june AMD Ryzen 9 3900XT 12-Core testing with a MSI MEG X570 GODLIKE (MS-7C34) v1.0 (1.B3 BIOS) and AMD Radeon RX 56/64 8GB on Ubuntu 22.04 via the Phoronix Test Suite.
HTML result view exported from: https://openbenchmarking.org/result/2206054-PTS-JUNE759444&sor&grs .
june Processor Motherboard Chipset Memory Disk Graphics Audio Monitor Network OS Kernel Desktop Display Server OpenGL Vulkan Compiler File-System Screen Resolution A B C D AMD Ryzen 9 3900XT 12-Core @ 3.80GHz (12 Cores / 24 Threads) MSI MEG X570 GODLIKE (MS-7C34) v1.0 (1.B3 BIOS) AMD Starship/Matisse 16GB 500GB Seagate FireCuda 520 SSD ZP500GM30002 AMD Radeon RX 56/64 8GB (1630/945MHz) AMD Vega 10 HDMI Audio ASUS MG28U Realtek Device 2600 + Realtek Killer E3000 2.5GbE + Intel Wi-Fi 6 AX200 Ubuntu 22.04 5.15.0-22-generic (x86_64) GNOME Shell 41.3 X Server + Wayland 4.6 Mesa 21.3.5 (LLVM 12.0.1) 1.2.195 GCC 11.2.0 ext4 3840x2160 4.6 Mesa 22.0.1 (LLVM 13.0.1 DRM 3.42) 1.3.204 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-XWYfV6/gcc-11-11.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-XWYfV6/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 - D: --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 - Scaling Governor: acpi-cpufreq schedutil (Boost: Enabled) - CPU Microcode: 0x8701021 Graphics Details - BAR1 / Visible vRAM Size: 256 MB - vBIOS Version: 113-D0500100-102 Java Details - OpenJDK Runtime Environment (build 11.0.15+10-Ubuntu-0ubuntu0.22.04.1) Python Details - A: Python 3.10.2 - B: Python 3.10.4 - C: Python 3.10.4 - D: 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 Full AMD retpoline IBPB: conditional STIBP: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected
june onednn: Recurrent Neural Network Training - bf16bf16bf16 - CPU onednn: Recurrent Neural Network Training - u8s8f32 - CPU tensorflow-lite: SqueezeNet onednn: Recurrent Neural Network Training - f32 - CPU onednn: IP Shapes 3D - f32 - CPU tensorflow-lite: Inception V4 tensorflow-lite: Inception ResNet V2 onednn: Deconvolution Batch shapes_3d - f32 - CPU onednn: IP Shapes 3D - u8s8f32 - CPU onednn: IP Shapes 1D - u8s8f32 - CPU onednn: Deconvolution Batch shapes_3d - u8s8f32 - CPU onednn: Matrix Multiply Batch Shapes Transformer - f32 - CPU onednn: Deconvolution Batch shapes_1d - u8s8f32 - CPU onednn: Matrix Multiply Batch Shapes Transformer - u8s8f32 - CPU onednn: Deconvolution Batch shapes_1d - f32 - CPU onednn: IP Shapes 1D - f32 - CPU tensorflow-lite: NASNet Mobile tensorflow-lite: Mobilenet Quant onednn: Recurrent Neural Network Inference - u8s8f32 - CPU onednn: Recurrent Neural Network Inference - bf16bf16bf16 - CPU tensorflow-lite: Mobilenet Float onednn: Recurrent Neural Network Inference - f32 - CPU onednn: Convolution Batch Shapes Auto - u8s8f32 - CPU onednn: Convolution Batch Shapes Auto - f32 - CPU stress-ng: NUMA onnx: fcn-resnet101-11 - CPU - Standard onnx: ArcFace ResNet-100 - CPU - Standard onnx: yolov4 - CPU - Standard stress-ng: SENDFILE perf-bench: Futex Lock-Pi svt-hevc: 7 - Bosphorus 4K svt-av1: Preset 8 - Bosphorus 4K renaissance: Scala Dotty onnx: fcn-resnet101-11 - CPU - Parallel onnx: GPT-2 - CPU - Standard influxdb: 4 - 10000 - 2,5000,1 - 10000 perf-bench: Memcpy 1MB nettle: chacha glibc-bench: log2 gromacs: MPI CPU - water_GMX50_bare svt-av1: Preset 10 - Bosphorus 4K glibc-bench: sincos svt-vp9: Visual Quality Optimized - Bosphorus 4K glibc-bench: ffsll renaissance: Genetic Algorithm Using Jenetics + Futures perf-bench: Syscall Basic glibc-bench: sinh stress-ng: Futex glibc-bench: modf renaissance: Finagle HTTP Requests glibc-bench: sqrt nettle: aes256 glibc-bench: sin glibc-bench: asinh glibc-bench: tanh glibc-bench: cos perf-bench: Sched Pipe renaissance: Savina Reactors.IO glibc-bench: ffs svt-vp9: Visual Quality Optimized - Bosphorus 1080p perf-bench: Memset 1MB stress-ng: Context Switching glibc-bench: atanh perf-bench: Epoll Wait svt-vp9: PSNR/SSIM Optimized - Bosphorus 4K etcpak: Single-Threaded - ETC2 avifenc: 2 avifenc: 10, Lossless avifenc: 6, Lossless avifenc: 6 onnx: GPT-2 - CPU - Parallel svt-av1: Preset 12 - Bosphorus 1080p renaissance: In-Memory Database Shootout svt-hevc: 1 - Bosphorus 1080p svt-hevc: 10 - Bosphorus 4K stress-ng: Malloc svt-hevc: 10 - Bosphorus 1080p onnx: yolov4 - CPU - Parallel etcpak: Single-Threaded - DXT1 svt-hevc: 7 - Bosphorus 1080p svt-hevc: 1 - Bosphorus 4K webp2: Quality 95, Compression Effort 7 stress-ng: Glibc C String Functions stress-ng: Matrix Math stress-ng: Glibc Qsort Data Sorting perf-bench: Futex Hash java-jmh: Throughput stress-ng: Vector Math avifenc: 0 simdjson: PartialTweets stress-ng: CPU Cache onnx: bertsquad-12 - CPU - Parallel onnx: bertsquad-12 - CPU - Standard svt-vp9: PSNR/SSIM Optimized - Bosphorus 1080p onnx: super-resolution-10 - CPU - Standard stress-ng: Crypto svt-av1: Preset 10 - Bosphorus 1080p onnx: ArcFace ResNet-100 - CPU - Parallel influxdb: 1024 - 10000 - 2,5000,1 - 10000 renaissance: Rand Forest stress-ng: Memory Copying onnx: super-resolution-10 - CPU - Parallel svt-av1: Preset 12 - Bosphorus 4K stress-ng: Forking stress-ng: Socket Activity webp2: Default simdjson: LargeRand svt-av1: Preset 4 - Bosphorus 4K influxdb: 64 - 10000 - 2,5000,1 - 10000 webp2: Quality 75, Compression Effort 7 simdjson: DistinctUserID stress-ng: CPU Stress nettle: sha512 glibc-bench: pthread_once svt-av1: Preset 4 - Bosphorus 1080p webp2: Quality 100, Compression Effort 5 etcpak: Multi-Threaded - DXT1 svt-vp9: VMAF Optimized - Bosphorus 1080p simdjson: Kostya etcpak: Multi-Threaded - ETC2 webp2: Quality 100, Lossless Compression stress-ng: System V Message Passing x264: Bosphorus 1080p stress-ng: MEMFD renaissance: Apache Spark ALS stress-ng: IO_uring x264: Bosphorus 4K renaissance: Apache Spark Bayes svt-av1: Preset 8 - Bosphorus 1080p renaissance: Apache Spark PageRank glibc-bench: exp simdjson: TopTweet renaissance: Akka Unbalanced Cobwebbed Tree svt-vp9: VMAF Optimized - Bosphorus 4K stress-ng: MMAP gravitymark: 2560 x 