AMD EPYC 9684X 2P Genoa-X Benchmarks

Benchmarks by Michael Larabel for a future article for launch day review.

Compare your own system(s) to this result file with the Phoronix Test Suite by running the command: phoronix-test-suite benchmark 2307191-PTS-GENOAX8678
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
Allow Limiting Results To Certain Suite(s)

Statistics

Show Overall Harmonic Mean(s)
Show Overall Geometric Mean
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
Toggle/Hide
Result
Result
Identifier
View Logs
Performance Per
Dollar
Date
Run
  Test
  Duration
EPYC 7773X 2P
July 10 2023
  15 Hours, 44 Minutes
EPYC 9554 2P
June 29 2023
  11 Hours, 42 Minutes
EPYC 9554 2P - Power 400W
June 30 2023
  12 Hours, 8 Minutes
EPYC 9654 2P
June 25 2023
  15 Hours, 45 Minutes
EPYC 9654 2P - Power 400W
June 26 2023
  13 Hours, 30 Minutes
EPYC 9684X 2P
July 02 2023
  11 Hours, 59 Minutes
EPYC 9684X 2P - Power 400W
July 03 2023
  14 Hours, 18 Minutes
EPYC 9754 2P
July 05 2023
  15 Hours, 10 Minutes
EPYC 9754 2P - Power 400W
July 07 2023
  16 Hours, 47 Minutes
Xeon Platinum 8490H 2P
June 23 2023
  10 Hours, 12 Minutes
Xeon Max 9480 2P
June 21 2023
  13 Hours, 2 Minutes
Xeon Max 9480 2P - HBM Only
July 18 2023
  5 Hours, 35 Minutes
Invert Behavior (Only Show Selected Data)
  13 Hours

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 9684X 2P Genoa-X BenchmarksProcessorMotherboardChipsetMemoryDiskGraphicsMonitorNetworkOSKernelDesktopDisplay ServerCompilerFile-SystemScreen ResolutionEPYC 7773X 2PEPYC 9554 2PEPYC 9554 2P - Power 400WEPYC 9654 2PEPYC 9654 2P - Power 400WEPYC 9684X 2PEPYC 9684X 2P - Power 400WEPYC 9754 2PEPYC 9754 2P - Power 400WXeon Platinum 8490H 2PXeon Max 9480 2PXeon Max 9480 2P - HBM Only2 x AMD EPYC 7773X 64-Core @ 2.20GHz (128 Cores / 256 Threads)AMD DAYTONA_X (RYM1009B BIOS)AMD Starship/Matisse512GB3201GB Micron_7450_MTFDKCC3T2TFSASPEEDVE2282 x Mellanox MT27710Ubuntu 23.046.2.0-23-generic (x86_64)GNOME Shell 44.0X Server 1.21.1.7GCC 13.0.1 20230315ext41920x10802 x AMD EPYC 9554 64-Core @ 3.10GHz (128 Cores / 256 Threads)AMD Titanite_4G (RTI1007B BIOS)AMD Device 14a41520GBVGA HDMIBroadcom NetXtreme BCM5720 PCIe2 x AMD EPYC 9654 96-Core @ 2.40GHz (192 Cores / 384 Threads)2 x AMD EPYC 9684X 96-Core @ 2.55GHz (192 Cores / 384 Threads)2 x AMD EPYC 9754 128-Core @ 2.25GHz (256 Cores / 512 Threads)1024x7682 x Intel Xeon Platinum 8490H @ 3.50GHz (120 Cores / 240 Threads)Quanta Cloud S6Q-MB-MPS (3A10.uh BIOS)Intel Device 1bce1008GBVGA HDMI4 x Intel E810-C for QSFP + 2 x Intel X710 for 10GBASE-T1920x10802 x Intel Xeon Max 9480 @ 3.50GHz (112 Cores / 224 Threads)Supermicro X13DEM v1.10 (1.3 BIOS)512GB3201GB Micron_7450_MTFDKCC3T2TFS + 250GB SABRENTVE2282 x Broadcom BCM57508 NetXtreme-E 10Gb/25Gb/40Gb/50Gb/100Gb/200Gb128GB3201GB Micron_7450_MTFDKCC3T2TFSGCC 12.2.0OpenBenchmarking.orgKernel Details- Transparent Huge Pages: madviseCompiler Details- EPYC 7773X 2P: --build=x86_64-linux-gnu --disable-nls --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --enable-checking=yes,extra,rtl --enable-clocale=gnu --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2,rust --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-snapshot-TjSf9o/gcc-snapshot-20230315/debian/tmp-nvptx/usr/lib/gcc-snapshot,amdgcn-amdhsa=/build/gcc-snapshot-TjSf9o/gcc-snapshot-20230315/debian/tmp-gcn/usr/lib/gcc-snapshot --enable-plugin --enable-shared --host=x86_64-linux-gnu --program-prefix= --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --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 -v - EPYC 9554 2P: --build=x86_64-linux-gnu --disable-nls --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --enable-checking=yes,extra,rtl --enable-clocale=gnu --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2,rust --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-snapshot-TjSf9o/gcc-snapshot-20230315/debian/tmp-nvptx/usr/lib/gcc-snapshot,amdgcn-amdhsa=/build/gcc-snapshot-TjSf9o/gcc-snapshot-20230315/debian/tmp-gcn/usr/lib/gcc-snapshot --enable-plugin --enable-shared --host=x86_64-linux-gnu --program-prefix= --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --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 -v - EPYC 9554 2P - Power 400W: --build=x86_64-linux-gnu --disable-nls --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --enable-checking=yes,extra,rtl --enable-clocale=gnu --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2,rust --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-snapshot-TjSf9o/gcc-snapshot-20230315/debian/tmp-nvptx/usr/lib/gcc-snapshot,amdgcn-amdhsa=/build/gcc-snapshot-TjSf9o/gcc-snapshot-20230315/debian/tmp-gcn/usr/lib/gcc-snapshot --enable-plugin --enable-shared --host=x86_64-linux-gnu --program-prefix= --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --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 -v - EPYC 9654 2P: --build=x86_64-linux-gnu --disable-nls --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --enable-checking=yes,extra,rtl --enable-clocale=gnu --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2,rust --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-snapshot-TjSf9o/gcc-snapshot-20230315/debian/tmp-nvptx/usr/lib/gcc-snapshot,amdgcn-amdhsa=/build/gcc-snapshot-TjSf9o/gcc-snapshot-20230315/debian/tmp-gcn/usr/lib/gcc-snapshot --enable-plugin --enable-shared --host=x86_64-linux-gnu --program-prefix= --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --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 -v - EPYC 9654 2P - Power 400W: --build=x86_64-linux-gnu --disable-nls --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --enable-checking=yes,extra,rtl --enable-clocale=gnu --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2,rust --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-snapshot-TjSf9o/gcc-snapshot-20230315/debian/tmp-nvptx/usr/lib/gcc-snapshot,amdgcn-amdhsa=/build/gcc-snapshot-TjSf9o/gcc-snapshot-20230315/debian/tmp-gcn/usr/lib/gcc-snapshot --enable-plugin --enable-shared --host=x86_64-linux-gnu --program-prefix= --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --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 -v - EPYC 9684X 2P: --build=x86_64-linux-gnu --disable-nls --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --enable-checking=yes,extra,rtl --enable-clocale=gnu --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2,rust --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-snapshot-TjSf9o/gcc-snapshot-20230315/debian/tmp-nvptx/usr/lib/gcc-snapshot,amdgcn-amdhsa=/build/gcc-snapshot-TjSf9o/gcc-snapshot-20230315/debian/tmp-gcn/usr/lib/gcc-snapshot --enable-plugin --enable-shared --host=x86_64-linux-gnu --program-prefix= --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --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 -v - EPYC 9684X 2P - Power 400W: --build=x86_64-linux-gnu --disable-nls --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --enable-checking=yes,extra,rtl --enable-clocale=gnu --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2,rust --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-snapshot-TjSf9o/gcc-snapshot-20230315/debian/tmp-nvptx/usr/lib/gcc-snapshot,amdgcn-amdhsa=/build/gcc-snapshot-TjSf9o/gcc-snapshot-20230315/debian/tmp-gcn/usr/lib/gcc-snapshot --enable-plugin --enable-shared --host=x86_64-linux-gnu --program-prefix= --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --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 -v - EPYC 9754 2P: --build=x86_64-linux-gnu --disable-nls --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --enable-checking=yes,extra,rtl --enable-clocale=gnu --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2,rust --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-snapshot-TjSf9o/gcc-snapshot-20230315/debian/tmp-nvptx/usr/lib/gcc-snapshot,amdgcn-amdhsa=/build/gcc-snapshot-TjSf9o/gcc-snapshot-20230315/debian/tmp-gcn/usr/lib/gcc-snapshot --enable-plugin --enable-shared --host=x86_64-linux-gnu --program-prefix= --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --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 -v - EPYC 9754 2P - Power 400W: --build=x86_64-linux-gnu --disable-nls --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --enable-checking=yes,extra,rtl --enable-clocale=gnu --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2,rust --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-snapshot-TjSf9o/gcc-snapshot-20230315/debian/tmp-nvptx/usr/lib/gcc-snapshot,amdgcn-amdhsa=/build/gcc-snapshot-TjSf9o/gcc-snapshot-20230315/debian/tmp-gcn/usr/lib/gcc-snapshot --enable-plugin --enable-shared --host=x86_64-linux-gnu --program-prefix= --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --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 -v - Xeon Platinum 8490H 2P: --build=x86_64-linux-gnu --disable-nls --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --enable-checking=yes,extra,rtl --enable-clocale=gnu --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2,rust --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-snapshot-TjSf9o/gcc-snapshot-20230315/debian/tmp-nvptx/usr/lib/gcc-snapshot,amdgcn-amdhsa=/build/gcc-snapshot-TjSf9o/gcc-snapshot-20230315/debian/tmp-gcn/usr/lib/gcc-snapshot --enable-plugin --enable-shared --host=x86_64-linux-gnu --program-prefix= --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --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 -v - Xeon Max 9480 2P: --build=x86_64-linux-gnu --disable-nls --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --enable-checking=yes,extra,rtl --enable-clocale=gnu --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2,rust --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-snapshot-TjSf9o/gcc-snapshot-20230315/debian/tmp-nvptx/usr/lib/gcc-snapshot,amdgcn-amdhsa=/build/gcc-snapshot-TjSf9o/gcc-snapshot-20230315/debian/tmp-gcn/usr/lib/gcc-snapshot --enable-plugin --enable-shared --host=x86_64-linux-gnu --program-prefix= --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --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 -v - Xeon Max 9480 2P - HBM Only: --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-Pa930Z/gcc-12-12.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-12-Pa930Z/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 -v Processor Details- EPYC 7773X 2P: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa001229- EPYC 9554 2P: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa101121- EPYC 9554 2P - Power 400W: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa101121- EPYC 9654 2P: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa101121- EPYC 9654 2P - Power 400W: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa101121- EPYC 9684X 2P: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa101121- EPYC 9684X 2P - Power 400W: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa101121- EPYC 9754 2P: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xaa0010b- EPYC 9754 2P - Power 400W: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xaa0010b- Xeon Platinum 8490H 2P: Scaling Governor: intel_pstate performance (EPP: performance) - CPU Microcode: 0x2b000181- Xeon Max 9480 2P: Scaling Governor: intel_cpufreq performance - CPU Microcode: 0x2c0001d1- Xeon Max 9480 2P - HBM Only: Scaling Governor: intel_cpufreq performance - CPU Microcode: 0x2c0001d1Python Details- Python 3.11.2Security Details- 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- 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 400W: 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 400W: 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 9684X 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 9684X 2P - Power 400W: 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 9754 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 9754 2P - Power 400W: 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 8490H 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 Enhanced IBRS IBPB: conditional RSB filling PBRSB-eIBRS: SW sequence + srbds: Not affected + tsx_async_abort: Not affected- Xeon Max 9480 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 Enhanced IBRS IBPB: conditional RSB filling PBRSB-eIBRS: SW sequence + srbds: Not affected + tsx_async_abort: Not affected- Xeon Max 9480 2P - HBM Only: 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 Enhanced IBRS IBPB: conditional RSB filling PBRSB-eIBRS: SW sequence + srbds: Not affected + tsx_async_abort: Not affectedJava Details- EPYC 9654 2P, EPYC 9654 2P - Power 400W, Xeon Platinum 8490H 2P, Xeon Max 9480 2P: OpenJDK Runtime Environment (build 11.0.19+7-post-Ubuntu-0ubuntu123.04)

EPYC 7773X 2PEPYC 9554 2PEPYC 9554 2P - Power 400WEPYC 9654 2PEPYC 9654 2P - Power 400WEPYC 9684X 2PEPYC 9684X 2P - Power 400WEPYC 9754 2PEPYC 9754 2P - Power 400WXeon Platinum 8490H 2PXeon Max 9480 2PXeon Max 9480 2P - HBM OnlyResult OverviewPhoronix Test Suite100%231%363%494%625%EmbreePostgreSQLPETScXmrigBlenderOSPRay StudiominiFEsrsRAN ProjectASKAPRELIONHigh Performance Conjugate GradientAlgebraic Multi-Grid BenchmarkKvazaarHeFFTe - Highly Efficient FFT for ExascaleLeelaChessZeroGPAWXcompact3d Incompact3dNAS Parallel BenchmarksTimed Linux Kernel CompilationTimed Godot Game Engine CompilationLiquid-DSPTimed PHP CompilationZ3 Theorem Prover

