onnx 5950X

AMD Ryzen 9 5950X 16-Core testing with a ASUS ROG CROSSHAIR VIII HERO (WI-FI) (3904 BIOS) and AMD Radeon RX 6800 16GB on Ubuntu 22.04 via the Phoronix Test Suite.

Compare your own system(s) to this result file with the Phoronix Test Suite by running the command: phoronix-test-suite benchmark 2203313-NE-ONNX5950X50
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
A
March 31 2022
  1 Hour, 31 Minutes
B
March 31 2022
  1 Hour, 49 Minutes
C
March 31 2022
  25 Minutes
D
March 31 2022
  25 Minutes
E
March 31 2022
  2 Hours, 11 Minutes
Invert Hiding All Results Option
  1 Hour, 16 Minutes

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


onnx 5950XOpenBenchmarking.orgPhoronix Test SuiteAMD Ryzen 9 5950X 16-Core @ 3.40GHz (16 Cores / 32 Threads)ASUS ROG CROSSHAIR VIII HERO (WI-FI) (3904 BIOS)AMD Starship/Matisse32GB1000GB Sabrent Rocket 4.0 PlusAMD Radeon RX 6800 16GB (2475/1000MHz)AMD Navi 21 HDMI AudioASUS MG28URealtek RTL8125 2.5GbE + Intel I211 + Intel Wi-Fi 6 AX200Ubuntu 22.045.17.0-phx (x86_64)GNOME ShellX Server + Wayland4.6 Mesa 22.0.0 (LLVM 13.0.1 DRM 3.44)1.2.204GCC 11.2.0ext43840x2160ProcessorMotherboardChipsetMemoryDiskGraphicsAudioMonitorNetworkOSKernelDesktopDisplay ServerOpenGLVulkanCompilerFile-SystemScreen ResolutionOnnx 5950X BenchmarksSystem Logs- Transparent Huge Pages: madvise- --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-XWYfV6/gcc-11-11.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-XWYfV6/gcc-11-11.2.0/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-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 - Scaling Governor: acpi-cpufreq schedutil (Boost: Enabled) - CPU Microcode: 0xa201016 - Python 3.10.3- itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: 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 + srbds: Not affected + tsx_async_abort: Not affected

ABCDEResult OverviewPhoronix Test Suite100%116%131%147%162%ONNX RuntimeONNX RuntimeONNX RuntimeONNX RuntimeONNX RuntimeONNX RuntimeONNX RuntimeONNX RuntimeONNX RuntimeONNX RuntimeONNX RuntimeONNX Runtimesuper-resolution-10 - CPU - StandardArcFace ResNet-100 - CPU - Standardbertsquad-12 - CPU - Standardyolov4 - CPU - Standardfcn-resnet101-11 - CPU - StandardGPT-2 - CPU - Standardsuper-resolution-10 - CPU - Parallelfcn-resnet101-11 - CPU - ParallelArcFace ResNet-100 - CPU - ParallelGPT-2 - CPU - Parallelbertsquad-12 - CPU - Parallelyolov4 - CPU - Parallel

onnx 5950Xonnx: GPT-2 - CPU - Parallelonnx: GPT-2 - CPU - Standardonnx: yolov4 - CPU - Parallelonnx: yolov4 - CPU - Standardonnx: bertsquad-12 - CPU - Parallelonnx: bertsquad-12 - CPU - Standardonnx: fcn-resnet101-11 - CPU - Parallelonnx: fcn-resnet101-11 - CPU - Standardonnx: ArcFace ResNet-100 - CPU - Parallelonnx: ArcFace ResNet-100 - CPU - Standardonnx: super-resolution-10 - CPU - Parallelonnx: super-resolution-10 - CPU - StandardABCDE549672282954725498518989151215306385619454707398296471550795899615071519647061025494742329545955010409088150215596561611754927222295487548807898815052073644199005481725729557855083989881512156064389274OpenBenchmarking.org

