onnx new

AMD Ryzen 7 7840U testing with a PHX Swift SFE16-43 Ray_PEU (V1.04 BIOS) and AMD Phoenix1 512MB on Ubuntu 23.10 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 2402036-NE-ONNXNEW5418
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
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
Toggle/Hide
Result
Result
Identifier
Performance Per
Dollar
Date
Run
  Test
  Duration
a
February 03
  41 Minutes
b
February 03
  5 Hours, 32 Minutes
c
February 03
  41 Minutes
Invert Behavior (Only Show Selected Data)
  2 Hours, 18 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):

a

Kernel Notes: Transparent Huge Pages: madvise
Compiler Notes: --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,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-defaulted --enable-offload-targets=nvptx-none=/build/gcc-13-XYspKM/gcc-13-13.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-13-XYspKM/gcc-13-13.2.0/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
Processor Notes: Scaling Governor: amd-pstate-epp powersave (EPP: performance) - CPU Microcode: 0xa704101
Python Notes: Python 3.11.6
Security Notes: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_rstack_overflow: Vulnerable: Safe RET no microcode + 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 / Automatic IBRS IBPB: conditional STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected

b

c

Processor: AMD Ryzen 7 7840U @ 5.29GHz (8 Cores / 16 Threads), Motherboard: PHX Swift SFE16-43 Ray_PEU (V1.04 BIOS), Chipset: AMD Device 14e8, Memory: 4 x 4GB DRAM-6400MT/s K3LKBKB0BM-MGCP, Disk: 1024GB Micron_3400_MTFDKBA1T0TFH, Graphics: AMD Phoenix1 512MB (2700/800MHz), Audio: AMD Rembrandt Radeon HD Audio, Network: MEDIATEK MT7922 802.11ax PCI

OS: Ubuntu 23.10, Kernel: 6.7.0-060700-generic (x86_64), Desktop: GNOME Shell 45.2, Display Server: X Server + Wayland, OpenGL: 4.6 Mesa 24.1~git2401230600.42fc83~oibaf~m (git-42fc83a 2024-01-23 mantic-oibaf-ppa) (LLVM 16.0.6 DRM 3.56), Compiler: GCC 13.2.0, File-System: ext4, Screen Resolution: 3200x2000

onnx newOpenBenchmarking.orgPhoronix Test SuiteAMD Ryzen 7 7840U @ 5.29GHz (8 Cores / 16 Threads)PHX Swift SFE16-43 Ray_PEU (V1.04 BIOS)AMD Device 14e84 x 4GB DRAM-6400MT/s K3LKBKB0BM-MGCP1024GB Micron_3400_MTFDKBA1T0TFHAMD Phoenix1 512MB (2700/800MHz)AMD Rembrandt Radeon HD AudioMEDIATEK MT7922 802.11ax PCIUbuntu 23.106.7.0-060700-generic (x86_64)GNOME Shell 45.2X Server + Wayland4.6 Mesa 24.1~git2401230600.42fc83~oibaf~m (git-42fc83a 2024-01-23 mantic-oibaf-ppa) (LLVM 16.0.6 DRM 3.56)GCC 13.2.0ext43200x2000ProcessorMotherboardChipsetMemoryDiskGraphicsAudioNetworkOSKernelDesktopDisplay ServerOpenGLCompilerFile-SystemScreen ResolutionOnnx New 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,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-defaulted --enable-offload-targets=nvptx-none=/build/gcc-13-XYspKM/gcc-13-13.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-13-XYspKM/gcc-13-13.2.0/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: amd-pstate-epp powersave (EPP: performance) - CPU Microcode: 0xa704101- Python 3.11.6- gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_rstack_overflow: Vulnerable: Safe RET no microcode + 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 / Automatic IBRS IBPB: conditional STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected

abcResult OverviewPhoronix Test Suite100%113%126%139%152%ONNX RuntimeONNX RuntimeONNX RuntimeONNX RuntimeONNX RuntimeONNX RuntimeONNX RuntimeONNX RuntimeONNX RuntimeONNX RuntimeONNX RuntimeONNX RuntimeONNX RuntimeONNX RuntimeONNX RuntimeONNX RuntimeONNX RuntimeONNX RuntimeONNX RuntimeONNX RuntimeONNX RuntimeONNX RuntimeONNX RuntimeONNX RuntimeONNX RuntimeONNX RuntimeONNX RuntimeONNX RuntimeONNX RuntimeONNX RuntimeONNX RuntimeONNX RuntimeONNX RuntimeONNX RuntimeONNX RuntimeONNX RuntimeONNX RuntimeONNX RuntimeONNX RuntimeONNX RuntimeArcFace ResNet-100 - CPU - Standardsuper-resolution-10 - CPU - Standardyolov4 - CPU - Standardbertsquad-12 - CPU - StandardF.R.C.R.5.F.i - CPU - Standardbertsquad-12 - CPU - Parallelfcn-resnet101-11 - CPU - StandardR.v.1.i - CPU - StandardR.v.1.i - CPU - Parallelfcn-resnet101-11 - CPU - Parallelsuper-resolution-10 - CPU - Parallelyolov4 - CPU - ParallelArcFace ResNet-100 - CPU - ParallelCaffeNet 12-int8 - CPU - ParallelCaffeNet 12-int8 - CPU - StandardGPT-2 - CPU - StandardF.R.C.R.5.F.i - CPU - ParallelT5 Encoder - CPU - StandardGPT-2 - CPU - ParallelT5 Encoder - CPU - Parallelfcn-resnet101-11 - CPU - ParallelGPT-2 - CPU - Standardyolov4 - CPU - Parallelbertsquad-12 - CPU - StandardArcFace ResNet-100 - CPU - StandardCaffeNet 12-int8 - CPU - Standardsuper-resolution-10 - CPU - StandardF.R.C.R.5.F.i - CPU - Standardyolov4 - CPU - Standardfcn-resnet101-11 - CPU - StandardF.R.C.R.5.F.i - CPU - ParallelGPT-2 - CPU - Parallelbertsquad-12 - CPU - ParallelT5 Encoder - CPU - StandardT5 Encoder - CPU - ParallelArcFace ResNet-100 - CPU - ParallelCaffeNet 12-int8 - CPU - ParallelR.v.1.i - CPU - StandardR.v.1.i - CPU - Parallelsuper-resolution-10 - CPU - Parallel

