New Tests 2 x Intel Xeon Platinum 8380 testing with a Intel M50CYP2SB2U (SE5C6200.86B.0022.D08.2103221623 BIOS) and ASPEED on Clear Linux OS 36990 via the Phoronix Test Suite.
HTML result view exported from: https://openbenchmarking.org/result/2209025-NE-2209017NE69&grs&sor .
New Tests Processor Motherboard Chipset Memory Disk Graphics Monitor Network OS Kernel Desktop Display Server Compiler File-System Screen Resolution CentOS Stream 9 Clear Linux 36990 2 x Intel Xeon Platinum 8380 @ 3.40GHz (80 Cores / 160 Threads) Intel M50CYP2SB2U (SE5C6200.86B.0022.D08.2103221623 BIOS) Intel Device 0998 512GB 7682GB INTEL SSDPF2KX076TZ ASPEED VE228 2 x Intel X710 for 10GBASE-T + 2 x Intel E810-C for QSFP CentOS Stream 9 5.14.0-148.el9.x86_64 (x86_64) GNOME Shell 40.10 X Server GCC 11.3.1 20220421 xfs 1920x1080 Clear Linux OS 36990 5.19.6-1185.native (x86_64) GNOME Shell 42.4 X Server 1.21.1.3 GCC 12.2.1 20220831 releases/gcc-12.2.0-35-g63997f2223 + Clang 14.0.6 + LLVM 14.0.6 ext4 OpenBenchmarking.org Kernel Details - Transparent Huge Pages: always Compiler Details - CentOS Stream 9: --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-host-bind-now --enable-host-pie --enable-initfini-array --enable-languages=c,c++,fortran,lto --enable-link-serialization=1 --enable-multilib --enable-offload-targets=nvptx-none --enable-plugin --enable-shared --enable-threads=posix --mandir=/usr/share/man --with-arch_32=x86-64 --with-arch_64=x86-64-v2 --with-build-config=bootstrap-lto --with-gcc-major-version-only --with-linker-hash-style=gnu --with-tune=generic --without-cuda-driver --without-isl - Clear Linux 36990: --build=x86_64-generic-linux --disable-libmpx --disable-libunwind-exceptions --disable-multiarch --disable-vtable-verify --disable-werror --enable-__cxa_atexit --enable-bootstrap --enable-cet --enable-clocale=gnu --enable-default-pie --enable-gnu-indirect-function --enable-gnu-indirect-function --enable-host-shared --enable-languages=c,c++,fortran,go,jit --enable-ld=default --enable-libstdcxx-pch --enable-linux-futex --enable-lto --enable-multilib --enable-plugin --enable-shared --enable-threads=posix --exec-prefix=/usr --includedir=/usr/include --target=x86_64-generic-linux --with-arch=x86-64-v3 --with-gcc-major-version-only --with-glibc-version=2.35 --with-gnu-ld --with-isl --with-pic --with-ppl=yes --with-tune=skylake-avx512 --with-zstd Disk Details - CentOS Stream 9: NONE / attr2,inode64,logbsize=32k,logbufs=8,noquota,relatime,rw,seclabel / Block Size: 4096 - Clear Linux 36990: MQ-DEADLINE / relatime,rw,stripe=256 / Block Size: 4096 Processor Details - CentOS Stream 9: Scaling Governor: intel_pstate powersave (EPP: balance_performance) - CPU Microcode: 0xd000363 - Clear Linux 36990: Scaling Governor: intel_pstate performance (EPP: performance) - CPU Microcode: 0xd000375 Java Details - CentOS Stream 9: OpenJDK Runtime Environment (Red_Hat-11.0.16.0.8-2.el9) (build 11.0.16+8-LTS) - Clear Linux 36990: OpenJDK Runtime Environment (build 18.0.1-internal+0-adhoc.mockbuild.corretto-18-18.0.1.10.1) Python Details - CentOS Stream 9: Python 3.9.13 - Clear Linux 36990: Python 3.10.6 Security Details - CentOS Stream 9: SELinux + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Mitigation of Clear buffers; SMT vulnerable + retbleed: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + 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 - Clear Linux 36990: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Mitigation of Clear buffers; SMT vulnerable + retbleed: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced IBRS IBPB: conditional RSB filling PBRSB-eIBRS: SW sequence + srbds: Not affected + tsx_async_abort: Not affected Environment Details - Clear Linux 36990: FFLAGS="-g -O3 -feliminate-unused-debug-types -pipe -Wall -Wp,-D_FORTIFY_SOURCE=2 -fexceptions -m64 -fasynchronous-unwind-tables -Wp,-D_REENTRANT -ftree-loop-distribute-patterns -Wl,-z -Wl,now -Wl,-z -Wl,relro -malign-data=abi -fno-semantic-interposition -ftree-vectorize -ftree-loop-vectorize -Wl,--enable-new-dtags" CXXFLAGS="-g -O3 -feliminate-unused-debug-types -pipe -Wall -Wp,-D_FORTIFY_SOURCE=2 -fexceptions -Wformat -Wformat-security -m64 -fasynchronous-unwind-tables -Wp,-D_REENTRANT -ftree-loop-distribute-patterns -Wl,-z -Wl,now -Wl,-z -Wl,relro -fno-semantic-interposition -ffat-lto-objects -fno-trapping-math -Wl,-sort-common -Wl,--enable-new-dtags -mtune=skylake -mrelax-cmpxchg-loop -fvisibility-inlines-hidden -Wl,--enable-new-dtags" FCFLAGS="-g -O3 -feliminate-unused-debug-types -pipe -Wall -Wp,-D_FORTIFY_SOURCE=2 -fexceptions -m64 -fasynchronous-unwind-tables -Wp,-D_REENTRANT -ftree-loop-distribute-patterns -Wl,-z -Wl,now -Wl,-z -Wl,relro -malign-data=abi -fno-semantic-interposition -ftree-vectorize -ftree-loop-vectorize -Wl,-sort-common -Wl,--enable-new-dtags" CFLAGS="-g -O3 -feliminate-unused-debug-types -pipe -Wall -Wp,-D_FORTIFY_SOURCE=2 -fexceptions -Wformat -Wformat-security -m64 -fasynchronous-unwind-tables -Wp,-D_REENTRANT -ftree-loop-distribute-patterns -Wl,-z -Wl,now -Wl,-z -Wl,relro -fno-semantic-interposition -ffat-lto-objects -fno-trapping-math -Wl,-sort-common -Wl,--enable-new-dtags -mtune=skylake -mrelax-cmpxchg-loop" THEANO_FLAGS="floatX=float32,openmp=true,gcc.cxxflags="-ftree-vectorize -mavx""
New Tests pgbench: 100 - 500 - Read Write - Average Latency pgbench: 100 - 500 - Read Write spark: 40000000 - 500 - SHA-512 Benchmark Time pgbench: 100 - 250 - Read Write pgbench: 100 - 250 - Read Write - Average Latency dacapobench: H2 blosc: blosclz shuffle compress-zstd: 3, Long Mode - Compression Speed blosc: blosclz bitshuffle compress-zstd: 8, Long Mode - Compression Speed natron: Spaceship renaissance: Savina Reactors.IO onnx: super-resolution-10 - CPU - Parallel stress-ng: Context Switching x264: Bosphorus 4K renaissance: Apache Spark Bayes stress-ng: Semaphores renaissance: Rand Forest svt-av1: Preset 12 - Bosphorus 4K renaissance: ALS Movie Lens svt-av1: Preset 10 - Bosphorus 4K vpxenc: Speed 0 - Bosphorus 4K node-express-loadtest: stress-ng: NUMA build-llvm: Ninja svt-av1: Preset 8 - Bosphorus 4K svt-av1: Preset 4 - Bosphorus 4K avifenc: 6 svt-hevc: 7 - Bosphorus 4K svt-hevc: 10 - Bosphorus 4K clickhouse: 100M Rows Web Analytics Dataset, First Run / Cold Cache clickhouse: 100M Rows Web Analytics Dataset, Third Run clickhouse: 100M Rows Web Analytics Dataset, Second Run ospray: particle_volume/pathtracer/real_time redis: GET - 50 svt-vp9: Visual Quality Optimized - Bosphorus 4K avifenc: 6, Lossless svt-vp9: PSNR/SSIM Optimized - Bosphorus 4K avifenc: 10, Lossless svt-vp9: VMAF Optimized - Bosphorus 4K graphics-magick: Sharpen graphics-magick: Noise-Gaussian compress-zstd: 8 - Compression Speed node-web-tooling: pyhpc: CPU - Numpy - 4194304 - Isoneutral Mixing stress-ng: System V Message Passing unpack-linux: linux-5.19.tar.xz onnx: ArcFace ResNet-100 - CPU - Parallel lammps: Rhodopsin Protein webp: Quality 100, Lossless stress-ng: Matrix Math stress-ng: Crypto avifenc: 2 stress-ng: Memory Copying astcenc: Medium redis: GET - 1000 compress-zstd: 19, Long Mode - Compression Speed stress-ng: MMAP stress-ng: Malloc tensorflow-lite: Mobilenet Quant apache: 1000 onnx: ArcFace ResNet-100 - CPU - Standard onnx: bertsquad-12 - CPU - Standard spark: 40000000 - 500 - Calculate Pi Benchmark stress-ng: SENDFILE webp: Quality 100, Highest Compression mnn: MobileNetV2_224 graphics-magick: Swirl tnn: CPU - DenseNet astcenc: Thorough tnn: CPU - MobileNet v2 astcenc: Exhaustive stress-ng: MEMFD webp: Quality 100, Lossless, Highest Compression avifenc: 0 nginx: 1000 redis: SET - 50 mnn: mobilenetV3 gromacs: MPI CPU - water_GMX50_bare compress-zstd: 19 - Compression Speed tnn: CPU - SqueezeNet v2 astcenc: Fast stress-ng: Glibc Qsort Data Sorting pyhpc: CPU - Numpy - 4194304 - Equation of State onednn: Recurrent Neural Network Training - bf16bf16bf16 - CPU stress-ng: Vector Math tensorflow-lite: Inception ResNet V2 graphics-magick: Resizing onnx: bertsquad-12 - CPU - Parallel stress-ng: CPU Stress simdjson: PartialTweets graphics-magick: Enhanced blender: BMW27 - CPU-Only compress-zstd: 3 - Compression Speed blender: Fishy Cat - CPU-Only stress-ng: Forking tnn: CPU - SqueezeNet v1.1 simdjson: TopTweet onnx: fcn-resnet101-11 - CPU - Parallel simdjson: LargeRand stress-ng: Glibc C String Functions compress-zstd: 19 - Decompression Speed compress-7zip: Decompression Rating mnn: inception-v3 ospray: particle_volume/scivis/real_time onnx: yolov4 - CPU - Parallel onednn: Convolution Batch Shapes Auto - bf16bf16bf16 - CPU blender: Barbershop - CPU-Only hpcg: compress-zstd: 3 - Decompression Speed compress-zstd: 8, Long Mode - Decompression Speed mnn: resnet-v2-50 blender: Pabellon Barcelona - CPU-Only compress-7zip: Compression Rating simdjson: DistinctUserID simdjson: Kostya openssl: ospray: particle_volume/ao/real_time onednn: Deconvolution Batch shapes_3d - bf16bf16bf16 - CPU ospray: gravity_spheres_volume/dim_512/scivis/real_time blender: Classroom - CPU-Only compress-zstd: 19, Long Mode - Decompression Speed stress-ng: CPU Cache ospray-studio: 2 - 4K - 16 - Path Tracer openssl: ospray-studio: 3 - 4K - 16 - Path Tracer ospray: gravity_spheres_volume/dim_512/ao/real_time ospray-studio: 3 - 4K - 32 - Path Tracer