ONNX Runtime

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

OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.11Model: GPT-2 - Device: CPU - Executor: ParallelABCDE12002400360048006000SE +/- 9.83, N = 3SE +/- 7.44, N = 3SE +/- 4.09, N = 3549654705494549254811. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt
OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.11Model: GPT-2 - Device: CPU - Executor: ParallelABCDE10002000300040005000Min: 5478 / Avg: 5495.5 / Max: 5512Min: 5458 / Avg: 5469.67 / Max: 5483.5Min: 5472.5 / Avg: 5480.5 / Max: 54861. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.11Model: GPT-2 - Device: CPU - Executor: StandardABCDE16003200480064008000SE +/- 14.58, N = 3SE +/- 57.62, N = 3SE +/- 81.11, N = 5722873987423722272571. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt
OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.11Model: GPT-2 - Device: CPU - Executor: StandardABCDE13002600390052006500Min: 7200.5 / Avg: 7228.17 / Max: 7250Min: 7283.5 / Avg: 7398.17 / Max: 7465.5Min: 6982 / Avg: 7257.1 / Max: 74571. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.11Model: yolov4 - Device: CPU - Executor: ParallelABCDE60120180240300SE +/- 0.17, N = 3SE +/- 0.00, N = 3SE +/- 0.33, N = 32952962952952951. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt
OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.11Model: yolov4 - Device: CPU - Executor: ParallelABCDE50100150200250Min: 295 / Avg: 295.17 / Max: 295.5Min: 296 / Avg: 296 / Max: 296Min: 294.5 / Avg: 295.17 / Max: 295.51. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.11Model: yolov4 - Device: CPU - Executor: StandardABCDE120240360480600SE +/- 5.64, N = 3SE +/- 12.61, N = 12SE +/- 20.18, N = 124724714594875781. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt
OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.11Model: yolov4 - Device: CPU - Executor: StandardABCDE100200300400500Min: 463 / Avg: 472.33 / Max: 482.5Min: 457.5 / Avg: 471.33 / Max: 610Min: 460 / Avg: 578.38 / Max: 619.51. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.11Model: bertsquad-12 - Device: CPU - Executor: ParallelABCDE120240360480600SE +/- 1.26, N = 3SE +/- 0.73, N = 3SE +/- 0.60, N = 35495505505485501. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt
OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.11Model: bertsquad-12 - Device: CPU - Executor: ParallelABCDE100200300400500Min: 546 / Avg: 548.5 / Max: 550Min: 549 / Avg: 550.17 / Max: 551.5Min: 549 / Avg: 549.83 / Max: 5511. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.11Model: bertsquad-12 - Device: CPU - Executor: StandardABCDE2004006008001000SE +/- 29.27, N = 12SE +/- 2.08, N = 3SE +/- 27.88, N = 1285179510408078391. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt
OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.11Model: bertsquad-12 - Device: CPU - Executor: StandardABCDE2004006008001000Min: 793.5 / Avg: 851.21 / Max: 1044Min: 792 / Avg: 795 / Max: 799Min: 782.5 / Avg: 839.08 / Max: 1047.51. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.11Model: fcn-resnet101-11 - Device: CPU - Executor: ParallelABCDE20406080100SE +/- 0.58, N = 3SE +/- 0.29, N = 3SE +/- 0.17, N = 389899089891. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt
OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.11Model: fcn-resnet101-11 - Device: CPU - Executor: ParallelABCDE20406080100Min: 88 / Avg: 89 / Max: 90Min: 88.5 / Avg: 89 / Max: 89.5Min: 89 / Avg: 89.17 / Max: 89.51. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.11Model: fcn-resnet101-11 - Device: CPU - Executor: StandardABCDE20406080100SE +/- 0.17, N = 3SE +/- 4.37, N = 12SE +/- 0.17, N = 389968888881. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt
OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.11Model: fcn-resnet101-11 - Device: CPU - Executor: StandardABCDE20406080100Min: 89 / Avg: 89.33 / Max: 89.5Min: 88.5 / Avg: 95.58 / Max: 128Min: 88 / Avg: 88.17 / Max: 88.51. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.11Model: ArcFace ResNet-100 - Device: CPU - Executor: ParallelABCDE30060090012001500SE +/- 4.41, N = 3SE +/- 2.74, N = 3SE +/- 5.21, N = 3151215071502150515121. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt
OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.11Model: ArcFace ResNet-100 - Device: CPU - Executor: ParallelABCDE30060090012001500Min: 1505 / Avg: 1511.67 / Max: 1520Min: 1502 / Avg: 1506.83 / Max: 1511.5Min: 1503.5 / Avg: 1512.17 / Max: 1521.51. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.11Model: ArcFace ResNet-100 - Device: CPU - Executor: StandardABCDE400800120016002000SE +/- 0.33, N = 3SE +/- 14.19, N = 3SE +/- 3.35, N = 3153015191559207315601. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt
OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.11Model: ArcFace ResNet-100 - Device: CPU - Executor: StandardABCDE400800120016002000Min: 1530 / Avg: 1530.33 / Max: 1531Min: 1490.5 / Avg: 1518.5 / Max: 1536.5Min: 1556 / Avg: 1559.83 / Max: 1566.51. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.11Model: super-resolution-10 - Device: CPU - Executor: ParallelABCDE14002800420056007000SE +/- 21.25, N = 3SE +/- 55.62, N = 3SE +/- 56.56, N = 3638564706561644164381. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt
OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.11Model: super-resolution-10 - Device: CPU - Executor: ParallelABCDE11002200330044005500Min: 6347 / Avg: 6385 / Max: 6420.5Min: 6364 / Avg: 6470.17 / Max: 6552Min: 6326 / Avg: 6437.83 / Max: 6508.51. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.11Model: super-resolution-10 - Device: CPU - Executor: StandardABCDE2K4K6K8K10KSE +/- 26.96, N = 3SE +/- 28.01, N = 3SE +/- 429.03, N = 12619461026117990092741. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt
OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.11Model: super-resolution-10 - Device: CPU - Executor: StandardABCDE2K4K6K8K10KMin: 6149.5 / Avg: 6193.5 / Max: 6242.5Min: 6051 / Avg: 6102.17 / Max: 6147.5Min: 6091.5 / Avg: 9274.04 / Max: 9939.51. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt