Xeon Platinum 8380 Fedora 2 x Intel Xeon Platinum 8380 testing with a Intel M50CYP2SB2U (SE5C6200.86B.0022.D08.2103221623 BIOS) and ASPEED on Fedora 34 via the Phoronix Test Suite.
HTML result view exported from: https://openbenchmarking.org/result/2109295-TJ-XEONPLATI45&grs .
Xeon Platinum 8380 Fedora Processor Motherboard Chipset Memory Disk Graphics Monitor Network OS Kernel Compiler File-System Screen Resolution Fedora 34 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 Fedora 34 5.11.12-300.fc34.x86_64 (x86_64) GCC 11.2.1 20210728 xfs 1920x1080 OpenBenchmarking.org - Transparent Huge Pages: madvise - --build=x86_64-redhat-linux --disable-libunwind-exceptions --enable-__cxa_atexit --enable-bootstrap --enable-cet --enable-checking=release --enable-gnu-indirect-function --enable-gnu-unique-object --enable-initfini-array --enable-languages=c,c++,fortran,objc,obj-c++,ada,go,d,lto --enable-multilib --enable-offload-targets=nvptx-none --enable-plugin --enable-shared --enable-threads=posix --mandir=/usr/share/man --with-arch_32=i686 --with-gcc-major-version-only --with-linker-hash-style=gnu --with-tune=generic --without-cuda-driver - NONE / attr2,inode64,logbsize=32k,logbufs=8,noquota,relatime,rw,seclabel / Block Size: 4096 - Scaling Governor: intel_pstate powersave - CPU Microcode: 0xd000270 - OpenJDK Runtime Environment 18.9 (build 11.0.12+7) - Python 3.9.7 - SELinux + 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
Xeon Platinum 8380 Fedora v-ray: CPU git: Time To Complete Common Git Commands phpbench: PHP Benchmark Suite appleseed: Material Tester appleseed: Disney Material appleseed: Emily apache: 1000 apache: 200 apache: 100 nginx: 1000 nginx: 500 nginx: 200 nginx: 100 pyperformance: pickle_pure_python pyperformance: django_template pyperformance: python_startup pyperformance: regex_compile pyperformance: crypto_pyaes pyperformance: json_loads pyperformance: raytrace pyperformance: pathlib pyperformance: nbody pyperformance: float pyperformance: chaos pyperformance: 2to3 pyperformance: go pybench: Total For Average Test Times onnx: shufflenet-v2-10 - OpenMP CPU onnx: fcn-resnet101-11 - OpenMP CPU onnx: bertsquad-10 - OpenMP CPU onnx: yolov4 - OpenMP CPU blender: Barbershop - CPU-Only blender: Classroom - CPU-Only blender: BMW27 - CPU-Only rocksdb: Read Rand Write Rand rocksdb: Rand Fill Sync rocksdb: Seq Fill rocksdb: Update Rand rocksdb: Rand Read rocksdb: Rand Fill cassandra: Writes tnn: CPU - SqueezeNet v1.1 tnn: CPU - SqueezeNet v2 tnn: CPU - MobileNet v2 tnn: CPU - DenseNet ncnn: CPU-v3-v3 - mobilenet-v3 ncnn: CPU - regnety_400m ncnn: CPU - squeezenet_ssd ncnn: CPU - yolov4-tiny ncnn: CPU - resnet50 ncnn: CPU - resnet18 ncnn: CPU - vgg16 ncnn: CPU - googlenet ncnn: CPU - blazeface ncnn: CPU - efficientnet-b0 ncnn: CPU - mnasnet ncnn: CPU - shufflenet-v2 ncnn: CPU-v2-v2 - mobilenet-v2 ncnn: CPU - mobilenet mnn: inception-v3 mnn: mobilenet-v1-1.0 mnn: MobileNetV2_224 mnn: SqueezeNetV1.0 mnn: resnet-v2-50 mnn: squeezenetv1.1 mnn: mobilenetV3 stress-ng: System V Message Passing stress-ng: Glibc Qsort Data Sorting stress-ng: Glibc C String Functions stress-ng: Context Switching stress-ng: Memory Copying stress-ng: Vector Math stress-ng: Matrix Math stress-ng: Semaphores stress-ng: CPU Stress stress-ng: CPU Cache stress-ng: SENDFILE stress-ng: IO_uring stress-ng: Forking stress-ng: RdRand stress-ng: Malloc stress-ng: Crypto stress-ng: MEMFD stress-ng: NUMA stress-ng: MMAP sqlite-speedtest: Timed Time - Size 1,000 pgbench: 100 - 250 - Read Write - Average Latency pgbench: 100 - 250 - Read Write pgbench: 100 - 250 - Read Only - Average Latency pgbench: 100 - 250 - Read Only tensorflow-lite: Inception ResNet V2 tensorflow-lite: Mobilenet Quant tensorflow-lite: Mobilenet Float tensorflow-lite: NASNet Mobile tensorflow-lite: Inception V4 tensorflow-lite: SqueezeNet gromacs: MPI CPU - water_GMX50_bare openssl: RSA4096 openssl: RSA4096 openssl: SHA256 securemark: SecureMark-TLS synthmark: VoiceMark_100 build-wasmer: Time To Compile onednn: Recurrent Neural Network Inference - bf16bf16bf16 - CPU onednn: Recurrent Neural Network Training - bf16bf16bf16 - CPU onednn: Deconvolution Batch shapes_3d - bf16bf16bf16 - CPU onednn: Deconvolution Batch shapes_1d - bf16bf16bf16 - CPU onednn: Convolution Batch Shapes Auto - bf16bf16bf16 - CPU onednn: IP Shapes 3D - bf16bf16bf16 - CPU onednn: IP Shapes 1D - bf16bf16bf16 - CPU build-nodejs: Time To Compile build-llvm: Unix Makefiles build-llvm: Ninja build-linux-kernel: Time To Compile build-godot: Time To Compile stockfish: Total Time compress-7zip: Compress Speed Test coremark: CoreMark Size 666 - Iterations Per Second openvkl: vklBenchmark ISPC oidn: RT.hdr_alb_nrm.3840x2160 x265: Bosphorus 1080p x265: Bosphorus 4K svt-vp9: Visual Quality Optimized - Bosphorus 1080p svt-vp9: PSNR/SSIM Optimized - Bosphorus 1080p svt-hevc: 7 - Bosphorus 1080p svt-hevc: 1 - Bosphorus 1080p svt-av1: Preset 8 - Bosphorus 4K svt-av1: Preset 4 - Bosphorus 4K embree: Pathtracer ISPC - Asian Dragon embree: Pathtracer - Asian Dragon embree: Pathtracer ISPC - Crown embree: Pathtracer - Crown ospray: Magnetic Reconnection - SciVis ospray: San Miguel - Path Tracer ospray: San Miguel - SciVis jpegxl: JPEG - 8 jpegxl: JPEG - 7 jpegxl: PNG - 8 jpegxl: PNG - 7 compress-zstd: 19, Long Mode - Decompression Speed compress-zstd: 19, Long Mode - Compression Speed compress-zstd: 19 - Decompression Speed compress-zstd: 19 - Compression Speed compress-zstd: 8 - Decompression Speed compress-zstd: 8 - Compression Speed compress-lz4: 9 - Decompression Speed compress-lz4: 9 - Compression Speed compress-lz4: 3 - Decompression Speed compress-lz4: 3 - Compression Speed renaissance: Genetic Algorithm Using Jenetics + Futures renaissance: Akka Unbalanced Cobwebbed Tree renaissance: In-Memory Database Shootout renaissance: Finagle HTTP Requests renaissance: Savina Reactors.IO renaissance: Apache Spark Bayes renaissance: Apache Spark ALS renaissance: ALS Movie Lens renaissance: Rand Forest dacapobench: Tradebeans dacapobench: H2 gmpbench: Total Time simdjson: DistinctUserID simdjson: PartialTweets simdjson: LargeRand simdjson: Kostya namd: ATPase Simulation - 327,506 Atoms rodinia: OpenMP Streamcluster rodinia: OpenMP CFD Solver rodinia: OpenMP LavaMD npb: SP.C npb: SP.B npb: MG.C npb: LU.C npb: IS.D npb: FT.C npb: EP.D npb: CG.C npb: BT.C hpcg: leveldb: Fill Sync leveldb: Fill Sync leveldb: Hot Read apache: 500 onnx: super-resolution-10 - OpenMP CPU rocksdb: Read While Writing ncnn: CPU - alexnet stress-ng: Socket Activity ospray: Magnetic Reconnection - Path Tracer node-express-loadtest: renaissance: Apache Spark PageRank renaissance: Scala Dotty dacapobench: Jython rodinia: OpenMP Leukocyte leveldb: Overwrite leveldb: Overwrite Fedora 34 63638 62.363 710168 184.402413 83.34648 181.274025 138979.94 43094.53 27134.59 196962.15 193186.18 183953.66 70447.15 539 61.0 16.1 211 138 27.6 574 27.2 154 151 146 529 293 1171 13123 468 664 584 108.64 72.83 29.53 877912 99834 101958 94416 351215402 100049 156353 366.383 75.860 398.942 4207.361 11.40 37.41 23.74 24.67 25.51 13.17 28.53 21.44 6.72 14.00 11.09 11.65 11.47 20.67 22.621 1.925 2.838 3.971 19.090 3.724 1.971 3746931.44 980.22 7826791.04 4686611.80 8673.24 284412.43 301027.31 9301083.81 127362.21 16.14 1282418.27 677113.28 60733.70 666508.11 1389299347.63 13494.56 3595.53 716.03 4517.40 58.363 8.143 30707 0.272 919636 576928 40351.0 38191.1 78466.2 682045 47928.4 8.727 1191777.3 17813.6 58492173530 226326 544.013 44.566 448.546 679.407 3.62321 3.23773 2.11532 1.83350 3.05116 101.183 203.109 134.425 26.310 76.580 179990009 290706 2388804.621125 270 2.68 27.34 12.08 169.54 196.81 166.48 29.90 28.090 2.909 106.9985 82.6008 64.4846 61.3407 111.11 10.38 90.91 16.17 40.68 0.67 7.08 2756.8 45.9 2683.8 82.3 3133.6 2105.1 7329.4 43.21 7278.8 44.09 6882.0 36586.4 19353.7 7856.1 21747.4 1089.4 3288.7 18744.7 1563.0 16863 10902 3760.6 4.18 3.63 0.85 2.45 0.27279 8.231 4.665 41.021 23813.08 22214.17 36812.20 38534.66 1998.45 36063.78 2792.44 20949.37 48340.28 40.4174 3444.736 4.9 192.481 133137.88 7389 9197711 8.83 3188.92 422.22 5646 5136.4 1278.9 5520 61.978 3079.676 5.8 OpenBenchmarking.org
Chaos Group V-RAY Mode: CPU OpenBenchmarking.org vsamples, More Is Better Chaos Group V-RAY 5 Mode: CPU Fedora 34 14K 28K 42K 56K 70K SE +/- 314.15, N = 3 63638
Git Time To Complete Common Git Commands OpenBenchmarking.org Seconds, Fewer Is Better Git Time To Complete Common Git Commands Fedora 34 14 28 42 56 70 SE +/- 0.28, N = 3 62.36 1. git version 2.31.1
PHPBench PHP Benchmark Suite OpenBenchmarking.org Score, More Is Better PHPBench 0.8.1 PHP Benchmark Suite Fedora 34 150K 300K 450K 600K 750K SE +/- 3969.06, N = 3 710168
Appleseed Scene: Material Tester OpenBenchmarking.org Seconds, Fewer Is Better Appleseed 2.0 Beta Scene: Material Tester Fedora 34 40 80 120 160 200 184.40
Appleseed Scene: Disney Material OpenBenchmarking.org Seconds, Fewer Is Better Appleseed 2.0 Beta Scene: Disney Material Fedora 34 20 40 60 80 100 83.35
Appleseed Scene: Emily OpenBenchmarking.org Seconds, Fewer Is Better Appleseed 2.0 Beta Scene: Emily Fedora 34 40 80 120 160 200 181.27
Apache HTTP Server Concurrent Requests: 1000 OpenBenchmarking.org Requests Per Second, More Is Better Apache HTTP Server 2.4.48 Concurrent Requests: 1000 Fedora 34 30K 60K 90K 120K 150K SE +/- 1250.02, N = 7 138979.94 1. (CC) gcc options: -shared -fPIC -O2 -pthread
Apache HTTP Server Concurrent Requests: 200 OpenBenchmarking.org Requests Per Second, More Is Better Apache HTTP Server 2.4.48 Concurrent Requests: 200 Fedora 34 9K 18K 27K 36K 45K SE +/- 250.08, N = 3 43094.53 1. (CC) gcc options: -shared -fPIC -O2 -pthread
Apache HTTP Server Concurrent Requests: 100 OpenBenchmarking.org Requests Per Second, More Is Better Apache HTTP Server 2.4.48 Concurrent Requests: 100 Fedora 34 6K 12K 18K 24K 30K SE +/- 163.78, N = 3 27134.59 1. (CC) gcc options: -shared -fPIC -O2 -pthread
nginx Concurrent Requests: 1000 OpenBenchmarking.org Requests Per Second, More Is Better nginx 1.21.1 Concurrent Requests: 1000 Fedora 34 40K 80K 120K 160K 200K SE +/- 777.39, N = 3 196962.15 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 Fedora 34 40K 80K 120K 160K 200K SE +/- 1542.78, N = 3 193186.18 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 Fedora 34 40K 80K 120K 160K 200K SE +/- 1808.55, N = 12 183953.66 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 Fedora 34 15K 30K 45K 60K 75K SE +/- 388.59, N = 3 70447.15 1. (CC) gcc options: -ldl -lpthread -lcrypt -lz -O3 -march=native
PyPerformance Benchmark: pickle_pure_python OpenBenchmarking.org Milliseconds, Fewer Is Better PyPerformance 1.0.0 Benchmark: pickle_pure_python Fedora 34 120 240 360 480 600 SE +/- 5.59, N = 5 539
PyPerformance Benchmark: django_template OpenBenchmarking.org Milliseconds, Fewer Is Better PyPerformance 1.0.0 Benchmark: django_template Fedora 34 14 28 42 56 70 SE +/- 0.70, N = 3 61.0
PyPerformance Benchmark: python_startup OpenBenchmarking.org Milliseconds, Fewer Is Better PyPerformance 1.0.0 Benchmark: python_startup Fedora 34 4 8 12 16 20 SE +/- 0.09, N = 3 16.1
PyPerformance Benchmark: regex_compile OpenBenchmarking.org Milliseconds, Fewer Is Better PyPerformance 1.0.0 Benchmark: regex_compile Fedora 34 50 100 150 200 250 SE +/- 1.44, N = 15 211
PyPerformance Benchmark: crypto_pyaes OpenBenchmarking.org Milliseconds, Fewer Is Better PyPerformance 1.0.0 Benchmark: crypto_pyaes Fedora 34 30 60 90 120 150 SE +/- 1.45, N = 3 138
PyPerformance Benchmark: json_loads OpenBenchmarking.org Milliseconds, Fewer Is Better PyPerformance 1.0.0 Benchmark: json_loads Fedora 34 6 12 18 24 30 SE +/- 0.18, N = 14 27.6
PyPerformance Benchmark: raytrace OpenBenchmarking.org Milliseconds, Fewer Is Better PyPerformance 1.0.0 Benchmark: raytrace Fedora 34 120 240 360 480 600 SE +/- 2.60, N = 3 574
PyPerformance Benchmark: pathlib OpenBenchmarking.org Milliseconds, Fewer Is Better PyPerformance 1.0.0 Benchmark: pathlib Fedora 34 6 12 18 24 30 SE +/- 0.03, N = 3 27.2
PyPerformance Benchmark: nbody OpenBenchmarking.org Milliseconds, Fewer Is Better PyPerformance 1.0.0 Benchmark: nbody Fedora 34 30 60 90 120 150 SE +/- 1.51, N = 15 154
PyPerformance Benchmark: float OpenBenchmarking.org Milliseconds, Fewer Is Better PyPerformance 1.0.0 Benchmark: float Fedora 34 30 60 90 120 150 SE +/- 1.54, N = 15 151
PyPerformance Benchmark: chaos OpenBenchmarking.org Milliseconds, Fewer Is Better PyPerformance 1.0.0 Benchmark: chaos Fedora 34 30 60 90 120 150 SE +/- 1.65, N = 4 146
PyPerformance Benchmark: 2to3 OpenBenchmarking.org Milliseconds, Fewer Is Better PyPerformance 1.0.0 Benchmark: 2to3 Fedora 34 110 220 330 440 550 529
