LLVM Clang benchmarks 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 2108236-TJ-LLVMCLANG38 LLVM Clang 13 Bencmarking Intel Xeon Ice Lake - Phoronix Test Suite LLVM Clang 13 Bencmarking Intel Xeon Ice Lake LLVM Clang benchmarks for a future article.
HTML result view exported from: https://openbenchmarking.org/result/2108236-TJ-LLVMCLANG38&grt&rdt .
LLVM Clang 13 Bencmarking Intel Xeon Ice Lake Processor Motherboard Chipset Memory Disk Graphics Monitor Network OS Kernel Desktop Display Server Compiler File-System Screen Resolution Clang 13 Clang 12 Clang 11 2 x Intel Xeon Platinum 8380 @ 3.40GHz (80 Cores / 160 Threads) Intel M50CYP2SB2U (SE5C6200.86B.0022.D08.2103221623 BIOS) Intel Device 0998 504GB 7682GB INTEL SSDPF2KX076TZ ASPEED VE228 2 x Intel X710 for 10GBASE-T + 2 x Intel E810-C for QSFP Ubuntu 21.04 5.14.0-rc1-folio (x86_64) 20210715 GNOME Shell 3.38.4 X Server 1.20.11 Clang 13.0.0-++20210820072921+23ba3732246a-1~exp1~20210820174536.53 ext4 1920x1080 Clang 12.0.0-3ubuntu1~21.04.1 Clang 11.0.1-2ubuntu4 OpenBenchmarking.org Kernel Details - Transparent Huge Pages: madvise Environment Details - CXXFLAGS="-O3 -march=native" CFLAGS="-O3 -march=native" Processor Details - Scaling Governor: intel_pstate performance - CPU Microcode: 0xd0002a0 Python Details - Clang 13, Clang 12: Python 3.9.5 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 Enhanced IBRS IBPB: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected
LLVM Clang 13 Bencmarking Intel Xeon Ice Lake aircrack-ng: aobench: 2048 x 2048 - Total Time aom-av1: Speed 6 Realtime - Bosphorus 4K aom-av1: Speed 8 Realtime - Bosphorus 4K aom-av1: Speed 9 Realtime - Bosphorus 4K apache: 500 apache: 1000 botan: KASUMI botan: KASUMI - Decrypt botan: AES-256 botan: AES-256 - Decrypt botan: Twofish botan: Twofish - Decrypt botan: Blowfish botan: Blowfish - Decrypt botan: CAST-256 botan: CAST-256 - Decrypt botan: ChaCha20Poly1305 botan: ChaCha20Poly1305 - Decrypt blosc: blosclz c-ray: Total Time - 4K, 16 Rays Per Pixel coremark: CoreMark Size 666 - Iterations Per Second dav1d: Summer Nature 4K dav1d: Chimera 1080p 10-bit fftw: Float + SSE - 2D FFT Size 4096 financebench: Repo OpenMP financebench: Bonds OpenMP draco: Lion draco: Church Facade synthmark: VoiceMark_100 graphics-magick: Swirl graphics-magick: Rotate graphics-magick: Sharpen graphics-magick: Enhanced graphics-magick: Resizing graphics-magick: Noise-Gaussian graphics-magick: HWB Color Space john-the-ripper: Blowfish john-the-ripper: MD5 libraw: Post-Processing Benchmark mysqlslap: 2048 mysqlslap: 4096 ncnn: CPU - mobilenet ncnn: CPU - shufflenet-v2 ncnn: CPU - mnasnet ncnn: CPU - efficientnet-b0 ncnn: CPU - blazeface ncnn: CPU - googlenet ncnn: CPU - alexnet ncnn: CPU - resnet50 ncnn: CPU - yolov4-tiny ncnn: CPU - squeezenet_ssd ncnn: CPU - regnety_400m nginx: 1 nginx: 20 nginx: 100 nginx: 200 nginx: 500 nginx: 1000 onednn: IP Shapes 1D - bf16bf16bf16 - CPU onednn: IP Shapes 3D - bf16bf16bf16 - CPU onednn: Convolution Batch Shapes Auto - bf16bf16bf16 - CPU onednn: Deconvolution Batch shapes_1d - bf16bf16bf16 - CPU onednn: Deconvolution Batch shapes_3d - bf16bf16bf16 - CPU onednn: Recurrent Neural Network Training - bf16bf16bf16 - CPU onednn: Recurrent Neural Network Inference - bf16bf16bf16 - CPU encode-opus: WAV To Opus Encode pjsip: INVITE pjsip: OPTIONS, Stateful pjsip: OPTIONS, Stateless pgbench: 100 - 250 - Read Only pgbench: 100 - 250 - Read Only - Average Latency pgbench: 100 - 250 - Read Write pgbench: 100 - 250 - Read Write - Average Latency quantlib: securemark: SecureMark-TLS sqlite-speedtest: Timed Time - Size 1,000 svt-av1: Preset 4 - Bosphorus 4K svt-av1: Preset 8 - Bosphorus 4K svt-hevc: 7 - Bosphorus 1080p svt-hevc: 10 - Bosphorus 1080p svt-vp9: PSNR/SSIM Optimized - Bosphorus 1080p svt-vp9: Visual Quality Optimized - Bosphorus 1080p tachyon: Total Time tnn: CPU - DenseNet tnn: CPU - MobileNet v2 tnn: CPU - SqueezeNet v2 tnn: CPU - SqueezeNet v1.1 tscp: AI Chess Performance vpxenc: Speed 0 - Bosphorus 4K vpxenc: Speed 5 - Bosphorus 4K compress-zstd: 3 - Compression Speed compress-zstd: 8 - Compression Speed compress-zstd: 19 - Compression Speed compress-zstd: 3, Long Mode - Compression Speed compress-zstd: 8, Long Mode - Compression Speed compress-zstd: 19, Long Mode - Compression Speed Clang 13 Clang 12 Clang 11 212825.677 36.000 19.60 45.30 56.65 145589.94 112600.02 77.094 76.248 5761.303 5753.637 288.807 290.469 327.933 333.278 116.103 114.500 855.764 849.956 24671.5 12.594 2185330.036774 533.02 843.96 18489 38153.404297 58281.786458 5967 7202 513.010 1874 728 877 1174 485 600 866 112407 10430000 39.99 712 321 17.38 7.84 8.79 12.66 4.86 17.87 9.64 21.71 27.94 19.21 23.98 75270.65 254133.55 208590.36 196023.59 204880.02 205977.68 2.78910 1.71770 2.07168 3.28114 3.61489 598.020 365.727 9.632 5271 10140 41871 973432 0.257 84854 2.948 2657.3 240447 64.635 4.967 58.982 353.72 626.33 476.72 374.91 13.4699 4370.099 539.646 84.610 400.261 1491816 5.71 15.35 6697.9 2775.9 83.6 863.1 828.0 47.0 210157.651 36.428 19.39 44.84 54.47 121643.80 112287.17 76.916 76.243 5735.246 