AMD Ryzen Threadripper GCC 10 PGO benchmarks by Michael Larabel for a future article.
Compare your own system(s) to this result file with the
Phoronix Test Suite by running the command:
phoronix-test-suite benchmark 1912222-PTS-GCC10AMD29 GCC 10 AMD Threadripper 3960X PGO Optimization - Phoronix Test Suite GCC 10 AMD Threadripper 3960X PGO Optimization AMD Ryzen Threadripper GCC 10 PGO benchmarks by Michael Larabel for a future article.
HTML result view exported from: https://openbenchmarking.org/result/1912222-PTS-GCC10AMD29&sro&grs .
GCC 10 AMD Threadripper 3960X PGO Optimization Processor Motherboard Chipset Memory Disk Graphics Audio Monitor Network OS Kernel Desktop Display Server Display Driver OpenGL Compiler File-System Screen Resolution GCC 10 GCC 10 - PGO AMD Ryzen Threadripper 3960X 24-Core @ 3.80GHz (24 Cores / 48 Threads) MSI Creator TRX40 (MS-7C59) v1.0 (1.12N1 BIOS) AMD Starship/Matisse 32768MB 1000GB Sabrent Rocket 4.0 1TB Gigabyte AMD Radeon 540/540X/550/550X / RX 540X/550/550X 2GB (1206/1750MHz) AMD Baffin HDMI/DP ASUS VP28U Aquantia AQC107 NBase-T/IEEE + Intel I211 + Intel Device 2723 Ubuntu 19.10 5.4.0-nvme-hwmon (x86_64) GNOME Shell 3.34.1 X Server 1.20.5 modesetting 1.20.5 4.5 Mesa 19.2.1 (LLVM 9.0.0) GCC 10.0.0 20191208 ext4 3840x2160 OpenBenchmarking.org Compiler Details - --disable-multilib --enable-checking=release Disk Details - NONE / errors=remount-ro,relatime,rw Processor Details - Scaling Governor: acpi-cpufreq ondemand - CPU Microcode: 0x8301025 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 + tsx_async_abort: Not affected
GCC 10 AMD Threadripper 3960X PGO Optimization tscp: AI Chess Performance himeno: Poisson Pressure Solver askap: tConvolve OpenMP - Degridding mkl-dnn: Convolution Batch conv_googlenet_v3 - f32 rocksdb: Rand Fill openssl: RSA 4096-bit Performance hpcc: G-Ffte hpcc: G-Ffte askap: tConvolve OpenMP - Gridding hpcc: Rand Ring Bandwidth hpcc: Max Ping Pong Bandwidth stockfish: Total Time qmcpack: byte: Dhrystone 2 hpcc: G-Ptrans hpcc: G-Rand Access crafty: Elapsed Time hpcc: EP-DGEMM radiance: SMP Parallel mkl-dnn: Convolution Batch conv_alexnet - f32 mkl-dnn: Recurrent Neural Network Training - f32 rocksdb: Read While Writing hpcc: Rand Ring Latency rocksdb: Rand Read mkl-dnn: Deconvolution Batch deconv_1d - f32 hpcc: G-HPL minife: Small hpcc: EP-STREAM Triad radiance: Serial rocksdb: Seq Fill askap: tConvolve MT - Degridding askap: tConvolve MT - Gridding rocksdb: Rand Fill Sync sqlite-speedtest: Timed Time - Size 1,000 pgbench: Buffer Test - Heavy Contention - Read Only pgbench: Buffer Test - Normal Load - Read Only gromacs: Water Benchmark encode-mp3: WAV To MP3 encode-flac: WAV To FLAC compress-xz: Compressing ubuntu-16.04.3-server-i386.img, Compression Level 9 build-imagemagick: Time To Compile ttsiod-renderer: Phong Rendering With Soft-Shadow Mapping mrbayes: Primate Phylogeny Analysis fftw: Float + SSE - 2D FFT Size 4096 fftw: Float + SSE - 2D FFT Size 32 fftw: Float + SSE - 1D FFT Size 32 fftw: Stock - 2D FFT Size 4096 fftw: Stock - 2D FFT Size 32 fftw: Stock - 1D