AMD Ryzen 9 7950X AVX-512 benchmark comparison by Michael Larabel launch day embargo lift review. Stock/out-of-the-box build with AVX-512. For lack of any AVX-512 toggle from the ASUS BIOS, the AVX2 / non-AVX-512 run was carried out by booting kernel with "clearcpuid=304" to clear AVX-512 support from the kernel and for the binary programs that scan /proc/cpuinfo for avx512* extensions. Plus for the open-source benchmarks specifying CFLAGS/CXXFLAGS without AVX-512 extensions. See full launch day review @ https://www.phoronix.com/review/amd-zen4-avx512
Without AVX-512 Kernel Notes: Transparent Huge Pages: madviseEnvironment Notes: CXXFLAGS="-O3 -march=native -mno-avx512f" CFLAGS="-O3 -march=native -mno-avx512f"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-OcsLtf/gcc-12-12-20220319/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-12-OcsLtf/gcc-12-12-20220319/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 -vProcessor Notes: Scaling Governor: amd-pstate performance (Boost: Enabled) - CPU Microcode: 0xa601203Python Notes: Python 3.10.4Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected
Default, AVX-512 Enabled Processor: AMD Ryzen 9 7950X 16-Core @ 5.88GHz (16 Cores / 32 Threads), Motherboard: ASUS ROG CROSSHAIR X670E HERO (0604 BIOS), Chipset: AMD Device 14d8, Memory: 32GB, Disk: 2000GB Samsung SSD 980 PRO 2TB + 2000GB, Graphics: AMD Radeon RX 6800 XT 16GB (2575/1000MHz), Audio: AMD Navi 21 HDMI Audio, Monitor: ASUS VP28U, Network: Intel I225-V + Intel Wi-Fi 6 AX210/AX211/AX411
OS: Ubuntu 22.04, Kernel: 6.0.0-060000rc1daily20220820-generic (x86_64), Desktop: GNOME Shell 42.2, Display Server: X Server + Wayland, OpenGL: 4.6 Mesa 22.3.0-devel (git-4685385 2022-08-23 jammy-oibaf-ppa) (LLVM 14.0.6 DRM 3.48), Vulkan: 1.3.224, Compiler: GCC 12.0.1 20220319, File-System: ext4, Screen Resolution: 3840x2160
Kernel Notes: Transparent Huge Pages: madviseEnvironment Notes: CXXFLAGS="-O3 -march=native -mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mavx512ifma -mavx512vbmi -mprefer-vector-width=512" CFLAGS="-O3 -march=native -mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mavx512ifma -mavx512vbmi -mprefer-vector-width=512"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-OcsLtf/gcc-12-12-20220319/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-12-OcsLtf/gcc-12-12-20220319/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 -vProcessor Notes: Scaling Governor: amd-pstate performance (Boost: Enabled) - CPU Microcode: 0xa601203Python Notes: Python 3.10.4Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected
AMD Ryzen 9 7950X AVX-512 OpenBenchmarking.org Phoronix Test Suite AMD Ryzen 9 7950X 16-Core @ 5.88GHz (16 Cores / 32 Threads) ASUS ROG CROSSHAIR X670E HERO (0604 BIOS) AMD Device 14d8 32GB 2000GB Samsung SSD 980 PRO 2TB + 2000GB AMD Radeon RX 6800 XT 16GB (2575/1000MHz) AMD Navi 21 HDMI Audio ASUS VP28U Intel I225-V + Intel Wi-Fi 6 AX210/AX211/AX411 Ubuntu 22.04 6.0.0-060000rc1daily20220820-generic (x86_64) GNOME Shell 42.2 X Server + Wayland 4.6 Mesa 22.3.0-devel (git-4685385 2022-08-23 jammy-oibaf-ppa) (LLVM 14.0.6 DRM 3.48) 1.3.224 GCC 12.0.1 20220319 ext4 3840x2160 Processor Motherboard Chipset Memory Disk Graphics Audio Monitor Network OS Kernel Desktop Display Server OpenGL Vulkan Compiler File-System Screen Resolution AMD Ryzen 9 7950X AVX-512 Benchmarks System Logs - Transparent Huge Pages: madvise - Without AVX-512: CXXFLAGS="-O3 -march=native -mno-avx512f" CFLAGS="-O3 -march=native -mno-avx512f" - Default, AVX-512 Enabled: CXXFLAGS="-O3 -march=native -mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mavx512ifma -mavx512vbmi -mprefer-vector-width=512" CFLAGS="-O3 -march=native -mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mavx512ifma -mavx512vbmi -mprefer-vector-width=512" - --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-OcsLtf/gcc-12-12-20220319/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-12-OcsLtf/gcc-12-12-20220319/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: amd-pstate performance (Boost: Enabled) - CPU Microcode: 0xa601203 - Python 3.10.4 - itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected
Without AVX-512 vs. Default, AVX-512 Enabled Comparison Phoronix Test Suite Baseline +66.4% +66.4% +132.8% +132.8% +199.2% +199.2% +265.6% +265.6% 265.7% 117.1% 117% 115.1% 114.4% 113.7% 113.6% 109.1% 108.6% 104.5% 103.8% 103.8% 100% 100% 98.2% 98.1% 97.1% 92.4% 88% 87% 86.8% 83.1% 80.2% 79.9% 79.8% 78.9% 77.6% 70.8% 68.2% 66.9% 58.6% 56.1% 54.8% 53.1% 50% 48% 47.9% 40% 39.3% 37.7% 37.4% 35.7% 32.6% 30.1% 26.1% 25.4% 23% 22.4% 21.4% 21.1% 21% 20.7% 20.1% 20% 15.6% 14% 12.8% 9.9% 8.3% 3.4% 2.8% Myriad-Groestl W.P.D.F.I - CPU W.P.D.F.I - CPU F.D.F - CPU F.D.F - CPU W.P.D.F - CPU W.P.D.F - CPU F.D.F.I - CPU F.D.F.I - CPU Blake-2 S M.T.E.T.D.F - CPU M.T.E.T.D.F - CPU A.G.R.R.0.F - CPU A.G.R.R.0.F - CPU V.D.F.I - CPU V.D.F.I - CPU LBC, LBRY Credits D.B.s - u8s8f32 - CPU D.B.s - u8s8f32 - CPU P.V.B.D.F - CPU P.V.B.D.F - CPU gravity_spheres_volume/dim_512/scivis/real_time P.D.F - CPU P.D.F - CPU P.D.F - CPU P.D.F - CPU gravity_spheres_volume/dim_512/ao/real_time A.G.R.R.0.F.I - CPU A.G.R.R.0.F.I - CPU Q.S.2.P CPU - vision_transformer R.N.N.I - u8s8f32 - CPU R.N.N.I - bf16bf16bf16 - CPU Garlicoin IP Shapes 1D - u8s8f32 - CPU V.D.F - CPU V.D.F - CPU C.B.S.A - u8s8f32 - CPU Skeincoin R.N.N.T - u8s8f32 - CPU gravity_spheres_volume/dim_512/pathtracer/real_time R.N.N.T - bf16bf16bf16 - CPU DistinctUserID vklBenchmark ISPC TopTweet PartialTweets 1 - 4K - 1 - Path Tracer 3 - 4K - 1 - Path Tracer Kostya 1 - 4K - 32 - Path Tracer Pathtracer ISPC - Crown 1 - 4K - 16 - Path Tracer 3 - 4K - 32 - Path Tracer 3 - 4K - 16 - Path Tracer Pathtracer ISPC - Asian Dragon LargeRand SqueezeNetV1.0 Eigen particle_volume/pathtracer/real_time Summer Nature 4K S.N.1 Cpuminer-Opt OpenVINO OpenVINO OpenVINO OpenVINO OpenVINO OpenVINO OpenVINO OpenVINO Cpuminer-Opt OpenVINO OpenVINO OpenVINO OpenVINO OpenVINO OpenVINO Cpuminer-Opt oneDNN oneDNN OpenVINO OpenVINO OSPRay OpenVINO OpenVINO OpenVINO OpenVINO OSPRay OpenVINO OpenVINO Cpuminer-Opt NCNN oneDNN oneDNN Cpuminer-Opt oneDNN OpenVINO OpenVINO oneDNN Cpuminer-Opt oneDNN OSPRay oneDNN simdjson OpenVKL simdjson simdjson OSPRay Studio OSPRay Studio simdjson OSPRay Studio Embree OSPRay Studio OSPRay Studio OSPRay Studio Embree simdjson Mobile Neural Network LeelaChessZero OSPRay dav1d dav1d Without AVX-512 Default, AVX-512 Enabled
AMD Ryzen 9 7950X AVX-512 cpuminer-opt: Myriad-Groestl openvino: Weld Porosity Detection FP16-INT8 - CPU openvino: Weld Porosity Detection FP16-INT8 - CPU openvino: Face Detection FP16 - CPU openvino: Face Detection FP16 - CPU openvino: Weld Porosity Detection FP16 - CPU openvino: Weld Porosity Detection FP16 - CPU openvino: Face Detection FP16-INT8 - CPU openvino: Face Detection FP16-INT8 - CPU openvino: Machine Translation EN To DE FP16 - CPU openvino: Machine Translation EN To DE FP16 - CPU openvino: Age Gender Recognition Retail 0013 FP16 - CPU openvino: Age Gender Recognition Retail 0013 FP16 - CPU openvino: Vehicle Detection FP16-INT8 - CPU openvino: Vehicle Detection FP16-INT8 - CPU cpuminer-opt: LBC, LBRY Credits onednn: Deconvolution Batch shapes_1d - u8s8f32 - CPU onednn: Deconvolution Batch shapes_3d - u8s8f32 - CPU openvino: Person Vehicle Bike Detection FP16 - CPU openvino: Person Vehicle Bike Detection FP16 - CPU ospray: gravity_spheres_volume/dim_512/scivis/real_time openvino: Person Detection FP16 - CPU openvino: Person Detection FP16 - CPU openvino: Person Detection FP32 - CPU openvino: Person Detection FP32 - CPU ospray: gravity_spheres_volume/dim_512/ao/real_time openvino: Age Gender Recognition Retail 0013 FP16-INT8 - CPU openvino: Age Gender Recognition Retail 0013 FP16-INT8 - CPU cpuminer-opt: Quad SHA-256, Pyrite ncnn: CPU - vision_transformer onednn: Recurrent Neural Network Inference - u8s8f32 - CPU onednn: Recurrent Neural Network Inference - bf16bf16bf16 - CPU openvino: Vehicle Detection FP16 - CPU openvino: Vehicle Detection FP16 - CPU onednn: Convolution Batch Shapes Auto - u8s8f32 - CPU cpuminer-opt: Skeincoin onednn: Recurrent Neural Network Training - u8s8f32 - CPU ospray: gravity_spheres_volume/dim_512/pathtracer/real_time onednn: Recurrent Neural Network Training - bf16bf16bf16 - CPU simdjson: DistinctUserID openvkl: vklBenchmark ISPC simdjson: TopTweet simdjson: PartialTweets ospray-studio: 1 - 4K - 1 - Path Tracer ospray-studio: 3 - 4K - 1 - Path Tracer simdjson: Kostya ospray-studio: 1 - 4K - 32 - Path Tracer embree: Pathtracer ISPC - Crown ospray-studio: 1 - 4K - 16 - Path Tracer ospray-studio: 3 - 4K - 32 - Path Tracer ospray-studio: 3 - 4K - 16 - Path Tracer embree: Pathtracer ISPC - Asian Dragon simdjson: LargeRand mnn: SqueezeNetV1.0 lczero: Eigen ospray: particle_volume/pathtracer/real_time dav1d: Summer Nature 4K dav1d: Summer Nature 1080p cpuminer-opt: Garlicoin cpuminer-opt: Blake-2 S onednn: IP Shapes 1D - u8s8f32 - CPU Without AVX-512 Default, AVX-512 Enabled 16393 11.81 1353.84 6.74 1178.81 11.73 681.37 13.60 585.81 121.06 66.03 0.7 22781.70 953.79 8.38 76960 0.800116 1.08396 907.36 8.80 4.33398 4.20 1889.40 4.20 1887.13 4.53529 0.41 38316.87 192667 62.74 910.460 902.102 15.92 502.28 7.44936 204320 1566.09 6.92227 1544.39 7.74 153 7.90 7.69 4502 5348 4.95 146156 29.1170 74844 172872 88344 30.3870 1.57 3.997 1578 231.378 380.32 1412.27 2597.65 1033700 0.625942 59957 5.44 2938.13 14.50 549.94 5.49 1455.45 28.44 280.86 59.39 134.59 0.35 45555.67 1890.25 4.23 151720 0.415940 0.576432 1696.82 4.71 7.93432 7.57 1050.37 7.55 1054.92 8.05397 0.24 64463.94 321503 39.57 583.316 582.901 10.76 742.90 5.32127 284667 1137.29 9.50906 1137.96 10.26 199 9.96 9.64 3659 4368 6.01 120727 35.2293 62029 143981 73617 35.1217 1.79 3.543 1735 250.655 393.40 1451.94 3977.80 2113434 0.417196 OpenBenchmarking.org
