Intel Core i9-7980XE testing with GCC 9 compiler by Michael Larabel.
Compare your own system(s) to this result file with the
Phoronix Test Suite by running the command:
phoronix-test-suite benchmark 1905120-HV-COREII79889 Core i9 7980XE GCC 9 Compiler Benchmarks - Phoronix Test Suite Core i9 7980XE GCC 9 Compiler Benchmarks Intel Core i9-7980XE testing with GCC 9 compiler by Michael Larabel.
HTML result view exported from: https://openbenchmarking.org/result/1905120-HV-COREII79889&obr_sgm=y&obr_sor=y&obr_rro=y&sro&grw .
Core i9 7980XE GCC 9 Compiler Benchmarks Processor Motherboard Chipset Memory Disk Graphics Audio Monitor Network OS Kernel Desktop Display Server Display Driver OpenGL Compiler File-System Screen Resolution -O3 -march=skylake -O3 -march=skylake-avx512 -mprefer-vector-width=128 -O3 -march=skylake-avx512 -mprefer-vector-width=256 -O3 -march=skylake-avx512 -mprefer-vector-width=512 Intel Core i9-7980XE @ 4.20GHz (18 Cores / 36 Threads) ASUS PRIME X299-A (1704 BIOS) Intel Sky Lake-E DMI3 Registers 16384MB Samsung SSD 970 EVO 500GB NVIDIA NV120 12GB Realtek ALC1220 ASUS PB278 Intel I219-V Clear Linux OS 29350 5.0.14-753.native (x86_64) GNOME Shell 3.32.1 X Server 1.20.4 nouveau 1.0.16 4.3 Mesa 19.1.0-devel GCC 9.1.1 20190509 gcc-9-branch@271025 + clang (Clear Linux OS for Intel Architecture) 9.1.1 20190509 gcc-9-branch@271025 + LLVM 8.0.0 ext4 2560x1440 OpenBenchmarking.org Environment Details - -O3 -march=skylake: CFFLAGS=-g-O3-feliminate-unused-debug-types-pipe-Wall-Wp-D_FORTIFY_SOURCE=2-fexceptions-fstack-protector--param=ssp-buffer-size=32-m64-fasynchronous-unwind-tables-Wp-D_REENTRANT-ftree-loop-distribute-patterns-Wl-z-Wl now-Wl-z-Wl relro-malign-data=abi-fno-semantic-interposition-ftree-vectorize-ftree-loop-vectorize-Wl-sort-common-Wl--enable-new-dtags FFLAGS=-g-O3-feliminate-unused-debug-types-pipe-Wall-Wp-D_FORTIFY_SOURCE=2-fexceptions-fstack-protector--param=ssp-buffer-size=32-m64-fasynchronous-unwind-tables-Wp-D_REENTRANT-ftree-loop-distribute-patterns-Wl-z-Wl relro-malign-data=abi-fno-semantic-interposition-ftree-vectorize-ftree-loop-vectorize-Wl--enable-new-dtags CXXFLAGS=-O3-march=skylake MESA_GLSL_CACHE_DISABLE=0 CFLAGS=-O3-march=skylake THEANO_FLAGS=floatX=float32 openmp=true gcc.cxxflags="-ftree-vectorize-mavx" - -O3 -march=skylake-avx512 -mprefer-vector-width=128: CFFLAGS=-g-O3-feliminate-unused-debug-types-pipe-Wall-Wp-D_FORTIFY_SOURCE=2-fexceptions-fstack-protector--param=ssp-buffer-size=32-m64-fasynchronous-unwind-tables-Wp-D_REENTRANT-ftree-loop-distribute-patterns-Wl-z-Wl now-Wl-z-Wl relro-malign-data=abi-fno-semantic-interposition-ftree-vectorize-ftree-loop-vectorize-Wl-sort-common-Wl--enable-new-dtags FFLAGS=-g-O3-feliminate-unused-debug-types-pipe-Wall-Wp-D_FORTIFY_SOURCE=2-fexceptions-fstack-protector--param=ssp-buffer-size=32-m64-fasynchronous-unwind-tables-Wp-D_REENTRANT-ftree-loop-distribute-patterns-Wl-z-Wl relro-malign-data=abi-fno-semantic-interposition-ftree-vectorize-ftree-loop-vectorize-Wl--enable-new-dtags CXXFLAGS=-O3-march=skylake-avx512-mprefer-vector-width=128 MESA_GLSL_CACHE_DISABLE=0 CFLAGS=-O3-march=skylake-avx512-mprefer-vector-width=128 THEANO_FLAGS=floatX=float32 openmp=true gcc.cxxflags="-ftree-vectorize-mavx" - -O3 -march=skylake-avx512 -mprefer-vector-width=256: CFFLAGS=-g-O3-feliminate-unused-debug-types-pipe-Wall-Wp-D_FORTIFY_SOURCE=2-fexceptions-fstack-protector--param=ssp-buffer-size=32-m64-fasynchronous-unwind-tables-Wp-D_REENTRANT-ftree-loop-distribute-patterns-Wl-z-Wl now-Wl-z-Wl relro-malign-data=abi-fno-semantic-interposition-ftree-vectorize-ftree-loop-vectorize-Wl-sort-common-Wl--enable-new-dtags FFLAGS=-g-O3-feliminate-unused-debug-types-pipe-Wall-Wp-D_FORTIFY_SOURCE=2-fexceptions-fstack-protector--param=ssp-buffer-size=32-m64-fasynchronous-unwind-tables-Wp-D_REENTRANT-ftree-loop-distribute-patterns-Wl-z-Wl relro-malign-data=abi-fno-semantic-interposition-ftree-vectorize-ftree-loop-vectorize-Wl--enable-new-dtags CXXFLAGS=-O3-march=skylake-avx512-mprefer-vector-width=256 MESA_GLSL_CACHE_DISABLE=0 CFLAGS=-O3-march=skylake-avx512-mprefer-vector-width=256 THEANO_FLAGS=floatX=float32 openmp=true gcc.cxxflags="-ftree-vectorize-mavx" - -O3 -march=skylake-avx512 -mprefer-vector-width=512: CFFLAGS=-g-O3-feliminate-unused-debug-types-pipe-Wall-Wp-D_FORTIFY_SOURCE=2-fexceptions-fstack-protector--param=ssp-buffer-size=32-m64-fasynchronous-unwind-tables-Wp-D_REENTRANT-ftree-loop-distribute-patterns-Wl-z-Wl now-Wl-z-Wl relro-malign-data=abi-fno-semantic-interposition-ftree-vectorize-ftree-loop-vectorize-Wl-sort-common-Wl--enable-new-dtags FFLAGS=-g-O3-feliminate-unused-debug-types-pipe-Wall-Wp-D_FORTIFY_SOURCE=2-fexceptions-fstack-protector--param=ssp-buffer-size=32-m64-fasynchronous-unwind-tables-Wp-D_REENTRANT-ftree-loop-distribute-patterns-Wl-z-Wl relro-malign-data=abi-fno-semantic-interposition-ftree-vectorize-ftree-loop-vectorize-Wl--enable-new-dtags CXXFLAGS=-O3-march=skylake-avx512-mprefer-vector-width=512 MESA_GLSL_CACHE_DISABLE=0 CFLAGS=-O3-march=skylake-avx512-mprefer-vector-width=512 THEANO_FLAGS=floatX=float32 openmp=true gcc.cxxflags="-ftree-vectorize-mavx" Compiler Details - --build=x86_64-generic-linux --disable-libmpx --disable-libunwind-exceptions --disable-multiarch --disable-vtable-verify --disable-werror --enable-__cxa_atexit --enable-bootstrap --enable-cet --enable-clocale=gnu --enable-default-pie --enable-gnu-indirect-function --enable-languages=c,c++,fortran,go --enable-ld=default --enable-libstdcxx-pch --enable-lto --enable-multilib --enable-plugin --enable-shared --enable-threads=posix --exec-prefix=/usr --includedir=/usr/include --target=x86_64-generic-linux --with-arch=westmere --with-gcc-major-version-only --with-glibc-version=2.19 --with-gnu-ld --with-isl --with-ppl=yes --with-tune=haswell Processor Details - Scaling Governor: intel_pstate performance Python Details - Python 3.7.3 Security Details - KPTI + __user pointer sanitization + Full generic retpoline IBPB: conditional IBRS_FW STIBP: conditional RSB filling + SSB disabled via prctl and seccomp + PTE Inversion; VMX: conditional cache flushes SMT vulnerable
Core i9 7980XE GCC 9 Compiler Benchmarks tscp: AI Chess Performance crafty: Elapsed Time clomp: Static OMP Speedup compress-xz: Compressing ubuntu-16.04.3-server-i386.img, Compression Level 9 cpp-perf-bench: Atol cpp-perf-bench: Ctype cpp-perf-bench: Math Library cpp-perf-bench: Rand Numbers cpp-perf-bench: Stepanov Vector cpp-perf-bench: Function Objects cpp-perf-bench: Stepanov Abstraction mkl-dnn: Convolution Batch conv_alexnet - f32 t-test1: 2 lzbench: XZ 0 - Compression lzbench: XZ 0 - Decompression lzbench: Zstd 1 - Compression lzbench: Zstd 1 - Decompression lzbench: Brotli 0 - Compression lzbench: Brotli 0 - Decompression lzbench: Libdeflate 1 - Compression lzbench: Libdeflate 1 - Decompression mkl-dnn: Deconvolution Batch deconv_1d - f32 blake2: botan: KASUMI - Encrypt botan: KASUMI - Decrypt mkl-dnn: Convolution Batch conv_googlenet_v3 - f32 botan: AES-256 - Encrypt botan: Twofish - Encrypt botan: Twofish - Decrypt botan: Blowfish - Encrypt botan: Blowfish - Decrypt botan: CAST-256 - Encrypt botan: CAST-256 - Decrypt encode-flac: WAV To FLAC encode-mp3: WAV To MP3 tjbench: Decompression Throughput luajit: Composite mkl-dnn: IP Batch 1D - f32 fftw: Stock - 2D FFT Size 4096 fftw: Float + SSE - 2D FFT Size 4096 hmmer: Pfam Database Search mrbayes: Primate Phylogeny Analysis himeno: Poisson Pressure Solver cloverleaf: Lagrangian-Eulerian Hydrodynamics parboil: OpenMP LBM parboil: OpenMP CUTCP mkl-dnn: Deconvolution Batch deconv_all - f32 botan: AES-256 - Decrypt parboil: OpenMP Stencil parboil: OpenMP MRI Gridding npb: BT.A npb: EP.C npb: FT.A npb: FT.B npb: LU.A npb: LU.C npb: SP.A rodinia: OpenMP LavaMD rodinia: OpenMP CFD Solver rodinia: OpenMP Streamcluster primesieve: 1e12 Prime Number Generation xsbench: stockfish: Total Time compress-7zip: Compress Speed Test build-php: Time To Compile compress-zstd: Compressing ubuntu-16.04.3-server-i386.img, Compression Level 19 m-queens: Time To Solve cpuminer-opt: m7m cpuminer-opt: deep cpuminer-opt: lbry cpuminer-opt: skein cpuminer-opt: myr-gr cpuminer-opt: sha256t build-linux-kernel: Time To Compile aobench: 2048 x 2048 - Total Time graphics-magick: Swirl graphics-magick: Rotate