onnx newonnx: fcn-resnet101-11 - CPU - Parallelonnx: fcn-resnet101-11 - CPU - Parallelonnx: GPT-2 - CPU - Standardonnx: GPT-2 - CPU - Standardonnx: yolov4 - CPU - Parallelonnx: yolov4 - CPU - Parallelonnx: bertsquad-12 - CPU - Standardonnx: bertsquad-12 - CPU - Standardonnx: ArcFace ResNet-100 - CPU - Standardonnx: ArcFace ResNet-100 - CPU - Standardonnx: CaffeNet 12-int8 - CPU - Standardonnx: CaffeNet 12-int8 - CPU - Standardonnx: super-resolution-10 - CPU - Standardonnx: super-resolution-10 - CPU - Standardonnx: Faster R-CNN R-50-FPN-int8 - CPU - Standardonnx: Faster R-CNN R-50-FPN-int8 - CPU - Standardonnx: yolov4 - CPU - Standardonnx: yolov4 - CPU - Standardonnx: fcn-resnet101-11 - CPU - Standardonnx: fcn-resnet101-11 - CPU - Standardonnx: Faster R-CNN R-50-FPN-int8 - CPU - Parallelonnx: Faster R-CNN R-50-FPN-int8 - CPU - Parallelonnx: GPT-2 - CPU - Parallelonnx: GPT-2 - CPU - Parallelonnx: bertsquad-12 - CPU - Parallelonnx: bertsquad-12 - CPU - Parallelonnx: T5 Encoder - CPU - Standardonnx: T5 Encoder - CPU - Standardonnx: T5 Encoder - CPU - Parallelonnx: T5 Encoder - CPU - Parallelonnx: ArcFace ResNet-100 - CPU - Parallelonnx: ArcFace ResNet-100 - CPU - Parallelonnx: CaffeNet 12-int8 - CPU - Parallelonnx: CaffeNet 12-int8 - CPU - Parallelonnx: ResNet50 v1-12-int8 - CPU - Standardonnx: ResNet50 v1-12-int8 - CPU - Standardonnx: ResNet50 v1-12-int8 - CPU - Parallelonnx: ResNet50 v1-12-int8 - CPU - Parallelonnx: super-resolution-10 - CPU - Parallelonnx: super-resolution-10 - CPU - Parallelabc1302.650.76766410.054999.3804177.9845.6184123.9788.0656336.368127.49542.28112438.1111.199989.270823.468842.6044180.2825.54675764.7981.3075327.774936.001110.895691.7451120.4258.303767.96284125.558.57597116.58454.196718.45072.37678420.3794.80345208.1185.00581199.72216.365661.10051368.270.7333999.99957100.2755186.8505.35577106.16739.8529050.386420.55542.45823407.24414.680070.412022.796344.0531148.7406.84051849.8631.1767029.004234.476410.952391.2732135.5047.382268.10241123.3908.64193115.70958.784617.01172.53589394.1015.22787191.2455.47098182.76617.868655.96161247.80.8014069.35371106.849171.9295.81626123.4428.1007155.121318.14092.32098430.53711.24188.943825.680338.936179.5975.56792756.2451.3223127.555636.287710.751492.9737119.7778.348668.18943122.0758.51836117.37254.998618.18182.35443424.3184.75585210.2065.04136198.32916.738559.7402OpenBenchmarking.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 Model Zoo. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: fcn-resnet101-11 - Device: CPU - Executor: Parallelbac30060090012001500SE +/- 21.12, N = 151368.271302.651247.801. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.17Model: fcn-resnet101-11 - Device: CPU - Executor: Parallelbac0.18030.36060.54090.72120.9015SE +/- 0.011857, N = 150.7333990.7676640.8014061. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: fcn-resnet101-11 - Device: CPU - Executor: Parallelbac30060090012001500SE +/- 21.12, N = 151368.271302.651247.801. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: GPT-2 - Device: CPU - Executor: Standardabc3691215SE +/- 0.15979, N = 1510.054909.999579.353711. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.17Model: GPT-2 - Device: CPU - Executor: Standardabc20406080100SE +/- 1.54, N = 1599.38100.28106.851. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: GPT-2 - Device: CPU - Executor: Standardabc3691215SE +/- 0.15979, N = 1510.054909.999579.353711. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: yolov4 - Device: CPU - Executor: Parallelbac4080120160200SE +/- 1.39, N = 15186.85177.98171.931. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.17Model: yolov4 - Device: CPU - Executor: Parallelbac1.30872.61743.92615.23486.5435SE +/- 0.03837, N = 155.355775.618405.816261. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: yolov4 - Device: CPU - Executor: Parallelbac4080120160200SE +/- 1.39, N = 15186.85177.98171.931. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: bertsquad-12 - Device: CPU - Executor: Standardacb306090120150SE +/- 6.20, N = 15123.98123.44106.171. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.17Model: bertsquad-12 - Device: CPU - Executor: Standardacb3691215SE +/- 0.53109, N = 158.065638.100719.852901. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: bertsquad-12 - Device: CPU - Executor: Standardacb306090120150SE +/- 6.20, N = 15123.98123.44106.171. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: ArcFace ResNet-100 - Device: CPU - Executor: Standardcba1224364860SE +/- 2.47, N = 1555.1250.3936.371. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.17Model: ArcFace ResNet-100 - Device: CPU - Executor: Standardcba612182430SE +/- 1.03, N = 1518.1420.5627.501. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: ArcFace ResNet-100 - Device: CPU - Executor: Standardcba1224364860SE +/- 2.47, N = 1555.1250.3936.371. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: CaffeNet 12-int8 - Device: CPU - Executor: Standardbca0.55311.10621.65932.21242.7655SE +/- 0.02717, N = 152.458232.320982.281121. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.17Model: CaffeNet 12-int8 - Device: CPU - Executor: Standardbca90180270360450SE +/- 4.53, N = 15407.24430.54438.111. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: CaffeNet 12-int8 - Device: CPU - Executor: Standardbca0.55311.10621.65932.21242.7655SE +/- 0.02717, N = 152.458232.320982.281121. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: super-resolution-10 - Device: CPU - Executor: Standardbca48121620SE +/- 0.74, N = 1514.6811.2411.201. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.17Model: super-resolution-10 - Device: CPU - Executor: Standardbca20406080100SE +/- 3.28, N = 1570.4188.9489.271. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: super-resolution-10 - Device: CPU - Executor: Standardbca48121620SE +/- 0.74, N = 1514.6811.2411.201. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: Standardcab612182430SE +/- 0.47, N = 1325.6823.4722.801. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.17Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: Standardcab1020304050SE +/- 0.77, N = 1338.9442.6044.051. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: Standardcab612182430SE +/- 0.47, N = 1325.6823.4722.801. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: yolov4 - Device: CPU - Executor: Standardacb4080120160200SE +/- 6.49, N = 12180.28179.60148.741. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.17Model: yolov4 - Device: CPU - Executor: Standardacb246810SE +/- 0.24590, N = 125.546755.567926.840511. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: yolov4 - Device: CPU - Executor: Standardacb4080120160200SE +/- 6.49, N = 12180.28179.60148.741. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: fcn-resnet101-11 - Device: CPU - Executor: Standardbac2004006008001000SE +/- 3.75, N = 3849.86764.80756.251. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.17Model: fcn-resnet101-11 - Device: CPU - Executor: Standardbac0.29750.5950.89251.191.4875SE +/- 0.00517, N = 31.176701.307531.322311. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: fcn-resnet101-11 - Device: CPU - Executor: Standardbac2004006008001000SE +/- 3.75, N = 3849.86764.80756.251. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: Parallelbac714212835SE +/- 0.11, N = 329.0027.7727.561. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.17Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: Parallelbac816243240SE +/- 0.13, N = 334.4836.0036.291. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: Parallelbac714212835SE +/- 0.11, N = 329.0027.7727.561. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: GPT-2 - Device: CPU - Executor: Parallelbac3691215SE +/- 0.03, N = 310.9510.9010.751. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.17Model: GPT-2 - Device: CPU - Executor: Parallelbac20406080100SE +/- 0.28, N = 391.2791.7592.971. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: GPT-2 - Device: CPU - Executor: Parallelbac3691215SE +/- 0.03, N = 310.9510.9010.751. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: bertsquad-12 - Device: CPU - Executor: Parallelbac306090120150SE +/- 1.77, N = 3135.50120.43119.781. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.17Model: bertsquad-12 - Device: CPU - Executor: Parallelbac246810SE +/- 0.09737, N = 37.382268.303768.348661. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: bertsquad-12 - Device: CPU - Executor: Parallelbac306090120150SE +/- 1.77, N = 3135.50120.43119.781. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: T5 Encoder - Device: CPU - Executor: Standardcba246810SE +/- 0.01695, N = 38.189438.102417.962841. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.17Model: T5 Encoder - Device: CPU - Executor: Standardcba306090120150SE +/- 0.26, N = 3122.08123.39125.551. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: T5 Encoder - Device: CPU - Executor: Standardcba246810SE +/- 0.01695, N = 38.189438.102417.962841. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: T5 Encoder - Device: CPU - Executor: Parallelbac246810SE +/- 0.06945, N = 38.641938.575978.518361. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.17Model: T5 Encoder - Device: CPU - Executor: Parallelbac306090120150SE +/- 0.92, N = 3115.71116.58117.371. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: T5 Encoder - Device: CPU - Executor: Parallelbac246810SE +/- 0.06945, N = 38.641938.575978.518361. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: ArcFace ResNet-100 - Device: CPU - Executor: Parallelbca1326395265SE +/- 0.31, N = 358.7855.0054.201. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.17Model: ArcFace ResNet-100 - Device: CPU - Executor: Parallelbca510152025SE +/- 0.09, N = 317.0118.1818.451. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: ArcFace ResNet-100 - Device: CPU - Executor: Parallelbca1326395265SE +/- 0.31, N = 358.7855.0054.201. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: CaffeNet 12-int8 - Device: CPU - Executor: Parallelbac0.57061.14121.71182.28242.853SE +/- 0.02113, N = 32.535892.376782.354431. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.17Model: CaffeNet 12-int8 - Device: CPU - Executor: Parallelbac90180270360450SE +/- 3.27, N = 3394.10420.38424.321. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: CaffeNet 12-int8 - Device: CPU - Executor: Parallelbac0.57061.14121.71182.28242.853SE +/- 0.02113, N = 32.535892.376782.354431. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: ResNet50 v1-12-int8 - Device: CPU - Executor: Standardbac1.17632.35263.52894.70525.8815SE +/- 0.03558, N = 35.227874.803454.755851. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.17Model: ResNet50 v1-12-int8 - Device: CPU - Executor: Standardbac50100150200250SE +/- 1.31, N = 3191.25208.12210.211. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: ResNet50 v1-12-int8 - Device: CPU - Executor: Standardbac1.17632.35263.52894.70525.8815SE +/- 0.03558, N = 35.227874.803454.755851. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: ResNet50 v1-12-int8 - Device: CPU - Executor: Parallelbca1.2312.4623.6934.9246.155SE +/- 0.03573, N = 35.470985.041365.005811. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.17Model: ResNet50 v1-12-int8 - Device: CPU - Executor: Parallelbca4080120160200SE +/- 1.19, N = 3182.77198.33199.721. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: ResNet50 v1-12-int8 - Device: CPU - Executor: Parallelbca1.2312.4623.6934.9246.155SE +/- 0.03573, N = 35.470985.041365.005811. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: super-resolution-10 - Device: CPU - Executor: Parallelbca48121620SE +/- 0.04, N = 317.8716.7416.371. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.17Model: super-resolution-10 - Device: CPU - Executor: Parallelbca1428425670SE +/- 0.13, N = 355.9659.7461.101. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: super-resolution-10 - Device: CPU - Executor: Parallelbca48121620SE +/- 0.04, N = 317.8716.7416.371. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

