Intel Core i5-12400 testing with a ASRock B660M-HDV (3.02 BIOS) and llvmpipe on Ubuntu 22.04 via the Phoronix Test Suite.
A Processor: Intel Core i5-12400 @ 5.60GHz (6 Cores / 12 Threads), Motherboard: ASRock B660M-HDV (3.02 BIOS), Chipset: Intel Device 7aa7, Memory: 16GB, Disk: 512GB Sabrent, Graphics: llvmpipe, Audio: Realtek ALC897, Network: Intel
OS: Ubuntu 22.04, Kernel: 5.15.0-18-generic (x86_64), Desktop: GNOME Shell 41.3, Display Server: X Server 1.20.14, OpenGL: 4.5 Mesa 21.2.2 (LLVM 12.0.1 256 bits), Vulkan: 1.1.182, Compiler: GCC 11.2.0, File-System: ext4, Screen Resolution: 1920x1080
Kernel Notes: Transparent Huge Pages: madviseCompiler 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,brig,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-11-iOLsLC/gcc-11-11.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-iOLsLC/gcc-11-11.2.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -vProcessor Notes: Scaling Governor: intel_pstate powersave (EPP: balance_performance) - CPU Microcode: 0x18 - Thermald 2.4.7Java Notes: OpenJDK Runtime Environment (build 11.0.14.1+1-Ubuntu-0ubuntu1)Python Notes: Python 3.9.12Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced IBRS IBPB: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected
Intel Core i5-12400 Kernel Notes: Transparent Huge Pages: madviseCompiler 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,brig,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-11-gBFGDP/gcc-11-11.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-gBFGDP/gcc-11-11.2.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -vProcessor Notes: Scaling Governor: intel_pstate powersave (EPP: balance_performance) - CPU Microcode: 0x18 - Thermald 2.4.9Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced IBRS IBPB: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected
B Kernel Notes: Transparent Huge Pages: madviseCompiler 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,brig,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-11-gBFGDP/gcc-11-11.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-gBFGDP/gcc-11-11.2.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -vProcessor Notes: Scaling Governor: intel_pstate powersave (EPP: balance_performance) - CPU Microcode: 0x18 - Thermald 2.4.9Java Notes: OpenJDK Runtime Environment (build 11.0.14.1+1-Ubuntu-0ubuntu1)Python Notes: Python 3.10.4Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced IBRS IBPB: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected
C OS: Ubuntu 22.04, Kernel: 5.15.0-18-generic (x86_64), Desktop: GNOME Shell 41.3, Display Server: X Server 1.20.14, OpenGL: 4.5 Mesa 22.0.1 (LLVM 13.0.1 256 bits), Vulkan: 1.2.204, Compiler: GCC 11.2.0, File-System: ext4, Screen Resolution: 1920x1080
core-i5-12400-april Processor Motherboard Chipset Memory Disk Graphics Audio Network OS Kernel Desktop Display Server OpenGL Vulkan Compiler File-System Screen Resolution A Intel Core i5-12400 B C Intel Core i5-12400 @ 5.60GHz (6 Cores / 12 Threads) ASRock B660M-HDV (3.02 BIOS) Intel Device 7aa7 16GB 512GB Sabrent llvmpipe Realtek ALC897 Intel Ubuntu 22.04 5.15.0-18-generic (x86_64) GNOME Shell 41.3 X Server 1.20.14 4.5 Mesa 21.2.2 (LLVM 12.0.1 256 bits) 1.1.182 GCC 11.2.0 ext4 1920x1080 4.5 Mesa 22.0.1 (LLVM 13.0.1 256 bits) 1.2.204 OpenBenchmarking.org Kernel Details - Transparent Huge Pages: madvise Compiler Details - A: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-11-iOLsLC/gcc-11-11.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-iOLsLC/gcc-11-11.2.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v - Intel Core i5-12400: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-11-gBFGDP/gcc-11-11.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-gBFGDP/gcc-11-11.2.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v - B: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-11-gBFGDP/gcc-11-11.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-gBFGDP/gcc-11-11.2.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v - C: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-11-gBFGDP/gcc-11-11.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-gBFGDP/gcc-11-11.2.