centos stream extra

2 x Intel Xeon Max 9480 testing with a Supermicro X13DEM v1.10 (1.3 BIOS) and ASPEED on CentOS Stream 9 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 2310174-NE-CENTOSSTR52
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

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
View Logs
Performance Per
Dollar
Date
Run
  Test
  Duration
2 x Intel Xeon Max 9480
October 17 2023
  1 Hour, 19 Minutes
b
October 17 2023
  1 Hour, 21 Minutes
c
October 17 2023
  1 Hour, 21 Minutes
Invert Behavior (Only Show Selected Data)
  1 Hour, 20 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):


centos stream extraOpenBenchmarking.orgPhoronix Test Suite2 x Intel Xeon Max 9480 @ 3.50GHz (112 Cores / 224 Threads)Supermicro X13DEM v1.10 (1.3 BIOS)Intel Device 1bce512GB2 x 7682GB INTEL SSDPF2KX076TZASPEEDVE2282 x Broadcom BCM57508 NetXtreme-E 10Gb/25Gb/40Gb/50Gb/100Gb/200GbCentOS Stream 95.14.0-373.el9.x86_64 (x86_64)GNOME Shell 40.10X ServerGCC 11.4.1 20230605xfs1920x1080ProcessorMotherboardChipsetMemoryDiskGraphicsMonitorNetworkOSKernelDesktopDisplay ServerCompilerFile-SystemScreen ResolutionCentos Stream Extra BenchmarksSystem Logs- Transparent Huge Pages: always- --build=x86_64-redhat-linux --disable-libunwind-exceptions --enable-__cxa_atexit --enable-bootstrap --enable-cet --enable-checking=release --enable-gnu-indirect-function --enable-gnu-unique-object --enable-host-bind-now --enable-host-pie --enable-initfini-array --enable-languages=c,c++,fortran,lto --enable-link-serialization=1 --enable-multilib --enable-offload-targets=nvptx-none --enable-plugin --enable-shared --enable-threads=posix --mandir=/usr/share/man --with-arch_32=x86-64 --with-arch_64=x86-64-v2 --with-build-config=bootstrap-lto --with-gcc-major-version-only --with-linker-hash-style=gnu --with-tune=generic --without-cuda-driver --without-isl - Scaling Governor: intel_cpufreq performance - CPU Microcode: 0x2c000271- Python 3.9.17- SELinux + 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_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 RSB filling PBRSB-eIBRS: SW sequence + srbds: Not affected + tsx_async_abort: Not affected

2 x Intel Xeon Max 9480bcResult OverviewPhoronix Test Suite100%104%107%111%114%Intel Open Image DenoiseOpenVKLoneDNNOpenVINO