compress-zstd: 8 - Decompression Speed stress-ng: x86_64 RdRand namd: ATPase Simulation - 327,506 Atoms onednn: Deconvolution Batch shapes_1d - bf16bf16bf16 - CPU ospray: gravity_spheres_volume/dim_512/pathtracer/real_time lammps: 20k Atoms ospray-studio: 2 - 4K - 32 - Path Tracer onnx: GPT-2 - CPU - Parallel ospray-studio: 1 - 4K - 32 - Path Tracer ospray-studio: 1 - 4K - 16 - Path Tracer graphics-magick: Rotate stress-ng: IO_uring dragonflydb: 50 - 5:1 dragonflydb: 50 - 1:5 dragonflydb: 50 - 1:1 spark: 40000000 - 500 - Broadcast Inner Join Test Time spark: 40000000 - 500 - Inner Join Test Time spark: 40000000 - 500 - Repartition Test Time spark: 40000000 - 500 - Group By Test Time influxdb: 4 - 10000 - 2,5000,1 - 10000 pyhpc: CPU - TensorFlow - 4194304 - Equation of State pyhpc: CPU - PyTorch - 4194304 - Isoneutral Mixing pyhpc: CPU - PyTorch - 4194304 - Equation of State pyhpc: CPU - Aesara - 4194304 - Isoneutral Mixing pyhpc: CPU - Aesara - 4194304 - Equation of State pyhpc: CPU - Numba - 4194304 - Isoneutral Mixing pyhpc: CPU - Numba - 4194304 - Equation of State pyhpc: CPU - JAX - 4194304 - Isoneutral Mixing pyhpc: CPU - JAX - 4194304 - Equation of State openvino: Age Gender Recognition Retail 0013 FP16 - CPU openvino: Age Gender Recognition Retail 0013 FP16 - CPU openvino: Weld Porosity Detection FP16-INT8 - CPU openvino: Weld Porosity Detection FP16-INT8 - CPU openvino: Machine Translation EN To DE FP16 - CPU openvino: Machine Translation EN To DE FP16 - CPU openvino: Weld Porosity Detection FP16 - CPU openvino: Weld Porosity Detection FP16 - CPU openvino: Vehicle Detection FP16-INT8 - CPU openvino: Vehicle Detection FP16-INT8 - CPU openvino: Face Detection FP16-INT8 - CPU openvino: Face Detection FP16-INT8 - CPU openvino: Vehicle Detection FP16 - CPU openvino: Vehicle Detection FP16 - CPU openvino: Person Detection FP32 - CPU openvino: Person Detection FP32 - CPU openvino: Person Detection FP16 - CPU openvino: Person Detection FP16 - CPU openvino: Face Detection FP16 - CPU openvino: Face Detection FP16 - CPU keydb: webp2: Quality 95, Compression Effort 7 webp2: Quality 75, Compression Effort 7 webp2: Default build-linux-kernel: defconfig build-gdb: Time To Compile compress-zstd: 3, Long Mode - Decompression Speed renaissance: In-Memory Database Shootout dacapobench: Tradebeans onnx: super-resolution-10 - CPU - Standard onnx: fcn-resnet101-11 - CPU - Standard onnx: yolov4 - CPU - Standard onnx: GPT-2 - CPU - Standard openvino: Age Gender Recognition Retail 0013 FP16-INT8 - CPU openvino: Age Gender Recognition Retail 0013 FP16-INT8 - CPU openvino: Person Vehicle Bike Detection FP16 - CPU openvino: Person Vehicle Bike Detection FP16 - CPU mnn: mobilenet-v1-1.0 mnn: SqueezeNetV1.0 mnn: squeezenetv1.1 mnn: nasnet stress-ng: Socket Activity stress-ng: Atomic stress-ng: Futex memtier-benchmark: Redis - 50 - 1:10 memtier-benchmark: Redis - 50 - 5:1 pgbench: 100 - 500 - Read Only - Average Latency pgbench: 100 - 500 - Read Only pgbench: 100 - 250 - Read Only - Average Latency pgbench: 100 - 250 - Read Only tensorflow-lite: Mobilenet Float tensorflow-lite: NASNet Mobile tensorflow-lite: Inception V4 tensorflow-lite: SqueezeNet redis: SET - 1000 redis: SET - 500 redis: GET - 500 spark: 40000000 - 500 - Calculate Pi Benchmark Using Dataframe onednn: Matrix Multiply Batch Shapes Transformer - bf16bf16bf16 - CPU onednn: Recurrent Neural Network Inference - bf16bf16bf16 - CPU onednn: IP Shapes 3D - bf16bf16bf16 - CPU onednn: IP Shapes 1D - bf16bf16bf16 - CPU stockfish: Total Time graphics-magick: HWB Color Space renaissance: Finagle HTTP Requests dacapobench: Jython webp: Quality 100 webp: Default CentOS Stream 9 Clear Linux 36990 26.724 18710 88.83 20745 12.051 9847 4916.7 281.0 3704.1 307.5 1.9 21219.4 3259 6233126.45 34.57 1075.3 7186364.51 1455.2 92.832 17123.9 65.620 3.04 4910 10.37 135.019 38.675 1.327 6.056 86.67 113.23 231.48 243.95 244.38 100.6696 2284227.2 99.27 9.260 115.50 6.605 112.93 641 738 1244.0 10.55 2.878 7093379.73 9.194 1693 30.870 21.115 286293.40 83808.91 48.710 12812.45 316.3743 2406986.65 43.4 3747.58 306750258.84 9540.86 131349.60 1881 1093 36.21 1271967.05 8.802 2.663 2340 3955.046 46.3848 378.879 4.5054 4098.84 41.208 84.316 200945.49 2189377.08 1.753 8.996 86.6 75.880 799.1120 934.26 1.936 697.282 322923.09 47297.8 2748 799 135517.46 4.85 1153 25.04 7026.1 33.37 63484.45 366.493 5.62 236 0.96 9473078.17 2571.3 371131 20.091 24.2951 630 2.15938 257.15 40.2812 3022.9 3201.0 8.663 82.89 467866 5.77 2.91 16866.1 24.3527 3.68404 22.0215 64.82 2635.7 16.26 20261 1112427.2 23967 22.4174 48319 3017.5 667284.36 0.28138 3.81155 25.5852 35.123 40852 5269 40580 20152 1030 666008.7 0.222 2.060 0.109 2.078 0.303 1.375 0.264 0.864 0.031 1.36 47224.77 8.27 9657.99 85.47 233.33 32.00 2478.96 4.52 4414.94 239.86 83.26 18.67 1071.70 1451.62 13.67 1424.57 13.92 819.63 24.29 233.750 111.920 2.667 29.670 95.415 3208.0 17787.2 16070 12260 443 694 11045 1.50 42731.93 13.60 1478.64 2.090 3.956 2.356 12.097 2460.37 187775.77 1088788.92 1398073.70 1339297.91 0.270 1855656 0.150 1669388 4240.41 68713.0 73896.5 16614.41 1847194.12 1931278.62 2018201.09 2.79 37.95778 447.616 2.38563 5.40603 179473129 1138 8693.9 5600 3.044 2.163 5.828 85792 20.21 87357 2.862 2453 17905.8 965.3 12603.1 993.1 5.0 8256.6 8024 14924848.44 82.43 479.0 15903941.88 668.3 195.934 8225.4 132.871 6.15 9808 5.21 267.387 73.188 2.351 3.463 147.63 192.06 386.79 400.32 400.44 161.930 3512867.33 148.91 6.174 163.87 4.690 153.77 869 994 1621.3 13.56 2.243 8684030.90 7.853 1978 35.995 18.186 328235.14 95806.71 42.625 11244.94 359.8980 2722264.50 48.8 3336.53 342573199.69 8576.95 118161.83 2077 992 33.05 1161464.61 8.046 2.912 2558 3620.857 50.4720 348.815 4.8916 3783.49 38.303 78.591 215488.10 2346688.3 1.862 9.525 91.5 72.128 837.1477 893.84 1.854 728.040 309299.86 49331.9 2851 828 140290.21 5.02 1192 24.25 6807.8 32.43 61843.01 358.153 5.74 241 0.98 9658490.04 2522.5 364209 20.448 24.7159 640 2.12637 253.27 40.8610 2985.2 3163.1 8.563 81.97 473026 5.71 2.94 17031.1 24.5903 3.64846 22.2247 64.23 2613.2 16.40 20404 1119831.8 24102 22.5168 48506 3007.5 669368.18 0.28053 3.80080 25.6467 35.046 40932 5259 40503 20180 1029 10692920.63 3826220.78 4236085.83 4003419.31 15.17 15.59 13.07 34.45 485587.54 10151 521 636 10211 2.179 4.244 2.529 12.813 36452.69 145035.86 1140633.72 1994991.48 1760873.07 0.275 1831665 0.132 1913115 3701.27 68566.7 42370.3 6244.19 2078925.13 2083152.81 2765192.67 2.04 12.2723 487.116 2.30251 4.64086 186079628 1737 5950.5 3683 2.656 1.662 OpenBenchmarking.org
PostgreSQL pgbench Scaling Factor: 100 - Clients: 500 - Mode: Read Write - Average Latency OpenBenchmarking.org ms, Fewer Is Better PostgreSQL pgbench 14.0 Scaling Factor: 100 - Clients: 500 - Mode: Read Write - Average Latency Clear Linux 36990 CentOS Stream 9 6 12 18 24 30 SE +/- 0.008, N = 3 SE +/- 0.047, N = 3 5.828 26.724 -O3 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake -mrelax-cmpxchg-loop -O2 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -lpgcommon -lpgport -lpq -lm
PostgreSQL pgbench Scaling Factor: 100 - Clients: 500 - Mode: Read Write OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 14.0 Scaling Factor: 100 - Clients: 500 - Mode: Read Write Clear Linux 36990 CentOS Stream 9 20K 40K 60K 80K 100K SE +/- 119.89, N = 3 SE +/- 32.56, N = 3 85792 18710 -O3 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake -mrelax-cmpxchg-loop -O2 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -lpgcommon -lpgport -lpq -lm
Apache Spark Row Count: 40000000 - Partitions: 500 - SHA-512 Benchmark Time OpenBenchmarking.org Seconds, Fewer Is Better Apache Spark 3.3 Row Count: 40000000 - Partitions: 500 - SHA-512 Benchmark Time Clear Linux 36990 CentOS Stream 9 20 40 60 80 100 SE +/- 0.19, N = 15 SE +/- 0.53, N = 3 20.21 88.83
PostgreSQL pgbench Scaling Factor: 100 - Clients: 250 - Mode: Read Write OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 14.0 Scaling Factor: 100 - Clients: 250 - Mode: Read Write Clear Linux 36990 CentOS Stream 9 20K 40K 60K 80K 100K SE +/- 149.93, N = 3 SE +/- 21.44, N = 3 87357 20745 -O3 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake -mrelax-cmpxchg-loop -O2 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -lpgcommon -lpgport -lpq -lm
PostgreSQL pgbench Scaling Factor: 100 - Clients: 250 - Mode: Read Write - Average Latency OpenBenchmarking.org ms, Fewer Is Better PostgreSQL pgbench 14.0 Scaling Factor: 100 - Clients: 250 - Mode: Read Write - Average Latency Clear Linux 36990 CentOS Stream 9 3 6 9 12 15 SE +/- 0.005, N = 3 SE +/- 0.012, N = 3 2.862 12.051 -O3 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake -mrelax-cmpxchg-loop -O2 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -lpgcommon -lpgport -lpq -lm
DaCapo Benchmark Java Test: H2 OpenBenchmarking.org msec, Fewer Is Better DaCapo Benchmark 9.12-MR1 Java Test: H2 Clear Linux 36990 CentOS Stream 9 2K 4K 6K 8K 10K SE +/- 29.40, N = 4 SE +/- 54.95, N = 4 2453 9847
C-Blosc Test: blosclz shuffle OpenBenchmarking.org MB/s, More Is Better C-Blosc 2.3 Test: blosclz shuffle Clear Linux 36990 CentOS Stream 9 4K 8K 12K 16K 20K SE +/- 153.72, N = 15 SE +/- 23.45, N = 3 17905.8 4916.7 1. (CC) gcc options: -std=gnu99 -O3 -lrt -lm