FFT Size 32 sqlite: 1 mt-dgemm: Sustained Floating-Point Rate GCC 10 GCC 10 - PGO 1346651 4684.299494 4096.25 52.3291 938039 7180.6 10.49127 10.49127 5433.8 3.40678 22976.998 79359613 1878 48055276.3 5.47737 0.14278 9234824 32.92793 171.295 123.990 194.248 4889956 0.45863 145207827 2.32419 63.62933 7740.10 1.79750 555.936 1019862 3359.12 1947.24 24588 57.263 676349.711031 669039.844251 2.505 7.297 7.719 19.865 16.469 938.471 70.008 22667 45404 15396 6687.3 10512 10443 14.184 8.567282 1533348 4848.093522 3995.25 53.4081 921081 7072.4 10.63663 10.63663 5361.35 3.36248 23248.086 78501983 1896 48511999.7 5.52421 0.14161 9309942 32.67613 172.353 123.296 195.321 4868440 0.45680 144768694 2.31720 63.47507 7728.25 1.79549 556.477 1020657 3359.70 1947.23 24588 9.669028 OpenBenchmarking.org
TSCP AI Chess Performance OpenBenchmarking.org Nodes Per Second, More Is Better TSCP 1.81 AI Chess Performance GCC 10 GCC 10 - PGO 300K 600K 900K 1200K 1500K SE +/- 1472.68, N = 5 SE +/- 852.40, N = 5 1346651 1533348 -fprofile-correction 1. (CC) gcc options: -O3 -march=native
Himeno Benchmark Poisson Pressure Solver OpenBenchmarking.org MFLOPS, More Is Better Himeno Benchmark 3.0 Poisson Pressure Solver GCC 10 GCC 10 - PGO 1000 2000 3000 4000 5000 SE +/- 55.99, N = 5 SE +/- 30.05, N = 3 4684.30 4848.09 1. (CC) gcc options: -O3 -mavx2
ASKAP Test: tConvolve OpenMP - Degridding OpenBenchmarking.org Million Grid Points Per Second, More Is Better ASKAP 2018-11-10 Test: tConvolve OpenMP - Degridding GCC 10 GCC 10 - PGO 900 1800 2700 3600 4500 SE +/- 0.00, N = 3 SE +/- 53.24, N = 3 4096.25 3995.25 1. (CXX) g++ options: -lpthread
MKL-DNN DNNL Harness: Convolution Batch conv_googlenet_v3 - Data Type: f32 OpenBenchmarking.org ms, Fewer Is Better MKL-DNN DNNL 1.1 Harness: Convolution Batch conv_googlenet_v3 - Data Type: f32 GCC 10 GCC 10 - PGO 12 24 36 48 60 SE +/- 0.14, N = 3 SE +/- 0.66, N = 3 52.33 53.41 MIN: 51.48 -lm - MIN: 51.6 1. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl
Facebook RocksDB Test: Random Fill OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 6.3.6 Test: Random Fill GCC 10 GCC 10 - PGO 200K 400K 600K 800K 1000K SE +/- 16043.44, N = 3 SE +/- 1253.44, N = 3 938039 921081 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fno-builtin-memcmp -fno-rtti -rdynamic -lpthread
OpenSSL RSA 4096-bit Performance OpenBenchmarking.org Signs Per Second, More Is Better OpenSSL 1.1.1 RSA 4096-bit Performance GCC 10 GCC 10 - PGO 1500 3000 4500 6000 7500 SE +/- 21.70, N = 3 SE +/- 20.62, N = 3 7180.6 7072.4 -O3 -lssl 1. (CC) gcc options: -pthread -m64 -lcrypto -ldl
HPC Challenge Test / Class: G-Ffte OpenBenchmarking.org GFLOP/s, More Is Better HPC Challenge 1.5.0 Test / Class: G-Ffte GCC 10 GCC 10 - PGO 3 6 9 12 15 SE +/- 0.05, N = 3 SE +/- 0.11, N = 3 10.49 10.64 1. (CC) gcc options: -lblas -lm -pthread -lmpi -fomit-frame-pointer -funroll-loops 2. ATLAS + Open MPI 3.1.3
HPC Challenge Test / Class: G-Ffte OpenBenchmarking.org GFLOPS, More Is Better HPC Challenge 1.5.0 Test / Class: G-Ffte GCC 10 GCC 10 - PGO 3 6 9 12 15 SE +/- 0.05, N = 3 SE +/- 0.11, N = 3 10.49 10.64 1. (CC) gcc options: -lblas -lm -pthread -lmpi -fomit-frame-pointer -funroll-loops 2. ATLAS + Open MPI 3.1.3
