- 1.63, N = 12SE +/- 0.08, N = 337.2519.1319.1237.3219.7138.2420.6720.1839.9645.2244.4886.0287.1637.8619.6283.6158.1745.3042.8140.771. (CXX) g++ options: -O3 -ffast-math -ftree-vectorize -lmpi_cxx -lmpi

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 2022.1Implementation: MPI CPU - Input: water_GMX50_bareEPYC 7713 2PEPYC 7713EPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P510152025SE +/- 0.025, N = 3SE +/- 0.017, N = 3SE +/- 0.014, N = 3SE +/- 0.109, N = 3SE +/- 0.021, N = 3SE +/- 0.020, N = 3SE +/- 0.024, N = 3SE +/- 0.010, N = 3SE +/- 0.003, N = 3SE +/- 0.012, N = 3SE +/- 0.010, N = 3SE +/- 0.011, N = 3SE +/- 1.013, N = 12SE +/- 0.026, N = 3SE +/- 0.010, N = 3SE +/- 0.058, N = 3SE +/- 0.022, N = 3SE +/- 0.020, N = 3SE +/- 0.011, N = 3SE +/- 0.090, N = 58.3185.1645.77210.0727.16511.2164.9804.3888.65611.14712.95618.68619.8347.6014.35817.10418.38210.3459.6419.0211. (CXX) g++ options: -O3

GraphicsMagick

This is a test of GraphicsMagick with its OpenMP implementation that performs various imaging tests on a sample 6000x4000 pixel JPEG image. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.38Operation: SharpenEPYC 7713 2PEPYC 7713EPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P30060090012001500SE +/- 2.08, N = 3SE +/- 1.86, N = 3SE +/- 0.58, N = 3SE +/- 0.67, N = 3SE +/- 0.33, N = 3SE +/- 2.03, N = 3SE +/- 0.33, N = 3SE +/- 0.33, N = 3SE +/- 0.88, N = 3SE +/- 0.58, N = 3SE +/- 0.67, N = 3SE +/- 3.46, N = 3SE +/- 2.91, N = 3SE +/- 2.52, N = 3SE +/- 0.00, N = 3SE +/- 3.18, N = 3SE +/- 1.67, N = 3SE +/- 0.33, N = 3SE +/- 0.33, N = 3SE +/- 1.73, N = 376051158285859587534831757984399911831393643387110211147046976281. (CC) gcc options: -fopenmp -O2 -ljbig -lwebp -lwebpmux -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lxml2 -lz -lm -lpthread

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 7713 2PEPYC 7713EPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P900M1800M2700M3600M4500MSE +/- 563451.27, N = 3SE +/- 417323.62, N = 3SE +/- 808623.73, N = 3SE +/- 1653035.32, N = 3SE +/- 423657.23, N = 3SE +/- 3210600.38, N = 3SE +/- 806586.84, N = 3SE +/- 754992.35, N = 3SE +/- 2102078.13, N = 3SE +/- 1264541.59, N = 3SE +/- 3283111.96, N = 3SE +/- 3661935.20, N = 3SE +/- 9793366.81, N = 3SE +/- 3326024.77, N = 3SE +/- 910976.46, N = 3SE +/- 13428026.69, N = 3SE +/- 14635410.92, N = 3SE +/- 3446302.00, N = 3SE +/- 2222006.08, N = 3SE +/- 5959719.32, N = 3191757000010142540001014445000192989166710570506671998897333108113100010678063332067115333233343033323419963334358309667441476333319253626671023022333425871733342795393332355505667235338000020657410001. (CC) gcc options: -lparcsr_ls -lparcsr_mv -lseq_mv -lIJ_mv -lkrylov -lHYPRE_utilities -lm -fopenmp -lmpi

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 2022.2.devModel: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPUEPYC 7713 2PEPYC 7713EPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P40K80K120K160K200KSE +/- 1255.87, N = 3SE +/- 50.17, N = 3SE +/- 47.17, N = 3SE +/- 544.04, N = 3SE +/- 101.99, N = 3SE +/- 1215.82, N = 3SE +/- 972.77, N = 15SE +/- 527.93, N = 15SE +/- 2609.49, N = 12SE +/- 169.28, N = 3SE +/- 151.20, N = 3SE +/- 734.15, N = 3SE +/- 731.54, N = 3SE +/- 64.38, N = 3SE +/- 105.89, N = 3SE +/- 2309.74, N = 3SE +/- 1524.49, N = 7SE +/- 114.30, N = 3SE +/- 119.74, N = 3SE +/- 1442.94, N = 3101816.8751141.5755150.32106094.9857873.68108150.7556565.0148059.01108301.83149560.47159812.84166269.03173823.4479094.2541209.65175383.10171196.42133585.43132051.79118721.531. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv

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 7713 2PEPYC 7713EPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P50K100K150K200K250KSE +/- 430.76, N = 10SE +/- 233.80, N = 9SE +/- 238.68, N = 9SE +/- 444.87, N = 10SE +/- 157.87, N = 9SE +/- 980.49, N = 15SE +/- 45.67, N = 9SE +/- 255.08, N = 9SE +/- 470.20, N = 11SE +/- 764.03, N = 15SE +/- 1317.18, N = 15SE +/- 1834.92, N = 15SE +/- 2783.28, N = 15SE +/- 427.89, N = 10SE +/- 304.81, N = 9SE +/- 990.19, N = 12SE +/- 1222.97, N = 12SE +/- 1333.51, N = 15SE +/- 1359.91, N = 15SE +/- 171.50, N = 11100065.1257128.2957200.1698920.0360128.52123247.0857809.3555604.70116706.64120349.96121727.31197332.18202432.69102839.1956330.80233220.37232995.13128432.87125660.14118435.741. (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 4.1.4

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 129 Cells Per DirectionEPYC 7713 2PEPYC 7713EPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P1.34812.69624.04435.39246.7405SE +/- 0.02528928, N = 9SE +/- 0.02956314, N = 7SE +/- 0.03796824, N = 15SE +/- 0.04202120, N = 12SE +/- 0.02518485, N = 7SE +/- 0.03428839, N = 15SE +/- 0.02863178, N = 7SE +/- 0.03922970, N = 6SE +/- 0.02095749, N = 9SE +/- 0.02850743, N = 15SE +/- 0.01859828, N = 9SE +/- 0.01070461, N = 10SE +/- 0.01039810, N = 15SE +/- 0.02063230, N = 8SE +/- 0.02359108, N = 7SE +/- 0.01020043, N = 10SE +/- 0.01173139, N = 15SE +/- 0.01464622, N = 9SE +/- 0.01662956, N = 9SE +/- 0.01225371, N = 93.089436215.039292205.179966773.131475114.382258622.246857125.330262325.991757152.901793352.289035302.241371101.481720701.448108473.288719035.635620121.498298301.515555212.481463912.546472792.616581811. (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

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 2022.2.devModel: Age Gender Recognition Retail 0013 FP16 - Device: CPUEPYC 7713 2PEPYC 7713EPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P0.47480.94961.42441.89922.374SE +/- 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 +/- 0.00, 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 = 32.111.981.881.951.771.851.371.291.230.650.620.540.521.471.390.510.510.510.521.331. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv

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: FT.CEPYC 7713 2PEPYC 7713EPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P50K100K150K200K250KSE +/- 472.14, N = 8SE +/- 171.64, N = 6SE +/- 449.74, N = 6SE +/- 811.29, N = 8SE +/- 81.03, N = 6SE +/- 898.92, N = 15SE +/- 76.54, N = 6SE +/- 80.21, N = 6SE +/- 602.31, N = 7SE +/- 377.17, N = 8SE +/- 986.09, N = 10SE +/- 1534.56, N = 9SE +/- 2780.73, N = 15SE +/- 557.99, N = 8SE +/- 35.88, N = 6SE +/- 1508.85, N = 10SE +/- 1649.35, N = 12SE +/- 565.95, N = 8SE +/- 704.40, N = 8SE +/- 103.75, N = 7116524.9961089.3360945.14118231.7364733.33127733.4956704.8256879.4697993.30121799.77125326.19215057.58222687.11105557.9961146.13234088.25234367.13127498.51124561.1399537.681. (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 4.1.4

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 4.0Preset: MediumEPYC 7713 2PEPYC 7713EPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P130260390520650SE +/- 1.54, N = 7SE +/- 0.16, N = 7SE +/- 0.15, N = 7SE +/- 0.32, N = 7SE +/- 0.09, N = 7SE +/- 0.67, N = 7SE +/- 0.19, N = 6SE +/- 0.09, N = 6SE +/- 0.42, N = 7SE +/- 0.19, N = 8SE +/- 0.34, N = 8SE +/- 1.52, N = 8SE +/- 1.79, N = 8SE +/- 0.71, N = 8SE +/- 0.06, N = 7SE +/- 0.91, N = 8SE +/- 0.91, N = 8SE +/- 0.07, N = 8SE +/- 0.06, N = 8SE +/- 0.23, N = 7379.49233.06262.03450.11264.50452.17167.02148.60289.38422.02480.19571.61601.36321.91177.16548.85613.64388.57360.55320.081. (CXX) g++ options: -O3 -flto -pthread

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 7713 2PEPYC 7713EPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P200K400K600K800K1000KSE +/- 1355.40, N = 3SE +/- 369.10, N = 3SE +/- 367.42, N = 3SE +/- 6365.85, N = 4SE +/- 518.75, N = 3SE +/- 2720.84, N = 3SE +/- 281.22, N = 3SE +/- 596.11, N = 3SE +/- 1105.00, N = 3SE +/- 1109.48, N = 3SE +/- 903.59, N = 3SE +/- 1019.34, N = 3SE +/- 6383.59, N = 3SE +/- 2831.65, N = 3SE +/- 256.67, N = 3SE +/- 6929.10, N = 3SE +/- 3650.73, N = 3SE +/- 544.47, N = 3SE +/- 3953.49, N = 3SE +/- 691.15, N = 35256543585053864115823844037185473852424662162633647306589237000858714408908894166442768297526087627775513955457283975341. (CXX) g++ options: -lpthread -ldl -O2 -fPIC

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 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P2040608010048.3535.3440.0530.3574.8685.9744.5128.5225.1422.8835.1956.0620.9821.2030.3231.2141.02-lfoamToVTK -ldynamicMesh -lfileFormats-lfoamToVTK -ldynamicMesh -lfileFormats-lfoamToVTK -ldynamicMesh -lfileFormats-lfoamToVTK -ldynamicMesh -lfileFormats-lfiniteVolume -lmeshTools -lparallel -lregionModels-lfiniteVolume -lmeshTools -lparallel -lregionModels-lfiniteVolume -lmeshTools -lparallel -lregionModels-lfiniteVolume -lmeshTools -lparallel -lregionModels-lfiniteVolume -lmeshTools -lparallel -lregionModels-lfiniteVolume -lmeshTools -lparallel -lregionModels-lfiniteVolume -lmeshTools -lparallel -lregionModels-lfiniteVolume -lmeshTools -lparallel -lregionModels-lfiniteVolume -lmeshTools -lparallel -lregionModels-lfiniteVolume -lmeshTools -lparallel -lregionModels-lfiniteVolume -lmeshTools -lparallel -lregionModels-lfiniteVolume -lmeshTools -lparallel -lregionModels-lfoamToVTK -ldynamicMesh -lfileFormats1. (CXX) g++ options: -std=c++14 -m64 -O3 -ftemplate-depth-100 -fPIC -fuse-ld=bfd -Xlinker --add-needed --no-as-needed -llagrangian -lgenericPatchFields -lOpenFOAM -ldl -lm

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 22.1Input: Carbon NanotubeEPYC 7713 2PEPYC 7713EPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P20406080100SE +/- 0.23, N = 3SE +/- 0.41, N = 3SE +/- 0.11, N = 3SE +/- 0.06, N = 3SE +/- 0.54, N = 3SE +/- 0.21, N = 3SE +/- 0.70, N = 7SE +/- 0.13, N = 3SE +/- 0.38, N = 12SE +/- 0.35, N = 3SE +/- 0.35, N = 4SE +/- 0.19, N = 3SE +/- 0.04, N = 3SE +/- 0.05, N = 3SE +/- 0.74, N = 3SE +/- 0.21, N = 3SE +/- 0.02, N = 3SE +/- 0.26, N = 13SE +/- 0.18, N = 3SE +/- 0.27, N = 1544.2373.4369.8942.5159.8538.2077.7983.2848.8735.8332.5523.1521.0155.1779.5524.6523.5039.2240.2946.781. (CC) gcc options: -shared -fwrapv -O2 -lxc -lblas -lmpi

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: Orange Juice - Acceleration: CPUEPYC 7713 2PEPYC 7713EPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P714212835SE +/- 0.11, N = 3SE +/- 0.03, N = 3SE +/- 0.08, N = 3SE +/- 0.28, N = 15SE +/- 0.01, N = 3SE +/- 0.06, N = 3SE +/- 0.03, N = 3SE +/- 0.02, N = 3SE +/- 0.06, N = 3SE +/- 0.15, N = 15SE +/- 0.02, N = 3SE +/- 0.73, N = 15SE +/- 0.19, N = 3SE +/- 0.20, N = 3SE +/- 0.02, N = 3SE +/- 0.09, N = 3SE +/- 0.57, N = 15SE +/- 0.05, N = 3SE +/- 0.06, N = 3SE +/- 0.15, N = 518.4912.4913.9121.7613.4321.238.797.7912.6721.4923.6229.1330.7915.769.1925.8226.8518.6318.5014.23

Timed LLVM Compilation

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

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed LLVM Compilation 13.0Build System: NinjaEPYC 7713 2PEPYC 7713EPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P60120180240300SE +/- 0.26, N = 3SE +/- 0.30, N = 3SE +/- 0.71, N = 3SE +/- 0.33, N = 3SE +/- 0.70, N = 3SE +/- 0.31, N = 3SE +/- 1.02, N = 3SE +/- 0.62, N = 3SE +/- 0.33, N = 3SE +/- 0.11, N = 3SE +/- 0.14, N = 3SE +/- 0.18, N = 3SE +/- 0.21, N = 3SE +/- 0.26, N = 3SE +/- 0.36, N = 3SE +/- 0.21, N = 3SE +/- 0.07, N = 3SE +/- 0.53, N = 3SE +/- 0.56, N = 3SE +/- 0.57, N = 3121.48186.43167.05112.58159.22108.52239.58267.73159.49105.1997.6274.6571.33135.10219.9483.3481.68115.77117.76149.60

