Memory Folios AMD Ryzen 9 5950X 16-Core testing with a ASUS ROG CROSSHAIR VIII HERO (WI-FI) (3601 BIOS) and AMD Radeon RX 5600 OEM/5600 XT / 5700/5700 8GB on Ubuntu 20.04 via the Phoronix Test Suite.
HTML result view exported from: https://openbenchmarking.org/result/2107162-PTS-MEMORYFO09&grs .
Memory Folios Processor Motherboard Chipset Memory Disk Graphics Audio Monitor Network OS Kernel Desktop Display Server OpenGL Vulkan Compiler File-System Screen Resolution Folios 14 Linux 5.14-rc1 AMD Ryzen 9 5950X 16-Core @ 3.40GHz (16 Cores / 32 Threads) ASUS ROG CROSSHAIR VIII HERO (WI-FI) (3601 BIOS) AMD Starship/Matisse 32GB 500GB Western Digital WDS500G3X0C-00SJG0 AMD Radeon RX 5600 OEM/5600 XT / 5700/5700 8GB (2100/875MHz) AMD Navi 10 HDMI Audio ASUS MG28U Realtek RTL8125 2.5GbE + Intel I211 + Intel Wi-Fi 6 AX200 Ubuntu 20.04 5.14.0-rc1-folio (x86_64) 20210715 GNOME Shell 3.36.9 X Server 1.20.9 4.6 Mesa 20.2.6 (LLVM 11.0.0) 1.2.131 GCC 9.3.0 ext4 3840x2160 5.14.0-rc1-vanilla (x86_64) 20210715 OpenBenchmarking.org Kernel Details - Transparent Huge Pages: madvise Compiler Details - --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,gm2 --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-9-HskZEa/gcc-9-9.3.0/debian/tmp-nvptx/usr,hsa --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v Disk Details - NONE / errors=remount-ro,relatime,rw / Block Size: 4096 Processor Details - Scaling Governor: acpi-cpufreq ondemand (Boost: Enabled) - CPU Microcode: 0xa201016 Graphics Details - GLAMOR Python Details - Python 3.8.10 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 IBRS_FW STIBP: always-on RSB filling + srbds: Not affected + tsx_async_abort: Not affected
Memory Folios stress-ng: Context Switching draco: Church Facade stress-ng: CPU Stress compilebench: Initial Create pybench: Total For Average Test Times npb: SP.B natron: Spaceship sqlite: 8 compilebench: Compile rocksdb: Read While Writing srsran: 4G PHY_DL_Test 100 PRB SISO 256-QAM npb: LU.C t-test1: 1 t-test1: 2 toktx: Zstd Compression 19 toktx: Zstd Compression 9 srsran: 5G PHY_DL_NR Test 270 PRB SISO 256-QAM srsran: 4G PHY_DL_Test 100 PRB MIMO 256-QAM keydb: sqlite-speedtest: Timed Time - Size 1,000 srsran: OFDM_Test stress-ng: Socket Activity rocksdb: Seq Fill build-llvm: Unix Makefiles srsran: 5G PHY_DL_NR Test 270 PRB SISO 256-QAM phpbench: PHP Benchmark Suite tnn: CPU - SqueezeNet v2 leveldb: Seek Rand npb: SP.C stress-ng: System V Message Passing luaradio: Complex Phase srsran: 4G PHY_DL_Test 100 PRB MIMO 256-QAM compress-zstd: 19 - Decompression Speed compilebench: Read Compiled Tree leveldb: Hot Read compress-lz4: 3 - Compression Speed luaradio: Five Back to Back FIR Filters stress-ng: SENDFILE compress-zstd: 8, Long Mode - Compression Speed rocksdb: Rand Fill Sync toktx: UASTC 3 + Zstd Compression 19 npb: MG.C pgbench: 100 - 50 - Read Only - Average Latency compress-zstd: 8 - Compression Speed srsran: 4G PHY_DL_Test 100 PRB SISO 256-QAM build-linux-kernel: Time To Compile rocksdb: Rand Fill leveldb: Overwrite npb: IS.D toktx: UASTC 3 npb: CG.C srsran: 4G PHY_DL_Test 100 PRB MIMO 64-QAM srsran: 4G PHY_DL_Test 100 PRB MIMO 64-QAM rocksdb: Read Rand Write Rand leveldb: Overwrite compress-zstd: 19, Long Mode - Decompression Speed srsran: 4G PHY_DL_Test 100 PRB SISO 64-QAM compress-zstd: 8 - Decompression Speed tnn: CPU - DenseNet paraview: Wavelet Volume - 3840 x 2160 paraview: Wavelet Volume - 3840 x 2160 xmrig: Wownero - 1M svt-hevc: 10 - Bosphorus 1080p leveldb: Fill Sync leveldb: Rand Read ocrmypdf: Processing 60 Page PDF Document srsran: 4G PHY_DL_Test 100 PRB SISO 64-QAM xmrig: Monero - 1M compress-lz4: 3 - Decompression Speed leveldb: Rand Delete blender: Barbershop - CPU-Only compress-lz4: 9 - Compression Speed aom-av1: Speed 8 Realtime - Bosphorus 4K unvanquished: 3840 x 2160 - Ultra hugin: Panorama Photo Assistant + Stitching Time tnn: CPU - MobileNet v2 build-llvm: Ninja rocksdb: Rand Read svt-av1: Preset 4 - Bosphorus 4K tensorflow-lite: Mobilenet Float tensorflow-lite: Inception ResNet V2 leveldb: Seq Fill compress-zstd: 19 - Compression Speed svt-av1: Preset 8 - Bosphorus 4K toktx: UASTC 4 + Zstd Compression 19 srsran: 5G PHY_DL_NR Test 52 PRB SISO 64-QAM pgbench: 100 - 50 - Read Only compress-lz4: 9 - Decompression Speed liquid-dsp: 32 - 256 - 57 openvkl: vklBenchmark blender: BMW27 - CPU-Only liquid-dsp: 16 - 256 - 57 stress-ng: Semaphores npb: FT.C npb: EP.C unvanquished: 3840 x 2160 - High compress-zstd: 8, Long Mode - Decompression Speed build-wasmer: Time To Compile build-mesa: Time To Compile tensorflow-lite: Mobilenet Quant fs-mark: 1000 Files, 1MB Size tnn: CPU - SqueezeNet v1.1 tensorflow-lite: SqueezeNet aom-av1: Speed 9 Realtime - Bosphorus 4K tensorflow-lite: Inception V4 leveldb: Seq Fill leveldb: Rand Fill luaradio: FM Deemphasis Filter unvanquished: 3840 x 2160 - Medium vpxenc: Speed 5 - Bosphorus 4K srsran: 5G PHY_DL_NR Test 52 PRB SISO 64-QAM paraview: Many Spheres - 3840 x 2160 paraview: Many Spheres - 3840 x 2160 leveldb: Rand Fill npb: BT.C paraview: Wavelet Contour - 3840 x 2160 paraview: Wavelet Contour - 3840 x 2160 blosc: blosclz luaradio: Hilbert Transform sqlite: 1 rawtherapee: Total Benchmark Time tensorflow-lite: NASNet Mobile draco: Lion rocksdb: Update Rand influxdb: 4 - 10000 - 2,5000,1 - 10000 build-nodejs: Time To Compile oidn: RTLightmap.hdr.4096x4096 oidn: RT.ldr_alb_nrm.3840x2160 oidn: RT.hdr_alb_nrm.3840x2160 ospray: San Miguel - Path Tracer ospray: San Miguel - SciVis compress-zstd: 19, Long Mode - Compression Speed gravitymark: 3840 x 2160 - Vulkan leveldb: Fill Sync mcperf: Add - 1 stress-ng: MMAP pgbench: 100 - 50 - Read Write - Average Latency pgbench: 100 - 50 - Read Write fs-mark: 4000 Files, 32 Sub Dirs, 1MB Size fs-mark: 5000 Files, 1MB Size, 4 Threads Folios 14 Linux 5.14-rc1 4252749.27 5441 10219.23 791.86 710 7605.78 3.7 34.265 2577.14 4157809 524.0 27277.22 10.156 4.261 14.757 