centos stream extraoidn: RTLightmap.hdr.4096x4096 - CPU-Onlyonednn: IP Shapes 1D - f32 - CPUonednn: IP Shapes 1D - u8s8f32 - CPUonednn: Recurrent Neural Network Training - f32 - CPUoidn: RT.ldr_alb_nrm.3840x2160 - CPU-Onlyonednn: Recurrent Neural Network Training - bf16bf16bf16 - CPUonednn: IP Shapes 3D - u8s8f32 - CPUonednn: Recurrent Neural Network Training - u8s8f32 - CPUopenvino: Age Gender Recognition Retail 0013 FP16 - CPUopenvino: Machine Translation EN To DE FP16 - CPUopenvino: Machine Translation EN To DE FP16 - CPUonednn: Recurrent Neural Network Inference - bf16bf16bf16 - CPUonednn: Deconvolution Batch shapes_1d - bf16bf16bf16 - CPUonednn: Deconvolution Batch shapes_3d - u8s8f32 - CPUonednn: IP Shapes 3D - f32 - CPUoidn: RT.hdr_alb_nrm.3840x2160 - CPU-Onlyopenvino: Vehicle Detection FP16 - CPUopenvino: Vehicle Detection FP16 - CPUonednn: Recurrent Neural Network Inference - f32 - CPUonednn: Deconvolution Batch shapes_3d - f32 - CPUonednn: Deconvolution Batch shapes_3d - bf16bf16bf16 - CPUopenvino: Age Gender Recognition Retail 0013 FP16 - CPUopenvkl: vklBenchmarkCPU ISPConednn: Deconvolution Batch shapes_1d - u8s8f32 - CPUopenvkl: vklBenchmarkCPU Scalaropenvino: Road Segmentation ADAS FP16 - CPUopenvino: Road Segmentation ADAS FP16 - CPUopenvino: Weld Porosity Detection FP16 - CPUopenvino: Weld Porosity Detection FP16 - CPUonednn: IP Shapes 1D - bf16bf16bf16 - CPUonednn: Recurrent Neural Network Inference - u8s8f32 - CPUopenvino: Weld Porosity Detection FP16-INT8 - CPUopenvino: Weld Porosity Detection FP16-INT8 - CPUopenvino: Age Gender Recognition Retail 0013 FP16-INT8 - CPUonednn: Deconvolution Batch shapes_1d - f32 - CPUonednn: IP Shapes 3D - bf16bf16bf16 - CPUopenvino: Person Detection FP16 - CPUonednn: Convolution Batch Shapes Auto - f32 - CPUopenvino: Person Detection FP16 - CPUopenvino: Age Gender Recognition Retail 0013 FP16-INT8 - CPUonednn: Convolution Batch Shapes Auto - u8s8f32 - CPUopenvino: Face Detection FP16 - CPUopenvino: Face Detection FP16 - CPUonednn: Convolution Batch Shapes Auto - bf16bf16bf16 - CPUopenvino: Person Detection FP32 - CPUopenvino: Person Detection FP32 - CPUopenvino: Road Segmentation ADAS FP16-INT8 - CPUopenvino: Road Segmentation ADAS FP16-INT8 - CPUopenvino: Handwritten English Recognition FP16 - CPUopenvino: Handwritten English Recognition FP16 - CPUopenvino: Face Detection Retail FP16 - CPUopenvino: Person Vehicle Bike Detection FP16 - CPUopenvino: Face Detection Retail FP16 - CPUopenvino: Person Vehicle Bike Detection FP16 - CPUopenvino: Face Detection Retail FP16-INT8 - CPUopenvino: Face Detection Retail FP16-INT8 - CPUopenvino: Vehicle Detection FP16-INT8 - CPUopenvino: Face Detection FP16-INT8 - CPUopenvino: Face Detection FP16-INT8 - CPUopenvino: Vehicle Detection FP16-INT8 - CPUopenvino: Handwritten English Recognition FP16-INT8 - CPUopenvino: Handwritten English Recognition FP16-INT8 - CPUembree: Pathtracer - Crown2 x Intel Xeon Max 9480bc0.946.398676.9066113799.31.2015485.15.2474416878.50.64132.15279.731233.210.6470920.8160298.188131.382083.7917.711389.64.274232.8758168584.859820.609168484909.8940.587.1115569.868.028651358.564.325154.51114066.714.808180.946402.199.0718391.890.347.11116370.4199.53.88111397.3193.011438.5877.763506.9231.910933.636126.4910.2218.257.115732.2621.9324.92343.575108.2848.022330.760.503.443456.5047887741.5817354.55.30718144040.61116.51317.241395.160.6670910.8958537.488841.322054.3617.961415.424.061292.6895873923.6110580.570467516966.9938.26.916043.368.378831421.144.4124505.4115792.6514.752584.2966396.128.8538393.250.347.01769360.67102.163.85134389.3194.91447.877.273522.9631.7710917.916150.0110.2318.187.1215673.5421.86324.12344.55114.447.972332.980.705.42413.76885140731.4113214.94.22247154670.55121.86303.331339.740.6055430.8143047.910511.441914.5419.271303.33.937142.6655573632.1710460.595536488947.3238.996.716509.918.478461432.044.1925725.95110854.0614.20781.8473387.619.1819295.290.336.90576366.12100.583.9391391.0294.461465.9976.333558.5831.4411057.326200.7410.1118.047.0715741.6821.83325.04343.65121.0548.042329.65OpenBenchmarking.org