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 7713 2PEPYC 7713EPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P20K40K60K80K100KSE +/- 272.04, N = 8SE +/- 131.39, N = 6SE +/- 74.99, N = 6SE +/- 404.03, N = 15SE +/- 271.08, N = 8SE +/- 413.94, N = 8SE +/- 18.32, N = 6SE +/- 27.03, N = 6SE +/- 67.42, N = 8SE +/- 546.79, N = 15SE +/- 691.56, N = 15SE +/- 1179.69, N = 15SE +/- 875.77, N = 15SE +/- 752.96, N = 15SE +/- 184.99, N = 7SE +/- 964.25, N = 15SE +/- 735.83, N = 15SE +/- 342.99, N = 8SE +/- 289.00, N = 8SE +/- 87.17, N = 847508.3423979.7924379.6746814.8240140.3651069.4522812.4322162.9437782.1654251.0255458.3979107.0882256.8942579.3230040.2082493.4081468.9546439.6045631.3439249.471. (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 4.1.4

GraphicsMagick

This is a test of GraphicsMagick with its OpenMP implementation that performs various imaging tests on a sample 6000x4000 pixel JPEG image. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.38Operation: EnhancedEPYC 7713 2PEPYC 7713EPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P400800120016002000SE +/- 2.08, N = 3SE +/- 0.58, N = 3SE +/- 0.67, N = 3SE +/- 1.67, N = 3SE +/- 0.88, N = 3SE +/- 3.67, N = 3SE +/- 0.33, N = 3SE +/- 0.67, N = 3SE +/- 1.45, N = 3SE +/- 0.58, N = 3SE +/- 0.33, N = 3SE +/- 8.96, N = 3SE +/- 14.97, N = 3SE +/- 11.66, N = 4SE +/- 0.33, N = 3SE +/- 1.45, N = 3SE +/- 4.51, N = 3SE +/- 0.67, N = 3SE +/- 0.58, N = 3SE +/- 4.91, N = 31289934103614461039145661756099814291665192320801093703175617371239121610641. (CC) gcc options: -fopenmp -O2 -ljbig -lwebp -lwebpmux -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lxml2 -lz -lm -lpthread

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 15Scaling Factor: 100 - Clients: 500 - Mode: Read Only - Average LatencyEPYC 9654EPYC 9654 - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P0.10890.21780.32670.43560.5445SE +/- 0.000, N = 3SE +/- 0.000, N = 3SE +/- 0.001, N = 3SE +/- 0.001, N = 3SE +/- 0.001, N = 12SE +/- 0.002, N = 4SE +/- 0.001, N = 3SE +/- 0.002, N = 3SE +/- 0.003, N = 120.1600.1350.2560.4840.1540.1510.1910.1920.2661. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL 15Scaling Factor: 100 - Clients: 500 - Mode: Read OnlyEPYC 9654EPYC 9654 - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P800K1600K2400K3200K4000KSE +/- 5336.89, N = 3SE +/- 7182.94, N = 3SE +/- 8234.43, N = 3SE +/- 1604.60, N = 3SE +/- 28561.38, N = 12SE +/- 35856.09, N = 4SE +/- 9277.57, N = 3SE +/- 21803.70, N = 3SE +/- 21999.01, N = 123120414370039519502761032195325644233147902614770260102618821111. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL 15Scaling Factor: 100 - Clients: 250 - Mode: Read Only - Average LatencyEPYC 9654EPYC 9654 - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P0.05330.10660.15990.21320.2665SE +/- 0.001, N = 3SE +/- 0.000, N = 3SE +/- 0.000, N = 3SE +/- 0.001, N = 3SE +/- 0.001, N = 3SE +/- 0.001, N = 4SE +/- 0.000, N = 3SE +/- 0.000, N = 3SE +/- 0.003, N = 120.0800.0670.1280.2370.0740.0740.0950.0940.1341. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -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 2021.01.31Threads: 64 - Buffer Length: 256 - Filter Length: 57EPYC 7713 2PEPYC 7713EPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P1000M2000M3000M4000M5000MSE +/- 6615386.11, N = 3SE +/- 5460565.70, N = 3SE +/- 5026927.49, N = 3SE +/- 4504442.25, N = 3SE +/- 2403007.38, N = 3SE +/- 2138535.32, N = 3SE +/- 4740018.75, N = 3SE +/- 2271563.34, N = 3SE +/- 3329164.06, N = 3SE +/- 3507610.77, N = 3SE +/- 14090698.27, N = 3SE +/- 1985782.80, N = 3SE +/- 7438936.60, N = 3SE +/- 2909180.87, N = 3SE +/- 2066666.67, N = 3SE +/- 8247895.35, N = 3SE +/- 8029321.27, N = 3SE +/- 7785956.02, N = 3SE +/- 2017699.46, N = 3SE +/- 3499682.53, N = 3318470000025780333332810400000318700000028449333333338000000161166666713095000002986100000405450000045475333334564800000455186666736862000002024033333461416666746254000004612933333434973333329300333331. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

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.orgTPS, More Is BetterPostgreSQL 15Scaling Factor: 1 - Clients: 500 - Mode: Read OnlyEPYC 9654EPYC 9654 - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P800K1600K2400K3200K4000KSE +/- 3064.84, N = 3SE +/- 16283.20, N = 3SE +/- 15905.36, N = 10SE +/- 5827.48, N = 3SE +/- 20578.11, N = 3SE +/- 38847.19, N = 3SE +/- 6219.97, N = 3SE +/- 13108.55, N = 3SE +/- 30910.94, N = 123236019381813120110811086708343904534648652722794271787219936751. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL 15Scaling Factor: 1 - Clients: 500 - Mode: Read Only - Average LatencyEPYC 9654EPYC 9654 - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P0.10350.2070.31050.4140.5175SE +/- 0.000, N = 3SE +/- 0.001, N = 3SE +/- 0.002, N = 10SE +/- 0.002, N = 3SE +/- 0.001, N = 3SE +/- 0.001, N = 3SE +/- 0.000, N = 3SE +/- 0.001, N = 3SE +/- 0.004, N = 120.1540.1310.2490.4600.1450.1440.1830.1840.2521. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL 15Scaling Factor: 100 - Clients: 250 - Mode: Read OnlyEPYC 9654EPYC 9654 - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P800K1600K2400K3200K4000KSE +/- 21432.95, N = 3SE +/- 8254.16, N = 3SE +/- 3592.47, N = 3SE +/- 2659.26, N = 3SE +/- 34621.78, N = 3SE +/- 41178.99, N = 4SE +/- 12477.20, N = 3SE +/- 5489.82, N = 3SE +/- 43235.34, N = 123135626370146219567081057177336007034114342640654264837518714251. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL 15Scaling Factor: 1 - Clients: 250 - Mode: Read OnlyEPYC 9654EPYC 9654 - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P800K1600K2400K3200K4000KSE +/- 16481.46, N = 3SE +/- 17338.24, N = 3SE +/- 9474.73, N = 3SE +/- 2870.95, N = 3SE +/- 23179.98, N = 3SE +/- 38023.52, N = 3SE +/- 15618.98, N = 3SE +/- 14108.92, N = 3SE +/- 22335.44, N = 33286136387247320565121106044344434034603452754409276016720759261. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

Intel Open Image Denoise

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

OpenBenchmarking.orgImages / Sec, More Is BetterIntel Open Image Denoise 1.4.0Run: RT.hdr_alb_nrm.3840x2160EPYC 7713 2PEPYC 7713EPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P0.87981.75962.63943.51924.399SE +/- 0.01, N = 4SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 4SE +/- 0.00, N = 3SE +/- 0.01, N = 4SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 4SE +/- 0.00, N = 5SE +/- 0.00, N = 5SE +/- 0.02, N = 5SE +/- 0.02, N = 5SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 5SE +/- 0.01, N = 5SE +/- 0.00, N = 4SE +/- 0.00, N = 4SE +/- 0.01, N = 52.251.411.652.561.651.941.741.592.713.043.333.573.701.881.123.843.912.732.672.89

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 15Scaling Factor: 1 - Clients: 250 - Mode: Read Only - Average LatencyEPYC 9654EPYC 9654 - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P0.05090.10180.15270.20360.2545SE +/- 0.001, N = 3SE +/- 0.000, N = 3SE +/- 0.001, N = 3SE +/- 0.001, N = 3SE +/- 0.000, N = 3SE +/- 0.001, N = 3SE +/- 0.001, N = 3SE +/- 0.000, N = 3SE +/- 0.001, N = 30.0760.0650.1220.2260.0730.0720.0910.0910.1201. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

Intel Open Image Denoise

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

OpenBenchmarking.orgImages / Sec, More Is BetterIntel Open Image Denoise 1.4.0Run: RT.ldr_alb_nrm.3840x2160EPYC 7713 2PEPYC 7713EPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P0.87531.75062.62593.50124.3765SE +/- 0.01, N = 4SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 4SE +/- 0.00, N = 3SE +/- 0.01, N = 4SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 4SE +/- 0.00, N = 5SE +/- 0.00, N = 5SE +/- 0.02, N = 5SE +/- 0.01, N = 5SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 5SE +/- 0.01, N = 5SE +/- 0.00, N = 4SE +/- 0.00, N = 4SE +/- 0.00, N = 52.271.411.652.571.661.961.741.602.723.053.333.573.691.891.123.823.892.732.672.89

WebP2 Image Encode

This is a test of Google's libwebp2 library with the WebP2 image encode utility and using a sample 6000x4000 pixel JPEG image as the input, similar to the WebP/libwebp test profile. WebP2 is currently experimental and under heavy development as ultimately the successor to WebP. WebP2 supports 10-bit HDR, more efficienct lossy compression, improved lossless compression, animation support, and full multi-threading support compared to WebP. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMP/s, More Is BetterWebP2 Image Encode 20220823Encode Settings: Quality 95, Compression Effort 7EPYC 7713 2PEPYC 7713EPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P0.10350.2070.31050.4140.5175SE +/- 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 = 4SE +/- 0.00, N = 3SE +/- 0.00, N = 30.340.240.240.350.260.360.150.140.260.410.450.460.450.310.180.460.460.360.360.271. (CXX) g++ options: -msse4.2 -fno-rtti -O3 -ldl

Intel Open Image Denoise

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

OpenBenchmarking.orgImages / Sec, More Is BetterIntel Open Image Denoise 1.4.0Run: RTLightmap.hdr.4096x4096EPYC 7713 2PEPYC 7713EPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P0.4140.8281.2421.6562.07SE +/- 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 +/- 0.01, N = 3SE +/- 0.00, 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 = 31.110.700.811.260.820.950.830.761.301.441.581.691.770.940.561.811.841.291.261.38

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 7713 2PEPYC 7713EPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P13K26K39K52K65KSE +/- 136.51, N = 3SE +/- 66.62, N = 3SE +/- 36.15, N = 3SE +/- 178.54, N = 3SE +/- 83.18, N = 3SE +/- 106.16, N = 3SE +/- 20.86, N = 5SE +/- 11.73, N = 5SE +/- 51.78, N = 4SE +/- 142.06, N = 4SE +/- 141.39, N = 4SE +/- 186.02, N = 4SE +/- 227.17, N = 4SE +/- 42.26, N = 4SE +/- 71.44, N = 5SE +/- 124.43, N = 4SE +/- 99.91, N = 4SE +/- 122.69, N = 4SE +/- 124.44, N = 4SE +/- 35.30, N = 437996.4919643.9219943.0938255.5122729.5943886.0018563.4818713.2735687.9029508.5930521.1258017.0759160.9030531.6119112.5659398.7960173.8730428.0930166.9234993.471. (CXX) g++ options: -O3 -fopenmp -lm -lmpi_cxx -lmpi

Graph500

This is a benchmark of the reference implementation of Graph500, an HPC benchmark focused on data intensive loads and commonly tested on supercomputers for complex data problems. Graph500 primarily stresses the communication subsystem of the hardware under test. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgsssp max_TEPS, More Is BetterGraph500 3.0Scale: 26EPYC 7713 2PEPYC 7713EPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P200M400M600M800M1000M4510230002971590003410420004745520003669230003753050002731510002633810003403680005277510005229330007378890008381590003292870002681600006318190006707210004440310004415220003704010001. (CC) gcc options: -fcommon -O3 -lpthread -lm -lmpi

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 2022.2.devModel: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPUEPYC 7713 2PEPYC 7713EPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P0.24530.49060.73590.98121.2265SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 15SE +/- 0.01, N = 15SE +/- 0.02, N = 12SE +/- 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 = 7SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.02, N = 31.091.040.981.010.900.960.630.600.570.450.430.360.360.790.770.350.350.360.370.591. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv

POV-Ray

This is a test of POV-Ray, the Persistence of Vision Raytracer. POV-Ray is used to create 3D graphics using ray-tracing. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterPOV-Ray 3.7.0.7Trace TimeEPYC 7713 2PEPYC 7713EPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P48121620SE +/- 0.035, N = 5SE +/- 0.036, N = 4SE +/- 0.060, N = 4SE +/- 0.039, N = 5SE +/- 0.022, N = 4SE +/- 0.043, N = 5SE +/- 0.090, N = 3SE +/- 0.034, N = 3SE +/- 0.104, N = 4SE +/- 0.034, N = 5SE +/- 0.032, N = 5SE +/- 0.041, N = 15SE +/- 0.042, N = 15SE +/- 0.060, N = 5SE +/- 0.014, N = 4SE +/- 0.035, N = 6SE +/- 0.024, N = 6SE +/- 0.025, N = 5SE +/- 0.037, N = 5SE +/- 0.048, N = 47.68910.5069.6957.2989.6677.18315.84117.4349.9307.1786.5786.0355.6738.23313.3695.8515.7337.1457.4459.5441. (CXX) g++ options: -pipe -O3 -ffast-math -march=native -R/usr/lib -lSDL -lXpm -lSM -lICE -lX11 -ltiff -ljpeg -lpng -lz -lrt -lm -lboost_thread -lboost_system

PJSIP

PJSIP is a free and open source multimedia communication library written in C language implementing standard based protocols such as SIP, SDP, RTP, STUN, TURN, and ICE. It combines signaling protocol (SIP) with rich multimedia framework and NAT traversal functionality into high level API that is portable and suitable for almost any type of systems ranging from desktops, embedded systems, to mobile handsets. This test profile is making use of pjsip-perf with both the client/server on teh system. More details on the PJSIP benchmark at https://www.pjsip.org/high-performance-sip.htm Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgResponses Per Second, More Is BetterPJSIP 2.11Method: OPTIONS, StatelessEPYC 7713 2PEPYC 7713EPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P20K40K60K80K100KSE +/- 821.92, N = 15SE +/- 377.55, N = 3SE +/- 317.58, N = 3SE +/- 734.76, N = 15SE +/- 445.63, N = 3SE +/- 1274.54, N = 15SE +/- 359.80, N = 9SE +/- 449.23, N = 3SE +/- 304.29, N = 15SE +/- 278.58, N = 3SE +/- 260.59, N = 3SE +/- 299.00, N = 3SE +/- 871.18, N = 5SE +/- 368.57, N = 15SE +/- 142.06, N = 3SE +/- 839.32, N = 15SE +/- 758.24, N = 15SE +/- 685.00, N = 3SE +/- 306.04, N = 3SE +/- 321.08, N = 368314743897233366415712086712843449446054380787898877288674983007294454283083661847458983489733430531. (CC) gcc options: -lavformat -lavcodec -lswscale -lavutil -lstdc++ -lssl -lcrypto -luuid -lm -lrt -lpthread -lasound -O2

