icelake 2023

Intel Core i7-1065G7 testing with a Dell 06CDVY (1.0.9 BIOS) and Intel Iris Plus ICL GT2 16GB on Ubuntu 23.04 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 2310250-NE-ICELAKE2082
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
View Logs
Performance Per
Dollar
Date
Run
  Test
  Duration
a
October 24 2023
  5 Hours, 52 Minutes
b
October 24 2023
  5 Hours, 43 Minutes
Invert Behavior (Only Show Selected Data)
  5 Hours, 48 Minutes
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-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-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-12-DAPbBt/gcc-12-12.3.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-12-DAPbBt/gcc-12-12.3.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-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: intel_pstate powersave (EPP: balance_performance) - CPU Microcode: 0xb8 - Thermald 2.5.2
Security Notes: itlb_multihit: KVM: Mitigation of VMX disabled + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Mitigation of Clear buffers; SMT vulnerable + retbleed: Mitigation of Enhanced IBRS + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced IBRS IBPB: conditional RSB filling PBRSB-eIBRS: SW sequence + srbds: Mitigation of Microcode + tsx_async_abort: Not affected

b

Processor: Intel Core i7-1065G7 @ 3.90GHz (4 Cores / 8 Threads), Motherboard: Dell 06CDVY (1.0.9 BIOS), Chipset: Intel Ice Lake-LP DRAM, Memory: 16GB, Disk: Toshiba KBG40ZPZ512G NVMe 512GB, Graphics: Intel Iris Plus ICL GT2 16GB (1100MHz), Audio: Realtek ALC289, Network: Intel Ice Lake-LP PCH CNVi WiFi

OS: Ubuntu 23.04, Kernel: 6.2.0-24-generic (x86_64), Desktop: GNOME Shell 44.0, Display Server: X Server + Wayland, OpenGL: 4.6 Mesa 23.0.4-0ubuntu1~23.04.1, OpenCL: OpenCL 3.0, Compiler: GCC 12.3.0, File-System: ext4, Screen Resolution: 1920x1200

icelake 2023OpenBenchmarking.orgPhoronix Test SuiteIntel Core i7-1065G7 @ 3.90GHz (4 Cores / 8 Threads)Dell 06CDVY (1.0.9 BIOS)Intel Ice Lake-LP DRAM16GBToshiba KBG40ZPZ512G NVMe 512GBIntel Iris Plus ICL GT2 16GB (1100MHz)Realtek ALC289Intel Ice Lake-LP PCH CNVi WiFiUbuntu 23.046.2.0-24-generic (x86_64)GNOME Shell 44.0X Server + Wayland4.6 Mesa 23.0.4-0ubuntu1~23.04.1OpenCL 3.0GCC 12.3.0ext41920x1200ProcessorMotherboardChipsetMemoryDiskGraphicsAudioNetworkOSKernelDesktopDisplay ServerOpenGLOpenCLCompilerFile-SystemScreen ResolutionIcelake 2023 BenchmarksSystem Logs- Transparent Huge Pages: madvise- --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --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-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-12-DAPbBt/gcc-12-12.3.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-12-DAPbBt/gcc-12-12.3.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-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: intel_pstate powersave (EPP: balance_performance) - CPU Microcode: 0xb8 - Thermald 2.5.2 - itlb_multihit: KVM: Mitigation of VMX disabled + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Mitigation of Clear buffers; SMT vulnerable + retbleed: Mitigation of Enhanced IBRS + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced IBRS IBPB: conditional RSB filling PBRSB-eIBRS: SW sequence + srbds: Mitigation of Microcode + tsx_async_abort: Not affected

a vs. b ComparisonPhoronix Test SuiteBaseline+16.5%+16.5%+33%+33%+49.5%+49.5%65.8%58.6%45.6%45%25.2%25%24.8%22.2%16.5%14.6%12.7%12.5%12.1%11.9%11.1%11.1%11.1%11%10.9%10.8%10.8%10.4%9.9%9.7%9.6%9.6%9.6%9.5%9.3%9.3%8.5%8.4%8.3%8.3%8.3%7.9%7.7%7.5%7.2%7.2%6.9%6.6%6.6%6.6%6.3%6.3%6.3%5.9%5.8%5.8%5.8%5.5%5.2%5.2%5%5%5%4.8%4.1%3.1%3%2.7%2.4%D.B.s - f32 - CPUCPU - shufflenet-v2Vulkan GPU - mnasnetCPU - mnasnetIP Shapes 3D - u8s8f32 - CPURTLightmap.hdr.4096x4096 - CPU-OnlyIP Shapes 1D - f32 - CPUIP Shapes 1D - u8s8f32 - CPUVulkan GPU - FastestDetC.B.S.A - u8s8f32 - CPUPreset 12 - Bosphorus 4KIP Shapes 3D - f32 - CPUPreset 8 - Bosphorus 1080pD.B.s - u8s8f32 - CPURT.ldr_alb_nrm.3840x2160 - CPU-OnlyRT.hdr_alb_nrm.3840x2160 - CPU-OnlyR.N.N.T - bf16bf16bf16 - CPUR.N.N.I - u8s8f32 - CPUR.N.N.T - f32 - CPUR.N.N.I - bf16bf16bf16 - CPUVulkan GPU - resnet18R.N.N.I - f32 - CPUCPU - resnet18Preset 8 - Bosphorus 4KPreset 4 - Bosphorus 1080pWide Vector MathCloningCPU - blazeface10, Lossless6Vulkan GPU - alexnetCPU - resnet50Vulkan GPU - blazeface6, LosslessPreset 13 - Bosphorus 4K2Vulkan GPU - vgg16CPU - vgg16CPU - alexnetVector ShuffleCPU - googlenetVulkan GPU - vision_transformerVulkan GPU - googlenetVulkan GPU - efficientnet-b0CPU - regnety_400mVulkan GPU - resnet50Vulkan GPU - squeezenet_ssdR.N.N.T - u8s8f32 - CPUVulkan GPU - mobilenetPreset 4 - Bosphorus 4KVulkan GPU - regnety_400mCPU - mobilenetCPU - yolov4-tinyVulkan GPU - yolov4-tinyCPU - squeezenet_ssdCPU - vision_transformerCPU - efficientnet-b0Pathtracer ISPC - Asian DragonB.S.o.W3.5%Pathtracer ISPC - Asian Dragon ObjPathtracer - CrownVulkan GPU - shufflenet-v23%Vulkan GPU-v2-v2 - mobilenet-v22.8%FP32-FP32Speed 10 Realtime - Bosphorus 4KCPU-v2-v2 - mobilenet-v22.1%oneDNNNCNNNCNNNCNNoneDNNIntel Open Image DenoiseoneDNNoneDNNNCNNoneDNNSVT-AV1oneDNNSVT-AV1oneDNNIntel Open Image DenoiseIntel Open Image DenoiseoneDNNoneDNNoneDNNoneDNNNCNNoneDNNNCNNSVT-AV1SVT-AV1Stress-NGStress-NGNCNNlibavif avifenclibavif avifencNCNNNCNNNCNNlibavif avifencSVT-AV1libavif avifencNCNNlibavif avifencNCNNNCNNStress-NGNCNNNCNNNCNNNCNNNCNNNCNNNCNNoneDNNNCNNSVT-AV1NCNNNCNNNCNNNCNNNCNNNCNNNCNNEmbreeOpenRadiossEmbreeEmbreeNCNNNCNNFluidX3DAOM AV1NCNNab