Zstd Compression Compression Level: 3, Long Mode - Compression Speed OpenBenchmarking.org MB/s, More Is Better Zstd Compression Compression Level: 3, Long Mode - Compression Speed Clear Linux 36990 CentOS Stream 9 200 400 600 800 1000 SE +/- 7.62, N = 15 SE +/- 4.03, N = 3 969.1 281.0 1. Clear Linux 36990: *** zstd command line interface 64-bits v1.5.2, by Yann Collet *** 2. CentOS Stream 9: *** zstd command line interface 64-bits v1.5.1, by Yann Collet ***
C-Blosc Test: blosclz bitshuffle OpenBenchmarking.org MB/s, More Is Better C-Blosc 2.3 Test: blosclz bitshuffle Clear Linux 36990 CentOS Stream 9 3K 6K 9K 12K 15K SE +/- 20.65, N = 3 SE +/- 6.11, N = 3 12603.1 3704.1 1. (CC) gcc options: -std=gnu99 -O3 -lrt -lm
Zstd Compression Compression Level: 8, Long Mode - Compression Speed OpenBenchmarking.org MB/s, More Is Better Zstd Compression Compression Level: 8, Long Mode - Compression Speed Clear Linux 36990 CentOS Stream 9 200 400 600 800 1000 SE +/- 3.84, N = 3 SE +/- 0.78, N = 3 995.9 307.5 1. Clear Linux 36990: *** zstd command line interface 64-bits v1.5.2, by Yann Collet *** 2. CentOS Stream 9: *** zstd command line interface 64-bits v1.5.1, by Yann Collet ***
Natron Input: Spaceship OpenBenchmarking.org FPS, More Is Better Natron 2.4.3 Input: Spaceship Clear Linux 36990 CentOS Stream 9 1.125 2.25 3.375 4.5 5.625 SE +/- 0.03, N = 3 SE +/- 0.01, N = 15 5.0 1.9
Renaissance Test: Savina Reactors.IO OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.14 Test: Savina Reactors.IO Clear Linux 36990 CentOS Stream 9 5K 10K 15K 20K 25K SE +/- 56.26, N = 15 SE +/- 296.93, N = 3 8256.6 21219.4 MIN: 7799.33 / MAX: 12715.24 MIN: 20627.9 / MAX: 32602.9
ONNX Runtime Model: super-resolution-10 - Device: CPU - Executor: Parallel OpenBenchmarking.org Inferences Per Minute, More Is Better ONNX Runtime 1.11 Model: super-resolution-10 - Device: CPU - Executor: Parallel Clear Linux 36990 CentOS Stream 9 2K 4K 6K 8K 10K SE +/- 8.23, N = 3 SE +/- 4.91, N = 3 8024 3259 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake -mrelax-cmpxchg-loop -flto=auto -flto 1. (CXX) g++ options: -O3 -ffunction-sections -fdata-sections -march=native -mtune=native -fno-fat-lto-objects -ldl -lrt
Stress-NG Test: Context Switching OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14 Test: Context Switching Clear Linux 36990 CentOS Stream 9 3M 6M 9M 12M 15M SE +/- 96811.45, N = 15 SE +/- 78706.86, N = 3 14924848.44 6233126.45 -O3 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake -mrelax-cmpxchg-loop -laio -latomic 1. (CC) gcc options: -O2 -std=gnu99 -lm -lc -lcrypt -ldl -ljpeg -lrt -lz -pthread
x264 Video Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better x264 2022-02-22 Video Input: Bosphorus 4K Clear Linux 36990 CentOS Stream 9 20 40 60 80 100 SE +/- 1.11, N = 3 SE +/- 0.49, N = 15 82.43 34.57 1. (CC) gcc options: -ldl -m64 -lm -lpthread -O3 -flto
Renaissance Test: Apache Spark Bayes OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.14 Test: Apache Spark Bayes Clear Linux 36990 CentOS Stream 9 200 400 600 800 1000 SE +/- 1.10, N = 3 SE +/- 11.23, N = 3 479.0 1075.3 MIN: 329.34 / MAX: 719.74 MIN: 628.33 / MAX: 1551.11
Stress-NG Test: Semaphores OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14 Test: Semaphores Clear Linux 36990 CentOS Stream 9 3M 6M 9M 12M 15M SE +/- 5152.27, N = 3 SE +/- 27158.37, N = 3 15903941.88 7186364.51 -O3 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake -mrelax-cmpxchg-loop -laio -latomic 1. (CC) gcc options: -O2 -std=gnu99 -lm -lc -lcrypt -ldl -ljpeg -lrt -lz -pthread
Renaissance Test: Random Forest OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.14 Test: Random Forest Clear Linux 36990 CentOS Stream 9 300 600 900 1200 1500 SE +/- 6.83, N = 3 SE +/- 6.85, N = 3 668.3 1455.2 MIN: 620.85 / MAX: 782.18 MIN: 1315.52 / MAX: 1806.24
SVT-AV1 Encoder Mode: Preset 12 - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.2 Encoder Mode: Preset 12 - Input: Bosphorus 4K Clear Linux 36990 CentOS Stream 9 40 80 120 160 200 SE +/- 1.35, N = 3 SE +/- 0.83, N = 3 195.93 92.83 -O3 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake -mrelax-cmpxchg-loop 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
Renaissance Test: ALS Movie Lens OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.14 Test: ALS Movie Lens Clear Linux 36990 CentOS Stream 9 4K 8K 12K 16K 20K SE +/- 28.18, N = 3 SE +/- 73.46, N = 3 8225.4 17123.9 MIN: 8194.03 / MAX: 9046.37 MIN: 16240.16 / MAX: 19195.87
SVT-AV1 Encoder Mode: Preset 10 - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.2 Encoder Mode: Preset 10 - Input: Bosphorus 4K Clear Linux 36990 CentOS Stream 9 30 60 90 120 150 SE +/- 0.37, N = 3 SE +/- 0.26, N = 3 132.87 65.62 -O3 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake -mrelax-cmpxchg-loop 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
VP9 libvpx Encoding Speed: Speed 0 - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better VP9 libvpx Encoding 1.10.0 Speed: Speed 0 - Input: Bosphorus 4K Clear Linux 36990 CentOS Stream 9 2 4 6 8 10 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 6.15 3.04 -pipe -fexceptions -ffat-lto-objects -fno-trapping-math -mtune=skylake -mrelax-cmpxchg-loop -U_FORTIFY_SOURCE 1. (CXX) g++ options: -m64 -lm -lpthread -O3 -fPIC -std=gnu++11
Node.js Express HTTP Load Test OpenBenchmarking.org Requests Per Second, More Is Better Node.js Express HTTP Load Test Clear Linux 36990 CentOS Stream 9 2K 4K 6K 8K 10K SE +/- 47.88, N = 3 SE +/- 73.75, N = 15 9808 4910 1. Nodejs
Stress-NG Test: NUMA OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14 Test: NUMA CentOS Stream 9 Clear Linux 36990 3 6 9 12 15 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 10.37 5.21 -O3 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake -mrelax-cmpxchg-loop -laio -latomic 1. (CC) gcc options: -O2 -std=gnu99 -lm -lc -lcrypt -ldl -ljpeg -lrt -lz -pthread
Timed LLVM Compilation Build System: Ninja OpenBenchmarking.org Seconds, Fewer Is Better Timed LLVM Compilation 13.0 Build System: Ninja CentOS Stream 9 Clear Linux 36990 60 120 180 240 300 SE +/- 0.23, N = 3 SE +/- 0.26, N = 3 135.02 267.39
SVT-AV1 Encoder Mode: Preset 8 - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.2 Encoder Mode: Preset 8 - Input: Bosphorus 4K Clear Linux 36990 CentOS Stream 9 16 32 48 64 80 SE +/- 0.40, N = 3 SE +/- 0.30, N = 3 73.19 38.68 -O3 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake -mrelax-cmpxchg-loop 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
SVT-AV1 Encoder Mode: Preset 4 - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.2 Encoder Mode: Preset 4 - Input: Bosphorus 4K Clear Linux 36990 CentOS Stream 9 0.529 1.058 1.587 2.116 2.645 SE +/- 0.003, N = 3 SE +/- 0.001, N = 3 2.351 1.327 -O3 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake -mrelax-cmpxchg-loop 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
libavif avifenc Encoder Speed: 6 OpenBenchmarking.org Seconds, Fewer Is Better libavif avifenc 0.10 Encoder Speed: 6 Clear Linux 36990 CentOS Stream 9 2 4 6 8 10 SE +/- 0.026, N = 3 SE +/- 0.037, N = 3 3.463 6.056 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake -mrelax-cmpxchg-loop 1. (CXX) g++ options: -O3 -fPIC -lm
SVT-HEVC Tuning: 7 - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better SVT-HEVC 1.5.0 Tuning: 7 - Input: Bosphorus 4K Clear Linux 36990 CentOS Stream 9 30 60 90 120 150 SE +/- 0.82, N = 3 SE +/- 1.08, N = 4 147.63 86.67 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake -mrelax-cmpxchg-loop 1. (CC) gcc options: -O3 -fPIE -fPIC -O2 -pie -rdynamic -lpthread -lrt
SVT-HEVC Tuning: 10 - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better SVT-HEVC 1.5.0 Tuning: 10 - Input: Bosphorus 4K Clear Linux 36990 CentOS Stream 9 40 80 120 160 200 SE +/- 2.32, N = 4 SE +/- 1.63, N = 3 192.06 113.23 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake -mrelax-cmpxchg-loop 1. (CC) gcc options: -O3 -fPIE -fPIC -O2 -pie -rdynamic -lpthread -lrt
ClickHouse 100M Rows Web Analytics Dataset, First Run / Cold Cache OpenBenchmarking.org Queries Per Minute, Geo Mean, More Is Better ClickHouse 22.5.4.19 100M Rows Web Analytics Dataset, First Run / Cold Cache Clear Linux 36990 CentOS Stream 9 80 160 240 320 400 SE +/- 5.14, N = 12 SE +/- 2.21, N = 15 386.79 231.48 MIN: 51.15 / MAX: 20000 MIN: 41.47 / MAX: 5454.55 1. ClickHouse server version 22.5.4.19 (official build).
ClickHouse 100M Rows Web Analytics Dataset, Third Run OpenBenchmarking.org Queries Per Minute, Geo Mean, More Is Better ClickHouse 22.5.4.19 100M Rows Web Analytics Dataset, Third Run Clear Linux 36990 CentOS Stream 9 90 180 270 360 450 SE +/- 5.35, N = 12 SE +/- 1.95, N = 15 400.32 243.95 MIN: 54.25 / MAX: 20000 MIN: 42.11 / MAX: 6000 1. ClickHouse server version 22.5.4.19 (official build).
ClickHouse 100M Rows Web Analytics Dataset, Second Run OpenBenchmarking.org Queries Per Minute, Geo Mean, More Is Better ClickHouse 22.5.4.19 100M Rows Web Analytics Dataset, Second Run Clear Linux 36990 CentOS Stream 9 90 180 270 360 450 SE +/- 5.40, N = 12 SE +/- 1.48, N = 15 400.44 244.38 MIN: 53.29 / MAX: 20000 MIN: 44.09 / MAX: 5454.55 1. ClickHouse server version 22.5.4.19 (official build).