Graph500

This is a benchmark of the reference implementation of Graph500, an HPC benchmark focused on data intensive loads and commonly tested on supercomputers for complex data problems. Graph500 primarily stresses the communication subsystem of the hardware under test. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgsssp median_TEPS, More Is BetterGraph500 3.0Scale: 26EPYC 7713 2PEPYC 7713EPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P130M260M390M520M650M3362480002336760002658680003568570002886580002989870002044730001973860002693030004176480004127410005398620006009060002681360002036440004549260004881300003549050003516070002844440001. (CC) gcc options: -fcommon -O3 -lpthread -lm -lmpi

WebP2 Image Encode

This is a test of Google's libwebp2 library with the WebP2 image encode utility and using a sample 6000x4000 pixel JPEG image as the input, similar to the WebP/libwebp test profile. WebP2 is currently experimental and under heavy development as ultimately the successor to WebP. WebP2 supports 10-bit HDR, more efficienct lossy compression, improved lossless compression, animation support, and full multi-threading support compared to WebP. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMP/s, More Is BetterWebP2 Image Encode 20220823Encode Settings: Quality 75, Compression Effort 7EPYC 7713 2PEPYC 7713EPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P0.19130.38260.57390.76520.9565SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 15SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 4SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, 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 = 3SE +/- 0.00, N = 13SE +/- 0.00, N = 30.630.480.480.640.520.660.320.280.510.780.830.830.830.590.370.850.840.720.720.531. (CXX) g++ options: -msse4.2 -fno-rtti -O3 -ldl

Neural Magic DeepSparse

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.1Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-StreamEPYC 9654EPYC 9654 - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P1632486480SE +/- 0.31, N = 3SE +/- 0.03, N = 3SE +/- 0.14, N = 3SE +/- 0.03, N = 3SE +/- 0.15, N = 3SE +/- 0.05, N = 3SE +/- 0.02, N = 3SE +/- 0.06, N = 3SE +/- 0.18, N = 342.6949.1047.4324.2670.0573.5136.9835.6647.47

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 7713 2PEPYC 7713EPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P80016002400320040002079.62314.22203.91999.12053.31866.53453.23956.72176.31550.01391.01534.01355.81696.83144.71341.81309.81441.51456.12190.61. (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

Neural Magic DeepSparse

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.1Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-StreamEPYC 9654EPYC 9654 - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P1632486480SE +/- 0.36, N = 3SE +/- 0.04, N = 3SE +/- 0.01, N = 3SE +/- 0.04, N = 3SE +/- 0.47, N = 3SE +/- 0.26, N = 3SE +/- 0.01, N = 3SE +/- 0.04, N = 3SE +/- 0.16, N = 342.5248.9847.5624.2269.6273.1236.9635.6947.56

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 18.8Time To CompileEPYC 7713 2PEPYC 7713EPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P60120180240300SE +/- 0.26, N = 3SE +/- 0.27, N = 3SE +/- 0.12, N = 3SE +/- 0.11, N = 3SE +/- 0.42, N = 3SE +/- 0.22, N = 3SE +/- 0.32, N = 3SE +/- 0.15, N = 3SE +/- 0.78, N = 3SE +/- 0.32, N = 3SE +/- 0.18, N = 3SE +/- 0.16, N = 3SE +/- 0.37, N = 3SE +/- 0.27, N = 3SE +/- 0.13, N = 3SE +/- 0.02, N = 3SE +/- 0.11, N = 3SE +/- 0.03, N = 3SE +/- 0.32, N = 3SE +/- 0.54, N = 3141.32203.23186.25135.21177.63130.04257.12279.48178.62123.43117.0698.5195.41152.42229.17100.2699.65132.32133.20173.99

Graph500

This is a benchmark of the reference implementation of Graph500, an HPC benchmark focused on data intensive loads and commonly tested on supercomputers for complex data problems. Graph500 primarily stresses the communication subsystem of the hardware under test. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgbfs max_TEPS, More Is BetterGraph500 3.0Scale: 26EPYC 7713 2PEPYC 7713EPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P300M600M900M1200M1500M72849900054631400068680200072568900073247100061117200071713200068002600083869300090661300088172900014375700001594850000597565000550370000119287000012975300008170750008222650008772920001. (CC) gcc options: -fcommon -O3 -lpthread -lm -lmpi

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 2.1Video Input: Bosphorus 4K - Video Preset: Very FastEPYC 7713 2PEPYC 7713EPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P20406080100SE +/- 0.42, N = 15SE +/- 0.10, N = 4SE +/- 0.08, N = 4SE +/- 0.41, N = 15SE +/- 0.06, N = 4SE +/- 0.61, N = 5SE +/- 0.03, N = 3SE +/- 0.04, N = 3SE +/- 0.06, N = 4SE +/- 0.51, N = 6SE +/- 0.53, N = 15SE +/- 0.55, N = 5SE +/- 0.30, N = 5SE +/- 0.08, N = 4SE +/- 0.10, N = 4SE +/- 0.40, N = 6SE +/- 0.31, N = 6SE +/- 0.12, N = 5SE +/- 0.20, N = 5SE +/- 0.09, N = 455.7737.0539.0856.9841.7555.0827.5529.3640.1076.6777.0571.5771.5750.0137.4673.3774.7062.1362.3339.821. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt

Graph500

This is a benchmark of the reference implementation of Graph500, an HPC benchmark focused on data intensive loads and commonly tested on supercomputers for complex data problems. Graph500 primarily stresses the communication subsystem of the hardware under test. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgbfs median_TEPS, More Is BetterGraph500 3.0Scale: 26EPYC 7713 2PEPYC 7713EPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P300M600M900M1200M1500M71301600053172500067655500069695500071637600059151300070370000064676400080655100088731400086336800013425400001479590000576137000538025000111518000012385400007973940007998690008440300001. (CC) gcc options: -fcommon -O3 -lpthread -lm -lmpi

Neural Magic DeepSparse

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.1Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Synchronous Single-StreamEPYC 9654EPYC 9654 - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P612182430SE +/- 0.0277, N = 3SE +/- 0.0122, N = 3SE +/- 0.2644, N = 6SE +/- 0.0482, N = 3SE +/- 0.0509, N = 3SE +/- 0.1144, N = 3SE +/- 0.0141, N = 3SE +/- 0.0441, N = 3SE +/- 0.0748, N = 39.83289.737526.652825.302510.920910.990310.706110.783312.9658

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.1Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Synchronous Single-StreamEPYC 9654EPYC 9654 - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P20406080100SE +/- 0.29, N = 3SE +/- 0.13, N = 3SE +/- 0.36, N = 6SE +/- 0.08, N = 3SE +/- 0.43, N = 3SE +/- 0.94, N = 3SE +/- 0.12, N = 3SE +/- 0.38, N = 3SE +/- 0.44, N = 3101.65102.6537.5139.5191.5090.9493.3492.6877.08

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 5.18Build: defconfigEPYC 7713 2PEPYC 7713EPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P1122334455SE +/- 0.25, N = 7SE +/- 0.47, N = 3SE +/- 0.41, N = 4SE +/- 0.23, N = 7SE +/- 0.36, N = 4SE +/- 0.22, N = 7SE +/- 0.42, N = 3SE +/- 0.41, N = 3SE +/- 0.42, N = 3SE +/- 0.26, N = 5SE +/- 0.23, N = 5SE +/- 0.16, N = 9SE +/- 0.15, N = 9SE +/- 0.32, N = 4SE +/- 0.42, N = 3SE +/- 0.17, N = 7SE +/- 0.18, N = 7SE +/- 0.24, N = 5SE +/- 0.32, N = 3SE +/- 0.42, N = 326.1235.8632.6124.6731.9224.1543.3846.6730.6323.6122.5119.0018.2327.6940.4219.1418.7923.8824.7329.95

Timed MPlayer Compilation

This test times how long it takes to build the MPlayer open-source media player program. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed MPlayer Compilation 1.5Time To CompileEPYC 7713 2PEPYC 7713EPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P48121620SE +/- 0.044, N = 5SE +/- 0.018, N = 4SE +/- 0.034, N = 4SE +/- 0.058, N = 5SE +/- 0.056, N = 4SE +/- 0.025, N = 5SE +/- 0.060, N = 3SE +/- 0.064, N = 3SE +/- 0.047, N = 4SE +/- 0.006, N = 5SE +/- 0.016, N = 5SE +/- 0.029, N = 6SE +/- 0.018, N = 6SE +/- 0.046, N = 5SE +/- 0.037, N = 4SE +/- 0.024, N = 6SE +/- 0.030, N = 6SE +/- 0.022, N = 5SE +/- 0.014, N = 5SE +/- 0.021, N = 410.39613.62312.59410.09712.2049.93916.64518.01211.9108.7658.4147.6977.49310.38414.4197.7957.6768.9479.16211.835

Neural Magic DeepSparse

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.1Model: CV Detection,YOLOv5s COCO - Scenario: Synchronous Single-StreamEPYC 9654EPYC 9654 - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P3691215SE +/- 0.0029, N = 3SE +/- 0.0082, N = 3SE +/- 0.0139, N = 3SE +/- 0.0238, N = 3SE +/- 0.0045, N = 3SE +/- 0.0039, N = 3SE +/- 0.0035, N = 3SE +/- 0.0022, N = 3SE +/- 0.0553, N = 35.19605.006211.813311.74045.31345.26595.26085.27908.3483

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.1Model: CV Detection,YOLOv5s COCO - Scenario: Synchronous Single-StreamEPYC 9654EPYC 9654 - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P4080120160200SE +/- 0.11, N = 3SE +/- 0.33, N = 3SE +/- 0.10, N = 3SE +/- 0.17, N = 3SE +/- 0.16, N = 3SE +/- 0.14, N = 3SE +/- 0.13, N = 3SE +/- 0.08, N = 3SE +/- 0.79, N = 3192.31199.5884.6085.14188.04189.73189.93189.26119.63

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/. 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 2022.10.13Model: Cell Phone Drop TestEPYC 9654EPYC 9654 - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P918273645SE +/- 0.20, N = 3SE +/- 0.09, N = 3SE +/- 0.03, N = 3SE +/- 0.16, N = 3SE +/- 0.04, N = 3SE +/- 0.10, N = 3SE +/- 0.09, N = 3SE +/- 0.01, N = 3SE +/- 0.09, N = 323.0920.4027.6938.9317.4816.6422.7823.1333.27

Neural Magic DeepSparse

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.1Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-StreamEPYC 9654EPYC 9654 - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P918273645SE +/- 0.06, N = 3SE +/- 0.08, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.07, N = 3SE +/- 0.07, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.08, N = 335.5737.2516.0216.3726.1126.3926.5826.4419.62

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.1Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-StreamEPYC 9654EPYC 9654 - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P1428425670SE +/- 0.05, N = 3SE +/- 0.05, N = 3SE +/- 0.08, N = 3SE +/- 0.06, N = 3SE +/- 0.10, N = 3SE +/- 0.10, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.21, N = 328.1126.8462.4361.0738.2937.8837.6237.8250.96

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.1Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-StreamEPYC 9654EPYC 9654 - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P918273645SE +/- 0.15, N = 3SE +/- 0.07, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.08, N = 3SE +/- 0.08, N = 3SE +/- 0.07, N = 3SE +/- 0.09, N = 335.6637.1516.0116.3526.1426.2826.4926.4419.59

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.1Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-StreamEPYC 9654EPYC 9654 - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P1428425670SE +/- 0.11, N = 3SE +/- 0.05, N = 3SE +/- 0.09, N = 3SE +/- 0.07, N = 3SE +/- 0.03, N = 3SE +/- 0.11, N = 3SE +/- 0.11, N = 3SE +/- 0.10, N = 3SE +/- 0.25, N = 328.0426.9162.4461.1638.2538.0437.7437.8151.05

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/. 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 2022.10.13Model: INIVOL and Fluid Structure Interaction Drop ContainerEPYC 9654EPYC 9654 - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P4080120160200SE +/- 0.49, N = 3SE +/- 0.13, N = 3SE +/- 0.27, N = 3SE +/- 0.61, N = 3SE +/- 0.15, N = 3SE +/- 0.35, N = 3SE +/- 0.30, N = 3SE +/- 0.15, N = 3SE +/- 0.26, N = 3103.5990.85138.72198.1287.7888.54117.81117.49147.10

Neural Magic DeepSparse

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.1Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-StreamEPYC 9654EPYC 9654 - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P4080120160200SE +/- 0.35, N = 3SE +/- 0.52, N = 3SE +/- 0.14, N = 3SE +/- 0.12, N = 3SE +/- 0.29, N = 3SE +/- 0.60, N = 3SE +/- 0.28, N = 3SE +/- 0.47, N = 3SE +/- 0.15, N = 3189.88196.2092.6095.40167.07168.25172.26172.18100.39

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.1Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-StreamEPYC 9654EPYC 9654 - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P3691215SE +/- 0.0098, N = 3SE +/- 0.0133, N = 3SE +/- 0.0170, N = 3SE +/- 0.0135, N = 3SE +/- 0.0103, N = 3SE +/- 0.0211, N = 3SE +/- 0.0095, N = 3SE +/- 0.0160, N = 3SE +/- 0.0147, N = 35.26315.093310.786110.47615.97825.93695.79945.80209.9536

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.1Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Asynchronous Multi-StreamEPYC 9654EPYC 9654 - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P4080120160200SE +/- 0.10, N = 3SE +/- 0.15, N = 3SE +/- 0.35, N = 3SE +/- 0.27, N = 3SE +/- 0.05, N = 3SE +/- 0.06, N = 3SE +/- 0.09, N = 3SE +/- 0.08, N = 3SE +/- 1.18, N = 3119.41111.75171.91161.37101.5191.9489.1397.09183.88

Timed LLVM Compilation

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

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed LLVM Compilation 13.0Build System: Unix MakefilesEPYC 7713 2PEPYC 7713EPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P70140210280350SE +/- 0.08, N = 3SE +/- 0.65, N = 3SE +/- 1.42, N = 3SE +/- 0.30, N = 3SE +/- 0.91, N = 3SE +/- 0.32, N = 3SE +/- 1.62, N = 3SE +/- 3.72, N = 3SE +/- 1.50, N = 3SE +/- 0.19, N = 3SE +/- 1.36, N = 3SE +/- 0.11, N = 3SE +/- 0.24, N = 3SE +/- 1.43, N = 3SE +/- 2.85, N = 4SE +/- 0.41, N = 3SE +/- 0.46, N = 3SE +/- 0.82, N = 3SE +/- 0.36, N = 3SE +/- 0.98, N = 3212.67258.75244.61210.12232.08201.37295.90324.08223.51171.12167.35158.69157.88199.54274.03159.74159.93178.75180.48222.62