5700.326 293.730 288.611 329.534 326.798 115.327 114.829 882.165 874.911 24249.3 15.224 2146447.380082 532.51 844.78 18443 37760.885417 58502.854167 5870 7057 503.930 1864 723 758 1104 452 600 852 111335 10275333 36.65 698 319 17.65 11.62 11.01 13.75 6.94 21.24 11.04 21.48 28.35 19.26 37.11 75015.29 251352.56 206297.92 194567.38 204058.28 205740.39 2.79658 1.72558 2.06918 3.05821 3.57952 611.926 368.449 9.908 5291 10185 40364 981525 0.255 84132 2.973 2606.3 250849 65.294 4.849 57.917 340.21 604.45 456.18 365.79 13.9533 4353.389 541.927 83.860 402.255 1481388 5.62 14.11 6321.0 2560.6 80.4 865.6 833.6 45.7 211799.583 36.167 19.32 44.06 54.44 122576.13 120827.45 74.395 73.561 5743.347 5714.916 286.034 279.963 326.769 325.704 114.754 115.648 869.352 866.095 23751.9 14.801 2103884.892521 528.63 842.95 18135 37221.003906 58558.255208 5827 7000 491.027 1860 728 745 1104 473 623 852 113200 8880000 34.55 700 319 17.30 11.46 10.90 15.32 6.07 21.59 9.97 22.36 26.79 19.72 36.26 74606.79 254323.92 205660.13 196465.21 204519.00 205224.87 2.78642 1.71640 2.08089 3.05315 3.59463 608.604 368.248 9.423 5289 10195 41305 967214 0.260 85162 2.938 2589.5 252089 64.415 4.895 57.841 344.59 616.45 460.20 362.67 14.2482 6912.120 773.467 105.397 657.100 1477410 5.60 14.32 6433.3 2729.0 84.8 826.7 798.8 45.5 OpenBenchmarking.org
Aircrack-ng OpenBenchmarking.org k/s, More Is Better Aircrack-ng 1.5.2 Clang 13 Clang 12 Clang 11 50K 100K 150K 200K 250K SE +/- 467.06, N = 3 SE +/- 504.25, N = 3 SE +/- 607.21, N = 3 212825.68 210157.65 211799.58 1. (CXX) g++ options: -O3 -fvisibility=hidden -masm=intel -fcommon -rdynamic -lsqlite3 -lpthread -lz -lcrypto -lhwloc -ldl -lm -pthread
AOBench Size: 2048 x 2048 - Total Time OpenBenchmarking.org Seconds, Fewer Is Better AOBench Size: 2048 x 2048 - Total Time Clang 13 Clang 12 Clang 11 8 16 24 32 40 SE +/- 0.02, N = 3 SE +/- 0.24, N = 3 SE +/- 0.03, N = 3 36.00 36.43 36.17 1. (CC) gcc options: -lm -O3 -march=native
AOM AV1 Encoder Mode: Speed 6 Realtime - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.1 Encoder Mode: Speed 6 Realtime - Input: Bosphorus 4K Clang 13 Clang 12 Clang 11 5 10 15 20 25 SE +/- 0.24, N = 3 SE +/- 0.28, N = 3 SE +/- 0.23, N = 3 19.60 19.39 19.32 1. (CXX) g++ options: -O3 -march=native -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
AOM AV1 Encoder Mode: Speed 8 Realtime - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.1 Encoder Mode: Speed 8 Realtime - Input: Bosphorus 4K Clang 13 Clang 12 Clang 11 10 20 30 40 50 SE +/- 0.42, N = 7 SE +/- 0.40, N = 3 SE +/- 0.36, N = 9 45.30 44.84 44.06 1. (CXX) g++ options: -O3 -march=native -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
AOM AV1 Encoder Mode: Speed 9 Realtime - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.1 Encoder Mode: Speed 9 Realtime - Input: Bosphorus 4K Clang 13 Clang 12 Clang 11 13 26 39 52 65 SE +/- 0.03, N = 3 SE +/- 0.12, N = 3 SE +/- 0.16, N = 3 56.65 54.47 54.44 1. (CXX) g++ options: -O3 -march=native -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
Apache HTTP Server Concurrent Requests: 500 OpenBenchmarking.org Requests Per Second, More Is Better Apache HTTP Server 2.4.48 Concurrent Requests: 500 Clang 13 Clang 12 Clang 11 30K 60K 90K 120K 150K SE +/- 843.46, N = 3 SE +/- 1145.12, N = 15 SE +/- 798.53, N = 3 145589.94 121643.80 122576.13 1. (CC) gcc options: -shared -fPIC -pthread -O3 -march=native
Apache HTTP Server Concurrent Requests: 1000 OpenBenchmarking.org Requests Per Second, More Is Better Apache HTTP Server 2.4.48 Concurrent Requests: 1000 Clang 13 Clang 12 Clang 11 30K 60K 90K 120K 150K SE +/- 485.15, N = 3 SE +/- 534.15, N = 3 SE +/- 924.52, N = 15 112600.02 112287.17 120827.45 1. (CC) gcc options: -shared -fPIC -pthread -O3 -march=native
Botan Test: KASUMI OpenBenchmarking.org MiB/s, More Is Better Botan 2.17.3 Test: KASUMI Clang 13 Clang 12 Clang 11 20 40 60 80 100 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 77.09 76.92 74.40 1. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt
Botan Test: KASUMI - Decrypt OpenBenchmarking.org MiB/s, More Is Better Botan 2.17.3 Test: KASUMI - Decrypt Clang 13 Clang 12 Clang 11 20 40 60 80 100 SE +/- 0.02, N = 3 SE +/- 0.23, N = 3 SE +/- 0.02, N = 3 76.25 76.24 73.56 1. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt
Botan Test: AES-256 OpenBenchmarking.org MiB/s, More Is Better Botan 2.17.3 Test: AES-256 Clang 13 Clang 12 Clang 11 1200 2400 3600 4800 6000 SE +/- 0.33, N = 3 SE +/- 5.15, N = 3 SE +/- 0.30, N = 3 5761.30 5735.25 5743.35 1. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt
Botan Test: AES-256 - Decrypt OpenBenchmarking.org MiB/s, More Is Better Botan 2.17.3 Test: AES-256 - Decrypt Clang 13 Clang 12 Clang 11 1200 2400 3600 4800 6000 SE +/- 0.20, N = 3 SE +/- 0.79, N = 3 SE +/- 0.51, N = 3 5753.64 5700.33 5714.92 1. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt
Botan Test: Twofish OpenBenchmarking.org MiB/s, More Is Better Botan 2.17.3 Test: Twofish Clang 13 Clang 12 Clang 11 60 120 180 240 300 SE +/- 0.22, N = 3 SE +/- 0.97, N = 3 SE +/- 0.21, N = 3 288.81 293.73 286.03 1. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt
Botan Test: Twofish - Decrypt OpenBenchmarking.org MiB/s, More Is Better Botan 2.17.3 Test: Twofish - Decrypt Clang 13 Clang 12 Clang 11 60 120 180 240 300 SE +/- 0.27, N = 3 SE +/- 0.24, N = 3 SE +/- 0.36, N = 3 290.47 288.61 279.96 1. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt
Botan Test: Blowfish OpenBenchmarking.org MiB/s, More Is Better Botan 2.17.3 Test: Blowfish Clang 13 Clang 12 Clang 11 70 140 210 280 350 SE +/- 0.02, N = 3 SE +/- 0.04, N = 3 SE +/- 0.04, N = 3 327.93 329.53 326.77 1. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt
Botan Test: Blowfish - Decrypt OpenBenchmarking.org MiB/s, More Is Better Botan 2.17.3 Test: Blowfish - Decrypt Clang 13 Clang 12 Clang 11 70 140 210 280 350 SE +/- 0.04, N = 3 SE +/- 3.35, N = 3 SE +/- 0.09, N = 3 333.28 326.80 325.70 1. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt
Botan Test: CAST-256 OpenBenchmarking.org MiB/s, More Is Better Botan 2.17.3 Test: CAST-256 Clang 13 Clang 12 Clang 11 30 60 90 120 150 SE +/- 0.02, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 116.10 115.33 114.75 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 2.17.3 Test: CAST-256 - Decrypt Clang 13 Clang 12 Clang 11 30 60 90 120 150 SE +/- 0.03, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 114.50 114.83 115.65 1. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt
Botan Test: ChaCha20Poly1305 OpenBenchmarking.org MiB/s, More Is Better Botan 2.17.3 Test: ChaCha20Poly1305 Clang 13 Clang 12 Clang 11 200 400 600 800 1000 SE +/- 4.73, N = 3 SE +/- 0.87, N = 3 SE +/- 0.40, N = 3 855.76 882.17 869.35 1. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt
Botan Test: ChaCha20Poly1305 - Decrypt OpenBenchmarking.org MiB/s, More Is Better Botan 2.17.3 Test: ChaCha20Poly1305 - Decrypt Clang 13 Clang 12 Clang 11 200 400 600 800 1000 SE +/- 1.46, N = 3 SE +/- 0.95, N = 3 SE +/- 0.04, N = 3 849.96 874.91 866.10 1. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt
C-Blosc Compressor: blosclz OpenBenchmarking.org MB/s, More Is Better C-Blosc 2.0 Compressor: blosclz Clang 13 Clang 12 Clang 11 5K 10K 15K 20K 25K SE +/- 33.59, N = 3 SE +/- 34.61, N = 3 SE +/- 34.48, N = 3 24671.5 24249.3 23751.9 1. (CXX) g++ options: -O3 -march=native
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 Clang 13 Clang 12 Clang 11 4 8 12 16 20 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 12.59 15.22 14.80 1. (CC) gcc options: -lm -lpthread -O3 -march=native
Coremark CoreMark Size 666 - Iterations Per Second OpenBenchmarking.org Iterations/Sec, More Is Better Coremark 1.0 CoreMark Size 666 - Iterations Per Second Clang 13 Clang 12 Clang 11 500K 1000K 1500K 2000K 2500K SE +/- 1510.09, N = 3 SE +/- 3711.92, N = 3 SE +/- 2482.75, N = 3 2185330.04 2146447.38 2103884.89 1. (CC) gcc options: -O2 -O3 -march=native -lrt" -lrt
dav1d Video Input: Summer Nature 4K OpenBenchmarking.org FPS, More Is Better dav1d 0.9.1 Video Input: Summer Nature 4K Clang 13 Clang 12 Clang 11 120 240 360 480 600 SE +/- 0.44, N = 3 SE +/- 0.77, N = 3 SE +/- 2.65, N = 3 533.02 532.51 528.63 MIN: 186.74 / MAX: 587.2 MIN: 186.64 / MAX: 587.12 MIN: 176.65 / MAX: 587.68 1. (CC) gcc options: -O3 -march=native -pthread
dav1d Video Input: Chimera 1080p 10-bit OpenBenchmarking.org FPS, More Is Better dav1d 0.9.1 Video Input: Chimera 1080p 10-bit Clang 13 Clang 12 Clang 11 200 400 600 800 1000 SE +/- 2.33, N = 3 SE +/- 1.52, N = 3 SE +/- 0.82, N = 3 843.96 844.78 842.95 MIN: 503.8 / MAX: 1131.86 MIN: 517.09 / MAX: 1121.33 MIN: 515.35 / MAX: 1115.74 1. (CC) gcc options: -O3 -march=native -pthread
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 Clang 13 Clang 12 Clang 11 4K 8K 12K 16K 20K SE +/- 43.73, N = 3 SE +/- 34.47, N = 3 SE +/- 187.54, N = 4 18489 18443 18135 1. (CC) gcc options: -pthread -O3 -march=native -lm
FinanceBench Benchmark: Repo OpenMP OpenBenchmarking.org ms, Fewer Is Better FinanceBench 2016-07-25 Benchmark: Repo OpenMP Clang 13 Clang 12 Clang 11 8K 16K 24K 32K 40K SE +/- 450.24, N = 4 SE +/- 290.04, N = 3 SE +/- 19.15, N = 3 38153.40 37760.89 37221.00 1. (CXX) g++ options: -O3 -march=native -fopenmp
FinanceBench Benchmark: Bonds OpenMP OpenBenchmarking.org ms, Fewer Is Better FinanceBench 2016-07-25 Benchmark: Bonds OpenMP Clang 13 Clang 12 Clang 11 13K 26K 39K 52K 65K SE +/- 17.71, N = 3 SE +/- 82.28, N = 3 SE +/- 38.93, N = 3 58281.79 58502.85 58558.26 1. (CXX) g++ options: -O3 -march=native -fopenmp
Google Draco Model: Lion OpenBenchmarking.org ms, Fewer Is Better Google Draco 1.4.1 Model: Lion Clang 13 Clang 12 Clang 11 1300 2600 3900 5200 6500 SE +/- 1.73, N = 3 5967 5870 5827 1. (CXX) g++ options: -O3 -march=native
Google Draco Model: Church Facade OpenBenchmarking.org ms, Fewer Is Better Google Draco 1.4.1 Model: Church Facade Clang 13 Clang 12 Clang 11 1500 3000 4500 6000 7500 SE +/- 4.26, N = 3 SE +/- 3.18, N = 3 7202 7057 7000 1. (CXX) g++ options: -O3 -march=native