1440 - OpenGL renaissance: ALS Movie Lens gravitymark: 3840 x 2160 - Vulkan gravitymark: 1920 x 1080 - OpenGL gravitymark: 3840 x 2160 - OpenGL nettle: poly1305-aes stress-ng: Atomic gravitymark: 2560 x 1440 - Vulkan gravitymark: 1920 x 1080 - Vulkan stress-ng: Semaphores onednn: IP Shapes 1D - bf16bf16bf16 - CPU A B C D 35077.9 33601.7 206917 32226.3 73.3569 2445920 2330410 23.2198 36.7089 59.1302 12.031 30.0269 47.9482 36.1728 92.1343 73.1795 2271630 44820.6 30995.1 28223.8 240371 25968.5 41.1929 36.9585 211.02 59 1119 365 219949.89 542 42.2 30.777 778.7 60 5775 909621 14.624821 1068.17 21.5269 1.047 72.339 45.9757 45.49 7.04916 2666.5 17962305 26.9821 2786611.95 7.09614 3814.1 7.86042 6059.02 65.3259 30.644 38.3749 73.9182 326839 8321.1 6.09947 168 69.022774 4520622.35 38.3398 42469 43.96 232.166 66.028 5.95 11.431 8.089 4580 352.206 3614.9 11 75.56 16082432.37 274.85 244 236.904 151.75 2.82 323.97 1991624.53 58365.05 188.3 4693851 23214280399.043 86846.17 134.16 3.83 156.96 432 547 180 4435 21561.58 223.218 1117 1293571.6 743.4 4844.13 4541 95.65 52768.88 9558.26 2.972 1.01 2.467 1236274.6 151.784 4.59 29249.94 637.04 6.23097 6.229 4.242 3072.047 179.51 2.93 3061.536 742.934 7796050.7 137.76 850.42 3211.3 35619.31 35.58 2126.2 116.763 3174.2 16.1858 4.68 12754.4 44.54 296.27 91.1 12757.9 65 107.2 65.7 3216.07 576128.96 90.6 105.3 2483545.87 4105.68 4101.51 2898.87 4089.48 11.9803 42001 42072.8 5.25702 0.933945 1.80376 3.40615 1.24528 2.44129 1.85271 5.65439 4.70466 15355.6 3096.7 2496.51 2483.66 2411.06 2485.34 24.9072 22.587 328.2 78 1660 323 216302.59 669 50.39 36.48 833.9 68 6058 852735.1 16.239476 1185.58 19.4563 1.138 76.445 41.7435 49.51 6.46721 2888.2 19410883 24.8246 2871422.77 6.53862 3571.9 7.27802 6131.07 62.1677 31.7456 35.6057 68.5977 340408 7969.9 5.68026 176.38 72.014007 4833096.84 37.458 45429 46.88 246.144 62.502 5.648 10.878 7.654 4858 350.931 3646.0 11.63 78.87 16996416.51 290.42 256 237.857 159.49 2.95 309.655 2026796.06 60985 196.5 4904887 24255951266.374 90749.35 129.526 3.99 152.09 449 571 187.87 4324 22488.17 232.831 1165 1291849.9 721.2 5038.57 4619 98.212 54543.49 9191.93 2.886 1.04 2.563 1240324.6 146.316 4.72 30044.54 658.67 6.05998 6.44 4.11 3156.579 184.6 2.92 3146.367 721.681 8003229.07 141.25 871.88 3133.9 34951.82 35.64 2104.4 117.447 3153.2 16.4404 4.61 12943.4 45.21 300.58 90.4 12616.7 64.5 106.5 65.3 3212.21 577614.81 90.4 105.3 2481083.26 4117.24 4092.33 2894.31 4133.63 11.9752 42840.4 42165.8 5.26468 0.930888 1.79634 3.38355 1.16856 2.44352 2.2579 8.239 4.7102 15359.5 3146.6 2485.86 2492.88 2435.6 2458.19 24.9595 22.5856 326.62 60 1183 337 246261.31 663 50.44 36.35 729.0 68 6445 847482 14.765638 1151.97 20.7323 1.14 78.409 41.7416 49.84 6.93142 2871.2 17850063 26.847 2787436.17 6.71077 3529.2 7.46367 6541.11 64.7313 29.4417 38.0593 70.3809 351971 7858.7 6.08636 176.32 73.955339 4842631.56 35.8417 45264 46.52 246.805 63.47 5.601 10.764 7.718 4859 351.994 3824.8 11.63 79.86 16871709.82 287.22 257 249.284 158.6 2.96 308.71 2080090.43 61156.12 197.1 4910773 24266478961.702 90779.38 128.777 4 158.82 449 567 187.19 4511 22493.23 230.171 1163 1291195 730.9 5039.59 4586 98.216 54932.41 9185.34 3.003 1.04 2.556 1237035.8 148.841 4.55 29333.09 637.71 6.02658 6.435 4.14 3169.25 183.53 2.89 3144.303 722.894 7995516.42 140.99 869.61 3137.4 34815.95 35.36 2149.7 117.33 3116.0 16.1542 4.61 12759.6 45.12 300.57 91.7 12677.3 64.4 106.5 65.2 3217.7 580078.48 90.5 105.6 2485080.45 4100.65 4110.74 2888.78 4126.65 11.3832 42166.7 41956.7 5.27803 0.92482 1.81319 3.40609 1.29107 2.43 1.99646 7.65826 4.70911 15326 3113.9 2495.97 2473.22 2401.33 2458.93 24.8524 22.5007 331.54 88 1154 453 192604.94 649 50.62 36.587 818.3 68 5962 816036 14.845633 1095 19.5047 1.155 79.787 42.8935 49.86 6.46463 2903.9 19384879 26.9788 3025044.82 6.54065 3587.1 7.28112 6515.5 60.5126 29.4292 38.3276 68.63 344956 8459.7 5.69216 180.36 72.413917 4808874.54 35.869 45400 46.83 247.108 62.152 5.644 10.981 7.619 4795 372.283 3732.7 11.61 79.6 16827898.02 288.05 257 238.625 158.69 2.95 310.504 2087104.71 61125.26 195.83 4910651 24234601965.181 90727.65 128.396 4 156.92 451 570 187.34 4423 22466.9 226.788 1165 1240380.9 751.7 5048.06 4730 99.572 54797.96 9193.24 2.896 1.05 2.561 1195550.6 147.237 4.72 29002.22 637.39 6.09718 6.428 4.14 3162.38 185.11 2.98 3154.65 721.401 7971710.38 141 867.3 3162.4 35188.01 34.85 2113.8 119.133 3117.0 16.381 4.66 12947.6 45.2 298.14 91.2 12638.5 65 106.3 65.7 3234.76 576825.66 90.7 105.5 2481553.24 OpenBenchmarking.org
oneDNN Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.6 Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPU D B C A 8K 16K 24K 32K 40K 4100.65 4105.68 4117.24 35077.90 MIN: 21314.5 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl
oneDNN Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.6 Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPU C B D A 7K 14K 21K 28K 35K 4092.33 4101.51 4110.74 33601.70 MIN: 21286.5 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl
TensorFlow Lite Model: SqueezeNet OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2022-05-18 Model: SqueezeNet D C B A 40K 80K 120K 160K 200K 2888.78 2894.31 2898.87 206917.00
oneDNN Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.6 Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPU B D C A 7K 14K 21K 28K 35K 4089.48 4126.65 4133.63 32226.30 MIN: 17963.3 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl
oneDNN Harness: IP Shapes 3D - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.6 Harness: IP Shapes 3D - Data Type: f32 - Engine: CPU D C B A 16 32 48 64 80 11.38 11.98 11.98 73.36 MIN: 11.24 MIN: 11.88 MIN: 11.88 MIN: 49.92 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl
TensorFlow Lite Model: Inception V4 OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2022-05-18 Model: Inception V4 B D C A 500K 1000K 1500K 2000K 2500K 42001.0 42166.7 42840.4 2445920.0