icelake 2023onednn: Deconvolution Batch shapes_1d - f32 - CPUncnn: CPU - shufflenet-v2ncnn: Vulkan GPU - mnasnetncnn: CPU - mnasnetonednn: IP Shapes 3D - u8s8f32 - CPUoidn: RTLightmap.hdr.4096x4096 - CPU-Onlyonednn: IP Shapes 1D - f32 - CPUonednn: IP Shapes 1D - u8s8f32 - CPUncnn: Vulkan GPU - FastestDetonednn: Convolution Batch Shapes Auto - u8s8f32 - CPUsvt-av1: Preset 12 - Bosphorus 4Konednn: IP Shapes 3D - f32 - CPUsvt-av1: Preset 8 - Bosphorus 1080ponednn: Deconvolution Batch shapes_1d - u8s8f32 - CPUoidn: RT.ldr_alb_nrm.3840x2160 - CPU-Onlyoidn: RT.hdr_alb_nrm.3840x2160 - CPU-Onlyonednn: Recurrent Neural Network Training - bf16bf16bf16 - CPUonednn: Recurrent Neural Network Inference - u8s8f32 - CPUonednn: Recurrent Neural Network Training - f32 - CPUonednn: Recurrent Neural Network Inference - bf16bf16bf16 - CPUncnn: Vulkan GPU - resnet18onednn: Recurrent Neural Network Inference - f32 - CPUncnn: CPU - resnet18svt-av1: Preset 8 - Bosphorus 4Ksvt-av1: Preset 4 - Bosphorus 1080pstress-ng: Wide Vector Mathstress-ng: Cloningncnn: CPU - blazefaceavifenc: 10, Losslessavifenc: 6ncnn: Vulkan GPU - alexnetncnn: CPU - resnet50ncnn: Vulkan GPU - blazefaceavifenc: 6, Losslesssvt-av1: Preset 13 - Bosphorus 4Kavifenc: 2ncnn: Vulkan GPU - vgg16avifenc: 0ncnn: CPU - vgg16ncnn: CPU - alexnetstress-ng: Vector Shufflencnn: CPU - googlenetncnn: Vulkan GPU - vision_transformerncnn: Vulkan GPU - googlenetncnn: Vulkan GPU - efficientnet-b0ncnn: CPU - regnety_400mncnn: Vulkan GPU - resnet50ncnn: Vulkan GPU - squeezenet_ssdonednn: Recurrent Neural Network Training - u8s8f32 - CPUncnn: Vulkan GPU - mobilenetsvt-av1: Preset 4 - Bosphorus 4Kncnn: Vulkan GPU - regnety_400mncnn: CPU - mobilenetncnn: CPU - yolov4-tinyncnn: Vulkan GPU - yolov4-tinyncnn: CPU - squeezenet_ssdncnn: CPU - vision_transformerncnn: CPU - efficientnet-b0embree: Pathtracer ISPC - Asian Dragonopenradioss: Bird Strike on Windshieldembree: Pathtracer ISPC - Asian Dragon Objembree: Pathtracer - Crownncnn: Vulkan GPU - shufflenet-v2ncnn: Vulkan GPU-v2-v2 - mobilenet-v2fluidx3d: FP32-FP32aom-av1: Speed 10 Realtime - Bosphorus 4Kncnn: CPU-v2-v2 - mobilenet-v2ncnn: CPU - FastestDetquantlib: Multi-Threadedembree: Pathtracer - Asian Dragon Objncnn: Vulkan GPU-v3-v3 - mobilenet-v3svt-av1: Preset 13 - Bosphorus 1080popenradioss: Chrysler Neon 1Membree: Pathtracer ISPC - Crownopenradioss: Bumper Beamfluidx3d: FP32-FP16Saom-av1: Speed 10 Realtime - Bosphorus 1080ponednn: Deconvolution Batch shapes_3d - f32 - CPUfluidx3d: FP32-FP16Csvt-av1: Preset 12 - Bosphorus 1080popenradioss: INIVOL and Fluid Structure Interaction Drop Containeraom-av1: Speed 11 Realtime - Bosphorus 4Kopenradioss: Cell Phone Drop Testeasywave: e2Asean Grid + BengkuluSept2007 Source - 240onednn: Deconvolution Batch shapes_3d - u8s8f32 - CPUaom-av1: Speed 9 Realtime - Bosphorus 4Kopenradioss: Rubber O-Ring Seal Installationquantlib: Single-Threadedaom-av1: Speed 11 Realtime - Bosphorus 1080paom-av1: Speed 9 Realtime - Bosphorus 1080pembree: Pathtracer - Asian Dragoneasywave: e2Asean Grid + BengkuluSept2007 Source - 2400easywave: e2Asean Grid + BengkuluSept2007 Source - 1200onednn: Convolution Batch Shapes Auto - f32 - CPUncnn: CPU-v3-v3 - mobilenet-v3onednn: IP Shapes 1D - bf16bf16bf16 - CPUab21.44054.335.245.833.811750.0413.39036.001775.6417.71527.9399.0571525.2939.485110.090.0914376.47378.414396.77398.6313.067400.6412.989.0952.72688229.8641.541.1513.1428.75710.3834.191.1739.91230.093257.0870.21581.55970.0810.32156.5117.18268.4717.1910.7811.9734.2813.8914373.924.150.72711.9524.1432.2232.213.81267.0510.723.6724921.193.20882.56412.714.3525734.324.375.157472.82.98283.54255.3972917.082.8093512.2500144.815.1772210191.2791818.2133.21337.4711.918.1622234.32693.042898.3150.75146.873.2657560.794225.67813.13283.5412.93252.733.64.023.04390.0510.73024.911464.8415.463531.4838.0491428.3578.474140.100.1012945.56648.2712976.66677.0311.796701.811.819.9742.98996693.23702.931.0512.0226.3099.5731.551.0836.84532.582238.24665.22540.78665.369.612306.1116.11251.8816.1310.1411.2632.2513.1213583.822.830.76911.3322.9430.6230.6613.15254.3710.233.8233953.643.30912.64092.794.4726435.134.465.257336.63.0353.48252.1582947.382.8357516.66496143.6715.0825209190.5981824.1333.31338.3611.9338.14934.37694.012894.4150.93147.013.2676560.991225.75513.13093.54OpenBenchmarking.org

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: CPUba51015202512.9321.44MIN: 11.01MIN: 17.21. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

NCNN

NCNN is a high performance neural network inference framework optimized for mobile and other platforms developed by Tencent. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: shufflenet-v2ba0.97431.94862.92293.89724.87152.734.33MIN: 2.61 / MAX: 12.22MIN: 3.92 / MAX: 15.311. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: mnasnetba1.1792.3583.5374.7165.8953.605.24MIN: 3.47 / MAX: 8.6MIN: 3.48 / MAX: 17.521. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: mnasnetba1.31182.62363.93545.24726.5594.025.83MIN: 3.47 / MAX: 16.72MIN: 5.4 / MAX: 191. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

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 3D - Data Type: u8s8f32 - Engine: CPUba0.85761.71522.57283.43044.2883.043903.81175MIN: 2.19MIN: 2.411. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

Intel Open Image Denoise

OpenBenchmarking.orgImages / Sec, More Is BetterIntel Open Image Denoise 2.1Run: RTLightmap.hdr.4096x4096 - Device: CPU-Onlyba0.01130.02260.03390.04520.05650.050.04

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: CPUba369121510.7313.39MIN: 7.53MIN: 7.711. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.3Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPUba2468104.911466.00177MIN: 3.5MIN: 3.571. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

NCNN

NCNN is a high performance neural network inference framework optimized for mobile and other platforms developed by Tencent. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: FastestDetba1.2692.5383.8075.0766.3454.845.64MIN: 4.59 / MAX: 13.78MIN: 5.29 / MAX: 16.111. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

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: CPUba4812162015.4617.72MIN: 14.77MIN: 14.781. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

SVT-AV1

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.7Encoder Mode: Preset 12 - Input: Bosphorus 4Kba71421283531.4827.941. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