graphics-magick: Sharpen graphics-magick: Enhanced graphics-magick: Resizing graphics-magick: Noise-Gaussian graphics-magick: HWB Color Space svt-vp9: 1080p 8-bit YUV To VP9 Video Encode x264: H.264 Video Encoding dav1d: Summer Nature 4K dav1d: Summer Nature 1080p svt-av1: 1080p 8-bit YUV To AV1 Video Encode x265: H.265 1080p Video Encoding c-ray: Total Time - 4K, 16 Rays Per Pixel ttsiod-renderer: Phong Rendering With Soft-Shadow Mapping svt-hevc: 1080p 8-bit YUV To HEVC Video Encode ffmpeg: H.264 HD To NTSC DV mcperf: Add mcperf: Get mcperf: Set mcperf: Append mcperf: Delete mcperf: Prepend mcperf: Replace nginx: Static Web Page Serving apache: Static Web Page Serving redis: LPOP redis: SADD redis: LPUSH redis: GET redis: SET pgbench: Buffer Test - Normal Load - Read Only pgbench: Buffer Test - Normal Load - Read Write polybench-c: 3 Matrix Multiplications -O3 -march=skylake -O3 -march=skylake-avx512 -mprefer-vector-width=128 -O3 -march=skylake-avx512 -mprefer-vector-width=256 -O3 -march=skylake-avx512 -mprefer-vector-width=512 1368057 8852846 2.12 15.88 57.08 29.69 260 846 82.98 13.62 32.49 1822 5.93 39 108 451 1137 430 620 248 1189 23.03 4.02 96.02 95.01 752 4220 400 393 295 293 145 145 8.77 9.32 196 1606 20.79 6327 17183 3.49 65.67 3302 2.32 68.54 2.38 10446 4212 7.74 132 4391 2038 8581 9376 37394 33669 4062 16.96 11.52 13.63 12.79 5164164 47112136 100157 51.80 9.71 48.42 499 15323 48547 56227 16360 125653 36.34 31.17 252 291 204 227 277 198 288 342 139 19.15 6.93 24.44 53.71 30.87 710 304 5.45 72123 117212 72585 78294 120897 77484 78460 47570 36040 3140283 2339849 2059237 2958563 2163293 520100 13311 2.64 1388054 8840395 2.11 15.84 57.07 30.57 262 821 82.88 13.28 32.44 1820 5.81 39 107 451 1138 429 620 249 1190 23.01 4.02 96.22 95.26 749 3847 401 395 295 294 145 146 8.76 9.05 196 1605 20.84 6863 17522 3.40 63.06 3310 2.29 68.35 2.38 10397 3840 7.98 135 4773 2090 8581 9337 39791 34962 4073 16.99 11.47 13.72 12.80 5171354 46810779 99546 51.84 9.59 48.42 503 15497 52793 62813 15560 124672 36.33 31.15 251 290 207 225 277 197 289 346 140 19.47 6.97 24.37 53.34 33.34 738 339 5.50 73307 107497 73045 78021 122131 77547 78432 46938 35982 3095145 2624995 1962269 2992962 2189741 519930 13495 2.61 1380406 8845689 2.12 15.80 57.00 30.89 264 857 83.16 13.70 32.44 1819 5.82 39 107 452 1137 429 620 249 1191 22.93 4.02 96.21 95.17 751 3833 401 395 295 293 145 146 8.66 9.30 194 1607 20.74 6615 17326 3.50 63.20 3292 2.29 68.26 2.38 10405 3855 7.77 134 4784 2109 8544 9331 39343 35007 4185 16.95 11.31 13.88 12.78 5140078 47046623 99960 51.90 9.69 48.40 506 15490 53473 62560 15695 124030 36.93 31.11 251 290 206 224 275 198 288 347 140 19.34 6.95 24.34 53.97 33.47 729 337 5.47 72947 117621 72688 77703 114714 79076 77373 49221 35946 3139485 2449355 2013442 2944968 1971745 521901 13576 2.63 1373514 8840945 2.12 15.99 57.06 30.56 263 846 98.92 13.39 37.27 1819 5.82 39 108 452 1138 428 621 249 1191 23.07 4.02 96.25 95.30 751 3835 401 395 295 294 145 146 9.14 10.19 197 1608 20.66 5673 17334 3.88 65.66 2814 2.30 68.18 2.41 10424 3839 7.80 132 4391 2113 8543 9387 37305 33676 4080 16.98 11.71 14.12 12.96 5166043 46997822 100416 52.19 9.76 48.41 479 14490 53620 62027 15310 124567 37.36 31.29 228 250 186 196 243 195 253 337 140 19.67 7.05 24.43 50.05 35.86 669 304 5.45 73346 112844 72940 77932 115719 79234 78798 44072 33240 3059844 2383273 2026656 3002750 2135179 498539 13424 2.63 OpenBenchmarking.org
TSCP AI Chess Performance OpenBenchmarking.org Nodes Per Second, More Is Better TSCP 1.81 AI Chess Performance -O3 -march=skylake -O3 -march=skylake-avx512 -mprefer-vector-width=512 -O3 -march=skylake-avx512 -mprefer-vector-width=256 -O3 -march=skylake-avx512 -mprefer-vector-width=128 300K 600K 900K 1200K 1500K SE +/- 1357.03, N = 5 SE +/- 1083.24, N = 5 SE +/- 1890.20, N = 5 SE +/- 1307.98, N = 5 1368057 1373514 1380406 1388054 -march=skylake 1. (CC) gcc options: -O3 -march=native
Crafty Elapsed Time OpenBenchmarking.org Nodes Per Second, More Is Better Crafty 25.2 Elapsed Time -O3 -march=skylake-avx512 -mprefer-vector-width=128 -O3 -march=skylake-avx512 -mprefer-vector-width=512 -O3 -march=skylake-avx512 -mprefer-vector-width=256 -O3 -march=skylake 2M 4M 6M 8M 10M SE +/- 5800.58, N = 3 SE +/- 7719.64, N = 3 SE +/- 7027.53, N = 3 SE +/- 4114.60, N = 3 8840395 8840945 8845689 8852846 1. (CC) gcc options: -pthread -lstdc++ -fprofile-use -lm
CLOMP Static OMP Speedup OpenBenchmarking.org Speedup, More Is Better CLOMP 3.3 Static OMP Speedup -O3 -march=skylake-avx512 -mprefer-vector-width=128 -O3 -march=skylake -O3 -march=skylake-avx512 -mprefer-vector-width=256 -O3 -march=skylake-avx512 -mprefer-vector-width=512 0.477 0.954 1.431 1.908 2.385 SE +/- 0.01, N = 5 SE +/- 0.01, N = 5 SE +/- 0.01, N = 5 SE +/- 0.01, N = 5 2.11 2.12 2.12 2.12 1. (CC) gcc options: --openmp -O3 -lm
XZ Compression Compressing ubuntu-16.04.3-server-i386.img, Compression Level 9 OpenBenchmarking.org Seconds, Fewer Is Better XZ Compression 5.2.4 Compressing ubuntu-16.04.3-server-i386.img, Compression Level 9 -O3 -march=skylake-avx512 -mprefer-vector-width=512 -O3 -march=skylake -O3 -march=skylake-avx512 -mprefer-vector-width=128 -O3 -march=skylake-avx512 -mprefer-vector-width=256 4 8 12 16 20 SE +/- 0.02, N = 3 SE +/- 0.06, N = 3 SE +/- 0.03, N = 3 SE +/- 0.06, N = 3 15.99 15.88 15.84 15.80 -march=skylake 1. (CC) gcc options: -pthread -fvisibility=hidden -O3
CppPerformanceBenchmarks Test: Atol OpenBenchmarking.org Seconds, Fewer Is Better CppPerformanceBenchmarks 9 Test: Atol -O3 -march=skylake -O3 -march=skylake-avx512 -mprefer-vector-width=128 -O3 -march=skylake-avx512 -mprefer-vector-width=512 -O3 -march=skylake-avx512 -mprefer-vector-width=256 13 26 39 52 65 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 SE +/- 0.04, N = 3 SE +/- 0.04, N = 3 57.08 57.07 57.06 57.00 -march=skylake 1. (CXX) g++ options: -O3 -std=c++11
CppPerformanceBenchmarks Test: Ctype OpenBenchmarking.org Seconds, Fewer Is Better CppPerformanceBenchmarks 9 Test: Ctype -O3 -march=skylake-avx512 -mprefer-vector-width=256 -O3 -march=skylake-avx512 -mprefer-vector-width=128 -O3 -march=skylake-avx512 -mprefer-vector-width=512 -O3 -march=skylake 7 14 21 28 35 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 30.89 30.57 30.56 29.69 -march=skylake 1. (CXX) g++ options: -O3 -std=c++11
CppPerformanceBenchmarks Test: Math Library OpenBenchmarking.org Seconds, Fewer Is Better CppPerformanceBenchmarks 9 Test: Math Library -O3 -march=skylake-avx512 -mprefer-vector-width=256 -O3 -march=skylake-avx512 -mprefer-vector-width=512 -O3 -march=skylake-avx512 -mprefer-vector-width=128 -O3 -march=skylake 60 120 180 240 300 SE +/- 1.04, N = 3 SE +/- 0.10, N = 3 SE +/- 0.10, N = 3 SE +/- 0.17, N = 3 264 263 262 260 -march=skylake 1. (CXX) g++ options: -O3 -std=c++11
CppPerformanceBenchmarks Test: Random Numbers OpenBenchmarking.org Seconds, Fewer Is Better CppPerformanceBenchmarks 9 Test: Random Numbers -O3 -march=skylake-avx512 -mprefer-vector-width=256 -O3 -march=skylake-avx512 -mprefer-vector-width=512 -O3 -march=skylake -O3 -march=skylake-avx512 -mprefer-vector-width=128 200 400 600 800 1000 SE +/- 0.00, N = 3 SE +/- 0.10, N = 3 SE +/- 0.29, N = 3 SE +/- 0.19, N = 3 857 846 846 821 -march=skylake 1. (CXX) g++ options: -O3 -std=c++11
CppPerformanceBenchmarks Test: Stepanov Vector OpenBenchmarking.org Seconds, Fewer Is Better CppPerformanceBenchmarks 9 Test: Stepanov Vector -O3 -march=skylake-avx512 -mprefer-vector-width=512 -O3 -march=skylake-avx512 -mprefer-vector-width=256 -O3 -march=skylake -O3 -march=skylake-avx512 -mprefer-vector-width=128 20 40 60 80 100 SE +/- 0.02, N = 3 SE +/- 0.03, N = 3 SE +/- 0.01, N = 3 SE +/- 0.03, N = 3 98.92 83.16 82.98 82.88 -march=skylake 1. (CXX) g++ options: -O3 -std=c++11
CppPerformanceBenchmarks Test: Function Objects OpenBenchmarking.org Seconds, Fewer Is Better CppPerformanceBenchmarks 9 Test: Function Objects -O3 -march=skylake-avx512 -mprefer-vector-width=256 -O3 -march=skylake -O3 -march=skylake-avx512 -mprefer-vector-width=512 -O3 -march=skylake-avx512 -mprefer-vector-width=128 4 8 12 16 20 SE +/- 0.08, N = 3 SE +/- 0.08, N = 3 SE +/- 0.07, N = 3 SE +/- 0.01, N = 3 13.70 13.62 13.39 13.28 -march=skylake 1. (CXX) g++ options: -O3 -std=c++11