40 Results Shown

ONNX Runtime:
  fcn-resnet101-11 - CPU - Parallel:
    Inference Time Cost (ms)
    Inferences Per Second
  GPT-2 - CPU - Standard:
    Inference Time Cost (ms)
    Inferences Per Second
  yolov4 - CPU - Parallel:
    Inference Time Cost (ms)
    Inferences Per Second
  bertsquad-12 - CPU - Standard:
    Inference Time Cost (ms)
    Inferences Per Second
  ArcFace ResNet-100 - CPU - Standard:
    Inference Time Cost (ms)
    Inferences Per Second
  CaffeNet 12-int8 - CPU - Standard:
    Inference Time Cost (ms)
    Inferences Per Second
  super-resolution-10 - CPU - Standard:
    Inference Time Cost (ms)
    Inferences Per Second
  Faster R-CNN R-50-FPN-int8 - CPU - Standard:
    Inference Time Cost (ms)
    Inferences Per Second
  yolov4 - CPU - Standard:
    Inference Time Cost (ms)
    Inferences Per Second
  fcn-resnet101-11 - CPU - Standard:
    Inference Time Cost (ms)
    Inferences Per Second
  Faster R-CNN R-50-FPN-int8 - CPU - Parallel:
    Inference Time Cost (ms)
    Inferences Per Second
  GPT-2 - CPU - Parallel:
    Inference Time Cost (ms)
    Inferences Per Second
  bertsquad-12 - CPU - Parallel:
    Inference Time Cost (ms)
    Inferences Per Second
  T5 Encoder - CPU - Standard:
    Inference Time Cost (ms)
    Inferences Per Second
  T5 Encoder - CPU - Parallel:
    Inference Time Cost (ms)
    Inferences Per Second
  ArcFace ResNet-100 - CPU - Parallel:
    Inference Time Cost (ms)
    Inferences Per Second
  CaffeNet 12-int8 - CPU - Parallel:
    Inference Time Cost (ms)
    Inferences Per Second
  ResNet50 v1-12-int8 - CPU - Standard:
    Inference Time Cost (ms)
    Inferences Per Second
  ResNet50 v1-12-int8 - CPU - Parallel:
    Inference Time Cost (ms)
    Inferences Per Second
  super-resolution-10 - CPU - Parallel:
    Inference Time Cost (ms)
    Inferences Per Second