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v Processor Details - A: Scaling Governor: intel_pstate powersave (EPP: balance_performance) - CPU Microcode: 0x18 - Thermald 2.4.7 - Intel Core i5-12400: Scaling Governor: intel_pstate powersave (EPP: balance_performance) - CPU Microcode: 0x18 - Thermald 2.4.9 - B: Scaling Governor: intel_pstate powersave (EPP: balance_performance) - CPU Microcode: 0x18 - Thermald 2.4.9 - C: Scaling Governor: intel_pstate powersave (EPP: balance_performance) - CPU Microcode: 0x18 - Thermald 2.4.9 Java Details - A, B, C: OpenJDK Runtime Environment (build 11.0.14.1+1-Ubuntu-0ubuntu1) Python Details - A: Python 3.9.12 - B: Python 3.10.4 - C: Python 3.10.4 Security Details - itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced IBRS IBPB: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected
core-i5-12400-april onnx: bertsquad-12 - CPU - Parallel ospray: particle_volume/scivis/real_time ospray: particle_volume/pathtracer/real_time ospray: particle_volume/ao/real_time java-jmh: Throughput avifenc: 0 ospray-studio: 2 - 1080p - 16 - Path Tracer ospray-studio: 1 - 1080p - 16 - Path Tracer aom-av1: Speed 4 Two-Pass - Bosphorus 4K ospray: gravity_spheres_volume/dim_512/scivis/real_time ospray: gravity_spheres_volume/dim_512/ao/real_time aom-av1: Speed 0 Two-Pass - Bosphorus 4K ospray-studio: 3 - 1080p - 1 - Path Tracer ospray-studio: 1 - 1080p - 1 - Path Tracer ospray-studio: 2 - 1080p - 1 - Path Tracer ospray: gravity_spheres_volume/dim_512/pathtracer/real_time ospray-studio: 3 - 1080p - 32 - Path Tracer onnx: fcn-resnet101-11 - CPU - Parallel onnx: fcn-resnet101-11 - CPU - Standard onnx: GPT-2 - CPU - Parallel onnx: yolov4 - CPU - Parallel onnx: ArcFace ResNet-100 - CPU - Parallel onnx: GPT-2 - CPU - Standard onnx: bertsquad-12 - CPU - Standard onnx: ArcFace ResNet-100 - CPU - Standard onnx: yolov4 - CPU - Standard onnx: super-resolution-10 - CPU - Standard onnx: super-resolution-10 - CPU - Parallel ospray-studio: 2 - 1080p - 32 - Path Tracer ospray-studio: 1 - 1080p - 32 - Path Tracer aom-av1: Speed 6 Realtime - Bosphorus 4K onednn: Recurrent Neural Network Training - bf16bf16bf16 - CPU onednn: Recurrent Neural Network Training - u8s8f32 - CPU onednn: Recurrent Neural Network Training - f32 - CPU onednn: Recurrent Neural Network Inference - f32 - CPU onednn: Recurrent Neural Network Inference - u8s8f32 - CPU onednn: Recurrent Neural Network Inference - bf16bf16bf16 - CPU onednn: Deconvolution Batch shapes_1d - f32 - CPU avifenc: 2 aom-av1: Speed 6 Realtime - Bosphorus 1080p aom-av1: Speed 6 Two-Pass - Bosphorus 4K build-wasmer: Time To Compile ospray-studio: 3 - 1080p - 16 - Path Tracer aom-av1: Speed 4 Two-Pass - Bosphorus 1080p rocksdb: Update Rand rocksdb: Read Rand Write Rand rocksdb: Read While Writing rocksdb: Rand Read aom-av1: Speed 0 Two-Pass - Bosphorus 1080p build-mplayer: Time To Compile aom-av1: Speed 6 Two-Pass - Bosphorus 1080p onednn: Deconvolution Batch shapes_1d - u8s8f32 - CPU dav1d: Summer Nature 4K dav1d: Chimera 1080p 10-bit onednn: IP Shapes 1D - f32 - CPU onednn: IP Shapes 1D - u8s8f32 - CPU dav1d: Chimera 1080p avifenc: 6, Lossless aom-av1: Speed 8 Realtime - Bosphorus 4K avifenc: 6 onednn: Matrix Multiply Batch Shapes Transformer - f32 - CPU onednn: Matrix Multiply Batch Shapes Transformer - u8s8f32 - CPU aom-av1: Speed 9 Realtime - Bosphorus 1080p compress-pbzip2: FreeBSD-13.0-RELEASE-amd64-memstick.img Compression aom-av1: Speed 9 Realtime - Bosphorus 4K onednn: IP Shapes 3D - f32 - CPU onednn: IP Shapes 3D - u8s8f32 - CPU aom-av1: Speed 10 Realtime - Bosphorus 4K avifenc: 10, Lossless onednn: Convolution Batch Shapes Auto - u8s8f32 - CPU onednn: Convolution Batch Shapes Auto - f32 - CPU aom-av1: Speed 8 Realtime - Bosphorus 1080p dav1d: Summer Nature 1080p aom-av1: Speed 10 Realtime - Bosphorus 1080p onednn: Deconvolution Batch shapes_3d - f32 - CPU onednn: Deconvolution Batch shapes_3d - u8s8f32 - CPU onednn: IP Shapes 1D - bf16bf16bf16 - CPU A Intel Core i5-12400 B C 427 12.3203 163.591 12.9688 20972409216.502 57299 56352 4.17 1.79913 1.83804 0.13 4189 3398 3471 2.47222 136929 44 42 5745 277 853 6878 439 869 292 2822 2845 116689 115145 13.91 36805.2 