GCC 9 Compiler Benchmarking vs. LLVM Clang Intel Core i9-7980XE benchmarks of GCC 8 / GCC 9 versus LLVM Clang 7 and LLVM Clang 8 compilers on Ubuntu Linux. Benchmarks by Michael Larabel for a future article on Phoronix.com.
HTML result view exported from: https://openbenchmarking.org/result/1811133-SK-GCC9COMPI38&grs .
GCC 9 Compiler Benchmarking vs. LLVM Clang Processor Motherboard Chipset Memory Disk Graphics Audio Monitor Network OS Kernel Desktop Display Server Display Driver OpenGL Compiler File-System Screen Resolution GCC 8.2.0 GCC 9.0.0 20181112 Clang 7.0.0 Clang 8.0.0 20181111 Intel Core i9-7980XE @ 4.20GHz (18 Cores / 36 Threads) ASUS PRIME X299-A (1503 BIOS) Intel Sky Lake-E DMI3 Registers 16384MB 240GB Force MP510 NV120 12GB Realtek ALC1220 ASUS PB278 Intel Connection Ubuntu 18.10 4.18.0-10-generic (x86_64) GNOME Shell 3.30.1 X Server 1.20.1 modesetting 1.20.1 4.3 Mesa 18.2.2 GCC 8.2.0 ext4 2560x1440 GCC 9.0.0 20181112 Clang 7.0.0-3 Clang 8.0.0-svn346617-1~exp1+0~20181111195013.162~1.gbp8d271f OpenBenchmarking.org Environment Details - CXXFLAGS=-O3-march=native CFLAGS=-O3-march=native Compiler Details - GCC 8.2.0, GCC 9.0.0 20181112: --disable-multilib --enable-checking=release Processor Details - Scaling Governor: intel_pstate powersave Python Details - Python 2.7.15+ + Python 3.6.7 Security Details - KPTI + __user pointer sanitization + Full generic retpoline IBPB IBRS_FW + SSB disabled via prctl and seccomp + PTE Inversion; VMX: conditional cache flushes SMT vulnerable
GCC 9 Compiler Benchmarking vs. LLVM Clang c-ray: Total Time - 4K, 16 Rays Per Pixel john-the-ripper: Traditional DES npb: EP.C scimark2: Monte Carlo himeno: Poisson Pressure Solver scimark2: Jacobi Successive Over-Relaxation encode-mp3: WAV To MP3 john-the-ripper: Blowfish hmmer: Pfam Database Search john-the-ripper: MD5 build-llvm: Time To Compile build-apache: Time To Compile tjbench: Decompression Throughput xsbench: hpcg: npb: SP.A fftw: Float + SSE - 1D FFT Size 2048 cloverleaf: Lagrangian-Eulerian Hydrodynamics scimark2: Dense LU Matrix Factorization mcperf: Get npb: BT.A scimark2: Fast Fourier Transform ebizzy: stockfish: Total Time compress-zstd: Compressing ubuntu-16.04.3-server-i386.img, Compression Level 19 m-queens: Time To Solve aobench: 2048 x 2048 - Total Time fftw: Float + SSE - 2D FFT Size 2048 openssl: RSA 4096-bit Performance parboil: OpenMP LBM x264: H.264 Video Encoding mcperf: Set pgbench: Buffer Test - Normal Load - Read Only crafty: Elapsed Time scimark2: Composite parboil: OpenMP Stencil parboil: OpenMP CUTCP parboil: OpenMP MRI Gridding npb: FT.B npb: FT.A scimark2: Sparse Matrix Multiply build-linux-kernel: Time To Compile compress-7zip: Compress Speed Test pgbench: Buffer Test - Normal Load - Read Write blake2: GCC 8.2.0 GCC 9.0.0 20181112 Clang 7.0.0 Clang 8.0.0 20181111 33.70 72707667 925 906 3089 2074 10.13 22254 10.26 670435 223 22.05 183 4662395 1.25 3542 57019 2.98 6071 108730 4834 727 607319 47827811 10.61 48.73 31.35 20014 4658 79.36 128 71776 496730 8560641 2615 7.13 2.46 146 7220 6756 3295 44.26 93576 