CppPerformanceBenchmarks Test: Stepanov Abstraction OpenBenchmarking.org Seconds, Fewer Is Better CppPerformanceBenchmarks 9 Test: Stepanov Abstraction -O3 -march=skylake-avx512 -mprefer-vector-width=512 -O3 -march=skylake -O3 -march=skylake-avx512 -mprefer-vector-width=256 -O3 -march=skylake-avx512 -mprefer-vector-width=128 9 18 27 36 45 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 SE +/- 0.03, N = 3 SE +/- 0.02, N = 3 37.27 32.49 32.44 32.44 -march=skylake 1. (CXX) g++ options: -O3 -std=c++11
MKL-DNN Harness: Convolution Batch conv_alexnet - Data Type: f32 OpenBenchmarking.org ms, Fewer Is Better MKL-DNN 2019-04-16 Harness: Convolution Batch conv_alexnet - Data Type: f32 -O3 -march=skylake -O3 -march=skylake-avx512 -mprefer-vector-width=128 -O3 -march=skylake-avx512 -mprefer-vector-width=512 -O3 -march=skylake-avx512 -mprefer-vector-width=256 400 800 1200 1600 2000 SE +/- 0.89, N = 3 SE +/- 0.22, N = 3 SE +/- 0.68, N = 3 SE +/- 0.28, N = 3 1822 1820 1819 1819 -march=skylake - MIN: 1818.58 MIN: 1817.59 MIN: 1815.94 MIN: 1816.37 1. (CXX) g++ options: -O3 -std=c++11 -march=native -mtune=native -fPIC -fopenmp -pie -lmklml_intel -ldl
t-test1 Threads: 2 OpenBenchmarking.org Seconds, Fewer Is Better t-test1 2017-01-13 Threads: 2 -O3 -march=skylake -O3 -march=skylake-avx512 -mprefer-vector-width=512 -O3 -march=skylake-avx512 -mprefer-vector-width=256 -O3 -march=skylake-avx512 -mprefer-vector-width=128 1.3343 2.6686 4.0029 5.3372 6.6715 SE +/- 0.10, N = 3 SE +/- 0.02, N = 3 SE +/- 0.03, N = 3 SE +/- 0.02, N = 3 5.93 5.82 5.82 5.81 -march=skylake 1. (CC) gcc options: -pthread -O3
lzbench Test: XZ 0 - Process: Compression OpenBenchmarking.org MB/s, More Is Better lzbench 2017-08-08 Test: XZ 0 - Process: Compression -O3 -march=skylake -O3 -march=skylake-avx512 -mprefer-vector-width=128 -O3 -march=skylake-avx512 -mprefer-vector-width=256 -O3 -march=skylake-avx512 -mprefer-vector-width=512 9 18 27 36 45 39 39 39 39 1. (CXX) g++ options: -lrt -static -lpthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3
lzbench Test: XZ 0 - Process: Decompression OpenBenchmarking.org MB/s, More Is Better lzbench 2017-08-08 Test: XZ 0 - Process: Decompression -O3 -march=skylake-avx512 -mprefer-vector-width=128 -O3 -march=skylake-avx512 -mprefer-vector-width=256 -O3 -march=skylake -O3 -march=skylake-avx512 -mprefer-vector-width=512 20 40 60 80 100 107 107 108 108 1. (CXX) g++ options: -lrt -static -lpthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3
lzbench Test: Zstd 1 - Process: Compression OpenBenchmarking.org MB/s, More Is Better lzbench 2017-08-08 Test: Zstd 1 - Process: Compression -O3 -march=skylake -O3 -march=skylake-avx512 -mprefer-vector-width=128 -O3 -march=skylake-avx512 -mprefer-vector-width=256 -O3 -march=skylake-avx512 -mprefer-vector-width=512 100 200 300 400 500 SE +/- 0.58, N = 3 451 451 452 452 1. (CXX) g++ options: -lrt -static -lpthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3
lzbench Test: Zstd 1 - Process: Decompression OpenBenchmarking.org MB/s, More Is Better lzbench 2017-08-08 Test: Zstd 1 - Process: Decompression -O3 -march=skylake -O3 -march=skylake-avx512 -mprefer-vector-width=256 -O3 -march=skylake-avx512 -mprefer-vector-width=128 -O3 -march=skylake-avx512 -mprefer-vector-width=512 200 400 600 800 1000 SE +/- 0.33, N = 3 SE +/- 0.58, N = 3 1137 1137 1138 1138 1. (CXX) g++ options: -lrt -static -lpthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3
lzbench Test: Brotli 0 - Process: Compression OpenBenchmarking.org MB/s, More Is Better lzbench 2017-08-08 Test: Brotli 0 - Process: Compression -O3 -march=skylake-avx512 -mprefer-vector-width=512 -O3 -march=skylake-avx512 -mprefer-vector-width=128 -O3 -march=skylake-avx512 -mprefer-vector-width=256 -O3 -march=skylake 90 180 270 360 450 SE +/- 1.67, N = 3 SE +/- 0.67, N = 3 SE +/- 0.67, N = 3 SE +/- 0.58, N = 3 428 429 429 430 1. (CXX) g++ options: -lrt -static -lpthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3
lzbench Test: Brotli 0 - Process: Decompression OpenBenchmarking.org MB/s, More Is Better lzbench 2017-08-08 Test: Brotli 0 - Process: Decompression -O3 -march=skylake -O3 -march=skylake-avx512 -mprefer-vector-width=128 -O3 -march=skylake-avx512 -mprefer-vector-width=256 -O3 -march=skylake-avx512 -mprefer-vector-width=512 130 260 390 520 650 SE +/- 1.00, N = 3 SE +/- 1.00, N = 3 SE +/- 0.58, N = 3 620 620 620 621 1. (CXX) g++ options: -lrt -static -lpthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3
lzbench Test: Libdeflate 1 - Process: Compression OpenBenchmarking.org MB/s, More Is Better lzbench 2017-08-08 Test: Libdeflate 1 - Process: Compression -O3 -march=skylake -O3 -march=skylake-avx512 -mprefer-vector-width=128 -O3 -march=skylake-avx512 -mprefer-vector-width=256 -O3 -march=skylake-avx512 -mprefer-vector-width=512 50 100 150 200 250 SE +/- 0.33, N = 3 248 249 249 249 1. (CXX) g++ options: -lrt -static -lpthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3
lzbench Test: Libdeflate 1 - Process: Decompression OpenBenchmarking.org MB/s, More Is Better lzbench 2017-08-08 Test: Libdeflate 1 - Process: Decompression -O3 -march=skylake -O3 -march=skylake-avx512 -mprefer-vector-width=128 -O3 -march=skylake-avx512 -mprefer-vector-width=256 -O3 -march=skylake-avx512 -mprefer-vector-width=512 300 600 900 1200 1500 SE +/- 0.33, N = 3 SE +/- 0.67, N = 3 SE +/- 0.67, N = 3 1189 1190 1191 1191 1. (CXX) g++ options: -lrt -static -lpthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3
MKL-DNN Harness: Deconvolution Batch deconv_1d - Data Type: f32 OpenBenchmarking.org ms, Fewer Is Better MKL-DNN 2019-04-16 Harness: Deconvolution Batch deconv_1d - Data Type: f32 -O3 -march=skylake-avx512 -mprefer-vector-width=512 -O3 -march=skylake -O3 -march=skylake-avx512 -mprefer-vector-width=128 -O3 -march=skylake-avx512 -mprefer-vector-width=256 6 12 18 24 30 SE +/- 0.22, N = 3 SE +/- 0.10, N = 3 SE +/- 0.17, N = 3 SE +/- 0.15, N = 3 23.07 23.03 23.01 22.93 MIN: 22.7 -march=skylake - MIN: 22.69 MIN: 22.68 MIN: 22.61 1. (CXX) g++ options: -O3 -std=c++11 -march=native -mtune=native -fPIC -fopenmp -pie -lmklml_intel -ldl
BLAKE2 OpenBenchmarking.org Cycles Per Byte, Fewer Is Better BLAKE2 20170307 -O3 -march=skylake-avx512 -mprefer-vector-width=512 -O3 -march=skylake-avx512 -mprefer-vector-width=256 -O3 -march=skylake-avx512 -mprefer-vector-width=128 -O3 -march=skylake 0.9045 1.809 2.7135 3.618 4.5225 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 4.02 4.02 4.02 4.02 1. (CC) gcc options: -O3 -march=native -lcrypto -lz
Botan Test: KASUMI - Encrypt OpenBenchmarking.org MiB/s, More Is Better Botan 2.8.0 Test: KASUMI - Encrypt -O3 -march=skylake -O3 -march=skylake-avx512 -mprefer-vector-width=256 -O3 -march=skylake-avx512 -mprefer-vector-width=128 -O3 -march=skylake-avx512 -mprefer-vector-width=512 20 40 60 80 100 SE +/- 0.04, N = 3 SE +/- 0.05, N = 3 SE +/- 0.04, N = 3 SE +/- 0.08, N = 3 96.02 96.21 96.22 96.25 1. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt
Botan Test: KASUMI - Decrypt OpenBenchmarking.org MiB/s, More Is Better Botan 2.8.0 Test: KASUMI - Decrypt -O3 -march=skylake -O3 -march=skylake-avx512 -mprefer-vector-width=256 -O3 -march=skylake-avx512 -mprefer-vector-width=128 -O3 -march=skylake-avx512 -mprefer-vector-width=512 20 40 60 80 100 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 SE +/- 0.04, N = 3 95.01 95.17 95.26 95.30 1. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt
MKL-DNN Harness: Convolution Batch conv_googlenet_v3 - Data Type: f32 OpenBenchmarking.org ms, Fewer Is Better MKL-DNN 2019-04-16 Harness: Convolution Batch conv_googlenet_v3 - Data Type: f32 -O3 -march=skylake -O3 -march=skylake-avx512 -mprefer-vector-width=512 -O3 -march=skylake-avx512 -mprefer-vector-width=256 -O3 -march=skylake-avx512 -mprefer-vector-width=128 160 320 480 640 800 SE +/- 0.92, N = 3 SE +/- 0.64, N = 3 SE +/- 0.50, N = 3 SE +/- 1.26, N = 3 752 751 751 749 -march=skylake - MIN: 744 MIN: 745 MIN: 744.39 MIN: 741.69 1. (CXX) g++ options: -O3 -std=c++11 -march=native -mtune=native -fPIC -fopenmp -pie -lmklml_intel -ldl
Botan Test: AES-256 - Encrypt OpenBenchmarking.org MiB/s, More Is Better Botan 2.8.0 Test: AES-256 - Encrypt -O3 -march=skylake-avx512 -mprefer-vector-width=256 -O3 -march=skylake-avx512 -mprefer-vector-width=512 -O3 -march=skylake-avx512 -mprefer-vector-width=128 -O3 -march=skylake 900 1800 2700 3600 4500 SE +/- 1.21, N = 3 SE +/- 1.37, N = 3 SE +/- 0.98, N = 3 SE +/- 0.41, N = 3 3833 3835 3847 4220 1. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt
Botan Test: Twofish - Encrypt OpenBenchmarking.org MiB/s, More Is Better Botan 2.8.0 Test: Twofish - Encrypt -O3 -march=skylake -O3 -march=skylake-avx512 -mprefer-vector-width=128 -O3 -march=skylake-avx512 -mprefer-vector-width=256 -O3 -march=skylake-avx512 -mprefer-vector-width=512 90 180 270 360 450 SE +/- 1.99, N = 3 SE +/- 0.12, N = 3 SE +/- 0.34, N = 3 SE +/- 0.17, N = 3 400 401 401 401 1. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt
Botan Test: Twofish - Decrypt OpenBenchmarking.org MiB/s, More Is Better Botan 2.8.0 Test: Twofish - Decrypt -O3 -march=skylake -O3 -march=skylake-avx512 -mprefer-vector-width=128 -O3 -march=skylake-avx512 -mprefer-vector-width=256 -O3 -march=skylake-avx512 -mprefer-vector-width=512 90 180 270 360 450 SE +/- 1.58, N = 3 SE +/- 0.13, N = 3 SE +/- 0.21, N = 3 SE +/- 0.07, N = 3 393 395 395 395 1. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt
Botan Test: Blowfish - Encrypt OpenBenchmarking.org MiB/s, More Is Better Botan 2.8.0 Test: Blowfish - Encrypt -O3 -march=skylake -O3 -march=skylake-avx512 -mprefer-vector-width=128 -O3 -march=skylake-avx512 -mprefer-vector-width=256 -O3 -march=skylake-avx512 -mprefer-vector-width=512 60 120 180 240 300 SE +/- 0.09, N = 3 SE +/- 0.22, N = 3 SE +/- 0.17, N = 3 SE +/- 0.03, N = 3 295 295 295 295 1. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt
Botan Test: Blowfish - Decrypt OpenBenchmarking.org MiB/s, More Is Better Botan 2.8.0 Test: Blowfish - Decrypt -O3 -march=skylake -O3 -march=skylake-avx512 -mprefer-vector-width=256 -O3 -march=skylake-avx512 -mprefer-vector-width=128 -O3 -march=skylake-avx512 -mprefer-vector-width=512 60 120 180 240 300 SE +/- 0.34, N = 3 SE +/- 0.18, N = 3 SE +/- 0.51, N = 3 SE +/- 0.03, N = 3 293 293 294 294 1. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt
Botan Test: CAST-256 - Encrypt OpenBenchmarking.org MiB/s, More Is Better Botan 2.8.0 Test: CAST-256 - Encrypt -O3 -march=skylake -O3 -march=skylake-avx512 -mprefer-vector-width=128 -O3 -march=skylake-avx512 -mprefer-vector-width=256 -O3 -march=skylake-avx512 -mprefer-vector-width=512 30 60 90 120 150 SE +/- 0.12, N = 3 SE +/- 0.11, N = 3 SE +/- 0.18, N = 3 SE +/- 0.06, N = 3 145 145 145 145 1. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt
Botan Test: CAST-256 - Decrypt OpenBenchmarking.org MiB/s, More Is Better Botan 2.8.0 Test: CAST-256 - Decrypt -O3 -march=skylake -O3 -march=skylake-avx512 -mprefer-vector-width=128 -O3 -march=skylake-avx512 -mprefer-vector-width=256 -O3 -march=skylake-avx512 -mprefer-vector-width=512 30 60 90 120 150 SE +/- 0.07, N = 3 SE +/- 0.08, N = 3 SE +/- 0.06, N = 3 SE +/- 0.04, N = 3 145 146 146 146 1. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt
FLAC Audio Encoding WAV To FLAC OpenBenchmarking.org Seconds, Fewer Is Better FLAC Audio Encoding 1.3.2 WAV To FLAC -O3 -march=skylake-avx512 -mprefer-vector-width=512 -O3 -march=skylake -O3 -march=skylake-avx512 -mprefer-vector-width=128 -O3 -march=skylake-avx512 -mprefer-vector-width=256 3 6 9 12 15 SE +/- 0.01, N = 5 SE +/- 0.00, N = 5 SE +/- 0.00, N = 5 SE +/- 0.01, N = 5 9.14 8.77 8.76 8.66 -march=skylake 1. (CXX) g++ options: -O3 -fvisibility=hidden -logg -lm
LAME MP3 Encoding WAV To MP3 OpenBenchmarking.org Seconds, Fewer Is Better LAME MP3 Encoding 3.100 WAV To MP3 -O3 -march=skylake-avx512 -mprefer-vector-width=512 -O3 -march=skylake -O3 -march=skylake-avx512 -mprefer-vector-width=256 -O3 -march=skylake-avx512 -mprefer-vector-width=128 3 6 9 12 15 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 10.19 9.32 9.30 9.05 -march=skylake 1. (CC) gcc options: -O3 -lncurses -lm
libjpeg-turbo tjbench Test: Decompression Throughput OpenBenchmarking.org Megapixels/sec, More Is Better libjpeg-turbo tjbench 1.5.3 Test: Decompression Throughput -O3 -march=skylake-avx512 -mprefer-vector-width=256 -O3 -march=skylake -O3 -march=skylake-avx512 -mprefer-vector-width=128 -O3 -march=skylake-avx512 -mprefer-vector-width=512 40 80 120 160 200 SE +/- 0.33, N = 3 SE +/- 0.06, N = 3 SE +/- 0.64, N = 3 SE +/- 0.42, N = 3 194 196 196 197 -march=skylake 1. (CC) gcc options: -O3 -lm
LuaJIT Test: Composite OpenBenchmarking.org Mflops, More Is Better LuaJIT 2.1-git Test: Composite -O3 -march=skylake-avx512 -mprefer-vector-width=128 -O3 -march=skylake -O3 -march=skylake-avx512 -mprefer-vector-width=256 -O3 -march=skylake-avx512 -mprefer-vector-width=512 300 600 900 1200 1500 SE +/- 0.83, N = 3 SE +/- 2.67, N = 3 SE +/- 5.01, N = 3 SE +/- 1.35, N = 3 1605 1606 1607 1608 -march=skylake 1. (CC) gcc options: -lm -ldl -O2 -fomit-frame-pointer -O3 -U_FORTIFY_SOURCE -fno-stack-protector
MKL-DNN Harness: IP Batch 1D - Data Type: f32 OpenBenchmarking.org ms, Fewer Is Better MKL-DNN 2019-04-16 Harness: IP Batch 1D - Data Type: f32 -O3 -march=skylake-avx512 -mprefer-vector-width=128 -O3 -march=skylake -O3 -march=skylake-avx512 -mprefer-vector-width=256 -O3 -march=skylake-avx512 -mprefer-vector-width=512 5 10 15 20 25 SE +/- 0.08, N = 3 SE +/- 0.08, N = 3 SE +/- 0.05, N = 3 SE +/- 0.04, N = 3 20.84 20.79 20.74 20.66 MIN: 19.89 -march=skylake - MIN: 19.84 MIN: 19.8 MIN: 19.73 1. (CXX) g++ options: -O3 -std=c++11 -march=native -mtune=native -fPIC -fopenmp -pie -lmklml_intel -ldl
FFTW Build: Stock - Size: 2D FFT Size 4096 OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Stock - Size: 2D FFT Size 4096 -O3 -march=skylake-avx512 -mprefer-vector-width=512 -O3 -march=skylake -O3 -march=skylake-avx512 -mprefer-vector-width=256 -O3 -march=skylake-avx512 -mprefer-vector-width=128 1500 3000 4500 6000 7500 SE +/- 31.31, N = 3 SE +/- 55.64, N = 3 SE +/- 19.27, N = 3 SE +/- 28.38, N = 3 5673 6327 6615 6863 -march=skylake 1. (CC) gcc options: -pthread -O3 -lm
FFTW Build: Float + SSE - Size: 2D FFT Size 4096 OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Float + SSE - Size: 2D FFT Size 4096 -O3 -march=skylake -O3 -march=skylake-avx512 -mprefer-vector-width=256 -O3 -march=skylake-avx512 -mprefer-vector-width=512 -O3 -march=skylake-avx512 -mprefer-vector-width=128 4K 8K 12K 16K 20K SE +/- 39.05, N = 3 SE +/- 90.51, N = 3 SE +/- 71.84, N = 3 SE +/- 111.64, N = 3 17183 17326 17334 17522 -march=skylake 1. (CC) gcc options: -pthread -O3 -lm
Timed HMMer Search Pfam Database Search OpenBenchmarking.org Seconds, Fewer Is Better Timed HMMer Search 2.3.2 Pfam Database Search -O3 -march=skylake-avx512 -mprefer-vector-width=512 -O3 -march=skylake-avx512 -mprefer-vector-width=256 -O3 -march=skylake -O3 -march=skylake-avx512 -mprefer-vector-width=128 0.873 1.746 2.619 3.492 4.365 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 SE +/- 0.03, N = 3 SE +/- 0.03, N = 3 3.88 3.50 3.49 3.40 -march=skylake 1. (CC) gcc options: -O3 -pthread -lhmmer -lsquid -lm
Timed MrBayes Analysis Primate Phylogeny Analysis OpenBenchmarking.org Seconds, Fewer Is Better Timed MrBayes Analysis 3.1.2 Primate Phylogeny Analysis -O3 -march=skylake -O3 -march=skylake-avx512 -mprefer-vector-width=512 -O3 -march=skylake-avx512 -mprefer-vector-width=256 -O3 -march=skylake-avx512 -mprefer-vector-width=128 15 30 45 60 75 SE +/- 0.03, N = 3 SE +/- 0.11, N = 3 SE +/- 0.07, N = 3 SE +/- 0.08, N = 3 65.67 65.66 63.20 63.06 -march=skylake 1. (CC) gcc options: -march=native -O3 -msse -mfpmath=sse -lm -pthread -lmpi
Himeno Benchmark Poisson Pressure Solver OpenBenchmarking.org MFLOPS, More Is Better Himeno Benchmark 3.0 Poisson Pressure Solver -O3 -march=skylake-avx512 -mprefer-vector-width=512 -O3 -march=skylake-avx512 -mprefer-vector-width=256 -O3 -march=skylake -O3 -march=skylake-avx512 -mprefer-vector-width=128 700 1400 2100 2800 3500 SE +/- 9.47, N = 3 SE +/- 4.67, N = 3 SE +/- 5.71, N = 3 SE +/- 2.31, N = 3 2814 3292 3302 3310 -march=skylake 1. (CC) gcc options: -O3 -mavx2
CloverLeaf Lagrangian-Eulerian Hydrodynamics OpenBenchmarking.org Seconds, Fewer Is Better CloverLeaf Lagrangian-Eulerian Hydrodynamics -O3 -march=skylake -O3 -march=skylake-avx512 -mprefer-vector-width=512 -O3 -march=skylake-avx512 -mprefer-vector-width=256 -O3 -march=skylake-avx512 -mprefer-vector-width=128 0.522 1.044 1.566 2.088 2.61 SE +/- 0.02, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 2.32 2.30 2.29 2.29 1. (F9X) gfortran options: -O3 -march=native -funroll-loops -fopenmp