Intel Open Image Denoise

OpenBenchmarking.orgImages / Sec, More Is BetterIntel Open Image Denoise 2.1Run: RTLightmap.hdr.4096x4096 - Device: CPU-Only2 x Intel Xeon Max 9480cb0.21150.4230.63450.8461.05750.940.700.50

oneDNN

This is a test of the Intel oneDNN as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Intel oneDNN was formerly known as DNNL (Deep Neural Network Library) and MKL-DNN before being rebranded as part of the Intel oneAPI toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.3Harness: IP Shapes 1D - Data Type: f32 - Engine: CPUbc2 x Intel Xeon Max 94802468103.443455.424106.39867MIN: 2.76MIN: 4.54MIN: 5.471. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.3Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPUcb2 x Intel Xeon Max 94802468103.768856.504786.90661MIN: 2.93MIN: 5.31MIN: 5.541. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.3Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPUb2 x Intel Xeon Max 9480c3K6K9K12K15K8774.013799.314073.0MIN: 8085.71MIN: 12882.7MIN: 12966.81. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread

Intel Open Image Denoise

OpenBenchmarking.orgImages / Sec, More Is BetterIntel Open Image Denoise 2.1Run: RT.ldr_alb_nrm.3840x2160 - Device: CPU-Onlybc2 x Intel Xeon Max 94800.35550.7111.06651.4221.77751.581.411.20

oneDNN

This is a test of the Intel oneDNN as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Intel oneDNN was formerly known as DNNL (Deep Neural Network Library) and MKL-DNN before being rebranded as part of the Intel oneAPI toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.3Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPUc2 x Intel Xeon Max 9480b4K8K12K16K20K13214.915485.117354.5MIN: 8210.66MIN: 13354.1MIN: 16239.71. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.3Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPUc2 x Intel Xeon Max 9480b1.19412.38823.58234.77645.97054.222475.247445.30718MIN: 2.99MIN: 3.67MIN: 3.811. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.3Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPUbc2 x Intel Xeon Max 94804K8K12K16K20K14404.015467.016878.5MIN: 13476.1MIN: 13719.2MIN: 15171.71. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread

OpenVINO

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.1Model: Age Gender Recognition Retail 0013 FP16 - Device: CPUcb2 x Intel Xeon Max 94800.1440.2880.4320.5760.720.550.610.64MIN: 0.29 / MAX: 35.36MIN: 0.3 / MAX: 54.1MIN: 0.3 / MAX: 64.491. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -std=c++11 -MD -MT -MF

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.1Model: Machine Translation EN To DE FP16 - Device: CPUbc2 x Intel Xeon Max 9480306090120150116.51121.86132.15MIN: 36.69 / MAX: 460.49MIN: 40.59 / MAX: 437.84MIN: 35.31 / MAX: 443.721. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -std=c++11 -MD -MT -MF

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.1Model: Machine Translation EN To DE FP16 - Device: CPUbc2 x Intel Xeon Max 948070140210280350317.24303.33279.731. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -std=c++11 -MD -MT -MF

oneDNN

This is a test of the Intel oneDNN as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Intel oneDNN was formerly known as DNNL (Deep Neural Network Library) and MKL-DNN before being rebranded as part of the Intel oneAPI toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.3Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPU2 x Intel Xeon Max 9480cb300600900120015001233.211339.741395.16MIN: 1125.02MIN: 1229.23MIN: 1306.921. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.3Harness: Deconvolution Batch shapes_1d - Data Type: bf16bf16bf16 - Engine: CPUc2 x Intel Xeon Max 9480b0.15010.30020.45030.60040.75050.6055430.6470920.667091MIN: 0.49MIN: 0.51MIN: 0.511. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.3Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPUc2 x Intel Xeon Max 9480b0.20160.40320.60480.80641.0080.8143040.8160290.895853MIN: 0.63MIN: 0.63MIN: 0.651. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.3Harness: IP Shapes 3D - Data Type: f32 - Engine: CPUbc2 x Intel Xeon Max 94802468107.488847.910518.18813MIN: 6.39MIN: 6.61MIN: 6.831. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread

Intel Open Image Denoise

OpenBenchmarking.orgImages / Sec, More Is BetterIntel Open Image Denoise 2.1Run: RT.hdr_alb_nrm.3840x2160 - Device: CPU-Onlyc2 x Intel Xeon Max 9480b0.3240.6480.9721.2961.621.441.381.32

OpenVINO

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.1Model: Vehicle Detection FP16 - Device: CPU2 x Intel Xeon Max 9480bc4008001200160020002083.792054.361914.541. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -std=c++11 -MD -MT -MF

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.1Model: Vehicle Detection FP16 - Device: CPU2 x Intel Xeon Max 9480bc51015202517.7117.9619.27MIN: 8.79 / MAX: 229.39MIN: 9.08 / MAX: 231.3MIN: 9.17 / MAX: 219.841. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -std=c++11 -MD -MT -MF

oneDNN

This is a test of the Intel oneDNN as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Intel oneDNN was formerly known as DNNL (Deep Neural Network Library) and MKL-DNN before being rebranded as part of the Intel oneAPI toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.3Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPUc2 x Intel Xeon Max 9480b300600900120015001303.301389.601415.42MIN: 1163.26MIN: 1235.38MIN: 1317.11. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.3Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPUcb2 x Intel Xeon Max 94800.96171.92342.88513.84684.80853.937144.061294.27423MIN: 2.83MIN: 2.94MIN: 2.851. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.3Harness: Deconvolution Batch shapes_3d - Data Type: bf16bf16bf16 - Engine: CPUcb2 x Intel Xeon Max 94800.64711.29421.94132.58843.23552.665552.689582.87581MIN: 2.08MIN: 2.13MIN: 2.351. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread

OpenVINO

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.1Model: Age Gender Recognition Retail 0013 FP16 - Device: CPUbc2 x Intel Xeon Max 948016K32K48K64K80K73923.6173632.1768584.851. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -std=c++11 -MD -MT -MF

OpenVKL

OpenVKL is the Intel Open Volume Kernel Library that offers high-performance volume computation kernels and part of the Intel oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgItems / Sec, More Is BetterOpenVKL 2.0.0Benchmark: vklBenchmarkCPU ISPCbc2 x Intel Xeon Max 9480200400600800100010581046982MIN: 79 / MAX: 12504MIN: 82 / MAX: 12371MIN: 77 / MAX: 12444

oneDNN

This is a test of the Intel oneDNN as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Intel oneDNN was formerly known as DNNL (Deep Neural Network Library) and MKL-DNN before being rebranded as part of the Intel oneAPI toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.3Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPUbc2 x Intel Xeon Max 94800.13710.27420.41130.54840.68550.5704670.5955360.609168MIN: 0.45MIN: 0.46MIN: 0.461. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread

OpenVKL

OpenVKL is the Intel Open Volume Kernel Library that offers high-performance volume computation kernels and part of the Intel oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgItems / Sec, More Is BetterOpenVKL 2.0.0Benchmark: vklBenchmarkCPU Scalarbc2 x Intel Xeon Max 9480110220330440550516488484MIN: 48 / MAX: 7431MIN: 49 / MAX: 7159MIN: 44 / MAX: 7212

OpenVINO

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.1Model: Road Segmentation ADAS FP16 - Device: CPUbc2 x Intel Xeon Max 94802004006008001000966.99947.32909.891. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -std=c++11 -MD -MT -MF

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.1Model: Road Segmentation ADAS FP16 - Device: CPUbc2 x Intel Xeon Max 948091827364538.2038.9940.58MIN: 26.14 / MAX: 101.74MIN: 25.7 / MAX: 110.21MIN: 26.74 / MAX: 152.151. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -std=c++11 -MD -MT -MF

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.1Model: Weld Porosity Detection FP16 - Device: CPUcb2 x Intel Xeon Max 94802468106.706.907.11MIN: 4.41 / MAX: 66.66MIN: 4.38 / MAX: 93.9MIN: 4.45 / MAX: 76.171. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -std=c++11 -MD -MT -MF