23830 3.66 33.75 74356333 1250 906 3093 2069 9.74 22173 10.42 675993 220 22.26 184 4664809 1.22 3865 59299 3.20 6063 110495 4557 732 620245 46908339 10.63 48.72 31.32 20468 4673 81.52 128 72449 500154 8423397 2613 7.19 2.44 147 7174 6718 3295 44.18 93437 21776 3.51 66.76 98537500 717 2463 1662 12.16 27611 8.59 799209 216 21.13 204 5156109 1.33 56274 6476 115868 763 594997 46179707 10.27 50.19 32.30 20258 4547 125 73064 504725 2584 3300 17186 3.02 67.06 100083000 717 2455 1661 11.80 25614 8.52 818976 189 19.70 198 5022107 1.34 54433 6449 115247 768 588266 45725081 10.34 50.41 32.19 19871 4544 125 73009 505631 2577 3288 10012 3.10 OpenBenchmarking.org
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 GCC 8.2.0 GCC 9.0.0 20181112 Clang 7.0.0 Clang 8.0.0 20181111 15 30 45 60 75 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 33.70 33.75 66.76 67.06 1. (CC) gcc options: -lm -lpthread -O3 -march=native
John The Ripper Test: Traditional DES OpenBenchmarking.org Real C/S, More Is Better John The Ripper 1.8.0-jumbo-1 Test: Traditional DES GCC 8.2.0 GCC 9.0.0 20181112 Clang 7.0.0 Clang 8.0.0 20181111 20M 40M 60M 80M 100M SE +/- 1115841.74, N = 3 SE +/- 132290.51, N = 3 SE +/- 1095165.68, N = 12 SE +/- 185734.58, N = 3 72707667 74356333 98537500 100083000 1. (CC) gcc options: -lssl -lcrypto -fopenmp -lgmp -pthread -lm -lz -ldl -lcrypt
NAS Parallel Benchmarks Test / Class: EP.C OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.3 Test / Class: EP.C GCC 8.2.0 GCC 9.0.0 20181112 300 600 900 1200 1500 SE +/- 4.53, N = 3 SE +/- 12.17, N = 3 925 1250 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi
SciMark Computational Test: Monte Carlo OpenBenchmarking.org Mflops, More Is Better SciMark 2.0 Computational Test: Monte Carlo GCC 8.2.0 GCC 9.0.0 20181112 Clang 7.0.0 Clang 8.0.0 20181111 200 400 600 800 1000 SE +/- 1.15, N = 3 SE +/- 0.99, N = 3 SE +/- 0.32, N = 3 SE +/- 0.29, N = 3 906 906 717 717 1. (CC) gcc options: -O3 -march=native -lm
Himeno Benchmark Poisson Pressure Solver OpenBenchmarking.org MFLOPS, More Is Better Himeno Benchmark 3.0 Poisson Pressure Solver GCC 8.2.0 GCC 9.0.0 20181112 Clang 7.0.0 Clang 8.0.0 20181111 700 1400 2100 2800 3500 SE +/- 4.75, N = 3 SE +/- 3.44, N = 3 SE +/- 2.40, N = 3 SE +/- 4.58, N = 3 3089 3093 2463 2455 1. (CC) gcc options: -O3 -march=native -mavx2
SciMark Computational Test: Jacobi Successive Over-Relaxation OpenBenchmarking.org Mflops, More Is Better SciMark 2.0 Computational Test: Jacobi Successive Over-Relaxation GCC 8.2.0 GCC 9.0.0 20181112 Clang 7.0.0 Clang 8.0.0 20181111 400 800 1200 1600 2000 SE +/- 2.18, N = 3 SE +/- 3.14, N = 3 SE +/- 1.35, N = 3 SE +/- 1.35, N = 3 2074 2069 1662 1661 1. (CC) gcc options: -O3 -march=native -lm
LAME MP3 Encoding WAV To MP3 OpenBenchmarking.org Seconds, Fewer Is Better LAME MP3 Encoding 3.100 WAV To MP3 GCC 8.2.0 GCC 9.0.0 20181112 Clang 7.0.0 Clang 8.0.0 20181111 3 6 9 12 15 SE +/- 0.04, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 10.13 9.74 12.16 11.80 -pipe -lncurses -pipe -lncurses 1. (CC) gcc options: -O3 -march=native -lm