PyPerformance Benchmark: go OpenBenchmarking.org Milliseconds, Fewer Is Better PyPerformance 1.0.0 Benchmark: go Fedora 34 60 120 180 240 300 SE +/- 3.63, N = 4 293
PyBench Total For Average Test Times OpenBenchmarking.org Milliseconds, Fewer Is Better PyBench 2018-02-16 Total For Average Test Times Fedora 34 300 600 900 1200 1500 SE +/- 1.53, N = 3 1171
ONNX Runtime Model: shufflenet-v2-10 - Device: OpenMP CPU OpenBenchmarking.org Inferences Per Minute, More Is Better ONNX Runtime 1.8.2 Model: shufflenet-v2-10 - Device: OpenMP CPU Fedora 34 3K 6K 9K 12K 15K SE +/- 46.17, N = 3 13123 1. (CXX) g++ options: -fopenmp -ffunction-sections -fdata-sections -O3 -ldl -lrt
ONNX Runtime Model: fcn-resnet101-11 - Device: OpenMP CPU OpenBenchmarking.org Inferences Per Minute, More Is Better ONNX Runtime 1.8.2 Model: fcn-resnet101-11 - Device: OpenMP CPU Fedora 34 100 200 300 400 500 SE +/- 1.92, N = 3 468 1. (CXX) g++ options: -fopenmp -ffunction-sections -fdata-sections -O3 -ldl -lrt
ONNX Runtime Model: bertsquad-10 - Device: OpenMP CPU OpenBenchmarking.org Inferences Per Minute, More Is Better ONNX Runtime 1.8.2 Model: bertsquad-10 - Device: OpenMP CPU Fedora 34 140 280 420 560 700 SE +/- 8.32, N = 3 664 1. (CXX) g++ options: -fopenmp -ffunction-sections -fdata-sections -O3 -ldl -lrt
ONNX Runtime Model: yolov4 - Device: OpenMP CPU OpenBenchmarking.org Inferences Per Minute, More Is Better ONNX Runtime 1.8.2 Model: yolov4 - Device: OpenMP CPU Fedora 34 130 260 390 520 650 SE +/- 1.92, N = 3 584 1. (CXX) g++ options: -fopenmp -ffunction-sections -fdata-sections -O3 -ldl -lrt
Blender Blend File: Barbershop - Compute: CPU-Only OpenBenchmarking.org Seconds, Fewer Is Better Blender 2.92 Blend File: Barbershop - Compute: CPU-Only Fedora 34 20 40 60 80 100 SE +/- 0.40, N = 3 108.64
Blender Blend File: Classroom - Compute: CPU-Only OpenBenchmarking.org Seconds, Fewer Is Better Blender 2.92 Blend File: Classroom - Compute: CPU-Only Fedora 34 16 32 48 64 80 SE +/- 0.05, N = 3 72.83
Blender Blend File: BMW27 - Compute: CPU-Only OpenBenchmarking.org Seconds, Fewer Is Better Blender 2.92 Blend File: BMW27 - Compute: CPU-Only Fedora 34 7 14 21 28 35 SE +/- 0.13, N = 3 29.53
Facebook RocksDB Test: Read Random Write Random OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 6.22.1 Test: Read Random Write Random Fedora 34 200K 400K 600K 800K 1000K SE +/- 809.32, N = 3 877912 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
Facebook RocksDB Test: Random Fill Sync OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 6.22.1 Test: Random Fill Sync Fedora 34 20K 40K 60K 80K 100K SE +/- 125.17, N = 3 99834 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
Facebook RocksDB Test: Sequential Fill OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 6.22.1 Test: Sequential Fill Fedora 34 20K 40K 60K 80K 100K SE +/- 79.90, N = 3 101958 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
Facebook RocksDB Test: Update Random OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 6.22.1 Test: Update Random Fedora 34 20K 40K 60K 80K 100K SE +/- 113.85, N = 3 94416 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
Facebook RocksDB Test: Random Read OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 6.22.1 Test: Random Read Fedora 34 80M 160M 240M 320M 400M SE +/- 2155193.83, N = 3 351215402 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
Facebook RocksDB Test: Random Fill OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 6.22.1 Test: Random Fill Fedora 34 20K 40K 60K 80K 100K SE +/- 34.20, N = 3 100049 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
Apache Cassandra Test: Writes OpenBenchmarking.org Op/s, More Is Better Apache Cassandra 4.0 Test: Writes Fedora 34 30K 60K 90K 120K 150K SE +/- 1490.43, N = 3 156353
TNN Target: CPU - Model: SqueezeNet v1.1 OpenBenchmarking.org ms, Fewer Is Better TNN 0.3 Target: CPU - Model: SqueezeNet v1.1 Fedora 34 80 160 240 320 400 SE +/- 0.21, N = 3 366.38 MIN: 365.86 / MAX: 369.23 1. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl
TNN Target: CPU - Model: SqueezeNet v2 OpenBenchmarking.org ms, Fewer Is Better TNN 0.3 Target: CPU - Model: SqueezeNet v2 Fedora 34 20 40 60 80 100 SE +/- 0.54, N = 3 75.86 MIN: 74.7 / MAX: 110.89 1. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl
TNN Target: CPU - Model: MobileNet v2 OpenBenchmarking.org ms, Fewer Is Better TNN 0.3 Target: CPU - Model: MobileNet v2 Fedora 34 90 180 270 360 450 SE +/- 4.74, N = 15 398.94 MIN: 372.27 / MAX: 540.41 1. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl
TNN Target: CPU - Model: DenseNet OpenBenchmarking.org ms, Fewer Is Better TNN 0.3 Target: CPU - Model: DenseNet Fedora 34 900 1800 2700 3600 4500 SE +/- 35.05, N = 3 4207.36 MIN: 3844.88 / MAX: 6555.07 1. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl
NCNN Target: CPU-v3-v3 - Model: mobilenet-v3 OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: CPU-v3-v3 - Model: mobilenet-v3 Fedora 34 3 6 9 12 15 SE +/- 0.05, N = 2 11.40 MIN: 10.85 / MAX: 55.12 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
NCNN Target: CPU - Model: regnety_400m OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: CPU - Model: regnety_400m Fedora 34 9 18 27 36 45 SE +/- 0.49, N = 3 37.41 MIN: 36.05 / MAX: 155.75 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
NCNN Target: CPU - Model: squeezenet_ssd OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: CPU - Model: squeezenet_ssd Fedora 34 6 12 18 24 30 SE +/- 0.46, N = 3 23.74 MIN: 22.35 / MAX: 263.77 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
NCNN Target: CPU - Model: yolov4-tiny OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: CPU - Model: yolov4-tiny Fedora 34 6 12 18 24 30 SE +/- 0.27, N = 3 24.67 MIN: 23.8 / MAX: 129.92 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
NCNN Target: CPU - Model: resnet50 OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: CPU - Model: resnet50 Fedora 34 6 12 18 24 30 SE +/- 0.68, N = 3 25.51 MIN: 23.72 / MAX: 42.35 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
NCNN Target: CPU - Model: resnet18 OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: CPU - Model: resnet18 Fedora 34 3 6 9 12 15 SE +/- 0.16, N = 3 13.17 MIN: 12.65 / MAX: 14.19 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
NCNN Target: CPU - Model: vgg16 OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: CPU - Model: vgg16 Fedora 34 7 14 21 28 35 SE +/- 0.65, N = 3 28.53 MIN: 26.99 / MAX: 202.72 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