OSPRay Benchmark: particle_volume/pathtracer/real_time OpenBenchmarking.org Items Per Second, More Is Better OSPRay 2.10 Benchmark: particle_volume/pathtracer/real_time Clear Linux 36990 CentOS Stream 9 40 80 120 160 200 SE +/- 0.68, N = 3 SE +/- 0.72, N = 3 161.93 100.67
Redis Test: GET - Parallel Connections: 50 OpenBenchmarking.org Requests Per Second, More Is Better Redis 7.0.4 Test: GET - Parallel Connections: 50 Clear Linux 36990 CentOS Stream 9 800K 1600K 2400K 3200K 4000K SE +/- 3266.10, N = 3 SE +/- 2019.92, N = 3 3512867.33 2284227.20 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake -mrelax-cmpxchg-loop 1. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3
SVT-VP9 Tuning: Visual Quality Optimized - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better SVT-VP9 0.3 Tuning: Visual Quality Optimized - Input: Bosphorus 4K Clear Linux 36990 CentOS Stream 9 30 60 90 120 150 SE +/- 1.00, N = 3 SE +/- 1.23, N = 3 148.91 99.27 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake -mrelax-cmpxchg-loop 1. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm
libavif avifenc Encoder Speed: 6, Lossless OpenBenchmarking.org Seconds, Fewer Is Better libavif avifenc 0.10 Encoder Speed: 6, Lossless Clear Linux 36990 CentOS Stream 9 3 6 9 12 15 SE +/- 0.021, N = 3 SE +/- 0.070, N = 15 6.174 9.260 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake -mrelax-cmpxchg-loop 1. (CXX) g++ options: -O3 -fPIC -lm
SVT-VP9 Tuning: PSNR/SSIM Optimized - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better SVT-VP9 0.3 Tuning: PSNR/SSIM Optimized - Input: Bosphorus 4K Clear Linux 36990 CentOS Stream 9 40 80 120 160 200 SE +/- 0.92, N = 3 SE +/- 1.37, N = 4 163.87 115.50 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake -mrelax-cmpxchg-loop 1. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm
libavif avifenc Encoder Speed: 10, Lossless OpenBenchmarking.org Seconds, Fewer Is Better libavif avifenc 0.10 Encoder Speed: 10, Lossless Clear Linux 36990 CentOS Stream 9 2 4 6 8 10 SE +/- 0.012, N = 3 SE +/- 0.073, N = 15 4.690 6.605 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake -mrelax-cmpxchg-loop 1. (CXX) g++ options: -O3 -fPIC -lm
SVT-VP9 Tuning: VMAF Optimized - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better SVT-VP9 0.3 Tuning: VMAF Optimized - Input: Bosphorus 4K Clear Linux 36990 CentOS Stream 9 30 60 90 120 150 SE +/- 2.02, N = 3 SE +/- 0.07, N = 3 153.77 112.93 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake -mrelax-cmpxchg-loop 1. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm
GraphicsMagick Operation: Sharpen OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.38 Operation: Sharpen Clear Linux 36990 CentOS Stream 9 200 400 600 800 1000 SE +/- 2.31, N = 3 SE +/- 1.76, N = 3 869 641 -O3 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake -mrelax-cmpxchg-loop -ltiff -lfreetype -lSM -lICE -lxml2 -O2 1. (CC) gcc options: -fopenmp -ljpeg -lXext -lX11 -lbz2 -lz -lm -lpthread
GraphicsMagick Operation: Noise-Gaussian OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.38 Operation: Noise-Gaussian Clear Linux 36990 CentOS Stream 9 200 400 600 800 1000 SE +/- 3.93, N = 3 SE +/- 0.88, N = 3 994 738 -O3 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake -mrelax-cmpxchg-loop -ltiff -lfreetype -lSM -lICE -lxml2 -O2 1. (CC) gcc options: -fopenmp -ljpeg -lXext -lX11 -lbz2 -lz -lm -lpthread
Zstd Compression Compression Level: 8 - Compression Speed OpenBenchmarking.org MB/s, More Is Better Zstd Compression Compression Level: 8 - Compression Speed Clear Linux 36990 CentOS Stream 9 300 600 900 1200 1500 SE +/- 15.83, N = 15 SE +/- 18.11, N = 12 1621.3 1244.0 1. Clear Linux 36990: *** zstd command line interface 64-bits v1.5.2, by Yann Collet *** 2. CentOS Stream 9: *** zstd command line interface 64-bits v1.5.1, by Yann Collet ***
Node.js V8 Web Tooling Benchmark OpenBenchmarking.org runs/s, More Is Better Node.js V8 Web Tooling Benchmark Clear Linux 36990 CentOS Stream 9 3 6 9 12 15 SE +/- 0.03, N = 3 SE +/- 0.06, N = 3 13.56 10.55
PyHPC Benchmarks Device: CPU - Backend: Numpy - Project Size: 4194304 - Benchmark: Isoneutral Mixing OpenBenchmarking.org Seconds, Fewer Is Better PyHPC Benchmarks 3.0 Device: CPU - Backend: Numpy - Project Size: 4194304 - Benchmark: Isoneutral Mixing Clear Linux 36990 CentOS Stream 9 0.6476 1.2952 1.9428 2.5904 3.238 SE +/- 0.001, N = 3 SE +/- 0.033, N = 3 2.243 2.878
Stress-NG Test: System V Message Passing OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14 Test: System V Message Passing Clear Linux 36990 CentOS Stream 9 2M 4M 6M 8M 10M SE +/- 1671.17, N = 3 SE +/- 85352.98, N = 4 8684030.90 7093379.73 -O3 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake -mrelax-cmpxchg-loop -laio -latomic 1. (CC) gcc options: -O2 -std=gnu99 -lm -lc -lcrypt -ldl -ljpeg -lrt -lz -pthread
Unpacking The Linux Kernel linux-5.19.tar.xz OpenBenchmarking.org Seconds, Fewer Is Better Unpacking The Linux Kernel 5.19 linux-5.19.tar.xz Clear Linux 36990 CentOS Stream 9 3 6 9 12 15 SE +/- 0.002, N = 4 SE +/- 0.116, N = 17 7.853 9.194
ONNX Runtime Model: ArcFace ResNet-100 - Device: CPU - Executor: Parallel OpenBenchmarking.org Inferences Per Minute, More Is Better ONNX Runtime 1.11 Model: ArcFace ResNet-100 - Device: CPU - Executor: Parallel Clear Linux 36990 CentOS Stream 9 400 800 1200 1600 2000 SE +/- 3.21, N = 3 SE +/- 3.09, N = 3 1978 1693 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake -mrelax-cmpxchg-loop -flto=auto -flto 1. (CXX) g++ options: -O3 -ffunction-sections -fdata-sections -march=native -mtune=native -fno-fat-lto-objects -ldl -lrt
LAMMPS Molecular Dynamics Simulator Model: Rhodopsin Protein OpenBenchmarking.org ns/day, More Is Better LAMMPS Molecular Dynamics Simulator 23Jun2022 Model: Rhodopsin Protein Clear Linux 36990 CentOS Stream 9 8 16 24 32 40 SE +/- 0.08, N = 3 SE +/- 0.06, N = 3 36.00 30.87 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake -mrelax-cmpxchg-loop 1. (CXX) g++ options: -O3 -lm -ldl
WebP Image Encode Encode Settings: Quality 100, Lossless OpenBenchmarking.org Encode Time - Seconds, Fewer Is Better WebP Image Encode 1.1 Encode Settings: Quality 100, Lossless Clear Linux 36990 CentOS Stream 9 5 10 15 20 25 SE +/- 0.08, N = 3 SE +/- 0.17, N = 3 18.19 21.12 -O3 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake -mrelax-cmpxchg-loop -ltiff -O2 1. (CC) gcc options: -fvisibility=hidden -lm -ljpeg -lpng16
Stress-NG Test: Matrix Math OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14 Test: Matrix Math Clear Linux 36990 CentOS Stream 9 70K 140K 210K 280K 350K SE +/- 272.45, N = 3 SE +/- 512.51, N = 3 328235.14 286293.40 -O3 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake -mrelax-cmpxchg-loop -laio -latomic 1. (CC) gcc options: -O2 -std=gnu99 -lm -lc -lcrypt -ldl -ljpeg -lrt -lz -pthread
Stress-NG Test: Crypto OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14 Test: Crypto Clear Linux 36990 CentOS Stream 9 20K 40K 60K 80K 100K SE +/- 22.86, N = 3 SE +/- 289.31, N = 3 95806.71 83808.91 -O3 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake -mrelax-cmpxchg-loop -laio -latomic 1. (CC) gcc options: -O2 -std=gnu99 -lm -lc -lcrypt -ldl -ljpeg -lrt -lz -pthread
libavif avifenc Encoder Speed: 2 OpenBenchmarking.org Seconds, Fewer Is Better libavif avifenc 0.10 Encoder Speed: 2 Clear Linux 36990 CentOS Stream 9 11 22 33 44 55 SE +/- 0.10, N = 3 SE +/- 0.53, N = 3 42.63 48.71 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake -mrelax-cmpxchg-loop 1. (CXX) g++ options: -O3 -fPIC -lm
Stress-NG Test: Memory Copying OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14 Test: Memory Copying CentOS Stream 9 Clear Linux 36990 3K 6K 9K 12K 15K SE +/- 5.23, N = 3 SE +/- 141.11, N = 3 12812.45 11244.94 -O3 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake -mrelax-cmpxchg-loop -laio -latomic 1. (CC) gcc options: -O2 -std=gnu99 -lm -lc -lcrypt -ldl -ljpeg -lrt -lz -pthread
ASTC Encoder Preset: Medium OpenBenchmarking.org MT/s, More Is Better ASTC Encoder 4.0 Preset: Medium Clear Linux 36990 CentOS Stream 9 80 160 240 320 400 SE +/- 1.16, N = 3 SE +/- 2.47, N = 15 359.90 316.37 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake -mrelax-cmpxchg-loop 1. (CXX) g++ options: -O3 -flto -pthread
Redis Test: GET - Parallel Connections: 1000 OpenBenchmarking.org Requests Per Second, More Is Better Redis 7.0.4 Test: GET - Parallel Connections: 1000 Clear Linux 36990 CentOS Stream 9 600K 1200K 1800K 2400K 3000K SE +/- 23267.85, N = 3 SE +/- 26860.41, N = 5 2722264.50 2406986.65 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake -mrelax-cmpxchg-loop 1. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3
Zstd Compression Compression Level: 19, Long Mode - Compression Speed OpenBenchmarking.org MB/s, More Is Better Zstd Compression Compression Level: 19, Long Mode - Compression Speed Clear Linux 36990 CentOS Stream 9 11 22 33 44 55 SE +/- 0.37, N = 3 SE +/- 0.45, N = 5 48.8 43.4 1. Clear Linux 36990: *** zstd command line interface 64-bits v1.5.2, by Yann Collet *** 2. CentOS Stream 9: *** zstd command line interface 64-bits v1.5.1, by Yann Collet ***
Stress-NG Test: MMAP OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14 Test: MMAP CentOS Stream 9 Clear Linux 36990 800 1600 2400 3200 4000 SE +/- 34.11, N = 3 SE +/- 1.76, N = 3 3747.58 3336.53 -O3 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake -mrelax-cmpxchg-loop -laio -latomic 1. (CC) gcc options: -O2 -std=gnu99 -lm -lc -lcrypt -ldl -ljpeg -lrt -lz -pthread
Stress-NG Test: Malloc OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14 Test: Malloc Clear Linux 36990 CentOS Stream 9 70M 140M 210M 280M 350M SE +/- 1194169.90, N = 3 SE +/- 452266.97, N = 3 342573199.69 306750258.84 -O3 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake -mrelax-cmpxchg-loop -laio -latomic 1. (CC) gcc options: -O2 -std=gnu99 -lm -lc -lcrypt -ldl -ljpeg -lrt -lz -pthread