a

Kernel Notes: Transparent Huge Pages: madvise
Compiler Notes: --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,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-defaulted --enable-offload-targets=nvptx-none=/build/gcc-13-XYspKM/gcc-13-13.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-13-XYspKM/gcc-13-13.2.0/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
Processor Notes: Scaling Governor: amd-pstate-epp powersave (EPP: performance) - CPU Microcode: 0xa704101
Python Notes: Python 3.11.6
Security Notes: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_rstack_overflow: Vulnerable: Safe RET no microcode + 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 / Automatic IBRS IBPB: conditional STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected

Testing initiated at 3 February 2024 01:52 by user phoronix.

b

Kernel Notes: Transparent Huge Pages: madvise
Compiler Notes: --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,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-defaulted --enable-offload-targets=nvptx-none=/build/gcc-13-XYspKM/gcc-13-13.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-13-XYspKM/gcc-13-13.2.0/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
Processor Notes: Scaling Governor: amd-pstate-epp powersave (EPP: performance) - CPU Microcode: 0xa704101
Python Notes: Python 3.11.6
Security Notes: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_rstack_overflow: Vulnerable: Safe RET no microcode + 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 / Automatic IBRS IBPB: conditional STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected

Testing initiated at 3 February 2024 02:37 by user phoronix.

c

Processor: AMD Ryzen 7 7840U @ 5.29GHz (8 Cores / 16 Threads), Motherboard: PHX Swift SFE16-43 Ray_PEU (V1.04 BIOS), Chipset: AMD Device 14e8, Memory: 4 x 4GB DRAM-6400MT/s K3LKBKB0BM-MGCP, Disk: 1024GB Micron_3400_MTFDKBA1T0TFH, Graphics: AMD Phoenix1 512MB (2700/800MHz), Audio: AMD Rembrandt Radeon HD Audio, Network: MEDIATEK MT7922 802.11ax PCI

OS: Ubuntu 23.10, Kernel: 6.7.0-060700-generic (x86_64), Desktop: GNOME Shell 45.2, Display Server: X Server + Wayland, OpenGL: 4.6 Mesa 24.1~git2401230600.42fc83~oibaf~m (git-42fc83a 2024-01-23 mantic-oibaf-ppa) (LLVM 16.0.6 DRM 3.56), Compiler: GCC 13.2.0, File-System: ext4, Screen Resolution: 3200x2000

Kernel Notes: Transparent Huge Pages: madvise
Compiler Notes: --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,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-defaulted --enable-offload-targets=nvptx-none=/build/gcc-13-XYspKM/gcc-13-13.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-13-XYspKM/gcc-13-13.2.0/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
Processor Notes: Scaling Governor: amd-pstate-epp powersave (EPP: performance) - CPU Microcode: 0xa704101
Python Notes: Python 3.11.6
Security Notes: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_rstack_overflow: Vulnerable: Safe RET no microcode + 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 / Automatic IBRS IBPB: conditional STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected

Testing initiated at 3 February 2024 10:20 by user phoronix.