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.1Model: Weld Porosity Detection FP16 - Device: CPUcb2 x Intel Xeon Max 94804K8K12K16K20K16509.9116043.3615569.861. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -std=c++11 -MD -MT -MF

oneDNN

This is a test of the Intel oneDNN as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Intel oneDNN was formerly known as DNNL (Deep Neural Network Library) and MKL-DNN before being rebranded as part of the Intel oneAPI toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.3Harness: IP Shapes 1D - Data Type: bf16bf16bf16 - Engine: CPU2 x Intel Xeon Max 9480bc2468108.028658.378838.47846MIN: 6.31MIN: 6.6MIN: 6.671. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.3Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPU2 x Intel Xeon Max 9480bc300600900120015001358.561421.141432.04MIN: 1274.34MIN: 1315.46MIN: 1315.41. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread

OpenVINO

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.1Model: Weld Porosity Detection FP16-INT8 - Device: CPUc2 x Intel Xeon Max 9480b0.99231.98462.97693.96924.96154.194.304.41MIN: 2.7 / MAX: 72.58MIN: 2.77 / MAX: 70.91MIN: 2.68 / MAX: 54.341. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -std=c++11 -MD -MT -MF

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.1Model: Weld Porosity Detection FP16-INT8 - Device: CPUc2 x Intel Xeon Max 9480b6K12K18K24K30K25725.9525154.5124505.401. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -std=c++11 -MD -MT -MF

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.1Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPUb2 x Intel Xeon Max 9480c20K40K60K80K100K115792.65114066.70110854.061. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -std=c++11 -MD -MT -MF

oneDNN

This is a test of the Intel oneDNN as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Intel oneDNN was formerly known as DNNL (Deep Neural Network Library) and MKL-DNN before being rebranded as part of the Intel oneAPI toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.3Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPUcb2 x Intel Xeon Max 94804812162014.2114.7514.81MIN: 12.52MIN: 12.76MIN: 12.761. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.3Harness: IP Shapes 3D - Data Type: bf16bf16bf16 - Engine: CPU2 x Intel Xeon Max 9480cb2040608010080.9581.8584.30MIN: 70.18MIN: 70.51MIN: 73.121. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread

OpenVINO

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.1Model: Person Detection FP16 - Device: CPU2 x Intel Xeon Max 9480bc90180270360450402.19396.12387.611. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -std=c++11 -MD -MT -MF

oneDNN

This is a test of the Intel oneDNN as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Intel oneDNN was formerly known as DNNL (Deep Neural Network Library) and MKL-DNN before being rebranded as part of the Intel oneAPI toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.3Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPUb2 x Intel Xeon Max 9480c36912158.853839.071839.18192MIN: 7.98MIN: 7.95MIN: 7.961. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread

OpenVINO

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.1Model: Person Detection FP16 - Device: CPU2 x Intel Xeon Max 9480bc2040608010091.8993.2595.29MIN: 50.89 / MAX: 322.98MIN: 51.93 / MAX: 743.64MIN: 53.05 / MAX: 745.331. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -std=c++11 -MD -MT -MF

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.1Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPUc2 x Intel Xeon Max 9480b0.07650.1530.22950.3060.38250.330.340.34MIN: 0.27 / MAX: 11.81MIN: 0.28 / MAX: 31.55MIN: 0.28 / MAX: 18.61. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -std=c++11 -MD -MT -MF

oneDNN

This is a test of the Intel oneDNN as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Intel oneDNN was formerly known as DNNL (Deep Neural Network Library) and MKL-DNN before being rebranded as part of the Intel oneAPI toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.3Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPUcb2 x Intel Xeon Max 94802468106.905767.017697.11116MIN: 6.2MIN: 6.23MIN: 6.281. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread

OpenVINO

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.1Model: Face Detection FP16 - Device: CPUbc2 x Intel Xeon Max 948080160240320400360.67366.12370.41MIN: 191.19 / MAX: 1244.17MIN: 184.46 / MAX: 1083.67MIN: 188.28 / MAX: 1143.061. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -std=c++11 -MD -MT -MF