Cpuminer-Opt Cpuminer-Opt is a fork of cpuminer-multi that carries a wide range of CPU performance optimizations for measuring the potential cryptocurrency mining performance of the CPU/processor with a wide variety of cryptocurrencies. The benchmark reports the hash speed for the CPU mining performance for the selected cryptocurrency. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org kH/s, More Is Better Cpuminer-Opt 3.18 Algorithm: Myriad-Groestl Without AVX-512 Default, AVX-512 Enabled 13K 26K 39K 52K 65K SE +/- 105.88, N = 3 SE +/- 669.95, N = 15 16393 59957 -mno-avx512f -mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mavx512ifma -mavx512vbmi 1. (CXX) g++ options: -O3 -march=native -lcurl -lz -lpthread -lssl -lcrypto -lgmp kH/s Per Watt
OpenBenchmarking.org kH/s Per Watt, More Is Better Cpuminer-Opt 3.18 Algorithm: Myriad-Groestl Without AVX-512 Default, AVX-512 Enabled 110 220 330 440 550 128.78 496.89 CPU Peak Freq (Highest CPU Core Frequency
Min Avg Max Without AVX-512 5344 5449 5881 Default, AVX-512 Enabled 5298 5503 5881 OpenBenchmarking.org Megahertz, More Is Better Cpuminer-Opt 3.18 CPU Peak Freq (Highest CPU Core Frequency) Monitor 1600 3200 4800 6400 8000 CPU Power Consumption
Min Avg Max Without AVX-512 23.6 127.3 150.7 Default, AVX-512 Enabled 21.7 120.7 179.8 OpenBenchmarking.org Watts, Fewer Is Better Cpuminer-Opt 3.18 CPU Power Consumption Monitor 50 100 150 200 250 CPU Temp
Min Avg Max Without AVX-512 43.3 67.7 73.0 Default, AVX-512 Enabled 42.1 67.6 71.3 OpenBenchmarking.org Celsius, Fewer Is Better Cpuminer-Opt 3.18 CPU Temperature Monitor 20 40 60 80 100
OpenVINO This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2022.2.dev Model: Weld Porosity Detection FP16-INT8 - Device: CPU Without AVX-512 Default, AVX-512 Enabled 3 6 9 12 15 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 11.81 5.44 -mno-avx512f - MIN: 6.9 / MAX: 19.2 -mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mavx512ifma -mavx512vbmi - MIN: 2.88 / MAX: 13.32 1. (CXX) g++ options: -fPIC -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -fno-strict-overflow -fwrapv -flto -shared CPU Peak Freq (Highest CPU Core Frequency
Min Avg Max Without AVX-512 4982 5093 5881 Default, AVX-512 Enabled 4582 5163 5881 OpenBenchmarking.org Megahertz, More Is Better OpenVINO 2022.2.dev CPU Peak Freq (Highest CPU Core Frequency) Monitor 1600 3200 4800 6400 8000 CPU Power Consumption
Min Avg Max Without AVX-512 23.1 211.2 232.0 Default, AVX-512 Enabled 23.3 212.3 236.0 OpenBenchmarking.org Watts, Fewer Is Better OpenVINO 2022.2.dev CPU Power Consumption Monitor 60 120 180 240 300 CPU Temp
Min Avg Max Without AVX-512 47.9 93.5 95.4 Default, AVX-512 Enabled 45.9 93.1 95.3 OpenBenchmarking.org Celsius, Fewer Is Better OpenVINO 2022.2.dev CPU Temperature Monitor 20 40 60 80 100
OpenBenchmarking.org FPS, More Is Better OpenVINO 2022.2.dev Model: Weld Porosity Detection FP16-INT8 - Device: CPU Without AVX-512 Default, AVX-512 Enabled 600 1200 1800 2400 3000 SE +/- 2.11, N = 3 SE +/- 4.82, N = 3 1353.84 2938.13 -mno-avx512f -mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mavx512ifma -mavx512vbmi 1. (CXX) g++ options: -fPIC -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -fno-strict-overflow -fwrapv -flto -shared
OpenBenchmarking.org FPS, More Is Better OpenVINO 2022.2.dev Model: Face Detection FP16 - Device: CPU Without AVX-512 Default, AVX-512 Enabled 4 8 12 16 20 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 6.74 14.50 -mno-avx512f -mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mavx512ifma -mavx512vbmi 1. (CXX) g++ options: -fPIC -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -fno-strict-overflow -fwrapv -flto -shared
Result
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2022.2.dev Model: Face Detection FP16 - Device: CPU Without AVX-512 Default, AVX-512 Enabled 300 600 900 1200 1500 SE +/- 0.92, N = 3 SE +/- 0.48, N = 3 1178.81 549.94 -mno-avx512f - MIN: 596.16 / MAX: 1250.72 -mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mavx512ifma -mavx512vbmi - MIN: 282.71 / MAX: 577.01 1. (CXX) g++ options: -fPIC -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -fno-strict-overflow -fwrapv -flto -shared CPU Peak Freq (Highest CPU Core Frequency
Min Avg Max Without AVX-512 4988 5151 5881 Default, AVX-512 Enabled 5038 5180 5881 OpenBenchmarking.org Megahertz, More Is Better OpenVINO 2022.2.dev CPU Peak Freq (Highest CPU Core Frequency) Monitor 1600 3200 4800 6400 8000 CPU Power Consumption
Min Avg Max Without AVX-512 20.6 212.4 235.9 Default, AVX-512 Enabled 23.3 209.6 235.1 OpenBenchmarking.org Watts, Fewer Is Better OpenVINO 2022.2.dev CPU Power Consumption Monitor 60 120 180 240 300 CPU Temp
Min Avg Max Without AVX-512 41.8 93.0 96.3 Default, AVX-512 Enabled 40.9 93.1 95.9 OpenBenchmarking.org Celsius, Fewer Is Better OpenVINO 2022.2.dev CPU Temperature Monitor 20 40 60 80 100
Result
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2022.2.dev Model: Weld Porosity Detection FP16 - Device: CPU Without AVX-512 Default, AVX-512 Enabled 3 6 9 12 15 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 11.73 5.49 -mno-avx512f - MIN: 6.24 / MAX: 20.45 -mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mavx512ifma -mavx512vbmi - MIN: 2.89 / MAX: 13.22 1. (CXX) g++ options: -fPIC -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -fno-strict-overflow -fwrapv -flto -shared CPU Peak Freq (Highest CPU Core Frequency
Min Avg Max Without AVX-512 5008 5103 5881 Default, AVX-512 Enabled 5075 5159 5881 OpenBenchmarking.org Megahertz, More Is Better OpenVINO 2022.2.dev CPU Peak Freq (Highest CPU Core Frequency) Monitor 1600 3200 4800 6400 8000 CPU Power Consumption
Min Avg Max Without AVX-512 23.1 212.2 232.9 Default, AVX-512 Enabled 22.8 208.9 234.0 OpenBenchmarking.org Watts, Fewer Is Better OpenVINO 2022.2.dev CPU Power Consumption Monitor 60 120 180 240 300 CPU Temp
Min Avg Max Without AVX-512 48.0 93.9 95.8 Default, AVX-512 Enabled 47.8 93.3 95.4 OpenBenchmarking.org Celsius, Fewer Is Better OpenVINO 2022.2.dev CPU Temperature Monitor 20 40 60 80 100
OpenBenchmarking.org FPS, More Is Better OpenVINO 2022.2.dev Model: Weld Porosity Detection FP16 - Device: CPU Without AVX-512 Default, AVX-512 Enabled 300 600 900 1200 1500 SE +/- 0.52, N = 3 SE +/- 1.06, N = 3 681.37 1455.45 -mno-avx512f -mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mavx512ifma -mavx512vbmi 1. (CXX) g++ options: -fPIC -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -fno-strict-overflow -fwrapv -flto -shared
OpenBenchmarking.org FPS, More Is Better OpenVINO 2022.2.dev Model: Face Detection FP16-INT8 - Device: CPU Without AVX-512 Default, AVX-512 Enabled 7 14 21 28 35 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 13.60 28.44 -mno-avx512f -mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mavx512ifma -mavx512vbmi 1. (CXX) g++ options: -fPIC -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -fno-strict-overflow -fwrapv -flto -shared
Result
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2022.2.dev Model: Face Detection FP16-INT8 - Device: CPU Without AVX-512 Default, AVX-512 Enabled 130 260 390 520 650 SE +/- 0.73, N = 3 SE +/- 0.17, N = 3 585.81 280.86 -mno-avx512f - MIN: 556.1 / MAX: 596 -mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mavx512ifma -mavx512vbmi - MIN: 263.49 / MAX: 294.78 1. (CXX) g++ options: -fPIC -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -fno-strict-overflow -fwrapv -flto -shared CPU Peak Freq (Highest CPU Core Frequency
Min Avg Max Without AVX-512 4963 5101 5881 Default, AVX-512 Enabled 5069 5188 5881 OpenBenchmarking.org Megahertz, More Is Better OpenVINO 2022.2.dev CPU Peak Freq (Highest CPU Core Frequency) Monitor 1600 3200 4800 6400 8000 CPU Power Consumption
Min Avg Max Without AVX-512 22.9 206.6 233.0 Default, AVX-512 Enabled 22.2 207.0 227.9 OpenBenchmarking.org Watts, Fewer Is Better OpenVINO 2022.2.dev CPU Power Consumption Monitor 60 120 180 240 300 CPU Temp
Min Avg Max Without AVX-512 48.3 93.3 95.6 Default, AVX-512 Enabled 45.8 93.2 96.0 OpenBenchmarking.org Celsius, Fewer Is Better OpenVINO 2022.2.dev CPU Temperature Monitor 20 40 60 80 100
Result
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2022.2.dev Model: Machine Translation EN To DE FP16 - Device: CPU Without AVX-512 Default, AVX-512 Enabled 30 60 90 120 150 SE +/- 0.21, N = 3 SE +/- 0.18, N = 3 121.06 59.39 -mno-avx512f - MIN: 57.76 / MAX: 141.8 -mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mavx512ifma -mavx512vbmi - MIN: 26.85 / MAX: 70.78 1. (CXX) g++ options: -fPIC -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -fno-strict-overflow -fwrapv -flto -shared CPU Peak Freq (Highest CPU Core Frequency
Min Avg Max Without AVX-512 4888 5140 5881 Default, AVX-512 Enabled 5139 5243 5881 OpenBenchmarking.org Megahertz, More Is Better OpenVINO 2022.2.dev CPU Peak Freq (Highest CPU Core Frequency) Monitor 1600 3200 4800 6400 8000 CPU Power Consumption
Min Avg Max Without AVX-512 23.2 205.1 225.9 Default, AVX-512 Enabled 23.6 191.8 217.6 OpenBenchmarking.org Watts, Fewer Is Better OpenVINO 2022.2.dev CPU Power Consumption Monitor 60 120 180 240 300 CPU Temp
Min Avg Max Without AVX-512 48.6 93.7 96.8 Default, AVX-512 Enabled 47.3 87.2 90.1 OpenBenchmarking.org Celsius, Fewer Is Better OpenVINO 2022.2.dev CPU Temperature Monitor 20 40 60 80 100