EPYC 7773X 2PEPYC 9554 2PEPYC 9554 2P - Power 400WEPYC 9654 2PEPYC 9654 2P - Power 400WEPYC 9684X 2PEPYC 9684X 2P - Power 400WEPYC 9754 2PEPYC 9754 2P - Power 400WXeon Platinum 8490H 2PXeon Max 9480 2PXeon Max 9480 2P - HBM OnlyLogarithmic Per Watt Result OverviewPhoronix Test SuiteminiFEXmrigKvazaarHigh Performance Conjugate GradientHeFFTe - Highly Efficient FFT for ExascalePETScASKAPNAS Parallel BenchmarksLeelaChessZerosrsRAN ProjectEmbreeAlgebraic Multi-Grid BenchmarkLiquid-DSPP.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 9684X 2P Genoa-X Benchmarksembree: Pathtracer ISPC - Asian Dragonembree: Pathtracer ISPC - Asian Dragon Objembree: Pathtracer - Asian Dragon Objembree: Pathtracer ISPC - Crownembree: Pathtracer - Asian Dragonxmrig: Wownero - 1Mxmrig: Monero - 1Maskap: tConvolve MPI - Degriddingaskap: tConvolve MPI - Griddingopenvino: Person Vehicle Bike Detection FP16 - CPUblender: Barbershop - CPU-Onlylibxsmm: 32ospray-studio: 3 - 4K - 32 - Path Tracerlibxsmm: 256ospray-studio: 3 - 4K - 1 - Path Tracerospray-studio: 3 - 1080p - 16 - Path Tracerospray-studio: 1 - 1080p - 32 - Path Tracerospray-studio: 1 - 4K - 32 - Path Tracerospray-studio: 3 - 4K - 16 - Path Tracerospray-studio: 3 - 1080p - 32 - Path Tracersrsran: PUSCH Processor Benchmark, Throughput Totalwrf: conus 2.5kmheffte: r2c - FFTW - float - 512heffte: c2c - FFTW - float - 512relion: Basic - CPUopenvino: Vehicle Detection FP16 - CPUhpcg: 104 104 104 - 60kvazaar: Bosphorus 4K - Mediumamg: kvazaar: Bosphorus 4K - Slownpb: SP.Cheffte: r2c - FFTW - double - 512incompact3d: input.i3d 193 Cells Per Directionheffte: c2c - FFTW - double - 512libxsmm: 64heffte: r2c - FFTW - double - 256npb: MG.Copenfoam: drivaerFastback, Medium Mesh Size - Execution Timelibxsmm: 128npb: LU.Clczero: BLASnpb: BT.Cgpaw: Carbon Nanotubeopenvino: Machine Translation EN To DE FP16 - CPUopenvino: Vehicle Detection FP16 - CPUbuild-llvm: Ninjaincompact3d: input.i3d 129 Cells Per Directionbuild-linux-kernel: defconfignpb: CG.Cbuild-godot: Time To Compilebuild-nodejs: Time To Compileliquid-dsp: 224 - 256 - 32openvino: Person Vehicle Bike Detection FP16 - CPUhpcg: 144 144 144 - 60z3: 1.smt2hpcg: 192 192 192 - 60build-php: Time To Compilehpcg: 160 160 160 - 60cp2k: H2O-DFT-LSopenvino: Machine Translation EN To DE FP16 - CPUbuild-llvm: Unix Makefilesz3: 2.smt2pgbench: 100 - 1000 - Read Only - Average Latencypgbench: 100 - 1000 - Read Onlypetsc: Streamsnpb: IS.Dincompact3d: X3D-benchmarking input.i3daskap: tConvolve MT - Degriddingminife: SmallEPYC 7773X 2PEPYC 9554 2PEPYC 9554 2P - Power 400WEPYC 9654 2PEPYC 9654 2P - Power 400WEPYC 9684X 2PEPYC 9684X 2P - Power 400WEPYC 9754 2PEPYC 9754 2P - Power 400WXeon Platinum 8490H 2PXeon Max 9480 2PXeon Max 9480 2P - HBM Only82.728876.189975.2567116.946186.187949842.944133.361441.965262.5136.451387.2420551816.713055276893935271209711055019272.810994.34304.967146.156155.50238.528933.26198854333332.88230772.86125.1089.6258064360.99862479.6149.946124155.94165.256033010.3395342.956388375894.5338.212200.8952.2447532736.67851653.20194.497174.558668473333338.306323.00375.01938.1718417.79474.5650.3402940406247183.49495104.50264.85171511018.4423547.7181.2046154.7801146.6541154.7283163.887099547.583001.560853.972808.34.397.241398.8276624613.5866349858592321013801699429598.05138.985477.755247.150141.4945986.3356.061946.64391191433346.03244961.40235.8334.80414799127.8072672.3305.716233525.20131.275563969.1480255.4211066466102.6922.834780.725.33156.7481.4494534629.49587564.20165.241138.48674614000007429.3354.608226.78654.697666.02753.21192023.48640.94344.01869.0290.2963377813501964.62077725.20209.93499112762.451915.1186.2801159.3917150.4166164.3641168.2334101344.883722.160555.674108.54.2487.961405.8254144973.8795321353712124312717640733145.45060.635480.331249.474140.5156269.7956.471646.75394872253346.19247051.81235.9584.90615211127.4042669.9311.873238244.69127.461754083.5486004.4911285461016.8022.138804.675.09153.6031.4475130528.50886896.70163.309137.12575380666677536.1054.486626.41052.760866.20254.20321999.23939.72343.02768.8440.2923426783491308.08407582.72210.67405215165.252687.4214.5794183.9434174.4107181.7287194.9779128571.3104948.981812.989976.45.2583.291680.9228865695.5716289548581916011419578834984.65333.319555.828278.868120.4357369.2950.660465.99323526900064.99269429.29251.0474.19870104132.0592970.2349.104207828.63109.345924581.2503710.8511144513456.9321.536953.226.50144.8521.3733183228.70684056.04164.591134.41671467333339128.2150.124026.47843.376267.25349.88772355.9450.30342.67370.0720.3053277193498825.92707816.33221.99201112817.655164.1240.4117205.1349195.7776209.1992218.9603139145.3111812.186299.098445.74.9172.941701.8197695980.161324974182165079856499038529.24301.371566.202281.561138.4117969.6347.149566.17287224230865.69272856.60253.7894.19422695133.5173012.0345.253202036.80105.618124939.0517505.9111607556402.9119.8541001.166.01138.0721.3380898627.67986108.56161.276131.19675660000009766.4243.761526.75143.011266.88843.54512009.73747.89341.38970.1140.3083251179440996.49637697.45202.56462711420.453638.5235.3684201.5685190.0161200.9968211.1147121765.6114127.11159131340305.378.835033.4219995848.9686279047141849810948559336154.94229.354728.137388.65598.4757322.6953.051064.60338272446764.22353333.76319.3743.96554245153.3005858.1352.652243282.6794.6398036630.3506243.2811387621820.2722.179938.666.54141.7451.3256056728.53381336.72159.604132.89167359333339040.4451.550321.72749.218165.43050.48261977.28351.07339.45468.0620.2883467303519663.49059151.12172.52589218298.970954.3263.8853226.3855213.4161226.9873236.2182133768.7124603.81268071476154.7971.265468.2193676284.660124524129162259644489241390.83501.107763.648398.27288.4958124.9868.110066.70452654400066.12402805.72322.6363.74949122153.7586224.3361.982233932.0083.8072186972.9562925.8413458727314.5419.3711065.115.90135.2301.1970348827.59787838.87156.152127.865757416666710005.2162.203921.73669.516765.19158.83301653.83545.03333.94668.4260.2933427229502329.42499261.03121.40053812311.066383.1254.8691219.9523210.2346210.7757234.3144141784.688748.358059.161459.56.5570.031493.3184536099.158223623935156229255471719500.15684.005424.729217.098167.7126180.6752.172260.70309198150059.30219855.27206.5594.56930038110.0102828.6229.199249822.83116.159014833.8598185.378483501819.6721.9511163.4510.35152.3701.2803632133.05667108.57196.882150.15464528000009753.6452.775735.10452.005780.49152.60002227.21754.95402.71086.6640.3522847041449040.09229289.82213.55955412273.659986.6259.3375224.0609216.9415222.6037242.5743149757.588765.256000.158015.76.2163.971493.0168396454.452521383582139818387428218353.04962.047426.974220.808171.0797097.4857.214959.28300936723160.37223859.81208.4844.59087753112.1822844.0234.667246501.36115.410275108.1597743.038410508790.7520.7991248.909.01148.7971.2860179933.46466770.55194.909148.601644813333310290.1034.73480.2591935.6451.19402.38686.6930.3562820486402880.36729057.55237.08162215582.459651.0152.4517131.6672113.6990122.4240125.190961567.645711.234833.141871.615.72147.34326451027412168592714816304823317947.36580.632251.569133.919194.1743678.6463.655133.02307632033332.26150552.39128.8196.2397610370.1138159.797167917.37192.29532263499.1011087335827.1930.860692.558.14205.4351.7077232135.95958253.89200.214174.72756626333337617.0761.650421.71661.330374.27861.08642454.14743.11395.68086.5421.358772029382936.00683643.82193.82065816676.740387.739.218134.351234.744137.202141.157531710.228561.929155.134120.217.98256.1266114183273751218947356283821427012708.86866.03289.918165.383251.3792888.0585.676424.32328741980024.27176292.33154.3466.2751565883.1382177.072238922.48196.5745273751.975935322599.6943.438586.509.67256.9211.8250832451.09948170.79231.605218.17644888333336216.0154.732927.66980.21447.694547.66458.50686.5621.594637417822547.78092867.34157.25834711840.9520503.949.275444.514146.809254.785751.097139637.235445.838003.046113.014.60199.264437314015675915136859223891124217844.3415.333227.698169.3193607.03105.90427.46543855820026.69244889.16221.0624.45004143115.197241.480291332.66305114.308193407912.9130.513688.497.741.3508441033.08661740.12134.86952763333337652.3126.98349.82040.6085.9381.5596531931244507.93953976.14104.39184312870.823471.2OpenBenchmarking.org

Embree

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

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 4.1Binary: Pathtracer ISPC - Model: Asian DragonXeon Max 9480 2PXeon Max 9480 2P - HBM OnlyEPYC 7773X 2PXeon Platinum 8490H 2PEPYC 9554 2PEPYC 9554 2P - Power 400WEPYC 9654 2PEPYC 9684X 2PEPYC 9654 2P - Power 400WEPYC 9754 2PEPYC 9754 2P - Power 400WEPYC 9684X 2P - Power 400W60120180240300SE +/- 0.50, N = 15SE +/- 1.11, N = 15SE +/- 0.73, N = 15SE +/- 0.13, N = 7SE +/- 0.16, N = 8SE +/- 0.26, N = 8SE +/- 0.15, N = 9SE +/- 0.20, N = 9SE +/- 0.46, N = 9SE +/- 0.22, N = 9SE +/- 0.34, N = 9SE +/- 0.27, N = 939.2249.2882.73152.45181.20186.28214.58235.37240.41254.87259.34263.89MIN: 31.86 / MAX: 52.05MIN: 38.54 / MAX: 66.72MIN: 78.27 / MAX: 91.35MIN: 143.51 / MAX: 169.52MIN: 177.59 / MAX: 186.4MIN: 182.05 / MAX: 191.35MIN: 209.56 / MAX: 234.63MIN: 226.19 / MAX: 254.26MIN: 233.48 / MAX: 250.75MIN: 248.76 / MAX: 264.19MIN: 253.29 / MAX: 268.38MIN: 255.55 / MAX: 279.17

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 4.1Binary: Pathtracer ISPC - Model: Asian Dragon ObjXeon Max 9480 2PXeon Max 9480 2P - HBM OnlyEPYC 7773X 2PXeon Platinum 8490H 2PEPYC 9554 2PEPYC 9554 2P - Power 400WEPYC 9654 2PEPYC 9684X 2PEPYC 9654 2P - Power 400WEPYC 9754 2PEPYC 9754 2P - Power 400WEPYC 9684X 2P - Power 400W50100150200250SE +/- 0.57, N = 15SE +/- 0.51, N = 4SE +/- 0.83, N = 5SE +/- 0.11, N = 4SE +/- 0.19, N = 4SE +/- 0.11, N = 4SE +/- 0.11, N = 4SE +/- 0.27, N = 4SE +/- 0.49, N = 4SE +/- 0.83, N = 4SE +/- 0.20, N = 4SE +/- 0.32, N = 434.3544.5176.19131.67154.78159.39183.94201.57205.13219.95224.06226.39MIN: 29.4 / MAX: 42.83MIN: 40.22 / MAX: 54.34MIN: 70.47 / MAX: 79.79MIN: 124.39 / MAX: 148.04MIN: 151.58 / MAX: 158.56MIN: 156.35 / MAX: 163.43MIN: 179.63 / MAX: 191.54MIN: 194.63 / MAX: 213.18MIN: 199.72 / MAX: 212.77MIN: 214.08 / MAX: 228.41MIN: 218.19 / MAX: 231.32MIN: 220.31 / MAX: 235.74

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 4.1Binary: Pathtracer - Model: Asian Dragon ObjXeon Max 9480 2PXeon Max 9480 2P - HBM OnlyEPYC 7773X 2PXeon Platinum 8490H 2PEPYC 9554 2PEPYC 9554 2P - Power 400WEPYC 9654 2PEPYC 9684X 2PEPYC 9654 2P - Power 400WEPYC 9754 2PEPYC 9684X 2P - Power 400WEPYC 9754 2P - Power 400W50100150200250SE +/- 0.96, N = 12SE +/- 0.53, N = 14SE +/- 0.80, N = 4SE +/- 0.07, N = 3SE +/- 0.04, N = 4SE +/- 0.18, N = 4SE +/- 0.14, N = 4SE +/- 0.29, N = 4SE +/- 0.26, N = 4SE +/- 0.34, N = 4SE +/- 0.48, N = 4SE +/- 0.29, N = 434.7446.8175.26113.70146.65150.42174.41190.02195.78210.23213.42216.94MIN: 22.21 / MAX: 43.5MIN: 37.84 / MAX: 61.44MIN: 71.65 / MAX: 81.93MIN: 108.15 / MAX: 125.27MIN: 143.95 / MAX: 150.69MIN: 147.39 / MAX: 154.08MIN: 169.81 / MAX: 184.57MIN: 184.37 / MAX: 203.08MIN: 190.15 / MAX: 203.08MIN: 204.67 / MAX: 217.34MIN: 206.23 / MAX: 226.5MIN: 211.37 / MAX: 224.16

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 4.1Binary: Pathtracer ISPC - Model: CrownXeon Max 9480 2PXeon Max 9480 2P - HBM OnlyEPYC 7773X 2PXeon Platinum 8490H 2PEPYC 9554 2PEPYC 9554 2P - Power 400WEPYC 9654 2PEPYC 9684X 2PEPYC 9654 2P - Power 400WEPYC 9754 2PEPYC 9754 2P - Power 400WEPYC 9684X 2P - Power 400W50100150200250SE +/- 1.26, N = 15SE +/- 1.19, N = 12SE +/- 0.17, N = 7SE +/- 0.20, N = 7SE +/- 0.08, N = 8SE +/- 0.19, N = 8SE +/- 0.11, N = 8SE +/- 0.18, N = 9SE +/- 0.23, N = 9SE +/- 0.31, N = 9SE +/- 0.12, N = 9SE +/- 0.19, N = 937.2054.79116.95122.42154.73164.36181.73201.00209.20210.78222.60226.99MIN: 22.99 / MAX: 56.2MIN: 41.82 / MAX: 69.08MIN: 113.56 / MAX: 128.62MIN: 111.51 / MAX: 143.43MIN: 150.38 / MAX: 160.93MIN: 159.69 / MAX: 170.15MIN: 175.35 / MAX: 197.9MIN: 190.76 / MAX: 224.67MIN: 200.36 / MAX: 225.27MIN: 203.95 / MAX: 223.57MIN: 215.48 / MAX: 232.87MIN: 218.44 / MAX: 251.82