NCNN Target: CPU - Model: googlenet OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: CPU - Model: googlenet Fedora 34 5 10 15 20 25 SE +/- 0.41, N = 3 21.44 MIN: 20.41 / MAX: 35.87 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
NCNN Target: CPU - Model: blazeface OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: CPU - Model: blazeface Fedora 34 2 4 6 8 10 SE +/- 0.05, N = 3 6.72 MIN: 6.47 / MAX: 19.6 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
NCNN Target: CPU - Model: efficientnet-b0 OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: CPU - Model: efficientnet-b0 Fedora 34 4 8 12 16 20 SE +/- 0.21, N = 3 14.00 MIN: 13.24 / MAX: 62.01 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
NCNN Target: CPU - Model: mnasnet OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: CPU - Model: mnasnet Fedora 34 3 6 9 12 15 SE +/- 0.09, N = 3 11.09 MIN: 10.55 / MAX: 39.45 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
NCNN Target: CPU - Model: shufflenet-v2 OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: CPU - Model: shufflenet-v2 Fedora 34 3 6 9 12 15 SE +/- 0.39, N = 3 11.65 MIN: 11.01 / MAX: 258.17 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
NCNN Target: CPU-v2-v2 - Model: mobilenet-v2 OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: CPU-v2-v2 - Model: mobilenet-v2 Fedora 34 3 6 9 12 15 SE +/- 0.06, N = 3 11.47 MIN: 11.03 / MAX: 28.39 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
NCNN Target: CPU - Model: mobilenet OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: CPU - Model: mobilenet Fedora 34 5 10 15 20 25 SE +/- 0.09, N = 3 20.67 MIN: 19.84 / MAX: 45.47 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
Mobile Neural Network Model: inception-v3 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 1.2 Model: inception-v3 Fedora 34 5 10 15 20 25 SE +/- 0.09, N = 3 22.62 MIN: 20.88 / MAX: 104.52 1. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl
Mobile Neural Network Model: mobilenet-v1-1.0 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 1.2 Model: mobilenet-v1-1.0 Fedora 34 0.4331 0.8662 1.2993 1.7324 2.1655 SE +/- 0.025, N = 3 1.925 MIN: 1.71 / MAX: 4.19 1. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl
Mobile Neural Network Model: MobileNetV2_224 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 1.2 Model: MobileNetV2_224 Fedora 34 0.6386 1.2772 1.9158 2.5544 3.193 SE +/- 0.060, N = 3 2.838 MIN: 2.3 / MAX: 7.85 1. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl
Mobile Neural Network Model: SqueezeNetV1.0 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 1.2 Model: SqueezeNetV1.0 Fedora 34 0.8935 1.787 2.6805 3.574 4.4675 SE +/- 0.026, N = 3 3.971 MIN: 3.75 / MAX: 5.86 1. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl
Mobile Neural Network Model: resnet-v2-50 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 1.2 Model: resnet-v2-50 Fedora 34 5 10 15 20 25 SE +/- 0.18, N = 3 19.09 MIN: 18.35 / MAX: 59.55 1. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl
Mobile Neural Network Model: squeezenetv1.1 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 1.2 Model: squeezenetv1.1 Fedora 34 0.8379 1.6758 2.5137 3.3516 4.1895 SE +/- 0.055, N = 3 3.724 MIN: 3.61 / MAX: 4.79 1. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl
Mobile Neural Network Model: mobilenetV3 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 1.2 Model: mobilenetV3 Fedora 34 0.4435 0.887 1.3305 1.774 2.2175 SE +/- 0.021, N = 3 1.971 MIN: 1.91 / MAX: 3.08 1. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl
Stress-NG Test: System V Message Passing OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.13.02 Test: System V Message Passing Fedora 34 800K 1600K 2400K 3200K 4000K SE +/- 50261.31, N = 13 3746931.44 1. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -pthread -lc
Stress-NG Test: Glibc Qsort Data Sorting OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.13.02 Test: Glibc Qsort Data Sorting Fedora 34 200 400 600 800 1000 SE +/- 2.80, N = 3 980.22 1. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -pthread -lc
Stress-NG Test: Glibc C String Functions OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.13.02 Test: Glibc C String Functions Fedora 34 2M 4M 6M 8M 10M SE +/- 48137.27, N = 3 7826791.04 1. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -pthread -lc
Stress-NG Test: Context Switching OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.13.02 Test: Context Switching Fedora 34 1000K 2000K 3000K 4000K 5000K SE +/- 56710.38, N = 3 4686611.80 1. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -pthread -lc
Stress-NG Test: Memory Copying OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.13.02 Test: Memory Copying Fedora 34 2K 4K 6K 8K 10K SE +/- 18.22, N = 3 8673.24 1. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -pthread -lc
Stress-NG Test: Vector Math OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.13.02 Test: Vector Math Fedora 34 60K 120K 180K 240K 300K SE +/- 1004.63, N = 3 284412.43 1. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -pthread -lc
Stress-NG Test: Matrix Math OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.13.02 Test: Matrix Math Fedora 34 60K 120K 180K 240K 300K SE +/- 1727.43, N = 3 301027.31 1. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -pthread -lc
Stress-NG Test: Semaphores OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.13.02 Test: Semaphores Fedora 34 2M 4M 6M 8M 10M SE +/- 5357.91, N = 3 9301083.81 1. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -pthread -lc
Stress-NG Test: CPU Stress OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.13.02 Test: CPU Stress Fedora 34 30K 60K 90K 120K 150K SE +/- 404.61, N = 3 127362.21 1. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -pthread -lc
Stress-NG Test: CPU Cache OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.13.02 Test: CPU Cache Fedora 34 4 8 12 16 20 SE +/- 0.11, N = 13 16.14 1. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -pthread -lc
Stress-NG Test: SENDFILE OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.13.02 Test: SENDFILE Fedora 34 300K 600K 900K 1200K 1500K SE +/- 2865.31, N = 3 1282418.27 1. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -pthread -lc