OpenBenchmarking.org FPS, More Is Better OpenVINO 2022.2.dev Model: Machine Translation EN To DE FP16 - Device: CPU Without AVX-512 Default, AVX-512 Enabled 30 60 90 120 150 SE +/- 0.12, N = 3 SE +/- 0.42, N = 3 66.03 134.59 -mno-avx512f -mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mavx512ifma -mavx512vbmi 1. (CXX) g++ options: -fPIC -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -fno-strict-overflow -fwrapv -flto -shared
Result
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2022.2.dev Model: Age Gender Recognition Retail 0013 FP16 - Device: CPU Without AVX-512 Default, AVX-512 Enabled 0.1575 0.315 0.4725 0.63 0.7875 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 0.70 0.35 -mno-avx512f - MIN: 0.39 / MAX: 8.82 -mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mavx512ifma -mavx512vbmi - MIN: 0.21 / MAX: 7.78 1. (CXX) g++ options: -fPIC -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -fno-strict-overflow -fwrapv -flto -shared CPU Peak Freq (Highest CPU Core Frequency
Min Avg Max Without AVX-512 4945 5053 5881 Default, AVX-512 Enabled 5006 5107 5881 OpenBenchmarking.org Megahertz, More Is Better OpenVINO 2022.2.dev CPU Peak Freq (Highest CPU Core Frequency) Monitor 1600 3200 4800 6400 8000 CPU Power Consumption
Min Avg Max Without AVX-512 23.3 209.3 228.7 Default, AVX-512 Enabled 23.2 214.9 234.4 OpenBenchmarking.org Watts, Fewer Is Better OpenVINO 2022.2.dev CPU Power Consumption Monitor 60 120 180 240 300 CPU Temp
Min Avg Max Without AVX-512 48.6 93.2 95.5 Default, AVX-512 Enabled 47.0 93.2 95.5 OpenBenchmarking.org Celsius, Fewer Is Better OpenVINO 2022.2.dev CPU Temperature Monitor 20 40 60 80 100
OpenBenchmarking.org FPS, More Is Better OpenVINO 2022.2.dev Model: Age Gender Recognition Retail 0013 FP16 - Device: CPU Without AVX-512 Default, AVX-512 Enabled 10K 20K 30K 40K 50K SE +/- 51.81, N = 3 SE +/- 43.30, N = 3 22781.70 45555.67 -mno-avx512f -mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mavx512ifma -mavx512vbmi 1. (CXX) g++ options: -fPIC -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -fno-strict-overflow -fwrapv -flto -shared
OpenBenchmarking.org FPS, More Is Better OpenVINO 2022.2.dev Model: Vehicle Detection FP16-INT8 - Device: CPU Without AVX-512 Default, AVX-512 Enabled 400 800 1200 1600 2000 SE +/- 0.65, N = 3 SE +/- 2.10, N = 3 953.79 1890.25 -mno-avx512f -mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mavx512ifma -mavx512vbmi 1. (CXX) g++ options: -fPIC -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -fno-strict-overflow -fwrapv -flto -shared
Result
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2022.2.dev Model: Vehicle Detection FP16-INT8 - Device: CPU Without AVX-512 Default, AVX-512 Enabled 2 4 6 8 10 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 8.38 4.23 -mno-avx512f - MIN: 4.65 / MAX: 17.13 -mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mavx512ifma -mavx512vbmi - MIN: 2.63 / MAX: 12.45 1. (CXX) g++ options: -fPIC -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -fno-strict-overflow -fwrapv -flto -shared CPU Peak Freq (Highest CPU Core Frequency
Min Avg Max Without AVX-512 5027 5125 5881 Default, AVX-512 Enabled 5066 5147 5881 OpenBenchmarking.org Megahertz, More Is Better OpenVINO 2022.2.dev CPU Peak Freq (Highest CPU Core Frequency) Monitor 1600 3200 4800 6400 8000 CPU Power Consumption
Min Avg Max Without AVX-512 23.5 209.4 234.1 Default, AVX-512 Enabled 22.8 212.9 234.8 OpenBenchmarking.org Watts, Fewer Is Better OpenVINO 2022.2.dev CPU Power Consumption Monitor 60 120 180 240 300 CPU Temp
Min Avg Max Without AVX-512 48.3 93.5 95.4 Default, AVX-512 Enabled 47.3 93.3 95.4 OpenBenchmarking.org Celsius, Fewer Is Better OpenVINO 2022.2.dev CPU Temperature Monitor 20 40 60 80 100
Cpuminer-Opt Cpuminer-Opt is a fork of cpuminer-multi that carries a wide range of CPU performance optimizations for measuring the potential cryptocurrency mining performance of the CPU/processor with a wide variety of cryptocurrencies. The benchmark reports the hash speed for the CPU mining performance for the selected cryptocurrency. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org kH/s, More Is Better Cpuminer-Opt 3.18 Algorithm: LBC, LBRY Credits Without AVX-512 Default, AVX-512 Enabled 30K 60K 90K 120K 150K SE +/- 40.41, N = 3 SE +/- 177.76, N = 3 76960 151720 -mno-avx512f -mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mavx512ifma -mavx512vbmi 1. (CXX) g++ options: -O3 -march=native -lcurl -lz -lpthread -lssl -lcrypto -lgmp kH/s Per Watt
OpenBenchmarking.org kH/s Per Watt, More Is Better Cpuminer-Opt 3.18 Algorithm: LBC, LBRY Credits Without AVX-512 Default, AVX-512 Enabled 300 600 900 1200 1500 579.30 1370.92 CPU Peak Freq (Highest CPU Core Frequency
Min Avg Max Without AVX-512 5164 5459 5881 Default, AVX-512 Enabled 5208 5520 5881 OpenBenchmarking.org Megahertz, More Is Better Cpuminer-Opt 3.18 CPU Peak Freq (Highest CPU Core Frequency) Monitor 1600 3200 4800 6400 8000 CPU Power Consumption
Min Avg Max Without AVX-512 23.5 132.8 181.2 Default, AVX-512 Enabled 23.3 110.7 206.7 OpenBenchmarking.org Watts, Fewer Is Better Cpuminer-Opt 3.18 CPU Power Consumption Monitor 60 120 180 240 300 CPU Temp
Min Avg Max Without AVX-512 41.9 73.0 86.5 Default, AVX-512 Enabled 40.5 66.6 83.9 OpenBenchmarking.org Celsius, Fewer Is Better Cpuminer-Opt 3.18 CPU Temperature Monitor 20 40 60 80 100
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.
Result
OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.6 Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPU Without AVX-512 Default, AVX-512 Enabled 0.18 0.36 0.54 0.72 0.9 SE +/- 0.010456, N = 3 SE +/- 0.000107, N = 3 0.800116 0.415940 -mno-avx512f - MIN: 0.76 -mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mavx512ifma -mavx512vbmi - MIN: 0.4 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl -lpthread CPU Peak Freq (Highest CPU Core Frequency
Min Avg Max Without AVX-512 4992 5348 5881 Default, AVX-512 Enabled 5180 5381 5881 OpenBenchmarking.org Megahertz, More Is Better oneDNN 2.6 CPU Peak Freq (Highest CPU Core Frequency) Monitor 1600 3200 4800 6400 8000 CPU Power Consumption
Min Avg Max Without AVX-512 17.5 152.3 233.2 Default, AVX-512 Enabled 23.0 149.1 219.8 OpenBenchmarking.org Watts, Fewer Is Better oneDNN 2.6 CPU Power Consumption Monitor 60 120 180 240 300 CPU Temp
Min Avg Max Without AVX-512 40.9 81.9 94.9 Default, AVX-512 Enabled 41.3 75.8 86.6 OpenBenchmarking.org Celsius, Fewer Is Better oneDNN 2.6 CPU Temperature Monitor 20 40 60 80 100
Result
OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.6 Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPU Without AVX-512 Default, AVX-512 Enabled 0.2439 0.4878 0.7317 0.9756 1.2195 SE +/- 0.006665, N = 9 SE +/- 0.001581, N = 9 1.083960 0.576432 -mno-avx512f - MIN: 1.03 -mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mavx512ifma -mavx512vbmi - MIN: 0.56 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl -lpthread CPU Peak Freq (Highest CPU Core Frequency
Min Avg Max Without AVX-512 5157 5585 5881 Default, AVX-512 Enabled 5208 5613 5881 OpenBenchmarking.org Megahertz, More Is Better oneDNN 2.6 CPU Peak Freq (Highest CPU Core Frequency) Monitor 1600 3200 4800 6400 8000 CPU Power Consumption
Min Avg Max Without AVX-512 22.8 108.1 230.7 Default, AVX-512 Enabled 23.1 102.3 213.6 OpenBenchmarking.org Watts, Fewer Is Better oneDNN 2.6 CPU Power Consumption Monitor 60 120 180 240 300 CPU Temp
Min Avg Max Without AVX-512 44.8 77.9 91.6 Default, AVX-512 Enabled 43.5 72.4 82.6 OpenBenchmarking.org Celsius, Fewer Is Better oneDNN 2.6 CPU Temperature Monitor 20 40 60 80 100
OpenVINO This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org FPS, More Is Better OpenVINO 2022.2.dev Model: Person Vehicle Bike Detection FP16 - Device: CPU Without AVX-512 Default, AVX-512 Enabled 400 800 1200 1600 2000 SE +/- 1.39, N = 3 SE +/- 3.05, N = 3 907.36 1696.82 -mno-avx512f -mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mavx512ifma -mavx512vbmi 1. (CXX) g++ options: -fPIC -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -fno-strict-overflow -fwrapv -flto -shared
Result
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2022.2.dev Model: Person Vehicle Bike Detection FP16 - Device: CPU Without AVX-512 Default, AVX-512 Enabled 2 4 6 8 10 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 8.80 4.71 -mno-avx512f - MIN: 5.34 / MAX: 19.18 -mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mavx512ifma -mavx512vbmi - MIN: 3.46 / MAX: 12.8 1. (CXX) g++ options: -fPIC -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -fno-strict-overflow -fwrapv -flto -shared CPU Peak Freq (Highest CPU Core Frequency
Min Avg Max Without AVX-512 4899 5114 5881 Default, AVX-512 Enabled 5100 5188 5881 OpenBenchmarking.org Megahertz, More Is Better OpenVINO 2022.2.dev CPU Peak Freq (Highest CPU Core Frequency) Monitor 1600 3200 4800 6400 8000 CPU Power Consumption
Min Avg Max Without AVX-512 23.7 209.7 228.7 Default, AVX-512 Enabled 19.8 209.2 227.6 OpenBenchmarking.org Watts, Fewer Is Better OpenVINO 2022.2.dev CPU Power Consumption Monitor 60 120 180 240 300 CPU Temp
Min Avg Max Without AVX-512 48.3 93.4 96.0 Default, AVX-512 Enabled 47.5 91.1 94.1 OpenBenchmarking.org Celsius, Fewer Is Better OpenVINO 2022.2.dev CPU Temperature Monitor 20 40 60 80 100
OSPRay Intel OSPRay is a portable ray-tracing engine for high-performance, high-fidelity scientific 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.