TensorFlow Lite Model: Inception ResNet V2 OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2022-05-18 Model: Inception ResNet V2 D B C A 500K 1000K 1500K 2000K 2500K 41956.7 42072.8 42165.8 2330410.0
oneDNN Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.6 Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPU B C D A 6 12 18 24 30 5.25702 5.26468 5.27803 23.21980 MIN: 5.18 MIN: 5.18 MIN: 5.19 MIN: 5.62 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl
oneDNN Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.6 Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPU D C B A 8 16 24 32 40 0.924820 0.930888 0.933945 36.708900 MIN: 0.87 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl
oneDNN Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.6 Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPU C B D A 13 26 39 52 65 1.79634 1.80376 1.81319 59.13020 MIN: 1.76 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl
oneDNN Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.6 Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPU C D B A 3 6 9 12 15 3.38355 3.40609 3.40615 12.03100 MIN: 3.26 MIN: 3.29 MIN: 3.27 MIN: 3.34 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl
oneDNN Harness: Matrix Multiply Batch Shapes Transformer - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.6 Harness: Matrix Multiply Batch Shapes Transformer - Data Type: f32 - Engine: CPU C B D A 7 14 21 28 35 1.16856 1.24528 1.29107 30.02690 MIN: 2.16 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl
oneDNN Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.6 Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPU D B C A 11 22 33 44 55 2.43000 2.44129 2.44352 47.94820 MIN: 12.07 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl
oneDNN Harness: Matrix Multiply Batch Shapes Transformer - Data Type: u8s8f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.6 Harness: Matrix Multiply Batch Shapes Transformer - Data Type: u8s8f32 - Engine: CPU B D C A 8 16 24 32 40 1.85271 1.99646 2.25790 36.17280 MIN: 2.27 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl
oneDNN Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.6 Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPU B D C A 20 40 60 80 100 5.65439 7.65826 8.23900 92.13430 MIN: 5.12 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl
oneDNN Harness: IP Shapes 1D - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.6 Harness: IP Shapes 1D - Data Type: f32 - Engine: CPU B D C A 16 32 48 64 80 4.70466 4.70911 4.71020 73.17950 MIN: 4.61 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl
TensorFlow Lite Model: NASNet Mobile OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2022-05-18 Model: NASNet Mobile D B C A 500K 1000K 1500K 2000K 2500K 15326.0 15355.6 15359.5 2271630.0
TensorFlow Lite Model: Mobilenet Quant OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2022-05-18 Model: Mobilenet Quant B D C A 10K 20K 30K 40K 50K 3096.7 3113.9 3146.6 44820.6
oneDNN Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.6 Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPU C D B A 7K 14K 21K 28K 35K 2485.86 2495.97 2496.51 30995.10 MIN: 14054.2 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl
oneDNN Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.6 Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPU D B C A 6K 12K 18K 24K 30K 2473.22 2483.66 2492.88 28223.80 MIN: 12718 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl
TensorFlow Lite Model: Mobilenet Float OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2022-05-18 Model: Mobilenet Float D B C A 50K 100K 150K 200K 250K 2401.33 2411.06 2435.60 240371.00
oneDNN Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.6 Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPU C D B A 6K 12K 18K 24K 30K 2458.19 2458.93 2485.34 25968.50 MIN: 12631 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl
oneDNN Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.6 Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPU D B C A 9 18 27 36 45 24.85 24.91 24.96 41.19 MIN: 24.57 MIN: 24.56 MIN: 24.62 MIN: 27.53 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl
oneDNN Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.6 Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPU D C B A 8 16 24 32 40 22.50 22.59 22.59 36.96 MIN: 21.97 MIN: 22.18 MIN: 22.13 MIN: 22.25 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl
Stress-NG Test: NUMA OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14 Test: NUMA D B C A 70 140 210 280 350 331.54 328.20 326.62 211.02 1. (CC) gcc options: -O2 -std=gnu99 -lm -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lrt -lz -pthread
ONNX Runtime Model: fcn-resnet101-11 - Device: CPU - Executor: Standard OpenBenchmarking.org Inferences Per Minute, More Is Better ONNX Runtime 1.11 Model: fcn-resnet101-11 - Device: CPU - Executor: Standard D B C A 20 40 60 80 100 88 78 60 59 1. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt
ONNX Runtime Model: ArcFace ResNet-100 - Device: CPU - Executor: Standard OpenBenchmarking.org Inferences Per Minute, More Is Better ONNX Runtime 1.11 Model: ArcFace ResNet-100 - Device: CPU - Executor: Standard B C D A 400 800 1200 1600 2000 1660 1183 1154 1119 1. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt
ONNX Runtime Model: yolov4 - Device: CPU - Executor: Standard OpenBenchmarking.org Inferences Per Minute, More Is Better ONNX Runtime 1.11 Model: yolov4 - Device: CPU - Executor: Standard D A C B 100 200 300 400 500 453 365 337 323 1. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt
Stress-NG Test: SENDFILE OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14 Test: SENDFILE C A B D 50K 100K 150K 200K 250K 246261.31 219949.89 216302.59 192604.94 1. (CC) gcc options: -O2 -std=gnu99 -lm -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lrt -lz -pthread
perf-bench Benchmark: Futex Lock-Pi OpenBenchmarking.org ops/sec, More Is Better perf-bench Benchmark: Futex Lock-Pi B C D A 140 280 420 560 700 669 663 649 542 1. (CC) gcc options: -pthread -shared -Xlinker -O6 -ggdb3 -funwind-tables -std=gnu99 -lnuma