John The Ripper Test: Blowfish OpenBenchmarking.org Real C/S, More Is Better John The Ripper 1.8.0-jumbo-1 Test: Blowfish GCC 8.2.0 GCC 9.0.0 20181112 Clang 7.0.0 Clang 8.0.0 20181111 6K 12K 18K 24K 30K SE +/- 70.42, N = 3 SE +/- 65.83, N = 3 SE +/- 11.67, N = 3 SE +/- 9.29, N = 3 22254 22173 27611 25614 1. (CC) gcc options: -lssl -lcrypto -fopenmp -lgmp -pthread -lm -lz -ldl -lcrypt
Timed HMMer Search Pfam Database Search OpenBenchmarking.org Seconds, Fewer Is Better Timed HMMer Search 2.3.2 Pfam Database Search GCC 8.2.0 GCC 9.0.0 20181112 Clang 7.0.0 Clang 8.0.0 20181111 3 6 9 12 15 SE +/- 0.06, N = 3 SE +/- 0.10, N = 3 SE +/- 0.12, N = 3 SE +/- 0.11, N = 3 10.26 10.42 8.59 8.52 1. (CC) gcc options: -O3 -march=native -pthread -lhmmer -lsquid -lm
John The Ripper Test: MD5 OpenBenchmarking.org Real C/S, More Is Better John The Ripper 1.8.0-jumbo-1 Test: MD5 GCC 8.2.0 GCC 9.0.0 20181112 Clang 7.0.0 Clang 8.0.0 20181111 200K 400K 600K 800K 1000K SE +/- 925.69, N = 3 SE +/- 1299.84, N = 3 SE +/- 11085.39, N = 3 SE +/- 768.00, N = 3 670435 675993 799209 818976 1. (CC) gcc options: -lssl -lcrypto -fopenmp -lgmp -pthread -lm -lz -ldl -lcrypt
Timed LLVM Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed LLVM Compilation 6.0.1 Time To Compile GCC 8.2.0 GCC 9.0.0 20181112 Clang 7.0.0 Clang 8.0.0 20181111 50 100 150 200 250 223 220 216 189
Timed Apache Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed Apache Compilation 2.4.7 Time To Compile GCC 8.2.0 GCC 9.0.0 20181112 Clang 7.0.0 Clang 8.0.0 20181111 5 10 15 20 25 SE +/- 0.07, N = 3 SE +/- 0.05, N = 3 SE +/- 0.06, N = 3 SE +/- 0.06, N = 3 22.05 22.26 21.13 19.70
libjpeg-turbo tjbench Test: Decompression Throughput OpenBenchmarking.org Megapixels/sec, More Is Better libjpeg-turbo tjbench 1.5.3 Test: Decompression Throughput GCC 8.2.0 GCC 9.0.0 20181112 Clang 7.0.0 Clang 8.0.0 20181111 40 80 120 160 200 SE +/- 0.06, N = 3 SE +/- 0.54, N = 3 SE +/- 0.36, N = 3 SE +/- 1.17, N = 3 183 184 204 198 1. (CC) gcc options: -O3 -march=native -lm
Xsbench OpenBenchmarking.org Lookups/s, More Is Better Xsbench 2017-07-06 GCC 8.2.0 GCC 9.0.0 20181112 Clang 7.0.0 Clang 8.0.0 20181111 1.1M 2.2M 3.3M 4.4M 5.5M SE +/- 806.44, N = 3 SE +/- 1108.05, N = 3 SE +/- 843.35, N = 3 SE +/- 1402.44, N = 3 4662395 4664809 5156109 5022107 1. (CC) gcc options: -std=gnu99 -fopenmp -O3 -lm
High Performance Conjugate Gradient OpenBenchmarking.org GFLOP/s, More Is Better High Performance Conjugate Gradient 3.0 GCC 8.2.0 GCC 9.0.0 20181112 Clang 7.0.0 Clang 8.0.0 20181111 0.3015 0.603 0.9045 1.206 1.5075 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 1.25 1.22 1.33 1.34
NAS Parallel Benchmarks Test / Class: SP.A OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.3 Test / Class: SP.A GCC 8.2.0 GCC 9.0.0 20181112 800 1600 2400 3200 4000 SE +/- 45.01, N = 3 SE +/- 28.57, N = 3 3542 3865 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi
FFTW Build: Float + SSE - Size: 1D FFT Size 2048 OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Float + SSE - Size: 1D FFT Size 2048 GCC 8.2.0 GCC 9.0.0 20181112 Clang 7.0.0 Clang 8.0.0 20181111 13K 26K 39K 52K 65K SE +/- 1025.80, N = 3 SE +/- 196.81, N = 3 SE +/- 463.90, N = 3 SE +/- 809.18, N = 5 57019 59299 56274 54433 1. (CC) gcc options: -pthread -O3 -march=native -lm
CloverLeaf Lagrangian-Eulerian Hydrodynamics OpenBenchmarking.org Seconds, Fewer Is Better CloverLeaf Lagrangian-Eulerian Hydrodynamics GCC 8.2.0 GCC 9.0.0 20181112 0.72 1.44 2.16 2.88 3.6 SE +/- 0.03, N = 3 SE +/- 0.01, N = 3 2.98 3.20 1. (F9X) gfortran options: -O3 -march=native -funroll-loops -fopenmp
SciMark Computational Test: Dense LU Matrix Factorization OpenBenchmarking.org Mflops, More Is Better SciMark 2.0 Computational Test: Dense LU Matrix Factorization GCC 8.2.0 GCC 9.0.0 20181112 Clang 7.0.0 Clang 8.0.0 20181111 1400 2800 4200 5600 7000 SE +/- 10.59, N = 3 SE +/- 7.72, N = 3 SE +/- 0.69, N = 3 SE +/- 18.31, N = 3 6071 6063 6476 6449 1. (CC) gcc options: -O3 -march=native -lm
Memcached mcperf Method: Get OpenBenchmarking.org Operations Per Second, More Is Better Memcached mcperf 1.5.10 Method: Get GCC 8.2.0 GCC 9.0.0 20181112 Clang 7.0.0 Clang 8.0.0 20181111 20K 40K 60K 80K 100K SE +/- 767.29, N = 3 SE +/- 666.93, N = 3 SE +/- 605.02, N = 3 SE +/- 1208.65, N = 3 108730 110495 115868 115247 1. (CC) gcc options: -O3 -march=native -lm -rdynamic
NAS Parallel Benchmarks Test / Class: BT.A OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.3 Test / Class: BT.A GCC 8.2.0 GCC 9.0.0 20181112 1000 2000 3000 4000 5000 SE +/- 31.51, N = 3 SE +/- 35.44, N = 3 4834 4557 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi
SciMark Computational Test: Fast Fourier Transform OpenBenchmarking.org Mflops, More Is Better SciMark 2.0 Computational Test: Fast Fourier Transform GCC 8.2.0 GCC 9.0.0 20181112 Clang 7.0.0 Clang 8.0.0 20181111 170 340 510 680 850 SE +/- 0.86, N = 3 SE +/- 1.85, N = 3 SE +/- 3.38, N = 3 SE +/- 1.98, N = 3 727 732 763 768 1. (CC) gcc options: -O3 -march=native -lm
ebizzy OpenBenchmarking.org Records/s, More Is Better ebizzy 0.3 GCC 8.2.0 GCC 9.0.0 20181112 Clang 7.0.0 Clang 8.0.0 20181111 130K 260K 390K 520K 650K SE +/- 5181.95, N = 3 SE +/- 7775.77, N = 3 SE +/- 8494.47, N = 12 SE +/- 10943.27, N = 3 607319 620245 594997 588266 1. (CC) gcc options: -pthread -lpthread -O3 -march=native
Stockfish Total Time OpenBenchmarking.org Nodes Per Second, More Is Better Stockfish 9 Total Time GCC 8.2.0 GCC 9.0.0 20181112 Clang 7.0.0 Clang 8.0.0 20181111 10M 20M 30M 40M 50M SE +/- 290155.29, N = 3 SE +/- 469942.62, N = 3 SE +/- 358695.82, N = 3 SE +/- 77465.59, N = 3 47827811 46908339 46179707 45725081 1. (CXX) g++ options: -m64 -lpthread -O3 -march=native -fno-exceptions -std=c++11 -pedantic -msse -msse3 -mpopcnt -flto
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 GCC 8.2.0 GCC 9.0.0 20181112 Clang 7.0.0 Clang 8.0.0 20181111 3 6 9 12 15 SE +/- 0.01, N = 3 SE +/- 0.03, N = 3 SE +/- 0.04, N = 3 SE +/- 0.07, N = 3 10.61 10.63 10.27 10.34 1. (CC) gcc options: -O3 -march=native -pthread -lz -llzma