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.1Model: Face Detection FP16 - Device: CPUbc2 x Intel Xeon Max 948020406080100102.16100.5899.501. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -std=c++11 -MD -MT -MF

oneDNN

This is a test of the Intel oneDNN as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Intel oneDNN was formerly known as DNNL (Deep Neural Network Library) and MKL-DNN before being rebranded as part of the Intel oneAPI toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.3Harness: Convolution Batch Shapes Auto - Data Type: bf16bf16bf16 - Engine: CPUb2 x Intel Xeon Max 9480c0.88631.77262.65893.54524.43153.851343.881113.93910MIN: 3.36MIN: 3.25MIN: 3.251. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread

OpenVINO

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.1Model: Person Detection FP32 - Device: CPU2 x Intel Xeon Max 9480cb90180270360450397.31391.02389.311. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -std=c++11 -MD -MT -MF

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.1Model: Person Detection FP32 - Device: CPU2 x Intel Xeon Max 9480cb2040608010093.0194.4694.90MIN: 49.97 / MAX: 447.8MIN: 50.39 / MAX: 395.2MIN: 53.38 / MAX: 377.911. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -std=c++11 -MD -MT -MF

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.1Model: Road Segmentation ADAS FP16-INT8 - Device: CPUcb2 x Intel Xeon Max 9480300600900120015001465.991447.801438.581. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -std=c++11 -MD -MT -MF

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.1Model: Road Segmentation ADAS FP16-INT8 - Device: CPUcb2 x Intel Xeon Max 94802040608010076.3377.2777.76MIN: 55.8 / MAX: 123.47MIN: 66.37 / MAX: 117.25MIN: 56.41 / MAX: 122.241. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -std=c++11 -MD -MT -MF

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.1Model: Handwritten English Recognition FP16 - Device: CPUcb2 x Intel Xeon Max 948080016002400320040003558.583522.963506.921. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -std=c++11 -MD -MT -MF

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.1Model: Handwritten English Recognition FP16 - Device: CPUcb2 x Intel Xeon Max 948071421283531.4431.7731.90MIN: 26.5 / MAX: 78.01MIN: 25.35 / MAX: 81.87MIN: 25.84 / MAX: 72.491. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -std=c++11 -MD -MT -MF

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.1Model: Face Detection Retail FP16 - Device: CPUc2 x Intel Xeon Max 9480b2K4K6K8K10K11057.3210933.6310917.911. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -std=c++11 -MD -MT -MF

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.1Model: Person Vehicle Bike Detection FP16 - Device: CPUcb2 x Intel Xeon Max 9480130026003900520065006200.746150.016126.491. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -std=c++11 -MD -MT -MF

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.1Model: Face Detection Retail FP16 - Device: CPUc2 x Intel Xeon Max 9480b369121510.1110.2210.23MIN: 7.6 / MAX: 47.72MIN: 7.99 / MAX: 47.71MIN: 7.34 / MAX: 51.031. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -std=c++11 -MD -MT -MF

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.1Model: Person Vehicle Bike Detection FP16 - Device: CPUcb2 x Intel Xeon Max 94804812162018.0418.1818.25MIN: 12.84 / MAX: 58.35MIN: 12.71 / MAX: 50.87MIN: 12.34 / MAX: 134.571. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -std=c++11 -MD -MT -MF

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.1Model: Face Detection Retail FP16-INT8 - Device: CPUc2 x Intel Xeon Max 9480b2468107.077.107.12MIN: 5.06 / MAX: 53.17MIN: 5.48 / MAX: 56.37MIN: 5.46 / MAX: 57.881. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -std=c++11 -MD -MT -MF

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.1Model: Face Detection Retail FP16-INT8 - Device: CPUc2 x Intel Xeon Max 9480b3K6K9K12K15K15741.6815732.2615673.541. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -std=c++11 -MD -MT -MF

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.1Model: Vehicle Detection FP16-INT8 - Device: CPUcb2 x Intel Xeon Max 948051015202521.8321.8621.90MIN: 15.02 / MAX: 101.76MIN: 16.73 / MAX: 100.58MIN: 16.31 / MAX: 96.241. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -std=c++11 -MD -MT -MF