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 3D - Data Type: f32 - Engine: CPUba36912158.049149.05715MIN: 7.4MIN: 7.611. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

SVT-AV1

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.7Encoder Mode: Preset 8 - Input: Bosphorus 1080pba71421283528.3625.291. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

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: CPUba36912158.474149.48511MIN: 7.22MIN: 8.161. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

Intel Open Image Denoise

OpenBenchmarking.orgImages / Sec, More Is BetterIntel Open Image Denoise 2.1Run: RT.ldr_alb_nrm.3840x2160 - Device: CPU-Onlyba0.02250.0450.06750.090.11250.100.09

OpenBenchmarking.orgImages / Sec, More Is BetterIntel Open Image Denoise 2.1Run: RT.hdr_alb_nrm.3840x2160 - Device: CPU-Onlyba0.02250.0450.06750.090.11250.100.09

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: CPUba3K6K9K12K15K12945.514376.4MIN: 12762.5MIN: 14135.61. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.3Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPUba160032004800640080006648.277378.40MIN: 6485.23MIN: 7171.271. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.3Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPUba3K6K9K12K15K12976.614396.7MIN: 12797.4MIN: 14160.61. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.3Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPUba160032004800640080006677.037398.63MIN: 6521.21MIN: 7210.771. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

NCNN

NCNN is a high performance neural network inference framework optimized for mobile and other platforms developed by Tencent. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: resnet18ba369121511.7913.06MIN: 11.39 / MAX: 25.81MIN: 12.51 / MAX: 261. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

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: CPUba160032004800640080006701.807400.64MIN: 6511.57MIN: 7186.271. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

NCNN

NCNN is a high performance neural network inference framework optimized for mobile and other platforms developed by Tencent. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: resnet18ba369121511.8112.98MIN: 11.4 / MAX: 27.26MIN: 12.11 / MAX: 25.941. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

SVT-AV1

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.7Encoder Mode: Preset 8 - Input: Bosphorus 4Kba36912159.9749.0951. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.7Encoder Mode: Preset 4 - Input: Bosphorus 1080pba0.67251.3452.01752.693.36252.9892.7261. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

Stress-NG

Stress-NG is a Linux stress tool developed by Colin Ian King. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: Wide Vector Mathba20K40K60K80K100K96693.2388229.801. (CXX) g++ options: -lm -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lmpfr -lpthread -lrt -lz

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: Cloningba150300450600750702.93641.541. (CXX) g++ options: -lm -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lmpfr -lpthread -lrt -lz

NCNN

NCNN is a high performance neural network inference framework optimized for mobile and other platforms developed by Tencent. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: blazefaceba0.25880.51760.77641.03521.2941.051.15MIN: 0.98 / MAX: 5.03MIN: 1.08 / MAX: 7.241. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

libavif avifenc

This is a test of the AOMedia libavif library testing the encoding of a JPEG image to AV1 Image Format (AVIF). Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 1.0Encoder Speed: 10, Losslessba369121512.0213.141. (CXX) g++ options: -O3 -fPIC -lm

OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 1.0Encoder Speed: 6ba71421283526.3128.761. (CXX) g++ options: -O3 -fPIC -lm

NCNN

NCNN is a high performance neural network inference framework optimized for mobile and other platforms developed by Tencent. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: alexnetba36912159.5710.38MIN: 8.44 / MAX: 19.55MIN: 8.85 / MAX: 21.961. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: resnet50ba81624324031.5534.19MIN: 30.01 / MAX: 42.43MIN: 32.53 / MAX: 48.471. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: blazefaceba0.26330.52660.78991.05321.31651.081.17MIN: 1.03 / MAX: 5.53MIN: 1.07 / MAX: 10.591. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

libavif avifenc

This is a test of the AOMedia libavif library testing the encoding of a JPEG image to AV1 Image Format (AVIF). Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 1.0Encoder Speed: 6, Losslessba91827364536.8539.911. (CXX) g++ options: -O3 -fPIC -lm

SVT-AV1

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.7Encoder Mode: Preset 13 - Input: Bosphorus 4Kba81624324032.5830.091. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

libavif avifenc

This is a test of the AOMedia libavif library testing the encoding of a JPEG image to AV1 Image Format (AVIF). Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 1.0Encoder Speed: 2ba60120180240300238.25257.081. (CXX) g++ options: -O3 -fPIC -lm

NCNN

NCNN is a high performance neural network inference framework optimized for mobile and other platforms developed by Tencent. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: vgg16ba163248648065.2270.21MIN: 63.02 / MAX: 76.03MIN: 66.55 / MAX: 80.561. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

libavif avifenc

This is a test of the AOMedia libavif library testing the encoding of a JPEG image to AV1 Image Format (AVIF). Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 1.0Encoder Speed: 0ba130260390520650540.79581.561. (CXX) g++ options: -O3 -fPIC -lm

NCNN

NCNN is a high performance neural network inference framework optimized for mobile and other platforms developed by Tencent. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: vgg16ba163248648065.3670.08MIN: 62.97 / MAX: 77.5MIN: 66.44 / MAX: 80.571. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: alexnetba36912159.6110.30MIN: 8.48 / MAX: 20.48MIN: 8.89 / MAX: 20.311. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