2.140 100.3 536.8 825158.88 44.741 162683333 19817.16 1515090 429.151 179.4 846610 49.944 18.929 5340.58 21848700.89 808.4 184.4 3978.2 4699.87 13.496 71.01 1690.7 378808.57 1250.1 27262 10.632 9794.90 0.112 1256.9 310.9 49.982 1345985 86.153 658.58 6.450 7015.13 171.9 477.8 2861763 41.1 4109.3 480.4 4627.1 2418.921 255.36 4085.690 13634.5 356.07 1192.788 13.757 15.677 260.4 7181.1 13042.2 83.257 300.11 69.20 55.20 351.4 34.892 223.428 406.278 114121586 2.138 63498.8 1230850 87.023 51.3 23.733 158.194 163.6 447961 13048.1 1083333333 285 80.51 1025800000 2330190.95 12160.58 1875.75 389.5 4895.5 57.529 34.025 68795.7 761.6 211.004 95962.6 73.06 1366393 40.6 40.9 465.6 395.4 19.75 77.1 6345.612 63.29 86.558 23964.57 257.55 2683.996 30058.8 128.1 8.935 46.437 104513 4144 791729 2149719.4 249.578 0.27 0.55 0.55 2.45 29.41 36.5 62.7 2.9 103090.8 431.89 1.737 28869 453.7 604.8 3653119.41 5132 10629.99 821.62 730 7811.79 3.8 35.186 2510.65 4059438 536.3 27899.42 9.936 4.172 14.464 2.098 102.3 526.5 840501.65 43.927 159766667 19465.75 1541890 422.045 182.3 860137 49.177 19.216 5419.76 22157554.24 797.2 181.9 4027.9 4758.54 13.659 71.84 1710.1 382823.95 1263.3 26985 10.532 9883.75 0.111 1268.0 313.6 49.552 1335128 86.849 653.57 6.401 6962.07 173.2 481.4 2840514 40.8 4081.2 483.6 4657.6 2403.406 253.74 4059.911 13549.2 358.20 1199.779 13.836 15.766 259.0 7142.9 13110.8 83.687 298.58 69.55 55.47 353.1 34.729 224.406 404.511 114609777 2.147 63240.0 1225970 87.366 51.5 23.645 157.610 164.2 449591 13095.1 1087200000 286 80.23 1022300000 2322589.07 12121.69 1869.89 390.7 4910.4 57.355 33.924 68595.8 759.4 211.605 95711.3 73.25 1362860 40.5 40.8 464.5 394.5 19.71 77.0 6353.636 63.37 86.661 23937.77 257.28 2681.202 30083.1 128.0 8.929 46.465 104571 4143 791624 2149476.5 249.565 0.27 0.55 0.55 2.45 29.41 36.5 62.7 2.9 447.97 1.756 28608 433.8 605.6 OpenBenchmarking.org
Stress-NG Test: Context Switching OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: Context Switching Folios 14 Linux 5.14-rc1 900K 1800K 2700K 3600K 4500K SE +/- 43827.00, N = 15 SE +/- 43327.36, N = 4 4252749.27 3653119.41 1. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lsctp -lz -ldl -lpthread -lc
Google Draco Model: Church Facade OpenBenchmarking.org ms, Fewer Is Better Google Draco 1.4.1 Model: Church Facade Folios 14 Linux 5.14-rc1 1200 2400 3600 4800 6000 SE +/- 7.17, N = 3 SE +/- 15.06, N = 3 5441 5132 1. (CXX) g++ options: -O3
Stress-NG Test: CPU Stress OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: CPU Stress Folios 14 Linux 5.14-rc1 2K 4K 6K 8K 10K SE +/- 121.03, N = 3 SE +/- 107.78, N = 15 10219.23 10629.99 1. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lsctp -lz -ldl -lpthread -lc
Compile Bench Test: Initial Create OpenBenchmarking.org MB/s, More Is Better Compile Bench 0.6 Test: Initial Create Folios 14 Linux 5.14-rc1 200 400 600 800 1000 SE +/- 10.02, N = 3 SE +/- 17.92, N = 3 791.86 821.62
PyBench Total For Average Test Times OpenBenchmarking.org Milliseconds, Fewer Is Better PyBench 2018-02-16 Total For Average Test Times Folios 14 Linux 5.14-rc1 160 320 480 640 800 SE +/- 7.36, N = 3 SE +/- 2.31, N = 3 710 730
NAS Parallel Benchmarks Test / Class: SP.B OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: SP.B Folios 14 Linux 5.14-rc1 2K 4K 6K 8K 10K SE +/- 3.48, N = 3 SE +/- 9.52, N = 3 7605.78 7811.79 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi 2. Open MPI 4.0.3
Natron Input: Spaceship OpenBenchmarking.org FPS, More Is Better Natron 2.4 Input: Spaceship Folios 14 Linux 5.14-rc1 0.855 1.71 2.565 3.42 4.275 SE +/- 0.03, N = 15 SE +/- 0.04, N = 4 3.7 3.8
SQLite Threads / Copies: 8 OpenBenchmarking.org Seconds, Fewer Is Better SQLite 3.30.1 Threads / Copies: 8 Folios 14 Linux 5.14-rc1 8 16 24 32 40 SE +/- 0.09, N = 3 SE +/- 0.19, N = 3 34.27 35.19 1. (CC) gcc options: -O2 -lz -lm -ldl -lpthread
Compile Bench Test: Compile OpenBenchmarking.org MB/s, More Is Better Compile Bench 0.6 Test: Compile Folios 14 Linux 5.14-rc1 600 1200 1800 2400 3000 SE +/- 38.86, N = 15 SE +/- 22.43, N = 15 2577.14 2510.65
Facebook RocksDB Test: Read While Writing OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 6.22.1 Test: Read While Writing Folios 14 Linux 5.14-rc1 900K 1800K 2700K 3600K 4500K SE +/- 33377.49, N = 15 SE +/- 41379.43, N = 6 4157809 4059438 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
srsRAN Test: 4G PHY_DL_Test 100 PRB SISO 256-QAM OpenBenchmarking.org eNb Mb/s, More Is Better srsRAN 21.04 Test: 4G PHY_DL_Test 100 PRB SISO 256-QAM Folios 14 Linux 5.14-rc1 120 240 360 480 600 SE +/- 3.99, N = 12 SE +/- 1.32, N = 3 524.0 536.3 1. (CXX) g++ options: -std=c++11 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -rdynamic -lpthread -lbladeRF -lm -lfftw3f -lmbedcrypto
NAS Parallel Benchmarks Test / Class: LU.C OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: LU.C Folios 14 Linux 5.14-rc1 6K 12K 18K 24K 30K SE +/- 21.01, N = 3 SE +/- 19.52, N = 3 27277.22 27899.42 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi 2. Open MPI 4.0.3
t-test1 Threads: 1 OpenBenchmarking.org Seconds, Fewer Is Better t-test1 2017-01-13 Threads: 1 Folios 14 Linux 5.14-rc1 3 6 9 12 15 SE +/- 0.110, N = 4 SE +/- 0.057, N = 3 10.156 9.936 1. (CC) gcc options: -pthread
t-test1 Threads: 2 OpenBenchmarking.org Seconds, Fewer Is Better t-test1 2017-01-13 Threads: 2 Folios 14 Linux 5.14-rc1 0.9587 1.9174 2.8761 3.8348 4.7935 SE +/- 0.021, N = 3 SE +/- 0.033, N = 3 4.261 4.172 1. (CC) gcc options: -pthread
KTX-Software toktx Settings: Zstd Compression 19 OpenBenchmarking.org Seconds, Fewer Is Better KTX-Software toktx 4.0 Settings: Zstd Compression 19 Folios 14 Linux 5.14-rc1 4 8 12 16 20 SE +/- 0.03, N = 3 SE +/- 0.07, N = 3 14.76 14.46
KTX-Software toktx Settings: Zstd Compression 9 OpenBenchmarking.org Seconds, Fewer Is Better KTX-Software toktx 4.0 Settings: Zstd Compression 9 Folios 14 Linux 5.14-rc1 0.4815 0.963 1.4445 1.926 2.4075 SE +/- 0.008, N = 3 SE +/- 0.020, N = 3 2.140 2.098