ASKAP Test: tConvolve OpenMP - Gridding OpenBenchmarking.org Million Grid Points Per Second, More Is Better ASKAP 2018-11-10 Test: tConvolve OpenMP - Gridding GCC 10 GCC 10 - PGO 1200 2400 3600 4800 6000 SE +/- 0.00, N = 3 SE +/- 36.23, N = 3 5433.80 5361.35 1. (CXX) g++ options: -lpthread
HPC Challenge Test / Class: Random Ring Bandwidth OpenBenchmarking.org GB/s, More Is Better HPC Challenge 1.5.0 Test / Class: Random Ring Bandwidth GCC 10 GCC 10 - PGO 0.7665 1.533 2.2995 3.066 3.8325 SE +/- 0.01038, N = 3 SE +/- 0.04431, N = 3 3.40678 3.36248 1. (CC) gcc options: -lblas -lm -pthread -lmpi -fomit-frame-pointer -funroll-loops 2. ATLAS + Open MPI 3.1.3
HPC Challenge Test / Class: Max Ping Pong Bandwidth OpenBenchmarking.org MB/s, More Is Better HPC Challenge 1.5.0 Test / Class: Max Ping Pong Bandwidth GCC 10 GCC 10 - PGO 5K 10K 15K 20K 25K SE +/- 313.29, N = 3 SE +/- 58.02, N = 3 22977.00 23248.09 1. (CC) gcc options: -lblas -lm -pthread -lmpi -fomit-frame-pointer -funroll-loops 2. ATLAS + Open MPI 3.1.3
Stockfish Total Time OpenBenchmarking.org Nodes Per Second, More Is Better Stockfish 9 Total Time GCC 10 GCC 10 - PGO 20M 40M 60M 80M 100M SE +/- 526550.53, N = 3 SE +/- 536300.93, N = 3 79359613 78501983 1. (CXX) g++ options: -m64 -lpthread -fno-exceptions -std=c++11 -pedantic -O3 -msse -msse3 -mpopcnt -flto
QMCPACK OpenBenchmarking.org Total Execution Time - Seconds, Fewer Is Better QMCPACK 3.8 GCC 10 GCC 10 - PGO 400 800 1200 1600 2000 1878 1896 -fprofile-correction 1. (CXX) g++ options: -fopenmp -fomit-frame-pointer -finline-limit=1000 -fstrict-aliasing -funroll-all-loops -march=native -O3 -ffast-math -lm
BYTE Unix Benchmark Computational Test: Dhrystone 2 OpenBenchmarking.org LPS, More Is Better BYTE Unix Benchmark 3.6 Computational Test: Dhrystone 2 GCC 10 GCC 10 - PGO 10M 20M 30M 40M 50M SE +/- 550382.53, N = 3 SE +/- 627061.00, N = 3 48055276.3 48511999.7
HPC Challenge Test / Class: G-Ptrans OpenBenchmarking.org GB/s, More Is Better HPC Challenge 1.5.0 Test / Class: G-Ptrans GCC 10 GCC 10 - PGO 1.2429 2.4858 3.7287 4.9716 6.2145 SE +/- 0.00581, N = 3 SE +/- 0.03180, N = 3 5.47737 5.52421 1. (CC) gcc options: -lblas -lm -pthread -lmpi -fomit-frame-pointer -funroll-loops 2. ATLAS + Open MPI 3.1.3
HPC Challenge Test / Class: G-Random Access OpenBenchmarking.org GUP/s, More Is Better HPC Challenge 1.5.0 Test / Class: G-Random Access GCC 10 GCC 10 - PGO 0.0321 0.0642 0.0963 0.1284 0.1605 SE +/- 0.00039, N = 3 SE +/- 0.00060, N = 3 0.14278 0.14161 1. (CC) gcc options: -lblas -lm -pthread -lmpi -fomit-frame-pointer -funroll-loops 2. ATLAS + Open MPI 3.1.3
Crafty Elapsed Time OpenBenchmarking.org Nodes Per Second, More Is Better Crafty 25.2 Elapsed Time GCC 10 GCC 10 - PGO 2M 4M 6M 8M 10M SE +/- 7954.66, N = 3 SE +/- 73907.13, N = 3 9234824 9309942 1. (CC) gcc options: -pthread -lstdc++ -fprofile-use -lm