34757.4 29463.3 34134.5 28488.2 24467.5 162.853 11.67 8 85.485 68568 9.58 679780 1497554 1467166 45697206 0.34 42.432 24.11 46.3983 172.71 481.75 113.724 28.3268 561.82 42.47 71.8268 53.7011 124.6 10.955 63.16 64.3737 27.9172 61.38 50.7024 47.6937 107.06 710.02 133.21 46.6701 17.2152 189.74 85.16 14.918 12.207 6.2 443 13.8893 182.112 14.2127 23002668637.36 191.075 50897 50151 4.70 1.96577 2.00038 0.14 3740 3114 3165 2.73146 122366 56 44 6076 301 944 7205 458 884 309 2940 3247 104124 102548 15.08 4099.42 4102.34 4095.96 2264.90 2264.98 2271.69 9.06388 85.968 12.36 8.99 77.914 62054 10.39 742880 1631656 1558793 49594691 0.37 39.113 26.97 1.42641 191.89 536.82 3.74052 0.957803 612.15 14.975 45.65 12.213 2.68966 1.04716 149.25 9.890 68.14 9.90106 2.10894 72.38 6.247 13.7565 14.3318 116.51 795.53 150.33 7.69890 1.98156 438 13.8804 182.037 14.1561 22882301161.56 191.476 50954 50418 4.70 1.95220 1.98550 0.14 3735 3108 3163 2.73399 122245 57 44 6049 301 944 7194 458 884 309 2963 3257 104044 102588 15.02 4098.3 4101.91 4086.37 2264.46 2261.84 2270.92 8.90115 85.939 12.41 8.92 77.817 62054 10.37 743135 1621120 1598728 49606865 0.37 39.062 26.95 1.42738 192.02 536.42 3.73962 0.959336 612.41 14.999 45.68 12.193 2.69025 1.05341 142.90 10.031 68.39 9.84082 2.09714 72.41 6.257 13.8003 14.3255 114.84 796.46 149.66 7.81726 1.99365 OpenBenchmarking.org
ONNX Runtime ONNX Runtime is developed by Microsoft and partners as a open-source, cross-platform, high performance machine learning inferencing and training accelerator. This test profile runs the ONNX Runtime with various models available from the ONNX Zoo. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Inferences Per Minute, More Is Better ONNX Runtime 1.11 Model: bertsquad-12 - Device: CPU - Executor: Parallel C B A 100 200 300 400 500 SE +/- 3.68, N = 12 SE +/- 4.83, N = 12 438 443 427 1. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt
OSPray OpenBenchmarking.org Items Per Second, More Is Better OSPray 2.9 Benchmark: particle_volume/scivis/real_time C B A 4 8 12 16 20 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 13.88 13.89 12.32
OpenBenchmarking.org Items Per Second, More Is Better OSPray 2.9 Benchmark: particle_volume/pathtracer/real_time C B A 40 80 120 160 200 SE +/- 0.10, N = 3 SE +/- 0.02, N = 3 182.04 182.11 163.59
OpenBenchmarking.org Items Per Second, More Is Better OSPray 2.9 Benchmark: particle_volume/ao/real_time C B A 4 8 12 16 20 SE +/- 0.04, N = 3 SE +/- 0.03, N = 3 14.16 14.21 12.97
OSPray Studio Intel OSPray Studio is an open-source, interactive visualization and ray-tracing software package. OSPray Studio makes use of Intel OSPray, a portable ray-tracing engine for high-performance, high-fidelity visualizations. OSPray builds off Intel's Embree and Intel SPMD Program Compiler (ISPC) components as part of the oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better OSPray Studio 0.10 Camera: 2 - Resolution: 1080p - Samples Per Pixel: 16 - Renderer: Path Tracer C B A 12K 24K 36K 48K 60K SE +/- 27.83, N = 3 SE +/- 44.19, N = 3 50954 50897 57299 1. (CXX) g++ options: -O3 -lm -ldl
OpenBenchmarking.org ms, Fewer Is Better OSPray Studio 0.10 Camera: 1 - Resolution: 1080p - Samples Per Pixel: 16 - Renderer: Path Tracer C B A 12K 24K 36K 48K 60K SE +/- 272.17, N = 3 SE +/- 21.38, N = 3 50418 50151 56352 1. (CXX) g++ options: -O3 -lm -ldl
AOM AV1 OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.3 Encoder Mode: Speed 4 Two-Pass - Input: Bosphorus 4K C B A 1.0575 2.115 3.1725 4.23 5.2875 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 4.70 4.70 4.17 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm
OSPray OpenBenchmarking.org Items Per Second, More Is Better OSPray 2.9 Benchmark: gravity_spheres_volume/dim_512/scivis/real_time C B A 0.4423 0.8846 1.3269 1.7692 2.2115 SE +/- 0.00260, N = 3 SE +/- 0.00094, N = 3 1.95220 1.96577 1.79913
OpenBenchmarking.org Items Per Second, More Is Better OSPray 2.9 Benchmark: gravity_spheres_volume/dim_512/ao/real_time C B A 0.4501 0.9002 1.3503 1.8004 2.2505 SE +/- 0.00129, N = 3 SE +/- 0.00584, N = 3 1.98550 2.00038 1.83804