SVT-HEVC Tuning: 7 - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better SVT-HEVC 1.5.0 Tuning: 7 - Input: Bosphorus 4K D C B A 11 22 33 44 55 50.62 50.44 50.39 42.20 1. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt
SVT-AV1 Encoder Mode: Preset 8 - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.0 Encoder Mode: Preset 8 - Input: Bosphorus 4K D B C A 8 16 24 32 40 36.59 36.48 36.35 30.78 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq -pie
Renaissance Test: Scala Dotty OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.14 Test: Scala Dotty C A D B 200 400 600 800 1000 729.0 778.7 818.3 833.9 MIN: 618.39 / MAX: 1281.64 MIN: 646.98 / MAX: 1439.03 MIN: 618.81 / MAX: 1331.73 MIN: 636.78 / MAX: 1324.63
ONNX Runtime Model: fcn-resnet101-11 - Device: CPU - Executor: Parallel OpenBenchmarking.org Inferences Per Minute, More Is Better ONNX Runtime 1.11 Model: fcn-resnet101-11 - Device: CPU - Executor: Parallel D C B A 15 30 45 60 75 68 68 68 60 1. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt
ONNX Runtime Model: GPT-2 - Device: CPU - Executor: Standard OpenBenchmarking.org Inferences Per Minute, More Is Better ONNX Runtime 1.11 Model: GPT-2 - Device: CPU - Executor: Standard C B D A 1400 2800 4200 5600 7000 6445 6058 5962 5775 1. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt
InfluxDB Concurrent Streams: 4 - Batch Size: 10000 - Tags: 2,5000,1 - Points Per Series: 10000 OpenBenchmarking.org val/sec, More Is Better InfluxDB 1.8.2 Concurrent Streams: 4 - Batch Size: 10000 - Tags: 2,5000,1 - Points Per Series: 10000 A B C D 200K 400K 600K 800K 1000K 909621.0 852735.1 847482.0 816036.0
perf-bench Benchmark: Memcpy 1MB OpenBenchmarking.org GB/sec, More Is Better perf-bench Benchmark: Memcpy 1MB B D C A 4 8 12 16 20 16.24 14.85 14.77 14.62 1. (CC) gcc options: -pthread -shared -Xlinker -O6 -ggdb3 -funwind-tables -std=gnu99 -lnuma
Nettle Test: chacha OpenBenchmarking.org Mbyte/s, More Is Better Nettle 3.8 Test: chacha B C D A 300 600 900 1200 1500 1185.58 1151.97 1095.00 1068.17 MIN: 574.66 / MAX: 3420.69 MIN: 558.73 / MAX: 3316.95 MIN: 529.55 / MAX: 3168.56 MIN: 514.62 / MAX: 3098.54 1. (CC) gcc options: -O2 -ggdb3 -lnettle -lm -lcrypto
Glibc Benchmarks Benchmark: log2 OpenBenchmarking.org ns, Fewer Is Better Glibc Benchmarks Benchmark: log2 B D C A 5 10 15 20 25 19.46 19.50 20.73 21.53 1. (CC) gcc options: -pie -nostdlib -nostartfiles -lgcc -lgcc_s
GROMACS Implementation: MPI CPU - Input: water_GMX50_bare OpenBenchmarking.org Ns Per Day, More Is Better GROMACS 2022.1 Implementation: MPI CPU - Input: water_GMX50_bare D C B A 0.2599 0.5198 0.7797 1.0396 1.2995 1.155 1.140 1.138 1.047 1. (CXX) g++ options: -O3
SVT-AV1 Encoder Mode: Preset 10 - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.0 Encoder Mode: Preset 10 - Input: Bosphorus 4K D C B A 20 40 60 80 100 79.79 78.41 76.45 72.34 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq -pie
Glibc Benchmarks Benchmark: sincos OpenBenchmarking.org ns, Fewer Is Better Glibc Benchmarks Benchmark: sincos C B D A 10 20 30 40 50 41.74 41.74 42.89 45.98 1. (CC) gcc options: -pie -nostdlib -nostartfiles -lgcc -lgcc_s
SVT-VP9 Tuning: Visual Quality Optimized - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better SVT-VP9 0.3 Tuning: Visual Quality Optimized - Input: Bosphorus 4K D C B A 11 22 33 44 55 49.86 49.84 49.51 45.49 1. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm
Glibc Benchmarks Benchmark: ffsll OpenBenchmarking.org ns, Fewer Is Better Glibc Benchmarks Benchmark: ffsll D B C A 2 4 6 8 10 6.46463 6.46721 6.93142 7.04916 1. (CC) gcc options: -pie -nostdlib -nostartfiles -lgcc -lgcc_s
Renaissance Test: Genetic Algorithm Using Jenetics + Futures OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.14 Test: Genetic Algorithm Using Jenetics + Futures A C B D 600 1200 1800 2400 3000 2666.5 2871.2 2888.2 2903.9 MIN: 2472.42 / MAX: 2807.84 MIN: 2838.52 / MAX: 2898.82 MIN: 2858.54 / MAX: 2927.17 MIN: 2862.13 / MAX: 2943.57
perf-bench Benchmark: Syscall Basic OpenBenchmarking.org ops/sec, More Is Better perf-bench Benchmark: Syscall Basic B D A C 4M 8M 12M 16M 20M 19410883 19384879 17962305 17850063 1. (CC) gcc options: -pthread -shared -Xlinker -O6 -ggdb3 -funwind-tables -std=gnu99 -lnuma
Glibc Benchmarks Benchmark: sinh OpenBenchmarking.org ns, Fewer Is Better Glibc Benchmarks Benchmark: sinh B C D A 6 12 18 24 30 24.82 26.85 26.98 26.98 1. (CC) gcc options: -pie -nostdlib -nostartfiles -lgcc -lgcc_s
Stress-NG Test: Futex OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14 Test: Futex D B C A 600K 1200K 1800K 2400K 3000K 3025044.82 2871422.77 2787436.17 2786611.95 1. (CC) gcc options: -O2 -std=gnu99 -lm -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lrt -lz -pthread
Glibc Benchmarks Benchmark: modf OpenBenchmarking.org ns, Fewer Is Better Glibc Benchmarks Benchmark: modf B D C A 2 4 6 8 10 6.53862 6.54065 6.71077 7.09614 1. (CC) gcc options: -pie -nostdlib -nostartfiles -lgcc -lgcc_s
Renaissance Test: Finagle HTTP Requests OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.14 Test: Finagle HTTP Requests C B D A 800 1600 2400 3200 4000 3529.2 3571.9 3587.1 3814.1 MIN: 3302.49 / MAX: 3811.65 MIN: 3345.25 / MAX: 3795.91 MIN: 3364.31 / MAX: 3763.07 MIN: 3534.91 / MAX: 3897.61
Glibc Benchmarks Benchmark: sqrt OpenBenchmarking.org ns, Fewer Is Better Glibc Benchmarks Benchmark: sqrt B D C A 2 4 6 8 10 7.27802 7.28112 7.46367 7.86042 1. (CC) gcc options: -pie -nostdlib -nostartfiles -lgcc -lgcc_s
Nettle Test: aes256 OpenBenchmarking.org Mbyte/s, More Is Better Nettle 3.8 Test: aes256 C D B A 1400 2800 4200 5600 7000 6541.11 6515.50 6131.07 6059.02 MIN: 4692.01 / MAX: 10192.6 MIN: 4701.43 / MAX: 10170.91 MIN: 4421.4 / MAX: 9534.58 MIN: 4394.53 / MAX: 9359.29 1. (CC) gcc options: -O2 -ggdb3 -lnettle -lm -lcrypto