HPC Challenge Test / Class: EP-DGEMM OpenBenchmarking.org GFLOPS, More Is Better HPC Challenge 1.5.0 Test / Class: EP-DGEMM GCC 10 GCC 10 - PGO 8 16 24 32 40 SE +/- 0.38, N = 3 SE +/- 0.06, N = 3 32.93 32.68 1. (CC) gcc options: -lblas -lm -pthread -lmpi -fomit-frame-pointer -funroll-loops 2. ATLAS + Open MPI 3.1.3
Radiance Benchmark Test: SMP Parallel OpenBenchmarking.org Seconds, Fewer Is Better Radiance Benchmark 5.0 Test: SMP Parallel GCC 10 GCC 10 - PGO 40 80 120 160 200 171.30 172.35
MKL-DNN DNNL Harness: Convolution Batch conv_alexnet - Data Type: f32 OpenBenchmarking.org ms, Fewer Is Better MKL-DNN DNNL 1.1 Harness: Convolution Batch conv_alexnet - Data Type: f32 GCC 10 GCC 10 - PGO 30 60 90 120 150 SE +/- 1.44, N = 3 SE +/- 0.70, N = 3 123.99 123.30 MIN: 121.92 -lm - MIN: 121.28 1. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl
MKL-DNN DNNL Harness: Recurrent Neural Network Training - Data Type: f32 OpenBenchmarking.org ms, Fewer Is Better MKL-DNN DNNL 1.1 Harness: Recurrent Neural Network Training - Data Type: f32 GCC 10 GCC 10 - PGO 40 80 120 160 200 SE +/- 0.35, N = 3 SE +/- 0.82, N = 3 194.25 195.32 MIN: 192.53 -lm - MIN: 192.26 1. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl
Facebook RocksDB Test: Read While Writing OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 6.3.6 Test: Read While Writing GCC 10 GCC 10 - PGO 1000K 2000K 3000K 4000K 5000K SE +/- 20082.88, N = 3 SE +/- 26586.51, N = 3 4889956 4868440 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fno-builtin-memcmp -fno-rtti -rdynamic -lpthread
HPC Challenge Test / Class: Random Ring Latency OpenBenchmarking.org usecs, Fewer Is Better HPC Challenge 1.5.0 Test / Class: Random Ring Latency GCC 10 GCC 10 - PGO 0.1032 0.2064 0.3096 0.4128 0.516 SE +/- 0.00067, N = 3 SE +/- 0.00047, N = 3 0.45863 0.45680 1. (CC) gcc options: -lblas -lm -pthread -lmpi -fomit-frame-pointer -funroll-loops 2. ATLAS + Open MPI 3.1.3
Facebook RocksDB Test: Random Read OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 6.3.6 Test: Random Read GCC 10 GCC 10 - PGO 30M 60M 90M 120M 150M SE +/- 1800355.11, N = 3 SE +/- 727018.18, N = 3 145207827 144768694 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fno-builtin-memcmp -fno-rtti -rdynamic -lpthread
MKL-DNN DNNL Harness: Deconvolution Batch deconv_1d - Data Type: f32 OpenBenchmarking.org ms, Fewer Is Better MKL-DNN DNNL 1.1 Harness: Deconvolution Batch deconv_1d - Data Type: f32 GCC 10 GCC 10 - PGO 0.5229 1.0458 1.5687 2.0916 2.6145 SE +/- 0.00388, N = 3 SE +/- 0.00905, N = 3 2.32419 2.31720 MIN: 2.26 -lm - MIN: 2.24 1. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl
HPC Challenge Test / Class: G-HPL OpenBenchmarking.org GFLOPS, More Is Better HPC Challenge 1.5.0 Test / Class: G-HPL GCC 10 GCC 10 - PGO 14 28 42 56 70 SE +/- 0.23, N = 3 SE +/- 0.02, N = 3 63.63 63.48 1. (CC) gcc options: -lblas -lm -pthread -lmpi -fomit-frame-pointer -funroll-loops 2. ATLAS + Open MPI 3.1.3
miniFE Problem Size: Small OpenBenchmarking.org CG Mflops, More Is Better miniFE 2.2 Problem Size: Small GCC 10 GCC 10 - PGO 1700 3400 5100 6800 8500 SE +/- 11.29, N = 3 SE +/- 8.78, N = 3 7740.10 7728.25 1. (CXX) g++ options: -O3 -fopenmp -pthread -lmpi_cxx -lmpi