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 2022.2.devModel: Face Detection FP16 - Device: CPUEPYC 7713 2PEPYC 7713EPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P20406080100SE +/- 0.07, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.05, N = 3SE +/- 0.01, N = 3SE +/- 0.06, N = 3SE +/- 0.03, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.04, N = 3SE +/- 0.25, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.09, N = 3SE +/- 0.07, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.14, N = 315.808.979.7416.0110.3617.4112.0510.8221.8450.0653.51102.38109.7811.106.6782.0183.2642.8741.6323.931. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.2.devModel: Vehicle Detection FP16 - Device: CPUEPYC 7713 2PEPYC 7713EPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P2K4K6K8K10KSE +/- 1.87, N = 3SE +/- 1.20, N = 3SE +/- 1.50, N = 3SE +/- 1.76, N = 3SE +/- 0.12, N = 3SE +/- 0.77, N = 3SE +/- 0.30, N = 3SE +/- 0.24, N = 3SE +/- 0.33, N = 3SE +/- 10.61, N = 3SE +/- 5.11, N = 3SE +/- 1.33, N = 3SE +/- 7.95, N = 3SE +/- 0.56, N = 3SE +/- 0.44, N = 3SE +/- 1.39, N = 3SE +/- 4.40, N = 3SE +/- 13.95, N = 3SE +/- 3.40, N = 3SE +/- 2.48, N = 31904.67945.341060.632173.491204.492336.77551.20522.871027.013426.693414.627435.728084.611497.62776.796063.846310.012880.482847.391112.381. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv

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 7.32.6VGR Performance MetricEPYC 7713 2PEPYC 7713EPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P1.2M2.4M3.6M4.8M6M3244103708943744533296259377756429929453844086427113123990317945757937505820929874385462318400666741367841247960119637522506311. (CXX) g++ options: -std=c++11 -pipe -fvisibility=hidden -fno-strict-aliasing -fno-common -fexceptions -ftemplate-depth-128 -m64 -ggdb3 -O3 -fipa-pta -fstrength-reduce -finline-functions -flto -pedantic -ldl -lm

VGR Performance Metric

Xeon Platinum 8380: The test quit with a non-zero exit status. E: ERROR: Could not find the BRL-CAD raytracer

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 2022.2.devModel: Weld Porosity Detection FP16 - Device: CPUEPYC 7713 2PEPYC 7713EPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P2K4K6K8K10KSE +/- 4.19, N = 3SE +/- 0.66, N = 3SE +/- 0.07, N = 3SE +/- 2.03, N = 3SE +/- 0.31, N = 3SE +/- 0.36, N = 3SE +/- 1.45, N = 3SE +/- 1.88, N = 3SE +/- 1.08, N = 3SE +/- 0.56, N = 3SE +/- 2.77, N = 3SE +/- 5.49, N = 3SE +/- 7.19, N = 3SE +/- 5.10, N = 3SE +/- 0.17, N = 3SE +/- 4.40, N = 3SE +/- 0.65, N = 3SE +/- 1.00, N = 3SE +/- 2.02, N = 3SE +/- 2.45, N = 31909.811029.061126.902136.931195.392407.711234.661118.622186.185004.255329.579979.6610858.901488.56770.458090.588198.284279.784165.022408.311. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv

oneDNN

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.7Harness: Convolution Batch Shapes Auto - Data Type: bf16bf16bf16 - Engine: CPUXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P1.05952.1193.17854.2385.2975SE +/- 0.004466, N = 7SE +/- 0.011150, N = 7SE +/- 0.001660, N = 7SE +/- 0.001543, N = 7SE +/- 0.001518, N = 7SE +/- 0.001212, N = 7SE +/- 0.003312, N = 7SE +/- 0.002017, N = 7SE +/- 0.002384, N = 15SE +/- 0.000790, N = 7SE +/- 0.001053, N = 7SE +/- 0.003087, N = 74.1012104.7088602.3874300.3944560.3751840.4415670.3865610.3599650.3529900.3971860.4005312.127880MIN: 3.98MIN: 4.29MIN: 2.21MIN: 2.031. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread

Harness: Convolution Batch Shapes Auto - Data Type: bf16bf16bf16 - Engine: CPU

EPYC 75F3 2P: The test run did not produce a result.

EPYC 75F3: 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.orgFPS, More Is BetterOpenVINO 2022.2.devModel: Weld Porosity Detection FP16-INT8 - Device: CPUEPYC 7713 2PEPYC 7713EPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P5K10K15K20K25KSE +/- 1.67, N = 3SE +/- 1.31, N = 3SE +/- 0.60, N = 3SE +/- 2.09, N = 3SE +/- 1.99, N = 3SE +/- 1.68, N = 3SE +/- 6.16, N = 3SE +/- 0.47, N = 3SE +/- 2.01, N = 3SE +/- 2.62, N = 3SE +/- 2.97, N = 3SE +/- 46.02, N = 3SE +/- 17.72, N = 3SE +/- 0.84, N = 3SE +/- 0.09, N = 3SE +/- 13.90, N = 3SE +/- 13.29, N = 3SE +/- 2.84, N = 3SE +/- 3.17, N = 3SE +/- 22.44, N = 35276.792458.722756.765931.552664.495735.054465.684023.358569.859842.9310601.8319812.0921859.023788.711811.3416203.4116421.678512.588228.709597.931. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv

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 7713 2PEPYC 7713EPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P20K40K60K80K100KSE +/- 370.23, N = 3SE +/- 64.10, N = 3SE +/- 137.18, N = 3SE +/- 153.43, N = 3SE +/- 0.00, N = 3SE +/- 307.17, N = 3SE +/- 19.57, N = 3SE +/- 30.05, N = 3SE +/- 61.83, N = 3SE +/- 383.40, N = 3SE +/- 223.70, N = 3SE +/- 0.00, N = 3SE +/- 721.42, N = 3SE +/- 431.65, N = 3SE +/- 131.90, N = 3SE +/- 509.24, N = 3SE +/- 307.17, N = 3SE +/- 270.04, N = 3SE +/- 158.23, N = 3SE +/- 37.10, N = 339243.6020056.1022333.2044039.5032294.8062354.408766.097391.6714994.5042366.7046081.4083966.6088708.8039616.3020316.2060853.9062047.3031335.5031647.3017075.801. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp

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 2022.2.devModel: Face Detection FP16-INT8 - Device: CPUEPYC 7713 2PEPYC 7713EPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P50100150200250SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.03, N = 3SE +/- 0.02, N = 3SE +/- 0.05, N = 3SE +/- 0.08, N = 3SE +/- 0.05, N = 3SE +/- 0.04, N = 3SE +/- 0.07, N = 3SE +/- 0.10, N = 3SE +/- 0.12, N = 3SE +/- 0.08, N = 3SE +/- 0.06, N = 3SE +/- 0.01, N = 3SE +/- 0.15, N = 3SE +/- 0.04, N = 3SE +/- 0.09, N = 3SE +/- 0.07, N = 3SE +/- 0.22, N = 350.2024.5827.6757.3827.0454.9642.6938.4873.3096.87103.49194.03212.4337.0118.35156.27158.2983.2780.6282.001. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.2.devModel: Machine Translation EN To DE FP16 - Device: CPUEPYC 7713 2PEPYC 7713EPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P2004006008001000SE +/- 1.23, N = 3SE +/- 0.18, N = 3SE +/- 0.27, N = 3SE +/- 1.09, N = 3SE +/- 0.06, N = 3SE +/- 0.69, N = 3SE +/- 0.14, N = 3SE +/- 0.24, N = 3SE +/- 0.97, N = 3SE +/- 0.51, N = 3SE +/- 0.50, N = 3SE +/- 0.69, N = 3SE +/- 1.17, N = 3SE +/- 0.39, N = 3SE +/- 0.19, N = 3SE +/- 0.64, N = 3SE +/- 1.35, N = 3SE +/- 0.27, N = 3SE +/- 0.82, N = 3SE +/- 1.24, N = 3223.15116.91131.27254.03140.19275.03140.24123.56205.84547.98590.08973.451037.28174.0689.82792.53808.16470.91449.76230.221. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv

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 7713 2PEPYC 7713EPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P20K40K60K80K100KSE +/- 133.20, N = 3SE +/- 183.61, N = 3SE +/- 85.47, N = 3SE +/- 160.07, N = 3SE +/- 364.13, N = 3SE +/- 610.89, N = 3SE +/- 0.00, N = 3SE +/- 40.72, N = 3SE +/- 82.76, N = 3SE +/- 626.96, N = 3SE +/- 277.50, N = 3SE +/- 460.77, N = 3SE +/- 1025.23, N = 3SE +/- 526.29, N = 3SE +/- 316.90, N = 3SE +/- 696.55, N = 3SE +/- 438.43, N = 3SE +/- 219.20, N = 3SE +/- 0.00, N = 3SE +/- 84.38, N = 341026.9020855.8023153.2044983.2034048.4066651.4010092.108603.5217349.3047485.2051341.3093531.7098935.0043745.3022500.1071171.8074093.3037265.9037485.1019582.501. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp

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 3.0Algorithm: SHA256EPYC 7713 2PEPYC 7713EPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P60000M120000M180000M240000M300000MSE +/- 401898644.45, N = 3SE +/- 28092099.50, N = 3SE +/- 10744204.26, N = 3SE +/- 22229383.18, N = 3SE +/- 66727027.10, N = 3SE +/- 112290036.56, N = 3SE +/- 65833761.08, N = 3SE +/- 42250028.06, N = 3SE +/- 23310559.35, N = 3SE +/- 380252901.09, N = 3SE +/- 91643095.12, N = 3SE +/- 584082922.27, N = 3SE +/- 281531389.95, N = 3SE +/- 4248731.03, N = 3SE +/- 87203247.94, N = 3SE +/- 145742816.61, N = 3SE +/- 540081125.64, N = 3SE +/- 113242158.65, N = 3SE +/- 88674415.22, N = 3SE +/- 282889949.77, N = 31286166369006520601457774358249567148797141130740139306001464564119902853888308725151039647514171679771259794446071431634700572515112738532844998186079097400932345499341367205408037813205338727447103745920213103690964737572672218131. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -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/. 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 2022.10.13Model: Rubber O-Ring Seal InstallationEPYC 9654EPYC 9654 - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P20406080100SE +/- 0.04, N = 3SE +/- 0.16, N = 3SE +/- 1.42, N = 3SE +/- 0.27, N = 3SE +/- 0.09, N = 3SE +/- 0.04, N = 3SE +/- 0.03, N = 3SE +/- 0.05, N = 3SE +/- 0.58, N = 1266.8161.5299.4168.3080.0679.9950.2850.1482.63

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 3.2.3Time To CompileEPYC 7713 2PEPYC 7713EPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P1428425670SE +/- 0.53, N = 3SE +/- 0.13, N = 3SE +/- 0.12, N = 3SE +/- 0.53, N = 3SE +/- 0.13, N = 3SE +/- 0.30, N = 3SE +/- 0.14, N = 3SE +/- 0.20, N = 3SE +/- 0.22, N = 3SE +/- 0.18, N = 3SE +/- 0.07, N = 3SE +/- 0.09, N = 3SE +/- 0.38, N = 4SE +/- 0.28, N = 3SE +/- 0.10, N = 3SE +/- 0.31, N = 3SE +/- 0.38, N = 4SE +/- 0.14, N = 3SE +/- 0.06, N = 3SE +/- 0.27, N = 343.5347.9245.4043.0742.8138.9959.2063.0544.6833.2632.4533.7833.3440.6752.2432.6032.9734.2034.5345.77

Neural Magic DeepSparse

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.1Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Synchronous Single-StreamEPYC 9654EPYC 9654 - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P20406080100SE +/- 0.21, N = 3SE +/- 0.11, N = 3SE +/- 0.16, N = 3SE +/- 0.03, N = 3SE +/- 0.23, N = 3SE +/- 0.16, N = 3SE +/- 0.12, N = 3SE +/- 0.19, N = 3SE +/- 0.39, N = 387.5289.5049.0451.4688.2088.0589.1089.0351.59

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.1Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Synchronous Single-StreamEPYC 9654EPYC 9654 - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P510152025SE +/- 0.03, N = 3SE +/- 0.01, N = 3SE +/- 0.06, N = 3SE +/- 0.01, N = 3SE +/- 0.03, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.15, N = 311.4211.1720.3819.4211.3311.3511.2211.2319.38

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.1Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-StreamEPYC 9654EPYC 9654 - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P246810SE +/- 0.0115, N = 3SE +/- 0.0062, N = 3SE +/- 0.0024, N = 3SE +/- 0.0078, N = 3SE +/- 0.0072, N = 3SE +/- 0.0077, N = 3SE +/- 0.0116, N = 3SE +/- 0.0046, N = 3SE +/- 0.0151, N = 35.19985.19237.02456.97063.89413.90803.90673.95774.4379

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.1Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-StreamEPYC 9654EPYC 9654 - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P60120180240300SE +/- 0.43, N = 3SE +/- 0.23, N = 3SE +/- 0.04, N = 3SE +/- 0.16, N = 3SE +/- 0.47, N = 3SE +/- 0.50, N = 3SE +/- 0.76, N = 3SE +/- 0.30, N = 3SE +/- 0.77, N = 3192.24192.52142.28143.41256.65255.74255.83252.55224.92

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 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P91827364534.4931.5628.9430.6435.6437.1830.9425.9423.1931.6724.4428.2921.9322.2922.8522.8439.47-lfoamToVTK -ldynamicMesh -lfileFormats-lfoamToVTK -ldynamicMesh -lfileFormats-lfoamToVTK -ldynamicMesh -lfileFormats-lfoamToVTK -ldynamicMesh -lfileFormats-lfiniteVolume -lmeshTools -lparallel -lregionModels-lfiniteVolume -lmeshTools -lparallel -lregionModels-lfiniteVolume -lmeshTools -lparallel -lregionModels-lfiniteVolume -lmeshTools -lparallel -lregionModels-lfiniteVolume -lmeshTools -lparallel -lregionModels-lfiniteVolume -lmeshTools -lparallel -lregionModels-lfiniteVolume -lmeshTools -lparallel -lregionModels-lfiniteVolume -lmeshTools -lparallel -lregionModels-lfiniteVolume -lmeshTools -lparallel -lregionModels-lfiniteVolume -lmeshTools -lparallel -lregionModels-lfiniteVolume -lmeshTools -lparallel -lregionModels-lfiniteVolume -lmeshTools -lparallel -lregionModels-lfoamToVTK -ldynamicMesh -lfileFormats1. (CXX) g++ options: -std=c++14 -m64 -O3 -ftemplate-depth-100 -fPIC -fuse-ld=bfd -Xlinker --add-needed --no-as-needed -llagrangian -lgenericPatchFields -lOpenFOAM -ldl -lm

OpenBenchmarking.orgSeconds, Fewer Is BetterOpenFOAM 10Input: drivaerFastback, Medium Mesh Size - Mesh TimeEPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P4080120160200161.85154.21126.71147.74173.54177.06156.83131.29120.42129.44131.09143.31109.42106.44110.84102.78175.08-lfoamToVTK -ldynamicMesh -lfileFormats-lfoamToVTK -ldynamicMesh -lfileFormats-lfoamToVTK -ldynamicMesh -lfileFormats-lfoamToVTK -ldynamicMesh -lfileFormats-lfiniteVolume -lmeshTools -lparallel -lregionModels-lfiniteVolume -lmeshTools -lparallel -lregionModels-lfiniteVolume -lmeshTools -lparallel -lregionModels-lfiniteVolume -lmeshTools -lparallel -lregionModels-lfiniteVolume -lmeshTools -lparallel -lregionModels-lfiniteVolume -lmeshTools -lparallel -lregionModels-lfiniteVolume -lmeshTools -lparallel -lregionModels-lfiniteVolume -lmeshTools -lparallel -lregionModels-lfiniteVolume -lmeshTools -lparallel -lregionModels-lfiniteVolume -lmeshTools -lparallel -lregionModels-lfiniteVolume -lmeshTools -lparallel -lregionModels-lfiniteVolume -lmeshTools -lparallel -lregionModels-lfoamToVTK -ldynamicMesh -lfileFormats1. (CXX) g++ options: -std=c++14 -m64 -O3 -ftemplate-depth-100 -fPIC -fuse-ld=bfd -Xlinker --add-needed --no-as-needed -llagrangian -lgenericPatchFields -lOpenFOAM -ldl -lm

Etcpak

Etcpack is the self-proclaimed "fastest ETC compressor on the planet" with focused on providing open-source, very fast ETC and S3 texture compression support. The test profile uses a 8K x 8K game texture as a sample input. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMpx/s, More Is BetterEtcpak 1.0Benchmark: Multi-Threaded - Configuration: ETC2EPYC 7713 2PEPYC 7713EPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P2K4K6K8K10KSE +/- 34.64, N = 8SE +/- 12.27, N = 9SE +/- 10.29, N = 9SE +/- 38.74, N = 8SE +/- 7.06, N = 9SE +/- 24.69, N = 8SE +/- 4.01, N = 8SE +/- 4.50, N = 9SE +/- 44.69, N = 8SE +/- 97.61, N = 15SE +/- 79.32, N = 15SE +/- 70.12, N = 9SE +/- 47.66, N = 9SE +/- 18.81, N = 9SE +/- 8.39, N = 9SE +/- 26.45, N = 9SE +/- 28.22, N = 9SE +/- 18.91, N = 9SE +/- 16.14, N = 9SE +/- 42.29, N = 86628.316694.856689.616678.406990.006926.205532.156170.396238.499257.889335.769305.679232.757726.467919.468902.858825.798976.898966.415779.841. (CXX) g++ options: -O3 -march=native -std=c++11 -lpthread

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 21.2Time To CompileEPYC 7713 2PEPYC 7713EPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P50100150200250SE +/- 1.63, N = 3SE +/- 2.24, N = 3SE +/- 2.33, N = 3SE +/- 0.84, N = 3SE +/- 1.36, N = 12SE +/- 0.34, N = 3SE +/- 1.27, N = 3SE +/- 0.31, N = 3SE +/- 1.75, N = 6SE +/- 2.00, N = 3SE +/- 0.21, N = 3SE +/- 0.76, N = 3SE +/- 0.87, N = 3SE +/- 0.43, N = 3SE +/- 0.16, N = 3SE +/- 1.11, N = 3SE +/- 0.87, N = 3SE +/- 1.25, N = 3SE +/- 1.10, N = 12SE +/- 2.02, N = 3162.23196.93188.63161.44178.79154.93211.95225.74183.40146.31141.44137.08135.26157.73188.03135.99134.83148.97150.77183.95

simdjson

This is a benchmark of SIMDJSON, a high performance JSON parser. SIMDJSON aims to be the fastest JSON parser and is used by projects like Microsoft FishStore, Yandex ClickHouse, Shopify, and others. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGB/s, More Is Bettersimdjson 2.0Throughput Test: TopTweetEPYC 7713 2PEPYC 7713EPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P246810SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.06, N = 3SE +/- 0.02, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.03, N = 3SE +/- 0.04, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.03, N = 3SE +/- 0.05, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 34.294.294.044.064.084.085.696.106.106.576.556.496.574.664.676.666.656.606.655.731. (CXX) g++ options: -O3

Neural Magic DeepSparse

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.1Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-StreamEPYC 9654EPYC 9654 - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P1326395265SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.11, N = 3SE +/- 0.07, N = 3SE +/- 0.00, N = 3SE +/- 0.05, N = 3SE +/- 0.03, N = 3SE +/- 0.04, N = 3SE +/- 0.06, N = 347.2542.2959.7259.3139.5536.7336.3537.8948.47

simdjson

This is a benchmark of SIMDJSON, a high performance JSON parser. SIMDJSON aims to be the fastest JSON parser and is used by projects like Microsoft FishStore, Yandex ClickHouse, Shopify, and others. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGB/s, More Is Bettersimdjson 2.0Throughput Test: DistinctUserIDEPYC 7713 2PEPYC 7713EPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P246810SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.03, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.04, N = 3SE +/- 0.03, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.00, N = 34.454.454.244.244.244.245.696.046.106.826.836.866.874.844.836.926.936.916.955.691. (CXX) g++ options: -O3

OpenBenchmarking.orgGB/s, More Is Bettersimdjson 2.0Throughput Test: PartialTweetsEPYC 7713 2PEPYC 7713EPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P1.2872.5743.8615.1486.435SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 33.723.743.563.543.563.544.745.035.035.675.665.675.674.064.055.705.725.725.704.731. (CXX) g++ options: -O3

srsRAN

srsRAN is an open-source LTE/5G software radio suite created by Software Radio Systems (SRS). The srsRAN 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.orgUE Mb/s, More Is BettersrsRAN 22.04.1Test: 5G PHY_DL_NR Test 52 PRB SISO 64-QAMEPYC 7713 2PEPYC 7713EPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P20406080100SE +/- 0.12, N = 3SE +/- 0.09, N = 3SE +/- 0.09, N = 3SE +/- 0.09, N = 3SE +/- 0.15, N = 3SE +/- 0.03, N = 3SE +/- 0.24, N = 3SE +/- 0.29, N = 3SE +/- 1.94, N = 4SE +/- 2.60, N = 4SE +/- 0.09, N = 4SE +/- 0.17, N = 4SE +/- 0.31, N = 4SE +/- 0.07, N = 3SE +/- 0.31, N = 3SE +/- 2.78, N = 4SE +/- 0.36, N = 4SE +/- 0.29, N = 4SE +/- 0.28, N = 4SE +/- 0.12, N = 362.562.859.659.559.859.972.678.077.492.294.594.994.468.168.193.495.695.995.971.41. (CXX) g++ options: -std=c++14 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -ldl -lpthread -lm

Node.js Express HTTP Load Test

A Node.js Express server with a Node-based loadtest client for facilitating HTTP benchmarking. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgRequests Per Second, More Is BetterNode.js Express HTTP Load TestEPYC 7713 2PEPYC 7713EPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P2K4K6K8K10KSE +/- 42.80, N = 15SE +/- 14.88, N = 3SE +/- 19.43, N = 3SE +/- 40.61, N = 15SE +/- 16.70, N = 3SE +/- 43.93, N = 15SE +/- 18.16, N = 4SE +/- 30.67, N = 4SE +/- 48.12, N = 4SE +/- 11.05, N = 4SE +/- 17.64, N = 4SE +/- 62.92, N = 8SE +/- 73.54, N = 6SE +/- 58.66, N = 3SE +/- 9.06, N = 3SE +/- 36.28, N = 4SE +/- 74.87, N = 5SE +/- 27.20, N = 4SE +/- 39.98, N = 4SE +/- 32.04, N = 450195438523649125175489966717085677878297780750874745280597174537500788478466245

Neural Magic DeepSparse

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.1Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-StreamEPYC 9654EPYC 9654 - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P4080120160200SE +/- 0.55, N = 3SE +/- 0.50, N = 3SE +/- 0.23, N = 3SE +/- 0.08, N = 3SE +/- 0.15, N = 3SE +/- 0.41, N = 3SE +/- 0.18, N = 3SE +/- 0.23, N = 3SE +/- 0.02, N = 3151.40142.33159.54155.47125.42114.56113.41121.43181.75

Build2

This test profile measures the time to bootstrap/install the build2 C++ build toolchain from source. Build2 is a cross-platform build toolchain for C/C++ code and features Cargo-like features. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBuild2 0.13Time To CompileEPYC 7713 2PEPYC 7713EPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P20406080100SE +/- 0.23, N = 3SE +/- 0.17, N = 3SE +/- 0.17, N = 3SE +/- 0.18, N = 3SE +/- 0.17, N = 3SE +/- 0.21, N = 3SE +/- 0.27, N = 3SE +/- 0.19, N = 3SE +/- 0.20, N = 3SE +/- 0.05, N = 3SE +/- 0.23, N = 3SE +/- 0.23, N = 3SE +/- 0.10, N = 3SE +/- 0.11, N = 3SE +/- 0.20, N = 3SE +/- 0.28, N = 3SE +/- 0.12, N = 3SE +/- 0.10, N = 3SE +/- 0.08, N = 3SE +/- 0.33, N = 360.7767.2965.5660.8663.1359.3774.7275.8962.4850.6049.5348.7848.7356.1664.8948.3248.4950.7150.8664.55

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 21.0Time To CompileEPYC 7713 2PEPYC 7713EPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P714212835SE +/- 0.03, N = 3SE +/- 0.02, N = 3SE +/- 0.05, N = 3SE +/- 0.04, N = 3SE +/- 0.03, N = 3SE +/- 0.05, N = 3SE +/- 0.07, N = 3SE +/- 0.06, N = 3SE +/- 0.18, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.07, N = 3SE +/- 0.19, N = 3SE +/- 0.15, N = 3SE +/- 0.07, N = 3SE +/- 0.09, N = 3SE +/- 0.08, N = 3SE +/- 0.04, N = 3SE +/- 0.06, N = 3SE +/- 0.04, N = 324.6227.7526.8724.9526.3824.5431.0130.8026.0920.7720.3820.2519.9422.7526.1619.8119.8020.5720.7926.83

AOM AV1

This is a test of the AOMedia AV1 encoder (libaom) developed by AOMedia and Google as the AV1 Codec Library. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.5Encoder Mode: Speed 0 Two-Pass - Input: Bosphorus 4KEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P0.11930.23860.35790.47720.5965SE +/- 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 = 30.430.350.340.440.520.520.480.410.520.520.530.530.411. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm

Neural Magic DeepSparse

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.1Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-StreamEPYC 9654EPYC 9654 - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P20406080100SE +/- 0.26, N = 3SE +/- 0.11, N = 3SE +/- 0.04, N = 3SE +/- 0.13, N = 3SE +/- 0.06, N = 3SE +/- 0.17, N = 3SE +/- 0.14, N = 3SE +/- 0.08, N = 3SE +/- 0.18, N = 376.6071.9681.0178.8664.1258.5357.4061.3888.67

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/. 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 2022.10.13Model: Bird Strike on WindshieldEPYC 9654EPYC 9654 - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P4080120160200SE +/- 0.70, N = 3SE +/- 0.79, N = 3SE +/- 1.23, N = 3SE +/- 0.40, N = 3SE +/- 0.22, N = 3SE +/- 0.19, N = 3SE +/- 0.31, N = 3SE +/- 0.17, N = 3SE +/- 0.94, N = 3119.94111.28128.95141.46165.94166.46108.19109.32141.93

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 7713 2PEPYC 7713EPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P130260390520650SE +/- 0.91, N = 3SE +/- 1.09, N = 3SE +/- 2.62, N = 3SE +/- 0.72, N = 3SE +/- 1.00, N = 3SE +/- 1.81, N = 3SE +/- 0.26, N = 3SE +/- 0.65, N = 3SE +/- 0.48, N = 3SE +/- 1.13, N = 3SE +/- 0.08, N = 3SE +/- 1.32, N = 3SE +/- 1.36, N = 3SE +/- 1.36, N = 3SE +/- 2.49, N = 3SE +/- 1.62, N = 3SE +/- 2.27, N = 3SE +/- 0.79, N = 3SE +/- 0.88, N = 3SE +/- 1.53, N = 3479.53486.42466.89455.68492.43488.61398.58415.99412.16585.06583.50586.86584.26525.03529.07592.13591.08593.13592.89389.89

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 2021.01.31Threads: 32 - Buffer Length: 256 - Filter Length: 57EPYC 7713 2PEPYC 7713EPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P500M1000M1500M2000M2500MSE +/- 3291571.73, N = 3SE +/- 1331665.62, N = 3SE +/- 5453744.89, N = 3SE +/- 1713994.68, N = 3SE +/- 959745.34, N = 3SE +/- 2140353.03, N = 3SE +/- 2321158.71, N = 3SE +/- 4351755.71, N = 3SE +/- 2318045.15, N = 3SE +/- 9321659.37, N = 3SE +/- 4493328.39, N = 3SE +/- 2804955.93, N = 3SE +/- 3401960.22, N = 3SE +/- 5138849.85, N = 3SE +/- 2702468.01, N = 3SE +/- 1123981.02, N = 3SE +/- 3540872.46, N = 3SE +/- 5660683.12, N = 3SE +/- 3481538.61, N = 3SE +/- 3667121.18, N = 3159493333315916000001590000000159806666716793333331670933333155246666715683333331770300000226880000022843000002282066667228150000019492333331856000000231740000023118666672308200000231926666716963333331. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

PyPerformance

PyPerformance is the reference Python performance benchmark suite. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: regex_compileEPYC 7713 2PEPYC 7713EPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P4080120160200SE +/- 0.33, N = 3SE +/- 0.00, N = 3SE +/- 0.33, N = 3SE +/- 0.33, N = 3SE +/- 0.00, N = 3SE +/- 0.33, N = 3SE +/- 0.00, N = 3SE +/- 0.33, 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 = 3156156164163163164169160160116116116117143143114115114115169

simdjson

This is a benchmark of SIMDJSON, a high performance JSON parser. SIMDJSON aims to be the fastest JSON parser and is used by projects like Microsoft FishStore, Yandex ClickHouse, Shopify, and others. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGB/s, More Is Bettersimdjson 2.0Throughput Test: KostyaEPYC 7713 2PEPYC 7713EPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P0.93831.87662.81493.75324.6915SE +/- 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 +/- 0.01, 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 = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 32.982.982.842.842.842.842.913.063.014.104.114.104.113.243.244.154.164.174.172.831. (CXX) g++ options: -O3

AOM AV1

This is a test of the AOMedia AV1 encoder (libaom) developed by AOMedia and Google as the AV1 Codec Library. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.5Encoder Mode: Speed 4 Two-Pass - Input: Bosphorus 4KEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P48121620SE +/- 0.07, N = 3SE +/- 0.05, N = 3SE +/- 0.01, N = 3SE +/- 0.06, N = 3SE +/- 0.13, N = 15SE +/- 0.22, N = 12SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.04, N = 3SE +/- 0.12, N = 3SE +/- 0.06, N = 3SE +/- 0.01, N = 3SE +/- 0.09, N = 310.619.759.579.8513.1712.7810.5911.4612.5612.7413.9813.919.561. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm

srsRAN

srsRAN is an open-source LTE/5G software radio suite created by Software Radio Systems (SRS). The srsRAN 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.orgUE Mb/s, More Is BettersrsRAN 22.04.1Test: 4G PHY_DL_Test 100 PRB MIMO 64-QAMEPYC 7713 2PEPYC 7713EPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P4080120160200SE +/- 0.37, N = 3SE +/- 0.20, N = 12SE +/- 0.19, N = 3SE +/- 0.43, N = 3SE +/- 0.22, N = 3SE +/- 0.60, N = 3SE +/- 1.30, N = 3SE +/- 0.12, N = 3SE +/- 0.17, N = 3SE +/- 0.19, N = 3SE +/- 0.20, N = 14SE +/- 0.12, N = 3SE +/- 0.15, N = 3SE +/- 0.37, N = 3SE +/- 0.47, N = 3SE +/- 0.35, N = 3SE +/- 0.27, N = 3SE +/- 0.43, N = 3SE +/- 0.03, N = 3SE +/- 0.24, N = 3134.6135.4128.1128.5129.8128.4110.2133.7132.3158.5158.4158.6158.1147.5147.0160.1159.6160.9160.4120.71. (CXX) g++ options: -std=c++14 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -ldl -lpthread -lm

Neural Magic DeepSparse

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.1Model: CV Detection,YOLOv5s COCO - Scenario: Asynchronous Multi-StreamEPYC 9654EPYC 9654 - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P306090120150SE +/- 0.19, N = 3SE +/- 0.13, N = 3SE +/- 0.18, N = 3SE +/- 0.09, N = 3SE +/- 0.23, N = 3SE +/- 0.27, N = 3SE +/- 0.07, N = 3SE +/- 0.18, N = 3SE +/- 0.24, N = 3107.0195.85119.11116.7789.8182.2682.2987.56119.75

srsRAN

srsRAN is an open-source LTE/5G software radio suite created by Software Radio Systems (SRS). The srsRAN 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.orgUE Mb/s, More Is BettersrsRAN 22.04.1Test: 4G PHY_DL_Test 100 PRB SISO 64-QAMEPYC 7713 2PEPYC 7713EPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P4080120160200SE +/- 0.55, N = 4SE +/- 0.28, N = 4SE +/- 0.44, N = 3SE +/- 0.99, N = 3SE +/- 0.26, N = 4SE +/- 0.21, N = 4SE +/- 0.70, N = 13SE +/- 0.79, N = 15SE +/- 0.07, N = 3SE +/- 0.15, N = 4SE +/- 0.38, N = 4SE +/- 0.84, N = 4SE +/- 0.36, N = 4SE +/- 0.44, N = 4SE +/- 1.02, N = 4SE +/- 0.81, N = 4SE +/- 0.57, N = 4SE +/- 0.65, N = 4SE +/- 0.68, N = 4SE +/- 0.24, N = 3145.1146.0137.3138.0138.6138.3118.1126.4125.2166.6166.6165.2166.3158.5157.8168.0168.7169.0168.1116.11. (CXX) g++ options: -std=c++14 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -ldl -lpthread -lm

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/. 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 2022.10.13Model: Bumper BeamEPYC 9654EPYC 9654 - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P20406080100SE +/- 0.17, N = 3SE +/- 0.23, N = 3SE +/- 0.60, N = 3SE +/- 0.17, N = 3SE +/- 0.32, N = 3SE +/- 0.14, N = 3SE +/- 0.27, N = 3SE +/- 0.26, N = 3SE +/- 0.26, N = 373.7669.37100.5490.7973.1372.5971.0471.1086.21

Zstd Compression

This test measures the time needed to compress/decompress a sample file (a FreeBSD disk image - FreeBSD-12.2-RELEASE-amd64-memstick.img) using Zstd compression with options for different compression levels / settings. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.0Compression Level: 19, Long Mode - Decompression SpeedEPYC 7713 2PEPYC 7713EPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P8001600240032004000SE +/- 12.57, N = 15SE +/- 13.08, N = 3SE +/- 12.82, N = 3SE +/- 10.83, N = 15SE +/- 44.74, N = 3SE +/- 17.82, N = 4SE +/- 3.78, N = 3SE +/- 1.66, N = 3SE +/- 15.95, N = 3SE +/- 1.24, N = 3SE +/- 39.99, N = 3SE +/- 11.04, N = 15SE +/- 21.16, N = 12SE +/- 13.14, N = 15SE +/- 47.75, N = 3SE +/- 18.13, N = 12SE +/- 30.54, N = 12SE +/- 5.81, N = 3SE +/- 40.76, N = 3SE +/- 6.09, N = 33492.23538.03328.43336.63378.43343.32815.92982.52828.93798.13852.83797.63779.63727.83754.73870.93843.53837.03926.02731.21. (CC) gcc options: -O3 -pthread -lz -llzma

AOM AV1

This is a test of the AOMedia AV1 encoder (libaom) developed by AOMedia and Google as the AV1 Codec Library. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.5Encoder Mode: Speed 4 Two-Pass - Input: Bosphorus 1080pEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P612182430SE +/- 0.18, N = 15SE +/- 0.08, N = 3SE +/- 0.02, N = 3SE +/- 0.22, N = 4SE +/- 0.35, N = 3SE +/- 0.23, N = 7SE +/- 0.05, N = 3SE +/- 0.06, N = 3SE +/- 0.19, N = 11SE +/- 0.23, N = 3SE +/- 0.12, N = 3SE +/- 0.08, N = 3SE +/- 0.19, N = 319.7619.1519.8819.4324.9624.8320.9522.4925.1725.3726.3826.6019.091. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm

PyPerformance

PyPerformance is the reference Python performance benchmark suite. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: json_loadsEPYC 7713 2PEPYC 7713EPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P510152025SE +/- 0.03, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.03, N = 3SE +/- 0.00, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.00, N = 3SE +/- 0.03, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 321.521.322.522.322.322.522.621.421.416.616.716.516.619.519.616.516.416.316.322.6

Zstd Compression

This test measures the time needed to compress/decompress a sample file (a FreeBSD disk image - FreeBSD-12.2-RELEASE-amd64-memstick.img) using Zstd compression with options for different compression levels / settings. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.0Compression Level: 19 - Compression SpeedEPYC 7713 2PEPYC 7713EPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P20406080100SE +/- 0.89, N = 15SE +/- 0.79, N = 3SE +/- 0.88, N = 5SE +/- 1.28, N = 15SE +/- 0.83, N = 3SE +/- 0.98, N = 7SE +/- 0.20, N = 3SE +/- 0.15, N = 3SE +/- 0.94, N = 3SE +/- 0.23, N = 3SE +/- 1.03, N = 3SE +/- 0.35, N = 3SE +/- 0.61, N = 3SE +/- 1.67, N = 14SE +/- 1.10, N = 3SE +/- 1.46, N = 3SE +/- 1.36, N = 15SE +/- 0.31, N = 3SE +/- 0.23, N = 3SE +/- 0.44, N = 382.284.885.080.1103.6107.682.483.787.1106.1107.3108.4107.894.795.1103.3102.9102.1103.386.21. (CC) gcc options: -O3 -pthread -lz -llzma

srsRAN

srsRAN is an open-source LTE/5G software radio suite created by Software Radio Systems (SRS). The srsRAN 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.orgUE Mb/s, More Is BettersrsRAN 22.04.1Test: 4G PHY_DL_Test 100 PRB MIMO 256-QAMEPYC 7713 2PEPYC 7713EPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P4080120160200SE +/- 0.63, N = 3SE +/- 0.30, N = 3SE +/- 0.66, N = 3SE +/- 0.23, N = 3SE +/- 0.33, N = 3SE +/- 0.17, N = 3SE +/- 1.56, N = 3SE +/- 2.02, N = 3SE +/- 0.17, N = 3SE +/- 0.54, N = 3SE +/- 0.29, N = 3SE +/- 0.19, N = 3SE +/- 0.58, N = 3SE +/- 0.22, N = 3SE +/- 0.52, N = 3SE +/- 0.26, N = 3SE +/- 0.00, N = 3SE +/- 0.23, N = 3SE +/- 0.13, N = 3SE +/- 3.20, N = 3142.2143.3135.8136.0136.4137.0135.2137.3138.9166.2166.4166.1166.7154.9156.1168.5168.9169.1169.3125.71. (CXX) g++ options: -std=c++14 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -ldl -lpthread -lm

DaCapo Benchmark

This test runs the DaCapo Benchmarks written in Java and intended to test system/CPU performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 9.12-MR1Java Test: JythonEPYC 7713 2PEPYC 7713EPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P9001800270036004500SE +/- 15.85, N = 7SE +/- 11.39, N = 7SE +/- 7.99, N = 7SE +/- 35.81, N = 8SE +/- 13.60, N = 7SE +/- 31.80, N = 7SE +/- 21.78, N = 7SE +/- 16.15, N = 7SE +/- 26.05, N = 7SE +/- 19.92, N = 8SE +/- 16.67, N = 8SE +/- 24.10, N = 8SE +/- 22.93, N = 8SE +/- 32.86, N = 7SE +/- 9.91, N = 7SE +/- 21.16, N = 8SE +/- 18.24, N = 8SE +/- 12.71, N = 8SE +/- 19.41, N = 8SE +/- 13.65, N = 740764088412542174053424838303646365932403219338033953706356633023321317132053855

Timed Wasmer Compilation

This test times how long it takes to compile Wasmer. Wasmer is written in the Rust programming language and is a WebAssembly runtime implementation that supports WASI and EmScripten. This test profile builds Wasmer with the Cranelift and Singlepast compiler features enabled. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Wasmer Compilation 2.3Time To CompileEPYC 7713 2PEPYC 7713EPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P1224364860SE +/- 0.32, N = 3SE +/- 0.08, N = 3SE +/- 0.07, N = 3SE +/- 0.10, N = 3SE +/- 0.06, N = 3SE +/- 0.11, N = 3SE +/- 0.12, N = 3SE +/- 0.19, N = 3SE +/- 0.14, N = 3SE +/- 0.12, N = 3SE +/- 0.09, N = 3SE +/- 0.06, N = 3SE +/- 0.16, N = 3SE +/- 0.14, N = 3SE +/- 0.08, N = 3SE +/- 0.04, N = 3SE +/- 0.14, N = 3SE +/- 0.08, N = 3SE +/- 0.11, N = 3SE +/- 0.17, N = 351.3552.0252.9053.1149.6850.3348.6947.4146.7440.4540.4141.0941.4445.8246.0840.7240.8640.1840.1048.331. (CC) gcc options: -m64 -ldl -lgcc_s -lutil -lrt -lpthread -lm -lc -pie -nodefaultlibs

simdjson

This is a benchmark of SIMDJSON, a high performance JSON parser. SIMDJSON aims to be the fastest JSON parser and is used by projects like Microsoft FishStore, Yandex ClickHouse, Shopify, and others. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGB/s, More Is Bettersimdjson 2.0Throughput Test: LargeRandomEPYC 7713 2PEPYC 7713EPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P0.28580.57160.85741.14321.429SE +/- 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 = 31.031.030.980.980.980.980.971.021.001.251.251.251.251.121.121.271.271.261.270.961. (CXX) g++ options: -O3

srsRAN

srsRAN is an open-source LTE/5G software radio suite created by Software Radio Systems (SRS). The srsRAN 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.orgSamples / Second, More Is BettersrsRAN 22.04.1Test: OFDM_TestEPYC 7713 2PEPYC 7713EPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P40M80M120M160M200MSE +/- 1229303.58, N = 15SE +/- 1264695.92, N = 7SE +/- 961718.04, N = 15SE +/- 1074873.19, N = 15SE +/- 1757207.38, N = 3SE +/- 1046835.32, N = 9SE +/- 523874.45, N = 3SE +/- 581186.53, N = 3SE +/- 520683.31, N = 3SE +/- 2007485.99, N = 3SE +/- 1212530.99, N = 11SE +/- 1841496.98, N = 3SE +/- 520683.31, N = 3SE +/- 1646207.76, N = 3SE +/- 876229.30, N = 3SE +/- 688799.28, N = 3SE +/- 1211518.79, N = 3SE +/- 550757.05, N = 3SE +/- 592546.29, N = 3SE +/- 218581.28, N = 31364933331345571431301066671274800001287666671303444441352333331431666671432666671620000001612363641586333331637666671477000001480666671666666671641666671668000001645666671361666671. (CXX) g++ options: -std=c++14 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -ldl -lpthread -lm

PyPerformance

PyPerformance is the reference Python performance benchmark suite. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: crypto_pyaesEPYC 7713 2PEPYC 7713EPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P20406080100SE +/- 0.25, N = 3SE +/- 0.00, N = 3SE +/- 0.33, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.33, N = 3SE +/- 0.00, N = 3SE +/- 0.33, N = 3SE +/- 0.00, N = 3SE +/- 0.21, N = 3SE +/- 0.15, N = 3SE +/- 0.12, N = 3SE +/- 0.27, N = 3SE +/- 0.10, N = 3SE +/- 0.13, N = 3SE +/- 0.20, N = 3SE +/- 0.12, N = 3SE +/- 0.26, N = 3SE +/- 0.17, N = 3SE +/- 0.00, N = 398.2101.0103.0105.0103.0103.0110.0104.0104.088.287.490.189.591.291.986.687.386.887.0111.0

Timed CPython Compilation

This test times how long it takes to build the reference Python implementation, CPython, with optimizations and LTO enabled for a release build. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed CPython Compilation 3.10.6Build Configuration: DefaultEPYC 7713 2PEPYC 7713EPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P51015202518.1218.7519.0218.8718.7518.7919.7018.9218.2415.5915.6315.6415.7116.6417.0015.4715.4515.5015.4619.07

srsRAN

srsRAN is an open-source LTE/5G software radio suite created by Software Radio Systems (SRS). The srsRAN 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.orgeNb Mb/s, More Is BettersrsRAN 22.04.1Test: 5G PHY_DL_NR Test 52 PRB SISO 64-QAMEPYC 7713 2PEPYC 7713EPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P306090120150SE +/- 0.23, N = 3SE +/- 0.23, N = 3SE +/- 0.06, N = 3SE +/- 0.26, N = 3SE +/- 0.24, N = 3SE +/- 0.21, N = 3SE +/- 0.20, N = 3SE +/- 0.20, N = 3SE +/- 1.43, N = 4SE +/- 0.34, N = 4SE +/- 0.42, N = 4SE +/- 0.44, N = 4SE +/- 0.40, N = 4SE +/- 0.23, N = 3SE +/- 0.78, N = 3SE +/- 0.23, N = 4SE +/- 0.44, N = 4SE +/- 0.45, N = 4SE +/- 0.06, N = 4SE +/- 0.30, N = 3127.8127.5121.6121.8121.7121.9113.1122.0123.0139.4139.8139.3138.8139.1138.2141.7141.0141.6141.9111.31. (CXX) g++ options: -std=c++14 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -ldl -lpthread -lm