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 4.1Binary: Pathtracer - Model: Asian DragonXeon Max 9480 2PXeon Max 9480 2P - HBM OnlyEPYC 7773X 2PXeon Platinum 8490H 2PEPYC 9554 2PEPYC 9554 2P - Power 400WEPYC 9654 2PEPYC 9684X 2PEPYC 9654 2P - Power 400WEPYC 9754 2PEPYC 9684X 2P - Power 400WEPYC 9754 2P - Power 400W50100150200250SE +/- 0.48, N = 3SE +/- 1.00, N = 15SE +/- 0.59, N = 5SE +/- 0.10, N = 6SE +/- 0.10, N = 8SE +/- 0.11, N = 8SE +/- 0.14, N = 8SE +/- 0.13, N = 9SE +/- 0.32, N = 9SE +/- 0.14, N = 9SE +/- 0.69, N = 9SE +/- 0.25, N = 941.1651.1086.19125.19163.89168.23194.98211.11218.96234.31236.22242.57MIN: 32.84 / MAX: 50.78MIN: 31.18 / MAX: 62.95MIN: 83.85 / MAX: 93.75MIN: 118.36 / MAX: 139.42MIN: 160.98 / MAX: 167.95MIN: 164.94 / MAX: 172.86MIN: 189.75 / MAX: 208.29MIN: 204.92 / MAX: 236.13MIN: 212.81 / MAX: 228.98MIN: 228.93 / MAX: 241.96MIN: 225.48 / MAX: 250.95MIN: 236.63 / MAX: 250.57

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 6.18.1Variant: Wownero - Hash Count: 1MXeon Max 9480 2PXeon Max 9480 2P - HBM OnlyEPYC 7773X 2PXeon Platinum 8490H 2PEPYC 9554 2PEPYC 9554 2P - Power 400WEPYC 9684X 2PEPYC 9654 2PEPYC 9684X 2P - Power 400WEPYC 9654 2P - Power 400WEPYC 9754 2PEPYC 9754 2P - Power 400W30K60K90K120K150KSE +/- 482.03, N = 15SE +/- 377.68, N = 3SE +/- 133.62, N = 3SE +/- 48.49, N = 3SE +/- 312.03, N = 4SE +/- 480.63, N = 5SE +/- 369.71, N = 5SE +/- 335.56, N = 5SE +/- 498.64, N = 5SE +/- 212.19, N = 5SE +/- 564.86, N = 5SE +/- 888.75, N = 531710.239637.249842.961567.699547.5101344.8121765.6128571.3133768.7139145.3141784.6149757.51. (CXX) g++ options: -fexceptions -fno-rtti -maes -O3 -Ofast -static-libgcc -static-libstdc++ -rdynamic -lssl -lcrypto -luv -lpthread -lrt -ldl -lhwloc

OpenBenchmarking.orgH/s, More Is BetterXmrig 6.18.1Variant: Monero - Hash Count: 1MXeon Max 9480 2PXeon Max 9480 2P - HBM OnlyEPYC 7773X 2PXeon Platinum 8490H 2PEPYC 9554 2PEPYC 9554 2P - Power 400WEPYC 9754 2PEPYC 9754 2P - Power 400WEPYC 9654 2PEPYC 9654 2P - Power 400WEPYC 9684X 2PEPYC 9684X 2P - Power 400W30K60K90K120K150KSE +/- 281.65, N = 15SE +/- 361.95, N = 15SE +/- 270.91, N = 3SE +/- 267.77, N = 3SE +/- 72.30, N = 4SE +/- 204.25, N = 4SE +/- 204.62, N = 4SE +/- 692.90, N = 4SE +/- 213.17, N = 5SE +/- 101.12, N = 5SE +/- 124.19, N = 5SE +/- 279.20, N = 528561.935445.844133.345711.283001.583722.188748.388765.2104948.9111812.1114127.1124603.81. (CXX) g++ options: -fexceptions -fno-rtti -maes -O3 -Ofast -static-libgcc -static-libstdc++ -rdynamic -lssl -lcrypto -luv -lpthread -lrt -ldl -lhwloc

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 - DegriddingXeon Max 9480 2PXeon Platinum 8490H 2PXeon Max 9480 2P - HBM OnlyEPYC 9754 2P - Power 400WEPYC 9754 2PEPYC 9554 2P - Power 400WEPYC 9554 2PEPYC 7773X 2PEPYC 9654 2PEPYC 9654 2P - Power 400WEPYC 9684X 2PEPYC 9684X 2P - Power 400W30K60K90K120K150KSE +/- 0.00, N = 3SE +/- 178.00, N = 3SE +/- 131.50, N = 3SE +/- 945.08, N = 15SE +/- 748.64, N = 15SE +/- 289.77, N = 3SE +/- 509.24, N = 3SE +/- 298.23, N = 3SE +/- 1048.90, N = 3SE +/- 1166.20, N = 3SE +/- 706.67, N = 3SE +/- 856.67, N = 329155.134833.138003.056000.158059.160555.660853.961441.981812.986299.0115913.0126807.01. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp

OpenBenchmarking.orgMpix/sec, More Is BetterASKAP 1.0Test: tConvolve MPI - GriddingXeon Max 9480 2PXeon Platinum 8490H 2PXeon Max 9480 2P - HBM OnlyEPYC 9754 2P - Power 400WEPYC 9754 2PEPYC 7773X 2PEPYC 9554 2PEPYC 9554 2P - Power 400WEPYC 9654 2PEPYC 9654 2P - Power 400WEPYC 9684X 2PEPYC 9684X 2P - Power 400W30K60K90K120K150KSE +/- 105.97, N = 3SE +/- 0.00, N = 3SE +/- 193.77, N = 3SE +/- 977.32, N = 15SE +/- 804.21, N = 15SE +/- 336.40, N = 3SE +/- 423.30, N = 3SE +/- 861.73, N = 3SE +/- 742.18, N = 3SE +/- 1514.53, N = 3SE +/- 1646.73, N = 3SE +/- 1162.33, N = 334120.241871.646113.058015.761459.565262.572808.374108.589976.498445.7134030.0147615.01. (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.orgms, Fewer Is BetterOpenVINO 2022.3Model: Person Vehicle Bike Detection FP16 - Device: CPUXeon Max 9480 2PXeon Platinum 8490H 2PXeon Max 9480 2P - HBM OnlyEPYC 9754 2PEPYC 9754 2P - Power 400WEPYC 9684X 2PEPYC 9654 2PEPYC 9654 2P - Power 400WEPYC 9684X 2P - Power 400WEPYC 9554 2PEPYC 9554 2P - Power 400W48121620SE +/- 0.09, 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 +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 317.9815.7214.606.556.215.305.254.914.794.304.24MIN: 12.98 / MAX: 146.53MIN: 12.18 / MAX: 76.76MIN: 12.54 / MAX: 125.98MIN: 5.82 / MAX: 56.8MIN: 5.67 / MAX: 53.74MIN: 4.47 / MAX: 37.31MIN: 4.36 / MAX: 36.19MIN: 4.36 / MAX: 20.8MIN: 4.34 / MAX: 21.51MIN: 4.13 / MAX: 22.63MIN: 4.09 / MAX: 21.931. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -msse4.1 -msse4.2 -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -Os -std=c++11 -MD -MT -MF

Blender

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

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 3.5Blend File: Barbershop - Compute: CPU-OnlyXeon Max 9480 2PXeon Max 9480 2P - HBM OnlyXeon Platinum 8490H 2PEPYC 7773X 2PEPYC 9554 2PEPYC 9554 2P - Power 400WEPYC 9654 2PEPYC 9684X 2PEPYC 9654 2P - Power 400WEPYC 9684X 2P - Power 400WEPYC 9754 2PEPYC 9754 2P - Power 400W60120180240300SE +/- 0.56, N = 3SE +/- 0.75, N = 3SE +/- 0.19, N = 3SE +/- 0.10, N = 3SE +/- 0.22, N = 3SE +/- 0.34, N = 3SE +/- 0.09, N = 3SE +/- 0.10, N = 3SE +/- 0.15, N = 3SE +/- 0.20, N = 3SE +/- 0.15, N = 3SE +/- 0.36, N = 3256.12199.26147.34136.4597.2487.9683.2978.8372.9471.2670.0363.97

libxsmm

Libxsmm is an open-source library for specialized dense and sparse matrix operations and deep learning primitives. Libxsmm supports making use of Intel AMX, AVX-512, and other modern CPU instruction set capabilities. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGFLOPS/s, More Is Betterlibxsmm 2-1.17-3645M N K: 32EPYC 7773X 2PEPYC 9554 2PEPYC 9554 2P - Power 400WEPYC 9754 2P - Power 400WEPYC 9754 2PEPYC 9654 2PEPYC 9654 2P - Power 400WEPYC 9684X 2PEPYC 9684X 2P - Power 400W12002400360048006000SE +/- 13.04, N = 15SE +/- 3.15, N = 7SE +/- 5.81, N = 8SE +/- 8.71, N = 8SE +/- 6.12, N = 8SE +/- 12.77, N = 8SE +/- 10.47, N = 8SE +/- 46.29, N = 15SE +/- 33.74, N = 121387.21398.81405.81493.01493.31680.91701.85033.45468.21. (CXX) g++ options: -dynamic -Bstatic -static-libgcc -lgomp -lm -lrt -ldl -lquadmath -lstdc++ -pthread -fPIC -std=c++14 -O2 -fopenmp-simd -funroll-loops -ftree-vectorize -fdata-sections -ffunction-sections -fvisibility=hidden -msse4.2

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 TracerXeon Max 9480 2PXeon Max 9480 2P - HBM OnlyEPYC 7773X 2PXeon Platinum 8490H 2PEPYC 9554 2PEPYC 9554 2P - Power 400WEPYC 9654 2PEPYC 9684X 2PEPYC 9654 2P - Power 400WEPYC 9684X 2P - Power 400WEPYC 9754 2PEPYC 9754 2P - Power 400W14K28K42K56K70KSE +/- 994.84, N = 15SE +/- 195.26, N = 3SE +/- 91.34, N = 3SE +/- 7.33, N = 3SE +/- 27.00, N = 3SE +/- 29.02, N = 3SE +/- 41.28, N = 3SE +/- 49.95, N = 3SE +/- 49.64, N = 3SE +/- 78.15, N = 3SE +/- 10.68, N = 3SE +/- 79.68, N = 36611444373420553264527662254142288621999197691936718453168391. (CXX) g++ options: -O3 -lm -ldl

libxsmm

Libxsmm is an open-source library for specialized dense and sparse matrix operations and deep learning primitives. Libxsmm supports making use of Intel AMX, AVX-512, and other modern CPU instruction set capabilities. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGFLOPS/s, More Is Betterlibxsmm 2-1.17-3645M N K: 256EPYC 7773X 2PEPYC 9554 2PEPYC 9554 2P - Power 400WEPYC 9654 2PEPYC 9684X 2PEPYC 9654 2P - Power 400WEPYC 9754 2PEPYC 9684X 2P - Power 400WEPYC 9754 2P - Power 400W14002800420056007000SE +/- 52.36, N = 9SE +/- 32.54, N = 3SE +/- 37.23, N = 3SE +/- 18.19, N = 3SE +/- 36.52, N = 3SE +/- 40.29, N = 3SE +/- 25.31, N = 3SE +/- 11.49, N = 3SE +/- 28.63, N = 31816.74613.54973.85695.55848.95980.16099.16284.66454.41. (CXX) g++ options: -dynamic -Bstatic -static-libgcc -lgomp -lm -lrt -ldl -lquadmath -lstdc++ -pthread -fPIC -std=c++14 -O2 -fopenmp-simd -funroll-loops -ftree-vectorize -fdata-sections -ffunction-sections -fvisibility=hidden -msse4.2

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 TracerXeon Max 9480 2PXeon Max 9480 2P - HBM OnlyEPYC 7773X 2PXeon Platinum 8490H 2PEPYC 9554 2PEPYC 9554 2P - Power 400WEPYC 9654 2PEPYC 9684X 2PEPYC 9654 2P - Power 400WEPYC 9684X 2P - Power 400WEPYC 9754 2PEPYC 9754 2P - Power 400W400800120016002000SE +/- 19.22, N = 3SE +/- 3.21, N = 3SE +/- 1.76, N = 3SE +/- 1.20, N = 3SE +/- 1.20, N = 3SE +/- 1.00, N = 3SE +/- 1.33, N = 3SE +/- 1.00, N = 3SE +/- 0.33, N = 3SE +/- 1.45, N = 3SE +/- 2.19, N = 3SE +/- 1.45, N = 318321401130510278667957166866136015825251. (CXX) g++ options: -O3 -lm -ldl

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.11Camera: 3 - Resolution: 1080p - Samples Per Pixel: 16 - Renderer: Path TracerXeon Max 9480 2PXeon Max 9480 2P - HBM OnlyEPYC 7773X 2PXeon Platinum 8490H 2PEPYC 9554 2PEPYC 9554 2P - Power 400WEPYC 9654 2PEPYC 9684X 2PEPYC 9654 2P - Power 400WEPYC 9684X 2P - Power 400WEPYC 9754 2PEPYC 9754 2P - Power 400W16003200480064008000SE +/- 71.33, N = 6SE +/- 26.30, N = 3SE +/- 8.33, N = 3SE +/- 1.20, N = 3SE +/- 1.73, N = 3SE +/- 1.86, N = 3SE +/- 2.00, N = 3SE +/- 3.79, N = 3SE +/- 3.84, N = 3SE +/- 4.58, N = 3SE +/- 2.85, N = 3SE +/- 0.88, N = 37375567552764121349832132895279024972452236221381. (CXX) g++ options: -O3 -lm -ldl

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.11Camera: 1 - Resolution: 1080p - Samples Per Pixel: 32 - Renderer: Path TracerXeon Max 9480 2PXeon Max 9480 2P - HBM OnlyEPYC 7773X 2PXeon Platinum 8490H 2PEPYC 9554 2PEPYC 9554 2P - Power 400WEPYC 9654 2PEPYC 9684X 2PEPYC 9654 2P - Power 400WEPYC 9684X 2P - Power 400WEPYC 9754 2PEPYC 9754 2P - Power 400W3K6K9K12K15KSE +/- 86.30, N = 3SE +/- 28.50, N = 3SE +/- 5.86, N = 3SE +/- 2.52, N = 3SE +/- 0.58, N = 3SE +/- 11.86, N = 3SE +/- 6.17, N = 3SE +/- 7.54, N = 3SE +/- 8.37, N = 3SE +/- 5.29, N = 3SE +/- 5.33, N = 3SE +/- 9.53, N = 312189915189396859585953714858471441824129393535821. (CXX) g++ options: -O3 -lm -ldl