HPC Challenge Test / Class: EP-STREAM Triad OpenBenchmarking.org GB/s, More Is Better HPC Challenge 1.5.0 Test / Class: EP-STREAM Triad GCC 10 GCC 10 - PGO 0.4044 0.8088 1.2132 1.6176 2.022 SE +/- 0.00127, N = 3 SE +/- 0.00146, N = 3 1.79750 1.79549 1. (CC) gcc options: -lblas -lm -pthread -lmpi -fomit-frame-pointer -funroll-loops 2. ATLAS + Open MPI 3.1.3
Radiance Benchmark Test: Serial OpenBenchmarking.org Seconds, Fewer Is Better Radiance Benchmark 5.0 Test: Serial GCC 10 GCC 10 - PGO 120 240 360 480 600 555.94 556.48
Facebook RocksDB Test: Sequential Fill OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 6.3.6 Test: Sequential Fill GCC 10 GCC 10 - PGO 200K 400K 600K 800K 1000K SE +/- 3135.06, N = 3 SE +/- 3754.87, N = 3 1019862 1020657 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fno-builtin-memcmp -fno-rtti -rdynamic -lpthread
ASKAP Test: tConvolve MT - Degridding OpenBenchmarking.org Million Grid Points Per Second, More Is Better ASKAP 2018-11-10 Test: tConvolve MT - Degridding GCC 10 GCC 10 - PGO 700 1400 2100 2800 3500 SE +/- 3.58, N = 3 SE +/- 2.69, N = 3 3359.12 3359.70 1. (CXX) g++ options: -lpthread
ASKAP Test: tConvolve MT - Gridding OpenBenchmarking.org Million Grid Points Per Second, More Is Better ASKAP 2018-11-10 Test: tConvolve MT - Gridding GCC 10 GCC 10 - PGO 400 800 1200 1600 2000 SE +/- 3.33, N = 3 SE +/- 2.66, N = 3 1947.24 1947.23 1. (CXX) g++ options: -lpthread
Facebook RocksDB Test: Random Fill Sync OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 6.3.6 Test: Random Fill Sync GCC 10 GCC 10 - PGO 5K 10K 15K 20K 25K SE +/- 19.92, N = 3 SE +/- 28.62, N = 3 24588 24588 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fno-builtin-memcmp -fno-rtti -rdynamic -lpthread
SQLite Speedtest Timed Time - Size 1,000 OpenBenchmarking.org Seconds, Fewer Is Better SQLite Speedtest 3.30 Timed Time - Size 1,000 GCC 10 13 26 39 52 65 SE +/- 0.13, N = 3 57.26 1. (CC) gcc options: -O2 -ldl -lz -lpthread
PostgreSQL pgbench Scaling: Buffer Test - Test: Heavy Contention - Mode: Read Only OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 12.0 Scaling: Buffer Test - Test: Heavy Contention - Mode: Read Only GCC 10 140K 280K 420K 560K 700K SE +/- 4887.19, N = 3 676349.71 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -lcrypt -ldl -lm
PostgreSQL pgbench Scaling: Buffer Test - Test: Normal Load - Mode: Read Only OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 12.0 Scaling: Buffer Test - Test: Normal Load - Mode: Read Only GCC 10 140K 280K 420K 560K 700K SE +/- 622.09, N = 3 669039.84 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -lcrypt -ldl -lm
GROMACS Water Benchmark OpenBenchmarking.org Ns Per Day, More Is Better GROMACS 2019.4 Water Benchmark GCC 10 0.5636 1.1272 1.6908 2.2544 2.818 SE +/- 0.002, N = 3 2.505 1. (CXX) g++ options: -mavx2 -mfma -std=c++11 -O3 -funroll-all-loops -pthread -lrt -lpthread -lm