Parboil Test: OpenMP LBM OpenBenchmarking.org Seconds, Fewer Is Better Parboil 2.5 Test: OpenMP LBM -O3 -march=skylake -O3 -march=skylake-avx512 -mprefer-vector-width=128 -O3 -march=skylake-avx512 -mprefer-vector-width=256 -O3 -march=skylake-avx512 -mprefer-vector-width=512 15 30 45 60 75 SE +/- 0.15, N = 3 SE +/- 0.04, N = 3 SE +/- 0.05, N = 3 SE +/- 0.07, N = 3 68.54 68.35 68.26 68.18 1. (CXX) g++ options: -lm -lpthread -lgomp -O3 -ffast-math -fopenmp
Parboil Test: OpenMP CUTCP OpenBenchmarking.org Seconds, Fewer Is Better Parboil 2.5 Test: OpenMP CUTCP -O3 -march=skylake-avx512 -mprefer-vector-width=512 -O3 -march=skylake-avx512 -mprefer-vector-width=256 -O3 -march=skylake-avx512 -mprefer-vector-width=128 -O3 -march=skylake 0.5423 1.0846 1.6269 2.1692 2.7115 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 2.41 2.38 2.38 2.38 1. (CXX) g++ options: -lm -lpthread -lgomp -O3 -ffast-math -fopenmp
MKL-DNN Harness: Deconvolution Batch deconv_all - Data Type: f32 OpenBenchmarking.org ms, Fewer Is Better MKL-DNN 2019-04-16 Harness: Deconvolution Batch deconv_all - Data Type: f32 -O3 -march=skylake -O3 -march=skylake-avx512 -mprefer-vector-width=512 -O3 -march=skylake-avx512 -mprefer-vector-width=256 -O3 -march=skylake-avx512 -mprefer-vector-width=128 2K 4K 6K 8K 10K SE +/- 15.77, N = 3 SE +/- 6.33, N = 3 SE +/- 5.96, N = 3 SE +/- 3.81, N = 3 10446 10424 10405 10397 -march=skylake - MIN: 10397.8 MIN: 10383.1 MIN: 10370.6 MIN: 10360.8 1. (CXX) g++ options: -O3 -std=c++11 -march=native -mtune=native -fPIC -fopenmp -pie -lmklml_intel -ldl
Botan Test: AES-256 - Decrypt OpenBenchmarking.org MiB/s, More Is Better Botan 2.8.0 Test: AES-256 - Decrypt -O3 -march=skylake-avx512 -mprefer-vector-width=512 -O3 -march=skylake-avx512 -mprefer-vector-width=128 -O3 -march=skylake-avx512 -mprefer-vector-width=256 -O3 -march=skylake 900 1800 2700 3600 4500 SE +/- 1.97, N = 3 SE +/- 2.47, N = 3 SE +/- 1.90, N = 3 SE +/- 0.57, N = 3 3839 3840 3855 4212 1. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt
Parboil Test: OpenMP Stencil OpenBenchmarking.org Seconds, Fewer Is Better Parboil 2.5 Test: OpenMP Stencil -O3 -march=skylake-avx512 -mprefer-vector-width=128 -O3 -march=skylake-avx512 -mprefer-vector-width=512 -O3 -march=skylake-avx512 -mprefer-vector-width=256 -O3 -march=skylake 2 4 6 8 10 SE +/- 0.04, N = 3 SE +/- 0.08, N = 3 SE +/- 0.01, N = 3 SE +/- 0.08, N = 3 7.98 7.80 7.77 7.74 1. (CXX) g++ options: -lm -lpthread -lgomp -O3 -ffast-math -fopenmp
Parboil Test: OpenMP MRI Gridding OpenBenchmarking.org Seconds, Fewer Is Better Parboil 2.5 Test: OpenMP MRI Gridding -O3 -march=skylake-avx512 -mprefer-vector-width=128 -O3 -march=skylake-avx512 -mprefer-vector-width=256 -O3 -march=skylake-avx512 -mprefer-vector-width=512 -O3 -march=skylake 30 60 90 120 150 SE +/- 0.73, N = 3 SE +/- 0.33, N = 3 SE +/- 0.63, N = 3 SE +/- 0.79, N = 3 135 134 132 132 1. (CXX) g++ options: -lm -lpthread -lgomp -O3 -ffast-math -fopenmp
NAS Parallel Benchmarks Test / Class: BT.A OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.3.1 Test / Class: BT.A -O3 -march=skylake -O3 -march=skylake-avx512 -mprefer-vector-width=512 -O3 -march=skylake-avx512 -mprefer-vector-width=128 -O3 -march=skylake-avx512 -mprefer-vector-width=256 1000 2000 3000 4000 5000 SE +/- 10.11, N = 3 SE +/- 4.76, N = 3 SE +/- 7.81, N = 3 SE +/- 9.00, N = 3 4391 4391 4773 4784 -march=skylake 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi 2. 3.2
NAS Parallel Benchmarks Test / Class: EP.C OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.3.1 Test / Class: EP.C -O3 -march=skylake -O3 -march=skylake-avx512 -mprefer-vector-width=128 -O3 -march=skylake-avx512 -mprefer-vector-width=256 -O3 -march=skylake-avx512 -mprefer-vector-width=512 500 1000 1500 2000 2500 SE +/- 71.82, N = 12 SE +/- 9.18, N = 3 SE +/- 6.91, N = 3 SE +/- 14.49, N = 3 2038 2090 2109 2113 -march=skylake 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi 2. 3.2
NAS Parallel Benchmarks Test / Class: FT.A OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.3.1 Test / Class: FT.A -O3 -march=skylake-avx512 -mprefer-vector-width=512 -O3 -march=skylake-avx512 -mprefer-vector-width=256 -O3 -march=skylake -O3 -march=skylake-avx512 -mprefer-vector-width=128 2K 4K 6K 8K 10K SE +/- 32.16, N = 3 SE +/- 16.12, N = 3 SE +/- 18.45, N = 3 SE +/- 15.81, N = 3 8543 8544 8581 8581 -march=skylake 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi 2. 3.2
NAS Parallel Benchmarks Test / Class: FT.B OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.3.1 Test / Class: FT.B -O3 -march=skylake-avx512 -mprefer-vector-width=256 -O3 -march=skylake-avx512 -mprefer-vector-width=128 -O3 -march=skylake -O3 -march=skylake-avx512 -mprefer-vector-width=512 2K 4K 6K 8K 10K SE +/- 39.71, N = 3 SE +/- 63.29, N = 3 SE +/- 11.85, N = 3 SE +/- 26.14, N = 3 9331 9337 9376 9387 -march=skylake 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi 2. 3.2
NAS Parallel Benchmarks Test / Class: LU.A OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.3.1 Test / Class: LU.A -O3 -march=skylake-avx512 -mprefer-vector-width=512 -O3 -march=skylake -O3 -march=skylake-avx512 -mprefer-vector-width=256 -O3 -march=skylake-avx512 -mprefer-vector-width=128 9K 18K 27K 36K 45K SE +/- 98.50, N = 3 SE +/- 40.23, N = 3 SE +/- 73.39, N = 3 SE +/- 36.60, N = 3 37305 37394 39343 39791 -march=skylake 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi 2. 3.2
NAS Parallel Benchmarks Test / Class: LU.C OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.3.1 Test / Class: LU.C -O3 -march=skylake -O3 -march=skylake-avx512 -mprefer-vector-width=512 -O3 -march=skylake-avx512 -mprefer-vector-width=128 -O3 -march=skylake-avx512 -mprefer-vector-width=256 7K 14K 21K 28K 35K SE +/- 62.55, N = 3 SE +/- 86.87, N = 3 SE +/- 79.15, N = 3 SE +/- 34.14, N = 3 33669 33676 34962 35007 -march=skylake 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi 2. 3.2
NAS Parallel Benchmarks Test / Class: SP.A OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.3.1 Test / Class: SP.A -O3 -march=skylake -O3 -march=skylake-avx512 -mprefer-vector-width=128 -O3 -march=skylake-avx512 -mprefer-vector-width=512 -O3 -march=skylake-avx512 -mprefer-vector-width=256 900 1800 2700 3600 4500 SE +/- 41.78, N = 3 SE +/- 7.44, N = 3 SE +/- 17.99, N = 3 SE +/- 38.60, N = 3 4062 4073 4080 4185 -march=skylake 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi 2. 3.2
Rodinia Test: OpenMP LavaMD OpenBenchmarking.org Seconds, Fewer Is Better Rodinia 2.4 Test: OpenMP LavaMD -O3 -march=skylake-avx512 -mprefer-vector-width=128 -O3 -march=skylake-avx512 -mprefer-vector-width=512 -O3 -march=skylake -O3 -march=skylake-avx512 -mprefer-vector-width=256 4 8 12 16 20 SE +/- 0.03, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 16.99 16.98 16.96 16.95 1. (CXX) g++ options: -O2 -lOpenCL
Rodinia Test: OpenMP CFD Solver OpenBenchmarking.org Seconds, Fewer Is Better Rodinia 2.4 Test: OpenMP CFD Solver -O3 -march=skylake-avx512 -mprefer-vector-width=512 -O3 -march=skylake -O3 -march=skylake-avx512 -mprefer-vector-width=128 -O3 -march=skylake-avx512 -mprefer-vector-width=256 3 6 9 12 15 SE +/- 0.10, N = 3 SE +/- 0.10, N = 3 SE +/- 0.10, N = 3 SE +/- 0.08, N = 3 11.71 11.52 11.47 11.31 1. (CXX) g++ options: -O2 -lOpenCL
Rodinia Test: OpenMP Streamcluster OpenBenchmarking.org Seconds, Fewer Is Better Rodinia 2.4 Test: OpenMP Streamcluster -O3 -march=skylake-avx512 -mprefer-vector-width=512 -O3 -march=skylake-avx512 -mprefer-vector-width=256 -O3 -march=skylake-avx512 -mprefer-vector-width=128 -O3 -march=skylake 4 8 12 16 20 SE +/- 0.20, N = 4 SE +/- 0.13, N = 15 SE +/- 0.11, N = 15 SE +/- 0.13, N = 15 14.12 13.88 13.72 13.63 1. (CXX) g++ options: -O2 -lOpenCL
Primesieve 1e12 Prime Number Generation OpenBenchmarking.org Seconds, Fewer Is Better Primesieve 7.4 1e12 Prime Number Generation -O3 -march=skylake-avx512 -mprefer-vector-width=512 -O3 -march=skylake-avx512 -mprefer-vector-width=128 -O3 -march=skylake -O3 -march=skylake-avx512 -mprefer-vector-width=256 3 6 9 12 15 SE +/- 0.04, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 12.96 12.80 12.79 12.78 -march=skylake 1. (CXX) g++ options: -O3 -lpthread