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.11Camera: 1 - Resolution: 4K - Samples Per Pixel: 32 - Renderer: Path TracerXeon Max 9480 2PXeon Max 9480 2P - HBM OnlyEPYC 7773X 2PXeon Platinum 8490H 2PEPYC 9554 2PEPYC 9554 2P - Power 400WEPYC 9654 2PEPYC 9684X 2PEPYC 9654 2P - Power 400WEPYC 9684X 2P - Power 400WEPYC 9754 2PEPYC 9754 2P - Power 400W10K20K30K40K50KSE +/- 463.52, N = 12SE +/- 341.99, N = 3SE +/- 65.46, N = 3SE +/- 24.36, N = 3SE +/- 19.66, N = 3SE +/- 76.08, N = 3SE +/- 51.19, N = 3SE +/- 41.06, N = 3SE +/- 16.56, N = 3SE +/- 22.62, N = 3SE +/- 74.17, N = 3SE +/- 13.78, N = 34735636859352712714823210212431916018498165071622515622139811. (CXX) g++ options: -O3 -lm -ldl

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.11Camera: 3 - Resolution: 4K - Samples Per Pixel: 16 - Renderer: Path TracerXeon Max 9480 2PXeon Max 9480 2P - HBM OnlyEPYC 7773X 2PXeon Platinum 8490H 2PEPYC 9554 2PEPYC 9554 2P - Power 400WEPYC 9654 2PEPYC 9684X 2PEPYC 9654 2P - Power 400WEPYC 9684X 2P - Power 400WEPYC 9754 2PEPYC 9754 2P - Power 400W6K12K18K24K30KSE +/- 206.17, N = 3SE +/- 125.01, N = 3SE +/- 14.40, N = 3SE +/- 14.31, N = 3SE +/- 9.49, N = 3SE +/- 15.51, N = 3SE +/- 26.18, N = 3SE +/- 10.84, N = 3SE +/- 24.50, N = 3SE +/- 33.01, N = 3SE +/- 21.07, N = 3SE +/- 33.71, N = 3283822238920971163041380112717114191094898569644925583871. (CXX) g++ options: -O3 -lm -ldl

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.11Camera: 3 - Resolution: 1080p - Samples Per Pixel: 32 - Renderer: Path TracerXeon Max 9480 2PXeon Max 9480 2P - HBM OnlyEPYC 7773X 2PXeon Platinum 8490H 2PEPYC 9554 2PEPYC 9554 2P - Power 400WEPYC 9654 2PEPYC 9684X 2PEPYC 9654 2P - Power 400WEPYC 9684X 2P - Power 400WEPYC 9754 2PEPYC 9754 2P - Power 400W3K6K9K12K15KSE +/- 171.24, N = 3SE +/- 110.33, N = 3SE +/- 4.26, N = 3SE +/- 6.44, N = 3SE +/- 2.33, N = 3SE +/- 12.77, N = 3SE +/- 3.84, N = 3SE +/- 13.53, N = 3SE +/- 5.33, N = 3SE +/- 9.77, N = 3SE +/- 9.40, N = 3SE +/- 4.41, N = 31427011242105508233699464075788559349904892471742821. (CXX) g++ options: -O3 -lm -ldl

srsRAN Project

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

OpenBenchmarking.orgMbps, More Is BettersrsRAN Project 23.5Test: PUSCH Processor Benchmark, Throughput TotalXeon Max 9480 2PXeon Max 9480 2P - HBM OnlyXeon Platinum 8490H 2PEPYC 9754 2P - Power 400WEPYC 7773X 2PEPYC 9754 2PEPYC 9554 2PEPYC 9554 2P - Power 400WEPYC 9654 2PEPYC 9684X 2PEPYC 9654 2P - Power 400WEPYC 9684X 2P - Power 400W9K18K27K36K45KSE +/- 111.48, N = 7SE +/- 136.59, N = 3SE +/- 24.34, N = 3SE +/- 1298.75, N = 15SE +/- 16.49, N = 3SE +/- 1383.46, N = 15SE +/- 30.08, N = 3SE +/- 36.60, N = 3SE +/- 194.46, N = 3SE +/- 89.99, N = 3SE +/- 186.41, N = 3SE +/- 66.52, N = 312708.817844.317947.318353.019272.819500.129598.033145.434984.636154.938529.241390.81. (CXX) g++ options: -march=native -mfma -O3 -fno-trapping-math -fno-math-errno -lgtest

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 7773X 2PXeon Max 9480 2PXeon Platinum 8490H 2PEPYC 9754 2PEPYC 9654 2PEPYC 9554 2PEPYC 9554 2P - Power 400WEPYC 9754 2P - Power 400WEPYC 9654 2P - Power 400WEPYC 9684X 2PEPYC 9684X 2P - Power 400W2K4K6K8K10K10994.346866.036580.635684.015333.325138.995060.644962.054301.374229.353501.111. (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

HeFFTe - Highly Efficient FFT for Exascale

HeFFTe is the Highly Efficient FFT for Exascale software developed as part of the Exascale Computing Project. This test profile uses HeFFTe's built-in speed benchmarks under a variety of configuration options and currently catering to CPU/processor testing. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGFLOP/s, More Is BetterHeFFTe - Highly Efficient FFT for Exascale 2.3Test: r2c - Backend: FFTW - Precision: float - X Y Z: 512Xeon Platinum 8490H 2PXeon Max 9480 2PEPYC 7773X 2PXeon Max 9480 2P - HBM OnlyEPYC 9754 2PEPYC 9754 2P - Power 400WEPYC 9554 2PEPYC 9554 2P - Power 400WEPYC 9654 2PEPYC 9654 2P - Power 400WEPYC 9684X 2PEPYC 9684X 2P - Power 400W160320480640800SE +/- 0.48, N = 5SE +/- 3.18, N = 15SE +/- 0.38, N = 6SE +/- 6.55, N = 15SE +/- 1.85, N = 7SE +/- 1.06, N = 7SE +/- 1.93, N = 7SE +/- 3.25, N = 7SE +/- 3.25, N = 8SE +/- 2.70, N = 8SE +/- 4.79, N = 8SE +/- 4.08, N = 9251.57289.92304.97415.33424.73426.97477.76480.33555.83566.20728.14763.651. (CXX) g++ options: -O3

OpenBenchmarking.orgGFLOP/s, More Is BetterHeFFTe - Highly Efficient FFT for Exascale 2.3Test: c2c - Backend: FFTW - Precision: float - X Y Z: 512Xeon Platinum 8490H 2PEPYC 7773X 2PXeon Max 9480 2PEPYC 9754 2PEPYC 9754 2P - Power 400WXeon Max 9480 2P - HBM OnlyEPYC 9554 2PEPYC 9554 2P - Power 400WEPYC 9654 2PEPYC 9654 2P - Power 400WEPYC 9684X 2PEPYC 9684X 2P - Power 400W90180270360450SE +/- 0.40, N = 4SE +/- 1.32, N = 4SE +/- 1.96, N = 4SE +/- 1.41, N = 5SE +/- 1.16, N = 5SE +/- 1.58, N = 13SE +/- 1.99, N = 5SE +/- 1.21, N = 5SE +/- 1.04, N = 6SE +/- 1.26, N = 6SE +/- 2.14, N = 7SE +/- 1.84, N = 7133.92146.16165.38217.10220.81227.70247.15249.47278.87281.56388.66398.271. (CXX) g++ options: -O3

RELION

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

OpenBenchmarking.orgSeconds, Fewer Is BetterRELION 4.0.1Test: Basic - Device: CPUXeon Max 9480 2PXeon Platinum 8490H 2PEPYC 9754 2P - Power 400WXeon Max 9480 2P - HBM OnlyEPYC 9754 2PEPYC 7773X 2PEPYC 9554 2PEPYC 9554 2P - Power 400WEPYC 9654 2P - Power 400WEPYC 9654 2PEPYC 9684X 2PEPYC 9684X 2P - Power 400W50100150200250SE +/- 1.06, N = 3SE +/- 3.19, N = 12SE +/- 5.96, N = 12SE +/- 2.20, N = 3SE +/- 4.04, N = 12SE +/- 2.23, N = 3SE +/- 2.02, N = 3SE +/- 1.64, N = 12SE +/- 3.12, N = 12SE +/- 1.05, N = 3SE +/- 1.08, N = 15SE +/- 0.64, N = 15251.38194.17171.08169.32167.71155.50141.49140.52138.41120.4498.4888.501. (CXX) g++ options: -fopenmp -std=c++11 -O3 -rdynamic -ldl -ltiff -lfftw3f -lfftw3 -lpng -ljpeg -lmpi_cxx -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 2022.3Model: Vehicle Detection FP16 - Device: CPUXeon Max 9480 2PXeon Max 9480 2P - HBM OnlyXeon Platinum 8490H 2PEPYC 9554 2PEPYC 9754 2PEPYC 9554 2P - Power 400WEPYC 9754 2P - Power 400WEPYC 9684X 2PEPYC 9654 2PEPYC 9654 2P - Power 400WEPYC 9684X 2P - Power 400W2K4K6K8K10KSE +/- 5.45, N = 3SE +/- 4.09, N = 3SE +/- 1.48, N = 3SE +/- 4.41, N = 3SE +/- 59.43, N = 15SE +/- 4.86, N = 3SE +/- 6.01, N = 3SE +/- 1.84, N = 3SE +/- 9.27, N = 3SE +/- 0.73, N = 3SE +/- 4.86, N = 32888.053607.033678.645986.336180.676269.797097.487322.697369.297969.638124.981. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -msse4.1 -msse4.2 -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -Os -std=c++11 -MD -MT -MF

High Performance Conjugate Gradient

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

OpenBenchmarking.orgGFLOP/s, More Is BetterHigh Performance Conjugate Gradient 3.1X Y Z: 104 104 104 - RT: 60EPYC 7773X 2PEPYC 9654 2P - Power 400WEPYC 9654 2PEPYC 9754 2PEPYC 9684X 2PEPYC 9554 2PEPYC 9554 2P - Power 400WEPYC 9754 2P - Power 400WXeon Platinum 8490H 2PEPYC 9684X 2P - Power 400WXeon Max 9480 2PXeon Max 9480 2P - HBM Only20406080100SE +/- 0.01, N = 3SE +/- 0.38, N = 9SE +/- 0.70, N = 3SE +/- 0.47, N = 3SE +/- 0.16, N = 3SE +/- 0.40, N = 12SE +/- 0.95, N = 12SE +/- 0.14, N = 3SE +/- 0.75, N = 9SE +/- 0.52, N = 3SE +/- 1.53, N = 1238.5347.1550.6652.1753.0556.0656.4757.2163.6668.1185.68105.901. (CXX) g++ options: -O3 -ffast-math -ftree-vectorize -lmpi_cxx -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 2.2Video Input: Bosphorus 4K - Video Preset: MediumXeon Max 9480 2PXeon Max 9480 2P - HBM OnlyXeon Platinum 8490H 2PEPYC 7773X 2PEPYC 9554 2PEPYC 9554 2P - Power 400WEPYC 9754 2P - Power 400WEPYC 9754 2PEPYC 9684X 2PEPYC 9654 2PEPYC 9654 2P - Power 400WEPYC 9684X 2P - Power 400W1530456075SE +/- 0.52, N = 15SE +/- 0.10, N = 3SE +/- 0.14, N = 3SE +/- 0.21, N = 3SE +/- 0.08, N = 4SE +/- 0.08, N = 4SE +/- 0.57, N = 15SE +/- 0.65, N = 5SE +/- 0.32, N = 5SE +/- 0.26, N = 5SE +/- 0.18, N = 5SE +/- 0.14, N = 524.3227.4633.0233.2646.6446.7559.2860.7064.6065.9966.1766.701. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt

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 7773X 2PEPYC 9654 2P - Power 400WEPYC 9754 2P - Power 400WXeon Platinum 8490H 2PEPYC 9754 2PEPYC 9654 2PXeon Max 9480 2PEPYC 9684X 2PEPYC 9554 2PEPYC 9554 2P - Power 400WEPYC 9684X 2P - Power 400WXeon Max 9480 2P - HBM Only1200M2400M3600M4800M6000MSE +/- 2267723.11, N = 3SE +/- 59753635.01, N = 13SE +/- 46561867.68, N = 13SE +/- 5128608.17, N = 3SE +/- 44262083.97, N = 14SE +/- 54793231.38, N = 15SE +/- 39591478.78, N = 15SE +/- 93606095.21, N = 15SE +/- 49833209.25, N = 12SE +/- 36198694.29, N = 15SE +/- 9434203.22, N = 3SE +/- 54284212.92, N = 51988543333287224230830093672313076320333309198150032352690003287419800338272446739119143333948722533452654400054385582001. (CC) gcc options: -lparcsr_ls -lparcsr_mv -lseq_mv -lIJ_mv -lkrylov -lHYPRE_utilities -lm -fopenmp -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 2.2Video Input: Bosphorus 4K - Video Preset: SlowXeon Max 9480 2PXeon Max 9480 2P - HBM OnlyXeon Platinum 8490H 2PEPYC 7773X 2PEPYC 9554 2PEPYC 9554 2P - Power 400WEPYC 9754 2PEPYC 9754 2P - Power 400WEPYC 9684X 2PEPYC 9654 2PEPYC 9654 2P - Power 400WEPYC 9684X 2P - Power 400W1530456075SE +/- 0.25, N = 15SE +/- 0.19, N = 3SE +/- 0.15, N = 3SE +/- 0.12, N = 3SE +/- 0.09, N = 4SE +/- 0.06, N = 4SE +/- 0.65, N = 15SE +/- 0.62, N = 5SE +/- 0.22, N = 5SE +/- 0.21, N = 5SE +/- 0.20, N = 5SE +/- 0.10, N = 524.2726.6932.2632.8846.0346.1959.3060.3764.2264.9965.6966.121. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt

NAS Parallel Benchmarks

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

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: SP.CXeon Platinum 8490H 2PXeon Max 9480 2PEPYC 9754 2PEPYC 9754 2P - Power 400WEPYC 7773X 2PXeon Max 9480 2P - HBM OnlyEPYC 9554 2PEPYC 9554 2P - Power 400WEPYC 9654 2PEPYC 9654 2P - Power 400WEPYC 9684X 2PEPYC 9684X 2P - Power 400W90K180K270K360K450KSE +/- 176.69, N = 5SE +/- 1735.47, N = 5SE +/- 1446.03, N = 6SE +/- 1347.73, N = 6SE +/- 1149.47, N = 6SE +/- 1541.94, N = 6SE +/- 1003.27, N = 6SE +/- 674.41, N = 6SE +/- 1413.59, N = 6SE +/- 1050.85, N = 6SE +/- 912.34, N = 7SE +/- 2287.87, N = 8150552.39176292.33219855.27223859.81230772.86244889.16244961.40247051.81269429.29272856.60353333.76402805.721. (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

HeFFTe - Highly Efficient FFT for Exascale

HeFFTe is the Highly Efficient FFT for Exascale software developed as part of the Exascale Computing Project. This test profile uses HeFFTe's built-in speed benchmarks under a variety of configuration options and currently catering to CPU/processor testing. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGFLOP/s, More Is BetterHeFFTe - Highly Efficient FFT for Exascale 2.3Test: r2c - Backend: FFTW - Precision: double - X Y Z: 512EPYC 7773X 2PXeon Platinum 8490H 2PXeon Max 9480 2PEPYC 9754 2PEPYC 9754 2P - Power 400WXeon Max 9480 2P - HBM OnlyEPYC 9554 2PEPYC 9554 2P - Power 400WEPYC 9654 2PEPYC 9654 2P - Power 400WEPYC 9684X 2PEPYC 9684X 2P - Power 400W70140210280350SE +/- 0.34, N = 4SE +/- 0.63, N = 4SE +/- 1.72, N = 15SE +/- 0.88, N = 5SE +/- 1.19, N = 5SE +/- 2.98, N = 12SE +/- 0.31, N = 5SE +/- 1.23, N = 5SE +/- 1.03, N = 5SE +/- 0.91, N = 5SE +/- 2.12, N = 6SE +/- 2.22, N = 6125.11128.82154.35206.56208.48221.06235.83235.96251.05253.79319.37322.641. (CXX) g++ options: -O3

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 7773X 2PXeon Max 9480 2PXeon Platinum 8490H 2PEPYC 9554 2P - Power 400WEPYC 9554 2PEPYC 9754 2P - Power 400WEPYC 9754 2PXeon Max 9480 2P - HBM OnlyEPYC 9654 2PEPYC 9654 2P - Power 400WEPYC 9684X 2PEPYC 9684X 2P - Power 400W3691215SE +/- 0.07207418, N = 5SE +/- 0.05183946, N = 6SE +/- 0.01528686, N = 6SE +/- 0.03696191, N = 7SE +/- 0.01651966, N = 7SE +/- 0.02935664, N = 7SE +/- 0.02745951, N = 7SE +/- 0.01983325, N = 7SE +/- 0.01407862, N = 7SE +/- 0.02775030, N = 7SE +/- 0.02884245, N = 7SE +/- 0.02948821, N = 109.625806436.275156586.239761034.906152114.804147994.590877534.569300384.450041434.198701044.194226953.965542453.749491221. (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

HeFFTe - Highly Efficient FFT for Exascale

HeFFTe is the Highly Efficient FFT for Exascale software developed as part of the Exascale Computing Project. This test profile uses HeFFTe's built-in speed benchmarks under a variety of configuration options and currently catering to CPU/processor testing. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGFLOP/s, More Is BetterHeFFTe - Highly Efficient FFT for Exascale 2.3Test: c2c - Backend: FFTW - Precision: double - X Y Z: 512EPYC 7773X 2PXeon Platinum 8490H 2PXeon Max 9480 2PEPYC 9754 2PEPYC 9754 2P - Power 400WXeon Max 9480 2P - HBM OnlyEPYC 9554 2P - Power 400WEPYC 9554 2PEPYC 9654 2PEPYC 9654 2P - Power 400WEPYC 9684X 2PEPYC 9684X 2P - Power 400W306090120150SE +/- 0.12, N = 3SE +/- 0.23, N = 3SE +/- 0.70, N = 15SE +/- 1.36, N = 3SE +/- 0.22, N = 3SE +/- 1.62, N = 3SE +/- 1.45, N = 4SE +/- 0.88, N = 4SE +/- 0.69, N = 4SE +/- 0.45, N = 4SE +/- 1.05, N = 4SE +/- 0.31, N = 461.0070.1183.14110.01112.18115.20127.40127.81132.06133.52153.30153.761. (CXX) g++ options: -O3

libxsmm

Libxsmm is an open-source library for specialized dense and sparse matrix operations and deep learning primitives. Libxsmm supports making use of Intel AMX, AVX-512, and other modern CPU instruction set capabilities. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGFLOPS/s, More Is Betterlibxsmm 2-1.17-3645M N K: 64EPYC 7773X 2PEPYC 9554 2P - Power 400WEPYC 9554 2PEPYC 9754 2PEPYC 9754 2P - Power 400WEPYC 9654 2PEPYC 9654 2P - Power 400WEPYC 9684X 2PEPYC 9684X 2P - Power 400W13002600390052006500SE +/- 18.96, N = 15SE +/- 12.37, N = 7SE +/- 8.94, N = 7SE +/- 16.75, N = 7SE +/- 16.68, N = 7SE +/- 21.44, N = 8SE +/- 6.32, N = 8SE +/- 29.37, N = 10SE +/- 29.62, N = 102479.62669.92672.32828.62844.02970.23012.05858.16224.31. (CXX) g++ options: -dynamic -Bstatic -static-libgcc -lgomp -lm -lrt -ldl -lquadmath -lstdc++ -pthread -fPIC -std=c++14 -O2 -fopenmp-simd -funroll-loops -ftree-vectorize -fdata-sections -ffunction-sections -fvisibility=hidden -msse4.2

HeFFTe - Highly Efficient FFT for Exascale

HeFFTe is the Highly Efficient FFT for Exascale software developed as part of the Exascale Computing Project. This test profile uses HeFFTe's built-in speed benchmarks under a variety of configuration options and currently catering to CPU/processor testing. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGFLOP/s, More Is BetterHeFFTe - Highly Efficient FFT for Exascale 2.3Test: r2c - Backend: FFTW - Precision: double - X Y Z: 256EPYC 7773X 2PXeon Platinum 8490H 2PXeon Max 9480 2PEPYC 9754 2PEPYC 9754 2P - Power 400WXeon Max 9480 2P - HBM OnlyEPYC 9554 2PEPYC 9554 2P - Power 400WEPYC 9654 2P - Power 400WEPYC 9654 2PEPYC 9684X 2PEPYC 9684X 2P - Power 400W80160240320400SE +/- 1.16, N = 10SE +/- 0.79, N = 10SE +/- 3.36, N = 15SE +/- 0.80, N = 10SE +/- 1.25, N = 10SE +/- 2.97, N = 15SE +/- 3.53, N = 15SE +/- 2.88, N = 15SE +/- 6.03, N = 15SE +/- 2.63, N = 15SE +/- 1.76, N = 11SE +/- 1.58, N = 11149.95159.80177.07229.20234.67241.48305.72311.87345.25349.10352.65361.981. (CXX) g++ options: -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: MG.CEPYC 7773X 2PXeon Platinum 8490H 2PEPYC 9654 2P - Power 400WEPYC 9654 2PEPYC 9554 2PEPYC 9684X 2P - Power 400WEPYC 9554 2P - Power 400WXeon Max 9480 2PEPYC 9684X 2PEPYC 9754 2P - Power 400WEPYC 9754 2PXeon Max 9480 2P - HBM Only60K120K180K240K300KSE +/- 816.89, N = 14SE +/- 931.04, N = 11SE +/- 1682.35, N = 15SE +/- 2856.20, N = 15SE +/- 1627.62, N = 15SE +/- 5124.21, N = 15SE +/- 2528.43, N = 15SE +/- 2783.68, N = 15SE +/- 4555.29, N = 15SE +/- 3185.64, N = 15SE +/- 1814.99, N = 11SE +/- 1216.61, N = 12124155.94167917.37202036.80207828.63233525.20233932.00238244.69238922.48243282.67246501.36249822.83291332.661. (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

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 TimeXeon Max 9480 2PXeon Platinum 8490H 2PEPYC 7773X 2PEPYC 9554 2PEPYC 9554 2P - Power 400WEPYC 9754 2PEPYC 9754 2P - Power 400WEPYC 9654 2PEPYC 9654 2P - Power 400WEPYC 9684X 2PEPYC 9684X 2P - Power 400W4080120160200196.57192.30165.26131.28127.46116.16115.41109.35105.6294.6483.811. (CXX) g++ options: -std=c++14 -m64 -O3 -ftemplate-depth-100 -fPIC -fuse-ld=bfd -Xlinker --add-needed --no-as-needed -lfiniteVolume -lmeshTools -lparallel -llagrangian -lregionModels -lgenericPatchFields -lOpenFOAM -ldl -lm

libxsmm

Libxsmm is an open-source library for specialized dense and sparse matrix operations and deep learning primitives. Libxsmm supports making use of Intel AMX, AVX-512, and other modern CPU instruction set capabilities. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGFLOPS/s, More Is Betterlibxsmm 2-1.17-3645M N K: 128EPYC 7773X 2PEPYC 9554 2PEPYC 9554 2P - Power 400WEPYC 9654 2PEPYC 9754 2PEPYC 9654 2P - Power 400WEPYC 9754 2P - Power 400WEPYC 9684X 2PEPYC 9684X 2P - Power 400W15003000450060007500SE +/- 29.49, N = 3SE +/- 47.13, N = 4SE +/- 39.57, N = 6SE +/- 37.10, N = 3SE +/- 40.14, N = 3SE +/- 64.03, N = 3SE +/- 54.06, N = 9SE +/- 74.79, N = 3SE +/- 52.26, N = 33010.33969.14083.54581.24833.84939.05108.16630.36972.91. (CXX) g++ options: -dynamic -Bstatic -static-libgcc -lgomp -lm -lrt -ldl -lquadmath -lstdc++ -pthread -fPIC -std=c++14 -O2 -fopenmp-simd -funroll-loops -ftree-vectorize -fdata-sections -ffunction-sections -fvisibility=hidden -msse4.2

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.CXeon Platinum 8490H 2PXeon Max 9480 2PXeon Max 9480 2P - HBM OnlyEPYC 7773X 2PEPYC 9554 2PEPYC 9554 2P - Power 400WEPYC 9654 2PEPYC 9684X 2PEPYC 9654 2P - Power 400WEPYC 9684X 2P - Power 400WEPYC 9754 2P - Power 400WEPYC 9754 2P130K260K390K520K650KSE +/- 331.60, N = 5SE +/- 1520.10, N = 6SE +/- 213.51, N = 6SE +/- 5780.29, N = 15SE +/- 3539.12, N = 15SE +/- 4424.60, N = 7SE +/- 3172.98, N = 7SE +/- 4498.91, N = 7SE +/- 4093.98, N = 7SE +/- 4343.25, N = 8SE +/- 2807.48, N = 7SE +/- 7170.23, N = 12263499.10273751.97305114.30395342.95480255.42486004.49503710.85506243.28517505.91562925.84597743.03598185.371. (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

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: BLASXeon Max 9480 2PEPYC 7773X 2PXeon Max 9480 2P - HBM OnlyEPYC 9754 2P - Power 400WEPYC 9754 2PEPYC 9554 2PXeon Platinum 8490H 2PEPYC 9654 2PEPYC 9554 2P - Power 400WEPYC 9684X 2PEPYC 9654 2P - Power 400WEPYC 9684X 2P - Power 400W3K6K9K12K15KSE +/- 226.48, N = 6SE +/- 44.64, N = 3SE +/- 80.39, N = 3SE +/- 24.06, N = 3SE +/- 31.86, N = 3SE +/- 35.75, N = 3SE +/- 90.64, N = 3SE +/- 129.08, N = 3SE +/- 108.48, N = 3SE +/- 139.81, N = 4SE +/- 138.12, N = 4SE +/- 88.70, N = 359356388819384108483110661108711144112851138711607134581. (CXX) g++ options: -flto -pthread

NAS Parallel Benchmarks

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

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: BT.CXeon Max 9480 2PXeon Platinum 8490H 2PEPYC 7773X 2PXeon Max 9480 2P - HBM OnlyEPYC 9554 2P - Power 400WEPYC 9554 2PEPYC 9754 2PEPYC 9754 2P - Power 400WEPYC 9654 2PEPYC 9654 2P - Power 400WEPYC 9684X 2PEPYC 9684X 2P - Power 400W160K320K480K640K800KSE +/- 1676.04, N = 5SE +/- 807.78, N = 5SE +/- 1238.38, N = 5SE +/- 320.97, N = 6SE +/- 1894.85, N = 6SE +/- 2209.25, N = 6SE +/- 4198.29, N = 15SE +/- 4835.04, N = 15SE +/- 2609.81, N = 6SE +/- 2687.60, N = 7SE +/- 4824.10, N = 15SE +/- 2463.95, N = 7322599.69335827.19375894.53407912.91461016.80466102.69501819.67508790.75513456.93556402.91621820.27727314.541. (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

GPAW

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

OpenBenchmarking.orgSeconds, Fewer Is BetterGPAW 23.6Input: Carbon NanotubeXeon Max 9480 2PEPYC 7773X 2PXeon Platinum 8490H 2PXeon Max 9480 2P - HBM OnlyEPYC 9554 2PEPYC 9684X 2PEPYC 9554 2P - Power 400WEPYC 9754 2PEPYC 9654 2PEPYC 9754 2P - Power 400WEPYC 9654 2P - Power 400WEPYC 9684X 2P - Power 400W1020304050SE +/- 0.56, N = 3SE +/- 0.13, N = 3SE +/- 0.14, N = 3SE +/- 0.08, N = 3SE +/- 0.13, N = 3SE +/- 0.23, N = 3SE +/- 0.04, N = 3SE +/- 0.24, N = 5SE +/- 0.31, N = 3SE +/- 0.26, N = 4SE +/- 0.26, N = 3SE +/- 0.03, N = 343.4438.2130.8630.5122.8322.1822.1421.9521.5420.8019.8519.371. (CC) gcc options: -shared -fwrapv -O2 -lxc -lblas -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 2022.3Model: Machine Translation EN To DE FP16 - Device: CPUXeon Max 9480 2PXeon Max 9480 2P - HBM OnlyXeon Platinum 8490H 2PEPYC 9554 2PEPYC 9554 2P - Power 400WEPYC 9684X 2PEPYC 9654 2PEPYC 9654 2P - Power 400WEPYC 9684X 2P - Power 400WEPYC 9754 2PEPYC 9754 2P - Power 400W30060090012001500SE +/- 1.71, N = 3SE +/- 2.83, N = 3SE +/- 2.82, N = 3SE +/- 0.88, N = 3SE +/- 1.12, N = 3SE +/- 3.23, N = 3SE +/- 2.56, N = 3SE +/- 2.52, N = 3SE +/- 1.70, N = 3SE +/- 0.76, N = 3SE +/- 4.41, N = 3586.50688.49692.55780.72804.67938.66953.221001.161065.111163.451248.901. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -msse4.1 -msse4.2 -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -Os -std=c++11 -MD -MT -MF