srsRAN Test: 5G PHY_DL_NR Test 270 PRB SISO 256-QAM OpenBenchmarking.org UE Mb/s, More Is Better srsRAN 21.04 Test: 5G PHY_DL_NR Test 270 PRB SISO 256-QAM Folios 14 Linux 5.14-rc1 20 40 60 80 100 SE +/- 0.38, N = 3 SE +/- 0.50, N = 7 100.3 102.3 1. (CXX) g++ options: -std=c++11 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -rdynamic -lpthread -lbladeRF -lm -lfftw3f -lmbedcrypto
srsRAN Test: 4G PHY_DL_Test 100 PRB MIMO 256-QAM OpenBenchmarking.org eNb Mb/s, More Is Better srsRAN 21.04 Test: 4G PHY_DL_Test 100 PRB MIMO 256-QAM Folios 14 Linux 5.14-rc1 120 240 360 480 600 SE +/- 6.65, N = 3 SE +/- 4.25, N = 3 536.8 526.5 1. (CXX) g++ options: -std=c++11 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -rdynamic -lpthread -lbladeRF -lm -lfftw3f -lmbedcrypto
KeyDB OpenBenchmarking.org Ops/sec, More Is Better KeyDB 6.0.16 Folios 14 Linux 5.14-rc1 200K 400K 600K 800K 1000K SE +/- 2561.53, N = 3 SE +/- 4774.01, N = 3 825158.88 840501.65 1. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre
SQLite Speedtest Timed Time - Size 1,000 OpenBenchmarking.org Seconds, Fewer Is Better SQLite Speedtest 3.30 Timed Time - Size 1,000 Folios 14 Linux 5.14-rc1 10 20 30 40 50 SE +/- 0.13, N = 3 SE +/- 0.07, N = 3 44.74 43.93 1. (CC) gcc options: -O2 -ldl -lz -lpthread
srsRAN Test: OFDM_Test OpenBenchmarking.org Samples / Second, More Is Better srsRAN 21.04 Test: OFDM_Test Folios 14 Linux 5.14-rc1 30M 60M 90M 120M 150M SE +/- 1621607.57, N = 6 SE +/- 1194737.14, N = 15 162683333 159766667 1. (CXX) g++ options: -std=c++11 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -rdynamic -lpthread -lbladeRF -lm -lfftw3f -lmbedcrypto
Stress-NG Test: Socket Activity OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: Socket Activity Folios 14 Linux 5.14-rc1 4K 8K 12K 16K 20K SE +/- 58.91, N = 3 SE +/- 136.59, N = 3 19817.16 19465.75 1. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lsctp -lz -ldl -lpthread -lc
Facebook RocksDB Test: Sequential Fill OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 6.22.1 Test: Sequential Fill Folios 14 Linux 5.14-rc1 300K 600K 900K 1200K 1500K SE +/- 7752.92, N = 3 SE +/- 18416.88, N = 3 1515090 1541890 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
Timed LLVM Compilation Build System: Unix Makefiles OpenBenchmarking.org Seconds, Fewer Is Better Timed LLVM Compilation 12.0 Build System: Unix Makefiles Folios 14 Linux 5.14-rc1 90 180 270 360 450 SE +/- 3.84, N = 3 SE +/- 0.84, N = 3 429.15 422.05
srsRAN Test: 5G PHY_DL_NR Test 270 PRB SISO 256-QAM OpenBenchmarking.org eNb Mb/s, More Is Better srsRAN 21.04 Test: 5G PHY_DL_NR Test 270 PRB SISO 256-QAM Folios 14 Linux 5.14-rc1 40 80 120 160 200 SE +/- 0.75, N = 3 SE +/- 1.69, N = 7 179.4 182.3 1. (CXX) g++ options: -std=c++11 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -rdynamic -lpthread -lbladeRF -lm -lfftw3f -lmbedcrypto
PHPBench PHP Benchmark Suite OpenBenchmarking.org Score, More Is Better PHPBench 0.8.1 PHP Benchmark Suite Folios 14 Linux 5.14-rc1 200K 400K 600K 800K 1000K SE +/- 6776.40, N = 3 SE +/- 9203.55, N = 3 846610 860137
TNN Target: CPU - Model: SqueezeNet v2 OpenBenchmarking.org ms, Fewer Is Better TNN 0.3 Target: CPU - Model: SqueezeNet v2 Folios 14 Linux 5.14-rc1 11 22 33 44 55 SE +/- 0.45, N = 3 SE +/- 0.46, N = 3 49.94 49.18 MIN: 49.26 / MAX: 50.96 MIN: 48.58 / MAX: 50.34 1. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl
LevelDB Benchmark: Seek Random OpenBenchmarking.org Microseconds Per Op, Fewer Is Better LevelDB 1.22 Benchmark: Seek Random Folios 14 Linux 5.14-rc1 5 10 15 20 25 SE +/- 0.02, N = 3 SE +/- 0.06, N = 3 18.93 19.22 1. (CXX) g++ options: -O3 -lsnappy -lpthread
NAS Parallel Benchmarks Test / Class: SP.C OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: SP.C Folios 14 Linux 5.14-rc1 1200 2400 3600 4800 6000 SE +/- 2.61, N = 3 SE +/- 4.15, N = 3 5340.58 5419.76 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi 2. Open MPI 4.0.3
Stress-NG Test: System V Message Passing OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: System V Message Passing Folios 14 Linux 5.14-rc1 5M 10M 15M 20M 25M SE +/- 122315.21, N = 3 SE +/- 30612.94, N = 3 21848700.89 22157554.24 1. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lsctp -lz -ldl -lpthread -lc
LuaRadio Test: Complex Phase OpenBenchmarking.org MiB/s, More Is Better LuaRadio 0.9.1 Test: Complex Phase Folios 14 Linux 5.14-rc1 200 400 600 800 1000 SE +/- 1.67, N = 3 SE +/- 2.01, N = 3 808.4 797.2
srsRAN Test: 4G PHY_DL_Test 100 PRB MIMO 256-QAM OpenBenchmarking.org UE Mb/s, More Is Better srsRAN 21.04 Test: 4G PHY_DL_Test 100 PRB MIMO 256-QAM Folios 14 Linux 5.14-rc1 40 80 120 160 200 SE +/- 2.82, N = 3 SE +/- 0.78, N = 3 184.4 181.9 1. (CXX) g++ options: -std=c++11 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -rdynamic -lpthread -lbladeRF -lm -lfftw3f -lmbedcrypto
Zstd Compression Compression Level: 19 - Decompression Speed OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.5.0 Compression Level: 19 - Decompression Speed Folios 14 Linux 5.14-rc1 900 1800 2700 3600 4500 SE +/- 14.66, N = 3 SE +/- 30.38, N = 3 3978.2 4027.9 1. (CC) gcc options: -O3 -pthread -lz
Compile Bench Test: Read Compiled Tree OpenBenchmarking.org MB/s, More Is Better Compile Bench 0.6 Test: Read Compiled Tree Folios 14 Linux 5.14-rc1 1000 2000 3000 4000 5000 SE +/- 26.41, N = 3 SE +/- 48.30, N = 3 4699.87 4758.54
LevelDB Benchmark: Hot Read OpenBenchmarking.org Microseconds Per Op, Fewer Is Better LevelDB 1.22 Benchmark: Hot Read Folios 14 Linux 5.14-rc1 4 8 12 16 20 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 13.50 13.66 1. (CXX) g++ options: -O3 -lsnappy -lpthread
LZ4 Compression Compression Level: 3 - Compression Speed OpenBenchmarking.org MB/s, More Is Better LZ4 Compression 1.9.3 Compression Level: 3 - Compression Speed Folios 14 Linux 5.14-rc1 16 32 48 64 80 SE +/- 0.81, N = 4 SE +/- 0.88, N = 4 71.01 71.84 1. (CC) gcc options: -O3