Xsbench OpenBenchmarking.org Lookups/s, More Is Better Xsbench 2017-07-06 -O3 -march=skylake-avx512 -mprefer-vector-width=256 -O3 -march=skylake -O3 -march=skylake-avx512 -mprefer-vector-width=512 -O3 -march=skylake-avx512 -mprefer-vector-width=128 1.1M 2.2M 3.3M 4.4M 5.5M SE +/- 24818.37, N = 3 SE +/- 5774.93, N = 3 SE +/- 5240.08, N = 3 SE +/- 3451.22, N = 3 5140078 5164164 5166043 5171354 1. (CC) gcc options: -std=gnu99 -fopenmp -O3 -lm
Stockfish Total Time OpenBenchmarking.org Nodes Per Second, More Is Better Stockfish 9 Total Time -O3 -march=skylake-avx512 -mprefer-vector-width=128 -O3 -march=skylake-avx512 -mprefer-vector-width=512 -O3 -march=skylake-avx512 -mprefer-vector-width=256 -O3 -march=skylake 10M 20M 30M 40M 50M SE +/- 146682.07, N = 3 SE +/- 311424.12, N = 3 SE +/- 342455.58, N = 3 SE +/- 407607.78, N = 3 46810779 46997822 47046623 47112136 -march=skylake 1. (CXX) g++ options: -m64 -lpthread -O3 -fno-exceptions -std=c++11 -pedantic -msse -msse3 -mpopcnt -flto
7-Zip Compression Compress Speed Test OpenBenchmarking.org MIPS, More Is Better 7-Zip Compression 16.02 Compress Speed Test -O3 -march=skylake-avx512 -mprefer-vector-width=128 -O3 -march=skylake-avx512 -mprefer-vector-width=256 -O3 -march=skylake -O3 -march=skylake-avx512 -mprefer-vector-width=512 20K 40K 60K 80K 100K SE +/- 264.40, N = 3 SE +/- 414.93, N = 3 SE +/- 201.98, N = 3 SE +/- 174.10, N = 3 99546 99960 100157 100416 1. (CXX) g++ options: -pipe -lpthread
Timed PHP Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed PHP Compilation 7.1.9 Time To Compile -O3 -march=skylake-avx512 -mprefer-vector-width=512 -O3 -march=skylake-avx512 -mprefer-vector-width=256 -O3 -march=skylake-avx512 -mprefer-vector-width=128 -O3 -march=skylake 12 24 36 48 60 SE +/- 0.05, N = 3 SE +/- 0.08, N = 3 SE +/- 0.15, N = 3 SE +/- 0.08, N = 3 52.19 51.90 51.84 51.80 -march=skylake 1. (CC) gcc options: -O3 -pedantic -ldl -lz -lm
Zstd Compression Compressing ubuntu-16.04.3-server-i386.img, Compression Level 19 OpenBenchmarking.org Seconds, Fewer Is Better Zstd Compression 1.3.4 Compressing ubuntu-16.04.3-server-i386.img, Compression Level 19 -O3 -march=skylake-avx512 -mprefer-vector-width=512 -O3 -march=skylake -O3 -march=skylake-avx512 -mprefer-vector-width=256 -O3 -march=skylake-avx512 -mprefer-vector-width=128 3 6 9 12 15 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 9.76 9.71 9.69 9.59 -march=skylake 1. (CC) gcc options: -O3 -pthread -lz
m-queens Time To Solve OpenBenchmarking.org Seconds, Fewer Is Better m-queens 1.2 Time To Solve -O3 -march=skylake-avx512 -mprefer-vector-width=128 -O3 -march=skylake -O3 -march=skylake-avx512 -mprefer-vector-width=512 -O3 -march=skylake-avx512 -mprefer-vector-width=256 11 22 33 44 55 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 48.42 48.42 48.41 48.40 -march=skylake 1. (CXX) g++ options: -fopenmp -O3 -O2 -march=native
Cpuminer-Opt Algorithm: m7m OpenBenchmarking.org kH/s - Hash Speed, More Is Better Cpuminer-Opt 3.8.8.1 Algorithm: m7m -O3 -march=skylake-avx512 -mprefer-vector-width=512 -O3 -march=skylake -O3 -march=skylake-avx512 -mprefer-vector-width=128 -O3 -march=skylake-avx512 -mprefer-vector-width=256 110 220 330 440 550 SE +/- 1.44, N = 3 SE +/- 1.19, N = 3 SE +/- 1.28, N = 3 SE +/- 0.55, N = 3 479 499 503 506 -march=skylake 1. (CXX) g++ options: -O3 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
Cpuminer-Opt Algorithm: deep OpenBenchmarking.org kH/s - Hash Speed, More Is Better Cpuminer-Opt 3.8.8.1 Algorithm: deep -O3 -march=skylake-avx512 -mprefer-vector-width=512 -O3 -march=skylake -O3 -march=skylake-avx512 -mprefer-vector-width=256 -O3 -march=skylake-avx512 -mprefer-vector-width=128 3K 6K 9K 12K 15K SE +/- 65.06, N = 3 SE +/- 21.86, N = 3 SE +/- 15.28, N = 3 SE +/- 31.80, N = 3 14490 15323 15490 15497 -march=skylake 1. (CXX) g++ options: -O3 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
Cpuminer-Opt Algorithm: lbry OpenBenchmarking.org kH/s - Hash Speed, More Is Better Cpuminer-Opt 3.8.8.1 Algorithm: lbry -O3 -march=skylake -O3 -march=skylake-avx512 -mprefer-vector-width=128 -O3 -march=skylake-avx512 -mprefer-vector-width=256 -O3 -march=skylake-avx512 -mprefer-vector-width=512 11K 22K 33K 44K 55K SE +/- 3.33, N = 3 SE +/- 41.77, N = 3 SE +/- 283.57, N = 3 SE +/- 706.79, N = 4 48547 52793 53473 53620 -march=skylake 1. (CXX) g++ options: -O3 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
Cpuminer-Opt Algorithm: skein OpenBenchmarking.org kH/s - Hash Speed, More Is Better Cpuminer-Opt 3.8.8.1 Algorithm: skein -O3 -march=skylake -O3 -march=skylake-avx512 -mprefer-vector-width=512 -O3 -march=skylake-avx512 -mprefer-vector-width=256 -O3 -march=skylake-avx512 -mprefer-vector-width=128 13K 26K 39K 52K 65K SE +/- 3.33, N = 3 SE +/- 1026.67, N = 3 SE +/- 955.00, N = 3 SE +/- 678.39, N = 3 56227 62027 62560 62813 -march=skylake 1. (CXX) g++ options: -O3 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
Cpuminer-Opt Algorithm: myr-gr OpenBenchmarking.org kH/s - Hash Speed, More Is Better Cpuminer-Opt 3.8.8.1 Algorithm: myr-gr -O3 -march=skylake-avx512 -mprefer-vector-width=512 -O3 -march=skylake-avx512 -mprefer-vector-width=128 -O3 -march=skylake-avx512 -mprefer-vector-width=256 -O3 -march=skylake 4K 8K 12K 16K 20K SE +/- 32.15, N = 3 SE +/- 92.92, N = 3 SE +/- 219.87, N = 4 SE +/- 76.38, N = 3 15310 15560 15695 16360 -march=skylake 1. (CXX) g++ options: -O3 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
Cpuminer-Opt Algorithm: sha256t OpenBenchmarking.org kH/s - Hash Speed, More Is Better Cpuminer-Opt 3.8.8.1 Algorithm: sha256t -O3 -march=skylake-avx512 -mprefer-vector-width=256 -O3 -march=skylake-avx512 -mprefer-vector-width=512 -O3 -march=skylake-avx512 -mprefer-vector-width=128 -O3 -march=skylake 30K 60K 90K 120K 150K SE +/- 240.62, N = 3 SE +/- 661.72, N = 3 SE +/- 1469.65, N = 6 SE +/- 3.33, N = 3 124030 124567 124672 125653 -march=skylake 1. (CXX) g++ options: -O3 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
Timed Linux Kernel Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed Linux Kernel Compilation 4.18 Time To Compile -O3 -march=skylake-avx512 -mprefer-vector-width=512 -O3 -march=skylake-avx512 -mprefer-vector-width=256 -O3 -march=skylake -O3 -march=skylake-avx512 -mprefer-vector-width=128 9 18 27 36 45 SE +/- 0.53, N = 4 SE +/- 0.53, N = 4 SE +/- 0.38, N = 8 SE +/- 0.38, N = 8 37.36 36.93 36.34 36.33
AOBench Size: 2048 x 2048 - Total Time OpenBenchmarking.org Seconds, Fewer Is Better AOBench Size: 2048 x 2048 - Total Time -O3 -march=skylake-avx512 -mprefer-vector-width=512 -O3 -march=skylake -O3 -march=skylake-avx512 -mprefer-vector-width=128 -O3 -march=skylake-avx512 -mprefer-vector-width=256 7 14 21 28 35 SE +/- 0.15, N = 3 SE +/- 0.01, N = 3 SE +/- 0.06, N = 3 SE +/- 0.04, N = 3 31.29 31.17 31.15 31.11 -march=skylake 1. (CC) gcc options: -lm -O3
GraphicsMagick Operation: Swirl OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.30 Operation: Swirl -O3 -march=skylake-avx512 -mprefer-vector-width=512 -O3 -march=skylake-avx512 -mprefer-vector-width=128 -O3 -march=skylake-avx512 -mprefer-vector-width=256 -O3 -march=skylake 60 120 180 240 300 SE +/- 1.00, N = 3 SE +/- 1.33, N = 3 SE +/- 0.33, N = 3 228 251 251 252 -march=skylake 1. (CC) gcc options: -fopenmp -O3 -pthread -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -lbz2 -lz -lm -lgomp -lpthread
GraphicsMagick Operation: Rotate OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.30 Operation: Rotate -O3 -march=skylake-avx512 -mprefer-vector-width=512 -O3 -march=skylake-avx512 -mprefer-vector-width=128 -O3 -march=skylake-avx512 -mprefer-vector-width=256 -O3 -march=skylake 60 120 180 240 300 SE +/- 1.00, N = 3 250 290 290 291 -march=skylake 1. (CC) gcc options: -fopenmp -O3 -pthread -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -lbz2 -lz -lm -lgomp -lpthread
GraphicsMagick Operation: Sharpen OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.30 Operation: Sharpen -O3 -march=skylake-avx512 -mprefer-vector-width=512 -O3 -march=skylake -O3 -march=skylake-avx512 -mprefer-vector-width=256 -O3 -march=skylake-avx512 -mprefer-vector-width=128 50 100 150 200 250 SE +/- 0.33, N = 3 SE +/- 0.33, N = 3 SE +/- 0.33, N = 3 186 204 206 207 -march=skylake 1. (CC) gcc options: -fopenmp -O3 -pthread -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -lbz2 -lz -lm -lgomp -lpthread