PHPBench

PHPBench is a benchmark suite for PHP. It performs a large number of simple tests in order to bench various aspects of the PHP interpreter. PHPBench can be used to compare hardware, operating systems, PHP versions, PHP accelerators and caches, compiler options, etc. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgScore, More Is BetterPHPBench 0.8.1PHP Benchmark SuiteEPYC 7713 2PEPYC 7713EPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P200K400K600K800K1000KSE +/- 2398.01, N = 3SE +/- 3252.22, N = 3SE +/- 9346.50, N = 3SE +/- 1449.54, N = 3SE +/- 1748.53, N = 3SE +/- 1434.53, N = 3SE +/- 924.75, N = 3SE +/- 5721.95, N = 3SE +/- 987.27, N = 3SE +/- 5980.59, N = 3SE +/- 1659.67, N = 3SE +/- 7390.85, N = 3SE +/- 3619.22, N = 3SE +/- 3058.25, N = 3SE +/- 2116.45, N = 3SE +/- 9437.20, N = 4SE +/- 1751.73, N = 3SE +/- 9166.50, N = 3SE +/- 4409.84, N = 3SE +/- 1645.39, N = 3730528730550702291691655697059696203816743859511866491843665843411847129846790802341793816876214849730862102855637816968

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 7713 2PEPYC 7713EPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P2004006008001000SE +/- 7.57, N = 3SE +/- 3.18, N = 3SE +/- 12.19, N = 4SE +/- 2.33, N = 3SE +/- 2.03, N = 3SE +/- 1.76, N = 3SE +/- 0.58, N = 3SE +/- 1.53, N = 3SE +/- 1.45, N = 3SE +/- 6.01, N = 3SE +/- 6.08, N = 3SE +/- 5.61, N = 3SE +/- 4.33, N = 3SE +/- 8.88, N = 3SE +/- 0.88, N = 3SE +/- 2.33, N = 3SE +/- 3.93, N = 3SE +/- 1.15, N = 3SE +/- 3.84, N = 3SE +/- 10.13, N = 6970969101810161016101810429839868558648648628879018448468498491052

srsRAN

srsRAN is an open-source LTE/5G software radio suite created by Software Radio Systems (SRS). The srsRAN 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.orgUE Mb/s, More Is BettersrsRAN 22.04.1Test: 4G PHY_DL_Test 100 PRB SISO 256-QAMEPYC 7713 2PEPYC 7713EPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P4080120160200SE +/- 0.21, N = 3SE +/- 0.52, N = 3SE +/- 0.30, N = 3SE +/- 0.44, N = 3SE +/- 0.40, N = 3SE +/- 0.29, N = 3SE +/- 0.23, N = 3SE +/- 0.12, N = 3SE +/- 0.10, N = 3SE +/- 0.58, N = 3SE +/- 0.88, N = 3SE +/- 0.51, N = 3SE +/- 0.23, N = 3SE +/- 0.31, N = 3SE +/- 0.20, N = 3SE +/- 0.54, N = 3SE +/- 0.41, N = 3SE +/- 0.66, N = 3SE +/- 0.81, N = 3SE +/- 0.21, N = 15151.8152.6142.8143.8144.2144.3142.3146.6147.1172.8172.1173.2173.1164.3165.9174.0175.5175.6175.1140.91. (CXX) g++ options: -std=c++14 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -ldl -lpthread -lm

PyPerformance

PyPerformance is the reference Python performance benchmark suite. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: django_templateEPYC 7713 2PEPYC 7713EPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P1020304050SE +/- 0.09, N = 3SE +/- 0.07, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.09, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.06, N = 3SE +/- 0.07, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.06, N = 3SE +/- 0.06, N = 3SE +/- 0.09, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 339.839.942.241.842.142.144.341.841.936.336.536.136.236.936.835.835.736.036.044.3

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 1.21EPYC 7713 2PEPYC 7713EPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P7001400210028003500SE +/- 25.70, N = 3SE +/- 25.97, N = 3SE +/- 24.99, N = 3SE +/- 27.55, N = 5SE +/- 22.27, N = 3SE +/- 25.83, N = 3SE +/- 17.79, N = 3SE +/- 23.48, N = 3SE +/- 18.13, N = 3SE +/- 35.26, N = 3SE +/- 30.22, N = 3SE +/- 5.62, N = 3SE +/- 24.81, N = 9SE +/- 0.95, N = 3SE +/- 29.32, N = 3SE +/- 2.89, N = 3SE +/- 22.61, N = 3SE +/- 31.45, N = 3SE +/- 31.02, N = 3SE +/- 16.97, N = 32830.52827.52684.72689.62694.32668.02521.72664.82666.33028.23043.03049.83030.63094.03047.13106.43059.93089.53075.12514.71. (CXX) g++ options: -O3 -march=native -rdynamic

Timed CPython Compilation

This test times how long it takes to build the reference Python implementation, CPython, with optimizations and LTO enabled for a release build. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed CPython Compilation 3.10.6Build Configuration: Released Build, PGO + LTO OptimizedEPYC 7713 2PEPYC 7713EPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P70140210280350283.87286.23298.37298.90292.42292.80306.34293.08290.63254.59254.61255.75255.70263.87264.13253.34253.27251.21251.68307.76

WebP2 Image Encode

OpenBenchmarking.orgWatts, Fewer Is BetterWebP2 Image Encode 20220823CPU Power Consumption MonitorEPYC 7713 2PEPYC 7713EPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P90180270360450Min: 79.81 / Avg: 157.99 / Max: 323.15Min: 37.18 / Avg: 85.41 / Max: 202.89Min: 35.61 / Avg: 83.58 / Max: 209.48Min: 75.94 / Avg: 146.55 / Max: 297.33Min: 33.77 / Avg: 83.79 / Max: 224.42Min: 73.91 / Avg: 149.74 / Max: 323.44Min: 57.78 / Avg: 138.45 / Max: 287.62Min: 55.42 / Avg: 130.44 / Max: 283.74Min: 105.81 / Avg: 250.52 / Max: 498.31Min: 25.13 / Avg: 82.85 / Max: 220.37Min: 26.52 / Avg: 83.72 / Max: 233.39Min: 49.67 / Avg: 154.93 / Max: 353.94Min: 52.12 / Avg: 153.04 / Max: 350.04Min: 88.23 / Avg: 178.53 / Max: 398.49Min: 41.88 / Avg: 94.45 / Max: 249.32Min: 41.59 / Avg: 130.1 / Max: 319.48Min: 41.49 / Avg: 133.41 / Max: 322.48Min: 16.16 / Avg: 67.27 / Max: 200.66Min: 20.87 / Avg: 70.29 / Max: 201.63Min: 132.1 / Avg: 270.74 / Max: 510.03

OpenBenchmarking.orgMP/s Per Watt, More Is BetterWebP2 Image Encode 20220823Encode Settings: DefaultEPYC 7713 2PEPYC 7713EPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P0.03920.07840.11760.15680.1960.0520.1080.1090.0570.1140.0570.0590.0690.0320.1400.1440.0640.0670.0490.1090.0790.0760.1740.1670.029

OpenBenchmarking.orgMP/s, More Is BetterWebP2 Image Encode 20220823Encode Settings: DefaultEPYC 7713 2PEPYC 7713EPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P3691215SE +/- 0.18, N = 15SE +/- 0.11, N = 15SE +/- 0.09, N = 15SE +/- 0.13, N = 15SE +/- 0.13, N = 15SE +/- 0.16, N = 15SE +/- 0.04, N = 9SE +/- 0.07, N = 10SE +/- 0.07, N = 9SE +/- 0.10, N = 15SE +/- 0.18, N = 15SE +/- 0.15, N = 15SE +/- 0.20, N = 15SE +/- 0.12, N = 15SE +/- 0.09, N = 15SE +/- 0.21, N = 15SE +/- 0.20, N = 15SE +/- 0.17, N = 15SE +/- 0.19, N = 15SE +/- 0.06, N = 158.259.219.148.329.558.568.169.018.0511.6012.069.9610.218.7710.3010.3410.1511.6911.767.961. (CXX) g++ options: -msse4.2 -fno-rtti -O3 -ldl

CPU Power Consumption Monitor

OpenBenchmarking.orgWattsCPU Power Consumption MonitorPhoronix Test Suite System MonitoringEPYC 7713 2PEPYC 7713EPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P150300450600750Min: 40.73 / Avg: 292.32 / Max: 463.56Min: 19.29 / Avg: 158.59 / Max: 231.88Min: 17.91 / Avg: 169.5 / Max: 286.78Min: 38.66 / Avg: 332 / Max: 573.72Min: 17.66 / Avg: 193.18 / Max: 291.19Min: 38.36 / Avg: 336.85 / Max: 578.83Min: 31.32 / Avg: 223.73 / Max: 293.02Min: 37.91 / Avg: 225.19 / Max: 286.34Min: 55.85 / Avg: 410.13 / Max: 571.36Min: 13.46 / Avg: 223.35 / Max: 363.54Min: 13.57 / Avg: 256.57 / Max: 415.76Min: 22.26 / Avg: 361.53 / Max: 707.31Min: 29.18 / Avg: 443.82 / Max: 833.55Min: 44.29 / Avg: 388.91 / Max: 568.18Min: 41.77 / Avg: 216.76 / Max: 286.74Min: 21.75 / Avg: 366.87 / Max: 697.99Min: 21.9 / Avg: 420.09 / Max: 816.8Min: 15 / Avg: 234.13 / Max: 404.97Min: 10.82 / Avg: 221.23 / Max: 355.01Min: 73.9 / Avg: 431.65 / Max: 583.63

ebizzy

OpenBenchmarking.orgWatts, Fewer Is Betterebizzy 0.3CPU Power Consumption MonitorEPYC 7713 2PEPYC 7713EPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P130260390520650Min: 82.07 / Avg: 391.19 / Max: 461.45Min: 37.65 / Avg: 195.84 / Max: 230.29Min: 35.81 / Avg: 206.51 / Max: 245.66Min: 78.29 / Avg: 412.01 / Max: 496.95Min: 34.28 / Avg: 208.24 / Max: 246.4Min: 74.96 / Avg: 423.84 / Max: 505.86Min: 62.8 / Avg: 237.52 / Max: 290.91Min: 57.15 / Avg: 231.39 / Max: 285.46Min: 114.67 / Avg: 466.7 / Max: 570.84Min: 26.33 / Avg: 246.52 / Max: 293.17Min: 26.54 / Avg: 300.39 / Max: 357.13Min: 46.44 / Avg: 488.18 / Max: 604.99Min: 54.63 / Avg: 609.68 / Max: 750.06Min: 89.69 / Avg: 452.29 / Max: 549.22Min: 42.62 / Avg: 224.4 / Max: 265.28Min: 43.33 / Avg: 481.07 / Max: 577.37Min: 42.03 / Avg: 631.31 / Max: 767.46Min: 18.28 / Avg: 311.19 / Max: 372.03Min: 21.89 / Avg: 232.97 / Max: 277.3Min: 133.51 / Avg: 476.25 / Max: 581.88

OpenBenchmarking.orgRecords/s Per Watt, More Is Betterebizzy 0.3EPYC 7713 2PEPYC 7713EPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P4K8K12K16K20K8056.0412223.9111357.367429.4712415.087385.234709.474207.043513.7617391.2115548.2710754.949400.076341.708986.9011212.279220.4815325.4117226.243934.54

OpenBenchmarking.orgRecords/s, More Is Betterebizzy 0.3EPYC 7713 2PEPYC 7713EPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P1.2M2.4M3.6M4.8M6MSE +/- 8983.85, N = 3SE +/- 18666.48, N = 3SE +/- 31247.78, N = 13SE +/- 67846.42, N = 15SE +/- 3596.86, N = 3SE +/- 63488.17, N = 15SE +/- 7489.45, N = 3SE +/- 8108.16, N = 3SE +/- 19665.52, N = 12SE +/- 56812.23, N = 15SE +/- 53379.81, N = 15SE +/- 133651.04, N = 12SE +/- 121230.32, N = 15SE +/- 61589.71, N = 15SE +/- 18399.25, N = 7SE +/- 108149.58, N = 15SE +/- 105603.89, N = 15SE +/- 38422.79, N = 13SE +/- 41834.71, N = 15SE +/- 26102.71, N = 331514252393917234539530610512585316313017611185829734631639889428720046705625250316573104928682782016627539388258209484769106401319318725411. (CC) gcc options: -pthread -lpthread -O3 -march=native

oneDNN

OpenBenchmarking.orgWatts, Fewer Is BetteroneDNN 2.6CPU Power Consumption MonitorEPYC 7713 2PEPYC 7713EPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P100200300400500Min: 82.02 / Avg: 291.06 / Max: 460.21Min: 37.9 / Avg: 147.54 / Max: 230.36Min: 36.01 / Avg: 152.43 / Max: 241.75Min: 77.35 / Avg: 280.84 / Max: 490.19Min: 34.15 / Avg: 167.6 / Max: 269.49Min: 75.02 / Avg: 308.1 / Max: 572.87Min: 60.52 / Avg: 191.45 / Max: 290.97Min: 58.33 / Avg: 187.92 / Max: 285.25Min: 116.16 / Avg: 339.23 / Max: 540.54Min: 26.8 / Avg: 158.47 / Max: 286.83Min: 27.13 / Avg: 167.65 / Max: 295.22Min: 51.96 / Avg: 288.57 / Max: 456.99Min: 50.87 / Avg: 305.48 / Max: 505.31Min: 89.11 / Avg: 314.43 / Max: 508.41Min: 42.78 / Avg: 180.13 / Max: 277.72Min: 40.23 / Avg: 275.53 / Max: 514.15Min: 43.51 / Avg: 280.81 / Max: 537.42Min: 18.4 / Avg: 176 / Max: 333.69Min: 21.82 / Avg: 162.41 / Max: 286.89Min: 132.35 / Avg: 365.98 / Max: 540.89

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.6Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPUEPYC 7713 2PEPYC 7713EPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P0.44590.89181.33771.78362.2295SE +/- 0.028672, N = 15SE +/- 0.001820, N = 7SE +/- 0.002404, N = 7SE +/- 0.030182, N = 15SE +/- 0.018656, N = 12SE +/- 0.035324, N = 15SE +/- 0.001800, N = 7SE +/- 0.001212, N = 7SE +/- 0.002389, N = 7SE +/- 0.001346, N = 7SE +/- 0.001008, N = 7SE +/- 0.000899, N = 7SE +/- 0.002765, N = 15SE +/- 0.028000, N = 15SE +/- 0.004588, N = 7SE +/- 0.002218, N = 15SE +/- 0.001500, N = 7SE +/- 0.001154, N = 7SE +/- 0.000753, N = 7SE +/- 0.001485, N = 70.7938241.5957401.5776600.7965950.9338180.7148561.4030601.4999601.9816300.2858200.2811040.3811550.3418061.2984301.6042000.2897080.2820140.2610290.2802371.2275101. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl -lpthread