LuaRadio Test: Five Back to Back FIR Filters OpenBenchmarking.org MiB/s, More Is Better LuaRadio 0.9.1 Test: Five Back to Back FIR Filters Folios 14 Linux 5.14-rc1 400 800 1200 1600 2000 SE +/- 2.15, N = 3 SE +/- 1.31, N = 3 1690.7 1710.1
Stress-NG Test: SENDFILE OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: SENDFILE Folios 14 Linux 5.14-rc1 80K 160K 240K 320K 400K SE +/- 156.76, N = 3 SE +/- 37.50, N = 3 378808.57 382823.95 1. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lsctp -lz -ldl -lpthread -lc
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 Folios 14 Linux 5.14-rc1 300 600 900 1200 1500 SE +/- 5.53, N = 3 SE +/- 4.10, N = 3 1250.1 1263.3 1. (CC) gcc options: -O3 -pthread -lz
Facebook RocksDB Test: Random Fill Sync OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 6.22.1 Test: Random Fill Sync Folios 14 Linux 5.14-rc1 6K 12K 18K 24K 30K SE +/- 358.15, N = 3 SE +/- 187.32, N = 13 27262 26985 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
KTX-Software toktx Settings: UASTC 3 + Zstd Compression 19 OpenBenchmarking.org Seconds, Fewer Is Better KTX-Software toktx 4.0 Settings: UASTC 3 + Zstd Compression 19 Folios 14 Linux 5.14-rc1 3 6 9 12 15 SE +/- 0.09, N = 3 SE +/- 0.02, N = 3 10.63 10.53
NAS Parallel Benchmarks Test / Class: MG.C OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: MG.C Folios 14 Linux 5.14-rc1 2K 4K 6K 8K 10K SE +/- 5.88, N = 3 SE +/- 1.03, N = 3 9794.90 9883.75 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi 2. Open MPI 4.0.3
PostgreSQL pgbench Scaling Factor: 100 - Clients: 50 - Mode: Read Only - Average Latency OpenBenchmarking.org ms, Fewer Is Better PostgreSQL pgbench 13.0 Scaling Factor: 100 - Clients: 50 - Mode: Read Only - Average Latency Folios 14 Linux 5.14-rc1 0.0252 0.0504 0.0756 0.1008 0.126 SE +/- 0.000, N = 3 SE +/- 0.000, N = 3 0.112 0.111 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
Zstd Compression Compression Level: 8 - Compression Speed OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.5.0 Compression Level: 8 - Compression Speed Folios 14 Linux 5.14-rc1 300 600 900 1200 1500 SE +/- 14.22, N = 15 SE +/- 17.30, N = 3 1256.9 1268.0 1. (CC) gcc options: -O3 -pthread -lz
srsRAN Test: 4G PHY_DL_Test 100 PRB SISO 256-QAM OpenBenchmarking.org UE Mb/s, More Is Better srsRAN 21.04 Test: 4G PHY_DL_Test 100 PRB SISO 256-QAM Folios 14 Linux 5.14-rc1 70 140 210 280 350 SE +/- 0.51, N = 12 SE +/- 1.92, N = 3 310.9 313.6 1. (CXX) g++ options: -std=c++11 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -rdynamic -lpthread -lbladeRF -lm -lfftw3f -lmbedcrypto
Timed Linux Kernel Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed Linux Kernel Compilation 5.10.20 Time To Compile Folios 14 Linux 5.14-rc1 11 22 33 44 55 SE +/- 0.38, N = 3 SE +/- 0.43, N = 3 49.98 49.55
Facebook RocksDB Test: Random Fill OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 6.22.1 Test: Random Fill Folios 14 Linux 5.14-rc1 300K 600K 900K 1200K 1500K SE +/- 6794.33, N = 3 SE +/- 10205.35, N = 3 1345985 1335128 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
LevelDB Benchmark: Overwrite OpenBenchmarking.org Microseconds Per Op, Fewer Is Better LevelDB 1.22 Benchmark: Overwrite Folios 14 Linux 5.14-rc1 20 40 60 80 100 SE +/- 0.40, N = 3 SE +/- 0.06, N = 3 86.15 86.85 1. (CXX) g++ options: -O3 -lsnappy -lpthread
NAS Parallel Benchmarks Test / Class: IS.D OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: IS.D Folios 14 Linux 5.14-rc1 140 280 420 560 700 SE +/- 2.26, N = 3 SE +/- 1.25, N = 3 658.58 653.57 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi 2. Open MPI 4.0.3
KTX-Software toktx Settings: UASTC 3 OpenBenchmarking.org Seconds, Fewer Is Better KTX-Software toktx 4.0 Settings: UASTC 3 Folios 14 Linux 5.14-rc1 2 4 6 8 10 SE +/- 0.003, N = 3 SE +/- 0.006, N = 3 6.450 6.401
NAS Parallel Benchmarks Test / Class: CG.C OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: CG.C Folios 14 Linux 5.14-rc1 1500 3000 4500 6000 7500 SE +/- 30.67, N = 3 SE +/- 48.53, N = 3 7015.13 6962.07 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi 2. Open MPI 4.0.3
srsRAN Test: 4G PHY_DL_Test 100 PRB MIMO 64-QAM OpenBenchmarking.org UE Mb/s, More Is Better srsRAN 21.04 Test: 4G PHY_DL_Test 100 PRB MIMO 64-QAM Folios 14 Linux 5.14-rc1 40 80 120 160 200 SE +/- 0.03, N = 3 SE +/- 1.58, N = 3 171.9 173.2 1. (CXX) g++ options: -std=c++11 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -rdynamic -lpthread -lbladeRF -lm -lfftw3f -lmbedcrypto
srsRAN Test: 4G PHY_DL_Test 100 PRB MIMO 64-QAM OpenBenchmarking.org eNb Mb/s, More Is Better srsRAN 21.04 Test: 4G PHY_DL_Test 100 PRB MIMO 64-QAM Folios 14 Linux 5.14-rc1 100 200 300 400 500 SE +/- 1.15, N = 3 SE +/- 3.01, N = 3 477.8 481.4 1. (CXX) g++ options: -std=c++11 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -rdynamic -lpthread -lbladeRF -lm -lfftw3f -lmbedcrypto
Facebook RocksDB Test: Read Random Write Random OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 6.22.1 Test: Read Random Write Random Folios 14 Linux 5.14-rc1 600K 1200K 1800K 2400K 3000K SE +/- 10062.25, N = 3 SE +/- 10400.38, N = 3 2861763 2840514 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
LevelDB Benchmark: Overwrite OpenBenchmarking.org MB/s, More Is Better LevelDB 1.22 Benchmark: Overwrite Folios 14 Linux 5.14-rc1 9 18 27 36 45 SE +/- 0.20, N = 3 SE +/- 0.03, N = 3 41.1 40.8 1. (CXX) g++ options: -O3 -lsnappy -lpthread
Zstd Compression Compression Level: 19, Long Mode - Decompression Speed OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.5.0 Compression Level: 19, Long Mode - Decompression Speed Folios 14 Linux 5.14-rc1 900 1800 2700 3600 4500 SE +/- 24.21, N = 3 SE +/- 35.47, N = 3 4109.3 4081.2 1. (CC) gcc options: -O3 -pthread -lz