Stress-NG Test: IO_uring OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.13.02 Test: IO_uring Fedora 34 150K 300K 450K 600K 750K SE +/- 8554.61, N = 3 677113.28 1. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -pthread -lc
Stress-NG Test: Forking OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.13.02 Test: Forking Fedora 34 13K 26K 39K 52K 65K SE +/- 566.07, N = 3 60733.70 1. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -pthread -lc
Stress-NG Test: RdRand OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.13.02 Test: RdRand Fedora 34 140K 280K 420K 560K 700K SE +/- 2189.46, N = 3 666508.11 1. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -pthread -lc
Stress-NG Test: Malloc OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.13.02 Test: Malloc Fedora 34 300M 600M 900M 1200M 1500M SE +/- 7522508.90, N = 3 1389299347.63 1. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -pthread -lc
Stress-NG Test: Crypto OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.13.02 Test: Crypto Fedora 34 3K 6K 9K 12K 15K SE +/- 131.58, N = 3 13494.56 1. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -pthread -lc
Stress-NG Test: MEMFD OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.13.02 Test: MEMFD Fedora 34 800 1600 2400 3200 4000 SE +/- 36.33, N = 3 3595.53 1. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -pthread -lc
Stress-NG Test: NUMA OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.13.02 Test: NUMA Fedora 34 150 300 450 600 750 SE +/- 7.18, N = 3 716.03 1. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -pthread -lc
Stress-NG Test: MMAP OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.13.02 Test: MMAP Fedora 34 1000 2000 3000 4000 5000 SE +/- 45.70, N = 3 4517.40 1. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -pthread -lc
SQLite Speedtest Timed Time - Size 1,000 OpenBenchmarking.org Seconds, Fewer Is Better SQLite Speedtest 3.30 Timed Time - Size 1,000 Fedora 34 13 26 39 52 65 SE +/- 0.17, N = 3 58.36 1. (CC) gcc options: -O2 -ldl -lz -lpthread
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 Fedora 34 2 4 6 8 10 SE +/- 0.005, N = 3 8.143 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -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 Fedora 34 7K 14K 21K 28K 35K SE +/- 18.48, N = 3 30707 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -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 Fedora 34 0.0612 0.1224 0.1836 0.2448 0.306 SE +/- 0.004, N = 3 0.272 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
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 Fedora 34 200K 400K 600K 800K 1000K SE +/- 12078.13, N = 3 919636 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
TensorFlow Lite Model: Inception ResNet V2 OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2020-08-23 Model: Inception ResNet V2 Fedora 34 120K 240K 360K 480K 600K SE +/- 1625.00, N = 3 576928
TensorFlow Lite Model: Mobilenet Quant OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2020-08-23 Model: Mobilenet Quant Fedora 34 9K 18K 27K 36K 45K SE +/- 401.44, N = 15 40351.0
TensorFlow Lite Model: Mobilenet Float OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2020-08-23 Model: Mobilenet Float Fedora 34 8K 16K 24K 32K 40K SE +/- 645.60, N = 12 38191.1
TensorFlow Lite Model: NASNet Mobile OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2020-08-23 Model: NASNet Mobile Fedora 34 20K 40K 60K 80K 100K SE +/- 351.25, N = 3 78466.2
TensorFlow Lite Model: Inception V4 OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2020-08-23 Model: Inception V4 Fedora 34 150K 300K 450K 600K 750K SE +/- 1254.55, N = 3 682045
TensorFlow Lite Model: SqueezeNet OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2020-08-23 Model: SqueezeNet Fedora 34 10K 20K 30K 40K 50K SE +/- 294.24, N = 3 47928.4
GROMACS Implementation: MPI CPU - Input: water_GMX50_bare OpenBenchmarking.org Ns Per Day, More Is Better GROMACS 2021.2 Implementation: MPI CPU - Input: water_GMX50_bare Fedora 34 2 4 6 8 10 SE +/- 0.008, N = 3 8.727 1. (CXX) g++ options: -O3 -pthread
OpenSSL Algorithm: RSA4096 OpenBenchmarking.org verify/s, More Is Better OpenSSL 3.0 Algorithm: RSA4096 Fedora 34 300K 600K 900K 1200K 1500K SE +/- 204.92, N = 3 1191777.3 1. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl
OpenSSL Algorithm: RSA4096 OpenBenchmarking.org sign/s, More Is Better OpenSSL 3.0 Algorithm: RSA4096 Fedora 34 4K 8K 12K 16K 20K SE +/- 130.82, N = 3 17813.6 1. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl
OpenSSL Algorithm: SHA256 OpenBenchmarking.org byte/s, More Is Better OpenSSL 3.0 Algorithm: SHA256 Fedora 34 13000M 26000M 39000M 52000M 65000M SE +/- 96070848.52, N = 3 58492173530 1. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl
SecureMark Benchmark: SecureMark-TLS OpenBenchmarking.org marks, More Is Better SecureMark 1.0.4 Benchmark: SecureMark-TLS Fedora 34 50K 100K 150K 200K 250K SE +/- 108.24, N = 3 226326 1. (CC) gcc options: -pedantic -O3
Google SynthMark Test: VoiceMark_100 OpenBenchmarking.org Voices, More Is Better Google SynthMark 20201109 Test: VoiceMark_100 Fedora 34 120 240 360 480 600 SE +/- 0.39, N = 3 544.01 1. (CXX) g++ options: -lm -lpthread -std=c++11 -Ofast
Timed Wasmer Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed Wasmer Compilation 1.0.2 Time To Compile Fedora 34 10 20 30 40 50 SE +/- 0.21, N = 3 44.57 1. (CC) gcc options: -m64 -ldl -lgcc_s -lutil -lrt -lpthread -lm -lc -pie -nodefaultlibs
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 Fedora 34 100 200 300 400 500 SE +/- 5.66, N = 15 448.55 MIN: 424.5 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -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 Fedora 34 150 300 450 600 750 SE +/- 2.14, N = 3 679.41 MIN: 653.15 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -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 Fedora 34 0.8152 1.6304 2.4456 3.2608 4.076 SE +/- 0.03349, N = 14 3.62321 MIN: 3.49 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -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 Fedora 34 0.7285 1.457 2.1855 2.914 3.6425 SE +/- 0.00452, N = 3 3.23773 MIN: 3.03 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -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 Fedora 34 0.4759 0.9518 1.4277 1.9036 2.3795 SE +/- 0.01742, N = 3 2.11532 MIN: 2.03 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -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 Fedora 34 0.4125 0.825 1.2375 1.65 2.0625 SE +/- 0.00764, N = 3 1.83350 MIN: 1.69 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