TensorFlow Lite Model: Mobilenet Quant OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2022-05-18 Model: Mobilenet Quant Clear Linux 36990 CentOS Stream 9 2K 4K 6K 8K 10K SE +/- 81.76, N = 6 SE +/- 100.45, N = 3 8576.95 9540.86
Apache HTTP Server Concurrent Requests: 1000 OpenBenchmarking.org Requests Per Second, More Is Better Apache HTTP Server 2.4.48 Concurrent Requests: 1000 CentOS Stream 9 Clear Linux 36990 30K 60K 90K 120K 150K SE +/- 1558.40, N = 15 SE +/- 760.56, N = 3 131349.60 118161.83 -O2 -O3 -m64 -mtune=skylake -mrelax-cmpxchg-loop 1. (CC) gcc options: -shared -fPIC
ONNX Runtime Model: ArcFace ResNet-100 - Device: CPU - Executor: Standard OpenBenchmarking.org Inferences Per Minute, More Is Better ONNX Runtime 1.11 Model: ArcFace ResNet-100 - Device: CPU - Executor: Standard Clear Linux 36990 CentOS Stream 9 400 800 1200 1600 2000 SE +/- 24.49, N = 12 SE +/- 16.82, N = 12 2077 1881 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake -mrelax-cmpxchg-loop -flto=auto -flto 1. (CXX) g++ options: -O3 -ffunction-sections -fdata-sections -march=native -mtune=native -fno-fat-lto-objects -ldl -lrt
ONNX Runtime Model: bertsquad-12 - Device: CPU - Executor: Standard OpenBenchmarking.org Inferences Per Minute, More Is Better ONNX Runtime 1.11 Model: bertsquad-12 - Device: CPU - Executor: Standard CentOS Stream 9 Clear Linux 36990 200 400 600 800 1000 SE +/- 0.50, N = 3 SE +/- 5.77, N = 3 1093 992 -flto -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake -mrelax-cmpxchg-loop -flto=auto 1. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -fno-fat-lto-objects -ldl -lrt
Apache Spark Row Count: 40000000 - Partitions: 500 - Calculate Pi Benchmark OpenBenchmarking.org Seconds, Fewer Is Better Apache Spark 3.3 Row Count: 40000000 - Partitions: 500 - Calculate Pi Benchmark Clear Linux 36990 CentOS Stream 9 8 16 24 32 40 SE +/- 0.06, N = 15 SE +/- 0.12, N = 3 33.05 36.21
Stress-NG Test: SENDFILE OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14 Test: SENDFILE CentOS Stream 9 Clear Linux 36990 300K 600K 900K 1200K 1500K SE +/- 2669.03, N = 3 SE +/- 713.22, N = 3 1271967.05 1161464.61 -O3 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake -mrelax-cmpxchg-loop -laio -latomic 1. (CC) gcc options: -O2 -std=gnu99 -lm -lc -lcrypt -ldl -ljpeg -lrt -lz -pthread
WebP Image Encode Encode Settings: Quality 100, Highest Compression OpenBenchmarking.org Encode Time - Seconds, Fewer Is Better WebP Image Encode 1.1 Encode Settings: Quality 100, Highest Compression Clear Linux 36990 CentOS Stream 9 2 4 6 8 10 SE +/- 0.002, N = 3 SE +/- 0.061, N = 15 8.046 8.802 -O3 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake -mrelax-cmpxchg-loop -ltiff -O2 1. (CC) gcc options: -fvisibility=hidden -lm -ljpeg -lpng16
Mobile Neural Network Model: MobileNetV2_224 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 2.1 Model: MobileNetV2_224 CentOS Stream 9 Clear Linux 36990 0.6552 1.3104 1.9656 2.6208 3.276 SE +/- 0.014, N = 15 SE +/- 0.013, N = 3 2.663 2.912 MIN: 2.48 / MAX: 5.57 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake -mrelax-cmpxchg-loop - MIN: 2.72 / MAX: 5.76 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
GraphicsMagick Operation: Swirl OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.38 Operation: Swirl Clear Linux 36990 CentOS Stream 9 500 1000 1500 2000 2500 SE +/- 14.50, N = 3 SE +/- 10.48, N = 3 2558 2340 -O3 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake -mrelax-cmpxchg-loop -ltiff -lfreetype -lSM -lICE -lxml2 -O2 1. (CC) gcc options: -fopenmp -ljpeg -lXext -lX11 -lbz2 -lz -lm -lpthread
TNN Target: CPU - Model: DenseNet OpenBenchmarking.org ms, Fewer Is Better TNN 0.3 Target: CPU - Model: DenseNet Clear Linux 36990 CentOS Stream 9 800 1600 2400 3200 4000 SE +/- 1.46, N = 3 SE +/- 27.70, N = 3 3620.86 3955.05 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake -mrelax-cmpxchg-loop - MIN: 3599.42 / MAX: 3730.48 MIN: 3833.99 / MAX: 5510.15 1. (CXX) g++ options: -O3 -fopenmp -pthread -fvisibility=hidden -fvisibility=default -rdynamic -ldl
ASTC Encoder Preset: Thorough OpenBenchmarking.org MT/s, More Is Better ASTC Encoder 4.0 Preset: Thorough Clear Linux 36990 CentOS Stream 9 11 22 33 44 55 SE +/- 0.06, N = 3 SE +/- 0.05, N = 3 50.47 46.38 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake -mrelax-cmpxchg-loop 1. (CXX) g++ options: -O3 -flto -pthread
TNN Target: CPU - Model: MobileNet v2 OpenBenchmarking.org ms, Fewer Is Better TNN 0.3 Target: CPU - Model: MobileNet v2 Clear Linux 36990 CentOS Stream 9 80 160 240 320 400 SE +/- 0.42, N = 3 SE +/- 4.68, N = 4 348.82 378.88 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake -mrelax-cmpxchg-loop - MIN: 346.87 / MAX: 355.44 MIN: 371.88 / MAX: 634.44 1. (CXX) g++ options: -O3 -fopenmp -pthread -fvisibility=hidden -fvisibility=default -rdynamic -ldl
ASTC Encoder Preset: Exhaustive OpenBenchmarking.org MT/s, More Is Better ASTC Encoder 4.0 Preset: Exhaustive Clear Linux 36990 CentOS Stream 9 1.1006 2.2012 3.3018 4.4024 5.503 SE +/- 0.0032, N = 3 SE +/- 0.0017, N = 3 4.8916 4.5054 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake -mrelax-cmpxchg-loop 1. (CXX) g++ options: -O3 -flto -pthread
Stress-NG Test: MEMFD OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14 Test: MEMFD CentOS Stream 9 Clear Linux 36990 900 1800 2700 3600 4500 SE +/- 35.16, N = 3 SE +/- 5.40, N = 3 4098.84 3783.49 -O3 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake -mrelax-cmpxchg-loop -laio -latomic 1. (CC) gcc options: -O2 -std=gnu99 -lm -lc -lcrypt -ldl -ljpeg -lrt -lz -pthread
WebP Image Encode Encode Settings: Quality 100, Lossless, Highest Compression OpenBenchmarking.org Encode Time - Seconds, Fewer Is Better WebP Image Encode 1.1 Encode Settings: Quality 100, Lossless, Highest Compression Clear Linux 36990 CentOS Stream 9 9 18 27 36 45 SE +/- 0.04, N = 3 SE +/- 0.22, N = 3 38.30 41.21 -O3 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake -mrelax-cmpxchg-loop -ltiff -O2 1. (CC) gcc options: -fvisibility=hidden -lm -ljpeg -lpng16
libavif avifenc Encoder Speed: 0 OpenBenchmarking.org Seconds, Fewer Is Better libavif avifenc 0.10 Encoder Speed: 0 Clear Linux 36990 CentOS Stream 9 20 40 60 80 100 SE +/- 0.45, N = 3 SE +/- 0.66, N = 3 78.59 84.32 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake -mrelax-cmpxchg-loop 1. (CXX) g++ options: -O3 -fPIC -lm
nginx Concurrent Requests: 1000 OpenBenchmarking.org Requests Per Second, More Is Better nginx 1.21.1 Concurrent Requests: 1000 Clear Linux 36990 CentOS Stream 9 50K 100K 150K 200K 250K SE +/- 255.31, N = 3 SE +/- 1519.57, N = 3 215488.10 200945.49 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake -mrelax-cmpxchg-loop 1. (CC) gcc options: -lcrypt -lz -O3 -march=native
Redis Test: SET - Parallel Connections: 50 OpenBenchmarking.org Requests Per Second, More Is Better Redis 7.0.4 Test: SET - Parallel Connections: 50 Clear Linux 36990 CentOS Stream 9 500K 1000K 1500K 2000K 2500K SE +/- 9831.09, N = 3 SE +/- 29696.58, N = 3 2346688.30 2189377.08 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake -mrelax-cmpxchg-loop 1. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3
Mobile Neural Network Model: mobilenetV3 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 2.1 Model: mobilenetV3 CentOS Stream 9 Clear Linux 36990 0.419 0.838 1.257 1.676 2.095 SE +/- 0.020, N = 15 SE +/- 0.017, N = 3 1.753 1.862 MIN: 1.61 / MAX: 4.19 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake -mrelax-cmpxchg-loop - MIN: 1.81 / MAX: 2.51 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
GROMACS Implementation: MPI CPU - Input: water_GMX50_bare OpenBenchmarking.org Ns Per Day, More Is Better GROMACS 2022.1 Implementation: MPI CPU - Input: water_GMX50_bare Clear Linux 36990 CentOS Stream 9 3 6 9 12 15 SE +/- 0.033, N = 3 SE +/- 0.002, N = 3 9.525 8.996 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake -mrelax-cmpxchg-loop 1. (CXX) g++ options: -O3
Zstd Compression Compression Level: 19 - Compression Speed OpenBenchmarking.org MB/s, More Is Better Zstd Compression Compression Level: 19 - Compression Speed Clear Linux 36990 CentOS Stream 9 20 40 60 80 100 SE +/- 0.48, N = 3 SE +/- 0.52, N = 3 91.5 86.6 1. Clear Linux 36990: *** zstd command line interface 64-bits v1.5.2, by Yann Collet *** 2. CentOS Stream 9: *** zstd command line interface 64-bits v1.5.1, by Yann Collet ***
TNN Target: CPU - Model: SqueezeNet v2 OpenBenchmarking.org ms, Fewer Is Better TNN 0.3 Target: CPU - Model: SqueezeNet v2 Clear Linux 36990 CentOS Stream 9 20 40 60 80 100 SE +/- 0.57, N = 10 SE +/- 0.78, N = 3 72.13 75.88 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake -mrelax-cmpxchg-loop - MIN: 71.03 / MAX: 78.39 MIN: 74.63 / MAX: 111.7 1. (CXX) g++ options: -O3 -fopenmp -pthread -fvisibility=hidden -fvisibility=default -rdynamic -ldl
ASTC Encoder Preset: Fast OpenBenchmarking.org MT/s, More Is Better ASTC Encoder 4.0 Preset: Fast Clear Linux 36990 CentOS Stream 9 200 400 600 800 1000 SE +/- 1.80, N = 3 SE +/- 3.69, N = 3 837.15 799.11 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake -mrelax-cmpxchg-loop 1. (CXX) g++ options: -O3 -flto -pthread
Stress-NG Test: Glibc Qsort Data Sorting OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14 Test: Glibc Qsort Data Sorting CentOS Stream 9 Clear Linux 36990 200 400 600 800 1000 SE +/- 2.69, N = 3 SE +/- 1.09, N = 3 934.26 893.84 -O3 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake -mrelax-cmpxchg-loop -laio -latomic 1. (CC) gcc options: -O2 -std=gnu99 -lm -lc -lcrypt -ldl -ljpeg -lrt -lz -pthread