srsRAN Test: 4G PHY_DL_Test 100 PRB SISO 64-QAM OpenBenchmarking.org eNb Mb/s, More Is Better srsRAN 21.04 Test: 4G PHY_DL_Test 100 PRB SISO 64-QAM Folios 14 Linux 5.14-rc1 100 200 300 400 500 SE +/- 2.22, N = 3 SE +/- 0.90, N = 3 480.4 483.6 1. (CXX) g++ options: -std=c++11 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -rdynamic -lpthread -lbladeRF -lm -lfftw3f -lmbedcrypto
Zstd Compression Compression Level: 8 - Decompression Speed OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.5.0 Compression Level: 8 - Decompression Speed Folios 14 Linux 5.14-rc1 1000 2000 3000 4000 5000 SE +/- 20.72, N = 15 SE +/- 15.73, N = 3 4627.1 4657.6 1. (CC) gcc options: -O3 -pthread -lz
TNN Target: CPU - Model: DenseNet OpenBenchmarking.org ms, Fewer Is Better TNN 0.3 Target: CPU - Model: DenseNet Folios 14 Linux 5.14-rc1 500 1000 1500 2000 2500 SE +/- 6.65, N = 3 SE +/- 7.92, N = 3 2418.92 2403.41 MIN: 2330.48 / MAX: 2499.05 MIN: 2320.89 / MAX: 2488.63 1. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl
ParaView Test: Wavelet Volume - Resolution: 3840 x 2160 OpenBenchmarking.org Frames / Sec, More Is Better ParaView 5.9 Test: Wavelet Volume - Resolution: 3840 x 2160 Folios 14 Linux 5.14-rc1 60 120 180 240 300 SE +/- 0.23, N = 3 SE +/- 0.63, N = 3 255.36 253.74
ParaView Test: Wavelet Volume - Resolution: 3840 x 2160 OpenBenchmarking.org MiVoxels / Sec, More Is Better ParaView 5.9 Test: Wavelet Volume - Resolution: 3840 x 2160 Folios 14 Linux 5.14-rc1 900 1800 2700 3600 4500 SE +/- 3.70, N = 3 SE +/- 10.07, N = 3 4085.69 4059.91
Xmrig Variant: Wownero - Hash Count: 1M OpenBenchmarking.org H/s, More Is Better Xmrig 6.12.1 Variant: Wownero - Hash Count: 1M Folios 14 Linux 5.14-rc1 3K 6K 9K 12K 15K SE +/- 34.11, N = 3 SE +/- 123.37, N = 3 13634.5 13549.2 1. (CXX) g++ options: -fexceptions -fno-rtti -maes -O3 -Ofast -static-libgcc -static-libstdc++ -rdynamic -lssl -lcrypto -luv -lpthread -lrt -ldl -lhwloc
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 Folios 14 Linux 5.14-rc1 80 160 240 320 400 SE +/- 3.69, N = 12 SE +/- 3.70, N = 12 356.07 358.20 1. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt
LevelDB Benchmark: Fill Sync OpenBenchmarking.org Microseconds Per Op, Fewer Is Better LevelDB 1.22 Benchmark: Fill Sync Folios 14 Linux 5.14-rc1 300 600 900 1200 1500 SE +/- 2.46, N = 3 SE +/- 1.61, N = 3 1192.79 1199.78 1. (CXX) g++ options: -O3 -lsnappy -lpthread
LevelDB Benchmark: Random Read OpenBenchmarking.org Microseconds Per Op, Fewer Is Better LevelDB 1.22 Benchmark: Random Read Folios 14 Linux 5.14-rc1 4 8 12 16 20 SE +/- 0.03, N = 3 SE +/- 0.05, N = 3 13.76 13.84 1. (CXX) g++ options: -O3 -lsnappy -lpthread
OCRMyPDF Processing 60 Page PDF Document OpenBenchmarking.org Seconds, Fewer Is Better OCRMyPDF 9.6.0+dfsg Processing 60 Page PDF Document Folios 14 Linux 5.14-rc1 4 8 12 16 20 SE +/- 0.05, N = 3 SE +/- 0.04, N = 3 15.68 15.77
srsRAN Test: 4G PHY_DL_Test 100 PRB SISO 64-QAM OpenBenchmarking.org UE Mb/s, More Is Better srsRAN 21.04 Test: 4G PHY_DL_Test 100 PRB SISO 64-QAM Folios 14 Linux 5.14-rc1 60 120 180 240 300 SE +/- 1.90, N = 3 SE +/- 0.69, N = 3 260.4 259.0 1. (CXX) g++ options: -std=c++11 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -rdynamic -lpthread -lbladeRF -lm -lfftw3f -lmbedcrypto
Xmrig Variant: Monero - Hash Count: 1M OpenBenchmarking.org H/s, More Is Better Xmrig 6.12.1 Variant: Monero - Hash Count: 1M Folios 14 Linux 5.14-rc1 1500 3000 4500 6000 7500 SE +/- 20.64, N = 3 SE +/- 61.40, N = 3 7181.1 7142.9 1. (CXX) g++ options: -fexceptions -fno-rtti -maes -O3 -Ofast -static-libgcc -static-libstdc++ -rdynamic -lssl -lcrypto -luv -lpthread -lrt -ldl -lhwloc
LZ4 Compression Compression Level: 3 - Decompression Speed OpenBenchmarking.org MB/s, More Is Better LZ4 Compression 1.9.3 Compression Level: 3 - Decompression Speed Folios 14 Linux 5.14-rc1 3K 6K 9K 12K 15K SE +/- 22.11, N = 4 SE +/- 44.01, N = 4 13042.2 13110.8 1. (CC) gcc options: -O3
LevelDB Benchmark: Random Delete OpenBenchmarking.org Microseconds Per Op, Fewer Is Better LevelDB 1.22 Benchmark: Random Delete Folios 14 Linux 5.14-rc1 20 40 60 80 100 SE +/- 0.43, N = 3 SE +/- 0.45, N = 3 83.26 83.69 1. (CXX) g++ options: -O3 -lsnappy -lpthread
Blender Blend File: Barbershop - Compute: CPU-Only OpenBenchmarking.org Seconds, Fewer Is Better Blender 2.92 Blend File: Barbershop - Compute: CPU-Only Folios 14 Linux 5.14-rc1 70 140 210 280 350 SE +/- 0.16, N = 3 SE +/- 0.63, N = 3 300.11 298.58
LZ4 Compression Compression Level: 9 - Compression Speed OpenBenchmarking.org MB/s, More Is Better LZ4 Compression 1.9.3 Compression Level: 9 - Compression Speed Folios 14 Linux 5.14-rc1 15 30 45 60 75 SE +/- 0.66, N = 3 SE +/- 0.77, N = 5 69.20 69.55 1. (CC) gcc options: -O3
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 Folios 14 Linux 5.14-rc1 12 24 36 48 60 SE +/- 0.22, N = 3 SE +/- 0.28, N = 3 55.20 55.47 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
Unvanquished Resolution: 3840 x 2160 - Effects Quality: Ultra OpenBenchmarking.org Frames Per Second, More Is Better Unvanquished 0.52.1 Resolution: 3840 x 2160 - Effects Quality: Ultra Folios 14 Linux 5.14-rc1 80 160 240 320 400 SE +/- 0.46, N = 3 SE +/- 1.44, N = 3 351.4 353.1
Hugin Panorama Photo Assistant + Stitching Time OpenBenchmarking.org Seconds, Fewer Is Better Hugin Panorama Photo Assistant + Stitching Time Folios 14 Linux 5.14-rc1 8 16 24 32 40 SE +/- 0.17, N = 3 SE +/- 0.29, N = 3 34.89 34.73
TNN Target: CPU - Model: MobileNet v2 OpenBenchmarking.org ms, Fewer Is Better TNN 0.3 Target: CPU - Model: MobileNet v2 Folios 14 Linux 5.14-rc1 50 100 150 200 250 SE +/- 1.63, N = 3 SE +/- 0.43, N = 3 223.43 224.41 MIN: 219.37 / MAX: 230.96 MIN: 222.84 / MAX: 227.63 1. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl
Timed LLVM Compilation Build System: Ninja OpenBenchmarking.org Seconds, Fewer Is Better Timed LLVM Compilation 12.0 Build System: Ninja Folios 14 Linux 5.14-rc1 90 180 270 360 450 SE +/- 0.12, N = 3 SE +/- 0.21, N = 3 406.28 404.51