AOM AV1 OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.3 Encoder Mode: Speed 0 Two-Pass - Input: Bosphorus 4K C B A 0.0315 0.063 0.0945 0.126 0.1575 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 0.14 0.14 0.13 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm
OSPray Studio Intel OSPray Studio is an open-source, interactive visualization and ray-tracing software package. OSPray Studio makes use of Intel OSPray, a portable ray-tracing engine for high-performance, high-fidelity visualizations. OSPray builds off Intel's Embree and Intel SPMD Program Compiler (ISPC) components as part of the oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better OSPray Studio 0.10 Camera: 3 - Resolution: 1080p - Samples Per Pixel: 1 - Renderer: Path Tracer C B A 900 1800 2700 3600 4500 SE +/- 2.85, N = 3 SE +/- 3.53, N = 3 3735 3740 4189 1. (CXX) g++ options: -O3 -lm -ldl
OpenBenchmarking.org ms, Fewer Is Better OSPray Studio 0.10 Camera: 1 - Resolution: 1080p - Samples Per Pixel: 1 - Renderer: Path Tracer C B A 700 1400 2100 2800 3500 SE +/- 10.02, N = 3 SE +/- 7.42, N = 3 3108 3114 3398 1. (CXX) g++ options: -O3 -lm -ldl
OpenBenchmarking.org ms, Fewer Is Better OSPray Studio 0.10 Camera: 2 - Resolution: 1080p - Samples Per Pixel: 1 - Renderer: Path Tracer C B A 700 1400 2100 2800 3500 SE +/- 0.33, N = 3 SE +/- 0.58, N = 3 3163 3165 3471 1. (CXX) g++ options: -O3 -lm -ldl
OSPray OpenBenchmarking.org Items Per Second, More Is Better OSPray 2.9 Benchmark: gravity_spheres_volume/dim_512/pathtracer/real_time C B A 0.6151 1.2302 1.8453 2.4604 3.0755 SE +/- 0.00158, N = 3 SE +/- 0.00279, N = 3 2.73399 2.73146 2.47222
OSPray Studio Intel OSPray Studio is an open-source, interactive visualization and ray-tracing software package. OSPray Studio makes use of Intel OSPray, a portable ray-tracing engine for high-performance, high-fidelity visualizations. OSPray builds off Intel's Embree and Intel SPMD Program Compiler (ISPC) components as part of the oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better OSPray Studio 0.10 Camera: 3 - Resolution: 1080p - Samples Per Pixel: 32 - Renderer: Path Tracer C B A 30K 60K 90K 120K 150K SE +/- 103.73, N = 3 SE +/- 170.37, N = 3 122245 122366 136929 1. (CXX) g++ options: -O3 -lm -ldl
ONNX Runtime ONNX Runtime is developed by Microsoft and partners as a open-source, cross-platform, high performance machine learning inferencing and training accelerator. This test profile runs the ONNX Runtime with various models available from the ONNX Zoo. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Inferences Per Minute, More Is Better ONNX Runtime 1.11 Model: fcn-resnet101-11 - Device: CPU - Executor: Parallel C B A 13 26 39 52 65 SE +/- 0.17, N = 3 SE +/- 0.44, N = 3 57 56 44 1. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt
OpenBenchmarking.org Inferences Per Minute, More Is Better ONNX Runtime 1.11 Model: fcn-resnet101-11 - Device: CPU - Executor: Standard C B A 10 20 30 40 50 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 44 44 42 1. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt
OpenBenchmarking.org Inferences Per Minute, More Is Better ONNX Runtime 1.11 Model: GPT-2 - Device: CPU - Executor: Parallel C B A 1300 2600 3900 5200 6500 SE +/- 8.66, N = 3 SE +/- 5.13, N = 3 6049 6076 5745 1. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt
OpenBenchmarking.org Inferences Per Minute, More Is Better ONNX Runtime 1.11 Model: yolov4 - Device: CPU - Executor: Parallel C B A 70 140 210 280 350 SE +/- 1.36, N = 3 SE +/- 0.88, N = 3 301 301 277 1. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt
OpenBenchmarking.org Inferences Per Minute, More Is Better ONNX Runtime 1.11 Model: ArcFace ResNet-100 - Device: CPU - Executor: Parallel C B A 200 400 600 800 1000 SE +/- 2.96, N = 3 SE +/- 3.33, N = 3 944 944 853 1. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt
OpenBenchmarking.org Inferences Per Minute, More Is Better ONNX Runtime 1.11 Model: GPT-2 - Device: CPU - Executor: Standard C B A 1500 3000 4500 6000 7500 SE +/- 2.52, N = 3 SE +/- 6.71, N = 3 7194 7205 6878 1. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt
OpenBenchmarking.org Inferences Per Minute, More Is Better ONNX Runtime 1.11 Model: bertsquad-12 - Device: CPU - Executor: Standard C B A 100 200 300 400 500 SE +/- 0.17, N = 3 SE +/- 0.17, N = 3 458 458 439 1. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt
OpenBenchmarking.org Inferences Per Minute, More Is Better ONNX Runtime 1.11 Model: ArcFace ResNet-100 - Device: CPU - Executor: Standard C B A 200 400 600 800 1000 SE +/- 0.17, N = 3 SE +/- 0.00, N = 3 884 884 869 1. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt
OpenBenchmarking.org Inferences Per Minute, More Is Better ONNX Runtime 1.11 Model: yolov4 - Device: CPU - Executor: Standard C B A 70 140 210 280 350 SE +/- 0.17, N = 3 SE +/- 0.17, N = 3 309 309 292 1. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt
OpenBenchmarking.org Inferences Per Minute, More Is Better ONNX Runtime 1.11 Model: super-resolution-10 - Device: CPU - Executor: Standard C B A 600 1200 1800 2400 3000 SE +/- 0.67, N = 3 SE +/- 12.08, N = 3 2963 2940 2822 1. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt
OpenBenchmarking.org Inferences Per Minute, More Is Better ONNX Runtime 1.11 Model: super-resolution-10 - Device: CPU - Executor: Parallel C B A 700 1400 2100 2800 3500 SE +/- 11.90, N = 3 SE +/- 4.73, N = 3 3257 3247 2845 1. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt
OSPray Studio Intel OSPray Studio is an open-source, interactive visualization and ray-tracing software package. OSPray Studio makes use of Intel OSPray, a portable ray-tracing engine for high-performance, high-fidelity visualizations. OSPray builds off Intel's Embree and Intel SPMD Program Compiler (ISPC) components as part of the oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better OSPray Studio 0.10 Camera: 2 - Resolution: 1080p - Samples Per Pixel: 32 - Renderer: Path Tracer C B A 20K 40K 60K 80K 100K SE +/- 63.66, N = 3 SE +/- 167.02, N = 3 104044 104124 116689 1. (CXX) g++ options: -O3 -lm -ldl
OpenBenchmarking.org ms, Fewer Is Better OSPray Studio 0.10 Camera: 1 - Resolution: 1080p - Samples Per Pixel: 32 - Renderer: Path Tracer C B A 20K 40K 60K 80K 100K SE +/- 84.91, N = 3 SE +/- 146.65, N = 3 102588 102548 115145 1. (CXX) g++ options: -O3 -lm -ldl
AOM AV1 OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.3 Encoder Mode: Speed 6 Realtime - Input: Bosphorus 4K C B A 4 8 12 16 20 SE +/- 0.07, N = 3 SE +/- 0.13, N = 15 15.02 15.08 13.91 1. (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 Intel oneAPI. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.6 Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPU C B A 8K 16K 24K 32K 40K SE +/- 6.25, N = 3 SE +/- 7.00, N = 3 4098.30 4099.42 36805.20 MIN: 16567 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl
OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.6 Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPU C B A 7K 14K 21K 28K 35K SE +/- 3.15, N = 3 SE +/- 1.65, N = 3 4101.91 4102.34 34757.40 MIN: 18514.7 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl
OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.6 Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPU C B A 6K 12K 18K 24K 30K SE +/- 12.29, N = 3 SE +/- 3.35, N = 3 4086.37 4095.96 29463.30 MIN: 4011.27 MIN: 4045.08 MIN: 14417.6 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl
OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.6 Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPU C B A 7K 14K 21K 28K 35K SE +/- 3.21, N = 3 SE +/- 0.80, N = 3 2264.46 2264.90 34134.50 MIN: 18540.8 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl
OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.6 Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPU C B A 6K 12K 18K 24K 30K SE +/- 5.98, N = 3 SE +/- 1.35, N = 3 2261.84 2264.98 28488.20 MIN: 12419 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl
OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.6 Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPU C B A 5K 10K 15K 20K 25K SE +/- 3.05, N = 3 SE +/- 4.51, N = 3 2270.92 2271.69 24467.50 MIN: 9924.5 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl
OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.6 Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPU C B A 40 80 120 160 200 SE +/- 0.13280, N = 15 SE +/- 0.17309, N = 15 8.90115 9.06388 162.85300 MIN: 6.38 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl
AOM AV1 OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.3 Encoder Mode: Speed 6 Realtime - Input: Bosphorus 1080p C B A 3 6 9 12 15 SE +/- 0.10, N = 8 SE +/- 0.04, N = 3 12.41 12.36 11.67 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm
OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.3 Encoder Mode: Speed 6 Two-Pass - Input: Bosphorus 4K C B A 3 6 9 12 15 SE +/- 0.07, N = 3 SE +/- 0.00, N = 3 8.92 8.99 8.00 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm
Timed Wasmer Compilation This test times how long it takes to compile Wasmer. Wasmer is written in the Rust programming language and is a WebAssembly runtime implementation that supports WASI and EmScripten. This test profile builds Wasmer with the Cranelift and Singlepast compiler features enabled. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Timed Wasmer Compilation 2.2 Time To Compile C B A 20 40 60 80 100 SE +/- 0.23, N = 3 SE +/- 0.11, N = 3 77.82 77.91 85.49 1. (CC) gcc options: -m64 -ldl -lxkbcommon -lgcc_s -lutil -lrt -lpthread -lm -lc -pie -nodefaultlibs
OSPray Studio Intel OSPray Studio is an open-source, interactive visualization and ray-tracing software package. OSPray Studio makes use of Intel OSPray, a portable ray-tracing engine for high-performance, high-fidelity visualizations. OSPray builds off Intel's Embree and Intel SPMD Program Compiler (ISPC) components as part of the oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better OSPray Studio 0.10 Camera: 3 - Resolution: 1080p - Samples Per Pixel: 16 - Renderer: Path Tracer C B A 15K 30K 45K 60K 75K SE +/- 140.67, N = 3 SE +/- 147.67, N = 3 62054 62054 68568 1. (CXX) g++ options: -O3 -lm -ldl
AOM AV1 OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.3 Encoder Mode: Speed 4 Two-Pass - Input: Bosphorus 1080p C B A 3 6 9 12 15 SE +/- 0.04, N = 3 SE +/- 0.01, N = 3 10.37 10.39 9.58 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm
OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 7.0.1 Test: Read Random Write Random C B A 300K 600K 900K 1200K 1500K SE +/- 1481.37, N = 3 SE +/- 8702.90, N = 3 1621120 1631656 1497554 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 7.0.1 Test: Read While Writing C B A 300K 600K 900K 1200K 1500K SE +/- 12505.02, N = 3 SE +/- 7170.07, N = 3 1598728 1558793 1467166 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 7.0.1 Test: Random Read C B A 11M 22M 33M 44M 55M SE +/- 309988.44, N = 3 SE +/- 269279.25, N = 3 49606865 49594691 45697206 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
AOM AV1 OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.3 Encoder Mode: Speed 0 Two-Pass - Input: Bosphorus 1080p C B A 0.0833 0.1666 0.2499 0.3332 0.4165 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 0.37 0.37 0.34 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm
AOM AV1 OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.3 Encoder Mode: Speed 6 Two-Pass - Input: Bosphorus 1080p C B A 6 12 18 24 30 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 26.95 26.97 24.11 1. (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 Intel oneAPI. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.6 Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPU C B A 11 22 33 44 55 SE +/- 0.00246, N = 3 SE +/- 0.00232, N = 3 1.42738 1.42641 46.39830 MIN: 1.4 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl
OpenBenchmarking.org FPS, More Is Better dav1d 1.0 Video Input: Chimera 1080p 10-bit C B A 120 240 360 480 600 SE +/- 0.74, N = 3 SE +/- 0.72, N = 3 536.42 536.82 481.75 1. (CC) gcc options: -pthread -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 Intel oneAPI. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.6 Harness: IP Shapes 1D - Data Type: f32 - Engine: CPU C B A 30 60 90 120 150 SE +/- 0.00589, N = 3 SE +/- 0.00457, N = 3 3.73962 3.74052 113.72400 MIN: 51.18 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl
OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.6 Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPU C B A 7 14 21 28 35 SE +/- 0.001531, N = 3 SE +/- 0.001376, N = 3 0.959336 0.957803 28.326800 MIN: 0.92 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl
AOM AV1 OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.3 Encoder Mode: Speed 8 Realtime - Input: Bosphorus 4K C B A 10 20 30 40 50 SE +/- 0.07, N = 3 SE +/- 0.02, N = 3 45.68 45.65 42.47 1. (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 Intel oneAPI. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.6 Harness: Matrix Multiply Batch Shapes Transformer - Data Type: f32 - Engine: CPU C B A 16 32 48 64 80 SE +/- 0.00320, N = 3 SE +/- 0.00256, N = 3 2.69025 2.68966 71.82680 MIN: 3.12 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl
OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.6 Harness: Matrix Multiply Batch Shapes Transformer - Data Type: u8s8f32 - Engine: CPU C B A 12 24 36 48 60 SE +/- 0.00112, N = 3 SE +/- 0.00153, N = 3 1.05341 1.04716 53.70110 MIN: 1.03 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl
AOM AV1 OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.3 Encoder Mode: Speed 9 Realtime - Input: Bosphorus 1080p C B A 30 60 90 120 150 SE +/- 0.31, N = 3 SE +/- 2.69, N = 15 142.90 149.25 124.60 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm
AOM AV1 OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.3 Encoder Mode: Speed 9 Realtime - Input: Bosphorus 4K C B A 15 30 45 60 75 SE +/- 0.04, N = 3 SE +/- 0.12, N = 3 68.39 68.14 63.16 1. (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 Intel oneAPI. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.6 Harness: IP Shapes 3D - Data Type: f32 - Engine: CPU C B A 14 28 42 56 70 SE +/- 0.00524, N = 3 SE +/- 0.01269, N = 3 9.84082 9.90106 64.37370 MIN: 9.41 MIN: 9.49 MIN: 14.76 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl
OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.6 Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPU C B A 7 14 21 28 35 SE +/- 0.00196, N = 3 SE +/- 0.00109, N = 3 2.09714 2.10894 27.91720 MIN: 2.08 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl
AOM AV1 OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.3 Encoder Mode: Speed 10 Realtime - Input: Bosphorus 4K C B A 16 32 48 64 80 SE +/- 0.05, N = 3 SE +/- 0.14, N = 3 72.41 72.38 61.38 1. (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 Intel oneAPI. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.6 Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPU C B A 11 22 33 44 55 SE +/- 0.03, N = 3 SE +/- 0.02, N = 3 13.80 13.76 50.70 MIN: 13.2 MIN: 13.16 MIN: 19.83 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl
OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.6 Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPU C B A 11 22 33 44 55 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 14.33 14.33 47.69 MIN: 14.16 MIN: 14.19 MIN: 17.03 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl
AOM AV1 OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.3 Encoder Mode: Speed 8 Realtime - Input: Bosphorus 1080p C B A 30 60 90 120 150 SE +/- 0.29, N = 3 SE +/- 0.41, N = 3 114.84 116.51 107.06 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm
AOM AV1 OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.3 Encoder Mode: Speed 10 Realtime - Input: Bosphorus 1080p C B A 30 60 90 120 150 SE +/- 1.27, N = 3 SE +/- 0.90, N = 3 149.66 150.33 133.21 1. (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 Intel oneAPI. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.6 Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPU C B A 11 22 33 44 55 SE +/- 0.10400, N = 3 SE +/- 0.00768, N = 3 7.81726 7.69890 46.67010 MIN: 7.6 MIN: 7.57 MIN: 16.15 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl
OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.6 Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPU C B A 4 8 12 16 20 SE +/- 0.01869, N = 3 SE +/- 0.00178, N = 3 1.99365 1.98156 17.21520 MIN: 1.97 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl
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. The test run did not produce a result. The test run did not produce a result.
C: The test run did not produce a result. The test run did not produce a result. The test run did not produce a result.