Glibc Benchmarks Benchmark: sin OpenBenchmarking.org ns, Fewer Is Better Glibc Benchmarks Benchmark: sin D B C A 15 30 45 60 75 60.51 62.17 64.73 65.33 1. (CC) gcc options: -pie -nostdlib -nostartfiles -lgcc -lgcc_s
Glibc Benchmarks Benchmark: asinh OpenBenchmarking.org ns, Fewer Is Better Glibc Benchmarks Benchmark: asinh D C A B 7 14 21 28 35 29.43 29.44 30.64 31.75 1. (CC) gcc options: -pie -nostdlib -nostartfiles -lgcc -lgcc_s
Glibc Benchmarks Benchmark: tanh OpenBenchmarking.org ns, Fewer Is Better Glibc Benchmarks Benchmark: tanh B C D A 9 18 27 36 45 35.61 38.06 38.33 38.37 1. (CC) gcc options: -pie -nostdlib -nostartfiles -lgcc -lgcc_s
Glibc Benchmarks Benchmark: cos OpenBenchmarking.org ns, Fewer Is Better Glibc Benchmarks Benchmark: cos B D C A 16 32 48 64 80 68.60 68.63 70.38 73.92 1. (CC) gcc options: -pie -nostdlib -nostartfiles -lgcc -lgcc_s
perf-bench Benchmark: Sched Pipe OpenBenchmarking.org ops/sec, More Is Better perf-bench Benchmark: Sched Pipe C D B A 80K 160K 240K 320K 400K 351971 344956 340408 326839 1. (CC) gcc options: -pthread -shared -Xlinker -O6 -ggdb3 -funwind-tables -std=gnu99 -lnuma
Renaissance Test: Savina Reactors.IO OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.14 Test: Savina Reactors.IO C B A D 2K 4K 6K 8K 10K 7858.7 7969.9 8321.1 8459.7 MAX: 11840.34 MIN: 7969.86 / MAX: 11204.55 MAX: 12754.85 MAX: 12201.65
Glibc Benchmarks Benchmark: ffs OpenBenchmarking.org ns, Fewer Is Better Glibc Benchmarks Benchmark: ffs B D C A 2 4 6 8 10 5.68026 5.69216 6.08636 6.09947 1. (CC) gcc options: -pie -nostdlib -nostartfiles -lgcc -lgcc_s
SVT-VP9 Tuning: Visual Quality Optimized - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better SVT-VP9 0.3 Tuning: Visual Quality Optimized - Input: Bosphorus 1080p D B C A 40 80 120 160 200 180.36 176.38 176.32 168.00 1. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm
perf-bench Benchmark: Memset 1MB OpenBenchmarking.org GB/sec, More Is Better perf-bench Benchmark: Memset 1MB C D B A 16 32 48 64 80 73.96 72.41 72.01 69.02 1. (CC) gcc options: -pthread -shared -Xlinker -O6 -ggdb3 -funwind-tables -std=gnu99 -lnuma
Stress-NG Test: Context Switching OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14 Test: Context Switching C B D A 1000K 2000K 3000K 4000K 5000K 4842631.56 4833096.84 4808874.54 4520622.35 1. (CC) gcc options: -O2 -std=gnu99 -lm -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lrt -lz -pthread
Glibc Benchmarks Benchmark: atanh OpenBenchmarking.org ns, Fewer Is Better Glibc Benchmarks Benchmark: atanh C D B A 9 18 27 36 45 35.84 35.87 37.46 38.34 1. (CC) gcc options: -pie -nostdlib -nostartfiles -lgcc -lgcc_s
perf-bench Benchmark: Epoll Wait OpenBenchmarking.org ops/sec, More Is Better perf-bench Benchmark: Epoll Wait B D C A 10K 20K 30K 40K 50K 45429 45400 45264 42469 1. (CC) gcc options: -pthread -shared -Xlinker -O6 -ggdb3 -funwind-tables -std=gnu99 -lnuma
SVT-VP9 Tuning: PSNR/SSIM Optimized - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better SVT-VP9 0.3 Tuning: PSNR/SSIM Optimized - Input: Bosphorus 4K B D C A 11 22 33 44 55 46.88 46.83 46.52 43.96 1. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm
Etcpak Benchmark: Single-Threaded - Configuration: ETC2 OpenBenchmarking.org Mpx/s, More Is Better Etcpak 1.0 Benchmark: Single-Threaded - Configuration: ETC2 D C B A 50 100 150 200 250 247.11 246.81 246.14 232.17 1. (CXX) g++ options: -O3 -march=native -std=c++11 -lpthread
libavif avifenc Encoder Speed: 2 OpenBenchmarking.org Seconds, Fewer Is Better libavif avifenc 0.10 Encoder Speed: 2 D B C A 15 30 45 60 75 62.15 62.50 63.47 66.03 1. (CXX) g++ options: -O3 -fPIC -lm
libavif avifenc Encoder Speed: 10, Lossless OpenBenchmarking.org Seconds, Fewer Is Better libavif avifenc 0.10 Encoder Speed: 10, Lossless C D B A 1.3388 2.6776 4.0164 5.3552 6.694 5.601 5.644 5.648 5.950 1. (CXX) g++ options: -O3 -fPIC -lm
libavif avifenc Encoder Speed: 6, Lossless OpenBenchmarking.org Seconds, Fewer Is Better libavif avifenc 0.10 Encoder Speed: 6, Lossless C B D A 3 6 9 12 15 10.76 10.88 10.98 11.43 1. (CXX) g++ options: -O3 -fPIC -lm
libavif avifenc Encoder Speed: 6 OpenBenchmarking.org Seconds, Fewer Is Better libavif avifenc 0.10 Encoder Speed: 6 D B C A 2 4 6 8 10 7.619 7.654 7.718 8.089 1. (CXX) g++ options: -O3 -fPIC -lm
ONNX Runtime Model: GPT-2 - Device: CPU - Executor: Parallel OpenBenchmarking.org Inferences Per Minute, More Is Better ONNX Runtime 1.11 Model: GPT-2 - Device: CPU - Executor: Parallel C B D A 1000 2000 3000 4000 5000 4859 4858 4795 4580 1. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt
SVT-AV1 Encoder Mode: Preset 12 - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.0 Encoder Mode: Preset 12 - Input: Bosphorus 1080p D A C B 80 160 240 320 400 372.28 352.21 351.99 350.93 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq -pie
Renaissance Test: In-Memory Database Shootout OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.14 Test: In-Memory Database Shootout A B D C 800 1600 2400 3200 4000 3614.9 3646.0 3732.7 3824.8 MIN: 3226.39 / MAX: 3786.41 MIN: 3383.09 / MAX: 4041.23 MIN: 3478.56 / MAX: 4080.38 MIN: 3519.07 / MAX: 4246.27
SVT-HEVC Tuning: 1 - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better SVT-HEVC 1.5.0 Tuning: 1 - Input: Bosphorus 1080p C B D A 3 6 9 12 15 11.63 11.63 11.61 11.00 1. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt
SVT-HEVC Tuning: 10 - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better SVT-HEVC 1.5.0 Tuning: 10 - Input: Bosphorus 4K C D B A 20 40 60 80 100 79.86 79.60 78.87 75.56 1. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt
Stress-NG Test: Malloc OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14 Test: Malloc B C D A 4M 8M 12M 16M 20M 16996416.51 16871709.82 16827898.02 16082432.37 1. (CC) gcc options: -O2 -std=gnu99 -lm -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lrt -lz -pthread