Facebook RocksDB Test: Random Read OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 6.22.1 Test: Random Read Folios 14 Linux 5.14-rc1 20M 40M 60M 80M 100M SE +/- 178790.49, N = 3 SE +/- 245198.44, N = 3 114121586 114609777 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -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 Folios 14 Linux 5.14-rc1 0.4831 0.9662 1.4493 1.9324 2.4155 SE +/- 0.004, N = 3 SE +/- 0.007, N = 3 2.138 2.147 1. (CXX) g++ options: -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq -pie
TensorFlow Lite Model: Mobilenet Float OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2020-08-23 Model: Mobilenet Float Folios 14 Linux 5.14-rc1 14K 28K 42K 56K 70K SE +/- 44.71, N = 3 SE +/- 58.88, N = 3 63498.8 63240.0
TensorFlow Lite Model: Inception ResNet V2 OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2020-08-23 Model: Inception ResNet V2 Folios 14 Linux 5.14-rc1 300K 600K 900K 1200K 1500K SE +/- 1135.62, N = 3 SE +/- 792.23, N = 3 1230850 1225970
LevelDB Benchmark: Sequential Fill OpenBenchmarking.org Microseconds Per Op, Fewer Is Better LevelDB 1.22 Benchmark: Sequential Fill Folios 14 Linux 5.14-rc1 20 40 60 80 100 SE +/- 0.28, N = 3 SE +/- 0.24, N = 3 87.02 87.37 1. (CXX) g++ options: -O3 -lsnappy -lpthread
Zstd Compression Compression Level: 19 - Compression Speed OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.5.0 Compression Level: 19 - Compression Speed Folios 14 Linux 5.14-rc1 12 24 36 48 60 SE +/- 0.17, N = 3 SE +/- 0.00, N = 3 51.3 51.5 1. (CC) gcc options: -O3 -pthread -lz
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 Folios 14 Linux 5.14-rc1 6 12 18 24 30 SE +/- 0.02, N = 3 SE +/- 0.04, N = 3 23.73 23.65 1. (CXX) g++ options: -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq -pie
KTX-Software toktx Settings: UASTC 4 + Zstd Compression 19 OpenBenchmarking.org Seconds, Fewer Is Better KTX-Software toktx 4.0 Settings: UASTC 4 + Zstd Compression 19 Folios 14 Linux 5.14-rc1 30 60 90 120 150 SE +/- 0.23, N = 3 SE +/- 0.14, N = 3 158.19 157.61
srsRAN Test: 5G PHY_DL_NR Test 52 PRB SISO 64-QAM OpenBenchmarking.org eNb Mb/s, More Is Better srsRAN 21.04 Test: 5G PHY_DL_NR Test 52 PRB SISO 64-QAM Folios 14 Linux 5.14-rc1 40 80 120 160 200 SE +/- 1.18, N = 3 SE +/- 0.18, N = 3 163.6 164.2 1. (CXX) g++ options: -std=c++11 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -rdynamic -lpthread -lbladeRF -lm -lfftw3f -lmbedcrypto
PostgreSQL pgbench Scaling Factor: 100 - Clients: 50 - Mode: Read Only OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 13.0 Scaling Factor: 100 - Clients: 50 - Mode: Read Only Folios 14 Linux 5.14-rc1 100K 200K 300K 400K 500K SE +/- 735.37, N = 3 SE +/- 802.08, N = 3 447961 449591 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
LZ4 Compression Compression Level: 9 - Decompression Speed OpenBenchmarking.org MB/s, More Is Better LZ4 Compression 1.9.3 Compression Level: 9 - Decompression Speed Folios 14 Linux 5.14-rc1 3K 6K 9K 12K 15K SE +/- 23.49, N = 3 SE +/- 42.00, N = 5 13048.1 13095.1 1. (CC) gcc options: -O3
Liquid-DSP Threads: 32 - Buffer Length: 256 - Filter Length: 57 OpenBenchmarking.org samples/s, More Is Better Liquid-DSP 2021.01.31 Threads: 32 - Buffer Length: 256 - Filter Length: 57 Folios 14 Linux 5.14-rc1 200M 400M 600M 800M 1000M SE +/- 1722723.94, N = 3 SE +/- 1738773.51, N = 3 1083333333 1087200000 1. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
OpenVKL Benchmark: vklBenchmark OpenBenchmarking.org Items / Sec, More Is Better OpenVKL 0.9 Benchmark: vklBenchmark Folios 14 Linux 5.14-rc1 60 120 180 240 300 SE +/- 0.58, N = 3 SE +/- 0.67, N = 3 285 286 MIN: 1 / MAX: 1107 MIN: 1 / MAX: 1107
Blender Blend File: BMW27 - Compute: CPU-Only OpenBenchmarking.org Seconds, Fewer Is Better Blender 2.92 Blend File: BMW27 - Compute: CPU-Only Folios 14 Linux 5.14-rc1 20 40 60 80 100 SE +/- 0.16, N = 3 SE +/- 0.10, N = 3 80.51 80.23
Liquid-DSP Threads: 16 - Buffer Length: 256 - Filter Length: 57 OpenBenchmarking.org samples/s, More Is Better Liquid-DSP 2021.01.31 Threads: 16 - Buffer Length: 256 - Filter Length: 57 Folios 14 Linux 5.14-rc1 200M 400M 600M 800M 1000M SE +/- 3400490.16, N = 3 SE +/- 5781291.67, N = 3 1025800000 1022300000 1. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
Stress-NG Test: Semaphores OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: Semaphores Folios 14 Linux 5.14-rc1 500K 1000K 1500K 2000K 2500K SE +/- 1332.92, N = 3 SE +/- 2638.46, N = 3 2330190.95 2322589.07 1. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lsctp -lz -ldl -lpthread -lc
NAS Parallel Benchmarks Test / Class: FT.C OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: FT.C Folios 14 Linux 5.14-rc1 3K 6K 9K 12K 15K SE +/- 36.18, N = 3 SE +/- 16.13, N = 3 12160.58 12121.69 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi 2. Open MPI 4.0.3
NAS Parallel Benchmarks Test / Class: EP.C OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: EP.C Folios 14 Linux 5.14-rc1 400 800 1200 1600 2000 SE +/- 6.17, N = 3 SE +/- 5.89, N = 3 1875.75 1869.89 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi 2. Open MPI 4.0.3
Unvanquished Resolution: 3840 x 2160 - Effects Quality: High OpenBenchmarking.org Frames Per Second, More Is Better Unvanquished 0.52.1 Resolution: 3840 x 2160 - Effects Quality: High Folios 14 Linux 5.14-rc1 80 160 240 320 400 SE +/- 3.69, N = 3 SE +/- 1.96, N = 3 389.5 390.7
Zstd Compression Compression Level: 8, Long Mode - Decompression Speed OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.5.0 Compression Level: 8, Long Mode - Decompression Speed Folios 14 Linux 5.14-rc1 1100 2200 3300 4400 5500 SE +/- 18.30, N = 3 SE +/- 25.96, N = 3 4895.5 4910.4 1. (CC) gcc options: -O3 -pthread -lz
Timed Wasmer Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed Wasmer Compilation 1.0.2 Time To Compile Folios 14 Linux 5.14-rc1 13 26 39 52 65 SE +/- 0.17, N = 3 SE +/- 0.17, N = 3 57.53 57.36 1. (CC) gcc options: -m64 -pie -nodefaultlibs -ldl -lrt -lpthread -lgcc_s -lc -lm -lutil