Harness: Matrix Multiply Batch Shapes Transformer - Data Type: bf16bf16bf16 - Engine: CPU
A: The test run did not produce a result.
B: The test run did not produce a result. The test run did not produce a result. The test run did not produce a result.
C: The test run did not produce a result. The test run did not produce a result. The test run did not produce a result.
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. The test run did not produce a result. The test run did not produce a result.
C: The test run did not produce a result. The test run did not produce a result. 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. The test run did not produce a result. The test run did not produce a result.
C: The test run did not produce a result. The test run did not produce a result. 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. The test run did not produce a result. The test run did not produce a result.
C: The test run did not produce a result. The test run did not produce a result. 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. The test run did not produce a result. The test run did not produce a result.
C: The test run did not produce a result. The test run did not produce a result. The test run did not produce a result.
A Processor: Intel Core i5-12400 @ 5.60GHz (6 Cores / 12 Threads), Motherboard: ASRock B660M-HDV (3.02 BIOS), Chipset: Intel Device 7aa7, Memory: 16GB, Disk: 512GB Sabrent, Graphics: llvmpipe, Audio: Realtek ALC897, Network: Intel
OS: Ubuntu 22.04, Kernel: 5.15.0-18-generic (x86_64), Desktop: GNOME Shell 41.3, Display Server: X Server 1.20.14, OpenGL: 4.5 Mesa 21.2.2 (LLVM 12.0.1 256 bits), Vulkan: 1.1.182, Compiler: GCC 11.2.0, File-System: ext4, Screen Resolution: 1920x1080
Kernel Notes: Transparent Huge Pages: madviseCompiler 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,brig,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-11-iOLsLC/gcc-11-11.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-iOLsLC/gcc-11-11.2.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -vProcessor Notes: Scaling Governor: intel_pstate powersave (EPP: balance_performance) - CPU Microcode: 0x18 - Thermald 2.4.7Java Notes: OpenJDK Runtime Environment (build 11.0.14.1+1-Ubuntu-0ubuntu1)Python Notes: Python 3.9.12Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced IBRS IBPB: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected
Testing initiated at 6 April 2022 15:24 by user phoronix.
Intel Core i5-12400 Kernel Notes: Transparent Huge Pages: madviseCompiler 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,brig,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-11-gBFGDP/gcc-11-11.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-gBFGDP/gcc-11-11.2.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -vProcessor Notes: Scaling Governor: intel_pstate powersave (EPP: balance_performance) - CPU Microcode: 0x18 - Thermald 2.4.9Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced IBRS IBPB: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected
Testing initiated at 6 April 2022 19:43 by user phoronix.
B Kernel Notes: Transparent Huge Pages: madviseCompiler 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,brig,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-11-gBFGDP/gcc-11-11.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-gBFGDP/gcc-11-11.2.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -vProcessor Notes: Scaling Governor: intel_pstate powersave (EPP: balance_performance) - CPU Microcode: 0x18 - Thermald 2.4.9Java Notes: OpenJDK Runtime Environment (build 11.0.14.1+1-Ubuntu-0ubuntu1)Python Notes: Python 3.10.4Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced IBRS IBPB: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected
Testing initiated at 6 April 2022 20:29 by user phoronix.
C Processor: Intel Core i5-12400 @ 5.60GHz (6 Cores / 12 Threads), Motherboard: ASRock B660M-HDV (3.02 BIOS), Chipset: Intel Device 7aa7, Memory: 16GB, Disk: 512GB Sabrent, Graphics: llvmpipe, Audio: Realtek ALC897, Network: Intel
OS: Ubuntu 22.04, Kernel: 5.15.0-18-generic (x86_64), Desktop: GNOME Shell 41.3, Display Server: X Server 1.20.14, OpenGL: 4.5 Mesa 22.0.1 (LLVM 13.0.1 256 bits), Vulkan: 1.2.204, Compiler: GCC 11.2.0, File-System: ext4, Screen Resolution: 1920x1080
Kernel Notes: Transparent Huge Pages: madviseCompiler 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,brig,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-11-gBFGDP/gcc-11-11.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-gBFGDP/gcc-11-11.2.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -vProcessor Notes: Scaling Governor: intel_pstate powersave (EPP: balance_performance) - CPU Microcode: 0x18 - Thermald 2.4.9Java Notes: OpenJDK Runtime Environment (build 11.0.14.1+1-Ubuntu-0ubuntu1)Python Notes: Python 3.10.4Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced IBRS IBPB: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected
Testing initiated at 7 April 2022 05:56 by user phoronix.