PyHPC Benchmarks Device: CPU - Backend: Numpy - Project Size: 4194304 - Benchmark: Equation of State OpenBenchmarking.org Seconds, Fewer Is Better PyHPC Benchmarks 3.0 Device: CPU - Backend: Numpy - Project Size: 4194304 - Benchmark: Equation of State Clear Linux 36990 CentOS Stream 9 0.4356 0.8712 1.3068 1.7424 2.178 SE +/- 0.001, N = 3 SE +/- 0.001, N = 3 1.854 1.936
oneDNN Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.6 Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPU CentOS Stream 9 Clear Linux 36990 160 320 480 640 800 SE +/- 6.94, N = 12 SE +/- 6.52, N = 15 697.28 728.04 MIN: 605.85 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake -mrelax-cmpxchg-loop - MIN: 651.84 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl -lpthread
Stress-NG Test: Vector Math OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14 Test: Vector Math CentOS Stream 9 Clear Linux 36990 70K 140K 210K 280K 350K SE +/- 944.66, N = 3 SE +/- 79.17, N = 3 322923.09 309299.86 -O3 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake -mrelax-cmpxchg-loop -laio -latomic 1. (CC) gcc options: -O2 -std=gnu99 -lm -lc -lcrypt -ldl -ljpeg -lrt -lz -pthread
TensorFlow Lite Model: Inception ResNet V2 OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2022-05-18 Model: Inception ResNet V2 CentOS Stream 9 Clear Linux 36990 11K 22K 33K 44K 55K SE +/- 268.62, N = 3 SE +/- 583.51, N = 15 47297.8 49331.9
GraphicsMagick Operation: Resizing OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.38 Operation: Resizing Clear Linux 36990 CentOS Stream 9 600 1200 1800 2400 3000 SE +/- 35.23, N = 4 SE +/- 27.10, N = 3 2851 2748 -O3 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake -mrelax-cmpxchg-loop -ltiff -lfreetype -lSM -lICE -lxml2 -O2 1. (CC) gcc options: -fopenmp -ljpeg -lXext -lX11 -lbz2 -lz -lm -lpthread
ONNX Runtime Model: bertsquad-12 - Device: CPU - Executor: Parallel OpenBenchmarking.org Inferences Per Minute, More Is Better ONNX Runtime 1.11 Model: bertsquad-12 - Device: CPU - Executor: Parallel Clear Linux 36990 CentOS Stream 9 200 400 600 800 1000 SE +/- 0.29, N = 3 SE +/- 2.02, N = 3 828 799 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake -mrelax-cmpxchg-loop -flto=auto -flto 1. (CXX) g++ options: -O3 -ffunction-sections -fdata-sections -march=native -mtune=native -fno-fat-lto-objects -ldl -lrt
Stress-NG Test: CPU Stress OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14 Test: CPU Stress Clear Linux 36990 CentOS Stream 9 30K 60K 90K 120K 150K SE +/- 387.90, N = 3 SE +/- 758.69, N = 3 140290.21 135517.46 -O3 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake -mrelax-cmpxchg-loop -laio -latomic 1. (CC) gcc options: -O2 -std=gnu99 -lm -lc -lcrypt -ldl -ljpeg -lrt -lz -pthread
simdjson Throughput Test: PartialTweets OpenBenchmarking.org GB/s, More Is Better simdjson 2.0 Throughput Test: PartialTweets Clear Linux 36990 CentOS Stream 9 1.1295 2.259 3.3885 4.518 5.6475 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 5.02 4.85 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake -mrelax-cmpxchg-loop 1. (CXX) g++ options: -O3
GraphicsMagick Operation: Enhanced OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.38 Operation: Enhanced Clear Linux 36990 CentOS Stream 9 300 600 900 1200 1500 SE +/- 2.08, N = 3 SE +/- 1.76, N = 3 1192 1153 -O3 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake -mrelax-cmpxchg-loop -ltiff -lfreetype -lSM -lICE -lxml2 -O2 1. (CC) gcc options: -fopenmp -ljpeg -lXext -lX11 -lbz2 -lz -lm -lpthread
Blender Blend File: BMW27 - Compute: CPU-Only OpenBenchmarking.org Seconds, Fewer Is Better Blender 3.2 Blend File: BMW27 - Compute: CPU-Only Clear Linux 36990 CentOS Stream 9 6 12 18 24 30 SE +/- 0.06, N = 3 SE +/- 0.03, N = 3 24.25 25.04
Zstd Compression Compression Level: 3 - Compression Speed OpenBenchmarking.org MB/s, More Is Better Zstd Compression Compression Level: 3 - Compression Speed CentOS Stream 9 Clear Linux 36990 1500 3000 4500 6000 7500 SE +/- 78.16, N = 3 SE +/- 4.17, N = 3 7026.1 6807.8 1. CentOS Stream 9: *** zstd command line interface 64-bits v1.5.1, by Yann Collet *** 2. Clear Linux 36990: *** zstd command line interface 64-bits v1.5.2, by Yann Collet ***
Blender Blend File: Fishy Cat - Compute: CPU-Only OpenBenchmarking.org Seconds, Fewer Is Better Blender 3.2 Blend File: Fishy Cat - Compute: CPU-Only Clear Linux 36990 CentOS Stream 9 8 16 24 32 40 SE +/- 0.02, N = 3 SE +/- 0.07, N = 3 32.43 33.37
Stress-NG Test: Forking OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14 Test: Forking CentOS Stream 9 Clear Linux 36990 14K 28K 42K 56K 70K SE +/- 123.25, N = 3 SE +/- 173.91, N = 3 63484.45 61843.01 -O3 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake -mrelax-cmpxchg-loop -laio -latomic 1. (CC) gcc options: -O2 -std=gnu99 -lm -lc -lcrypt -ldl -ljpeg -lrt -lz -pthread
TNN Target: CPU - Model: SqueezeNet v1.1 OpenBenchmarking.org ms, Fewer Is Better TNN 0.3 Target: CPU - Model: SqueezeNet v1.1 Clear Linux 36990 CentOS Stream 9 80 160 240 320 400 SE +/- 0.09, N = 3 SE +/- 0.03, N = 3 358.15 366.49 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake -mrelax-cmpxchg-loop - MIN: 357.28 / MAX: 366.82 MIN: 366.26 / MAX: 366.87 1. (CXX) g++ options: -O3 -fopenmp -pthread -fvisibility=hidden -fvisibility=default -rdynamic -ldl
simdjson Throughput Test: TopTweet OpenBenchmarking.org GB/s, More Is Better simdjson 2.0 Throughput Test: TopTweet Clear Linux 36990 CentOS Stream 9 1.2915 2.583 3.8745 5.166 6.4575 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 5.74 5.62 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake -mrelax-cmpxchg-loop 1. (CXX) g++ options: -O3
ONNX Runtime Model: fcn-resnet101-11 - Device: CPU - Executor: Parallel OpenBenchmarking.org Inferences Per Minute, More Is Better ONNX Runtime 1.11 Model: fcn-resnet101-11 - Device: CPU - Executor: Parallel Clear Linux 36990 CentOS Stream 9 50 100 150 200 250 SE +/- 0.17, N = 3 SE +/- 0.17, N = 3 241 236 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake -mrelax-cmpxchg-loop -flto=auto -flto 1. (CXX) g++ options: -O3 -ffunction-sections -fdata-sections -march=native -mtune=native -fno-fat-lto-objects -ldl -lrt
simdjson Throughput Test: LargeRandom OpenBenchmarking.org GB/s, More Is Better simdjson 2.0 Throughput Test: LargeRandom Clear Linux 36990 CentOS Stream 9 0.2205 0.441 0.6615 0.882 1.1025 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 0.98 0.96 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake -mrelax-cmpxchg-loop 1. (CXX) g++ options: -O3
Stress-NG Test: Glibc C String Functions OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14 Test: Glibc C String Functions Clear Linux 36990 CentOS Stream 9 2M 4M 6M 8M 10M SE +/- 83362.05, N = 8 SE +/- 103735.47, N = 4 9658490.04 9473078.17 -O3 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake -mrelax-cmpxchg-loop -laio -latomic 1. (CC) gcc options: -O2 -std=gnu99 -lm -lc -lcrypt -ldl -ljpeg -lrt -lz -pthread
Zstd Compression Compression Level: 19 - Decompression Speed OpenBenchmarking.org MB/s, More Is Better Zstd Compression Compression Level: 19 - Decompression Speed CentOS Stream 9 Clear Linux 36990 600 1200 1800 2400 3000 SE +/- 6.30, N = 3 SE +/- 2.24, N = 3 2571.3 2522.5 1. CentOS Stream 9: *** zstd command line interface 64-bits v1.5.1, by Yann Collet *** 2. Clear Linux 36990: *** zstd command line interface 64-bits v1.5.2, by Yann Collet ***
7-Zip Compression Test: Decompression Rating OpenBenchmarking.org MIPS, More Is Better 7-Zip Compression 22.01 Test: Decompression Rating CentOS Stream 9 Clear Linux 36990 80K 160K 240K 320K 400K SE +/- 2273.35, N = 3 SE +/- 953.58, N = 3 371131 364209 1. (CXX) g++ options: -lpthread -ldl -O2 -fPIC
Mobile Neural Network Model: inception-v3 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 2.1 Model: inception-v3 CentOS Stream 9 Clear Linux 36990 5 10 15 20 25 SE +/- 0.19, N = 15 SE +/- 0.03, N = 3 20.09 20.45 MIN: 17.31 / MAX: 37.29 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake -mrelax-cmpxchg-loop - MIN: 19.73 / MAX: 33.83 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
OSPRay Benchmark: particle_volume/scivis/real_time OpenBenchmarking.org Items Per Second, More Is Better OSPRay 2.10 Benchmark: particle_volume/scivis/real_time Clear Linux 36990 CentOS Stream 9 6 12 18 24 30 SE +/- 0.05, N = 3 SE +/- 0.29, N = 3 24.72 24.30
ONNX Runtime Model: yolov4 - Device: CPU - Executor: Parallel OpenBenchmarking.org Inferences Per Minute, More Is Better ONNX Runtime 1.11 Model: yolov4 - Device: CPU - Executor: Parallel Clear Linux 36990 CentOS Stream 9 140 280 420 560 700 SE +/- 0.29, N = 3 SE +/- 1.04, N = 3 640 630 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake -mrelax-cmpxchg-loop -flto=auto -flto 1. (CXX) g++ options: -O3 -ffunction-sections -fdata-sections -march=native -mtune=native -fno-fat-lto-objects -ldl -lrt
oneDNN Harness: Convolution Batch Shapes Auto - Data Type: bf16bf16bf16 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.6 Harness: Convolution Batch Shapes Auto - Data Type: bf16bf16bf16 - Engine: CPU Clear Linux 36990 CentOS Stream 9 0.4859 0.9718 1.4577 1.9436 2.4295 SE +/- 0.00145, N = 3 SE +/- 0.01538, N = 3 2.12637 2.15938 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake -mrelax-cmpxchg-loop - MIN: 2.03 MIN: 2.04 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl -lpthread
Blender Blend File: Barbershop - Compute: CPU-Only OpenBenchmarking.org Seconds, Fewer Is Better Blender 3.2 Blend File: Barbershop - Compute: CPU-Only Clear Linux 36990 CentOS Stream 9 60 120 180 240 300 SE +/- 0.37, N = 3 SE +/- 0.55, N = 3 253.27 257.15
High Performance Conjugate Gradient OpenBenchmarking.org GFLOP/s, More Is Better High Performance Conjugate Gradient 3.1 Clear Linux 36990 CentOS Stream 9 9 18 27 36 45 SE +/- 0.05, N = 3 SE +/- 0.08, N = 3 40.86 40.28 -lmpi_cxx 1. (CXX) g++ options: -O3 -ffast-math -ftree-vectorize -lmpi