Google SynthMark Test: VoiceMark_100 OpenBenchmarking.org Voices, More Is Better Google SynthMark 20201109 Test: VoiceMark_100 Clang 13 Clang 12 Clang 11 110 220 330 440 550 SE +/- 0.05, N = 3 SE +/- 0.04, N = 3 SE +/- 0.01, N = 3 513.01 503.93 491.03 1. (CXX) g++ options: -lm -lpthread -std=c++11 -Ofast
GraphicsMagick Operation: Swirl OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.33 Operation: Swirl Clang 13 Clang 12 Clang 11 400 800 1200 1600 2000 SE +/- 8.69, N = 3 SE +/- 8.51, N = 3 SE +/- 13.09, N = 3 1874 1864 1860 1. (CC) gcc options: -fopenmp -O3 -march=native -pthread -ljbig -lwebp -lwebpmux -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread
GraphicsMagick Operation: Rotate OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.33 Operation: Rotate Clang 13 Clang 12 Clang 11 160 320 480 640 800 SE +/- 7.80, N = 3 SE +/- 2.65, N = 3 SE +/- 2.40, N = 3 728 723 728 1. (CC) gcc options: -fopenmp -O3 -march=native -pthread -ljbig -lwebp -lwebpmux -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread
GraphicsMagick Operation: Sharpen OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.33 Operation: Sharpen Clang 13 Clang 12 Clang 11 200 400 600 800 1000 SE +/- 5.24, N = 3 SE +/- 0.67, N = 3 SE +/- 3.18, N = 3 877 758 745 1. (CC) gcc options: -fopenmp -O3 -march=native -pthread -ljbig -lwebp -lwebpmux -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread
GraphicsMagick Operation: Enhanced OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.33 Operation: Enhanced Clang 13 Clang 12 Clang 11 300 600 900 1200 1500 SE +/- 5.78, N = 3 SE +/- 5.49, N = 3 SE +/- 0.67, N = 3 1174 1104 1104 1. (CC) gcc options: -fopenmp -O3 -march=native -pthread -ljbig -lwebp -lwebpmux -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread
GraphicsMagick Operation: Resizing OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.33 Operation: Resizing Clang 13 Clang 12 Clang 11 100 200 300 400 500 SE +/- 8.56, N = 15 SE +/- 9.74, N = 15 SE +/- 14.35, N = 12 485 452 473 1. (CC) gcc options: -fopenmp -O3 -march=native -pthread -ljbig -lwebp -lwebpmux -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread
GraphicsMagick Operation: Noise-Gaussian OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.33 Operation: Noise-Gaussian Clang 13 Clang 12 Clang 11 130 260 390 520 650 SE +/- 3.06, N = 3 SE +/- 4.10, N = 3 SE +/- 2.33, N = 3 600 600 623 1. (CC) gcc options: -fopenmp -O3 -march=native -pthread -ljbig -lwebp -lwebpmux -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread
GraphicsMagick Operation: HWB Color Space OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.33 Operation: HWB Color Space Clang 13 Clang 12 Clang 11 200 400 600 800 1000 SE +/- 8.76, N = 3 SE +/- 5.60, N = 15 SE +/- 6.84, N = 3 866 852 852 1. (CC) gcc options: -fopenmp -O3 -march=native -pthread -ljbig -lwebp -lwebpmux -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread
John The Ripper Test: Blowfish OpenBenchmarking.org Real C/S, More Is Better John The Ripper 1.9.0-jumbo-1 Test: Blowfish Clang 13 Clang 12 Clang 11 20K 40K 60K 80K 100K SE +/- 41.83, N = 3 SE +/- 138.68, N = 3 SE +/- 249.93, N = 3 112407 111335 113200 1. (CC) gcc options: -m64 -lssl -lcrypto -fopenmp -lgmp -pthread -lm -lz -ldl -lcrypt -lbz2
John The Ripper Test: MD5 OpenBenchmarking.org Real C/S, More Is Better John The Ripper 1.9.0-jumbo-1 Test: MD5 Clang 13 Clang 12 Clang 11 2M 4M 6M 8M 10M SE +/- 3785.94, N = 3 SE +/- 16973.84, N = 3 SE +/- 8504.90, N = 3 10430000 10275333 8880000 1. (CC) gcc options: -m64 -lssl -lcrypto -fopenmp -lgmp -pthread -lm -lz -ldl -lcrypt -lbz2
LibRaw Post-Processing Benchmark OpenBenchmarking.org Mpix/sec, More Is Better LibRaw 0.20 Post-Processing Benchmark Clang 13 Clang 12 Clang 11 9 18 27 36 45 SE +/- 0.19, N = 3 SE +/- 0.23, N = 3 SE +/- 0.13, N = 3 39.99 36.65 34.55 1. (CXX) g++ options: -O3 -march=native -fopenmp -ljpeg -lz -lm
MariaDB Clients: 2048 OpenBenchmarking.org Queries Per Second, More Is Better MariaDB 10.6.4 Clients: 2048 Clang 13 Clang 12 Clang 11 150 300 450 600 750 SE +/- 1.71, N = 3 SE +/- 6.96, N = 9 SE +/- 7.30, N = 9 712 698 700 -lpthread -lm -lstdc++ -lpthread -lm -lstdc++ -lbz2 -lsnappy 1. (CXX) g++ options: -fPIC -O3 -march=native -fstack-protector -shared -pthread -lrt -lz -ldl
MariaDB Clients: 4096 OpenBenchmarking.org Queries Per Second, More Is Better MariaDB 10.6.4 Clients: 4096 Clang 13 Clang 12 Clang 11 70 140 210 280 350 SE +/- 1.31, N = 3 SE +/- 1.07, N = 3 SE +/- 1.96, N = 3 321 319 319 -lpthread -lm -lstdc++ -lpthread -lm -lstdc++ -lbz2 -lsnappy 1. (CXX) g++ options: -fPIC -O3 -march=native -fstack-protector -shared -pthread -lrt -lz -ldl
NCNN Target: CPU - Model: mobilenet OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: CPU - Model: mobilenet Clang 13 Clang 12 Clang 11 4 8 12 16 20 SE +/- 0.11, N = 3 SE +/- 0.16, N = 3 SE +/- 0.27, N = 14 17.38 17.65 17.30 MIN: 16.17 / MAX: 40.05 MIN: 16.51 / MAX: 19.27 MIN: 15.79 / MAX: 37.29 1. (CXX) g++ options: -O3 -march=native -rdynamic -lomp -lpthread -pthread
NCNN Target: CPU - Model: shufflenet-v2 OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: CPU - Model: shufflenet-v2 Clang 13 Clang 12 Clang 11 3 6 9 12 15 SE +/- 0.01, N = 3 SE +/- 1.05, N = 3 SE +/- 0.67, N = 14 7.84 11.62 11.46 MIN: 7.49 / MAX: 13.76 MIN: 7.71 / MAX: 25.56 MIN: 7.56 / MAX: 31.76 1. (CXX) g++ options: -O3 -march=native -rdynamic -lomp -lpthread -pthread