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 Fedora 34 0.6865 1.373 2.0595 2.746 3.4325 SE +/- 0.02508, N = 13 3.05116 MIN: 2.87 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
Timed Node.js Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed Node.js Compilation 15.11 Time To Compile Fedora 34 20 40 60 80 100 SE +/- 0.49, N = 3 101.18
Timed LLVM Compilation Build System: Unix Makefiles OpenBenchmarking.org Seconds, Fewer Is Better Timed LLVM Compilation 12.0 Build System: Unix Makefiles Fedora 34 40 80 120 160 200 SE +/- 1.20, N = 3 203.11
Timed LLVM Compilation Build System: Ninja OpenBenchmarking.org Seconds, Fewer Is Better Timed LLVM Compilation 12.0 Build System: Ninja Fedora 34 30 60 90 120 150 SE +/- 0.38, N = 3 134.43
Timed Linux Kernel Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed Linux Kernel Compilation 5.14 Time To Compile Fedora 34 6 12 18 24 30 SE +/- 0.40, N = 14 26.31
Timed Godot Game Engine Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed Godot Game Engine Compilation 3.2.3 Time To Compile Fedora 34 20 40 60 80 100 SE +/- 0.69, N = 3 76.58
Stockfish Total Time OpenBenchmarking.org Nodes Per Second, More Is Better Stockfish 13 Total Time Fedora 34 40M 80M 120M 160M 200M SE +/- 2215655.62, N = 4 179990009 1. (CXX) g++ options: -lgcov -m64 -lpthread -fno-exceptions -std=c++17 -fprofile-use -fno-peel-loops -fno-tracer -pedantic -O3 -msse -msse3 -mpopcnt -mavx2 -mavx512f -mavx512bw -mavx512vnni -mavx512dq -mavx512vl -msse4.1 -mssse3 -msse2 -mbmi2 -flto -flto=jobserver
7-Zip Compression Compress Speed Test OpenBenchmarking.org MIPS, More Is Better 7-Zip Compression 16.02 Compress Speed Test Fedora 34 60K 120K 180K 240K 300K SE +/- 635.60, N = 3 290706 1. (CXX) g++ options: -pipe -lpthread
Coremark CoreMark Size 666 - Iterations Per Second OpenBenchmarking.org Iterations/Sec, More Is Better Coremark 1.0 CoreMark Size 666 - Iterations Per Second Fedora 34 500K 1000K 1500K 2000K 2500K SE +/- 1596.03, N = 3 2388804.62 1. (CC) gcc options: -O2 -lrt" -lrt
OpenVKL Benchmark: vklBenchmark ISPC OpenBenchmarking.org Items / Sec, More Is Better OpenVKL 1.0 Benchmark: vklBenchmark ISPC Fedora 34 60 120 180 240 300 SE +/- 2.89, N = 3 270 MIN: 18 / MAX: 6348
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 Fedora 34 0.603 1.206 1.809 2.412 3.015 SE +/- 0.01, N = 3 2.68
x265 Video Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better x265 3.4 Video Input: Bosphorus 1080p Fedora 34 6 12 18 24 30 SE +/- 0.26, N = 3 27.34 1. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl
x265 Video Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better x265 3.4 Video Input: Bosphorus 4K Fedora 34 3 6 9 12 15 SE +/- 0.12, N = 15 12.08 1. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl
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 Fedora 34 40 80 120 160 200 SE +/- 1.17, N = 13 169.54 1. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm
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 Fedora 34 40 80 120 160 200 SE +/- 1.93, N = 3 196.81 1. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm
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 Fedora 34 40 80 120 160 200 SE +/- 1.44, N = 3 166.48 1. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt
SVT-HEVC Tuning: 1 - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better SVT-HEVC 1.5.0 Tuning: 1 - Input: Bosphorus 1080p Fedora 34 7 14 21 28 35 SE +/- 0.17, N = 3 29.90 1. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt
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 Fedora 34 7 14 21 28 35 SE +/- 0.24, N = 15 28.09 1. (CXX) g++ options: -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq -pie
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 Fedora 34 0.6545 1.309 1.9635 2.618 3.2725 SE +/- 0.008, N = 3 2.909 1. (CXX) g++ options: -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq -pie
Embree Binary: Pathtracer ISPC - Model: Asian Dragon OpenBenchmarking.org Frames Per Second, More Is Better Embree 3.13 Binary: Pathtracer ISPC - Model: Asian Dragon Fedora 34 20 40 60 80 100 SE +/- 0.91, N = 3 107.00 MIN: 83.87 / MAX: 112.01
Embree Binary: Pathtracer - Model: Asian Dragon OpenBenchmarking.org Frames Per Second, More Is Better Embree 3.13 Binary: Pathtracer - Model: Asian Dragon Fedora 34 20 40 60 80 100 SE +/- 0.61, N = 3 82.60 MIN: 66.02 / MAX: 92.25
Embree Binary: Pathtracer ISPC - Model: Crown OpenBenchmarking.org Frames Per Second, More Is Better Embree 3.13 Binary: Pathtracer ISPC - Model: Crown Fedora 34 14 28 42 56 70 SE +/- 0.34, N = 3 64.48 MIN: 57.95 / MAX: 87.15
Embree Binary: Pathtracer - Model: Crown OpenBenchmarking.org Frames Per Second, More Is Better Embree 3.13 Binary: Pathtracer - Model: Crown Fedora 34 14 28 42 56 70 SE +/- 0.41, N = 3 61.34 MIN: 55.41 / MAX: 78.94
OSPray Demo: Magnetic Reconnection - Renderer: SciVis OpenBenchmarking.org FPS, More Is Better OSPray 1.8.5 Demo: Magnetic Reconnection - Renderer: SciVis Fedora 34 20 40 60 80 100 SE +/- 0.00, N = 3 111.11 MIN: 24.39
OSPray Demo: San Miguel - Renderer: Path Tracer OpenBenchmarking.org FPS, More Is Better OSPray 1.8.5 Demo: San Miguel - Renderer: Path Tracer Fedora 34 3 6 9 12 15 SE +/- 0.04, N = 3 10.38 MIN: 8.26 / MAX: 10.64
OSPray Demo: San Miguel - Renderer: SciVis OpenBenchmarking.org FPS, More Is Better OSPray 1.8.5 Demo: San Miguel - Renderer: SciVis Fedora 34 20 40 60 80 100 SE +/- 0.00, N = 3 90.91 MIN: 55.56 / MAX: 100
JPEG XL libjxl Input: JPEG - Encode Speed: 8 OpenBenchmarking.org MP/s, More Is Better JPEG XL libjxl 0.5 Input: JPEG - Encode Speed: 8 Fedora 34 4 8 12 16 20 SE +/- 0.07, N = 3 16.17 1. (CXX) g++ options: -funwind-tables -O3 -O2 -fPIE -pie -pthread
JPEG XL libjxl Input: JPEG - Encode Speed: 7 OpenBenchmarking.org MP/s, More Is Better JPEG XL libjxl 0.5 Input: JPEG - Encode Speed: 7 Fedora 34 9 18 27 36 45 SE +/- 0.15, N = 3 40.68 1. (CXX) g++ options: -funwind-tables -O3 -O2 -fPIE -pie -pthread
JPEG XL libjxl Input: PNG - Encode Speed: 8 OpenBenchmarking.org MP/s, More Is Better JPEG XL libjxl 0.5 Input: PNG - Encode Speed: 8 Fedora 34 0.1508 0.3016 0.4524 0.6032 0.754 SE +/- 0.00, N = 3 0.67 1. (CXX) g++ options: -funwind-tables -O3 -O2 -fPIE -pie -pthread
