OpenVINO AMX Benchmarks AMD EPYC Genoa

Benchmarks by Michael Larabel for a future article.

HTML result view exported from: https://openbenchmarking.org/result/2301166-NE-OPENVINOA64&gru&sro.

OpenVINO AMX Benchmarks AMD EPYC GenoaProcessorMotherboardChipsetMemoryDiskGraphicsMonitorNetworkOSKernelDesktopDisplay ServerVulkanCompilerFile-SystemScreen ResolutionXeon Platinum 8490H 2PXeon Platinum 8490H 2P - No AMXEPYC 9654 2P2 x Intel Xeon Platinum 8490H @ 3.50GHz (120 Cores / 240 Threads)Quanta Cloud S6Q-MB-MPS (3A10.uh BIOS)Intel Device 1bce16 x 64 GB 4800MT/s Samsung M321R8GA0BB0-CQKEG2 x 1920GB SAMSUNG MZWLJ1T9HBJR-00007 + 960GB INTEL SSDSC2KG96ASPEEDVGA HDMI4 x Intel E810-C for QSFP + 2 x Intel X710 for 10GBASE-TUbuntu 22.046.1.4-060104-generic (x86_64)GNOME Shell 42.2X Server 1.21.1.31.2.204GCC 11.3.0 + Clang 14.0.0-1ubuntu1ext41920x10802 x AMD EPYC 9654 96-Core @ 2.40GHz (192 Cores / 384 Threads)AMD Titanite_4G (RTI1002E BIOS)AMD Device 14a424 x 64 GB 4800MT/s Samsung M321R8GA0BB0-CQKEG2 x 1920GB SAMSUNG MZWLJ1T9HBJR-00007Broadcom NetXtreme BCM5720 PCIeOpenBenchmarking.orgKernel Details- Transparent Huge Pages: madviseCompiler Details- --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-11-xKiWfi/gcc-11-11.3.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-xKiWfi/gcc-11-11.3.0/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-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 Processor Details- Xeon Platinum 8490H 2P: Scaling Governor: intel_pstate performance (EPP: performance) - CPU Microcode: 0x2b0000c0- Xeon Platinum 8490H 2P - No AMX: Scaling Governor: intel_pstate performance (EPP: performance) - CPU Microcode: 0x2b0000c0- EPYC 9654 2P: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa10110dPython Details- Python 3.10.6Security Details- 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 Platinum 8490H 2P - No AMX: 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 - 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

OpenVINO AMX Benchmarks AMD EPYC Genoaopenvino: Face Detection FP16-INT8 - CPUopenvino: Weld Porosity Detection FP16-INT8 - CPUopenvino: Person Vehicle Bike Detection FP16 - CPUopenvino: Machine Translation EN To DE FP16 - CPUopenvino: Face Detection FP16-INT8 - CPUopenvino: Weld Porosity Detection FP16-INT8 - CPUopenvino: Person Vehicle Bike Detection FP16 - CPUopenvino: Machine Translation EN To DE FP16 - CPUXeon Platinum 8490H 2PXeon Platinum 8490H 2P - No AMXEPYC 9654 2P282.2523066.634778.34724.10424.165.1825.0982.79146.088897.102730.07321.28409.8113.4621.95186.53188.6418678.165320.83989.16507.2510.2618.0397.00OpenBenchmarking.org

CPU Peak Freq (Highest CPU Core Frequency) Monitor

Phoronix Test Suite System Monitoring

OpenBenchmarking.orgMegahertzCPU Peak Freq (Highest CPU Core Frequency) MonitorPhoronix Test Suite System MonitoringEPYC 9654 2PXeon Platinum 8490H 2PXeon Platinum 8490H 2P - No AMX7001400210028003500Min: 2400 / Avg: 3129.46 / Max: 3763Min: 1900 / Avg: 2744.33 / Max: 3516Min: 1000 / Avg: 2603.67 / Max: 3512

CPU Power Consumption Monitor

Phoronix Test Suite System Monitoring

OpenBenchmarking.orgWattsCPU Power Consumption MonitorPhoronix Test Suite System MonitoringEPYC 9654 2PXeon Platinum 8490H 2PXeon Platinum 8490H 2P - No AMX130260390520650Min: 53.42 / Avg: 596.25 / Max: 739.81Min: 208.07 / Avg: 624.35 / Max: 760.79Min: 122.95 / Avg: 646.09 / Max: 763.9

OpenVINO

Model: Face Detection FP16-INT8 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.3Model: Face Detection FP16-INT8 - Device: CPUEPYC 9654 2PXeon Platinum 8490H 2PXeon Platinum 8490H 2P - No AMX60120180240300SE +/- 0.17, N = 3SE +/- 2.56, N = 3SE +/- 0.29, N = 3188.64282.25146.081. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl

OpenVINO

Model: Weld Porosity Detection FP16-INT8 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.3Model: Weld Porosity Detection FP16-INT8 - Device: CPUEPYC 9654 2PXeon Platinum 8490H 2PXeon Platinum 8490H 2P - No AMX5K10K15K20K25KSE +/- 10.84, N = 3SE +/- 92.31, N = 3SE +/- 24.48, N = 318678.1623066.638897.101. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl

OpenVINO

Model: Person Vehicle Bike Detection FP16 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.3Model: Person Vehicle Bike Detection FP16 - Device: CPUEPYC 9654 2PXeon Platinum 8490H 2PXeon Platinum 8490H 2P - No AMX11002200330044005500SE +/- 44.61, N = 8SE +/- 14.65, N = 3SE +/- 11.17, N = 35320.834778.342730.071. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl

OpenVINO

Model: Machine Translation EN To DE FP16 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.3Model: Machine Translation EN To DE FP16 - Device: CPUEPYC 9654 2PXeon Platinum 8490H 2PXeon Platinum 8490H 2P - No AMX2004006008001000SE +/- 8.13, N = 8SE +/- 5.21, N = 3SE +/- 0.77, N = 3989.16724.10321.281. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl

OpenVINO

CPU Peak Freq (Highest CPU Core Frequency) Monitor

MinAvgMaxEPYC 9654 2P240029903702Xeon Platinum 8490H 2P190025613507Xeon Platinum 8490H 2P - No AMX123123743508OpenBenchmarking.orgMegahertz, More Is BetterOpenVINO 2022.3CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000

OpenVINO

CPU Peak Freq (Highest CPU Core Frequency) Monitor

MinAvgMaxEPYC 9654 2P240028093702Xeon Platinum 8490H 2P190028603501Xeon Platinum 8490H 2P - No AMX190029283512OpenBenchmarking.orgMegahertz, More Is BetterOpenVINO 2022.3CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000

OpenVINO

CPU Peak Freq (Highest CPU Core Frequency) Monitor

MinAvgMaxEPYC 9654 2P240034933763Xeon Platinum 8490H 2P190029653501Xeon Platinum 8490H 2P - No AMX190027393511OpenBenchmarking.orgMegahertz, More Is BetterOpenVINO 2022.3CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000

OpenVINO

CPU Peak Freq (Highest CPU Core Frequency) Monitor

MinAvgMaxEPYC 9654 2P240029653700Xeon Platinum 8490H 2P190027923516Xeon Platinum 8490H 2P - No AMX190026563508OpenBenchmarking.orgMegahertz, More Is BetterOpenVINO 2022.3CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000

OpenVINO

Model: Face Detection FP16-INT8 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.3Model: Face Detection FP16-INT8 - Device: CPUEPYC 9654 2PXeon Platinum 8490H 2PXeon Platinum 8490H 2P - No AMX110220330440550SE +/- 0.31, N = 3SE +/- 3.75, N = 3SE +/- 0.81, N = 3507.25424.16409.81MIN: 231.44 / MAX: 623.69MIN: 153.43 / MAX: 1952.95MIN: 203.37 / MAX: 909.921. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl

OpenVINO

Model: Weld Porosity Detection FP16-INT8 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.3Model: Weld Porosity Detection FP16-INT8 - Device: CPUEPYC 9654 2PXeon Platinum 8490H 2PXeon Platinum 8490H 2P - No AMX3691215SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.04, N = 310.265.1813.46MIN: 4.21 / MAX: 95.33MIN: 1.43 / MAX: 102.62MIN: 3.82 / MAX: 88.111. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl

OpenVINO

Model: Person Vehicle Bike Detection FP16 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.3Model: Person Vehicle Bike Detection FP16 - Device: CPUEPYC 9654 2PXeon Platinum 8490H 2PXeon Platinum 8490H 2P - No AMX612182430SE +/- 0.15, N = 8SE +/- 0.08, N = 3SE +/- 0.09, N = 318.0325.0921.95MIN: 5.34 / MAX: 112.51MIN: 11.66 / MAX: 132.09MIN: 11.62 / MAX: 120.041. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl

OpenVINO

Model: Machine Translation EN To DE FP16 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.3Model: Machine Translation EN To DE FP16 - Device: CPUEPYC 9654 2PXeon Platinum 8490H 2PXeon Platinum 8490H 2P - No AMX4080120160200SE +/- 0.78, N = 8SE +/- 0.60, N = 3SE +/- 0.45, N = 397.0082.79186.53MIN: 41.26 / MAX: 1899.38MIN: 31.64 / MAX: 1588.97MIN: 92.82 / MAX: 808.71. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl

OpenVINO

CPU Power Consumption Monitor

MinAvgMaxEPYC 9654 2P54602717Xeon Platinum 8490H 2P208616761Xeon Platinum 8490H 2P - No AMX210641748OpenBenchmarking.orgWatts, Fewer Is BetterOpenVINO 2022.3CPU Power Consumption Monitor2004006008001000

OpenVINO

CPU Power Consumption Monitor

MinAvgMaxEPYC 9654 2P59652717Xeon Platinum 8490H 2P217663757Xeon Platinum 8490H 2P - No AMX210665756OpenBenchmarking.orgWatts, Fewer Is BetterOpenVINO 2022.3CPU Power Consumption Monitor2004006008001000

OpenVINO

CPU Power Consumption Monitor

MinAvgMaxEPYC 9654 2P55567643Xeon Platinum 8490H 2P213640755Xeon Platinum 8490H 2P - No AMX132653756OpenBenchmarking.orgWatts, Fewer Is BetterOpenVINO 2022.3CPU Power Consumption Monitor2004006008001000

OpenVINO

CPU Power Consumption Monitor

MinAvgMaxEPYC 9654 2P55650740Xeon Platinum 8490H 2P212644742Xeon Platinum 8490H 2P - No AMX211652756OpenBenchmarking.orgWatts, Fewer Is BetterOpenVINO 2022.3CPU Power Consumption Monitor2004006008001000

Phoronix Test Suite v10.8.4