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.3Model: Vehicle Detection FP16 - Device: CPUEPYC 9754 2PXeon Max 9480 2PEPYC 9754 2P - Power 400WXeon Platinum 8490H 2PXeon Max 9480 2P - HBM OnlyEPYC 9684X 2PEPYC 9654 2PEPYC 9654 2P - Power 400WEPYC 9684X 2P - Power 400WEPYC 9554 2PEPYC 9554 2P - Power 400W3691215SE +/- 0.09, N = 15SE +/- 0.02, N = 3SE +/- 0.01, 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 +/- 0.00, N = 310.359.679.018.147.746.546.506.015.905.335.09MIN: 6.16 / MAX: 86.39MIN: 7.08 / MAX: 76.72MIN: 6.22 / MAX: 79.34MIN: 7.19 / MAX: 56.27MIN: 6.8 / MAX: 72.28MIN: 4.9 / MAX: 53.1MIN: 4.98 / MAX: 54.72MIN: 4.98 / MAX: 58.98MIN: 4.91 / MAX: 56.09MIN: 4.91 / MAX: 41.3MIN: 4.92 / MAX: 33.491. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -msse4.1 -msse4.2 -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -Os -std=c++11 -MD -MT -MF

Timed LLVM Compilation

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

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed LLVM Compilation 16.0Build System: NinjaXeon Max 9480 2PXeon Platinum 8490H 2PEPYC 7773X 2PEPYC 9554 2PEPYC 9554 2P - Power 400WEPYC 9754 2PEPYC 9754 2P - Power 400WEPYC 9654 2PEPYC 9684X 2PEPYC 9654 2P - Power 400WEPYC 9684X 2P - Power 400W60120180240300SE +/- 2.23, N = 3SE +/- 0.60, N = 3SE +/- 0.12, N = 3SE +/- 0.58, N = 3SE +/- 0.38, N = 3SE +/- 0.25, N = 3SE +/- 0.08, N = 3SE +/- 0.37, N = 3SE +/- 0.18, N = 3SE +/- 0.19, N = 3SE +/- 0.05, N = 3256.92205.44200.90156.75153.60152.37148.80144.85141.75138.07135.23

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 7773X 2PXeon Max 9480 2PXeon Platinum 8490H 2PEPYC 9554 2PEPYC 9554 2P - Power 400WEPYC 9654 2PXeon Max 9480 2P - HBM OnlyEPYC 9654 2P - Power 400WEPYC 9684X 2PEPYC 9754 2P - Power 400WEPYC 9754 2PEPYC 9684X 2P - Power 400W0.50511.01021.51532.02042.5255SE +/- 0.02377940, N = 15SE +/- 0.02218952, N = 13SE +/- 0.01614121, N = 15SE +/- 0.01444431, N = 15SE +/- 0.01579407, N = 15SE +/- 0.01339425, N = 15SE +/- 0.00626042, N = 10SE +/- 0.01071769, N = 15SE +/- 0.00998524, N = 15SE +/- 0.00914658, N = 9SE +/- 0.00468517, N = 10SE +/- 0.01071562, N = 152.244753271.825083241.707723211.449453461.447513051.373318321.350844101.338089861.325605671.286017991.280363211.197034881. (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

Timed Linux Kernel Compilation

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

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Linux Kernel Compilation 6.1Build: defconfigXeon Max 9480 2PEPYC 7773X 2PXeon Platinum 8490H 2PEPYC 9754 2P - Power 400WXeon Max 9480 2P - HBM OnlyEPYC 9754 2PEPYC 9554 2PEPYC 9654 2PEPYC 9684X 2PEPYC 9554 2P - Power 400WEPYC 9654 2P - Power 400WEPYC 9684X 2P - Power 400W1224364860SE +/- 0.38, N = 15SE +/- 0.35, N = 7SE +/- 0.43, N = 4SE +/- 0.22, N = 3SE +/- 0.36, N = 5SE +/- 0.25, N = 10SE +/- 0.28, N = 6SE +/- 0.19, N = 14SE +/- 0.22, N = 10SE +/- 0.25, N = 7SE +/- 0.27, N = 6SE +/- 0.21, N = 1251.1036.6835.9633.4633.0933.0629.5028.7128.5328.5127.6827.60

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.CXeon Max 9480 2PEPYC 7773X 2PXeon Platinum 8490H 2PXeon Max 9480 2P - HBM OnlyEPYC 9754 2P - Power 400WEPYC 9754 2PEPYC 9684X 2PEPYC 9654 2PEPYC 9654 2P - Power 400WEPYC 9554 2P - Power 400WEPYC 9554 2PEPYC 9684X 2P - Power 400W20K40K60K80K100KSE +/- 324.14, N = 8SE +/- 372.47, N = 11SE +/- 116.10, N = 9SE +/- 245.57, N = 9SE +/- 516.11, N = 8SE +/- 387.99, N = 8SE +/- 812.95, N = 15SE +/- 756.73, N = 15SE +/- 1489.58, N = 15SE +/- 898.57, N = 15SE +/- 732.46, N = 15SE +/- 1142.40, N = 1548170.7951653.2058253.8961740.1266770.5567108.5781336.7284056.0486108.5686896.7087564.2087838.871. (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

Timed Godot Game Engine Compilation

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

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Godot Game Engine Compilation 4.0Time To CompileXeon Max 9480 2PXeon Platinum 8490H 2PEPYC 9754 2PEPYC 9754 2P - Power 400WEPYC 7773X 2PEPYC 9554 2PEPYC 9654 2PEPYC 9554 2P - Power 400WEPYC 9654 2P - Power 400WEPYC 9684X 2PEPYC 9684X 2P - Power 400WXeon Max 9480 2P - HBM Only50100150200250SE +/- 2.11, N = 3SE +/- 1.36, N = 3SE +/- 0.39, N = 3SE +/- 0.27, N = 3SE +/- 0.06, N = 3SE +/- 0.12, N = 3SE +/- 0.17, N = 3SE +/- 0.34, N = 3SE +/- 0.11, N = 3SE +/- 0.28, N = 3SE +/- 0.33, N = 3SE +/- 1.49, N = 12231.61200.21196.88194.91194.50165.24164.59163.31161.28159.60156.15134.87

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 19.8.1Time To CompileXeon Max 9480 2PXeon Platinum 8490H 2PEPYC 7773X 2PEPYC 9754 2PEPYC 9754 2P - Power 400WEPYC 9554 2PEPYC 9554 2P - Power 400WEPYC 9654 2PEPYC 9684X 2PEPYC 9654 2P - Power 400WEPYC 9684X 2P - Power 400W50100150200250SE +/- 1.43, N = 3SE +/- 0.28, N = 3SE +/- 0.49, N = 3SE +/- 0.19, N = 3SE +/- 0.28, N = 3SE +/- 0.35, N = 3SE +/- 0.22, N = 3SE +/- 0.15, N = 3SE +/- 0.28, N = 3SE +/- 0.48, N = 3SE +/- 0.16, N = 3218.18174.73174.56150.15148.60138.49137.13134.42132.89131.20127.87

Liquid-DSP

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

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 1.6Threads: 224 - Buffer Length: 256 - Filter Length: 32Xeon Max 9480 2PXeon Max 9480 2P - HBM OnlyXeon Platinum 8490H 2PEPYC 9754 2P - Power 400WEPYC 9754 2PEPYC 7773X 2PEPYC 9684X 2PEPYC 9654 2PEPYC 9554 2PEPYC 9554 2P - Power 400WEPYC 9654 2P - Power 400WEPYC 9684X 2P - Power 400W1600M3200M4800M6400M8000MSE +/- 20621375.10, N = 3SE +/- 8418300.17, N = 3SE +/- 6527973.99, N = 3SE +/- 6821615.97, N = 3SE +/- 3160696.13, N = 3SE +/- 3602930.91, N = 3SE +/- 1254768.68, N = 3SE +/- 753510.30, N = 3SE +/- 7464583.04, N = 3SE +/- 1036554.12, N = 3SE +/- 4147690.12, N = 3SE +/- 2832156.62, N = 34488833333527633333356626333336448133333645280000066847333336735933333714673333374614000007538066667756600000075741666671. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

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 2022.3Model: Person Vehicle Bike Detection FP16 - Device: CPUXeon Max 9480 2PEPYC 9554 2PEPYC 9554 2P - Power 400WXeon Platinum 8490H 2PXeon Max 9480 2P - HBM OnlyEPYC 9684X 2PEPYC 9654 2PEPYC 9754 2PEPYC 9654 2P - Power 400WEPYC 9684X 2P - Power 400WEPYC 9754 2P - Power 400W2K4K6K8K10KSE +/- 30.37, N = 3SE +/- 3.86, N = 3SE +/- 6.85, N = 3SE +/- 0.62, N = 3SE +/- 5.68, N = 3SE +/- 3.29, N = 3SE +/- 6.84, N = 3SE +/- 11.29, N = 3SE +/- 6.54, N = 3SE +/- 11.35, N = 3SE +/- 8.20, N = 36216.017429.337536.107617.077652.319040.449128.219753.649766.4210005.2110290.101. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -msse4.1 -msse4.2 -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -Os -std=c++11 -MD -MT -MF

High Performance Conjugate Gradient

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

OpenBenchmarking.orgGFLOP/s, More Is BetterHigh Performance Conjugate Gradient 3.1X Y Z: 144 144 144 - RT: 60EPYC 7773X 2PEPYC 9654 2P - Power 400WEPYC 9654 2PEPYC 9684X 2PEPYC 9754 2PEPYC 9554 2P - Power 400WEPYC 9554 2PXeon Max 9480 2PXeon Platinum 8490H 2PEPYC 9684X 2P - Power 400W1428425670SE +/- 0.03, N = 3SE +/- 0.06, N = 3SE +/- 0.27, N = 3SE +/- 0.21, N = 3SE +/- 0.10, N = 3SE +/- 0.15, N = 3SE +/- 0.16, N = 3SE +/- 0.40, N = 3SE +/- 0.09, N = 3SE +/- 0.99, N = 938.3143.7650.1251.5552.7854.4954.6154.7361.6562.201. (CXX) g++ options: -O3 -ffast-math -ftree-vectorize -lmpi_cxx -lmpi

X Y Z: 144 144 144 - RT: 60

EPYC 9754 2P - Power 400W: The test run did not produce a result. E: sh: 1: exec: ./hpcg: not found

Z3 Theorem Prover

The Z3 Theorem Prover / SMT solver is developed by Microsoft Research under the MIT license. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterZ3 Theorem Prover 4.12.1SMT File: 1.smt2EPYC 9754 2PEPYC 9754 2P - Power 400WXeon Max 9480 2PXeon Max 9480 2P - HBM OnlyEPYC 9554 2PEPYC 9654 2P - Power 400WEPYC 9654 2PEPYC 9554 2P - Power 400WEPYC 7773X 2PEPYC 9684X 2P - Power 400WEPYC 9684X 2PXeon Platinum 8490H 2P816243240SE +/- 0.11, N = 3SE +/- 0.10, N = 3SE +/- 0.13, N = 3SE +/- 0.09, N = 3SE +/- 0.17, N = 3SE +/- 0.09, N = 3SE +/- 0.15, N = 3SE +/- 0.19, N = 3SE +/- 0.04, N = 3SE +/- 0.07, N = 3SE +/- 0.02, N = 3SE +/- 0.15, N = 335.1034.7327.6726.9826.7926.7526.4826.4123.0021.7421.7321.721. (CXX) g++ options: -lpthread -std=c++17 -fvisibility=hidden -mfpmath=sse -msse -msse2 -O3 -fPIC

High Performance Conjugate Gradient

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

OpenBenchmarking.orgGFLOP/s, More Is BetterHigh Performance Conjugate Gradient 3.1X Y Z: 192 192 192 - RT: 60EPYC 9654 2P - Power 400WEPYC 9654 2PEPYC 9684X 2PEPYC 9754 2PEPYC 9554 2P - Power 400WEPYC 9554 2PXeon Platinum 8490H 2PEPYC 9684X 2P - Power 400W1530456075SE +/- 0.07, N = 3SE +/- 0.64, N = 9SE +/- 0.17, N = 3SE +/- 0.45, N = 3SE +/- 0.22, N = 3SE +/- 0.32, N = 3SE +/- 0.41, N = 3SE +/- 0.70, N = 643.0143.3849.2252.0152.7654.7061.3369.521. (CXX) g++ options: -O3 -ffast-math -ftree-vectorize -lmpi_cxx -lmpi

X Y Z: 192 192 192 - RT: 60

EPYC 7773X 2P: The test quit with a non-zero exit status. E: cat: 'HPCG-Benchmark*.txt': No such file or directory

EPYC 9754 2P - Power 400W: The test run did not produce a result. E: sh: 1: exec: ./hpcg: not found

Xeon Max 9480 2P: The test quit with a non-zero exit status. E: cat: 'HPCG-Benchmark*.txt': No such file or directory

Timed PHP Compilation

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

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed PHP Compilation 8.1.9Time To CompileEPYC 9754 2PEPYC 9754 2P - Power 400WXeon Max 9480 2PEPYC 7773X 2PXeon Platinum 8490H 2PEPYC 9654 2PEPYC 9654 2P - Power 400WEPYC 9554 2P - Power 400WEPYC 9554 2PEPYC 9684X 2PEPYC 9684X 2P - Power 400WXeon Max 9480 2P - HBM Only20406080100SE +/- 0.03, N = 3SE +/- 0.05, N = 3SE +/- 0.68, N = 15SE +/- 0.32, N = 3SE +/- 0.42, N = 3SE +/- 0.07, N = 3SE +/- 0.04, N = 3SE +/- 0.25, N = 3SE +/- 0.04, N = 3SE +/- 0.02, N = 3SE +/- 0.17, N = 3SE +/- 0.28, N = 380.4980.2680.2175.0274.2867.2566.8966.2066.0365.4365.1949.82