LAME MP3 Encoding WAV To MP3 OpenBenchmarking.org Seconds, Fewer Is Better LAME MP3 Encoding 3.100 WAV To MP3 GCC 10 2 4 6 8 10 SE +/- 0.002, N = 3 7.297 1. (CC) gcc options: -O3 -ffast-math -funroll-loops -fschedule-insns2 -fbranch-count-reg -fforce-addr -pipe -lm
FLAC Audio Encoding WAV To FLAC OpenBenchmarking.org Seconds, Fewer Is Better FLAC Audio Encoding 1.3.2 WAV To FLAC GCC 10 2 4 6 8 10 SE +/- 0.009, N = 5 7.719 1. (CXX) g++ options: -O2 -fvisibility=hidden -logg -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 GCC 10 5 10 15 20 25 SE +/- 0.02, N = 3 19.87 1. (CC) gcc options: -pthread -fvisibility=hidden -O2
Timed ImageMagick Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed ImageMagick Compilation 6.9.0 Time To Compile GCC 10 4 8 12 16 20 SE +/- 0.08, N = 3 16.47
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 GCC 10 200 400 600 800 1000 SE +/- 1.21, N = 3 938.47 1. (CXX) g++ options: -O3 -fomit-frame-pointer -ffast-math -mtune=native -flto -msse -mrecip -mfpmath=sse -msse2 -mssse3 -lSDL -fopenmp -fwhole-program -lstdc++
Timed MrBayes Analysis Primate Phylogeny Analysis OpenBenchmarking.org Seconds, Fewer Is Better Timed MrBayes Analysis 3.2.7 Primate Phylogeny Analysis GCC 10 16 32 48 64 80 SE +/- 0.25, N = 3 70.01 1. (CC) gcc options: -mmmx -msse -msse2 -msse3 -mssse3 -msse4.1 -msse4.2 -msse4a -msha -maes -mavx -mfma -mavx2 -mrdrnd -mbmi -mbmi2 -madx -mabm -O3 -std=c99 -pedantic -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 GCC 10 5K 10K 15K 20K 25K SE +/- 285.77, N = 3 22667 1. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
FFTW Build: Float + SSE - Size: 2D FFT Size 32 OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Float + SSE - Size: 2D FFT Size 32 GCC 10 10K 20K 30K 40K 50K SE +/- 56.20, N = 3 45404 1. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
FFTW Build: Float + SSE - Size: 1D FFT Size 32 OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Float + SSE - Size: 1D FFT Size 32 GCC 10 3K 6K 9K 12K 15K SE +/- 15.37, N = 3 15396 1. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
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 GCC 10 1400 2800 4200 5600 7000 SE +/- 7.80, N = 3 6687.3 1. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
FFTW Build: Stock - Size: 2D FFT Size 32 OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Stock - Size: 2D FFT Size 32 GCC 10 2K 4K 6K 8K 10K SE +/- 11.02, N = 3 10512 1. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
FFTW Build: Stock - Size: 1D FFT Size 32 OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Stock - Size: 1D FFT Size 32 GCC 10 2K 4K 6K 8K 10K SE +/- 16.77, N = 3 10443 1. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
SQLite Threads / Copies: 1 OpenBenchmarking.org Seconds, Fewer Is Better SQLite 3.30.1 Threads / Copies: 1 GCC 10 4 8 12 16 20 SE +/- 0.01, N = 3 14.18 1. (CC) gcc options: -O2 -lz -lm -ldl -lpthread
ACES DGEMM Sustained Floating-Point Rate OpenBenchmarking.org GFLOP/s, More Is Better ACES DGEMM 1.0 Sustained Floating-Point Rate GCC 10 GCC 10 - PGO 3 6 9 12 15 SE +/- 0.158518, N = 12 SE +/- 0.073545, N = 3 8.567282 9.669028 1. (CC) gcc options: -O3 -march=native -fopenmp
Phoronix Test Suite v10.8.4