NCNN Target: CPU - Model: mnasnet OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: CPU - Model: mnasnet Clang 13 Clang 12 Clang 11 3 6 9 12 15 SE +/- 1.33, N = 3 SE +/- 1.31, N = 3 SE +/- 0.66, N = 14 8.79 11.01 10.90 MIN: 6.69 / MAX: 26.58 MIN: 7.09 / MAX: 20.3 MIN: 6.9 / MAX: 32.84 1. (CXX) g++ options: -O3 -march=native -rdynamic -lomp -lpthread -pthread
NCNN Target: CPU - Model: efficientnet-b0 OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: CPU - Model: efficientnet-b0 Clang 13 Clang 12 Clang 11 4 8 12 16 20 SE +/- 2.13, N = 3 SE +/- 2.00, N = 3 SE +/- 1.01, N = 14 12.66 13.75 15.32 MIN: 8.73 / MAX: 27.07 MIN: 9.12 / MAX: 41.76 MIN: 8.59 / MAX: 45.64 1. (CXX) g++ options: -O3 -march=native -rdynamic -lomp -lpthread -pthread
NCNN Target: CPU - Model: blazeface OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: CPU - Model: blazeface Clang 13 Clang 12 Clang 11 2 4 6 8 10 SE +/- 0.01, N = 3 SE +/- 1.08, N = 3 SE +/- 0.47, N = 14 4.86 6.94 6.07 MIN: 4.57 / MAX: 9.45 MIN: 4.49 / MAX: 19.88 MIN: 4.35 / MAX: 27.78 1. (CXX) g++ options: -O3 -march=native -rdynamic -lomp -lpthread -pthread
NCNN Target: CPU - Model: googlenet OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: CPU - Model: googlenet Clang 13 Clang 12 Clang 11 5 10 15 20 25 SE +/- 0.31, N = 3 SE +/- 1.87, N = 3 SE +/- 1.02, N = 14 17.87 21.24 21.59 MIN: 16.58 / MAX: 37.88 MIN: 17.28 / MAX: 39.77 MIN: 16.19 / MAX: 50.35 1. (CXX) g++ options: -O3 -march=native -rdynamic -lomp -lpthread -pthread
NCNN Target: CPU - Model: alexnet OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: CPU - Model: alexnet Clang 13 Clang 12 Clang 11 3 6 9 12 15 SE +/- 0.17, N = 3 SE +/- 1.31, N = 3 SE +/- 0.16, N = 14 9.64 11.04 9.97 MIN: 8.9 / MAX: 11.05 MIN: 9.24 / MAX: 14.73 MIN: 8.85 / MAX: 29.23 1. (CXX) g++ options: -O3 -march=native -rdynamic -lomp -lpthread -pthread
NCNN Target: CPU - Model: resnet50 OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: CPU - Model: resnet50 Clang 13 Clang 12 Clang 11 5 10 15 20 25 SE +/- 0.29, N = 3 SE +/- 0.14, N = 3 SE +/- 0.61, N = 14 21.71 21.48 22.36 MIN: 19.54 / MAX: 44.52 MIN: 19.9 / MAX: 40.42 MIN: 18.98 / MAX: 71.34 1. (CXX) g++ options: -O3 -march=native -rdynamic -lomp -lpthread -pthread
NCNN Target: CPU - Model: yolov4-tiny OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: CPU - Model: yolov4-tiny Clang 13 Clang 12 Clang 11 7 14 21 28 35 SE +/- 0.54, N = 3 SE +/- 0.55, N = 3 SE +/- 0.26, N = 14 27.94 28.35 26.79 MIN: 25.71 / MAX: 39.58 MIN: 25.63 / MAX: 60.64 MIN: 23.92 / MAX: 56.1 1. (CXX) g++ options: -O3 -march=native -rdynamic -lomp -lpthread -pthread
NCNN Target: CPU - Model: squeezenet_ssd OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: CPU - Model: squeezenet_ssd Clang 13 Clang 12 Clang 11 5 10 15 20 25 SE +/- 0.23, N = 3 SE +/- 0.22, N = 3 SE +/- 0.53, N = 14 19.21 19.26 19.72 MIN: 18.04 / MAX: 38.36 MIN: 18.05 / MAX: 35.83 MIN: 17.67 / MAX: 58.39 1. (CXX) g++ options: -O3 -march=native -rdynamic -lomp -lpthread -pthread
NCNN Target: CPU - Model: regnety_400m OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: CPU - Model: regnety_400m Clang 13 Clang 12 Clang 11 9 18 27 36 45 SE +/- 1.77, N = 3 SE +/- 3.84, N = 3 SE +/- 2.48, N = 14 23.98 37.11 36.26 MIN: 20.12 / MAX: 66.47 MIN: 19.88 / MAX: 96.76 MIN: 18.78 / MAX: 124.57 1. (CXX) g++ options: -O3 -march=native -rdynamic -lomp -lpthread -pthread
nginx Concurrent Requests: 1 OpenBenchmarking.org Requests Per Second, More Is Better nginx 1.21.1 Concurrent Requests: 1 Clang 13 Clang 12 Clang 11 16K 32K 48K 64K 80K SE +/- 160.67, N = 3 SE +/- 102.54, N = 3 SE +/- 131.50, N = 3 75270.65 75015.29 74606.79 1. (CC) gcc options: -ldl -lpthread -lcrypt -lz -O3 -march=native
nginx Concurrent Requests: 20 OpenBenchmarking.org Requests Per Second, More Is Better nginx 1.21.1 Concurrent Requests: 20 Clang 13 Clang 12 Clang 11 50K 100K 150K 200K 250K SE +/- 1379.02, N = 3 SE +/- 1222.93, N = 3 SE +/- 2398.86, N = 3 254133.55 251352.56 254323.92 1. (CC) gcc options: -ldl -lpthread -lcrypt -lz -O3 -march=native
nginx Concurrent Requests: 100 OpenBenchmarking.org Requests Per Second, More Is Better nginx 1.21.1 Concurrent Requests: 100 Clang 13 Clang 12 Clang 11 40K 80K 120K 160K 200K SE +/- 987.48, N = 3 SE +/- 431.14, N = 3 SE +/- 1506.43, N = 3 208590.36 206297.92 205660.13 1. (CC) gcc options: -ldl -lpthread -lcrypt -lz -O3 -march=native
nginx Concurrent Requests: 200 OpenBenchmarking.org Requests Per Second, More Is Better nginx 1.21.1 Concurrent Requests: 200 Clang 13 Clang 12 Clang 11 40K 80K 120K 160K 200K SE +/- 911.83, N = 3 SE +/- 312.30, N = 3 SE +/- 2823.39, N = 3 196023.59 194567.38 196465.21 1. (CC) gcc options: -ldl -lpthread -lcrypt -lz -O3 -march=native
nginx Concurrent Requests: 500 OpenBenchmarking.org Requests Per Second, More Is Better nginx 1.21.1 Concurrent Requests: 500 Clang 13 Clang 12 Clang 11 40K 80K 120K 160K 200K SE +/- 936.49, N = 3 SE +/- 63.72, N = 3 SE +/- 554.68, N = 3 204880.02 204058.28 204519.00 1. (CC) gcc options: -ldl -lpthread -lcrypt -lz -O3 -march=native