Result
OpenBenchmarking.org Items Per Second, More Is Better OSPRay 2.10 Benchmark: gravity_spheres_volume/dim_512/scivis/real_time Without AVX-512 Default, AVX-512 Enabled 2 4 6 8 10 SE +/- 0.00159, N = 3 SE +/- 0.03212, N = 3 4.33398 7.93432 Items Per Second Per Watt
OpenBenchmarking.org Items Per Second Per Watt, More Is Better OSPRay 2.10 Benchmark: gravity_spheres_volume/dim_512/scivis/real_time Without AVX-512 Default, AVX-512 Enabled 0.0095 0.019 0.0285 0.038 0.0475 0.022 0.042 CPU Peak Freq (Highest CPU Core Frequency
Min Avg Max Without AVX-512 5121 5201 5881 Default, AVX-512 Enabled 5166 5235 5881 OpenBenchmarking.org Megahertz, More Is Better OSPRay 2.10 CPU Peak Freq (Highest CPU Core Frequency) Monitor 1600 3200 4800 6400 8000 CPU Power Consumption
Min Avg Max Without AVX-512 23.1 193.1 207.2 Default, AVX-512 Enabled 22.4 188.0 204.2 OpenBenchmarking.org Watts, Fewer Is Better OSPRay 2.10 CPU Power Consumption Monitor 60 120 180 240 300 CPU Temp
Min Avg Max Without AVX-512 47.4 92.0 93.9 Default, AVX-512 Enabled 46.4 87.3 89.4 OpenBenchmarking.org Celsius, Fewer Is Better OSPRay 2.10 CPU Temperature Monitor 20 40 60 80 100
OpenVINO This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org FPS, More Is Better OpenVINO 2022.2.dev Model: Person Detection FP16 - Device: CPU Without AVX-512 Default, AVX-512 Enabled 2 4 6 8 10 SE +/- 0.00, N = 3 SE +/- 0.02, N = 3 4.20 7.57 -mno-avx512f -mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mavx512ifma -mavx512vbmi 1. (CXX) g++ options: -fPIC -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -fno-strict-overflow -fwrapv -flto -shared
Result
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2022.2.dev Model: Person Detection FP16 - Device: CPU Without AVX-512 Default, AVX-512 Enabled 400 800 1200 1600 2000 SE +/- 0.47, N = 3 SE +/- 2.40, N = 3 1889.40 1050.37 -mno-avx512f - MIN: 1032.21 / MAX: 2215.28 -mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mavx512ifma -mavx512vbmi - MIN: 604.91 / MAX: 1254.32 1. (CXX) g++ options: -fPIC -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -fno-strict-overflow -fwrapv -flto -shared CPU Peak Freq (Highest CPU Core Frequency
Min Avg Max Without AVX-512 4947 5189 5881 Default, AVX-512 Enabled 5035 5229 5881 OpenBenchmarking.org Megahertz, More Is Better OpenVINO 2022.2.dev CPU Peak Freq (Highest CPU Core Frequency) Monitor 1600 3200 4800 6400 8000 CPU Power Consumption
Min Avg Max Without AVX-512 10.2 206.7 232.4 Default, AVX-512 Enabled 23.2 199.4 219.9 OpenBenchmarking.org Watts, Fewer Is Better OpenVINO 2022.2.dev CPU Power Consumption Monitor 60 120 180 240 300 CPU Temp
Min Avg Max Without AVX-512 47.6 94.0 96.6 Default, AVX-512 Enabled 47.1 93.2 96.1 OpenBenchmarking.org Celsius, Fewer Is Better OpenVINO 2022.2.dev CPU Temperature Monitor 20 40 60 80 100
OpenBenchmarking.org FPS, More Is Better OpenVINO 2022.2.dev Model: Person Detection FP32 - Device: CPU Without AVX-512 Default, AVX-512 Enabled 2 4 6 8 10 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 4.20 7.55 -mno-avx512f -mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mavx512ifma -mavx512vbmi 1. (CXX) g++ options: -fPIC -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -fno-strict-overflow -fwrapv -flto -shared
Result
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2022.2.dev Model: Person Detection FP32 - Device: CPU Without AVX-512 Default, AVX-512 Enabled 400 800 1200 1600 2000 SE +/- 5.93, N = 3 SE +/- 3.05, N = 3 1887.13 1054.92 -mno-avx512f - MIN: 1054.92 / MAX: 2161.5 -mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mavx512ifma -mavx512vbmi - MIN: 641.2 / MAX: 1276.51 1. (CXX) g++ options: -fPIC -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -fno-strict-overflow -fwrapv -flto -shared CPU Peak Freq (Highest CPU Core Frequency
Min Avg Max Without AVX-512 4917 5157 5881 Default, AVX-512 Enabled 5059 5219 5881 OpenBenchmarking.org Megahertz, More Is Better OpenVINO 2022.2.dev CPU Peak Freq (Highest CPU Core Frequency) Monitor 1600 3200 4800 6400 8000 CPU Power Consumption
Min Avg Max Without AVX-512 23.4 205.1 233.4 Default, AVX-512 Enabled 23.0 199.5 219.7 OpenBenchmarking.org Watts, Fewer Is Better OpenVINO 2022.2.dev CPU Power Consumption Monitor 60 120 180 240 300 CPU Temp
Min Avg Max Without AVX-512 48.4 94.1 96.8 Default, AVX-512 Enabled 47.3 93.3 96.3 OpenBenchmarking.org Celsius, Fewer Is Better OpenVINO 2022.2.dev CPU Temperature Monitor 20 40 60 80 100
OSPRay Intel OSPRay is a portable ray-tracing engine for high-performance, high-fidelity scientific 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.
Result
OpenBenchmarking.org Items Per Second, More Is Better OSPRay 2.10 Benchmark: gravity_spheres_volume/dim_512/ao/real_time Without AVX-512 Default, AVX-512 Enabled 2 4 6 8 10 SE +/- 0.00574, N = 3 SE +/- 0.00437, N = 3 4.53529 8.05397 Items Per Second Per Watt
OpenBenchmarking.org Items Per Second Per Watt, More Is Better OSPRay 2.10 Benchmark: gravity_spheres_volume/dim_512/ao/real_time Without AVX-512 Default, AVX-512 Enabled 0.0097 0.0194 0.0291 0.0388 0.0485 0.023 0.043 CPU Peak Freq (Highest CPU Core Frequency
Min Avg Max Without AVX-512 5131 5201 5881 Default, AVX-512 Enabled 5165 5243 5881 OpenBenchmarking.org Megahertz, More Is Better OSPRay 2.10 CPU Peak Freq (Highest CPU Core Frequency) Monitor 1600 3200 4800 6400 8000 CPU Power Consumption
Min Avg Max Without AVX-512 23.1 193.5 209.6 Default, AVX-512 Enabled 22.5 189.2 205.4 OpenBenchmarking.org Watts, Fewer Is Better OSPRay 2.10 CPU Power Consumption Monitor 60 120 180 240 300 CPU Temp
Min Avg Max Without AVX-512 44.8 91.4 93.5 Default, AVX-512 Enabled 42.5 87.0 89.1 OpenBenchmarking.org Celsius, Fewer Is Better OSPRay 2.10 CPU Temperature Monitor 20 40 60 80 100
OpenVINO This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2022.2.dev Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU Without AVX-512 Default, AVX-512 Enabled 0.0923 0.1846 0.2769 0.3692 0.4615 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 0.41 0.24 -mno-avx512f - MIN: 0.22 / MAX: 7.87 -mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mavx512ifma -mavx512vbmi - MIN: 0.15 / MAX: 7.55 1. (CXX) g++ options: -fPIC -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -fno-strict-overflow -fwrapv -flto -shared CPU Peak Freq (Highest CPU Core Frequency
Min Avg Max Without AVX-512 4999 5114 5881 Default, AVX-512 Enabled 5062 5142 5881 OpenBenchmarking.org Megahertz, More Is Better OpenVINO 2022.2.dev CPU Peak Freq (Highest CPU Core Frequency) Monitor 1600 3200 4800 6400 8000 CPU Power Consumption
Min Avg Max Without AVX-512 23.1 208.4 234.1 Default, AVX-512 Enabled 20.0 217.4 237.8 OpenBenchmarking.org Watts, Fewer Is Better OpenVINO 2022.2.dev CPU Power Consumption Monitor 60 120 180 240 300 CPU Temp
Min Avg Max Without AVX-512 48.5 93.7 95.6 Default, AVX-512 Enabled 48.0 93.2 95.5 OpenBenchmarking.org Celsius, Fewer Is Better OpenVINO 2022.2.dev CPU Temperature Monitor 20 40 60 80 100
OpenBenchmarking.org FPS, More Is Better OpenVINO 2022.2.dev Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU Without AVX-512 Default, AVX-512 Enabled 14K 28K 42K 56K 70K SE +/- 43.53, N = 3 SE +/- 24.16, N = 3 38316.87 64463.94 -mno-avx512f -mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mavx512ifma -mavx512vbmi 1. (CXX) g++ options: -fPIC -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -fno-strict-overflow -fwrapv -flto -shared
Cpuminer-Opt Cpuminer-Opt is a fork of cpuminer-multi that carries a wide range of CPU performance optimizations for measuring the potential cryptocurrency mining performance of the CPU/processor with a wide variety of cryptocurrencies. The benchmark reports the hash speed for the CPU mining performance for the selected cryptocurrency. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org kH/s, More Is Better Cpuminer-Opt 3.18 Algorithm: Quad SHA-256, Pyrite Without AVX-512 Default, AVX-512 Enabled 70K 140K 210K 280K 350K SE +/- 177.04, N = 3 SE +/- 1040.42, N = 3 192667 321503 -mno-avx512f -mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mavx512ifma -mavx512vbmi 1. (CXX) g++ options: -O3 -march=native -lcurl -lz -lpthread -lssl -lcrypto -lgmp kH/s Per Watt
OpenBenchmarking.org kH/s Per Watt, More Is Better Cpuminer-Opt 3.18 Algorithm: Quad SHA-256, Pyrite Without AVX-512 Default, AVX-512 Enabled 600 1200 1800 2400 3000 1788.77 3025.64 CPU Peak Freq (Highest CPU Core Frequency
Min Avg Max Without AVX-512 5207 5522 5881 Default, AVX-512 Enabled 5224 5540 5881 OpenBenchmarking.org Megahertz, More Is Better Cpuminer-Opt 3.18 CPU Peak Freq (Highest CPU Core Frequency) Monitor 1600 3200 4800 6400 8000 CPU Power Consumption
Min Avg Max Without AVX-512 23.2 107.7 185.5 Default, AVX-512 Enabled 23.3 106.3 178.0 OpenBenchmarking.org Watts, Fewer Is Better Cpuminer-Opt 3.18 CPU Power Consumption Monitor 50 100 150 200 250 CPU Temp
Min Avg Max Without AVX-512 44.0 67.7 80.0 Default, AVX-512 Enabled 41.4 64.7 81.5 OpenBenchmarking.org Celsius, Fewer Is Better Cpuminer-Opt 3.18 CPU Temperature Monitor 20 40 60 80 100
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.org ms, Fewer Is Better NCNN 20220729 Target: CPU - Model: vision_transformer Without AVX-512 Default, AVX-512 Enabled 14 28 42 56 70 SE +/- 0.91, N = 3 SE +/- 0.03, N = 3 62.74 39.57 -mno-avx512f - MIN: 61.57 / MAX: 65.21 -mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mavx512ifma -mavx512vbmi - MIN: 39.32 / MAX: 41.99 1. (CXX) g++ options: -O3 -march=native -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 Intel oneAPI. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.6 Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPU Without AVX-512 Default, AVX-512 Enabled 200 400 600 800 1000 SE +/- 3.36, N = 3 SE +/- 0.21, N = 3 910.46 583.32 -mno-avx512f - MIN: 898.05 -mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mavx512ifma -mavx512vbmi - MIN: 579.29 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl -lpthread CPU Peak Freq (Highest CPU Core Frequency
Min Avg Max Without AVX-512 4804 5051 5881 Default, AVX-512 Enabled 4802 5091 5881 OpenBenchmarking.org Megahertz, More Is Better oneDNN 2.6 CPU Peak Freq (Highest CPU Core Frequency) Monitor 1600 3200 4800 6400 8000 CPU Power Consumption
Min Avg Max Without AVX-512 23.3 181.1 224.4 Default, AVX-512 Enabled 23.8 200.3 227.2 OpenBenchmarking.org Watts, Fewer Is Better oneDNN 2.6 CPU Power Consumption Monitor 60 120 180 240 300 CPU Temp
Min Avg Max Without AVX-512 47.5 86.4 95.8 Default, AVX-512 Enabled 47.0 89.2 92.6 OpenBenchmarking.org Celsius, Fewer Is Better oneDNN 2.6 CPU Temperature Monitor 20 40 60 80 100
Result
OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.6 Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPU Without AVX-512 Default, AVX-512 Enabled 200 400 600 800 1000 SE +/- 5.88, N = 3 SE +/- 1.02, N = 3 902.10 582.90 -mno-avx512f - MIN: 885.67 -mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mavx512ifma -mavx512vbmi - MIN: 578.18 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl -lpthread CPU Peak Freq (Highest CPU Core Frequency
Min Avg Max Without AVX-512 4495 5058 5881 Default, AVX-512 Enabled 4421 5088 5881 OpenBenchmarking.org Megahertz, More Is Better oneDNN 2.6 CPU Peak Freq (Highest CPU Core Frequency) Monitor 1600 3200 4800 6400 8000 CPU Power Consumption
Min Avg Max Without AVX-512 23.1 180.3 220.1 Default, AVX-512 Enabled 22.4 200.3 226.4 OpenBenchmarking.org Watts, Fewer Is Better oneDNN 2.6 CPU Power Consumption Monitor 60 120 180 240 300 CPU Temp
Min Avg Max Without AVX-512 47.6 86.8 96.0 Default, AVX-512 Enabled 47.5 88.9 92.8 OpenBenchmarking.org Celsius, Fewer Is Better oneDNN 2.6 CPU Temperature Monitor 20 40 60 80 100
OpenVINO This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2022.2.dev Model: Vehicle Detection FP16 - Device: CPU Without AVX-512 Default, AVX-512 Enabled 4 8 12 16 20 SE +/- 0.16, N = 3 SE +/- 0.12, N = 3 15.92 10.76 -mno-avx512f - MIN: 6.75 / MAX: 34.35 -mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mavx512ifma -mavx512vbmi - MIN: 4.25 / MAX: 23.39 1. (CXX) g++ options: -fPIC -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -fno-strict-overflow -fwrapv -flto -shared CPU Peak Freq (Highest CPU Core Frequency
Min Avg Max Without AVX-512 5062 5173 5881 Default, AVX-512 Enabled 5144 5265 5881 OpenBenchmarking.org Megahertz, More Is Better OpenVINO 2022.2.dev CPU Peak Freq (Highest CPU Core Frequency) Monitor 1600 3200 4800 6400 8000 CPU Power Consumption
Min Avg Max Without AVX-512 20.6 207.2 225.3 Default, AVX-512 Enabled 21.9 188.8 207.3 OpenBenchmarking.org Watts, Fewer Is Better OpenVINO 2022.2.dev CPU Power Consumption Monitor 60 120 180 240 300 CPU Temp
Min Avg Max Without AVX-512 47.9 91.2 94.1 Default, AVX-512 Enabled 47.5 83.4 86.0 OpenBenchmarking.org Celsius, Fewer Is Better OpenVINO 2022.2.dev CPU Temperature Monitor 20 40 60 80 100
OpenBenchmarking.org FPS, More Is Better OpenVINO 2022.2.dev Model: Vehicle Detection FP16 - Device: CPU Without AVX-512 Default, AVX-512 Enabled 160 320 480 640 800 SE +/- 5.20, N = 3 SE +/- 8.04, N = 3 502.28 742.90 -mno-avx512f -mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mavx512ifma -mavx512vbmi 1. (CXX) g++ options: -fPIC -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -fno-strict-overflow -fwrapv -flto -shared
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.