Timed Mesa Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed Mesa Compilation 21.0 Time To Compile Folios 14 Linux 5.14-rc1 8 16 24 32 40 SE +/- 0.01, N = 3 SE +/- 0.08, N = 3 34.03 33.92
TensorFlow Lite Model: Mobilenet Quant OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2020-08-23 Model: Mobilenet Quant Folios 14 Linux 5.14-rc1 15K 30K 45K 60K 75K SE +/- 55.78, N = 3 SE +/- 22.07, N = 3 68795.7 68595.8
FS-Mark Test: 1000 Files, 1MB Size OpenBenchmarking.org Files/s, More Is Better FS-Mark 3.3 Test: 1000 Files, 1MB Size Folios 14 Linux 5.14-rc1 160 320 480 640 800 SE +/- 1.74, N = 3 SE +/- 6.51, N = 3 761.6 759.4 1. (CC) gcc options: -static
TNN Target: CPU - Model: SqueezeNet v1.1 OpenBenchmarking.org ms, Fewer Is Better TNN 0.3 Target: CPU - Model: SqueezeNet v1.1 Folios 14 Linux 5.14-rc1 50 100 150 200 250 SE +/- 0.47, N = 3 SE +/- 0.51, N = 3 211.00 211.61 MIN: 210.37 / MAX: 212 MIN: 210.58 / MAX: 212.59 1. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl
TensorFlow Lite Model: SqueezeNet OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2020-08-23 Model: SqueezeNet Folios 14 Linux 5.14-rc1 20K 40K 60K 80K 100K SE +/- 85.21, N = 3 SE +/- 80.08, N = 3 95962.6 95711.3
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 Folios 14 Linux 5.14-rc1 16 32 48 64 80 SE +/- 0.21, N = 3 SE +/- 0.75, N = 3 73.06 73.25 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
TensorFlow Lite Model: Inception V4 OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2020-08-23 Model: Inception V4 Folios 14 Linux 5.14-rc1 300K 600K 900K 1200K 1500K SE +/- 1174.45, N = 3 SE +/- 442.98, N = 3 1366393 1362860
LevelDB Benchmark: Sequential Fill OpenBenchmarking.org MB/s, More Is Better LevelDB 1.22 Benchmark: Sequential Fill Folios 14 Linux 5.14-rc1 9 18 27 36 45 SE +/- 0.13, N = 3 SE +/- 0.12, N = 3 40.6 40.5 1. (CXX) g++ options: -O3 -lsnappy -lpthread
LevelDB Benchmark: Random Fill OpenBenchmarking.org MB/s, More Is Better LevelDB 1.22 Benchmark: Random Fill Folios 14 Linux 5.14-rc1 9 18 27 36 45 SE +/- 0.03, N = 3 SE +/- 0.17, N = 3 40.9 40.8 1. (CXX) g++ options: -O3 -lsnappy -lpthread
LuaRadio Test: FM Deemphasis Filter OpenBenchmarking.org MiB/s, More Is Better LuaRadio 0.9.1 Test: FM Deemphasis Filter Folios 14 Linux 5.14-rc1 100 200 300 400 500 SE +/- 1.00, N = 3 SE +/- 0.43, N = 3 465.6 464.5
Unvanquished Resolution: 3840 x 2160 - Effects Quality: Medium OpenBenchmarking.org Frames Per Second, More Is Better Unvanquished 0.52.1 Resolution: 3840 x 2160 - Effects Quality: Medium Folios 14 Linux 5.14-rc1 90 180 270 360 450 SE +/- 5.01, N = 3 SE +/- 1.33, N = 3 395.4 394.5
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 Folios 14 Linux 5.14-rc1 5 10 15 20 25 SE +/- 0.21, N = 5 SE +/- 0.04, N = 3 19.75 19.71 1. (CXX) g++ options: -m64 -lm -lpthread -O3 -fPIC -U_FORTIFY_SOURCE -std=gnu++11
srsRAN Test: 5G PHY_DL_NR Test 52 PRB SISO 64-QAM OpenBenchmarking.org UE Mb/s, More Is Better srsRAN 21.04 Test: 5G PHY_DL_NR Test 52 PRB SISO 64-QAM Folios 14 Linux 5.14-rc1 20 40 60 80 100 SE +/- 0.19, N = 3 SE +/- 0.03, N = 3 77.1 77.0 1. (CXX) g++ options: -std=c++11 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -rdynamic -lpthread -lbladeRF -lm -lfftw3f -lmbedcrypto
ParaView Test: Many Spheres - Resolution: 3840 x 2160 OpenBenchmarking.org MiPolys / Sec, More Is Better ParaView 5.9 Test: Many Spheres - Resolution: 3840 x 2160 Folios 14 Linux 5.14-rc1 1400 2800 4200 5600 7000 SE +/- 1.83, N = 3 SE +/- 1.97, N = 3 6345.61 6353.64
ParaView Test: Many Spheres - Resolution: 3840 x 2160 OpenBenchmarking.org Frames / Sec, More Is Better ParaView 5.9 Test: Many Spheres - Resolution: 3840 x 2160 Folios 14 Linux 5.14-rc1 14 28 42 56 70 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 63.29 63.37
LevelDB Benchmark: Random Fill OpenBenchmarking.org Microseconds Per Op, Fewer Is Better LevelDB 1.22 Benchmark: Random Fill Folios 14 Linux 5.14-rc1 20 40 60 80 100 SE +/- 0.08, N = 3 SE +/- 0.39, N = 3 86.56 86.66 1. (CXX) g++ options: -O3 -lsnappy -lpthread
NAS Parallel Benchmarks Test / Class: BT.C OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: BT.C Folios 14 Linux 5.14-rc1 5K 10K 15K 20K 25K SE +/- 8.21, N = 3 SE +/- 4.57, N = 3 23964.57 23937.77 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi 2. Open MPI 4.0.3
ParaView Test: Wavelet Contour - Resolution: 3840 x 2160 OpenBenchmarking.org Frames / Sec, More Is Better ParaView 5.9 Test: Wavelet Contour - Resolution: 3840 x 2160 Folios 14 Linux 5.14-rc1 60 120 180 240 300 SE +/- 0.09, N = 3 SE +/- 0.07, N = 3 257.55 257.28
ParaView Test: Wavelet Contour - Resolution: 3840 x 2160 OpenBenchmarking.org MiPolys / Sec, More Is Better ParaView 5.9 Test: Wavelet Contour - Resolution: 3840 x 2160 Folios 14 Linux 5.14-rc1 600 1200 1800 2400 3000 SE +/- 0.93, N = 3 SE +/- 0.76, N = 3 2684.00 2681.20
C-Blosc Compressor: blosclz OpenBenchmarking.org MB/s, More Is Better C-Blosc 2.0 Compressor: blosclz Folios 14 Linux 5.14-rc1 6K 12K 18K 24K 30K SE +/- 28.26, N = 3 SE +/- 192.66, N = 3 30058.8 30083.1 1. (CC) gcc options: -std=gnu99 -O3 -pthread -lrt -lm
LuaRadio Test: Hilbert Transform OpenBenchmarking.org MiB/s, More Is Better LuaRadio 0.9.1 Test: Hilbert Transform Folios 14 Linux 5.14-rc1 30 60 90 120 150 SE +/- 0.23, N = 3 SE +/- 0.12, N = 3 128.1 128.0
SQLite Threads / Copies: 1 OpenBenchmarking.org Seconds, Fewer Is Better SQLite 3.30.1 Threads / Copies: 1 Folios 14 Linux 5.14-rc1 2 4 6 8 10 SE +/- 0.046, N = 3 SE +/- 0.015, N = 3 8.935 8.929 1. (CC) gcc options: -O2 -lz -lm -ldl -lpthread
RawTherapee Total Benchmark Time OpenBenchmarking.org Seconds, Fewer Is Better RawTherapee Total Benchmark Time Folios 14 Linux 5.14-rc1 11 22 33 44 55 SE +/- 0.03, N = 3 SE +/- 0.02, N = 3 46.44 46.47 1. RawTherapee, version 5.8, command line.