m-queens Time To Solve OpenBenchmarking.org Seconds, Fewer Is Better m-queens 1.2 Time To Solve GCC 8.2.0 GCC 9.0.0 20181112 Clang 7.0.0 Clang 8.0.0 20181111 11 22 33 44 55 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 48.73 48.72 50.19 50.41 1. (CXX) g++ options: -fopenmp -O3 -march=native -O2
AOBench Size: 2048 x 2048 - Total Time OpenBenchmarking.org Seconds, Fewer Is Better AOBench Size: 2048 x 2048 - Total Time GCC 8.2.0 GCC 9.0.0 20181112 Clang 7.0.0 Clang 8.0.0 20181111 8 16 24 32 40 SE +/- 0.04, N = 3 SE +/- 0.03, N = 3 SE +/- 0.07, N = 3 SE +/- 0.01, N = 3 31.35 31.32 32.30 32.19 1. (CC) gcc options: -lm -O3 -march=native
FFTW Build: Float + SSE - Size: 2D FFT Size 2048 OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Float + SSE - Size: 2D FFT Size 2048 GCC 8.2.0 GCC 9.0.0 20181112 Clang 7.0.0 Clang 8.0.0 20181111 4K 8K 12K 16K 20K SE +/- 25.39, N = 3 SE +/- 88.29, N = 3 SE +/- 260.52, N = 3 SE +/- 95.21, N = 3 20014 20468 20258 19871 1. (CC) gcc options: -pthread -O3 -march=native -lm
OpenSSL RSA 4096-bit Performance OpenBenchmarking.org Signs Per Second, More Is Better OpenSSL 1.1.1 RSA 4096-bit Performance GCC 8.2.0 GCC 9.0.0 20181112 Clang 7.0.0 Clang 8.0.0 20181111 1000 2000 3000 4000 5000 SE +/- 5.28, N = 3 SE +/- 0.31, N = 3 SE +/- 2.68, N = 3 SE +/- 8.23, N = 3 4658 4673 4547 4544 -Qunused-arguments -Qunused-arguments 1. (CC) gcc options: -pthread -m64 -O3 -march=native -lssl -lcrypto -ldl
Parboil Test: OpenMP LBM OpenBenchmarking.org Seconds, Fewer Is Better Parboil 2.5 Test: OpenMP LBM GCC 8.2.0 GCC 9.0.0 20181112 20 40 60 80 100 SE +/- 0.33, N = 3 SE +/- 0.27, N = 3 79.36 81.52 1. (CXX) g++ options: -lm -lpthread -lgomp -O3 -ffast-math -fopenmp
x264 H.264 Video Encoding OpenBenchmarking.org Frames Per Second, More Is Better x264 2018-09-25 H.264 Video Encoding GCC 8.2.0 GCC 9.0.0 20181112 Clang 7.0.0 Clang 8.0.0 20181111 30 60 90 120 150 SE +/- 1.97, N = 3 SE +/- 1.58, N = 7 SE +/- 2.08, N = 4 SE +/- 1.11, N = 3 128 128 125 125 -mstack-alignment=64 -mstack-alignment=64 1. (CC) gcc options: -ldl -m64 -lm -lpthread -O3 -ffast-math -march=native -std=gnu99 -fPIC -fomit-frame-pointer -fno-tree-vectorize
Memcached mcperf Method: Set OpenBenchmarking.org Operations Per Second, More Is Better Memcached mcperf 1.5.10 Method: Set GCC 8.2.0 GCC 9.0.0 20181112 Clang 7.0.0 Clang 8.0.0 20181111 16K 32K 48K 64K 80K SE +/- 259.45, N = 3 SE +/- 305.67, N = 3 SE +/- 499.66, N = 3 SE +/- 408.85, N = 3 71776 72449 73064 73009 1. (CC) gcc options: -O3 -march=native -lm -rdynamic
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 GCC 8.2.0 GCC 9.0.0 20181112 Clang 7.0.0 Clang 8.0.0 20181111 110K 220K 330K 440K 550K SE +/- 210.08, N = 3 SE +/- 274.70, N = 3 SE +/- 3717.80, N = 3 SE +/- 3943.25, N = 3 496730 500154 504725 505631 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O3 -march=native -lpgcommon -lpgport -lpq -lpthread -lrt -lcrypt -ldl -lm
Crafty Elapsed Time OpenBenchmarking.org Nodes Per Second, More Is Better Crafty 25.2 Elapsed Time GCC 8.2.0 GCC 9.0.0 20181112 2M 4M 6M 8M 10M SE +/- 8409.72, N = 3 SE +/- 15686.24, N = 3 8560641 8423397 1. (CC) gcc options: -pthread -lstdc++ -fprofile-use -lm