nginx Concurrent Requests: 1000 OpenBenchmarking.org Requests Per Second, More Is Better nginx 1.21.1 Concurrent Requests: 1000 Clang 13 Clang 12 Clang 11 40K 80K 120K 160K 200K SE +/- 1305.06, N = 3 SE +/- 632.41, N = 3 SE +/- 947.34, N = 3 205977.68 205740.39 205224.87 1. (CC) gcc options: -ldl -lpthread -lcrypt -lz -O3 -march=native
oneDNN Harness: IP Shapes 1D - Data Type: bf16bf16bf16 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.1.2 Harness: IP Shapes 1D - Data Type: bf16bf16bf16 - Engine: CPU Clang 13 Clang 12 Clang 11 0.6292 1.2584 1.8876 2.5168 3.146 SE +/- 0.00435, N = 3 SE +/- 0.00591, N = 3 SE +/- 0.00451, N = 3 2.78910 2.79658 2.78642 MIN: 2.65 MIN: 2.65 MIN: 2.65 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp=libomp -msse4.1 -fPIC -pie -lpthread -ldl
oneDNN Harness: IP Shapes 3D - Data Type: bf16bf16bf16 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.1.2 Harness: IP Shapes 3D - Data Type: bf16bf16bf16 - Engine: CPU Clang 13 Clang 12 Clang 11 0.3883 0.7766 1.1649 1.5532 1.9415 SE +/- 0.00225, N = 3 SE +/- 0.00427, N = 3 SE +/- 0.00619, N = 3 1.71770 1.72558 1.71640 MIN: 1.55 MIN: 1.57 MIN: 1.53 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp=libomp -msse4.1 -fPIC -pie -lpthread -ldl
oneDNN Harness: Convolution Batch Shapes Auto - Data Type: bf16bf16bf16 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.1.2 Harness: Convolution Batch Shapes Auto - Data Type: bf16bf16bf16 - Engine: CPU Clang 13 Clang 12 Clang 11 0.4682 0.9364 1.4046 1.8728 2.341 SE +/- 0.00196, N = 3 SE +/- 0.00197, N = 3 SE +/- 0.00072, N = 3 2.07168 2.06918 2.08089 MIN: 1.99 MIN: 1.99 MIN: 1.99 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp=libomp -msse4.1 -fPIC -pie -lpthread -ldl
oneDNN Harness: Deconvolution Batch shapes_1d - Data Type: bf16bf16bf16 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.1.2 Harness: Deconvolution Batch shapes_1d - Data Type: bf16bf16bf16 - Engine: CPU Clang 13 Clang 12 Clang 11 0.7383 1.4766 2.2149 2.9532 3.6915 SE +/- 0.00367, N = 3 SE +/- 0.00384, N = 3 SE +/- 0.00886, N = 3 3.28114 3.05821 3.05315 MIN: 3.08 MIN: 2.86 MIN: 2.87 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp=libomp -msse4.1 -fPIC -pie -lpthread -ldl
oneDNN Harness: Deconvolution Batch shapes_3d - Data Type: bf16bf16bf16 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.1.2 Harness: Deconvolution Batch shapes_3d - Data Type: bf16bf16bf16 - Engine: CPU Clang 13 Clang 12 Clang 11 0.8134 1.6268 2.4402 3.2536 4.067 SE +/- 0.00211, N = 3 SE +/- 0.00151, N = 3 SE +/- 0.00881, N = 3 3.61489 3.57952 3.59463 MIN: 3.52 MIN: 3.5 MIN: 3.5 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp=libomp -msse4.1 -fPIC -pie -lpthread -ldl
oneDNN Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.1.2 Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPU Clang 13 Clang 12 Clang 11 130 260 390 520 650 SE +/- 0.92, N = 3 SE +/- 6.83, N = 4 SE +/- 5.71, N = 13 598.02 611.93 608.60 MIN: 575.43 MIN: 569.44 MIN: 570.79 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp=libomp -msse4.1 -fPIC -pie -lpthread -ldl
oneDNN Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.1.2 Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPU Clang 13 Clang 12 Clang 11 80 160 240 320 400 SE +/- 0.40, N = 3 SE +/- 1.79, N = 3 SE +/- 2.59, N = 3 365.73 368.45 368.25 MIN: 355.4 MIN: 347.27 MIN: 349.99 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp=libomp -msse4.1 -fPIC -pie -lpthread -ldl
Opus Codec Encoding WAV To Opus Encode OpenBenchmarking.org Seconds, Fewer Is Better Opus Codec Encoding 1.3.1 WAV To Opus Encode Clang 13 Clang 12 Clang 11 3 6 9 12 15 SE +/- 0.069, N = 5 SE +/- 0.006, N = 5 SE +/- 0.013, N = 5 9.632 9.908 9.423 1. (CXX) g++ options: -O3 -march=native -logg -lm
PJSIP Method: INVITE OpenBenchmarking.org Responses Per Second, More Is Better PJSIP 2.11 Method: INVITE Clang 13 Clang 12 Clang 11 1100 2200 3300 4400 5500 SE +/- 11.10, N = 3 SE +/- 10.68, N = 3 SE +/- 8.50, N = 3 5271 5291 5289 1. (CC) gcc options: -lSDL2 -lavformat -lavcodec -lswscale -lavutil -lstdc++ -lssl -lcrypto -luuid -lm -lrt -lpthread -lasound -O3 -march=native
PJSIP Method: OPTIONS, Stateful OpenBenchmarking.org Responses Per Second, More Is Better PJSIP 2.11 Method: OPTIONS, Stateful Clang 13 Clang 12 Clang 11 2K 4K 6K 8K 10K SE +/- 43.11, N = 3 SE +/- 11.92, N = 3 SE +/- 4.48, N = 3 10140 10185 10195 1. (CC) gcc options: -lSDL2 -lavformat -lavcodec -lswscale -lavutil -lstdc++ -lssl -lcrypto -luuid -lm -lrt -lpthread -lasound -O3 -march=native
PJSIP Method: OPTIONS, Stateless OpenBenchmarking.org Responses Per Second, More Is Better PJSIP 2.11 Method: OPTIONS, Stateless Clang 13 Clang 12 Clang 11 9K 18K 27K 36K 45K SE +/- 380.52, N = 3 SE +/- 510.13, N = 3 SE +/- 575.37, N = 3 41871 40364 41305 1. (CC) gcc options: -lSDL2 -lavformat -lavcodec -lswscale -lavutil -lstdc++ -lssl -lcrypto -luuid -lm -lrt -lpthread -lasound -O3 -march=native