Result
OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.6 Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPU Without AVX-512 Default, AVX-512 Enabled 2 4 6 8 10 SE +/- 0.00637, N = 7 SE +/- 0.00255, N = 7 7.44936 5.32127 -mno-avx512f - MIN: 7.29 -mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mavx512ifma -mavx512vbmi - MIN: 5.26 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl -lpthread CPU Peak Freq (Highest CPU Core Frequency
Min Avg Max Without AVX-512 5318 5585 5881 Default, AVX-512 Enabled 4910 5475 5881 OpenBenchmarking.org Megahertz, More Is Better oneDNN 2.6 CPU Peak Freq (Highest CPU Core Frequency) Monitor 1600 3200 4800 6400 8000 CPU Power Consumption
Min Avg Max Without AVX-512 23.5 93.1 166.1 Default, AVX-512 Enabled 11.5 107.7 218.9 OpenBenchmarking.org Watts, Fewer Is Better oneDNN 2.6 CPU Power Consumption Monitor 60 120 180 240 300 CPU Temp
Min Avg Max Without AVX-512 45.1 58.8 65.6 Default, AVX-512 Enabled 42.0 69.7 82.9 OpenBenchmarking.org Celsius, Fewer Is Better oneDNN 2.6 CPU Temperature Monitor 20 40 60 80 100
Cpuminer-Opt Cpuminer-Opt is a fork of cpuminer-multi that carries a wide range of CPU performance optimizations for measuring the potential cryptocurrency mining performance of the CPU/processor with a wide variety of cryptocurrencies. The benchmark reports the hash speed for the CPU mining performance for the selected cryptocurrency. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org kH/s, More Is Better Cpuminer-Opt 3.18 Algorithm: Skeincoin Without AVX-512 Default, AVX-512 Enabled 60K 120K 180K 240K 300K SE +/- 1803.62, N = 3 SE +/- 424.91, N = 3 204320 284667 -mno-avx512f -mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mavx512ifma -mavx512vbmi 1. (CXX) g++ options: -O3 -march=native -lcurl -lz -lpthread -lssl -lcrypto -lgmp kH/s Per Watt
OpenBenchmarking.org kH/s Per Watt, More Is Better Cpuminer-Opt 3.18 Algorithm: Skeincoin Without AVX-512 Default, AVX-512 Enabled 600 1200 1800 2400 3000 1926.96 2696.44 CPU Peak Freq (Highest CPU Core Frequency
Min Avg Max Without AVX-512 5189 5517 5881 Default, AVX-512 Enabled 5157 5535 5881 OpenBenchmarking.org Megahertz, More Is Better Cpuminer-Opt 3.18 CPU Peak Freq (Highest CPU Core Frequency) Monitor 1600 3200 4800 6400 8000 CPU Power Consumption
Min Avg Max Without AVX-512 22.9 106.0 219.4 Default, AVX-512 Enabled 22.7 105.6 218.2 OpenBenchmarking.org Watts, Fewer Is Better Cpuminer-Opt 3.18 CPU Power Consumption Monitor 60 120 180 240 300 CPU Temp
Min Avg Max Without AVX-512 44.8 68.5 84.1 Default, AVX-512 Enabled 43.3 66.6 85.6 OpenBenchmarking.org Celsius, Fewer Is Better Cpuminer-Opt 3.18 CPU Temperature Monitor 20 40 60 80 100
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.
Result
OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.6 Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPU Without AVX-512 Default, AVX-512 Enabled 300 600 900 1200 1500 SE +/- 8.37, N = 3 SE +/- 1.54, N = 3 1566.09 1137.29 -mno-avx512f - MIN: 1541.57 -mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mavx512ifma -mavx512vbmi - MIN: 1130.88 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl -lpthread CPU Peak Freq (Highest CPU Core Frequency
Min Avg Max Without AVX-512 4772 5007 5881 Default, AVX-512 Enabled 4822 5166 5881 OpenBenchmarking.org Megahertz, More Is Better oneDNN 2.6 CPU Peak Freq (Highest CPU Core Frequency) Monitor 1600 3200 4800 6400 8000 CPU Power Consumption
Min Avg Max Without AVX-512 23.2 187.5 219.5 Default, AVX-512 Enabled 22.8 200.9 226.3 OpenBenchmarking.org Watts, Fewer Is Better oneDNN 2.6 CPU Power Consumption Monitor 60 120 180 240 300 CPU Temp
Min Avg Max Without AVX-512 43.5 88.1 95.9 Default, AVX-512 Enabled 42.5 87.8 92.0 OpenBenchmarking.org Celsius, Fewer Is Better oneDNN 2.6 CPU Temperature Monitor 20 40 60 80 100
OSPRay Intel OSPRay is a portable ray-tracing engine for high-performance, high-fidelity scientific 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.
Result
OpenBenchmarking.org Items Per Second, More Is Better OSPRay 2.10 Benchmark: gravity_spheres_volume/dim_512/pathtracer/real_time Without AVX-512 Default, AVX-512 Enabled 3 6 9 12 15 SE +/- 0.00119, N = 3 SE +/- 0.00541, N = 3 6.92227 9.50906 Items Per Second Per Watt
OpenBenchmarking.org Items Per Second Per Watt, More Is Better OSPRay 2.10 Benchmark: gravity_spheres_volume/dim_512/pathtracer/real_time Without AVX-512 Default, AVX-512 Enabled 0.0113 0.0226 0.0339 0.0452 0.0565 0.035 0.050 CPU Peak Freq (Highest CPU Core Frequency
Min Avg Max Without AVX-512 5107 5187 5881 Default, AVX-512 Enabled 5155 5225 5881 OpenBenchmarking.org Megahertz, More Is Better OSPRay 2.10 CPU Peak Freq (Highest CPU Core Frequency) Monitor 1600 3200 4800 6400 8000 CPU Power Consumption
Min Avg Max Without AVX-512 23.4 197.7 214.7 Default, AVX-512 Enabled 22.8 191.7 209.5 OpenBenchmarking.org Watts, Fewer Is Better OSPRay 2.10 CPU Power Consumption Monitor 60 120 180 240 300 CPU Temp
Min Avg Max Without AVX-512 48.0 93.3 95.1 Default, AVX-512 Enabled 46.3 88.9 91.0 OpenBenchmarking.org Celsius, Fewer Is Better OSPRay 2.10 CPU Temperature Monitor 20 40 60 80 100
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.
Result
OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.6 Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPU Without AVX-512 Default, AVX-512 Enabled 300 600 900 1200 1500 SE +/- 19.60, N = 3 SE +/- 1.66, N = 3 1544.39 1137.96 -mno-avx512f - MIN: 1494.51 -mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mavx512ifma -mavx512vbmi - MIN: 1131.23 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl -lpthread CPU Peak Freq (Highest CPU Core Frequency
Min Avg Max Without AVX-512 4745 4985 5881 Default, AVX-512 Enabled 4560 5163 5881 OpenBenchmarking.org Megahertz, More Is Better oneDNN 2.6 CPU Peak Freq (Highest CPU Core Frequency) Monitor 1600 3200 4800 6400 8000 CPU Power Consumption
Min Avg Max Without AVX-512 23.4 189.5 220.2 Default, AVX-512 Enabled 20.3 200.1 223.4 OpenBenchmarking.org Watts, Fewer Is Better oneDNN 2.6 CPU Power Consumption Monitor 60 120 180 240 300 CPU Temp
Min Avg Max Without AVX-512 47.3 89.8 96.1 Default, AVX-512 Enabled 47.5 88.8 92.0 OpenBenchmarking.org Celsius, Fewer Is Better oneDNN 2.6 CPU Temperature Monitor 20 40 60 80 100
simdjson This is a benchmark of SIMDJSON, a high performance JSON parser. SIMDJSON aims to be the fastest JSON parser and is used by projects like Microsoft FishStore, Yandex ClickHouse, Shopify, and others. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org GB/s, More Is Better simdjson 2.0 Throughput Test: DistinctUserID Without AVX-512 Default, AVX-512 Enabled 3 6 9 12 15 SE +/- 0.07, N = 3 SE +/- 0.06, N = 3 7.74 10.26 -mno-avx512f -mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mavx512ifma -mavx512vbmi 1. (CXX) g++ options: -O3 -march=native GB/s Per Watt
OpenBenchmarking.org GB/s Per Watt, More Is Better simdjson 2.0 Throughput Test: DistinctUserID Without AVX-512 Default, AVX-512 Enabled 0.0371 0.0742 0.1113 0.1484 0.1855 0.122 0.165 CPU Peak Freq (Highest CPU Core Frequency
OpenBenchmarking.org Megahertz, More Is Better simdjson 2.0 CPU Peak Freq (Highest CPU Core Frequency) Monitor Default, AVX-512 Enabled 1300 2600 3900 5200 6500 5881 CPU Power Consumption
Min Avg Max Without AVX-512 23.1 63.4 67.0 Default, AVX-512 Enabled 22.3 62.1 66.4 OpenBenchmarking.org Watts, Fewer Is Better simdjson 2.0 CPU Power Consumption Monitor 20 40 60 80 100 CPU Temp
Min Avg Max Without AVX-512 38.9 67.2 69.5 Default, AVX-512 Enabled 38.9 66.7 68.6 OpenBenchmarking.org Celsius, Fewer Is Better simdjson 2.0 CPU Temperature Monitor 20 40 60 80 100
OpenVKL OpenVKL is the Intel Open Volume Kernel Library that offers high-performance volume computation kernels and part of the Intel oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Items / Sec, More Is Better OpenVKL 1.0 Benchmark: vklBenchmark ISPC Without AVX-512 Default, AVX-512 Enabled 40 80 120 160 200 SE +/- 0.00, N = 3 SE +/- 0.33, N = 3 153 199 MIN: 14 / MAX: 1843 MIN: 17 / MAX: 2254 Items / Sec Per Watt
OpenBenchmarking.org Items / Sec Per Watt, More Is Better OpenVKL 1.0 Benchmark: vklBenchmark ISPC Without AVX-512 Default, AVX-512 Enabled 0.2873 0.5746 0.8619 1.1492 1.4365 0.912 1.277 CPU Peak Freq (Highest CPU Core Frequency
Min Avg Max Without AVX-512 5072 5346 5881 Default, AVX-512 Enabled 5168 5403 5881 OpenBenchmarking.org Megahertz, More Is Better OpenVKL 1.0 CPU Peak Freq (Highest CPU Core Frequency) Monitor 1600 3200 4800 6400 8000 CPU Power Consumption
Min Avg Max Without AVX-512 23.6 167.7 228.1 Default, AVX-512 Enabled 22.4 155.8 211.8 OpenBenchmarking.org Watts, Fewer Is Better OpenVKL 1.0 CPU Power Consumption Monitor 60 120 180 240 300 CPU Temp
Min Avg Max Without AVX-512 43.9 84.9 95.4 Default, AVX-512 Enabled 43.8 79.1 89.5 OpenBenchmarking.org Celsius, Fewer Is Better OpenVKL 1.0 CPU Temperature Monitor 20 40 60 80 100
simdjson This is a benchmark of SIMDJSON, a high performance JSON parser. SIMDJSON aims to be the fastest JSON parser and is used by projects like Microsoft FishStore, Yandex ClickHouse, Shopify, and others. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org GB/s, More Is Better simdjson 2.0 Throughput Test: TopTweet Without AVX-512 Default, AVX-512 Enabled 3 6 9 12 15 SE +/- 0.02, N = 3 SE +/- 0.09, N = 3 7.90 9.96 -mno-avx512f -mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mavx512ifma -mavx512vbmi 1. (CXX) g++ options: -O3 -march=native GB/s Per Watt
OpenBenchmarking.org GB/s Per Watt, More Is Better simdjson 2.0 Throughput Test: TopTweet Without AVX-512 Default, AVX-512 Enabled 0.0356 0.0712 0.1068 0.1424 0.178 0.125 0.158 CPU Peak Freq (Highest CPU Core Frequency
OpenBenchmarking.org Megahertz, More Is Better simdjson 2.0 CPU Peak Freq (Highest CPU Core Frequency) Monitor Default, AVX-512 Enabled 1300 2600 3900 5200 6500 5881 CPU Power Consumption
Min Avg Max Without AVX-512 23.2 63.4 67.0 Default, AVX-512 Enabled 22.0 62.9 66.5 OpenBenchmarking.org Watts, Fewer Is Better simdjson 2.0 CPU Power Consumption Monitor 20 40 60 80 100 CPU Temp
Min Avg Max Without AVX-512 39.5 66.7 67.9 Default, AVX-512 Enabled 39.0 65.4 66.6 OpenBenchmarking.org Celsius, Fewer Is Better simdjson 2.0 CPU Temperature Monitor 20 40 60 80 100
Result
OpenBenchmarking.org GB/s, More Is Better simdjson 2.0 Throughput Test: PartialTweets Without AVX-512 Default, AVX-512 Enabled 3 6 9 12 15 SE +/- 0.01, N = 3 SE +/- 0.08, N = 3 7.69 9.64 -mno-avx512f -mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mavx512ifma -mavx512vbmi 1. (CXX) g++ options: -O3 -march=native GB/s Per Watt
OpenBenchmarking.org GB/s Per Watt, More Is Better simdjson 2.0 Throughput Test: PartialTweets Without AVX-512 Default, AVX-512 Enabled 0.0349 0.0698 0.1047 0.1396 0.1745 0.121 0.155 CPU Peak Freq (Highest CPU Core Frequency
OpenBenchmarking.org Megahertz, More Is Better simdjson 2.0 CPU Peak Freq (Highest CPU Core Frequency) Monitor Default, AVX-512 Enabled 1300 2600 3900 5200 6500 5881 CPU Power Consumption
Min Avg Max Without AVX-512 23.5 63.8 67.3 Default, AVX-512 Enabled 22.4 62.3 66.2 OpenBenchmarking.org Watts, Fewer Is Better simdjson 2.0 CPU Power Consumption Monitor 20 40 60 80 100 CPU Temp
Min Avg Max Without AVX-512 39.3 66.3 67.6 Default, AVX-512 Enabled 39.0 65.3 68.4 OpenBenchmarking.org Celsius, Fewer Is Better simdjson 2.0 CPU Temperature Monitor 20 40 60 80 100
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.
