EPYC 7551 ONNX

AMD EPYC 7551 32-Core testing with a GIGABYTE MZ31-AR0-00 v01010101 (F10 BIOS) and ASPEED on Debian 10 via the Phoronix Test Suite.

Compare your own system(s) to this result file with the Phoronix Test Suite by running the command: phoronix-test-suite benchmark 2101177-HA-EPYC7551O38
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

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
Prefer Vertical Bar Graphs

Multi-Way Comparison

Condense Multi-Option Tests Into Single Result Graphs

Table

Show Detailed System Result Table

Run Management

Highlight
Result
Hide
Result
Result
Identifier
View Logs
Performance Per
Dollar
Date
Run
  Test
  Duration
1
January 17 2021
  28 Minutes
2
January 17 2021
  37 Minutes
3
January 17 2021
  41 Minutes
4
January 17 2021
  47 Minutes
5
January 17 2021
  22 Minutes
Invert Hiding All Results Option
  35 Minutes

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


EPYC 7551 ONNXProcessorMotherboardChipsetMemoryDiskGraphicsNetworkOSKernelCompilerFile-SystemScreen Resolution12345AMD EPYC 7551 32-Core @ 2.00GHz (32 Cores / 64 Threads)GIGABYTE MZ31-AR0-00 v01010101 (F10 BIOS)AMD 17h32GBSamsung SSD 960 EVO 500GBASPEEDRealtek RTL8111/8168/8411 + 2 x Broadcom NetXtreme II BCM57810 10Debian 104.19.0-10-amd64 (x86_64)GCC 8.3.0ext41024x768OpenBenchmarking.orgCompiler Details- --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --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++ --enable-libmpx --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none --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 --with-tune=generic --without-cuda-driver -v Processor Details- Scaling Governor: acpi-cpufreq ondemand (Boost: Enabled) - CPU Microcode: 0x8001227Python Details- Python 2.7.16 + Python 3.7.3Security Details- itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional STIBP: disabled RSB filling + srbds: Not affected + tsx_async_abort: Not affected

EPYC 7551 ONNXonnx: yolov4 - OpenMP CPUonnx: bertsquad-10 - OpenMP CPUonnx: fcn-resnet101-11 - OpenMP CPUonnx: shufflenet-v2-10 - OpenMP CPUonnx: super-resolution-10 - OpenMP CPU123451221634545331614104179434413163811417544424315991091734143311611123179OpenBenchmarking.org

ONNX Runtime

OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.6Model: yolov4 - Device: OpenMP CPU12345306090120150SE +/- 1.00, N = 3SE +/- 1.20, N = 3SE +/- 2.56, N = 15SE +/- 3.76, N = 12SE +/- 1.32, N = 151221041141091231. (CXX) g++ options: -fopenmp -ffunction-sections -fdata-sections -O3 -ldl -lrt
OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.6Model: yolov4 - Device: OpenMP CPU1234520406080100Min: 121 / Avg: 122 / Max: 124Min: 102 / Avg: 103.67 / Max: 106Min: 103 / Avg: 114.13 / Max: 140Min: 89 / Avg: 108.92 / Max: 137Min: 111 / Avg: 122.67 / Max: 1301. (CXX) g++ options: -fopenmp -ffunction-sections -fdata-sections -O3 -ldl -lrt

OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.6Model: bertsquad-10 - Device: OpenMP CPU123454080120160200SE +/- 2.33, N = 15SE +/- 0.88, N = 3SE +/- 2.71, N = 15SE +/- 2.51, N = 61631791751731791. (CXX) g++ options: -fopenmp -ffunction-sections -fdata-sections -O3 -ldl -lrt
OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.6Model: bertsquad-10 - Device: OpenMP CPU12345306090120150Min: 149 / Avg: 162.53 / Max: 178Min: 177 / Avg: 178.67 / Max: 180Min: 156 / Avg: 173.13 / Max: 189Min: 170 / Avg: 178.83 / Max: 1841. (CXX) g++ options: -fopenmp -ffunction-sections -fdata-sections -O3 -ldl -lrt

OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.6Model: fcn-resnet101-11 - Device: OpenMP CPU12341020304050SE +/- 0.88, N = 3SE +/- 1.44, N = 12454344411. (CXX) g++ options: -fopenmp -ffunction-sections -fdata-sections -O3 -ldl -lrt
OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.6Model: fcn-resnet101-11 - Device: OpenMP CPU1234918273645Min: 44 / Avg: 45.33 / Max: 47Min: 31 / Avg: 43.33 / Max: 491. (CXX) g++ options: -fopenmp -ffunction-sections -fdata-sections -O3 -ldl -lrt

OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.6Model: shufflenet-v2-10 - Device: OpenMP CPU123410002000300040005000SE +/- 57.74, N = 3SE +/- 43.12, N = 15SE +/- 62.34, N = 3SE +/- 47.12, N = 345334413424343311. (CXX) g++ options: -fopenmp -ffunction-sections -fdata-sections -O3 -ldl -lrt
OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.6Model: shufflenet-v2-10 - Device: OpenMP CPU12348001600240032004000Min: 4418 / Avg: 4533.33 / Max: 4596Min: 3992 / Avg: 4412.8 / Max: 4629Min: 4130 / Avg: 4243.33 / Max: 4345Min: 4260 / Avg: 4330.67 / Max: 44201. (CXX) g++ options: -fopenmp -ffunction-sections -fdata-sections -O3 -ldl -lrt

OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.6Model: super-resolution-10 - Device: OpenMP CPU1234400800120016002000SE +/- 5.13, N = 3SE +/- 10.33, N = 3SE +/- 6.08, N = 3SE +/- 13.64, N = 316141638159916111. (CXX) g++ options: -fopenmp -ffunction-sections -fdata-sections -O3 -ldl -lrt
OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.6Model: super-resolution-10 - Device: OpenMP CPU123430060090012001500Min: 1607 / Avg: 1614 / Max: 1624Min: 1623 / Avg: 1638.33 / Max: 1658Min: 1589 / Avg: 1599 / Max: 1610Min: 1593 / Avg: 1611.33 / Max: 16381. (CXX) g++ options: -fopenmp -ffunction-sections -fdata-sections -O3 -ldl -lrt