GraphicsMagick Operation: Enhanced OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.30 Operation: Enhanced -O3 -march=skylake-avx512 -mprefer-vector-width=512 -O3 -march=skylake-avx512 -mprefer-vector-width=256 -O3 -march=skylake-avx512 -mprefer-vector-width=128 -O3 -march=skylake 50 100 150 200 250 SE +/- 0.33, N = 3 196 224 225 227 -march=skylake 1. (CC) gcc options: -fopenmp -O3 -pthread -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -lbz2 -lz -lm -lgomp -lpthread
GraphicsMagick Operation: Resizing OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.30 Operation: Resizing -O3 -march=skylake-avx512 -mprefer-vector-width=512 -O3 -march=skylake-avx512 -mprefer-vector-width=256 -O3 -march=skylake -O3 -march=skylake-avx512 -mprefer-vector-width=128 60 120 180 240 300 SE +/- 0.58, N = 3 243 275 277 277 -march=skylake 1. (CC) gcc options: -fopenmp -O3 -pthread -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -lbz2 -lz -lm -lgomp -lpthread
GraphicsMagick Operation: Noise-Gaussian OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.30 Operation: Noise-Gaussian -O3 -march=skylake-avx512 -mprefer-vector-width=512 -O3 -march=skylake-avx512 -mprefer-vector-width=128 -O3 -march=skylake -O3 -march=skylake-avx512 -mprefer-vector-width=256 40 80 120 160 200 SE +/- 0.67, N = 3 195 197 198 198 -march=skylake 1. (CC) gcc options: -fopenmp -O3 -pthread -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -lbz2 -lz -lm -lgomp -lpthread
GraphicsMagick Operation: HWB Color Space OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.30 Operation: HWB Color Space -O3 -march=skylake-avx512 -mprefer-vector-width=512 -O3 -march=skylake -O3 -march=skylake-avx512 -mprefer-vector-width=256 -O3 -march=skylake-avx512 -mprefer-vector-width=128 60 120 180 240 300 SE +/- 0.67, N = 3 SE +/- 0.33, N = 3 253 288 288 289 -march=skylake 1. (CC) gcc options: -fopenmp -O3 -pthread -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -lbz2 -lz -lm -lgomp -lpthread
SVT-VP9 1080p 8-bit YUV To VP9 Video Encode OpenBenchmarking.org Frames Per Second, More Is Better SVT-VP9 2019-02-17 1080p 8-bit YUV To VP9 Video Encode -O3 -march=skylake-avx512 -mprefer-vector-width=512 -O3 -march=skylake -O3 -march=skylake-avx512 -mprefer-vector-width=128 -O3 -march=skylake-avx512 -mprefer-vector-width=256 80 160 240 320 400 SE +/- 4.48, N = 5 SE +/- 4.85, N = 4 SE +/- 4.39, N = 4 SE +/- 5.15, N = 4 337 342 346 347 -march=skylake 1. (CC) gcc options: -O3 -fPIE -fPIC -O2 -flto -fvisibility=hidden -mavx -pie -rdynamic -lpthread -lrt -lm
x264 H.264 Video Encoding OpenBenchmarking.org Frames Per Second, More Is Better x264 2018-09-25 H.264 Video Encoding -O3 -march=skylake -O3 -march=skylake-avx512 -mprefer-vector-width=128 -O3 -march=skylake-avx512 -mprefer-vector-width=256 -O3 -march=skylake-avx512 -mprefer-vector-width=512 30 60 90 120 150 SE +/- 1.19, N = 3 SE +/- 1.54, N = 3 SE +/- 1.37, N = 3 SE +/- 1.04, N = 3 139 140 140 140 -march=skylake 1. (CC) gcc options: -ldl -m64 -lm -lpthread -O3 -ffast-math -std=gnu99 -fPIC -fomit-frame-pointer -fno-tree-vectorize
dav1d Video Input: Summer Nature 4K OpenBenchmarking.org Seconds, Fewer Is Better dav1d 0.3 Video Input: Summer Nature 4K -O3 -march=skylake-avx512 -mprefer-vector-width=512 -O3 -march=skylake-avx512 -mprefer-vector-width=128 -O3 -march=skylake-avx512 -mprefer-vector-width=256 -O3 -march=skylake 5 10 15 20 25 SE +/- 0.06, N = 3 SE +/- 0.04, N = 3 SE +/- 0.06, N = 3 SE +/- 0.05, N = 3 19.67 19.47 19.34 19.15 -march=skylake 1. (CC) gcc options: -O3 -pthread
dav1d Video Input: Summer Nature 1080p OpenBenchmarking.org Seconds, Fewer Is Better dav1d 0.3 Video Input: Summer Nature 1080p -O3 -march=skylake-avx512 -mprefer-vector-width=512 -O3 -march=skylake-avx512 -mprefer-vector-width=128 -O3 -march=skylake-avx512 -mprefer-vector-width=256 -O3 -march=skylake 2 4 6 8 10 SE +/- 0.05, N = 3 SE +/- 0.03, N = 3 SE +/- 0.04, N = 3 SE +/- 0.05, N = 3 7.05 6.97 6.95 6.93 -march=skylake 1. (CC) gcc options: -O3 -pthread
SVT-AV1 1080p 8-bit YUV To AV1 Video Encode OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 2019-03-07 1080p 8-bit YUV To AV1 Video Encode -O3 -march=skylake-avx512 -mprefer-vector-width=256 -O3 -march=skylake-avx512 -mprefer-vector-width=128 -O3 -march=skylake-avx512 -mprefer-vector-width=512 -O3 -march=skylake 6 12 18 24 30 SE +/- 0.10, N = 3 SE +/- 0.05, N = 3 SE +/- 0.07, N = 3 SE +/- 0.14, N = 3 24.34 24.37 24.43 24.44 -march=skylake 1. (CXX) g++ options: -O3 -pie -lpthread -lm
x265 H.265 1080p Video Encoding OpenBenchmarking.org Frames Per Second, More Is Better x265 3.0 H.265 1080p Video Encoding -O3 -march=skylake-avx512 -mprefer-vector-width=512 -O3 -march=skylake-avx512 -mprefer-vector-width=128 -O3 -march=skylake -O3 -march=skylake-avx512 -mprefer-vector-width=256 12 24 36 48 60 SE +/- 0.05, N = 3 SE +/- 0.21, N = 3 SE +/- 0.25, N = 3 SE +/- 0.07, N = 3 50.05 53.34 53.71 53.97 -march=skylake 1. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma
C-Ray Total Time - 4K, 16 Rays Per Pixel OpenBenchmarking.org Seconds, Fewer Is Better C-Ray 1.1 Total Time - 4K, 16 Rays Per Pixel -O3 -march=skylake-avx512 -mprefer-vector-width=512 -O3 -march=skylake-avx512 -mprefer-vector-width=256 -O3 -march=skylake-avx512 -mprefer-vector-width=128 -O3 -march=skylake 8 16 24 32 40 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 SE +/- 0.06, N = 3 35.86 33.47 33.34 30.87 -march=skylake 1. (CC) gcc options: -lm -lpthread -O3
TTSIOD 3D Renderer Phong Rendering With Soft-Shadow Mapping OpenBenchmarking.org FPS, More Is Better TTSIOD 3D Renderer 2.3b Phong Rendering With Soft-Shadow Mapping -O3 -march=skylake-avx512 -mprefer-vector-width=512 -O3 -march=skylake -O3 -march=skylake-avx512 -mprefer-vector-width=256 -O3 -march=skylake-avx512 -mprefer-vector-width=128 160 320 480 640 800 SE +/- 0.52, N = 3 SE +/- 1.31, N = 3 SE +/- 7.91, N = 7 SE +/- 1.58, N = 3 669 710 729 738 -march=skylake 1. (CXX) g++ options: -O3 -fomit-frame-pointer -ffast-math -mtune=native -flto -msse -mrecip -mfpmath=sse -msse2 -mssse3 -lSDL -lpthread -fopenmp -fwhole-program -lstdc++
SVT-HEVC 1080p 8-bit YUV To HEVC Video Encode OpenBenchmarking.org Frames Per Second, More Is Better SVT-HEVC 2019-02-03 1080p 8-bit YUV To HEVC Video Encode -O3 -march=skylake -O3 -march=skylake-avx512 -mprefer-vector-width=512 -O3 -march=skylake-avx512 -mprefer-vector-width=256 -O3 -march=skylake-avx512 -mprefer-vector-width=128 70 140 210 280 350 SE +/- 3.61, N = 3 SE +/- 3.22, N = 3 SE +/- 3.64, N = 3 SE +/- 2.96, N = 3 304 304 337 339 -march=skylake 1. (CC) gcc options: -O3 -fPIE -fPIC -O2 -flto -fvisibility=hidden -march=native -pie -rdynamic -lpthread -lrt
FFmpeg H.264 HD To NTSC DV OpenBenchmarking.org Seconds, Fewer Is Better FFmpeg 4.0.2 H.264 HD To NTSC DV -O3 -march=skylake-avx512 -mprefer-vector-width=128 -O3 -march=skylake-avx512 -mprefer-vector-width=256 -O3 -march=skylake-avx512 -mprefer-vector-width=512 -O3 -march=skylake 1.2375 2.475 3.7125 4.95 6.1875 SE +/- 0.02, N = 3 SE +/- 0.03, N = 3 SE +/- 0.03, N = 3 SE +/- 0.02, N = 3 5.50 5.47 5.45 5.45 -march=skylake 1. (CC) gcc options: -lavdevice -lavfilter -lavformat -lavcodec -lswresample -lswscale -lavutil -lXv -lX11 -lXext -lm -lxcb -lxcb-shm -lxcb-shape -lxcb-xfixes -pthread -lSDL2 -lbz2 -O3 -std=c11 -fomit-frame-pointer -fPIC -fno-math-errno -fno-signed-zeros -fno-tree-vectorize -MMD -MF -MT
Memcached mcperf Method: Add OpenBenchmarking.org Operations Per Second, More Is Better Memcached mcperf 1.5.10 Method: Add -O3 -march=skylake -O3 -march=skylake-avx512 -mprefer-vector-width=256 -O3 -march=skylake-avx512 -mprefer-vector-width=128 -O3 -march=skylake-avx512 -mprefer-vector-width=512 16K 32K 48K 64K 80K SE +/- 582.90, N = 3 SE +/- 163.23, N = 3 SE +/- 259.01, N = 3 SE +/- 622.40, N = 3 72123 72947 73307 73346 -march=skylake 1. (CC) gcc options: -O3 -lm -rdynamic
Memcached mcperf Method: Get OpenBenchmarking.org Operations Per Second, More Is Better Memcached mcperf 1.5.10 Method: Get -O3 -march=skylake-avx512 -mprefer-vector-width=128 -O3 -march=skylake-avx512 -mprefer-vector-width=512 -O3 -march=skylake -O3 -march=skylake-avx512 -mprefer-vector-width=256 30K 60K 90K 120K 150K SE +/- 876.94, N = 3 SE +/- 1768.29, N = 15 SE +/- 1600.60, N = 15 SE +/- 1645.69, N = 15 107497 112844 117212 117621 -march=skylake 1. (CC) gcc options: -O3 -lm -rdynamic