Result
OpenBenchmarking.org ms, Fewer Is Better OSPRay Studio 0.11 Camera: 1 - Resolution: 4K - Samples Per Pixel: 1 - Renderer: Path Tracer Without AVX-512 Default, AVX-512 Enabled 1000 2000 3000 4000 5000 SE +/- 6.51, N = 3 SE +/- 5.21, N = 3 4502 3659 -mno-avx512f -mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mavx512ifma -mavx512vbmi 1. (CXX) g++ options: -O3 -march=native -ldl CPU Peak Freq (Highest CPU Core Frequency
Min Avg Max Without AVX-512 5123 5212 5881 Default, AVX-512 Enabled 5136 5230 5881 OpenBenchmarking.org Megahertz, More Is Better OSPRay Studio 0.11 CPU Peak Freq (Highest CPU Core Frequency) Monitor 1600 3200 4800 6400 8000 CPU Power Consumption
Min Avg Max Without AVX-512 17.7 198.8 223.6 Default, AVX-512 Enabled 17.2 198.2 221.8 OpenBenchmarking.org Watts, Fewer Is Better OSPRay Studio 0.11 CPU Power Consumption Monitor 60 120 180 240 300 CPU Temp
Min Avg Max Without AVX-512 41.9 91.0 94.1 Default, AVX-512 Enabled 44.9 89.5 92.5 OpenBenchmarking.org Celsius, Fewer Is Better OSPRay Studio 0.11 CPU Temperature Monitor 20 40 60 80 100
Result
OpenBenchmarking.org ms, Fewer Is Better OSPRay Studio 0.11 Camera: 3 - Resolution: 4K - Samples Per Pixel: 1 - Renderer: Path Tracer Without AVX-512 Default, AVX-512 Enabled 1100 2200 3300 4400 5500 SE +/- 3.28, N = 3 SE +/- 5.55, N = 3 5348 4368 -mno-avx512f -mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mavx512ifma -mavx512vbmi 1. (CXX) g++ options: -O3 -march=native -ldl CPU Peak Freq (Highest CPU Core Frequency
Min Avg Max Without AVX-512 5117 5207 5881 Default, AVX-512 Enabled 5134 5227 5881 OpenBenchmarking.org Megahertz, More Is Better OSPRay Studio 0.11 CPU Peak Freq (Highest CPU Core Frequency) Monitor 1600 3200 4800 6400 8000 CPU Power Consumption
Min Avg Max Without AVX-512 22.8 197.3 224.0 Default, AVX-512 Enabled 22.9 198.4 217.9 OpenBenchmarking.org Watts, Fewer Is Better OSPRay Studio 0.11 CPU Power Consumption Monitor 60 120 180 240 300 CPU Temp
Min Avg Max Without AVX-512 47.6 91.8 94.5 Default, AVX-512 Enabled 47.0 89.7 92.5 OpenBenchmarking.org Celsius, Fewer Is Better OSPRay Studio 0.11 CPU Temperature Monitor 20 40 60 80 100
simdjson This is a benchmark of SIMDJSON, a high performance JSON parser. SIMDJSON aims to be the fastest JSON parser and is used by projects like Microsoft FishStore, Yandex ClickHouse, Shopify, and others. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org GB/s, More Is Better simdjson 2.0 Throughput Test: Kostya Without AVX-512 Default, AVX-512 Enabled 2 4 6 8 10 SE +/- 0.00, N = 3 SE +/- 0.04, N = 3 4.95 6.01 -mno-avx512f -mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mavx512ifma -mavx512vbmi 1. (CXX) g++ options: -O3 -march=native GB/s Per Watt
OpenBenchmarking.org GB/s Per Watt, More Is Better simdjson 2.0 Throughput Test: Kostya Without AVX-512 Default, AVX-512 Enabled 0.0212 0.0424 0.0636 0.0848 0.106 0.076 0.094 CPU Peak Freq (Highest CPU Core Frequency
OpenBenchmarking.org Megahertz, More Is Better simdjson 2.0 CPU Peak Freq (Highest CPU Core Frequency) Monitor Default, AVX-512 Enabled 1300 2600 3900 5200 6500 5881 CPU Power Consumption
Min Avg Max Without AVX-512 16.7 65.6 68.6 Default, AVX-512 Enabled 21.9 63.7 66.4 OpenBenchmarking.org Watts, Fewer Is Better simdjson 2.0 CPU Power Consumption Monitor 20 40 60 80 100 CPU Temp
Min Avg Max Without AVX-512 39.4 67.7 68.8 Default, AVX-512 Enabled 39.0 67.1 68.8 OpenBenchmarking.org Celsius, Fewer Is Better simdjson 2.0 CPU Temperature Monitor 20 40 60 80 100
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.
Result
OpenBenchmarking.org ms, Fewer Is Better OSPRay Studio 0.11 Camera: 1 - Resolution: 4K - Samples Per Pixel: 32 - Renderer: Path Tracer Without AVX-512 Default, AVX-512 Enabled 30K 60K 90K 120K 150K SE +/- 168.25, N = 3 SE +/- 140.99, N = 3 146156 120727 -mno-avx512f -mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mavx512ifma -mavx512vbmi 1. (CXX) g++ options: -O3 -march=native -ldl CPU Peak Freq (Highest CPU Core Frequency
Min Avg Max Without AVX-512 5106 5202 5881 Default, AVX-512 Enabled 5118 5229 5881 OpenBenchmarking.org Megahertz, More Is Better OSPRay Studio 0.11 CPU Peak Freq (Highest CPU Core Frequency) Monitor 1600 3200 4800 6400 8000 CPU Power Consumption
Min Avg Max Without AVX-512 16.1 199.9 221.5 Default, AVX-512 Enabled 14.7 198.1 226.1 OpenBenchmarking.org Watts, Fewer Is Better OSPRay Studio 0.11 CPU Power Consumption Monitor 60 120 180 240 300 CPU Temp
Min Avg Max Without AVX-512 48.1 92.3 95.3 Default, AVX-512 Enabled 46.6 90.0 93.5 OpenBenchmarking.org Celsius, Fewer Is Better OSPRay Studio 0.11 CPU Temperature Monitor 20 40 60 80 100
Embree Intel Embree is a collection of high-performance ray-tracing kernels for execution on CPUs and supporting instruction sets such as SSE, AVX, AVX2, and AVX-512. Embree also supports making use of the Intel SPMD Program Compiler (ISPC). Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Frames Per Second, More Is Better Embree 3.13 Binary: Pathtracer ISPC - Model: Crown Without AVX-512 Default, AVX-512 Enabled 8 16 24 32 40 SE +/- 0.11, N = 3 SE +/- 0.08, N = 3 29.12 35.23 MIN: 28.7 / MAX: 29.86 MIN: 34.75 / MAX: 36.08 Frames Per Second Per Watt
OpenBenchmarking.org Frames Per Second Per Watt, More Is Better Embree 3.13 Binary: Pathtracer ISPC - Model: Crown Without AVX-512 Default, AVX-512 Enabled 0.0423 0.0846 0.1269 0.1692 0.2115 0.153 0.188 CPU Peak Freq (Highest CPU Core Frequency
Min Avg Max Without AVX-512 5152 5300 5881 Default, AVX-512 Enabled 5146 5324 5881 OpenBenchmarking.org Megahertz, More Is Better Embree 3.13 CPU Peak Freq (Highest CPU Core Frequency) Monitor 1600 3200 4800 6400 8000 CPU Power Consumption
Min Avg Max Without AVX-512 23.3 190.5 227.8 Default, AVX-512 Enabled 22.6 187.3 235.9 OpenBenchmarking.org Watts, Fewer Is Better Embree 3.13 CPU Power Consumption Monitor 60 120 180 240 300 CPU Temp
Min Avg Max Without AVX-512 40.0 84.9 91.0 Default, AVX-512 Enabled 40.3 83.2 90.9 OpenBenchmarking.org Celsius, Fewer Is Better Embree 3.13 CPU Temperature Monitor 20 40 60 80 100
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.