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.1Model: Face Detection FP16-INT8 - Device: CPUc2 x Intel Xeon Max 9480b70140210280350325.04324.92324.121. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -std=c++11 -MD -MT -MF

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.1Model: Face Detection FP16-INT8 - Device: CPU2 x Intel Xeon Max 9480cb70140210280350343.57343.60344.50MIN: 279.79 / MAX: 642.34MIN: 254.33 / MAX: 730.72MIN: 263.98 / MAX: 1205.691. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -std=c++11 -MD -MT -MF

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.1Model: Vehicle Detection FP16-INT8 - Device: CPUcb2 x Intel Xeon Max 9480110022003300440055005121.055114.405108.281. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -std=c++11 -MD -MT -MF

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.1Model: Handwritten English Recognition FP16-INT8 - Device: CPUb2 x Intel Xeon Max 9480c112233445547.9748.0248.04MIN: 40.56 / MAX: 126.63MIN: 40.77 / MAX: 97.23MIN: 38.44 / MAX: 119.561. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -std=c++11 -MD -MT -MF

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.1Model: Handwritten English Recognition FP16-INT8 - Device: CPUb2 x Intel Xeon Max 9480c50010001500200025002332.982330.762329.651. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -std=c++11 -MD -MT -MF

Embree

Binary: Pathtracer ISPC - Model: Asian Dragon Obj

2 x Intel Xeon Max 9480: The test quit with a non-zero exit status. E: ./bin/embree_pathtracer_ispc: error while loading shared libraries: libOpenGL.so.0: cannot open shared object file: No such file or directory

b: The test quit with a non-zero exit status. E: ./bin/embree_pathtracer_ispc: error while loading shared libraries: libOpenGL.so.0: cannot open shared object file: No such file or directory

c: The test quit with a non-zero exit status. E: ./bin/embree_pathtracer_ispc: error while loading shared libraries: libOpenGL.so.0: cannot open shared object file: No such file or directory

Binary: Pathtracer ISPC - Model: Asian Dragon

2 x Intel Xeon Max 9480: The test quit with a non-zero exit status. E: ./bin/embree_pathtracer_ispc: error while loading shared libraries: libOpenGL.so.0: cannot open shared object file: No such file or directory

b: The test quit with a non-zero exit status. E: ./bin/embree_pathtracer_ispc: error while loading shared libraries: libOpenGL.so.0: cannot open shared object file: No such file or directory

c: The test quit with a non-zero exit status. E: ./bin/embree_pathtracer_ispc: error while loading shared libraries: libOpenGL.so.0: cannot open shared object file: No such file or directory

Binary: Pathtracer - Model: Asian Dragon Obj

2 x Intel Xeon Max 9480: The test quit with a non-zero exit status. E: ./bin/embree_pathtracer: error while loading shared libraries: libOpenGL.so.0: cannot open shared object file: No such file or directory

b: The test quit with a non-zero exit status. E: ./bin/embree_pathtracer: error while loading shared libraries: libOpenGL.so.0: cannot open shared object file: No such file or directory

c: The test quit with a non-zero exit status. E: ./bin/embree_pathtracer: error while loading shared libraries: libOpenGL.so.0: cannot open shared object file: No such file or directory

Binary: Pathtracer - Model: Asian Dragon

2 x Intel Xeon Max 9480: The test quit with a non-zero exit status. E: ./bin/embree_pathtracer: error while loading shared libraries: libOpenGL.so.0: cannot open shared object file: No such file or directory

b: The test quit with a non-zero exit status. E: ./bin/embree_pathtracer: error while loading shared libraries: libOpenGL.so.0: cannot open shared object file: No such file or directory

c: The test quit with a non-zero exit status. E: ./bin/embree_pathtracer: error while loading shared libraries: libOpenGL.so.0: cannot open shared object file: No such file or directory

Binary: Pathtracer ISPC - Model: Crown

2 x Intel Xeon Max 9480: The test quit with a non-zero exit status. E: ./bin/embree_pathtracer_ispc: error while loading shared libraries: libOpenGL.so.0: cannot open shared object file: No such file or directory

b: The test quit with a non-zero exit status. E: ./bin/embree_pathtracer_ispc: error while loading shared libraries: libOpenGL.so.0: cannot open shared object file: No such file or directory

c: The test quit with a non-zero exit status. E: ./bin/embree_pathtracer_ispc: error while loading shared libraries: libOpenGL.so.0: cannot open shared object file: No such file or directory