TensorFlow Lite Model: NASNet Mobile OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2020-08-23 Model: NASNet Mobile Folios 14 Linux 5.14-rc1 20K 40K 60K 80K 100K SE +/- 160.94, N = 3 SE +/- 258.99, N = 3 104513 104571
Google Draco Model: Lion OpenBenchmarking.org ms, Fewer Is Better Google Draco 1.4.1 Model: Lion Folios 14 Linux 5.14-rc1 900 1800 2700 3600 4500 SE +/- 28.35, N = 3 SE +/- 15.62, N = 3 4144 4143 1. (CXX) g++ options: -O3
Facebook RocksDB Test: Update Random OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 6.22.1 Test: Update Random Folios 14 Linux 5.14-rc1 200K 400K 600K 800K 1000K SE +/- 1935.82, N = 3 SE +/- 1523.53, N = 3 791729 791624 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
InfluxDB Concurrent Streams: 4 - Batch Size: 10000 - Tags: 2,5000,1 - Points Per Series: 10000 OpenBenchmarking.org val/sec, More Is Better InfluxDB 1.8.2 Concurrent Streams: 4 - Batch Size: 10000 - Tags: 2,5000,1 - Points Per Series: 10000 Folios 14 Linux 5.14-rc1 500K 1000K 1500K 2000K 2500K SE +/- 3046.84, N = 3 SE +/- 2764.58, N = 3 2149719.4 2149476.5
Timed Node.js Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed Node.js Compilation 15.11 Time To Compile Folios 14 Linux 5.14-rc1 50 100 150 200 250 SE +/- 0.22, N = 3 SE +/- 0.15, N = 3 249.58 249.57
Intel Open Image Denoise Run: RTLightmap.hdr.4096x4096 OpenBenchmarking.org Images / Sec, More Is Better Intel Open Image Denoise 1.4.0 Run: RTLightmap.hdr.4096x4096 Folios 14 Linux 5.14-rc1 0.0608 0.1216 0.1824 0.2432 0.304 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 0.27 0.27
Intel Open Image Denoise Run: RT.ldr_alb_nrm.3840x2160 OpenBenchmarking.org Images / Sec, More Is Better Intel Open Image Denoise 1.4.0 Run: RT.ldr_alb_nrm.3840x2160 Folios 14 Linux 5.14-rc1 0.1238 0.2476 0.3714 0.4952 0.619 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 0.55 0.55
Intel Open Image Denoise Run: RT.hdr_alb_nrm.3840x2160 OpenBenchmarking.org Images / Sec, More Is Better Intel Open Image Denoise 1.4.0 Run: RT.hdr_alb_nrm.3840x2160 Folios 14 Linux 5.14-rc1 0.1238 0.2476 0.3714 0.4952 0.619 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 0.55 0.55
OSPray Demo: San Miguel - Renderer: Path Tracer OpenBenchmarking.org FPS, More Is Better OSPray 1.8.5 Demo: San Miguel - Renderer: Path Tracer Folios 14 Linux 5.14-rc1 0.5513 1.1026 1.6539 2.2052 2.7565 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 2.45 2.45 MIN: 2.43 / MAX: 2.49 MIN: 2.42 / MAX: 2.48
OSPray Demo: San Miguel - Renderer: SciVis OpenBenchmarking.org FPS, More Is Better OSPray 1.8.5 Demo: San Miguel - Renderer: SciVis Folios 14 Linux 5.14-rc1 7 14 21 28 35 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 29.41 29.41 MIN: 28.57 / MAX: 31.25 MIN: 28.57 / MAX: 31.25
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 Folios 14 Linux 5.14-rc1 8 16 24 32 40 SE +/- 0.00, N = 3 SE +/- 0.06, N = 3 36.5 36.5 1. (CC) gcc options: -O3 -pthread -lz
GravityMark Resolution: 3840 x 2160 - Renderer: Vulkan OpenBenchmarking.org Frames Per Second, More Is Better GravityMark 1.2 Resolution: 3840 x 2160 - Renderer: Vulkan Folios 14 Linux 5.14-rc1 14 28 42 56 70 SE +/- 0.10, N = 3 SE +/- 0.06, N = 3 62.7 62.7
LevelDB Benchmark: Fill Sync OpenBenchmarking.org MB/s, More Is Better LevelDB 1.22 Benchmark: Fill Sync Folios 14 Linux 5.14-rc1 0.6525 1.305 1.9575 2.61 3.2625 SE +/- 0.03, N = 3 SE +/- 0.00, N = 3 2.9 2.9 1. (CXX) g++ options: -O3 -lsnappy -lpthread
Memcached mcperf Method: Add - Connections: 1 OpenBenchmarking.org Operations Per Second, More Is Better Memcached mcperf 1.6.9 Method: Add - Connections: 1 Folios 14 20K 40K 60K 80K 100K SE +/- 5362.72, N = 15 103090.8 1. (CC) gcc options: -O2 -lm -rdynamic
Stress-NG Test: MMAP OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: MMAP Folios 14 Linux 5.14-rc1 100 200 300 400 500 SE +/- 4.19, N = 15 SE +/- 7.70, N = 15 431.89 447.97 1. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lsctp -lz -ldl -lpthread -lc
PostgreSQL pgbench Scaling Factor: 100 - Clients: 50 - Mode: Read Write - Average Latency OpenBenchmarking.org ms, Fewer Is Better PostgreSQL pgbench 13.0 Scaling Factor: 100 - Clients: 50 - Mode: Read Write - Average Latency Folios 14 Linux 5.14-rc1 0.3951 0.7902 1.1853 1.5804 1.9755 SE +/- 0.024, N = 15 SE +/- 0.030, N = 15 1.737 1.756 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
PostgreSQL pgbench Scaling Factor: 100 - Clients: 50 - Mode: Read Write OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 13.0 Scaling Factor: 100 - Clients: 50 - Mode: Read Write Folios 14 Linux 5.14-rc1 6K 12K 18K 24K 30K SE +/- 382.94, N = 15 SE +/- 497.68, N = 15 28869 28608 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
FS-Mark Test: 4000 Files, 32 Sub Dirs, 1MB Size OpenBenchmarking.org Files/s, More Is Better FS-Mark 3.3 Test: 4000 Files, 32 Sub Dirs, 1MB Size Folios 14 Linux 5.14-rc1 100 200 300 400 500 SE +/- 12.56, N = 12 SE +/- 15.78, N = 15 453.7 433.8 1. (CC) gcc options: -static
FS-Mark Test: 5000 Files, 1MB Size, 4 Threads OpenBenchmarking.org Files/s, More Is Better FS-Mark 3.3 Test: 5000 Files, 1MB Size, 4 Threads Folios 14 Linux 5.14-rc1 130 260 390 520 650 SE +/- 18.35, N = 15 SE +/- 17.54, N = 15 604.8 605.6 1. (CC) gcc options: -static
Phoronix Test Suite v10.8.4