Result
OpenBenchmarking.org ms, Fewer Is Better OSPRay Studio 0.11 Camera: 1 - Resolution: 4K - Samples Per Pixel: 16 - Renderer: Path Tracer Without AVX-512 Default, AVX-512 Enabled 16K 32K 48K 64K 80K SE +/- 91.34, N = 3 SE +/- 138.54, N = 3 74844 62029 -mno-avx512f -mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mavx512ifma -mavx512vbmi 1. (CXX) g++ options: -O3 -march=native -ldl CPU Peak Freq (Highest CPU Core Frequency
Min Avg Max Without AVX-512 5118 5254 5881 Default, AVX-512 Enabled 5142 5295 5881 OpenBenchmarking.org Megahertz, More Is Better OSPRay Studio 0.11 CPU Peak Freq (Highest CPU Core Frequency) Monitor 1600 3200 4800 6400 8000 CPU Power Consumption
Min Avg Max Without AVX-512 12.7 189.2 223.7 Default, AVX-512 Enabled 19.2 185.5 223.2 OpenBenchmarking.org Watts, Fewer Is Better OSPRay Studio 0.11 CPU Power Consumption Monitor 60 120 180 240 300 CPU Temp
Min Avg Max Without AVX-512 48.0 90.2 95.0 Default, AVX-512 Enabled 46.9 87.8 92.4 OpenBenchmarking.org Celsius, Fewer Is Better OSPRay Studio 0.11 CPU Temperature Monitor 20 40 60 80 100
Result
OpenBenchmarking.org ms, Fewer Is Better OSPRay Studio 0.11 Camera: 3 - Resolution: 4K - Samples Per Pixel: 32 - Renderer: Path Tracer Without AVX-512 Default, AVX-512 Enabled 40K 80K 120K 160K 200K SE +/- 155.59, N = 3 SE +/- 116.66, N = 3 172872 143981 -mno-avx512f -mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mavx512ifma -mavx512vbmi 1. (CXX) g++ options: -O3 -march=native -ldl CPU Peak Freq (Highest CPU Core Frequency
Min Avg Max Without AVX-512 5118 5194 5881 Default, AVX-512 Enabled 5131 5220 5881 OpenBenchmarking.org Megahertz, More Is Better OSPRay Studio 0.11 CPU Peak Freq (Highest CPU Core Frequency) Monitor 1600 3200 4800 6400 8000 CPU Power Consumption
Min Avg Max Without AVX-512 23.1 201.2 218.3 Default, AVX-512 Enabled 22.9 199.7 222.9 OpenBenchmarking.org Watts, Fewer Is Better OSPRay Studio 0.11 CPU Power Consumption Monitor 60 120 180 240 300 CPU Temp
Min Avg Max Without AVX-512 48.0 92.3 95.1 Default, AVX-512 Enabled 47.4 90.0 93.4 OpenBenchmarking.org Celsius, Fewer Is Better OSPRay Studio 0.11 CPU Temperature Monitor 20 40 60 80 100
Result
OpenBenchmarking.org ms, Fewer Is Better OSPRay Studio 0.11 Camera: 3 - Resolution: 4K - Samples Per Pixel: 16 - Renderer: Path Tracer Without AVX-512 Default, AVX-512 Enabled 20K 40K 60K 80K 100K SE +/- 7.57, N = 3 SE +/- 149.41, N = 3 88344 73617 -mno-avx512f -mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mavx512ifma -mavx512vbmi 1. (CXX) g++ options: -O3 -march=native -ldl CPU Peak Freq (Highest CPU Core Frequency
Min Avg Max Without AVX-512 5122 5240 5881 Default, AVX-512 Enabled 5128 5264 5881 OpenBenchmarking.org Megahertz, More Is Better OSPRay Studio 0.11 CPU Peak Freq (Highest CPU Core Frequency) Monitor 1600 3200 4800 6400 8000 CPU Power Consumption
Min Avg Max Without AVX-512 23.0 192.2 220.6 Default, AVX-512 Enabled 22.9 188.7 219.2 OpenBenchmarking.org Watts, Fewer Is Better OSPRay Studio 0.11 CPU Power Consumption Monitor 60 120 180 240 300 CPU Temp
Min Avg Max Without AVX-512 48.3 90.4 94.5 Default, AVX-512 Enabled 47.5 88.3 93.0 OpenBenchmarking.org Celsius, Fewer Is Better OSPRay Studio 0.11 CPU Temperature Monitor 20 40 60 80 100
Embree Intel Embree is a collection of high-performance ray-tracing kernels for execution on CPUs and supporting instruction sets such as SSE, AVX, AVX2, and AVX-512. Embree also supports making use of the Intel SPMD Program Compiler (ISPC). Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Frames Per Second, More Is Better Embree 3.13 Binary: Pathtracer ISPC - Model: Asian Dragon Without AVX-512 Default, AVX-512 Enabled 8 16 24 32 40 SE +/- 0.16, N = 3 SE +/- 0.08, N = 3 30.39 35.12 MIN: 29.85 / MAX: 30.94 MIN: 34.64 / MAX: 36.13 Frames Per Second Per Watt
OpenBenchmarking.org Frames Per Second Per Watt, More Is Better Embree 3.13 Binary: Pathtracer ISPC - Model: Asian Dragon Without AVX-512 Default, AVX-512 Enabled 0.0477 0.0954 0.1431 0.1908 0.2385 0.171 0.212 CPU Peak Freq (Highest CPU Core Frequency
Min Avg Max Without AVX-512 5197 5354 5881 Default, AVX-512 Enabled 5222 5375 5881 OpenBenchmarking.org Megahertz, More Is Better Embree 3.13 CPU Peak Freq (Highest CPU Core Frequency) Monitor 1600 3200 4800 6400 8000 CPU Power Consumption
Min Avg Max Without AVX-512 24.3 177.3 210.0 Default, AVX-512 Enabled 22.6 166.0 203.7 OpenBenchmarking.org Watts, Fewer Is Better Embree 3.13 CPU Power Consumption Monitor 60 120 180 240 300 CPU Temp
Min Avg Max Without AVX-512 44.6 81.0 85.9 Default, AVX-512 Enabled 44.1 75.1 80.8 OpenBenchmarking.org Celsius, Fewer Is Better Embree 3.13 CPU Temperature Monitor 20 40 60 80 100
simdjson This is a benchmark of SIMDJSON, a high performance JSON parser. SIMDJSON aims to be the fastest JSON parser and is used by projects like Microsoft FishStore, Yandex ClickHouse, Shopify, and others. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org GB/s, More Is Better simdjson 2.0 Throughput Test: LargeRandom Without AVX-512 Default, AVX-512 Enabled 0.4028 0.8056 1.2084 1.6112 2.014 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 1.57 1.79 -mno-avx512f -mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mavx512ifma -mavx512vbmi 1. (CXX) g++ options: -O3 -march=native GB/s Per Watt
OpenBenchmarking.org GB/s Per Watt, More Is Better simdjson 2.0 Throughput Test: LargeRandom Without AVX-512 Default, AVX-512 Enabled 0.0065 0.013 0.0195 0.026 0.0325 0.025 0.029 CPU Peak Freq (Highest CPU Core Frequency
OpenBenchmarking.org Megahertz, More Is Better simdjson 2.0 CPU Peak Freq (Highest CPU Core Frequency) Monitor Default, AVX-512 Enabled 1300 2600 3900 5200 6500 5881 CPU Power Consumption
Min Avg Max Without AVX-512 22.9 62.6 65.3 Default, AVX-512 Enabled 22.2 62.7 65.8 OpenBenchmarking.org Watts, Fewer Is Better simdjson 2.0 CPU Power Consumption Monitor 20 40 60 80 100 CPU Temp
Min Avg Max Without AVX-512 38.9 68.8 69.9 Default, AVX-512 Enabled 38.5 66.6 68.0 OpenBenchmarking.org Celsius, Fewer Is Better simdjson 2.0 CPU Temperature Monitor 20 40 60 80 100
Mobile Neural Network MNN is the Mobile Neural Network as a highly efficient, lightweight deep learning framework developed by Alibaba. This MNN test profile is building the OpenMP / CPU threaded version for processor benchmarking and not any GPU-accelerated test. MNN does allow making use of AVX-512 extensions. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 2.1 Model: SqueezeNetV1.0 Without AVX-512 Default, AVX-512 Enabled 0.8993 1.7986 2.6979 3.5972 4.4965 SE +/- 0.121, N = 3 SE +/- 0.015, N = 6 3.997 3.543 -mno-avx512f - MIN: 3.72 / MAX: 5.69 -mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mavx512ifma -mavx512vbmi - MIN: 3.43 / MAX: 10.23 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl
LeelaChessZero LeelaChessZero (lc0 / lczero) is a chess engine automated vian neural networks. This test profile can be used for OpenCL, CUDA + cuDNN, and BLAS (CPU-based) benchmarking. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Nodes Per Second, More Is Better LeelaChessZero 0.28 Backend: Eigen Without AVX-512 Default, AVX-512 Enabled 400 800 1200 1600 2000 SE +/- 16.33, N = 3 SE +/- 7.31, N = 3 1578 1735 -mno-avx512f -mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mavx512ifma -mavx512vbmi 1. (CXX) g++ options: -flto -O3 -march=native -pthread Nodes Per Second Per Watt
OpenBenchmarking.org Nodes Per Second Per Watt, More Is Better LeelaChessZero 0.28 Backend: Eigen Without AVX-512 Default, AVX-512 Enabled 3 6 9 12 15 9.107 10.156 CPU Peak Freq (Highest CPU Core Frequency
Min Avg Max Without AVX-512 5152 5307 5881 Default, AVX-512 Enabled 5191 5321 5881 OpenBenchmarking.org Megahertz, More Is Better LeelaChessZero 0.28 CPU Peak Freq (Highest CPU Core Frequency) Monitor 1600 3200 4800 6400 8000 CPU Power Consumption
Min Avg Max Without AVX-512 23.3 173.3 195.1 Default, AVX-512 Enabled 22.5 170.8 192.1 OpenBenchmarking.org Watts, Fewer Is Better LeelaChessZero 0.28 CPU Power Consumption Monitor 50 100 150 200 250 CPU Temp
Min Avg Max Without AVX-512 36.1 88.3 91.0 Default, AVX-512 Enabled 33.6 84.4 87.4 OpenBenchmarking.org Celsius, Fewer Is Better LeelaChessZero 0.28 CPU Temperature Monitor 20 40 60 80 100
OSPRay Intel OSPRay is a portable ray-tracing engine for high-performance, high-fidelity scientific 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.