SVT-HEVC Tuning: 10 - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better SVT-HEVC 1.5.0 Tuning: 10 - Input: Bosphorus 1080p B D C A 60 120 180 240 300 290.42 288.05 287.22 274.85 1. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt
ONNX Runtime Model: yolov4 - Device: CPU - Executor: Parallel OpenBenchmarking.org Inferences Per Minute, More Is Better ONNX Runtime 1.11 Model: yolov4 - Device: CPU - Executor: Parallel D C B A 60 120 180 240 300 257 257 256 244 1. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt
Etcpak Benchmark: Single-Threaded - Configuration: DXT1 OpenBenchmarking.org Mpx/s, More Is Better Etcpak 1.0 Benchmark: Single-Threaded - Configuration: DXT1 C D B A 50 100 150 200 250 249.28 238.63 237.86 236.90 1. (CXX) g++ options: -O3 -march=native -std=c++11 -lpthread
SVT-HEVC Tuning: 7 - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better SVT-HEVC 1.5.0 Tuning: 7 - Input: Bosphorus 1080p B D C A 40 80 120 160 200 159.49 158.69 158.60 151.75 1. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt
SVT-HEVC Tuning: 1 - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better SVT-HEVC 1.5.0 Tuning: 1 - Input: Bosphorus 4K C D B A 0.666 1.332 1.998 2.664 3.33 2.96 2.95 2.95 2.82 1. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt
WebP2 Image Encode Encode Settings: Quality 95, Compression Effort 7 OpenBenchmarking.org Seconds, Fewer Is Better WebP2 Image Encode 20220422 Encode Settings: Quality 95, Compression Effort 7 C B D A 70 140 210 280 350 308.71 309.66 310.50 323.97 1. (CXX) g++ options: -msse4.2 -fno-rtti -O3 -ldl
Stress-NG Test: Glibc C String Functions OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14 Test: Glibc C String Functions D C B A 400K 800K 1200K 1600K 2000K 2087104.71 2080090.43 2026796.06 1991624.53 1. (CC) gcc options: -O2 -std=gnu99 -lm -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lrt -lz -pthread
Stress-NG Test: Matrix Math OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14 Test: Matrix Math C D B A 13K 26K 39K 52K 65K 61156.12 61125.26 60985.00 58365.05 1. (CC) gcc options: -O2 -std=gnu99 -lm -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lrt -lz -pthread
Stress-NG Test: Glibc Qsort Data Sorting OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14 Test: Glibc Qsort Data Sorting C B D A 40 80 120 160 200 197.10 196.50 195.83 188.30 1. (CC) gcc options: -O2 -std=gnu99 -lm -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lrt -lz -pthread
perf-bench Benchmark: Futex Hash OpenBenchmarking.org ops/sec, More Is Better perf-bench Benchmark: Futex Hash C D B A 1.1M 2.2M 3.3M 4.4M 5.5M 4910773 4910651 4904887 4693851 1. (CC) gcc options: -pthread -shared -Xlinker -O6 -ggdb3 -funwind-tables -std=gnu99 -lnuma
Java JMH Throughput OpenBenchmarking.org Ops/s, More Is Better Java JMH Throughput C B D A 5000M 10000M 15000M 20000M 25000M 24266478961.70 24255951266.37 24234601965.18 23214280399.04
Stress-NG Test: Vector Math OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14 Test: Vector Math C B D A 20K 40K 60K 80K 100K 90779.38 90749.35 90727.65 86846.17 1. (CC) gcc options: -O2 -std=gnu99 -lm -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lrt -lz -pthread
libavif avifenc Encoder Speed: 0 OpenBenchmarking.org Seconds, Fewer Is Better libavif avifenc 0.10 Encoder Speed: 0 D C B A 30 60 90 120 150 128.40 128.78 129.53 134.16 1. (CXX) g++ options: -O3 -fPIC -lm
simdjson Throughput Test: PartialTweets OpenBenchmarking.org GB/s, More Is Better simdjson 2.0 Throughput Test: PartialTweets D C B A 0.9 1.8 2.7 3.6 4.5 4.00 4.00 3.99 3.83 1. (CXX) g++ options: -O3
Stress-NG Test: CPU Cache OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14 Test: CPU Cache C A D B 40 80 120 160 200 158.82 156.96 156.92 152.09 1. (CC) gcc options: -O2 -std=gnu99 -lm -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lrt -lz -pthread
ONNX Runtime Model: bertsquad-12 - Device: CPU - Executor: Parallel OpenBenchmarking.org Inferences Per Minute, More Is Better ONNX Runtime 1.11 Model: bertsquad-12 - Device: CPU - Executor: Parallel D C B A 100 200 300 400 500 451 449 449 432 1. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt
ONNX Runtime Model: bertsquad-12 - Device: CPU - Executor: Standard OpenBenchmarking.org Inferences Per Minute, More Is Better ONNX Runtime 1.11 Model: bertsquad-12 - Device: CPU - Executor: Standard B D C A 120 240 360 480 600 571 570 567 547 1. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt
SVT-VP9 Tuning: PSNR/SSIM Optimized - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better SVT-VP9 0.3 Tuning: PSNR/SSIM Optimized - Input: Bosphorus 1080p B D C A 40 80 120 160 200 187.87 187.34 187.19 180.00 1. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm
ONNX Runtime Model: super-resolution-10 - Device: CPU - Executor: Standard OpenBenchmarking.org Inferences Per Minute, More Is Better ONNX Runtime 1.11 Model: super-resolution-10 - Device: CPU - Executor: Standard C A D B 1000 2000 3000 4000 5000 4511 4435 4423 4324 1. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt
Stress-NG Test: Crypto OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14 Test: Crypto C B D A 5K 10K 15K 20K 25K 22493.23 22488.17 22466.90 21561.58 1. (CC) gcc options: -O2 -std=gnu99 -lm -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lrt -lz -pthread
SVT-AV1 Encoder Mode: Preset 10 - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.0 Encoder Mode: Preset 10 - Input: Bosphorus 1080p B C D A 50 100 150 200 250 232.83 230.17 226.79 223.22 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq -pie
ONNX Runtime Model: ArcFace ResNet-100 - Device: CPU - Executor: Parallel OpenBenchmarking.org Inferences Per Minute, More Is Better ONNX Runtime 1.11 Model: ArcFace ResNet-100 - Device: CPU - Executor: Parallel D B C A 300 600 900 1200 1500 1165 1165 1163 1117 1. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt
InfluxDB Concurrent Streams: 1024 - Batch Size: 10000 - Tags: 2,5000,1 - Points Per Series: 10000 OpenBenchmarking.org val/sec, More Is Better InfluxDB 1.8.2 Concurrent Streams: 1024 - Batch Size: 10000 - Tags: 2,5000,1 - Points Per Series: 10000 A B C D 300K 600K 900K 1200K 1500K 1293571.6 1291849.9 1291195.0 1240380.9