Stress-NG

Stress-NG is a Linux stress tool developed by Colin Ian King. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: Vector Shuffleba50010001500200025002306.112156.511. (CXX) g++ options: -lm -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lmpfr -lpthread -lrt -lz

NCNN

NCNN is a high performance neural network inference framework optimized for mobile and other platforms developed by Tencent. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: googlenetba4812162016.1117.18MIN: 15.41 / MAX: 27.79MIN: 16 / MAX: 29.651. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: vision_transformerba60120180240300251.88268.47MIN: 245.57 / MAX: 275.27MIN: 262.87 / MAX: 279.731. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: googlenetba4812162016.1317.19MIN: 15.44 / MAX: 27.07MIN: 15.97 / MAX: 28.671. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: efficientnet-b0ba369121510.1410.78MIN: 8.56 / MAX: 21.18MIN: 10.21 / MAX: 21.921. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: regnety_400mba369121511.2611.97MIN: 10.71 / MAX: 22.01MIN: 11.19 / MAX: 23.341. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: resnet50ba81624324032.2534.28MIN: 30.03 / MAX: 45.13MIN: 32.55 / MAX: 45.961. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: squeezenet_ssdba4812162013.1213.89MIN: 12.52 / MAX: 24.8MIN: 13.1 / MAX: 28.841. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

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: u8s8f32 - Engine: CPUba3K6K9K12K15K13583.814373.9MIN: 13104.3MIN: 14132.51. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

NCNN

NCNN is a high performance neural network inference framework optimized for mobile and other platforms developed by Tencent. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: mobilenetba61218243022.8324.15MIN: 21.89 / MAX: 33.08MIN: 22.83 / MAX: 34.071. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

SVT-AV1

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.7Encoder Mode: Preset 4 - Input: Bosphorus 4Kba0.1730.3460.5190.6920.8650.7690.7271. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

NCNN

NCNN is a high performance neural network inference framework optimized for mobile and other platforms developed by Tencent. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: regnety_400mba369121511.3311.95MIN: 10.77 / MAX: 21.78MIN: 11.17 / MAX: 23.161. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: mobilenetba61218243022.9424.14MIN: 21.77 / MAX: 34.37MIN: 22.95 / MAX: 34.81. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: yolov4-tinyba71421283530.6232.22MIN: 29.78 / MAX: 41.83MIN: 30.8 / MAX: 42.971. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: yolov4-tinyba71421283530.6632.20MIN: 29.83 / MAX: 42MIN: 31.01 / MAX: 43.291. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: squeezenet_ssdba4812162013.1513.81MIN: 12.51 / MAX: 24.51MIN: 13.11 / MAX: 25.081. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: vision_transformerba60120180240300254.37267.05MIN: 245.85 / MAX: 753.75MIN: 261.81 / MAX: 284.751. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: efficientnet-b0ba369121510.2310.72MIN: 9.49 / MAX: 21.73MIN: 10.17 / MAX: 21.681. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

Embree

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 4.3Binary: Pathtracer ISPC - Model: Asian Dragonba0.86021.72042.58063.44084.3013.82333.6724MIN: 3.66 / MAX: 4.13MIN: 3.64 / MAX: 3.74

OpenRadioss

OpenRadioss is an open-source AGPL-licensed finite element solver for dynamic event analysis OpenRadioss is based on Altair Radioss and open-sourced in 2022. This open-source finite element solver is benchmarked with various example models available from https://www.openradioss.org/models/ and https://github.com/OpenRadioss/ModelExchange/tree/main/Examples. This test is currently using a reference OpenRadioss binary build offered via GitHub. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterOpenRadioss 2023.09.15Model: Bird Strike on Windshieldab2004006008001000921.19953.64

Embree

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 4.3Binary: Pathtracer ISPC - Model: Asian Dragon Objba0.74451.4892.23352.9783.72253.30913.2088MIN: 3.19 / MAX: 3.62MIN: 3.18 / MAX: 3.26

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 4.3Binary: Pathtracer - Model: Crownba0.59421.18841.78262.37682.9712.64092.5641MIN: 2.53 / MAX: 2.86MIN: 2.54 / MAX: 2.62

NCNN

NCNN is a high performance neural network inference framework optimized for mobile and other platforms developed by Tencent. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: shufflenet-v2ab0.62781.25561.88342.51123.1392.712.79MIN: 2.62 / MAX: 12.47MIN: 2.62 / MAX: 12.191. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2ab1.00582.01163.01744.02325.0294.354.47MIN: 4.2 / MAX: 14.21MIN: 4.2 / MAX: 14.851. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

FluidX3D

FluidX3D is a speedy and memory efficient Boltzmann CFD (Computational Fluid Dynamics) software package implemented using OpenCL and intended for GPU acceleration. FluidX3D is developed by Moritz Lehmann and written free for non-commercial use. This is a test profile measuring the system OpenCL performance using the FluidX3D benchmark. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMLUPs/s, More Is BetterFluidX3D 2.9Test: FP32-FP32ba60120180240300264257

AOM AV1

This is a test of the AOMedia AV1 encoder (libaom) developed by AOMedia and Google as the AV1 Codec Library. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.7Encoder Mode: Speed 10 Realtime - Input: Bosphorus 4Kba81624324035.1334.321. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm

NCNN

NCNN is a high performance neural network inference framework optimized for mobile and other platforms developed by Tencent. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU-v2-v2 - Model: mobilenet-v2ab1.00352.0073.01054.0145.01754.374.46MIN: 4.21 / MAX: 13.61MIN: 4.22 / MAX: 14.731. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: FastestDetab1.18132.36263.54394.72525.90655.155.25MIN: 4.89 / MAX: 15.82MIN: 5.09 / MAX: 12.351. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

QuantLib

QuantLib is an open-source library/framework around quantitative finance for modeling, trading and risk management scenarios. QuantLib is written in C++ with Boost and its built-in benchmark used reports the QuantLib Benchmark Index benchmark score. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMFLOPS, More Is BetterQuantLib 1.32Configuration: Multi-Threadedab160032004800640080007472.87336.61. (CXX) g++ options: -O3 -march=native -fPIE -pie

Embree

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 4.3Binary: Pathtracer - Model: Asian Dragon Objba0.68291.36582.04872.73163.41453.03502.9828MIN: 2.95 / MAX: 3.29MIN: 2.96 / MAX: 3.03

NCNN

NCNN is a high performance neural network inference framework optimized for mobile and other platforms developed by Tencent. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3ba0.79651.5932.38953.1863.98253.483.54MIN: 3.4 / MAX: 7.46MIN: 3.4 / MAX: 13.641. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

SVT-AV1

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.7Encoder Mode: Preset 13 - Input: Bosphorus 1080pab60120180240300255.40252.161. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

OpenRadioss

OpenRadioss is an open-source AGPL-licensed finite element solver for dynamic event analysis OpenRadioss is based on Altair Radioss and open-sourced in 2022. This open-source finite element solver is benchmarked with various example models available from https://www.openradioss.org/models/ and https://github.com/OpenRadioss/ModelExchange/tree/main/Examples. This test is currently using a reference OpenRadioss binary build offered via GitHub. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterOpenRadioss 2023.09.15Model: Chrysler Neon 1Mab60012001800240030002917.082947.38

Embree

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 4.3Binary: Pathtracer ISPC - Model: Crownba0.6381.2761.9142.5523.192.83572.8093MIN: 2.76 / MAX: 3.16MIN: 2.78 / MAX: 2.89

OpenRadioss

OpenRadioss is an open-source AGPL-licensed finite element solver for dynamic event analysis OpenRadioss is based on Altair Radioss and open-sourced in 2022. This open-source finite element solver is benchmarked with various example models available from https://www.openradioss.org/models/ and https://github.com/OpenRadioss/ModelExchange/tree/main/Examples. This test is currently using a reference OpenRadioss binary build offered via GitHub. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterOpenRadioss 2023.09.15Model: Bumper Beamab110220330440550512.20516.66

FluidX3D

FluidX3D is a speedy and memory efficient Boltzmann CFD (Computational Fluid Dynamics) software package implemented using OpenCL and intended for GPU acceleration. FluidX3D is developed by Moritz Lehmann and written free for non-commercial use. This is a test profile measuring the system OpenCL performance using the FluidX3D benchmark. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMLUPs/s, More Is BetterFluidX3D 2.9Test: FP32-FP16Sab110220330440550500496

AOM AV1

This is a test of the AOMedia AV1 encoder (libaom) developed by AOMedia and Google as the AV1 Codec Library. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.7Encoder Mode: Speed 10 Realtime - Input: Bosphorus 1080pab306090120150144.80143.671. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm

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_3d - Data Type: f32 - Engine: CPUba4812162015.0815.18MIN: 14.35MIN: 14.541. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

FluidX3D

FluidX3D is a speedy and memory efficient Boltzmann CFD (Computational Fluid Dynamics) software package implemented using OpenCL and intended for GPU acceleration. FluidX3D is developed by Moritz Lehmann and written free for non-commercial use. This is a test profile measuring the system OpenCL performance using the FluidX3D benchmark. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMLUPs/s, More Is BetterFluidX3D 2.9Test: FP32-FP16Cab50100150200250210209

SVT-AV1

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.7Encoder Mode: Preset 12 - Input: Bosphorus 1080pab4080120160200191.28190.601. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

OpenRadioss

OpenRadioss is an open-source AGPL-licensed finite element solver for dynamic event analysis OpenRadioss is based on Altair Radioss and open-sourced in 2022. This open-source finite element solver is benchmarked with various example models available from https://www.openradioss.org/models/ and https://github.com/OpenRadioss/ModelExchange/tree/main/Examples. This test is currently using a reference OpenRadioss binary build offered via GitHub. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterOpenRadioss 2023.09.15Model: INIVOL and Fluid Structure Interaction Drop Containerab4008001200160020001818.211824.13

AOM AV1

This is a test of the AOMedia AV1 encoder (libaom) developed by AOMedia and Google as the AV1 Codec Library. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.7Encoder Mode: Speed 11 Realtime - Input: Bosphorus 4Kba81624324033.3133.211. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm

OpenRadioss

OpenRadioss is an open-source AGPL-licensed finite element solver for dynamic event analysis OpenRadioss is based on Altair Radioss and open-sourced in 2022. This open-source finite element solver is benchmarked with various example models available from https://www.openradioss.org/models/ and https://github.com/OpenRadioss/ModelExchange/tree/main/Examples. This test is currently using a reference OpenRadioss binary build offered via GitHub. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterOpenRadioss 2023.09.15Model: Cell Phone Drop Testab70140210280350337.47338.36

easyWave

The easyWave software allows simulating tsunami generation and propagation in the context of early warning systems. EasyWave supports making use of OpenMP for CPU multi-threading and there are also GPU ports available but not currently incorporated as part of this test profile. The easyWave tsunami generation software is run with one of the example/reference input files for measuring the CPU execution time. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BettereasyWave r34Input: e2Asean Grid + BengkuluSept2007 Source - Time: 240ab369121511.9111.931. (CXX) g++ options: -O3 -fopenmp

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_3d - Data Type: u8s8f32 - Engine: CPUba2468108.149008.16222MIN: 7.2MIN: 7.271. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

AOM AV1

This is a test of the AOMedia AV1 encoder (libaom) developed by AOMedia and Google as the AV1 Codec Library. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.7Encoder Mode: Speed 9 Realtime - Input: Bosphorus 4Kba81624324034.3734.321. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm

OpenRadioss

OpenRadioss is an open-source AGPL-licensed finite element solver for dynamic event analysis OpenRadioss is based on Altair Radioss and open-sourced in 2022. This open-source finite element solver is benchmarked with various example models available from https://www.openradioss.org/models/ and https://github.com/OpenRadioss/ModelExchange/tree/main/Examples. This test is currently using a reference OpenRadioss binary build offered via GitHub. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterOpenRadioss 2023.09.15Model: Rubber O-Ring Seal Installationab150300450600750693.04694.01

QuantLib

QuantLib is an open-source library/framework around quantitative finance for modeling, trading and risk management scenarios. QuantLib is written in C++ with Boost and its built-in benchmark used reports the QuantLib Benchmark Index benchmark score. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMFLOPS, More Is BetterQuantLib 1.32Configuration: Single-Threadedab60012001800240030002898.32894.41. (CXX) g++ options: -O3 -march=native -fPIE -pie

AOM AV1

This is a test of the AOMedia AV1 encoder (libaom) developed by AOMedia and Google as the AV1 Codec Library. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.7Encoder Mode: Speed 11 Realtime - Input: Bosphorus 1080pba306090120150150.93150.751. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.7Encoder Mode: Speed 9 Realtime - Input: Bosphorus 1080pba306090120150147.01146.871. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm

Embree

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 4.3Binary: Pathtracer - Model: Asian Dragonba0.73521.47042.20562.94083.6763.26763.2657MIN: 3.2 / MAX: 3.53MIN: 3.23 / MAX: 3.33

easyWave

The easyWave software allows simulating tsunami generation and propagation in the context of early warning systems. EasyWave supports making use of OpenMP for CPU multi-threading and there are also GPU ports available but not currently incorporated as part of this test profile. The easyWave tsunami generation software is run with one of the example/reference input files for measuring the CPU execution time. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BettereasyWave r34Input: e2Asean Grid + BengkuluSept2007 Source - Time: 2400ab120240360480600560.79560.991. (CXX) g++ options: -O3 -fopenmp

OpenBenchmarking.orgSeconds, Fewer Is BettereasyWave r34Input: e2Asean Grid + BengkuluSept2007 Source - Time: 1200ab50100150200250225.68225.761. (CXX) g++ options: -O3 -fopenmp

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: CPUba369121513.1313.13MIN: 12.68MIN: 12.761. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

NCNN

NCNN is a high performance neural network inference framework optimized for mobile and other platforms developed by Tencent. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU-v3-v3 - Model: mobilenet-v3ab0.79651.5932.38953.1863.98253.543.54MIN: 3.4 / MAX: 13.43MIN: 3.39 / MAX: 13.391. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

Stress-NG

Stress-NG is a Linux stress tool developed by Colin Ian King. Learn more via the OpenBenchmarking.org test page.

Test: AVX-512 VNNI

a: The test run did not produce a result.

b: The test run did not produce a result.

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.

Harness: Deconvolution Batch shapes_3d - Data Type: bf16bf16bf16 - Engine: CPU

a: The test run did not produce a result.

b: The test run did not produce a result.

Harness: Deconvolution Batch shapes_1d - Data Type: bf16bf16bf16 - Engine: CPU

a: The test run did not produce a result.

b: The test run did not produce a result.

Harness: Convolution Batch Shapes Auto - Data Type: bf16bf16bf16 - Engine: CPU

a: The test run did not produce a result.

b: The test run did not produce a result.

Harness: IP Shapes 3D - Data Type: bf16bf16bf16 - Engine: CPU

a: The test run did not produce a result.

b: The test run did not produce a result.

Harness: IP Shapes 1D - Data Type: bf16bf16bf16 - Engine: CPU

a: The test run did not produce a result.

b: The test run did not produce a result.