Result
OpenBenchmarking.org Items Per Second, More Is Better OSPRay 2.10 Benchmark: particle_volume/pathtracer/real_time Without AVX-512 Default, AVX-512 Enabled 50 100 150 200 250 SE +/- 0.59, N = 3 SE +/- 0.91, N = 3 231.38 250.66 Items Per Second Per Watt
OpenBenchmarking.org Items Per Second Per Watt, More Is Better OSPRay 2.10 Benchmark: particle_volume/pathtracer/real_time Without AVX-512 Default, AVX-512 Enabled 0.3137 0.6274 0.9411 1.2548 1.5685 1.237 1.394 CPU Peak Freq (Highest CPU Core Frequency
Min Avg Max Without AVX-512 5070 5185 5881 Default, AVX-512 Enabled 5127 5270 5881 OpenBenchmarking.org Megahertz, More Is Better OSPRay 2.10 CPU Peak Freq (Highest CPU Core Frequency) Monitor 1600 3200 4800 6400 8000 CPU Power Consumption
Min Avg Max Without AVX-512 22.9 187.0 222.6 Default, AVX-512 Enabled 22.4 179.8 215.5 OpenBenchmarking.org Watts, Fewer Is Better OSPRay 2.10 CPU Power Consumption Monitor 60 120 180 240 300 CPU Temp
Min Avg Max Without AVX-512 45.0 90.8 95.8 Default, AVX-512 Enabled 43.1 86.3 93.0 OpenBenchmarking.org Celsius, Fewer Is Better OSPRay 2.10 CPU Temperature Monitor 20 40 60 80 100
dav1d Dav1d is an open-source, speedy AV1 video decoder. This test profile times how long it takes to decode sample AV1 video content. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org FPS, More Is Better dav1d 1.0 Video Input: Summer Nature 4K Without AVX-512 Default, AVX-512 Enabled 90 180 270 360 450 SE +/- 3.22, N = 5 SE +/- 1.37, N = 5 380.32 393.40 -mno-avx512f -mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mavx512ifma -mavx512vbmi -lm 1. (CC) gcc options: -O3 -march=native -pthread FPS Per Watt
OpenBenchmarking.org FPS Per Watt, More Is Better dav1d 1.0 Video Input: Summer Nature 4K Without AVX-512 Default, AVX-512 Enabled 0.7018 1.4036 2.1054 2.8072 3.509 2.937 3.119 CPU Peak Freq (Highest CPU Core Frequency
Min Avg Max Without AVX-512 5258 5492 5881 Default, AVX-512 Enabled 5239 5493 5881 OpenBenchmarking.org Megahertz, More Is Better dav1d 1.0 CPU Peak Freq (Highest CPU Core Frequency) Monitor 1600 3200 4800 6400 8000 CPU Power Consumption
Min Avg Max Without AVX-512 23.9 129.5 187.9 Default, AVX-512 Enabled 23.2 126.1 185.4 OpenBenchmarking.org Watts, Fewer Is Better dav1d 1.0 CPU Power Consumption Monitor 50 100 150 200 250 CPU Temp
Min Avg Max Without AVX-512 38.8 70.9 80.3 Default, AVX-512 Enabled 38.6 70.0 79.0 OpenBenchmarking.org Celsius, Fewer Is Better dav1d 1.0 CPU Temperature Monitor 20 40 60 80 100
Result
OpenBenchmarking.org FPS, More Is Better dav1d 1.0 Video Input: Summer Nature 1080p Without AVX-512 Default, AVX-512 Enabled 300 600 900 1200 1500 SE +/- 2.53, N = 10 SE +/- 1.72, N = 10 1412.27 1451.94 -mno-avx512f -mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mavx512ifma -mavx512vbmi -lm 1. (CC) gcc options: -O3 -march=native -pthread FPS Per Watt
OpenBenchmarking.org FPS Per Watt, More Is Better dav1d 1.0 Video Input: Summer Nature 1080p Without AVX-512 Default, AVX-512 Enabled 4 8 12 16 20 17.21 18.11 CPU Peak Freq (Highest CPU Core Frequency
Min Avg Max Without AVX-512 5263 5686 5881 Default, AVX-512 Enabled 5282 5674 5881 OpenBenchmarking.org Megahertz, More Is Better dav1d 1.0 CPU Peak Freq (Highest CPU Core Frequency) Monitor 1600 3200 4800 6400 8000 CPU Power Consumption
Min Avg Max Without AVX-512 23.6 82.1 180.6 Default, AVX-512 Enabled 23.2 80.2 178.7 OpenBenchmarking.org Watts, Fewer Is Better dav1d 1.0 CPU Power Consumption Monitor 50 100 150 200 250 CPU Temp
Min Avg Max Without AVX-512 41.3 65.1 74.4 Default, AVX-512 Enabled 41.3 64.5 73.3 OpenBenchmarking.org Celsius, Fewer Is Better dav1d 1.0 CPU Temperature Monitor 20 40 60 80 100
CPU Temperature Monitor OpenBenchmarking.org Celsius CPU Temperature Monitor Phoronix Test Suite System Monitoring Without AVX-512 Default, AVX-512 Enabled 20 40 60 80 100 Min: 36.13 / Avg: 84.12 / Max: 96.75 Min: 33.63 / Avg: 81.24 / Max: 96.25
CPU Power Consumption Monitor OpenBenchmarking.org Watts CPU Power Consumption Monitor Phoronix Test Suite System Monitoring Without AVX-512 Default, AVX-512 Enabled 40 80 120 160 200 Min: 10.2 / Avg: 161.11 / Max: 235.88 Min: 11.53 / Avg: 158.06 / Max: 237.76
CPU Peak Freq (Highest CPU Core Frequency) Monitor OpenBenchmarking.org Megahertz CPU Peak Freq (Highest CPU Core Frequency) Monitor Phoronix Test Suite System Monitoring Without AVX-512 Default, AVX-512 Enabled 1000 2000 3000 4000 5000 Min: 4495 / Avg: 5334.93 / Max: 5881 Min: 4421 / Avg: 5372.19 / Max: 5881
Cpuminer-Opt Min Avg Max Without AVX-512 44.3 75.9 79.9 Default, AVX-512 Enabled 40.8 72.9 76.3 OpenBenchmarking.org Celsius, Fewer Is Better Cpuminer-Opt 3.18 CPU Temperature Monitor 20 40 60 80 100
Min Avg Max Without AVX-512 23.1 168.2 190.7 Default, AVX-512 Enabled 22.9 161.5 185.7 OpenBenchmarking.org Watts, Fewer Is Better Cpuminer-Opt 3.18 CPU Power Consumption Monitor 50 100 150 200 250
Min Avg Max Without AVX-512 5244 5339 5881 Default, AVX-512 Enabled 5283 5374 5881 OpenBenchmarking.org Megahertz, More Is Better Cpuminer-Opt 3.18 CPU Peak Freq (Highest CPU Core Frequency) Monitor 1600 3200 4800 6400 8000
OpenBenchmarking.org kH/s Per Watt, More Is Better Cpuminer-Opt 3.18 Algorithm: Garlicoin Without AVX-512 Default, AVX-512 Enabled 6 12 18 24 30 15.45 24.63
Result
OpenBenchmarking.org kH/s, More Is Better Cpuminer-Opt 3.18 Algorithm: Garlicoin Without AVX-512 Default, AVX-512 Enabled 900 1800 2700 3600 4500 SE +/- 25.96, N = 3 SE +/- 75.31, N = 12 2597.65 3977.80 -mno-avx512f -mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mavx512ifma -mavx512vbmi 1. (CXX) g++ options: -O3 -march=native -lcurl -lz -lpthread -lssl -lcrypto -lgmp kH/s Per Watt
OpenBenchmarking.org kH/s Per Watt, More Is Better Cpuminer-Opt 3.18 Algorithm: Garlicoin Without AVX-512 Default, AVX-512 Enabled 6 12 18 24 30 15.45 24.63 CPU Peak Freq (Highest CPU Core Frequency
Min Avg Max Without AVX-512 5244 5339 5881 Default, AVX-512 Enabled 5283 5374 5881 OpenBenchmarking.org Megahertz, More Is Better Cpuminer-Opt 3.18 CPU Peak Freq (Highest CPU Core Frequency) Monitor 1600 3200 4800 6400 8000 CPU Power Consumption
Min Avg Max Without AVX-512 23.1 168.2 190.7 Default, AVX-512 Enabled 22.9 161.5 185.7 OpenBenchmarking.org Watts, Fewer Is Better Cpuminer-Opt 3.18 CPU Power Consumption Monitor 50 100 150 200 250 CPU Temp
Min Avg Max Without AVX-512 44.3 75.9 79.9 Default, AVX-512 Enabled 40.8 72.9 76.3 OpenBenchmarking.org Celsius, Fewer Is Better Cpuminer-Opt 3.18 CPU Temperature Monitor 20 40 60 80 100
Min Avg Max Without AVX-512 48.6 69.2 85.9 Default, AVX-512 Enabled 47.1 66.4 79.6 OpenBenchmarking.org Celsius, Fewer Is Better Cpuminer-Opt 3.18 CPU Temperature Monitor 20 40 60 80 100
Min Avg Max Without AVX-512 21.0 105.5 175.6 Default, AVX-512 Enabled 19.2 107.8 200.8 OpenBenchmarking.org Watts, Fewer Is Better Cpuminer-Opt 3.18 CPU Power Consumption Monitor 50 100 150 200 250
Min Avg Max Without AVX-512 5204 5521 5881 Default, AVX-512 Enabled 5260 5542 5881 OpenBenchmarking.org Megahertz, More Is Better Cpuminer-Opt 3.18 CPU Peak Freq (Highest CPU Core Frequency) Monitor 1600 3200 4800 6400 8000
OpenBenchmarking.org kH/s Per Watt, More Is Better Cpuminer-Opt 3.18 Algorithm: Blake-2 S Without AVX-512 Default, AVX-512 Enabled 4K 8K 12K 16K 20K 9800.37 19614.14
Result
OpenBenchmarking.org kH/s, More Is Better Cpuminer-Opt 3.18 Algorithm: Blake-2 S Without AVX-512 Default, AVX-512 Enabled 500K 1000K 1500K 2000K 2500K SE +/- 4192.40, N = 3 SE +/- 38034.65, N = 12 1033700 2113434 -mno-avx512f -mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mavx512ifma -mavx512vbmi 1. (CXX) g++ options: -O3 -march=native -lcurl -lz -lpthread -lssl -lcrypto -lgmp kH/s Per Watt
OpenBenchmarking.org kH/s Per Watt, More Is Better Cpuminer-Opt 3.18 Algorithm: Blake-2 S Without AVX-512 Default, AVX-512 Enabled 4K 8K 12K 16K 20K 9800.37 19614.14 CPU Peak Freq (Highest CPU Core Frequency
Min Avg Max Without AVX-512 5204 5521 5881 Default, AVX-512 Enabled 5260 5542 5881 OpenBenchmarking.org Megahertz, More Is Better Cpuminer-Opt 3.18 CPU Peak Freq (Highest CPU Core Frequency) Monitor 1600 3200 4800 6400 8000 CPU Power Consumption
Min Avg Max Without AVX-512 21.0 105.5 175.6 Default, AVX-512 Enabled 19.2 107.8 200.8 OpenBenchmarking.org Watts, Fewer Is Better Cpuminer-Opt 3.18 CPU Power Consumption Monitor 50 100 150 200 250 CPU Temp
Min Avg Max Without AVX-512 48.6 69.2 85.9 Default, AVX-512 Enabled 47.1 66.4 79.6 OpenBenchmarking.org Celsius, Fewer Is Better Cpuminer-Opt 3.18 CPU Temperature Monitor 20 40 60 80 100
oneDNN Min Avg Max Without AVX-512 48.1 80.2 93.6 Default, AVX-512 Enabled 48.4 70.8 87.5 OpenBenchmarking.org Celsius, Fewer Is Better oneDNN 2.6 CPU Temperature Monitor 20 40 60 80 100
Min Avg Max Without AVX-512 23.9 140.4 221.2 Default, AVX-512 Enabled 20.1 124.9 214.3 OpenBenchmarking.org Watts, Fewer Is Better oneDNN 2.6 CPU Power Consumption Monitor 60 120 180 240 300
Min Avg Max Without AVX-512 5125 5367 5881 Default, AVX-512 Enabled 5127 5419 5881 OpenBenchmarking.org Megahertz, More Is Better oneDNN 2.6 CPU Peak Freq (Highest CPU Core Frequency) Monitor 1600 3200 4800 6400 8000
Result
OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.6 Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPU Without AVX-512 Default, AVX-512 Enabled 0.1408 0.2816 0.4224 0.5632 0.704 SE +/- 0.006181, N = 5 SE +/- 0.007969, N = 15 0.625942 0.417196 -mno-avx512f - MIN: 0.58 -mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mavx512ifma -mavx512vbmi - MIN: 0.34 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl -lpthread CPU Peak Freq (Highest CPU Core Frequency
Min Avg Max Without AVX-512 5125 5367 5881 Default, AVX-512 Enabled 5127 5419 5881 OpenBenchmarking.org Megahertz, More Is Better oneDNN 2.6 CPU Peak Freq (Highest CPU Core Frequency) Monitor 1600 3200 4800 6400 8000 CPU Power Consumption
Min Avg Max Without AVX-512 23.9 140.4 221.2 Default, AVX-512 Enabled 20.1 124.9 214.3 OpenBenchmarking.org Watts, Fewer Is Better oneDNN 2.6 CPU Power Consumption Monitor 60 120 180 240 300 CPU Temp
Min Avg Max Without AVX-512 48.1 80.2 93.6 Default, AVX-512 Enabled 48.4 70.8 87.5 OpenBenchmarking.org Celsius, Fewer Is Better oneDNN 2.6 CPU Temperature Monitor 20 40 60 80 100
Without AVX-512 Kernel Notes: Transparent Huge Pages: madviseEnvironment Notes: CXXFLAGS="-O3 -march=native -mno-avx512f" CFLAGS="-O3 -march=native -mno-avx512f"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-OcsLtf/gcc-12-12-20220319/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-12-OcsLtf/gcc-12-12-20220319/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 -vProcessor Notes: Scaling Governor: amd-pstate performance (Boost: Enabled) - CPU Microcode: 0xa601203Python Notes: Python 3.10.4Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected
Testing initiated at 17 September 2022 15:47 by user phoronix.
Default, AVX-512 Enabled Processor: AMD Ryzen 9 7950X 16-Core @ 5.88GHz (16 Cores / 32 Threads), Motherboard: ASUS ROG CROSSHAIR X670E HERO (0604 BIOS), Chipset: AMD Device 14d8, Memory: 32GB, Disk: 2000GB Samsung SSD 980 PRO 2TB + 2000GB, Graphics: AMD Radeon RX 6800 XT 16GB (2575/1000MHz), Audio: AMD Navi 21 HDMI Audio, Monitor: ASUS VP28U, Network: Intel I225-V + Intel Wi-Fi 6 AX210/AX211/AX411
OS: Ubuntu 22.04, Kernel: 6.0.0-060000rc1daily20220820-generic (x86_64), Desktop: GNOME Shell 42.2, Display Server: X Server + Wayland, OpenGL: 4.6 Mesa 22.3.0-devel (git-4685385 2022-08-23 jammy-oibaf-ppa) (LLVM 14.0.6 DRM 3.48), Vulkan: 1.3.224, Compiler: GCC 12.0.1 20220319, File-System: ext4, Screen Resolution: 3840x2160
Kernel Notes: Transparent Huge Pages: madviseEnvironment Notes: CXXFLAGS="-O3 -march=native -mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mavx512ifma -mavx512vbmi -mprefer-vector-width=512" CFLAGS="-O3 -march=native -mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mavx512ifma -mavx512vbmi -mprefer-vector-width=512"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-OcsLtf/gcc-12-12-20220319/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-12-OcsLtf/gcc-12-12-20220319/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 -vProcessor Notes: Scaling Governor: amd-pstate performance (Boost: Enabled) - CPU Microcode: 0xa601203Python Notes: Python 3.10.4Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected
Testing initiated at 17 September 2022 20:32 by user phoronix.