High Performance Conjugate Gradient

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

OpenBenchmarking.orgGFLOP/s, More Is BetterHigh Performance Conjugate Gradient 3.1X Y Z: 160 160 160 - RT: 60EPYC 7773X 2PEPYC 9654 2P - Power 400WXeon Max 9480 2PEPYC 9654 2PEPYC 9684X 2PEPYC 9754 2PEPYC 9554 2PEPYC 9554 2P - Power 400WEPYC 9684X 2P - Power 400WXeon Platinum 8490H 2P1428425670SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.03, N = 3SE +/- 0.08, N = 3SE +/- 0.23, N = 3SE +/- 0.35, N = 3SE +/- 0.15, N = 3SE +/- 0.28, N = 3SE +/- 1.00, N = 9SE +/- 0.49, N = 338.1743.5547.6949.8950.4852.6053.2154.2058.8361.091. (CXX) g++ options: -O3 -ffast-math -ftree-vectorize -lmpi_cxx -lmpi

X Y Z: 160 160 160 - RT: 60

EPYC 9754 2P - Power 400W: The test run did not produce a result. E: sh: 1: exec: ./hpcg: not found

CP2K Molecular Dynamics

CP2K is an open-source molecular dynamics software package focused on quantum chemistry and solid-state physics. More details on the CP2K benchmark test cases and details can be found @ https://www.cp2k.org/performance Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterCP2K Molecular Dynamics 2023.1Input: H2O-DFT-LSXeon Platinum 8490H 2PEPYC 9654 2PEPYC 9754 2PEPYC 9554 2PEPYC 9654 2P - Power 400WEPYC 9554 2P - Power 400WEPYC 9684X 2PEPYC 9754 2P - Power 400WEPYC 9684X 2P - Power 400W50010001500200025002454.152355.942227.222023.492009.741999.241977.281935.641653.841. (F9X) gfortran options: -fopenmp -mtune=native -O3 -funroll-loops -fbacktrace -ffree-form -fimplicit-none -std=f2008 -lcp2kstart -lcp2kmc -lcp2kswarm -lcp2kmotion -lcp2kthermostat -lcp2kemd -lcp2ktmc -lcp2kmain -lcp2kdbt -lcp2ktas -lcp2kdbm -lcp2kgrid -lcp2kgridcpu -lcp2kgridref -lcp2kgridcommon -ldbcsrarnoldi -ldbcsrx -lcp2kshg_int -lcp2keri_mme -lcp2kminimax -lcp2khfxbase -lcp2ksubsys -lcp2kxc -lcp2kao -lcp2kpw_env -lcp2kinput -lcp2kpw -lcp2kgpu -lcp2kfft -lcp2kfpga -lcp2kfm -lcp2kcommon -lcp2koffload -lcp2kmpiwrap -lcp2kbase -ldbcsr -lsirius -lspla -lspfft -lsymspg -lvdwxc -lhdf5 -lhdf5_hl -lz -lgsl -lelpa_openmp -lcosma -lcosta -lscalapack -lxsmmf -lxsmm -ldl -lpthread -lxcf03 -lxc -lint2 -lfftw3_mpi -lfftw3 -lfftw3_omp -lmpi_cxx -lmpi -lopenblas -lvori -lstdc++ -lmpi_usempif08 -lmpi_mpifh -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm

Input: H2O-DFT-LS

EPYC 7773X 2P: The test quit with a non-zero exit status. E: mpirun noticed that process rank 77 with PID 0 on node phoronix-SYS-221H-TNR exited on signal 9 (Killed).

Xeon Max 9480 2P: The test quit with a non-zero exit status. E: mpirun noticed that process rank 106 with PID 0 on node phoronix-SYS-221H-TNR exited on signal 9 (Killed).

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 2022.3Model: Machine Translation EN To DE FP16 - Device: CPUEPYC 9754 2PEPYC 9754 2P - Power 400WEPYC 9684X 2PEPYC 9654 2PEPYC 9654 2P - Power 400WXeon Max 9480 2PEPYC 9684X 2P - Power 400WXeon Platinum 8490H 2PEPYC 9554 2PXeon Max 9480 2P - HBM OnlyEPYC 9554 2P - Power 400W1224364860SE +/- 0.04, N = 3SE +/- 0.18, N = 3SE +/- 0.18, N = 3SE +/- 0.14, N = 3SE +/- 0.13, N = 3SE +/- 0.14, N = 3SE +/- 0.07, N = 3SE +/- 0.18, N = 3SE +/- 0.05, N = 3SE +/- 0.17, N = 3SE +/- 0.06, N = 354.9551.1951.0750.3047.8947.6645.0343.1140.9440.6039.72MIN: 41.5 / MAX: 164.45MIN: 41.8 / MAX: 277.53MIN: 37.29 / MAX: 248.17MIN: 38.4 / MAX: 207.06MIN: 38.09 / MAX: 245.2MIN: 33.3 / MAX: 388.06MIN: 35.76 / MAX: 247.19MIN: 28 / MAX: 268.31MIN: 35.1 / MAX: 136.15MIN: 31.78 / MAX: 382.85MIN: 34.37 / MAX: 135.731. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -msse4.1 -msse4.2 -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -Os -std=c++11 -MD -MT -MF

Timed LLVM Compilation

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

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed LLVM Compilation 16.0Build System: Unix MakefilesXeon Max 9480 2PEPYC 7773X 2PEPYC 9754 2PEPYC 9754 2P - Power 400WXeon Platinum 8490H 2PEPYC 9554 2PEPYC 9554 2P - Power 400WEPYC 9654 2PEPYC 9654 2P - Power 400WEPYC 9684X 2PEPYC 9684X 2P - Power 400W100200300400500SE +/- 1.34, N = 3SE +/- 0.48, N = 3SE +/- 0.44, N = 3SE +/- 0.75, N = 3SE +/- 0.13, N = 3SE +/- 0.56, N = 3SE +/- 0.11, N = 3SE +/- 0.20, N = 3SE +/- 0.44, N = 3SE +/- 0.80, N = 3SE +/- 0.43, N = 3458.51417.79402.71402.39395.68344.02343.03342.67341.39339.45333.95

Z3 Theorem Prover

The Z3 Theorem Prover / SMT solver is developed by Microsoft Research under the MIT license. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterZ3 Theorem Prover 4.12.1SMT File: 2.smt2EPYC 9754 2P - Power 400WEPYC 9754 2PXeon Max 9480 2PXeon Platinum 8490H 2PXeon Max 9480 2P - HBM OnlyEPYC 7773X 2PEPYC 9654 2P - Power 400WEPYC 9654 2PEPYC 9554 2PEPYC 9554 2P - Power 400WEPYC 9684X 2P - Power 400WEPYC 9684X 2P20406080100SE +/- 0.17, N = 3SE +/- 0.13, N = 3SE +/- 0.10, N = 3SE +/- 0.04, N = 3SE +/- 0.12, N = 3SE +/- 0.43, N = 3SE +/- 0.21, N = 3SE +/- 0.01, N = 3SE +/- 0.23, N = 3SE +/- 0.05, N = 3SE +/- 0.04, N = 3SE +/- 0.05, N = 386.6986.6686.5686.5485.9474.5770.1170.0769.0368.8468.4368.061. (CXX) g++ options: -lpthread -std=c++17 -fvisibility=hidden -mfpmath=sse -msse -msse2 -O3 -fPIC

CPU Power Consumption Monitor

OpenBenchmarking.orgWattsCPU Power Consumption MonitorPhoronix Test Suite System MonitoringXeon Max 9480 2P - HBM OnlyEPYC 9684X 2P - Power 400WXeon Platinum 8490H 2PXeon Max 9480 2PEPYC 9654 2P - Power 400WEPYC 9684X 2PEPYC 9654 2PEPYC 9554 2P - Power 400WEPYC 9554 2PEPYC 9754 2P - Power 400WEPYC 9754 2PEPYC 7773X 2P2004006008001000Min: 146.06 / Avg: 598.76 / Max: 765.23Min: 38.27 / Avg: 585.13 / Max: 831.11Min: 101.45 / Avg: 568.83 / Max: 975.85Min: 138.49 / Avg: 537.85 / Max: 1189.69Min: 28.93 / Avg: 523.42 / Max: 821.33Min: 53.1 / Avg: 489.31 / Max: 729.22Min: 31.41 / Avg: 482.85 / Max: 741.21Min: 28.76 / Avg: 454.14 / Max: 824.28Min: 26.2 / Avg: 449.69 / Max: 715.97Min: 28.4 / Avg: 423.79 / Max: 821.27Min: 23.61 / Avg: 385.73 / Max: 797.26Min: 39.24 / Avg: 385.02 / Max: 584.32

PostgreSQL

OpenBenchmarking.orgWatts, Fewer Is BetterPostgreSQL 15CPU Power Consumption MonitorXeon Max 9480 2P - HBM OnlyXeon Max 9480 2PXeon Platinum 8490H 2PEPYC 9684X 2P - Power 400WEPYC 9654 2P - Power 400WEPYC 9684X 2PEPYC 9654 2PEPYC 7773X 2PEPYC 9554 2PEPYC 9554 2P - Power 400WEPYC 9754 2PEPYC 9754 2P - Power 400W120240360480600Min: 289.13 / Avg: 590.01 / Max: 666.35Min: 295.34 / Avg: 559.71 / Max: 670.33Min: 195.06 / Avg: 550.6 / Max: 651.69Min: 62.95 / Avg: 532.23 / Max: 633.82Min: 57.19 / Avg: 477.77 / Max: 569.65Min: 112.57 / Avg: 470.2 / Max: 537.14Min: 61.88 / Avg: 467.59 / Max: 544.82Min: 75.62 / Avg: 431.2 / Max: 522.13Min: 51.76 / Avg: 395.37 / Max: 456.33Min: 54.18 / Avg: 393.47 / Max: 455.98Min: 42.57 / Avg: 373.88 / Max: 461.89Min: 30.34 / Avg: 369.51 / Max: 460.7

OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL 15Scaling Factor: 100 - Clients: 1000 - Mode: Read Only - Average LatencyXeon Max 9480 2PXeon Max 9480 2P - HBM OnlyXeon Platinum 8490H 2PEPYC 9754 2P - Power 400WEPYC 9754 2PEPYC 7773X 2PEPYC 9654 2P - Power 400WEPYC 9654 2PEPYC 9554 2PEPYC 9684X 2P - Power 400WEPYC 9554 2P - Power 400WEPYC 9684X 2P0.35870.71741.07611.43481.7935SE +/- 0.057, N = 12SE +/- 0.061, N = 12SE +/- 0.082, N = 12SE +/- 0.006, N = 12SE +/- 0.006, N = 9SE +/- 0.002, N = 3SE +/- 0.004, N = 12SE +/- 0.003, N = 3SE +/- 0.003, N = 12SE +/- 0.005, N = 9SE +/- 0.004, N = 3SE +/- 0.002, N = 31.5941.5591.3580.3560.3520.3400.3080.3050.2960.2930.2920.2881. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL 15Scaling Factor: 100 - Clients: 1000 - Mode: Read OnlyXeon Max 9480 2PXeon Max 9480 2P - HBM OnlyXeon Platinum 8490H 2PEPYC 9754 2P - Power 400WEPYC 9754 2PEPYC 7773X 2PEPYC 9654 2P - Power 400WEPYC 9654 2PEPYC 9554 2PEPYC 9554 2P - Power 400WEPYC 9684X 2P - Power 400WEPYC 9684X 2P700K1400K2100K2800K3500KSE +/- 25994.21, N = 12SE +/- 27067.99, N = 12SE +/- 54529.71, N = 12SE +/- 50208.53, N = 12SE +/- 49501.12, N = 9SE +/- 12968.01, N = 3SE +/- 45903.35, N = 12SE +/- 33628.84, N = 3SE +/- 33550.50, N = 12SE +/- 42639.42, N = 3SE +/- 60842.89, N = 9SE +/- 18876.28, N = 36374176531937720292820486284704129404063251179327719333778133426783342722934673031. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

PETSc

OpenBenchmarking.orgWatts, Fewer Is BetterPETSc 3.19CPU Power Consumption MonitorXeon Max 9480 2P - HBM OnlyXeon Platinum 8490H 2PEPYC 9684X 2P - Power 400WXeon Max 9480 2PEPYC 9684X 2PEPYC 9654 2P - Power 400WEPYC 9654 2PEPYC 7773X 2PEPYC 9554 2P - Power 400WEPYC 9554 2PEPYC 9754 2P - Power 400WEPYC 9754 2P2004006008001000Min: 289.02 / Avg: 649.89 / Max: 751.07Min: 201.64 / Avg: 587.79 / Max: 746.92Min: 65.44 / Avg: 527.88 / Max: 740.35Min: 270.16 / Avg: 518.98 / Max: 1014.32Min: 115.28 / Avg: 489 / Max: 618.67Min: 57.35 / Avg: 473.53 / Max: 664.84Min: 60.32 / Avg: 464.62 / Max: 620.11Min: 76.67 / Avg: 425.65 / Max: 516.99Min: 55.24 / Avg: 423.09 / Max: 577.74Min: 51.92 / Avg: 422.41 / Max: 558.74Min: 54.08 / Avg: 366.96 / Max: 522.19Min: 42.94 / Avg: 365.03 / Max: 514.62

OpenBenchmarking.orgMB/s Per Watt, More Is BetterPETSc 3.19Test: StreamsEPYC 7773X 2PXeon Platinum 8490H 2PEPYC 9654 2P - Power 400WEPYC 9684X 2P - Power 400WEPYC 9684X 2PEPYC 9654 2PEPYC 9754 2P - Power 400WEPYC 9554 2P - Power 400WEPYC 9554 2PEPYC 9754 2PXeon Max 9480 2PXeon Max 9480 2P - HBM Only400800120016002000580.72651.49931.31951.601062.721073.621097.891161.251188.331230.161584.951914.94

OpenBenchmarking.orgMB/s, More Is BetterPETSc 3.19Test: StreamsEPYC 7773X 2PXeon Platinum 8490H 2PEPYC 9754 2P - Power 400WEPYC 9654 2P - Power 400WEPYC 9754 2PEPYC 9554 2P - Power 400WEPYC 9654 2PEPYC 9554 2PEPYC 9684X 2P - Power 400WEPYC 9684X 2PXeon Max 9480 2PXeon Max 9480 2P - HBM Only300K600K900K1200K1500KSE +/- 226.13, N = 3SE +/- 1463.10, N = 3SE +/- 16038.68, N = 9SE +/- 16940.03, N = 9SE +/- 19305.47, N = 6SE +/- 14054.14, N = 9SE +/- 7104.67, N = 9SE +/- 13801.50, N = 9SE +/- 35873.33, N = 6SE +/- 24624.10, N = 9SE +/- 34939.31, N = 6SE +/- 13204.52, N = 3247183.49382936.01402880.37440996.50449040.09491308.08498825.93501964.62502329.42519663.49822547.781244507.941. (CC) gcc options: -fPIC -O3 -O2 -lpthread -ludev -lpciaccess -lm