PostgreSQL pgbench Scaling Factor: 100 - Clients: 250 - Mode: Read Only OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 13.0 Scaling Factor: 100 - Clients: 250 - Mode: Read Only Clang 13 Clang 12 Clang 11 200K 400K 600K 800K 1000K SE +/- 10672.94, N = 3 SE +/- 3346.94, N = 3 SE +/- 16009.81, N = 15 973432 981525 967214 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O3 -march=native -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
PostgreSQL pgbench Scaling Factor: 100 - Clients: 250 - Mode: Read Only - Average Latency OpenBenchmarking.org ms, Fewer Is Better PostgreSQL pgbench 13.0 Scaling Factor: 100 - Clients: 250 - Mode: Read Only - Average Latency Clang 13 Clang 12 Clang 11 0.0585 0.117 0.1755 0.234 0.2925 SE +/- 0.003, N = 3 SE +/- 0.001, N = 3 SE +/- 0.005, N = 15 0.257 0.255 0.260 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O3 -march=native -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
PostgreSQL pgbench Scaling Factor: 100 - Clients: 250 - Mode: Read Write OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 13.0 Scaling Factor: 100 - Clients: 250 - Mode: Read Write Clang 13 Clang 12 Clang 11 20K 40K 60K 80K 100K SE +/- 119.61, N = 3 SE +/- 85.43, N = 3 SE +/- 786.14, N = 3 84854 84132 85162 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O3 -march=native -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
PostgreSQL pgbench Scaling Factor: 100 - Clients: 250 - Mode: Read Write - Average Latency OpenBenchmarking.org ms, Fewer Is Better PostgreSQL pgbench 13.0 Scaling Factor: 100 - Clients: 250 - Mode: Read Write - Average Latency Clang 13 Clang 12 Clang 11 0.6689 1.3378 2.0067 2.6756 3.3445 SE +/- 0.004, N = 3 SE +/- 0.003, N = 3 SE +/- 0.027, N = 3 2.948 2.973 2.938 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O3 -march=native -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
QuantLib OpenBenchmarking.org MFLOPS, More Is Better QuantLib 1.21 Clang 13 Clang 12 Clang 11 600 1200 1800 2400 3000 SE +/- 8.72, N = 3 SE +/- 4.59, N = 3 SE +/- 5.39, N = 3 2657.3 2606.3 2589.5 1. (CXX) g++ options: -O3 -march=native -rdynamic
SecureMark Benchmark: SecureMark-TLS OpenBenchmarking.org marks, More Is Better SecureMark 1.0.4 Benchmark: SecureMark-TLS Clang 13 Clang 12 Clang 11 50K 100K 150K 200K 250K SE +/- 40.95, N = 3 SE +/- 339.82, N = 3 SE +/- 87.48, N = 3 240447 250849 252089 1. (CC) gcc options: -pedantic -O3
SQLite Speedtest Timed Time - Size 1,000 OpenBenchmarking.org Seconds, Fewer Is Better SQLite Speedtest 3.30 Timed Time - Size 1,000 Clang 13 Clang 12 Clang 11 15 30 45 60 75 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 SE +/- 0.03, N = 3 64.64 65.29 64.42 1. (CC) gcc options: -O3 -march=native -ldl -lz -lpthread
SVT-AV1 Encoder Mode: Preset 4 - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 0.8.7 Encoder Mode: Preset 4 - Input: Bosphorus 4K Clang 13 Clang 12 Clang 11 1.1176 2.2352 3.3528 4.4704 5.588 SE +/- 0.027, N = 3 SE +/- 0.004, N = 3 SE +/- 0.020, N = 3 4.967 4.849 4.895 1. (CXX) g++ options: -O3 -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq -pie
SVT-AV1 Encoder Mode: Preset 8 - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 0.8.7 Encoder Mode: Preset 8 - Input: Bosphorus 4K Clang 13 Clang 12 Clang 11 13 26 39 52 65 SE +/- 0.38, N = 3 SE +/- 0.14, N = 3 SE +/- 0.15, N = 3 58.98 57.92 57.84 1. (CXX) g++ options: -O3 -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq -pie
SVT-HEVC Tuning: 7 - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better SVT-HEVC 1.5.0 Tuning: 7 - Input: Bosphorus 1080p Clang 13 Clang 12 Clang 11 80 160 240 320 400 SE +/- 3.85, N = 3 SE +/- 1.14, N = 3 SE +/- 2.06, N = 3 353.72 340.21 344.59 1. (CC) gcc options: -O3 -march=native -fPIE -fPIC -O2 -pie -rdynamic -lpthread -lrt
SVT-HEVC Tuning: 10 - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better SVT-HEVC 1.5.0 Tuning: 10 - Input: Bosphorus 1080p Clang 13 Clang 12 Clang 11 140 280 420 560 700 SE +/- 3.02, N = 3 SE +/- 2.53, N = 3 SE +/- 2.02, N = 3 626.33 604.45 616.45 1. (CC) gcc options: -O3 -march=native -fPIE -fPIC -O2 -pie -rdynamic -lpthread -lrt
SVT-VP9 Tuning: PSNR/SSIM Optimized - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better SVT-VP9 0.3 Tuning: PSNR/SSIM Optimized - Input: Bosphorus 1080p Clang 13 Clang 12 Clang 11 100 200 300 400 500 SE +/- 5.26, N = 3 SE +/- 4.57, N = 3 SE +/- 4.56, N = 3 476.72 456.18 460.20 1. (CC) gcc options: -O3 -fcommon -march=native -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm
SVT-VP9 Tuning: Visual Quality Optimized - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better SVT-VP9 0.3 Tuning: Visual Quality Optimized - Input: Bosphorus 1080p Clang 13 Clang 12 Clang 11 80 160 240 320 400 SE +/- 4.27, N = 3 SE +/- 2.53, N = 3 SE +/- 1.62, N = 3 374.91 365.79 362.67 1. (CC) gcc options: -O3 -fcommon -march=native -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm
Tachyon Total Time OpenBenchmarking.org Seconds, Fewer Is Better Tachyon 0.99b6 Total Time Clang 13 Clang 12 Clang 11 4 8 12 16 20 SE +/- 0.04, N = 3 SE +/- 0.06, N = 3 SE +/- 0.02, N = 3 13.47 13.95 14.25 1. (CC) gcc options: -m64 -O3 -fomit-frame-pointer -ffast-math -ltachyon -lm -lpthread