JPEG XL libjxl Input: PNG - Encode Speed: 7 OpenBenchmarking.org MP/s, More Is Better JPEG XL libjxl 0.5 Input: PNG - Encode Speed: 7 Fedora 34 2 4 6 8 10 SE +/- 0.02, N = 3 7.08 1. (CXX) g++ options: -funwind-tables -O3 -O2 -fPIE -pie -pthread
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 Fedora 34 600 1200 1800 2400 3000 SE +/- 2.27, N = 15 2756.8 1. (CC) gcc options: -O3 -pthread -lz
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 Fedora 34 10 20 30 40 50 SE +/- 0.43, N = 15 45.9 1. (CC) gcc options: -O3 -pthread -lz
Zstd Compression Compression Level: 19 - Decompression Speed OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.5.0 Compression Level: 19 - Decompression Speed Fedora 34 600 1200 1800 2400 3000 SE +/- 4.20, N = 3 2683.8 1. (CC) gcc options: -O3 -pthread -lz
Zstd Compression Compression Level: 19 - Compression Speed OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.5.0 Compression Level: 19 - Compression Speed Fedora 34 20 40 60 80 100 SE +/- 0.26, N = 3 82.3 1. (CC) gcc options: -O3 -pthread -lz
Zstd Compression Compression Level: 8 - Decompression Speed OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.5.0 Compression Level: 8 - Decompression Speed Fedora 34 700 1400 2100 2800 3500 SE +/- 4.21, N = 13 3133.6 1. (CC) gcc options: -O3 -pthread -lz
Zstd Compression Compression Level: 8 - Compression Speed OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.5.0 Compression Level: 8 - Compression Speed Fedora 34 500 1000 1500 2000 2500 SE +/- 20.01, N = 15 2105.1 1. (CC) gcc options: -O3 -pthread -lz
LZ4 Compression Compression Level: 9 - Decompression Speed OpenBenchmarking.org MB/s, More Is Better LZ4 Compression 1.9.3 Compression Level: 9 - Decompression Speed Fedora 34 1600 3200 4800 6400 8000 SE +/- 45.80, N = 3 7329.4 1. (CC) gcc options: -O3
LZ4 Compression Compression Level: 9 - Compression Speed OpenBenchmarking.org MB/s, More Is Better LZ4 Compression 1.9.3 Compression Level: 9 - Compression Speed Fedora 34 10 20 30 40 50 SE +/- 0.06, N = 3 43.21 1. (CC) gcc options: -O3
LZ4 Compression Compression Level: 3 - Decompression Speed OpenBenchmarking.org MB/s, More Is Better LZ4 Compression 1.9.3 Compression Level: 3 - Decompression Speed Fedora 34 1600 3200 4800 6400 8000 SE +/- 0.42, N = 3 7278.8 1. (CC) gcc options: -O3
LZ4 Compression Compression Level: 3 - Compression Speed OpenBenchmarking.org MB/s, More Is Better LZ4 Compression 1.9.3 Compression Level: 3 - Compression Speed Fedora 34 10 20 30 40 50 SE +/- 0.05, N = 3 44.09 1. (CC) gcc options: -O3
Renaissance Test: Genetic Algorithm Using Jenetics + Futures OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.12 Test: Genetic Algorithm Using Jenetics + Futures Fedora 34 1500 3000 4500 6000 7500 SE +/- 47.28, N = 3 6882.0 MIN: 6528.18 / MAX: 7114.97
Renaissance Test: Akka Unbalanced Cobwebbed Tree OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.12 Test: Akka Unbalanced Cobwebbed Tree Fedora 34 8K 16K 24K 32K 40K SE +/- 192.68, N = 3 36586.4 MIN: 27329.82 / MAX: 36962.06
Renaissance Test: In-Memory Database Shootout OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.12 Test: In-Memory Database Shootout Fedora 34 4K 8K 12K 16K 20K SE +/- 235.57, N = 9 19353.7 MIN: 18450.07 / MAX: 25349.26
Renaissance Test: Finagle HTTP Requests OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.12 Test: Finagle HTTP Requests Fedora 34 2K 4K 6K 8K 10K SE +/- 48.25, N = 3 7856.1 MIN: 6713.41 / MAX: 9128.14
Renaissance Test: Savina Reactors.IO OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.12 Test: Savina Reactors.IO Fedora 34 5K 10K 15K 20K 25K SE +/- 203.00, N = 9 21747.4 MIN: 20778.33 / MAX: 35769.63
Renaissance Test: Apache Spark Bayes OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.12 Test: Apache Spark Bayes Fedora 34 200 400 600 800 1000 SE +/- 8.77, N = 3 1089.4 MIN: 597.64 / MAX: 2513.74
Renaissance Test: Apache Spark ALS OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.12 Test: Apache Spark ALS Fedora 34 700 1400 2100 2800 3500 SE +/- 22.67, N = 3 3288.7 MIN: 2743.82 / MAX: 3948.41
Renaissance Test: ALS Movie Lens OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.12 Test: ALS Movie Lens Fedora 34 4K 8K 12K 16K 20K SE +/- 53.47, N = 3 18744.7 MIN: 18656.29 / MAX: 21899.3
Renaissance Test: Random Forest OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.12 Test: Random Forest Fedora 34 300 600 900 1200 1500 SE +/- 14.13, N = 3 1563.0 MIN: 1358.36 / MAX: 1923.48
DaCapo Benchmark Java Test: Tradebeans OpenBenchmarking.org msec, Fewer Is Better DaCapo Benchmark 9.12-MR1 Java Test: Tradebeans Fedora 34 4K 8K 12K 16K 20K SE +/- 74.66, N = 4 16863
DaCapo Benchmark Java Test: H2 OpenBenchmarking.org msec, Fewer Is Better DaCapo Benchmark 9.12-MR1 Java Test: H2 Fedora 34 2K 4K 6K 8K 10K SE +/- 86.09, N = 10 10902
GNU GMP GMPbench Total Time OpenBenchmarking.org GMPbench Score, More Is Better GNU GMP GMPbench 6.2.1 Total Time Fedora 34 800 1600 2400 3200 4000 3760.6 1. (CC) gcc options: -O3 -fomit-frame-pointer -lm
simdjson Throughput Test: DistinctUserID OpenBenchmarking.org GB/s, More Is Better simdjson 1.0 Throughput Test: DistinctUserID Fedora 34 0.9405 1.881 2.8215 3.762 4.7025 SE +/- 0.00, N = 3 4.18 1. (CXX) g++ options: -O3 -pthread
simdjson Throughput Test: PartialTweets OpenBenchmarking.org GB/s, More Is Better simdjson 1.0 Throughput Test: PartialTweets Fedora 34 0.8168 1.6336 2.4504 3.2672 4.084 SE +/- 0.00, N = 3 3.63 1. (CXX) g++ options: -O3 -pthread
simdjson Throughput Test: LargeRandom OpenBenchmarking.org GB/s, More Is Better simdjson 1.0 Throughput Test: LargeRandom Fedora 34 0.1913 0.3826 0.5739 0.7652 0.9565 SE +/- 0.00, N = 3 0.85 1. (CXX) g++ options: -O3 -pthread
simdjson Throughput Test: Kostya OpenBenchmarking.org GB/s, More Is Better simdjson 1.0 Throughput Test: Kostya Fedora 34 0.5513 1.1026 1.6539 2.2052 2.7565 SE +/- 0.00, N = 3 2.45 1. (CXX) g++ options: -O3 -pthread
NAMD ATPase Simulation - 327,506 Atoms OpenBenchmarking.org days/ns, Fewer Is Better NAMD 2.14 ATPase Simulation - 327,506 Atoms Fedora 34 0.0614 0.1228 0.1842 0.2456 0.307 SE +/- 0.00037, N = 3 0.27279
Rodinia Test: OpenMP Streamcluster OpenBenchmarking.org Seconds, Fewer Is Better Rodinia 3.1 Test: OpenMP Streamcluster Fedora 34 2 4 6 8 10 SE +/- 0.078, N = 3 8.231 1. (CXX) g++ options: -O2 -lOpenCL