NAS Parallel Benchmarks

OpenBenchmarking.orgWatts, Fewer Is BetterNAS Parallel Benchmarks 3.4CPU Power Consumption MonitorXeon Max 9480 2P - HBM OnlyXeon Max 9480 2PXeon Platinum 8490H 2PEPYC 9684X 2P - Power 400WEPYC 9754 2P - Power 400WEPYC 9684X 2PEPYC 9754 2PEPYC 7773X 2PEPYC 9654 2PEPYC 9654 2P - Power 400WEPYC 9554 2P - Power 400WEPYC 9554 2P130260390520650Min: 290.42 / Avg: 556.48 / Max: 748.04Min: 279.82 / Avg: 520.84 / Max: 752.65Min: 197.95 / Avg: 502.83 / Max: 704.5Min: 64.83 / Avg: 336.14 / Max: 677.28Min: 47.42 / Avg: 326.76 / Max: 695.89Min: 102.23 / Avg: 321.74 / Max: 579.82Min: 42.76 / Avg: 319.03 / Max: 648.26Min: 75.34 / Avg: 313.13 / Max: 540.33Min: 62.05 / Avg: 312.66 / Max: 592.38Min: 58.95 / Avg: 304.55 / Max: 634.68Min: 50.56 / Avg: 286.64 / Max: 586.7Min: 50.85 / Avg: 279.72 / Max: 571.62

OpenBenchmarking.orgTotal Mop/s Per Watt, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: IS.DXeon Max 9480 2PXeon Max 9480 2P - HBM OnlyXeon Platinum 8490H 2PEPYC 7773X 2PEPYC 9654 2PEPYC 9654 2P - Power 400WEPYC 9554 2P - Power 400WEPYC 9684X 2P - Power 400WEPYC 9554 2PEPYC 9754 2P - Power 400WEPYC 9684X 2PEPYC 9754 2P7142128355.5057.1457.24716.30224.99925.27526.45427.55127.61727.71928.44229.119

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: IS.DXeon Max 9480 2PXeon Platinum 8490H 2PXeon Max 9480 2P - HBM OnlyEPYC 7773X 2PEPYC 9554 2P - Power 400WEPYC 9654 2P - Power 400WEPYC 9554 2PEPYC 9654 2PEPYC 9754 2P - Power 400WEPYC 9684X 2PEPYC 9684X 2P - Power 400WEPYC 9754 2P2K4K6K8K10KSE +/- 149.62, N = 15SE +/- 19.30, N = 4SE +/- 232.54, N = 15SE +/- 69.03, N = 15SE +/- 127.05, N = 15SE +/- 169.04, N = 15SE +/- 198.65, N = 15SE +/- 169.13, N = 15SE +/- 192.87, N = 15SE +/- 227.70, N = 15SE +/- 297.02, N = 15SE +/- 146.87, N = 152867.343643.823976.145104.507582.727697.457725.207816.339057.559151.129261.039289.821. (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

OpenBenchmarking.orgWatts, Fewer Is BetterXcompact3d Incompact3d 2021-03-11CPU Power Consumption MonitorEPYC 9684X 2P - Power 400WEPYC 9654 2P - Power 400WXeon Max 9480 2P - HBM OnlyXeon Platinum 8490H 2PEPYC 9654 2PEPYC 9754 2P - Power 400WEPYC 9684X 2PEPYC 9754 2PEPYC 9554 2P - Power 400WEPYC 9554 2PXeon Max 9480 2PEPYC 7773X 2P2004006008001000Min: 64.66 / Avg: 733.16 / Max: 794.25Min: 58.02 / Avg: 710.68 / Max: 771.3Min: 290.01 / Avg: 689.98 / Max: 1116.33Min: 198.83 / Avg: 686.16 / Max: 730.73Min: 62.91 / Avg: 648.46 / Max: 684.86Min: 45.42 / Avg: 642.84 / Max: 708.21Min: 112.81 / Avg: 613.76 / Max: 641.22Min: 44.4 / Avg: 584.45 / Max: 632.47Min: 54.14 / Avg: 560.24 / Max: 611.03Min: 52.8 / Avg: 555.71 / Max: 602.08Min: 274.47 / Avg: 545.88 / Max: 887.32Min: 76.31 / Avg: 495.89 / Max: 539.44

OpenBenchmarking.orgSeconds, Fewer Is BetterXcompact3d Incompact3d 2021-03-11Input: X3D-benchmarking input.i3dEPYC 7773X 2PEPYC 9754 2P - Power 400WEPYC 9654 2PEPYC 9754 2PEPYC 9554 2P - Power 400WEPYC 9554 2PEPYC 9654 2P - Power 400WXeon Platinum 8490H 2PEPYC 9684X 2PXeon Max 9480 2PEPYC 9684X 2P - Power 400WXeon Max 9480 2P - HBM Only60120180240300SE +/- 0.60, N = 3SE +/- 7.88, N = 10SE +/- 6.85, N = 12SE +/- 5.48, N = 12SE +/- 4.85, N = 12SE +/- 4.96, N = 12SE +/- 6.42, N = 10SE +/- 0.05, N = 3SE +/- 5.14, N = 12SE +/- 0.27, N = 3SE +/- 2.39, N = 12SE +/- 0.40, N = 3264.85237.08221.99213.56210.67209.93202.56193.82172.53157.26121.40104.391. (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

ASKAP

OpenBenchmarking.orgWatts, Fewer Is BetterASKAP 1.0CPU Power Consumption MonitorXeon Max 9480 2P - HBM OnlyXeon Max 9480 2PXeon Platinum 8490H 2PEPYC 9684X 2P - Power 400WEPYC 9684X 2PEPYC 9654 2P - Power 400WEPYC 9654 2PEPYC 9554 2PEPYC 9554 2P - Power 400WEPYC 9754 2PEPYC 9754 2P - Power 400WEPYC 7773X 2P2004006008001000Min: 214.84 / Avg: 517.23 / Max: 1060.63Min: 224.73 / Avg: 499.55 / Max: 759.83Min: 172.94 / Avg: 471.71 / Max: 754.53Min: 65.15 / Avg: 367.13 / Max: 617.96Min: 114.02 / Avg: 345.26 / Max: 629.32Min: 57.67 / Avg: 329.99 / Max: 564.89Min: 60.9 / Avg: 323.5 / Max: 541.66Min: 52.46 / Avg: 278.88 / Max: 477.91Min: 52.22 / Avg: 278.66 / Max: 517.39Min: 42.96 / Avg: 266.26 / Max: 451.59Min: 46.5 / Avg: 265.01 / Max: 549.91Min: 70.03 / Avg: 261.97 / Max: 505.07

OpenBenchmarking.orgMillion Grid Points Per Second Per Watt, More Is BetterASKAP 1.0Test: tConvolve MT - DegriddingXeon Max 9480 2PXeon Max 9480 2P - HBM OnlyEPYC 9684X 2P - Power 400WEPYC 9654 2P - Power 400WXeon Platinum 8490H 2PEPYC 9654 2PEPYC 7773X 2PEPYC 9554 2PEPYC 9754 2PEPYC 9684X 2PEPYC 9554 2P - Power 400WEPYC 9754 2P - Power 400W132639526523.7024.8833.5334.6135.3539.6242.0645.7646.1053.0054.4258.80

OpenBenchmarking.orgMillion Grid Points Per Second, More Is BetterASKAP 1.0Test: tConvolve MT - DegriddingEPYC 7773X 2PEPYC 9654 2P - Power 400WXeon Max 9480 2PEPYC 9754 2PEPYC 9684X 2P - Power 400WEPYC 9554 2PEPYC 9654 2PXeon Max 9480 2P - HBM OnlyEPYC 9554 2P - Power 400WEPYC 9754 2P - Power 400WXeon Platinum 8490H 2PEPYC 9684X 2P4K8K12K16K20KSE +/- 279.37, N = 9SE +/- 255.26, N = 3SE +/- 594.43, N = 9SE +/- 79.95, N = 3SE +/- 80.53, N = 3SE +/- 460.78, N = 3SE +/- 224.95, N = 3SE +/- 350.77, N = 9SE +/- 772.33, N = 9SE +/- 1355.45, N = 9SE +/- 913.08, N = 9SE +/- 1833.85, N = 611018.4411420.4011840.9512273.6012311.0012762.4012817.6012870.8015165.2015582.4016676.7018298.901. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp

miniFE

OpenBenchmarking.orgWatts, Fewer Is BetterminiFE 2.2CPU Power Consumption MonitorXeon Max 9480 2P - HBM OnlyXeon Max 9480 2PXeon Platinum 8490H 2PEPYC 9684X 2P - Power 400WEPYC 9684X 2PEPYC 9654 2P - Power 400WEPYC 9654 2PEPYC 7773X 2PEPYC 9554 2P - Power 400WEPYC 9554 2PEPYC 9754 2P - Power 400WEPYC 9754 2P130260390520650Min: 279.39 / Avg: 525.56 / Max: 696.94Min: 309.77 / Avg: 494.12 / Max: 641.85Min: 189.31 / Avg: 442.47 / Max: 726.32Min: 65.76 / Avg: 318.34 / Max: 691.99Min: 111.43 / Avg: 308.78 / Max: 612.72Min: 58.67 / Avg: 296.18 / Max: 594.85Min: 62.5 / Avg: 289.26 / Max: 567.73Min: 75.02 / Avg: 283.5 / Max: 484.61Min: 55.63 / Avg: 255.49 / Max: 475.29Min: 52.04 / Avg: 253.61 / Max: 467.17Min: 53 / Avg: 248.43 / Max: 486.52Min: 43.63 / Avg: 243.12 / Max: 499.25

OpenBenchmarking.orgCG Mflops Per Watt, More Is BetterminiFE 2.2Problem Size: SmallXeon Max 9480 2PXeon Max 9480 2P - HBM OnlyEPYC 7773X 2PXeon Platinum 8490H 2PEPYC 9654 2P - Power 400WEPYC 9654 2PEPYC 9554 2PEPYC 9554 2P - Power 400WEPYC 9684X 2P - Power 400WEPYC 9684X 2PEPYC 9754 2P - Power 400WEPYC 9754 2P5010015020025041.5044.6683.0691.28181.10190.71205.51206.22208.53229.79240.11246.74

OpenBenchmarking.orgCG Mflops, More Is BetterminiFE 2.2Problem Size: SmallXeon Max 9480 2PXeon Max 9480 2P - HBM OnlyEPYC 7773X 2PXeon Platinum 8490H 2PEPYC 9554 2PEPYC 9554 2P - Power 400WEPYC 9654 2P - Power 400WEPYC 9654 2PEPYC 9754 2P - Power 400WEPYC 9754 2PEPYC 9684X 2P - Power 400WEPYC 9684X 2P15K30K45K60K75KSE +/- 640.81, N = 15SE +/- 537.92, N = 15SE +/- 570.34, N = 15SE +/- 243.91, N = 4SE +/- 436.84, N = 5SE +/- 176.36, N = 5SE +/- 1244.67, N = 15SE +/- 540.67, N = 5SE +/- 491.71, N = 5SE +/- 1371.46, N = 15SE +/- 548.90, N = 15SE +/- 2965.57, N = 1220503.923471.223547.740387.751915.152687.453638.555164.159651.059986.666383.170954.31. (CXX) g++ options: -O3 -fopenmp -lmpi_cxx -lmpi

80 Results Shown

Embree:
  Pathtracer ISPC - Asian Dragon
  Pathtracer ISPC - Asian Dragon Obj
  Pathtracer - Asian Dragon Obj
  Pathtracer ISPC - Crown
  Pathtracer - Asian Dragon
Xmrig:
  Wownero - 1M
  Monero - 1M
ASKAP:
  tConvolve MPI - Degridding
  tConvolve MPI - Gridding
OpenVINO
Blender
libxsmm
OSPRay Studio
libxsmm
OSPRay Studio:
  3 - 4K - 1 - Path Tracer
  3 - 1080p - 16 - Path Tracer
  1 - 1080p - 32 - Path Tracer
  1 - 4K - 32 - Path Tracer
  3 - 4K - 16 - Path Tracer
  3 - 1080p - 32 - Path Tracer
srsRAN Project
WRF
HeFFTe - Highly Efficient FFT for Exascale:
  r2c - FFTW - float - 512
  c2c - FFTW - float - 512
RELION
OpenVINO
High Performance Conjugate Gradient
Kvazaar
Algebraic Multi-Grid Benchmark
Kvazaar
NAS Parallel Benchmarks
HeFFTe - Highly Efficient FFT for Exascale
Xcompact3d Incompact3d
HeFFTe - Highly Efficient FFT for Exascale
libxsmm
HeFFTe - Highly Efficient FFT for Exascale
NAS Parallel Benchmarks
OpenFOAM
libxsmm
NAS Parallel Benchmarks
LeelaChessZero
NAS Parallel Benchmarks
GPAW
OpenVINO:
  Machine Translation EN To DE FP16 - CPU
  Vehicle Detection FP16 - CPU
Timed LLVM Compilation
Xcompact3d Incompact3d
Timed Linux Kernel Compilation
NAS Parallel Benchmarks
Timed Godot Game Engine Compilation
Timed Node.js Compilation
Liquid-DSP
OpenVINO
High Performance Conjugate Gradient
Z3 Theorem Prover
High Performance Conjugate Gradient
Timed PHP Compilation
High Performance Conjugate Gradient
CP2K Molecular Dynamics
OpenVINO
Timed LLVM Compilation
Z3 Theorem Prover
CPU Power Consumption Monitor:
  Phoronix Test Suite System Monitoring
  CPU Power Consumption Monitor
PostgreSQL:
  100 - 1000 - Read Only - Average Latency
  100 - 1000 - Read Only
PETSc:
  CPU Power Consumption Monitor
  Streams
PETSc
NAS Parallel Benchmarks:
  CPU Power Consumption Monitor
  IS.D
NAS Parallel Benchmarks
Xcompact3d Incompact3d
Xcompact3d Incompact3d
ASKAP:
  CPU Power Consumption Monitor
  tConvolve MT - Degridding
ASKAP
miniFE:
  CPU Power Consumption Monitor
  Small
miniFE