Renaissance Test: Random Forest OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.14 Test: Random Forest B C A D 160 320 480 640 800 721.2 730.9 743.4 751.7 MIN: 609.48 / MAX: 834.11 MIN: 607.63 / MAX: 901.62 MIN: 665.12 / MAX: 887.13 MIN: 622.63 / MAX: 907.43
Stress-NG Test: Memory Copying OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14 Test: Memory Copying D C B A 1100 2200 3300 4400 5500 5048.06 5039.59 5038.57 4844.13 1. (CC) gcc options: -O2 -std=gnu99 -lm -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lrt -lz -pthread
ONNX Runtime Model: super-resolution-10 - Device: CPU - Executor: Parallel OpenBenchmarking.org Inferences Per Minute, More Is Better ONNX Runtime 1.11 Model: super-resolution-10 - Device: CPU - Executor: Parallel D B C A 1000 2000 3000 4000 5000 4730 4619 4586 4541 1. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt
SVT-AV1 Encoder Mode: Preset 12 - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.0 Encoder Mode: Preset 12 - Input: Bosphorus 4K D C B A 20 40 60 80 100 99.57 98.22 98.21 95.65 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq -pie
Stress-NG Test: Forking OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14 Test: Forking C D B A 12K 24K 36K 48K 60K 54932.41 54797.96 54543.49 52768.88 1. (CC) gcc options: -O2 -std=gnu99 -lm -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lrt -lz -pthread
Stress-NG Test: Socket Activity OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14 Test: Socket Activity A D B C 2K 4K 6K 8K 10K 9558.26 9193.24 9191.93 9185.34 1. (CC) gcc options: -O2 -std=gnu99 -lm -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lrt -lz -pthread
WebP2 Image Encode Encode Settings: Default OpenBenchmarking.org Seconds, Fewer Is Better WebP2 Image Encode 20220422 Encode Settings: Default B D A C 0.6757 1.3514 2.0271 2.7028 3.3785 2.886 2.896 2.972 3.003 1. (CXX) g++ options: -msse4.2 -fno-rtti -O3 -ldl
simdjson Throughput Test: LargeRandom OpenBenchmarking.org GB/s, More Is Better simdjson 2.0 Throughput Test: LargeRandom D C B A 0.2363 0.4726 0.7089 0.9452 1.1815 1.05 1.04 1.04 1.01 1. (CXX) g++ options: -O3
SVT-AV1 Encoder Mode: Preset 4 - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.0 Encoder Mode: Preset 4 - Input: Bosphorus 4K B D C A 0.5767 1.1534 1.7301 2.3068 2.8835 2.563 2.561 2.556 2.467 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq -pie
InfluxDB Concurrent Streams: 64 - Batch Size: 10000 - Tags: 2,5000,1 - Points Per Series: 10000 OpenBenchmarking.org val/sec, More Is Better InfluxDB 1.8.2 Concurrent Streams: 64 - Batch Size: 10000 - Tags: 2,5000,1 - Points Per Series: 10000 B C A D 300K 600K 900K 1200K 1500K 1240324.6 1237035.8 1236274.6 1195550.6
WebP2 Image Encode Encode Settings: Quality 75, Compression Effort 7 OpenBenchmarking.org Seconds, Fewer Is Better WebP2 Image Encode 20220422 Encode Settings: Quality 75, Compression Effort 7 B D C A 30 60 90 120 150 146.32 147.24 148.84 151.78 1. (CXX) g++ options: -msse4.2 -fno-rtti -O3 -ldl
simdjson Throughput Test: DistinctUserID OpenBenchmarking.org GB/s, More Is Better simdjson 2.0 Throughput Test: DistinctUserID D B A C 1.062 2.124 3.186 4.248 5.31 4.72 4.72 4.59 4.55 1. (CXX) g++ options: -O3
Stress-NG Test: CPU Stress OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14 Test: CPU Stress B C A D 6K 12K 18K 24K 30K 30044.54 29333.09 29249.94 29002.22 1. (CC) gcc options: -O2 -std=gnu99 -lm -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lrt -lz -pthread
Nettle Test: sha512 OpenBenchmarking.org Mbyte/s, More Is Better Nettle 3.8 Test: sha512 B C D A 140 280 420 560 700 658.67 637.71 637.39 637.04 1. (CC) gcc options: -O2 -ggdb3 -lnettle -lm -lcrypto
Glibc Benchmarks Benchmark: pthread_once OpenBenchmarking.org ns, Fewer Is Better Glibc Benchmarks Benchmark: pthread_once C B D A 2 4 6 8 10 6.02658 6.05998 6.09718 6.23097 1. (CC) gcc options: -pie -nostdlib -nostartfiles -lgcc -lgcc_s
SVT-AV1 Encoder Mode: Preset 4 - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.0 Encoder Mode: Preset 4 - Input: Bosphorus 1080p B C D A 2 4 6 8 10 6.440 6.435 6.428 6.229 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq -pie
WebP2 Image Encode Encode Settings: Quality 100, Compression Effort 5 OpenBenchmarking.org Seconds, Fewer Is Better WebP2 Image Encode 20220422 Encode Settings: Quality 100, Compression Effort 5 B C D A 0.9545 1.909 2.8635 3.818 4.7725 4.110 4.140 4.140 4.242 1. (CXX) g++ options: -msse4.2 -fno-rtti -O3 -ldl
Etcpak Benchmark: Multi-Threaded - Configuration: DXT1 OpenBenchmarking.org Mpx/s, More Is Better Etcpak 1.0 Benchmark: Multi-Threaded - Configuration: DXT1 C D B A 700 1400 2100 2800 3500 3169.25 3162.38 3156.58 3072.05 1. (CXX) g++ options: -O3 -march=native -std=c++11 -lpthread
SVT-VP9 Tuning: VMAF Optimized - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better SVT-VP9 0.3 Tuning: VMAF Optimized - Input: Bosphorus 1080p D B C A 40 80 120 160 200 185.11 184.60 183.53 179.51 1. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm
simdjson Throughput Test: Kostya OpenBenchmarking.org GB/s, More Is Better simdjson 2.0 Throughput Test: Kostya D A B C 0.6705 1.341 2.0115 2.682 3.3525 2.98 2.93 2.92 2.89 1. (CXX) g++ options: -O3
Etcpak Benchmark: Multi-Threaded - Configuration: ETC2 OpenBenchmarking.org Mpx/s, More Is Better Etcpak 1.0 Benchmark: Multi-Threaded - Configuration: ETC2 D B C A 700 1400 2100 2800 3500 3154.65 3146.37 3144.30 3061.54 1. (CXX) g++ options: -O3 -march=native -std=c++11 -lpthread
WebP2 Image Encode Encode Settings: Quality 100, Lossless Compression OpenBenchmarking.org Seconds, Fewer Is Better WebP2 Image Encode 20220422 Encode Settings: Quality 100, Lossless Compression D B C A 160 320 480 640 800 721.40 721.68 722.89 742.93 1. (CXX) g++ options: -msse4.2 -fno-rtti -O3 -ldl