TNN Target: CPU - Model: DenseNet OpenBenchmarking.org ms, Fewer Is Better TNN 0.3 Target: CPU - Model: DenseNet Clang 13 Clang 12 Clang 11 1500 3000 4500 6000 7500 SE +/- 2.30, N = 3 SE +/- 1.66, N = 3 SE +/- 3.50, N = 3 4370.10 4353.39 6912.12 MIN: 4351.72 / MAX: 4450.96 MIN: 4332.87 / MAX: 4442 MIN: 6888.33 / MAX: 6947.75 1. (CXX) g++ options: -O3 -march=native -fopenmp=libomp -pthread -fvisibility=hidden -fvisibility=default -rdynamic -ldl
TNN Target: CPU - Model: MobileNet v2 OpenBenchmarking.org ms, Fewer Is Better TNN 0.3 Target: CPU - Model: MobileNet v2 Clang 13 Clang 12 Clang 11 170 340 510 680 850 SE +/- 0.66, N = 3 SE +/- 0.70, N = 3 SE +/- 0.69, N = 3 539.65 541.93 773.47 MIN: 536.06 / MAX: 559.33 MIN: 536.56 / MAX: 554.17 MIN: 690.55 / MAX: 820.36 1. (CXX) g++ options: -O3 -march=native -fopenmp=libomp -pthread -fvisibility=hidden -fvisibility=default -rdynamic -ldl
TNN Target: CPU - Model: SqueezeNet v2 OpenBenchmarking.org ms, Fewer Is Better TNN 0.3 Target: CPU - Model: SqueezeNet v2 Clang 13 Clang 12 Clang 11 20 40 60 80 100 SE +/- 0.00, N = 3 SE +/- 0.05, N = 3 SE +/- 0.15, N = 3 84.61 83.86 105.40 MIN: 84.23 / MAX: 85 MIN: 83.28 / MAX: 84.63 MIN: 104.83 / MAX: 106.1 1. (CXX) g++ options: -O3 -march=native -fopenmp=libomp -pthread -fvisibility=hidden -fvisibility=default -rdynamic -ldl
TNN Target: CPU - Model: SqueezeNet v1.1 OpenBenchmarking.org ms, Fewer Is Better TNN 0.3 Target: CPU - Model: SqueezeNet v1.1 Clang 13 Clang 12 Clang 11 140 280 420 560 700 SE +/- 0.27, N = 3 SE +/- 0.19, N = 3 SE +/- 0.05, N = 3 400.26 402.26 657.10 MIN: 399.7 / MAX: 401.33 MIN: 401.13 / MAX: 403.41 MIN: 656.47 / MAX: 657.89 1. (CXX) g++ options: -O3 -march=native -fopenmp=libomp -pthread -fvisibility=hidden -fvisibility=default -rdynamic -ldl
TSCP AI Chess Performance OpenBenchmarking.org Nodes Per Second, More Is Better TSCP 1.81 AI Chess Performance Clang 13 Clang 12 Clang 11 300K 600K 900K 1200K 1500K SE +/- 806.80, N = 5 SE +/- 1489.72, N = 5 SE +/- 794.00, N = 5 1491816 1481388 1477410 1. (CC) gcc options: -O3 -march=native
VP9 libvpx Encoding Speed: Speed 0 - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better VP9 libvpx Encoding 1.10.0 Speed: Speed 0 - Input: Bosphorus 4K Clang 13 Clang 12 Clang 11 1.2848 2.5696 3.8544 5.1392 6.424 SE +/- 0.06, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 5.71 5.62 5.60 1. (CXX) g++ options: -m64 -lm -lpthread -O3 -march=native -fPIC -U_FORTIFY_SOURCE -std=gnu++11
VP9 libvpx Encoding Speed: Speed 5 - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better VP9 libvpx Encoding 1.10.0 Speed: Speed 5 - Input: Bosphorus 4K Clang 13 Clang 12 Clang 11 4 8 12 16 20 SE +/- 0.14, N = 15 SE +/- 0.09, N = 3 SE +/- 0.13, N = 3 15.35 14.11 14.32 1. (CXX) g++ options: -m64 -lm -lpthread -O3 -march=native -fPIC -U_FORTIFY_SOURCE -std=gnu++11
Zstd Compression Compression Level: 3 - Compression Speed OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.5.0 Compression Level: 3 - Compression Speed Clang 13 Clang 12 Clang 11 1400 2800 4200 5600 7000 SE +/- 47.01, N = 3 SE +/- 60.99, N = 3 SE +/- 78.33, N = 3 6697.9 6321.0 6433.3 1. (CC) gcc options: -O3 -march=native -pthread -lz -llzma
Zstd Compression Compression Level: 8 - Compression Speed OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.5.0 Compression Level: 8 - Compression Speed Clang 13 Clang 12 Clang 11 600 1200 1800 2400 3000 SE +/- 7.16, N = 3 SE +/- 34.31, N = 15 SE +/- 32.58, N = 3 2775.9 2560.6 2729.0 1. (CC) gcc options: -O3 -march=native -pthread -lz -llzma
Zstd Compression Compression Level: 19 - Compression Speed OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.5.0 Compression Level: 19 - Compression Speed Clang 13 Clang 12 Clang 11 20 40 60 80 100 SE +/- 0.64, N = 10 SE +/- 0.45, N = 3 SE +/- 0.85, N = 15 83.6 80.4 84.8 1. (CC) gcc options: -O3 -march=native -pthread -lz -llzma
Zstd Compression Compression Level: 3, Long Mode - Compression Speed OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.5.0 Compression Level: 3, Long Mode - Compression Speed Clang 13 Clang 12 Clang 11 200 400 600 800 1000 SE +/- 1.29, N = 3 SE +/- 2.11, N = 3 SE +/- 1.30, N = 3 863.1 865.6 826.7 1. (CC) gcc options: -O3 -march=native -pthread -lz -llzma
Zstd Compression Compression Level: 8, Long Mode - Compression Speed OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.5.0 Compression Level: 8, Long Mode - Compression Speed Clang 13 Clang 12 Clang 11 200 400 600 800 1000 SE +/- 5.79, N = 3 SE +/- 1.68, N = 3 SE +/- 0.29, N = 3 828.0 833.6 798.8 1. (CC) gcc options: -O3 -march=native -pthread -lz -llzma
Zstd Compression Compression Level: 19, Long Mode - Compression Speed OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.5.0 Compression Level: 19, Long Mode - Compression Speed Clang 13 Clang 12 Clang 11 11 22 33 44 55 SE +/- 0.53, N = 15 SE +/- 0.55, N = 15 SE +/- 0.51, N = 4 47.0 45.7 45.5 1. (CC) gcc options: -O3 -march=native -pthread -lz -llzma
Phoronix Test Suite v10.8.4