SciMark Computational Test: Composite OpenBenchmarking.org Mflops, More Is Better SciMark 2.0 Computational Test: Composite GCC 8.2.0 GCC 9.0.0 20181112 Clang 7.0.0 Clang 8.0.0 20181111 600 1200 1800 2400 3000 SE +/- 1.63, N = 3 SE +/- 2.04, N = 3 SE +/- 1.31, N = 3 SE +/- 5.03, N = 3 2615 2613 2584 2577 1. (CC) gcc options: -O3 -march=native -lm
Parboil Test: OpenMP Stencil OpenBenchmarking.org Seconds, Fewer Is Better Parboil 2.5 Test: OpenMP Stencil GCC 8.2.0 GCC 9.0.0 20181112 2 4 6 8 10 SE +/- 0.05, N = 3 SE +/- 0.06, N = 3 7.13 7.19 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 GCC 8.2.0 GCC 9.0.0 20181112 0.5535 1.107 1.6605 2.214 2.7675 SE +/- 0.04, N = 3 SE +/- 0.02, N = 3 2.46 2.44 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 GCC 8.2.0 GCC 9.0.0 20181112 30 60 90 120 150 SE +/- 0.83, N = 3 SE +/- 0.40, N = 3 146 147 1. (CXX) g++ options: -lm -lpthread -lgomp -O3 -ffast-math -fopenmp
NAS Parallel Benchmarks Test / Class: FT.B OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.3 Test / Class: FT.B GCC 8.2.0 GCC 9.0.0 20181112 1500 3000 4500 6000 7500 SE +/- 8.95, N = 3 SE +/- 2.08, N = 3 7220 7174 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi
NAS Parallel Benchmarks Test / Class: FT.A OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.3 Test / Class: FT.A GCC 8.2.0 GCC 9.0.0 20181112 1400 2800 4200 5600 7000 SE +/- 12.06, N = 3 SE +/- 17.12, N = 3 6756 6718 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi
SciMark Computational Test: Sparse Matrix Multiply OpenBenchmarking.org Mflops, More Is Better SciMark 2.0 Computational Test: Sparse Matrix Multiply GCC 8.2.0 GCC 9.0.0 20181112 Clang 7.0.0 Clang 8.0.0 20181111 700 1400 2100 2800 3500 SE +/- 1.55, N = 3 SE +/- 3.31, N = 3 SE +/- 3.75, N = 3 SE +/- 5.51, N = 3 3295 3295 3300 3288 1. (CC) gcc options: -O3 -march=native -lm
Timed Linux Kernel Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed Linux Kernel Compilation 4.18 Time To Compile GCC 8.2.0 GCC 9.0.0 20181112 10 20 30 40 50 SE +/- 0.50, N = 9 SE +/- 0.61, N = 6 44.26 44.18
7-Zip Compression Compress Speed Test OpenBenchmarking.org MIPS, More Is Better 7-Zip Compression 16.02 Compress Speed Test GCC 8.2.0 GCC 9.0.0 20181112 20K 40K 60K 80K 100K SE +/- 184.01, N = 3 SE +/- 384.58, N = 3 93576 93437 1. (CXX) g++ options: -pipe -lpthread
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 GCC 8.2.0 GCC 9.0.0 20181112 Clang 7.0.0 Clang 8.0.0 20181111 5K 10K 15K 20K 25K SE +/- 402.82, N = 4 SE +/- 1475.07, N = 9 SE +/- 1724.11, N = 9 SE +/- 421.62, N = 12 23830 21776 17186 10012 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O3 -march=native -lpgcommon -lpgport -lpq -lpthread -lrt -lcrypt -ldl -lm
BLAKE2 OpenBenchmarking.org Cycles Per Byte, Fewer Is Better BLAKE2 20170307 GCC 8.2.0 GCC 9.0.0 20181112 Clang 7.0.0 Clang 8.0.0 20181111 0.8235 1.647 2.4705 3.294 4.1175 SE +/- 0.09, N = 12 SE +/- 0.11, N = 12 SE +/- 0.06, N = 3 SE +/- 0.01, N = 3 3.66 3.51 3.02 3.10 1. (CC) gcc options: -O3 -march=native -lcrypto -lz
Phoronix Test Suite v10.8.5