Zstd Compression Compression Level: 3 - Decompression Speed OpenBenchmarking.org MB/s, More Is Better Zstd Compression Compression Level: 3 - Decompression Speed CentOS Stream 9 Clear Linux 36990 600 1200 1800 2400 3000 SE +/- 0.65, N = 2 SE +/- 1.35, N = 3 3022.9 2985.2 1. CentOS Stream 9: *** zstd command line interface 64-bits v1.5.1, by Yann Collet *** 2. Clear Linux 36990: *** zstd command line interface 64-bits v1.5.2, by Yann Collet ***
Zstd Compression Compression Level: 8, Long Mode - Decompression Speed OpenBenchmarking.org MB/s, More Is Better Zstd Compression Compression Level: 8, Long Mode - Decompression Speed CentOS Stream 9 Clear Linux 36990 700 1400 2100 2800 3500 SE +/- 10.41, N = 3 3201.0 3163.1 1. CentOS Stream 9: *** zstd command line interface 64-bits v1.5.1, by Yann Collet *** 2. Clear Linux 36990: *** zstd command line interface 64-bits v1.5.2, by Yann Collet ***
Mobile Neural Network Model: resnet-v2-50 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 2.1 Model: resnet-v2-50 Clear Linux 36990 CentOS Stream 9 2 4 6 8 10 SE +/- 0.071, N = 3 SE +/- 0.088, N = 15 8.563 8.663 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake -mrelax-cmpxchg-loop - MIN: 8.16 / MAX: 9.67 MIN: 7.71 / MAX: 20.48 1. (CXX) g++ options: -O3 -std=c++11 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl
Blender Blend File: Pabellon Barcelona - Compute: CPU-Only OpenBenchmarking.org Seconds, Fewer Is Better Blender 3.2 Blend File: Pabellon Barcelona - Compute: CPU-Only Clear Linux 36990 CentOS Stream 9 20 40 60 80 100 SE +/- 0.10, N = 3 SE +/- 0.02, N = 3 81.97 82.89
7-Zip Compression Test: Compression Rating OpenBenchmarking.org MIPS, More Is Better 7-Zip Compression 22.01 Test: Compression Rating Clear Linux 36990 CentOS Stream 9 100K 200K 300K 400K 500K SE +/- 507.78, N = 3 SE +/- 5624.44, N = 3 473026 467866 1. (CXX) g++ options: -lpthread -ldl -O2 -fPIC
simdjson Throughput Test: DistinctUserID OpenBenchmarking.org GB/s, More Is Better simdjson 2.0 Throughput Test: DistinctUserID CentOS Stream 9 Clear Linux 36990 1.2983 2.5966 3.8949 5.1932 6.4915 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 5.77 5.71 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake -mrelax-cmpxchg-loop 1. (CXX) g++ options: -O3
simdjson Throughput Test: Kostya OpenBenchmarking.org GB/s, More Is Better simdjson 2.0 Throughput Test: Kostya Clear Linux 36990 CentOS Stream 9 0.6615 1.323 1.9845 2.646 3.3075 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 2.94 2.91 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake -mrelax-cmpxchg-loop 1. (CXX) g++ options: -O3
OpenSSL OpenBenchmarking.org sign/s, More Is Better OpenSSL Clear Linux 36990 CentOS Stream 9 4K 8K 12K 16K 20K SE +/- 134.27, N = 3 SE +/- 205.54, N = 4 17031.1 16866.1 1. Clear Linux 36990: OpenSSL 1.1.1q 5 Jul 2022 2. CentOS Stream 9: OpenSSL 3.0.1 14 Dec 2021 (Library: OpenSSL 3.0.1 14 Dec 2021)
OSPRay Benchmark: particle_volume/ao/real_time OpenBenchmarking.org Items Per Second, More Is Better OSPRay 2.10 Benchmark: particle_volume/ao/real_time Clear Linux 36990 CentOS Stream 9 6 12 18 24 30 SE +/- 0.14, N = 3 SE +/- 0.07, N = 3 24.59 24.35
oneDNN Harness: Deconvolution Batch shapes_3d - Data Type: bf16bf16bf16 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.6 Harness: Deconvolution Batch shapes_3d - Data Type: bf16bf16bf16 - Engine: CPU Clear Linux 36990 CentOS Stream 9 0.8289 1.6578 2.4867 3.3156 4.1445 SE +/- 0.00647, N = 3 SE +/- 0.03477, N = 14 3.64846 3.68404 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake -mrelax-cmpxchg-loop - MIN: 3.53 MIN: 3.54 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl -lpthread
OSPRay Benchmark: gravity_spheres_volume/dim_512/scivis/real_time OpenBenchmarking.org Items Per Second, More Is Better OSPRay 2.10 Benchmark: gravity_spheres_volume/dim_512/scivis/real_time Clear Linux 36990 CentOS Stream 9 5 10 15 20 25 SE +/- 0.07, N = 3 SE +/- 0.15, N = 3 22.22 22.02
Blender Blend File: Classroom - Compute: CPU-Only OpenBenchmarking.org Seconds, Fewer Is Better Blender 3.2 Blend File: Classroom - Compute: CPU-Only Clear Linux 36990 CentOS Stream 9 14 28 42 56 70 SE +/- 0.20, N = 3 SE +/- 0.04, N = 3 64.23 64.82
Zstd Compression Compression Level: 19, Long Mode - Decompression Speed OpenBenchmarking.org MB/s, More Is Better Zstd Compression Compression Level: 19, Long Mode - Decompression Speed CentOS Stream 9 Clear Linux 36990 600 1200 1800 2400 3000 SE +/- 4.30, N = 5 SE +/- 3.36, N = 3 2635.7 2613.2 1. CentOS Stream 9: *** zstd command line interface 64-bits v1.5.1, by Yann Collet *** 2. Clear Linux 36990: *** zstd command line interface 64-bits v1.5.2, by Yann Collet ***
Stress-NG Test: CPU Cache OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14 Test: CPU Cache Clear Linux 36990 CentOS Stream 9 4 8 12 16 20 SE +/- 0.18, N = 5 SE +/- 0.13, N = 10 16.40 16.26 -O3 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake -mrelax-cmpxchg-loop -laio -latomic 1. (CC) gcc options: -O2 -std=gnu99 -lm -lc -lcrypt -ldl -ljpeg -lrt -lz -pthread
OSPRay Studio Camera: 2 - Resolution: 4K - Samples Per Pixel: 16 - Renderer: Path Tracer OpenBenchmarking.org ms, Fewer Is Better OSPRay Studio 0.11 Camera: 2 - Resolution: 4K - Samples Per Pixel: 16 - Renderer: Path Tracer CentOS Stream 9 Clear Linux 36990 4K 8K 12K 16K 20K SE +/- 49.21, N = 3 SE +/- 50.10, N = 3 20261 20404 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake -mrelax-cmpxchg-loop -lm 1. (CXX) g++ options: -O3 -ldl
OpenSSL OpenBenchmarking.org verify/s, More Is Better OpenSSL Clear Linux 36990 CentOS Stream 9 200K 400K 600K 800K 1000K SE +/- 706.24, N = 3 SE +/- 4686.71, N = 4 1119831.8 1112427.2 1. Clear Linux 36990: OpenSSL 1.1.1q 5 Jul 2022 2. CentOS Stream 9: OpenSSL 3.0.1 14 Dec 2021 (Library: OpenSSL 3.0.1 14 Dec 2021)
OSPRay Studio Camera: 3 - Resolution: 4K - Samples Per Pixel: 16 - Renderer: Path Tracer OpenBenchmarking.org ms, Fewer Is Better OSPRay Studio 0.11 Camera: 3 - Resolution: 4K - Samples Per Pixel: 16 - Renderer: Path Tracer CentOS Stream 9 Clear Linux 36990 5K 10K 15K 20K 25K SE +/- 79.25, N = 3 SE +/- 16.17, N = 3 23967 24102 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake -mrelax-cmpxchg-loop -lm 1. (CXX) g++ options: -O3 -ldl
OSPRay Benchmark: gravity_spheres_volume/dim_512/ao/real_time OpenBenchmarking.org Items Per Second, More Is Better OSPRay 2.10 Benchmark: gravity_spheres_volume/dim_512/ao/real_time Clear Linux 36990 CentOS Stream 9 5 10 15 20 25 SE +/- 0.05, N = 3 SE +/- 0.06, N = 3 22.52 22.42
OSPRay Studio Camera: 3 - Resolution: 4K - Samples Per Pixel: 32 - Renderer: Path Tracer OpenBenchmarking.org ms, Fewer Is Better OSPRay Studio 0.11 Camera: 3 - Resolution: 4K - Samples Per Pixel: 32 - Renderer: Path Tracer CentOS Stream 9 Clear Linux 36990 10K 20K 30K 40K 50K SE +/- 81.93, N = 3 SE +/- 111.95, N = 3 48319 48506 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake -mrelax-cmpxchg-loop -lm 1. (CXX) g++ options: -O3 -ldl
Zstd Compression Compression Level: 8 - Decompression Speed OpenBenchmarking.org MB/s, More Is Better Zstd Compression Compression Level: 8 - Decompression Speed CentOS Stream 9 Clear Linux 36990 600 1200 1800 2400 3000 SE +/- 6.19, N = 12 SE +/- 4.36, N = 15 3017.5 3007.5 1. CentOS Stream 9: *** zstd command line interface 64-bits v1.5.1, by Yann Collet *** 2. Clear Linux 36990: *** zstd command line interface 64-bits v1.5.2, by Yann Collet ***
Stress-NG Test: x86_64 RdRand OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14 Test: x86_64 RdRand Clear Linux 36990 CentOS Stream 9 140K 280K 420K 560K 700K SE +/- 30.50, N = 3 SE +/- 2562.02, N = 3 669368.18 667284.36 -O3 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake -mrelax-cmpxchg-loop -laio -latomic 1. (CC) gcc options: -O2 -std=gnu99 -lm -lc -lcrypt -ldl -ljpeg -lrt -lz -pthread
NAMD ATPase Simulation - 327,506 Atoms OpenBenchmarking.org days/ns, Fewer Is Better NAMD 2.14 ATPase Simulation - 327,506 Atoms Clear Linux 36990 CentOS Stream 9 0.0633 0.1266 0.1899 0.2532 0.3165 SE +/- 0.00064, N = 3 SE +/- 0.00094, N = 3 0.28053 0.28138
oneDNN Harness: Deconvolution Batch shapes_1d - Data Type: bf16bf16bf16 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.6 Harness: Deconvolution Batch shapes_1d - Data Type: bf16bf16bf16 - Engine: CPU Clear Linux 36990 CentOS Stream 9 0.8576 1.7152 2.5728 3.4304 4.288 SE +/- 0.00397, N = 3 SE +/- 0.01173, N = 3 3.80080 3.81155 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake -mrelax-cmpxchg-loop - MIN: 3.42 MIN: 3.53 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl -lpthread
OSPRay Benchmark: gravity_spheres_volume/dim_512/pathtracer/real_time OpenBenchmarking.org Items Per Second, More Is Better OSPRay 2.10 Benchmark: gravity_spheres_volume/dim_512/pathtracer/real_time Clear Linux 36990 CentOS Stream 9 6 12 18 24 30 SE +/- 0.03, N = 3 SE +/- 0.04, N = 3 25.65 25.59
LAMMPS Molecular Dynamics Simulator Model: 20k Atoms OpenBenchmarking.org ns/day, More Is Better LAMMPS Molecular Dynamics Simulator 23Jun2022 Model: 20k Atoms CentOS Stream 9 Clear Linux 36990 8 16 24 32 40 SE +/- 0.05, N = 3 SE +/- 0.06, N = 3 35.12 35.05 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake -mrelax-cmpxchg-loop 1. (CXX) g++ options: -O3 -lm -ldl
OSPRay Studio Camera: 2 - Resolution: 4K - Samples Per Pixel: 32 - Renderer: Path Tracer OpenBenchmarking.org ms, Fewer Is Better OSPRay Studio 0.11 Camera: 2 - Resolution: 4K - Samples Per Pixel: 32 - Renderer: Path Tracer CentOS Stream 9 Clear Linux 36990 9K 18K 27K 36K 45K SE +/- 38.89, N = 3 SE +/- 84.10, N = 3 40852 40932 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake -mrelax-cmpxchg-loop -lm 1. (CXX) g++ options: -O3 -ldl