95 Results Shown

oneDNN
NCNN:
  CPU - shufflenet-v2
  Vulkan GPU - mnasnet
  CPU - mnasnet
oneDNN
Intel Open Image Denoise
oneDNN:
  IP Shapes 1D - f32 - CPU
  IP Shapes 1D - u8s8f32 - CPU
NCNN
oneDNN
SVT-AV1
oneDNN
SVT-AV1
oneDNN
Intel Open Image Denoise:
  RT.ldr_alb_nrm.3840x2160 - CPU-Only
  RT.hdr_alb_nrm.3840x2160 - CPU-Only
oneDNN:
  Recurrent Neural Network Training - bf16bf16bf16 - CPU
  Recurrent Neural Network Inference - u8s8f32 - CPU
  Recurrent Neural Network Training - f32 - CPU
  Recurrent Neural Network Inference - bf16bf16bf16 - CPU
NCNN
oneDNN
NCNN
SVT-AV1:
  Preset 8 - Bosphorus 4K
  Preset 4 - Bosphorus 1080p
Stress-NG:
  Wide Vector Math
  Cloning
NCNN
libavif avifenc:
  10, Lossless
  6
NCNN:
  Vulkan GPU - alexnet
  CPU - resnet50
  Vulkan GPU - blazeface
libavif avifenc
SVT-AV1
libavif avifenc
NCNN
libavif avifenc
NCNN:
  CPU - vgg16
  CPU - alexnet
Stress-NG
NCNN:
  CPU - googlenet
  Vulkan GPU - vision_transformer
  Vulkan GPU - googlenet
  Vulkan GPU - efficientnet-b0
  CPU - regnety_400m
  Vulkan GPU - resnet50
  Vulkan GPU - squeezenet_ssd
oneDNN
NCNN
SVT-AV1
NCNN:
  Vulkan GPU - regnety_400m
  CPU - mobilenet
  CPU - yolov4-tiny
  Vulkan GPU - yolov4-tiny
  CPU - squeezenet_ssd
  CPU - vision_transformer
  CPU - efficientnet-b0
Embree
OpenRadioss
Embree:
  Pathtracer ISPC - Asian Dragon Obj
  Pathtracer - Crown
NCNN:
  Vulkan GPU - shufflenet-v2
  Vulkan GPU-v2-v2 - mobilenet-v2
FluidX3D
AOM AV1
NCNN:
  CPU-v2-v2 - mobilenet-v2
  CPU - FastestDet
QuantLib
Embree
NCNN
SVT-AV1
OpenRadioss
Embree
OpenRadioss
FluidX3D
AOM AV1
oneDNN
FluidX3D
SVT-AV1
OpenRadioss
AOM AV1
OpenRadioss
easyWave
oneDNN
AOM AV1
OpenRadioss
QuantLib
AOM AV1:
  Speed 11 Realtime - Bosphorus 1080p
  Speed 9 Realtime - Bosphorus 1080p
Embree
easyWave:
  e2Asean Grid + BengkuluSept2007 Source - 2400
  e2Asean Grid + BengkuluSept2007 Source - 1200
oneDNN
NCNN

a

Kernel Notes: Transparent Huge Pages: madvise
Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --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-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-12-DAPbBt/gcc-12-12.3.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-12-DAPbBt/gcc-12-12.3.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-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: intel_pstate powersave (EPP: balance_performance) - CPU Microcode: 0xb8 - Thermald 2.5.2
Security Notes: itlb_multihit: KVM: Mitigation of VMX disabled + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Mitigation of Clear buffers; SMT vulnerable + retbleed: Mitigation of Enhanced IBRS + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced IBRS IBPB: conditional RSB filling PBRSB-eIBRS: SW sequence + srbds: Mitigation of Microcode + tsx_async_abort: Not affected

Testing initiated at 24 October 2023 12:47 by user phoronix.

b

Processor: Intel Core i7-1065G7 @ 3.90GHz (4 Cores / 8 Threads), Motherboard: Dell 06CDVY (1.0.9 BIOS), Chipset: Intel Ice Lake-LP DRAM, Memory: 16GB, Disk: Toshiba KBG40ZPZ512G NVMe 512GB, Graphics: Intel Iris Plus ICL GT2 16GB (1100MHz), Audio: Realtek ALC289, Network: Intel Ice Lake-LP PCH CNVi WiFi

OS: Ubuntu 23.04, Kernel: 6.2.0-24-generic (x86_64), Desktop: GNOME Shell 44.0, Display Server: X Server + Wayland, OpenGL: 4.6 Mesa 23.0.4-0ubuntu1~23.04.1, OpenCL: OpenCL 3.0, Compiler: GCC 12.3.0, File-System: ext4, Screen Resolution: 1920x1200

Kernel Notes: Transparent Huge Pages: madvise
Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --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-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-12-DAPbBt/gcc-12-12.3.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-12-DAPbBt/gcc-12-12.3.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-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: intel_pstate powersave (EPP: balance_performance) - CPU Microcode: 0xb8 - Thermald 2.5.2
Security Notes: itlb_multihit: KVM: Mitigation of VMX disabled + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Mitigation of Clear buffers; SMT vulnerable + retbleed: Mitigation of Enhanced IBRS + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced IBRS IBPB: conditional RSB filling PBRSB-eIBRS: SW sequence + srbds: Mitigation of Microcode + tsx_async_abort: Not affected

Testing initiated at 24 October 2023 17:50 by user phoronix.