NAS Parallel Benchmarks

OpenBenchmarking.orgWatts, Fewer Is BetterNAS Parallel Benchmarks 3.4CPU Power Consumption MonitorEPYC 7713 2PEPYC 7713EPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P110220330440550Min: 81.88 / Avg: 294.63 / Max: 451.81Min: 37.98 / Avg: 163.33 / Max: 222.6Min: 36.11 / Avg: 173.06 / Max: 256.08Min: 76.9 / Avg: 308.1 / Max: 520.1Min: 34.59 / Avg: 183.56 / Max: 278.02Min: 75.37 / Avg: 315.78 / Max: 548.53Min: 61.42 / Avg: 214.32 / Max: 277.23Min: 61.16 / Avg: 221.5 / Max: 271.85Min: 112.17 / Avg: 409.49 / Max: 548.23Min: 25.76 / Avg: 167.73 / Max: 292.41Min: 27.18 / Avg: 171.33 / Max: 306.38Min: 50.25 / Avg: 278 / Max: 574.66Min: 52.77 / Avg: 289.69 / Max: 613.7Min: 88.59 / Avg: 338.08 / Max: 546.81Min: 43.25 / Avg: 179.08 / Max: 260.37Min: 41.2 / Avg: 260.06 / Max: 549.34Min: 41.53 / Avg: 265.85 / Max: 569.98Min: 19.73 / Avg: 154.65 / Max: 279.54Min: 21.86 / Avg: 155.36 / Max: 278.04Min: 129.31 / Avg: 412.35 / Max: 564.07

OpenBenchmarking.orgTotal Mop/s Per Watt, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: IS.DEPYC 7713 2PEPYC 7713EPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P71421283516.16816.36315.57215.35115.46116.35710.6119.8957.06229.14628.84427.68027.75913.05414.74829.57030.09631.65731.4006.786

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: IS.DEPYC 7713 2PEPYC 7713EPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P2K4K6K8K10KSE +/- 74.45, N = 15SE +/- 10.18, N = 4SE +/- 15.95, N = 4SE +/- 75.53, N = 15SE +/- 34.33, N = 4SE +/- 42.90, N = 15SE +/- 4.23, N = 3SE +/- 3.06, N = 3SE +/- 12.95, N = 4SE +/- 24.99, N = 5SE +/- 18.47, N = 5SE +/- 138.87, N = 15SE +/- 190.79, N = 15SE +/- 11.17, N = 5SE +/- 28.14, N = 3SE +/- 127.97, N = 15SE +/- 146.90, N = 15SE +/- 8.06, N = 5SE +/- 13.30, N = 5SE +/- 8.39, N = 44763.442672.582695.004729.632838.045165.192274.132191.662891.844888.524941.757694.938041.384413.492641.007690.078001.124895.844878.232798.301. (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 4.1.4

OpenBenchmarking.orgWatts, Fewer Is BetterNAS Parallel Benchmarks 3.4CPU Power Consumption MonitorEPYC 7713 2PEPYC 7713EPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P140280420560700Min: 81.25 / Avg: 371.92 / Max: 461.44Min: 37.61 / Avg: 199.56 / Max: 230.17Min: 35.94 / Avg: 217.35 / Max: 256.47Min: 77.27 / Avg: 396.58 / Max: 518.88Min: 34.18 / Avg: 248.55 / Max: 286.58Min: 74.54 / Avg: 449.43 / Max: 573.91Min: 59.75 / Avg: 245.23 / Max: 290.78Min: 59.44 / Avg: 242.86 / Max: 285.08Min: 111.68 / Avg: 449.71 / Max: 570.3Min: 25.34 / Avg: 237.4 / Max: 323.86Min: 26.16 / Avg: 299.08 / Max: 409.41Min: 51.82 / Avg: 403.27 / Max: 671.24Min: 52.68 / Avg: 493.62 / Max: 819.03Min: 88.75 / Avg: 432.21 / Max: 545.6Min: 42.51 / Avg: 229.99 / Max: 274.73Min: 43.16 / Avg: 423.95 / Max: 660.91Min: 43.17 / Avg: 424.19 / Max: 670.3Min: 21.71 / Avg: 230.79 / Max: 300.9Min: 21.62 / Avg: 236.44 / Max: 317.87Min: 122.48 / Avg: 459.67 / Max: 581.5

OpenBenchmarking.orgTotal Mop/s Per Watt, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: EP.DEPYC 7713 2PEPYC 7713EPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P112233445525.1024.4124.3926.0622.1022.0818.9117.2218.3847.7541.1349.9044.0114.7514.0838.2138.5438.5136.5218.81

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: EP.DEPYC 7713 2PEPYC 7713EPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P5K10K15K20K25KSE +/- 108.23, N = 15SE +/- 5.07, N = 3SE +/- 10.07, N = 3SE +/- 85.20, N = 9SE +/- 35.17, N = 3SE +/- 269.85, N = 15SE +/- 51.61, N = 15SE +/- 58.00, N = 15SE +/- 91.51, N = 3SE +/- 56.69, N = 4SE +/- 324.02, N = 12SE +/- 249.56, N = 15SE +/- 666.94, N = 12SE +/- 66.24, N = 15SE +/- 12.27, N = 3SE +/- 571.15, N = 12SE +/- 406.67, N = 15SE +/- 21.62, N = 4SE +/- 165.09, N = 15SE +/- 114.34, N = 159336.774871.165300.7710333.195491.629921.734636.724181.138264.3611335.9412299.7920121.2321722.656374.823238.9116197.0516347.898887.578634.108647.741. (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 4.1.4

Pennant

OpenBenchmarking.orgWatts, Fewer Is BetterPennant 1.0.1CPU Power Consumption MonitorEPYC 7713 2PEPYC 7713EPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P140280420560700Min: 80.97 / Avg: 258.52 / Max: 460.75Min: 37.71 / Avg: 151.24 / Max: 230.33Min: 35.99 / Avg: 153.97 / Max: 253.07Min: 76.87 / Avg: 259.93 / Max: 497.86Min: 34.44 / Avg: 165.77 / Max: 278.34Min: 41.91 / Avg: 279.27 / Max: 567.9Min: 55.77 / Avg: 218.87 / Max: 290.86Min: 60.1 / Avg: 220.02 / Max: 284.79Min: 107.58 / Avg: 378.32 / Max: 568.51Min: 24.46 / Avg: 158.29 / Max: 316.6Min: 26.62 / Avg: 195.6 / Max: 409.46Min: 50.53 / Avg: 270.65 / Max: 636.18Min: 51.79 / Avg: 307.67 / Max: 818.81Min: 88.76 / Avg: 312.94 / Max: 546.78Min: 42.89 / Avg: 185.1 / Max: 276.13Min: 41.74 / Avg: 247.65 / Max: 622.17Min: 42.46 / Avg: 258.74 / Max: 664.84Min: 19.8 / Avg: 160.33 / Max: 318.28Min: 19.8 / Avg: 156.27 / Max: 311.63Min: 129.69 / Avg: 371.27 / Max: 581.86

OpenBenchmarking.orgHydro Cycle Time - Seconds, Fewer Is BetterPennant 1.0.1Test: leblancbigEPYC 7713 2PEPYC 7713EPYC 7763EPYC 7763 2PEPYC 7773XEPYC 7773X 2PXeon Platinum 8380Xeon Platinum 8362Xeon Platinum 8362 2PEPYC 9654EPYC 9654 - PowerEPYC 9654 2PEPYC 9654 2P - PowerEPYC 75F3 2PEPYC 75F3EPYC 9554 2PEPYC 9554 2P - PowerEPYC 9554 - PowerEPYC 9554Xeon Platinum 8380 2P48121620SE +/- 0.094749, N = 12SE +/- 0.065779, N = 15SE +/- 0.039217, N = 15SE +/- 0.083507, N = 15SE +/- 0.046366, N = 15SE +/- 0.038831, N = 15SE +/- 0.023873, N = 4SE +/- 0.017254, N = 4SE +/- 0.010589, N = 6SE +/- 0.088305, N = 15SE +/- 0.122551, N = 15SE +/- 0.050393, N = 15SE +/- 0.042439, N = 15SE +/- 0.032179, N = 15SE +/- 0.014185, N = 5SE +/- 0.062550, N = 15SE +/- 0.045794, N = 15SE +/- 0.056585, N = 15SE +/- 0.084956, N = 15SE +/- 0.006909, N = 73.6316286.1009385.8128083.4843255.4197123.30057812.00682013.7549406.4883743.7630213.3825162.4222642.1467664.3964258.2772372.3743822.3756193.9191484.0234704.8458151. (CXX) g++ options: -fopenmp -lmpi_cxx -lmpi

210 Results Shown

OpenVINO:
  Vehicle Detection FP16-INT8 - CPU
  Person Vehicle Bike Detection FP16 - CPU
  Face Detection FP16 - CPU
Sysbench
OSPRay
Pennant
LeelaChessZero
Liquid-DSP
Xmrig
OpenVINO
7-Zip Compression
Coremark
OpenVINO:
  Person Detection FP16 - CPU
  Person Detection FP32 - CPU
OpenFOAM
Blender
oneDNN
OSPRay Studio:
  1 - 4K - 16 - Path Tracer
  2 - 4K - 16 - Path Tracer
  3 - 4K - 16 - Path Tracer
C-Ray
NAS Parallel Benchmarks
Blender
m-queens
OSPRay Studio:
  2 - 4K - 32 - Path Tracer
  1 - 4K - 32 - Path Tracer
OpenVINO
Blender
OSPRay
OSPRay Studio
OpenVINO
Neural Magic DeepSparse
OSPRay Studio
Xmrig
Tachyon
Liquid-DSP
OSPRay Studio
OpenVINO
OSPRay Studio
ASTC Encoder
Blender
ACES DGEMM
OpenSSL
Embree
OpenSSL
Blender
Neural Magic DeepSparse
Xcompact3d Incompact3d
ASTC Encoder
RELION
Rodinia
Embree
NAS Parallel Benchmarks:
  EP.C
  BT.C
Embree
Neural Magic DeepSparse
Embree
OpenVINO
Neural Magic DeepSparse
OpenVINO
Neural Magic DeepSparse
NAMD
NAS Parallel Benchmarks
oneDNN
asmFish
oneDNN:
  Deconvolution Batch shapes_3d - f32 - CPU
  Convolution Batch Shapes Auto - f32 - CPU
WRF
Xcompact3d Incompact3d
NAS Parallel Benchmarks
OpenVINO
Timed Linux Kernel Compilation
LuxCoreRender
High Performance Conjugate Gradient
GROMACS
GraphicsMagick
Algebraic Multi-Grid Benchmark
OpenVINO
NAS Parallel Benchmarks
Xcompact3d Incompact3d
OpenVINO
NAS Parallel Benchmarks
ASTC Encoder
7-Zip Compression
OpenFOAM
GPAW
LuxCoreRender
Timed LLVM Compilation
NAS Parallel Benchmarks
GraphicsMagick
PostgreSQL:
  100 - 500 - Read Only - Average Latency
  100 - 500 - Read Only
  100 - 250 - Read Only - Average Latency
Liquid-DSP
PostgreSQL:
  1 - 500 - Read Only
  1 - 500 - Read Only - Average Latency
  100 - 250 - Read Only
  1 - 250 - Read Only
Intel Open Image Denoise
PostgreSQL
Intel Open Image Denoise
WebP2 Image Encode
Intel Open Image Denoise
LULESH
Graph500
OpenVINO
POV-Ray
PJSIP
Graph500
WebP2 Image Encode
Neural Magic DeepSparse
NWChem
Neural Magic DeepSparse
Timed Node.js Compilation
Graph500
Kvazaar
Graph500
Neural Magic DeepSparse:
  NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Synchronous Single-Stream:
    ms/batch
    items/sec
Timed Linux Kernel Compilation
Timed MPlayer Compilation
Neural Magic DeepSparse:
  CV Detection,YOLOv5s COCO - Synchronous Single-Stream:
    ms/batch
    items/sec
OpenRadioss
Neural Magic DeepSparse:
  NLP Token Classification, BERT base uncased conll2003 - Synchronous Single-Stream:
    items/sec
    ms/batch
  NLP Document Classification, oBERT base uncased on IMDB - Synchronous Single-Stream:
    items/sec
    ms/batch
OpenRadioss
Neural Magic DeepSparse:
  NLP Text Classification, DistilBERT mnli - Synchronous Single-Stream:
    items/sec
    ms/batch
  NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Asynchronous Multi-Stream:
    ms/batch
Timed LLVM Compilation
OpenVINO:
  Face Detection FP16 - CPU
  Vehicle Detection FP16 - CPU
BRL-CAD
OpenVINO
oneDNN
OpenVINO
ASKAP
OpenVINO:
  Face Detection FP16-INT8 - CPU
  Machine Translation EN To DE FP16 - CPU
ASKAP
OpenSSL
OpenRadioss
Timed Godot Game Engine Compilation
Neural Magic DeepSparse:
  NLP Text Classification, BERT base uncased SST2 - Synchronous Single-Stream:
    items/sec
    ms/batch
  CV Classification, ResNet-50 ImageNet - Synchronous Single-Stream:
    ms/batch
    items/sec
OpenFOAM:
  drivaerFastback, Small Mesh Size - Mesh Time
  drivaerFastback, Medium Mesh Size - Mesh Time
Etcpak
Timed Gem5 Compilation
simdjson
Neural Magic DeepSparse
simdjson:
  DistinctUserID
  PartialTweets
srsRAN
Node.js Express HTTP Load Test
Neural Magic DeepSparse
Build2
Timed Mesa Compilation
AOM AV1
Neural Magic DeepSparse
OpenRadioss
Numpy Benchmark
Liquid-DSP
PyPerformance
simdjson
AOM AV1
srsRAN
Neural Magic DeepSparse
srsRAN
OpenRadioss
Zstd Compression
AOM AV1
PyPerformance
Zstd Compression
srsRAN
DaCapo Benchmark
Timed Wasmer Compilation
simdjson
srsRAN
PyPerformance
Timed CPython Compilation
srsRAN
PHPBench
PyBench
srsRAN
PyPerformance
QuantLib
Timed CPython Compilation
WebP2 Image Encode:
  CPU Power Consumption Monitor
  Default
WebP2 Image Encode
CPU Power Consumption Monitor:
  Phoronix Test Suite System Monitoring
  CPU Power Consumption Monitor
 
ebizzy
oneDNN
oneDNN
NAS Parallel Benchmarks:
  CPU Power Consumption Monitor
  IS.D
NAS Parallel Benchmarks
NAS Parallel Benchmarks:
  CPU Power Consumption Monitor
  EP.D
NAS Parallel Benchmarks
Pennant
Pennant