Binary: Pathtracer - Model: Crown

2 x Intel Xeon Max 9480: The test quit with a non-zero exit status. E: ./bin/embree_pathtracer: error while loading shared libraries: libOpenGL.so.0: cannot open shared object file: No such file or directory

b: The test quit with a non-zero exit status. E: ./bin/embree_pathtracer: error while loading shared libraries: libOpenGL.so.0: cannot open shared object file: No such file or directory

c: The test quit with a non-zero exit status. E: ./bin/embree_pathtracer: error while loading shared libraries: libOpenGL.so.0: cannot open shared object file: No such file or directory

62 Results Shown

Intel Open Image Denoise
oneDNN:
  IP Shapes 1D - f32 - CPU
  IP Shapes 1D - u8s8f32 - CPU
  Recurrent Neural Network Training - f32 - CPU
Intel Open Image Denoise
oneDNN:
  Recurrent Neural Network Training - bf16bf16bf16 - CPU
  IP Shapes 3D - u8s8f32 - CPU
  Recurrent Neural Network Training - u8s8f32 - CPU
OpenVINO:
  Age Gender Recognition Retail 0013 FP16 - CPU
  Machine Translation EN To DE FP16 - CPU
  Machine Translation EN To DE FP16 - CPU
oneDNN:
  Recurrent Neural Network Inference - bf16bf16bf16 - CPU
  Deconvolution Batch shapes_1d - bf16bf16bf16 - CPU
  Deconvolution Batch shapes_3d - u8s8f32 - CPU
  IP Shapes 3D - f32 - CPU
Intel Open Image Denoise
OpenVINO:
  Vehicle Detection FP16 - CPU:
    FPS
    ms
oneDNN:
  Recurrent Neural Network Inference - f32 - CPU
  Deconvolution Batch shapes_3d - f32 - CPU
  Deconvolution Batch shapes_3d - bf16bf16bf16 - CPU
OpenVINO
OpenVKL
oneDNN
OpenVKL
OpenVINO:
  Road Segmentation ADAS FP16 - CPU:
    FPS
    ms
  Weld Porosity Detection FP16 - CPU:
    ms
    FPS
oneDNN:
  IP Shapes 1D - bf16bf16bf16 - CPU
  Recurrent Neural Network Inference - u8s8f32 - CPU
OpenVINO:
  Weld Porosity Detection FP16-INT8 - CPU:
    ms
    FPS
  Age Gender Recognition Retail 0013 FP16-INT8 - CPU:
    FPS
oneDNN:
  Deconvolution Batch shapes_1d - f32 - CPU
  IP Shapes 3D - bf16bf16bf16 - CPU
OpenVINO
oneDNN
OpenVINO:
  Person Detection FP16 - CPU
  Age Gender Recognition Retail 0013 FP16-INT8 - CPU
oneDNN
OpenVINO:
  Face Detection FP16 - CPU:
    ms
    FPS
oneDNN
OpenVINO:
  Person Detection FP32 - CPU:
    FPS
    ms
  Road Segmentation ADAS FP16-INT8 - CPU:
    FPS
    ms
  Handwritten English Recognition FP16 - CPU:
    FPS
    ms
  Face Detection Retail FP16 - CPU:
    FPS
  Person Vehicle Bike Detection FP16 - CPU:
    FPS
  Face Detection Retail FP16 - CPU:
    ms
  Person Vehicle Bike Detection FP16 - CPU:
    ms
  Face Detection Retail FP16-INT8 - CPU:
    ms
    FPS
  Vehicle Detection FP16-INT8 - CPU:
    ms
  Face Detection FP16-INT8 - CPU:
    FPS
    ms
  Vehicle Detection FP16-INT8 - CPU:
    FPS
  Handwritten English Recognition FP16-INT8 - CPU:
    ms
    FPS