Stress-NG Test: System V Message Passing OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14 Test: System V Message Passing B C D A 2M 4M 6M 8M 10M 8003229.07 7995516.42 7971710.38 7796050.70 1. (CC) gcc options: -O2 -std=gnu99 -lm -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lrt -lz -pthread
x264 Video Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better x264 2022-02-22 Video Input: Bosphorus 1080p B D C A 30 60 90 120 150 141.25 141.00 140.99 137.76 1. (CC) gcc options: -ldl -m64 -lm -lpthread -O3 -flto
Stress-NG Test: MEMFD OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14 Test: MEMFD B C D A 200 400 600 800 1000 871.88 869.61 867.30 850.42 1. (CC) gcc options: -O2 -std=gnu99 -lm -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lrt -lz -pthread
Renaissance Test: Apache Spark ALS OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.14 Test: Apache Spark ALS B C D A 700 1400 2100 2800 3500 3133.9 3137.4 3162.4 3211.3 MIN: 3035.49 / MAX: 3252.39 MIN: 3005.95 / MAX: 3263.19 MIN: 3046.43 / MAX: 3270.26 MIN: 3059.26 / MAX: 3335.58
Stress-NG Test: IO_uring OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14 Test: IO_uring A D B C 8K 16K 24K 32K 40K 35619.31 35188.01 34951.82 34815.95 1. (CC) gcc options: -O2 -std=gnu99 -lm -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lrt -lz -pthread
x264 Video Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better x264 2022-02-22 Video Input: Bosphorus 4K B A C D 8 16 24 32 40 35.64 35.58 35.36 34.85 1. (CC) gcc options: -ldl -m64 -lm -lpthread -O3 -flto
Renaissance Test: Apache Spark Bayes OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.14 Test: Apache Spark Bayes B D A C 500 1000 1500 2000 2500 2104.4 2113.8 2126.2 2149.7 MIN: 1617.62 / MAX: 2358.18 MIN: 1613.04 MIN: 1633.81 / MAX: 2126.21 MIN: 1657.38
SVT-AV1 Encoder Mode: Preset 8 - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.0 Encoder Mode: Preset 8 - Input: Bosphorus 1080p D B C A 30 60 90 120 150 119.13 117.45 117.33 116.76 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq -pie
Renaissance Test: Apache Spark PageRank OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.14 Test: Apache Spark PageRank C D B A 700 1400 2100 2800 3500 3116.0 3117.0 3153.2 3174.2 MIN: 2658.74 / MAX: 3170.73 MIN: 2793.69 / MAX: 3226.06 MIN: 2764.94 / MAX: 3198.77 MIN: 2810.59 / MAX: 3285.06
Glibc Benchmarks Benchmark: exp OpenBenchmarking.org ns, Fewer Is Better Glibc Benchmarks Benchmark: exp C A D B 4 8 12 16 20 16.15 16.19 16.38 16.44 1. (CC) gcc options: -pie -nostdlib -nostartfiles -lgcc -lgcc_s
simdjson Throughput Test: TopTweet OpenBenchmarking.org GB/s, More Is Better simdjson 2.0 Throughput Test: TopTweet A D C B 1.053 2.106 3.159 4.212 5.265 4.68 4.66 4.61 4.61 1. (CXX) g++ options: -O3
Renaissance Test: Akka Unbalanced Cobwebbed Tree OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.14 Test: Akka Unbalanced Cobwebbed Tree A C B D 3K 6K 9K 12K 15K 12754.4 12759.6 12943.4 12947.6 MIN: 10167.69 / MAX: 12754.41 MIN: 10128.47 MIN: 10264.93 / MAX: 12943.41 MIN: 10307.6 / MAX: 12947.63
SVT-VP9 Tuning: VMAF Optimized - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better SVT-VP9 0.3 Tuning: VMAF Optimized - Input: Bosphorus 4K B D C A 10 20 30 40 50 45.21 45.20 45.12 44.54 1. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm
Stress-NG Test: MMAP OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14 Test: MMAP B C D A 70 140 210 280 350 300.58 300.57 298.14 296.27 1. (CC) gcc options: -O2 -std=gnu99 -lm -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lrt -lz -pthread
GravityMark Resolution: 2560 x 1440 - Renderer: OpenGL OpenBenchmarking.org Frames Per Second, More Is Better GravityMark 1.53 Resolution: 2560 x 1440 - Renderer: OpenGL C D A B 20 40 60 80 100 91.7 91.2 91.1 90.4
Renaissance Test: ALS Movie Lens OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.14 Test: ALS Movie Lens B D C A 3K 6K 9K 12K 15K 12616.7 12638.5 12677.3 12757.9 MIN: 12616.69 / MAX: 13750.37 MAX: 13822.5 MIN: 12677.26 / MAX: 13923.11 MIN: 12757.86 / MAX: 14048.24
GravityMark Resolution: 3840 x 2160 - Renderer: Vulkan OpenBenchmarking.org Frames Per Second, More Is Better GravityMark 1.53 Resolution: 3840 x 2160 - Renderer: Vulkan D A B C 15 30 45 60 75 65.0 65.0 64.5 64.4
GravityMark Resolution: 1920 x 1080 - Renderer: OpenGL OpenBenchmarking.org Frames Per Second, More Is Better GravityMark 1.53 Resolution: 1920 x 1080 - Renderer: OpenGL A C B D 20 40 60 80 100 107.2 106.5 106.5 106.3
GravityMark Resolution: 3840 x 2160 - Renderer: OpenGL OpenBenchmarking.org Frames Per Second, More Is Better GravityMark 1.53 Resolution: 3840 x 2160 - Renderer: OpenGL D A B C 15 30 45 60 75 65.7 65.7 65.3 65.2
Nettle Test: poly1305-aes OpenBenchmarking.org Mbyte/s, More Is Better Nettle 3.8 Test: poly1305-aes D C A B 700 1400 2100 2800 3500 3234.76 3217.70 3216.07 3212.21 1. (CC) gcc options: -O2 -ggdb3 -lnettle -lm -lcrypto
Stress-NG Test: Atomic OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14 Test: Atomic C B D A 120K 240K 360K 480K 600K 580078.48 577614.81 576825.66 576128.96 1. (CC) gcc options: -O2 -std=gnu99 -lm -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lrt -lz -pthread
GravityMark Resolution: 2560 x 1440 - Renderer: Vulkan OpenBenchmarking.org Frames Per Second, More Is Better GravityMark 1.53 Resolution: 2560 x 1440 - Renderer: Vulkan D A C B 20 40 60 80 100 90.7 90.6 90.5 90.4
GravityMark Resolution: 1920 x 1080 - Renderer: Vulkan OpenBenchmarking.org Frames Per Second, More Is Better GravityMark 1.53 Resolution: 1920 x 1080 - Renderer: Vulkan C D B A 20 40 60 80 100 105.6 105.5 105.3 105.3
Stress-NG Test: Semaphores OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14 Test: Semaphores C A D B 500K 1000K 1500K 2000K 2500K 2485080.45 2483545.87 2481553.24 2481083.26 1. (CC) gcc options: -O2 -std=gnu99 -lm -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lrt -lz -pthread
Phoronix Test Suite v10.8.5