Memcached mcperf Method: Set OpenBenchmarking.org Operations Per Second, More Is Better Memcached mcperf 1.5.10 Method: Set -O3 -march=skylake -O3 -march=skylake-avx512 -mprefer-vector-width=256 -O3 -march=skylake-avx512 -mprefer-vector-width=512 -O3 -march=skylake-avx512 -mprefer-vector-width=128 16K 32K 48K 64K 80K SE +/- 335.26, N = 3 SE +/- 384.96, N = 3 SE +/- 141.11, N = 3 SE +/- 429.23, N = 3 72585 72688 72940 73045 -march=skylake 1. (CC) gcc options: -O3 -lm -rdynamic
Memcached mcperf Method: Append OpenBenchmarking.org Operations Per Second, More Is Better Memcached mcperf 1.5.10 Method: Append -O3 -march=skylake-avx512 -mprefer-vector-width=256 -O3 -march=skylake-avx512 -mprefer-vector-width=512 -O3 -march=skylake-avx512 -mprefer-vector-width=128 -O3 -march=skylake 20K 40K 60K 80K 100K SE +/- 182.38, N = 3 SE +/- 290.53, N = 3 SE +/- 510.45, N = 3 SE +/- 495.69, N = 3 77703 77932 78021 78294 -march=skylake 1. (CC) gcc options: -O3 -lm -rdynamic
Memcached mcperf Method: Delete OpenBenchmarking.org Operations Per Second, More Is Better Memcached mcperf 1.5.10 Method: Delete -O3 -march=skylake-avx512 -mprefer-vector-width=256 -O3 -march=skylake-avx512 -mprefer-vector-width=512 -O3 -march=skylake -O3 -march=skylake-avx512 -mprefer-vector-width=128 30K 60K 90K 120K 150K SE +/- 1539.98, N = 15 SE +/- 1672.82, N = 15 SE +/- 1837.94, N = 3 SE +/- 1623.43, N = 4 114714 115719 120897 122131 -march=skylake 1. (CC) gcc options: -O3 -lm -rdynamic
Memcached mcperf Method: Prepend OpenBenchmarking.org Operations Per Second, More Is Better Memcached mcperf 1.5.10 Method: Prepend -O3 -march=skylake -O3 -march=skylake-avx512 -mprefer-vector-width=128 -O3 -march=skylake-avx512 -mprefer-vector-width=256 -O3 -march=skylake-avx512 -mprefer-vector-width=512 20K 40K 60K 80K 100K SE +/- 755.85, N = 3 SE +/- 109.89, N = 3 SE +/- 428.91, N = 3 SE +/- 121.74, N = 3 77484 77547 79076 79234 -march=skylake 1. (CC) gcc options: -O3 -lm -rdynamic
Memcached mcperf Method: Replace OpenBenchmarking.org Operations Per Second, More Is Better Memcached mcperf 1.5.10 Method: Replace -O3 -march=skylake-avx512 -mprefer-vector-width=256 -O3 -march=skylake-avx512 -mprefer-vector-width=128 -O3 -march=skylake -O3 -march=skylake-avx512 -mprefer-vector-width=512 20K 40K 60K 80K 100K SE +/- 642.32, N = 3 SE +/- 549.37, N = 3 SE +/- 240.24, N = 3 SE +/- 216.99, N = 3 77373 78432 78460 78798 -march=skylake 1. (CC) gcc options: -O3 -lm -rdynamic
NGINX Benchmark Static Web Page Serving OpenBenchmarking.org Requests Per Second, More Is Better NGINX Benchmark 1.9.9 Static Web Page Serving -O3 -march=skylake-avx512 -mprefer-vector-width=512 -O3 -march=skylake-avx512 -mprefer-vector-width=128 -O3 -march=skylake -O3 -march=skylake-avx512 -mprefer-vector-width=256 11K 22K 33K 44K 55K SE +/- 88.86, N = 3 SE +/- 834.73, N = 15 SE +/- 643.64, N = 15 SE +/- 314.76, N = 3 44072 46938 47570 49221 -march=skylake 1. (CC) gcc options: -lpthread -lcrypt -lcrypto -lz -O3 -march=native
Apache Benchmark Static Web Page Serving OpenBenchmarking.org Requests Per Second, More Is Better Apache Benchmark 2.4.29 Static Web Page Serving -O3 -march=skylake-avx512 -mprefer-vector-width=512 -O3 -march=skylake-avx512 -mprefer-vector-width=256 -O3 -march=skylake-avx512 -mprefer-vector-width=128 -O3 -march=skylake 8K 16K 24K 32K 40K SE +/- 36.99, N = 3 SE +/- 63.22, N = 3 SE +/- 144.00, N = 3 SE +/- 52.04, N = 3 33240 35946 35982 36040 -march=skylake 1. (CC) gcc options: -shared -fPIC -pthread -O3
Redis Test: LPOP OpenBenchmarking.org Requests Per Second, More Is Better Redis 4.0.8 Test: LPOP -O3 -march=skylake-avx512 -mprefer-vector-width=512 -O3 -march=skylake-avx512 -mprefer-vector-width=128 -O3 -march=skylake-avx512 -mprefer-vector-width=256 -O3 -march=skylake 700K 1400K 2100K 2800K 3500K SE +/- 59550.07, N = 15 SE +/- 71217.78, N = 12 SE +/- 61579.63, N = 15 SE +/- 55290.27, N = 15 3059844 3095145 3139485 3140283 1. (CC) gcc options: -ggdb -rdynamic -lm -ldl -pthread
Redis Test: SADD OpenBenchmarking.org Requests Per Second, More Is Better Redis 4.0.8 Test: SADD -O3 -march=skylake -O3 -march=skylake-avx512 -mprefer-vector-width=512 -O3 -march=skylake-avx512 -mprefer-vector-width=256 -O3 -march=skylake-avx512 -mprefer-vector-width=128 600K 1200K 1800K 2400K 3000K SE +/- 33796.90, N = 15 SE +/- 50359.83, N = 15 SE +/- 56601.20, N = 15 SE +/- 20507.83, N = 3 2339849 2383273 2449355 2624995 1. (CC) gcc options: -ggdb -rdynamic -lm -ldl -pthread
Redis Test: LPUSH OpenBenchmarking.org Requests Per Second, More Is Better Redis 4.0.8 Test: LPUSH -O3 -march=skylake-avx512 -mprefer-vector-width=128 -O3 -march=skylake-avx512 -mprefer-vector-width=256 -O3 -march=skylake-avx512 -mprefer-vector-width=512 -O3 -march=skylake 400K 800K 1200K 1600K 2000K SE +/- 36055.36, N = 15 SE +/- 32556.93, N = 15 SE +/- 36075.54, N = 15 SE +/- 34258.37, N = 15 1962269 2013442 2026656 2059237 1. (CC) gcc options: -ggdb -rdynamic -lm -ldl -pthread
Redis Test: GET OpenBenchmarking.org Requests Per Second, More Is Better Redis 4.0.8 Test: GET -O3 -march=skylake-avx512 -mprefer-vector-width=256 -O3 -march=skylake -O3 -march=skylake-avx512 -mprefer-vector-width=128 -O3 -march=skylake-avx512 -mprefer-vector-width=512 600K 1200K 1800K 2400K 3000K SE +/- 56848.49, N = 15 SE +/- 45086.74, N = 15 SE +/- 54716.38, N = 15 SE +/- 58238.45, N = 15 2944968 2958563 2992962 3002750 1. (CC) gcc options: -ggdb -rdynamic -lm -ldl -pthread
Redis Test: SET OpenBenchmarking.org Requests Per Second, More Is Better Redis 4.0.8 Test: SET -O3 -march=skylake-avx512 -mprefer-vector-width=256 -O3 -march=skylake-avx512 -mprefer-vector-width=512 -O3 -march=skylake -O3 -march=skylake-avx512 -mprefer-vector-width=128 500K 1000K 1500K 2000K 2500K SE +/- 25293.75, N = 3 SE +/- 44027.91, N = 15 SE +/- 42954.48, N = 15 SE +/- 38284.96, N = 15 1971745 2135179 2163293 2189741 1. (CC) gcc options: -ggdb -rdynamic -lm -ldl -pthread
PostgreSQL pgbench Scaling: Buffer Test - Test: Normal Load - Mode: Read Only OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 10.3 Scaling: Buffer Test - Test: Normal Load - Mode: Read Only -O3 -march=skylake-avx512 -mprefer-vector-width=512 -O3 -march=skylake-avx512 -mprefer-vector-width=128 -O3 -march=skylake -O3 -march=skylake-avx512 -mprefer-vector-width=256 110K 220K 330K 440K 550K SE +/- 1960.25, N = 3 SE +/- 772.32, N = 3 SE +/- 1607.28, N = 3 SE +/- 2392.99, N = 3 498539 519930 520100 521901 -march=skylake 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O3 -lpgcommon -lpgport -lpq -lpthread -lrt -lcrypt -ldl -lm
PostgreSQL pgbench Scaling: Buffer Test - Test: Normal Load - Mode: Read Write OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 10.3 Scaling: Buffer Test - Test: Normal Load - Mode: Read Write -O3 -march=skylake -O3 -march=skylake-avx512 -mprefer-vector-width=512 -O3 -march=skylake-avx512 -mprefer-vector-width=128 -O3 -march=skylake-avx512 -mprefer-vector-width=256 3K 6K 9K 12K 15K SE +/- 128.04, N = 3 SE +/- 82.67, N = 3 SE +/- 44.82, N = 3 SE +/- 45.37, N = 3 13311 13424 13495 13576 -march=skylake 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O3 -lpgcommon -lpgport -lpq -lpthread -lrt -lcrypt -ldl -lm
PolyBench-C Test: 3 Matrix Multiplications OpenBenchmarking.org Seconds, Fewer Is Better PolyBench-C 4.2 Test: 3 Matrix Multiplications -O3 -march=skylake -O3 -march=skylake-avx512 -mprefer-vector-width=512 -O3 -march=skylake-avx512 -mprefer-vector-width=256 -O3 -march=skylake-avx512 -mprefer-vector-width=128 0.594 1.188 1.782 2.376 2.97 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 2.64 2.63 2.63 2.61 -march=skylake 1. (CC) gcc options: -O3 -march=native
Geometric Mean Of All Test Results Result Composite - Core i9 7980XE GCC 9 Compiler Benchmarks OpenBenchmarking.org Geometric Mean, More Is Better Geometric Mean Of All Test Results Result Composite - Core i9 7980XE GCC 9 Compiler Benchmarks -O3 -march=skylake-avx512 -mprefer-vector-width=512 -O3 -march=skylake -O3 -march=skylake-avx512 -mprefer-vector-width=256 -O3 -march=skylake-avx512 -mprefer-vector-width=128 90 180 270 360 450 405.16 414.04 415.02 415.90
Phoronix Test Suite v10.8.4