Rodinia Test: OpenMP CFD Solver OpenBenchmarking.org Seconds, Fewer Is Better Rodinia 3.1 Test: OpenMP CFD Solver Fedora 34 1.0496 2.0992 3.1488 4.1984 5.248 SE +/- 0.054, N = 13 4.665 1. (CXX) g++ options: -O2 -lOpenCL
Rodinia Test: OpenMP LavaMD OpenBenchmarking.org Seconds, Fewer Is Better Rodinia 3.1 Test: OpenMP LavaMD Fedora 34 9 18 27 36 45 SE +/- 0.08, N = 3 41.02 1. (CXX) g++ options: -O2 -lOpenCL
NAS Parallel Benchmarks Test / Class: SP.C OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: SP.C Fedora 34 5K 10K 15K 20K 25K SE +/- 83.84, N = 3 23813.08 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi
NAS Parallel Benchmarks Test / Class: SP.B OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: SP.B Fedora 34 5K 10K 15K 20K 25K SE +/- 121.09, N = 3 22214.17 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi
NAS Parallel Benchmarks Test / Class: MG.C OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: MG.C Fedora 34 8K 16K 24K 32K 40K SE +/- 285.06, N = 15 36812.20 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi
NAS Parallel Benchmarks Test / Class: LU.C OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: LU.C Fedora 34 8K 16K 24K 32K 40K SE +/- 144.80, N = 3 38534.66 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi
NAS Parallel Benchmarks Test / Class: IS.D OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: IS.D Fedora 34 400 800 1200 1600 2000 SE +/- 6.80, N = 3 1998.45 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi
NAS Parallel Benchmarks Test / Class: FT.C OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: FT.C Fedora 34 8K 16K 24K 32K 40K SE +/- 339.90, N = 3 36063.78 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi
NAS Parallel Benchmarks Test / Class: EP.D OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: EP.D Fedora 34 600 1200 1800 2400 3000 SE +/- 35.73, N = 3 2792.44 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi
NAS Parallel Benchmarks Test / Class: CG.C OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: CG.C Fedora 34 4K 8K 12K 16K 20K SE +/- 165.42, N = 15 20949.37 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi
NAS Parallel Benchmarks Test / Class: BT.C OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: BT.C Fedora 34 10K 20K 30K 40K 50K SE +/- 71.83, N = 3 48340.28 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi
High Performance Conjugate Gradient OpenBenchmarking.org GFLOP/s, More Is Better High Performance Conjugate Gradient 3.1 Fedora 34 9 18 27 36 45 SE +/- 0.02, N = 3 40.42 1. (CXX) g++ options: -O3 -ffast-math -ftree-vectorize -pthread -lmpi_cxx -lmpi
LevelDB Benchmark: Fill Sync OpenBenchmarking.org Microseconds Per Op, Fewer Is Better LevelDB 1.22 Benchmark: Fill Sync Fedora 34 700 1400 2100 2800 3500 SE +/- 45.41, N = 3 3444.74 1. (CXX) g++ options: -O3 -lsnappy -lpthread
LevelDB Benchmark: Fill Sync OpenBenchmarking.org MB/s, More Is Better LevelDB 1.22 Benchmark: Fill Sync Fedora 34 1.1025 2.205 3.3075 4.41 5.5125 SE +/- 0.06, N = 3 4.9 1. (CXX) g++ options: -O3 -lsnappy -lpthread
LevelDB Benchmark: Hot Read OpenBenchmarking.org Microseconds Per Op, Fewer Is Better LevelDB 1.22 Benchmark: Hot Read Fedora 34 40 80 120 160 200 SE +/- 1.60, N = 12 192.48 1. (CXX) g++ options: -O3 -lsnappy -lpthread
Apache HTTP Server Concurrent Requests: 500 OpenBenchmarking.org Requests Per Second, More Is Better Apache HTTP Server 2.4.48 Concurrent Requests: 500 Fedora 34 30K 60K 90K 120K 150K SE +/- 4279.53, N = 12 133137.88 1. (CC) gcc options: -shared -fPIC -O2 -pthread
ONNX Runtime Model: super-resolution-10 - Device: OpenMP CPU OpenBenchmarking.org Inferences Per Minute, More Is Better ONNX Runtime 1.8.2 Model: super-resolution-10 - Device: OpenMP CPU Fedora 34 1600 3200 4800 6400 8000 SE +/- 278.05, N = 12 7389 1. (CXX) g++ options: -fopenmp -ffunction-sections -fdata-sections -O3 -ldl -lrt
Facebook RocksDB Test: Read While Writing OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 6.22.1 Test: Read While Writing Fedora 34 2M 4M 6M 8M 10M SE +/- 227459.02, N = 12 9197711 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
NCNN Target: CPU - Model: alexnet OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: CPU - Model: alexnet Fedora 34 2 4 6 8 10 SE +/- 0.51, N = 3 8.83 MIN: 8.04 / MAX: 10.95 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
Stress-NG Test: Socket Activity OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.13.02 Test: Socket Activity Fedora 34 700 1400 2100 2800 3500 SE +/- 821.00, N = 15 3188.92 1. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -pthread -lc
OSPray Demo: Magnetic Reconnection - Renderer: Path Tracer OpenBenchmarking.org FPS, More Is Better OSPray 1.8.5 Demo: Magnetic Reconnection - Renderer: Path Tracer Fedora 34 90 180 270 360 450 SE +/- 22.22, N = 15 422.22 MIN: 142.86 / MAX: 1000
Node.js Express HTTP Load Test OpenBenchmarking.org Requests Per Second, More Is Better Node.js Express HTTP Load Test Fedora 34 1200 2400 3600 4800 6000 SE +/- 101.23, N = 12 5646 1. Nodejs
Renaissance Test: Apache Spark PageRank OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.12 Test: Apache Spark PageRank Fedora 34 1100 2200 3300 4400 5500 SE +/- 120.57, N = 9 5136.4 MIN: 3532.85 / MAX: 6381.82
Renaissance Test: Scala Dotty OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.12 Test: Scala Dotty Fedora 34 300 600 900 1200 1500 SE +/- 54.68, N = 15 1278.9 MIN: 728.98 / MAX: 2326.19
DaCapo Benchmark Java Test: Jython OpenBenchmarking.org msec, Fewer Is Better DaCapo Benchmark 9.12-MR1 Java Test: Jython Fedora 34 1200 2400 3600 4800 6000 SE +/- 129.85, N = 20 5520
Rodinia Test: OpenMP Leukocyte OpenBenchmarking.org Seconds, Fewer Is Better Rodinia 3.1 Test: OpenMP Leukocyte Fedora 34 14 28 42 56 70 SE +/- 1.27, N = 12 61.98 1. (CXX) g++ options: -O2 -lOpenCL
LevelDB Benchmark: Overwrite OpenBenchmarking.org Microseconds Per Op, Fewer Is Better LevelDB 1.22 Benchmark: Overwrite Fedora 34 700 1400 2100 2800 3500 SE +/- 114.36, N = 5 3079.68 1. (CXX) g++ options: -O3 -lsnappy -lpthread
LevelDB Benchmark: Overwrite OpenBenchmarking.org MB/s, More Is Better LevelDB 1.22 Benchmark: Overwrite Fedora 34 1.305 2.61 3.915 5.22 6.525 SE +/- 0.22, N = 5 5.8 1. (CXX) g++ options: -O3 -lsnappy -lpthread
Phoronix Test Suite v10.8.4