ONNX Runtime Model: GPT-2 - Device: CPU - Executor: Parallel OpenBenchmarking.org Inferences Per Minute, More Is Better ONNX Runtime 1.11 Model: GPT-2 - Device: CPU - Executor: Parallel CentOS Stream 9 Clear Linux 36990 1100 2200 3300 4400 5500 SE +/- 32.87, N = 3 SE +/- 26.07, N = 3 5269 5259 -flto -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake -mrelax-cmpxchg-loop -flto=auto 1. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -fno-fat-lto-objects -ldl -lrt
OSPRay Studio Camera: 1 - Resolution: 4K - Samples Per Pixel: 32 - Renderer: Path Tracer OpenBenchmarking.org ms, Fewer Is Better OSPRay Studio 0.11 Camera: 1 - Resolution: 4K - Samples Per Pixel: 32 - Renderer: Path Tracer Clear Linux 36990 CentOS Stream 9 9K 18K 27K 36K 45K SE +/- 180.17, N = 3 SE +/- 74.23, N = 3 40503 40580 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake -mrelax-cmpxchg-loop -lm 1. (CXX) g++ options: -O3 -ldl
OSPRay Studio Camera: 1 - Resolution: 4K - Samples Per Pixel: 16 - Renderer: Path Tracer OpenBenchmarking.org ms, Fewer Is Better OSPRay Studio 0.11 Camera: 1 - Resolution: 4K - Samples Per Pixel: 16 - Renderer: Path Tracer CentOS Stream 9 Clear Linux 36990 4K 8K 12K 16K 20K SE +/- 58.89, N = 3 SE +/- 13.09, N = 3 20152 20180 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake -mrelax-cmpxchg-loop -lm 1. (CXX) g++ options: -O3 -ldl
GraphicsMagick Operation: Rotate OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.38 Operation: Rotate CentOS Stream 9 Clear Linux 36990 200 400 600 800 1000 SE +/- 7.69, N = 15 SE +/- 10.17, N = 3 1030 1029 -O2 -O3 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake -mrelax-cmpxchg-loop -ltiff -lfreetype -lSM -lICE -lxml2 1. (CC) gcc options: -fopenmp -ljpeg -lXext -lX11 -lbz2 -lz -lm -lpthread
Stress-NG Test: IO_uring OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14 Test: IO_uring Clear Linux 36990 2M 4M 6M 8M 10M SE +/- 6299.40, N = 3 10692920.63 1. (CC) gcc options: -O3 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake -mrelax-cmpxchg-loop -O2 -std=gnu99 -lm -laio -latomic -lc -lcrypt -ldl -ljpeg -lrt -lz -pthread
Dragonflydb Clients: 50 - Set To Get Ratio: 5:1 OpenBenchmarking.org Ops/sec, More Is Better Dragonflydb 0.6 Clients: 50 - Set To Get Ratio: 5:1 Clear Linux 36990 800K 1600K 2400K 3200K 4000K SE +/- 16274.57, N = 3 3826220.78 1. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre
Dragonflydb Clients: 50 - Set To Get Ratio: 1:5 OpenBenchmarking.org Ops/sec, More Is Better Dragonflydb 0.6 Clients: 50 - Set To Get Ratio: 1:5 Clear Linux 36990 900K 1800K 2700K 3600K 4500K SE +/- 12346.26, N = 3 4236085.83 1. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre
Dragonflydb Clients: 50 - Set To Get Ratio: 1:1 OpenBenchmarking.org Ops/sec, More Is Better Dragonflydb 0.6 Clients: 50 - Set To Get Ratio: 1:1 Clear Linux 36990 900K 1800K 2700K 3600K 4500K SE +/- 10042.07, N = 3 4003419.31 1. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre
Apache Spark Row Count: 40000000 - Partitions: 500 - Broadcast Inner Join Test Time OpenBenchmarking.org Seconds, Fewer Is Better Apache Spark 3.3 Row Count: 40000000 - Partitions: 500 - Broadcast Inner Join Test Time Clear Linux 36990 4 8 12 16 20 SE +/- 0.83, N = 2 15.17
Apache Spark Row Count: 40000000 - Partitions: 500 - Inner Join Test Time OpenBenchmarking.org Seconds, Fewer Is Better Apache Spark 3.3 Row Count: 40000000 - Partitions: 500 - Inner Join Test Time Clear Linux 36990 4 8 12 16 20 SE +/- 0.23, N = 2 15.59
Apache Spark Row Count: 40000000 - Partitions: 500 - Repartition Test Time OpenBenchmarking.org Seconds, Fewer Is Better Apache Spark 3.3 Row Count: 40000000 - Partitions: 500 - Repartition Test Time Clear Linux 36990 3 6 9 12 15 SE +/- 0.21, N = 2 13.07
Apache Spark Row Count: 40000000 - Partitions: 500 - Group By Test Time OpenBenchmarking.org Seconds, Fewer Is Better Apache Spark 3.3 Row Count: 40000000 - Partitions: 500 - Group By Test Time Clear Linux 36990 8 16 24 32 40 SE +/- 5.10, N = 2 34.45
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 CentOS Stream 9 140K 280K 420K 560K 700K SE +/- 2481.53, N = 3 666008.7
PyHPC Benchmarks Device: CPU - Backend: TensorFlow - Project Size: 4194304 - Benchmark: Equation of State OpenBenchmarking.org Seconds, Fewer Is Better PyHPC Benchmarks 3.0 Device: CPU - Backend: TensorFlow - Project Size: 4194304 - Benchmark: Equation of State CentOS Stream 9 0.05 0.1 0.15 0.2 0.25 SE +/- 0.003, N = 4 0.222
PyHPC Benchmarks Device: CPU - Backend: PyTorch - Project Size: 4194304 - Benchmark: Isoneutral Mixing OpenBenchmarking.org Seconds, Fewer Is Better PyHPC Benchmarks 3.0 Device: CPU - Backend: PyTorch - Project Size: 4194304 - Benchmark: Isoneutral Mixing CentOS Stream 9 0.4635 0.927 1.3905 1.854 2.3175 SE +/- 0.004, N = 3 2.060
PyHPC Benchmarks Device: CPU - Backend: PyTorch - Project Size: 4194304 - Benchmark: Equation of State OpenBenchmarking.org Seconds, Fewer Is Better PyHPC Benchmarks 3.0 Device: CPU - Backend: PyTorch - Project Size: 4194304 - Benchmark: Equation of State CentOS Stream 9 0.0245 0.049 0.0735 0.098 0.1225 SE +/- 0.001, N = 3 0.109
PyHPC Benchmarks Device: CPU - Backend: Aesara - Project Size: 4194304 - Benchmark: Isoneutral Mixing OpenBenchmarking.org Seconds, Fewer Is Better PyHPC Benchmarks 3.0 Device: CPU - Backend: Aesara - Project Size: 4194304 - Benchmark: Isoneutral Mixing CentOS Stream 9 0.4676 0.9352 1.4028 1.8704 2.338 SE +/- 0.024, N = 3 2.078
PyHPC Benchmarks Device: CPU - Backend: Aesara - Project Size: 4194304 - Benchmark: Equation of State OpenBenchmarking.org Seconds, Fewer Is Better PyHPC Benchmarks 3.0 Device: CPU - Backend: Aesara - Project Size: 4194304 - Benchmark: Equation of State CentOS Stream 9 0.0682 0.1364 0.2046 0.2728 0.341 SE +/- 0.001, N = 3 0.303
PyHPC Benchmarks Device: CPU - Backend: Numba - Project Size: 4194304 - Benchmark: Isoneutral Mixing OpenBenchmarking.org Seconds, Fewer Is Better PyHPC Benchmarks 3.0 Device: CPU - Backend: Numba - Project Size: 4194304 - Benchmark: Isoneutral Mixing CentOS Stream 9 0.3094 0.6188 0.9282 1.2376 1.547 SE +/- 0.001, N = 3 1.375
PyHPC Benchmarks Device: CPU - Backend: Numba - Project Size: 4194304 - Benchmark: Equation of State OpenBenchmarking.org Seconds, Fewer Is Better PyHPC Benchmarks 3.0 Device: CPU - Backend: Numba - Project Size: 4194304 - Benchmark: Equation of State CentOS Stream 9 0.0594 0.1188 0.1782 0.2376 0.297 SE +/- 0.002, N = 3 0.264
PyHPC Benchmarks Device: CPU - Backend: JAX - Project Size: 4194304 - Benchmark: Isoneutral Mixing OpenBenchmarking.org Seconds, Fewer Is Better PyHPC Benchmarks 3.0 Device: CPU - Backend: JAX - Project Size: 4194304 - Benchmark: Isoneutral Mixing CentOS Stream 9 0.1944 0.3888 0.5832 0.7776 0.972 SE +/- 0.004, N = 3 0.864
PyHPC Benchmarks Device: CPU - Backend: JAX - Project Size: 4194304 - Benchmark: Equation of State OpenBenchmarking.org Seconds, Fewer Is Better PyHPC Benchmarks 3.0 Device: CPU - Backend: JAX - Project Size: 4194304 - Benchmark: Equation of State CentOS Stream 9 0.007 0.014 0.021 0.028 0.035 SE +/- 0.000, N = 3 0.031
OpenVINO Model: Age Gender Recognition Retail 0013 FP16 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2022.2.dev Model: Age Gender Recognition Retail 0013 FP16 - Device: CPU CentOS Stream 9 0.306 0.612 0.918 1.224 1.53 SE +/- 0.00, N = 3 1.36 MIN: 0.99 / MAX: 13.44 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
OpenVINO Model: Age Gender Recognition Retail 0013 FP16 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2022.2.dev Model: Age Gender Recognition Retail 0013 FP16 - Device: CPU CentOS Stream 9 10K 20K 30K 40K 50K SE +/- 99.47, N = 3 47224.77 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
OpenVINO Model: Weld Porosity Detection FP16-INT8 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2022.2.dev Model: Weld Porosity Detection FP16-INT8 - Device: CPU CentOS Stream 9 2 4 6 8 10 SE +/- 0.01, N = 3 8.27 MIN: 7.23 / MAX: 27.1 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
OpenVINO Model: Weld Porosity Detection FP16-INT8 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2022.2.dev Model: Weld Porosity Detection FP16-INT8 - Device: CPU CentOS Stream 9 2K 4K 6K 8K 10K SE +/- 8.29, N = 3 9657.99 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
OpenVINO Model: Machine Translation EN To DE FP16 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2022.2.dev Model: Machine Translation EN To DE FP16 - Device: CPU CentOS Stream 9 20 40 60 80 100 SE +/- 0.18, N = 3 85.47 MIN: 76.11 / MAX: 195.12 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
OpenVINO Model: Machine Translation EN To DE FP16 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2022.2.dev Model: Machine Translation EN To DE FP16 - Device: CPU CentOS Stream 9 50 100 150 200 250 SE +/- 0.51, N = 3 233.33 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
OpenVINO Model: Weld Porosity Detection FP16 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2022.2.dev Model: Weld Porosity Detection FP16 - Device: CPU CentOS Stream 9 7 14 21 28 35 SE +/- 0.01, N = 3 32.00 MIN: 21.78 / MAX: 67.35 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
OpenVINO Model: Weld Porosity Detection FP16 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2022.2.dev Model: Weld Porosity Detection FP16 - Device: CPU CentOS Stream 9 500 1000 1500 2000 2500 SE +/- 1.20, N = 3 2478.96 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
OpenVINO Model: Vehicle Detection FP16-INT8 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2022.2.dev Model: Vehicle Detection FP16-INT8 - Device: CPU CentOS Stream 9 1.017 2.034 3.051 4.068 5.085 SE +/- 0.00, N = 3 4.52 MIN: 4.11 / MAX: 44.74 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
OpenVINO Model: Vehicle Detection FP16-INT8 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2022.2.dev Model: Vehicle Detection FP16-INT8 - Device: CPU CentOS Stream 9 900 1800 2700 3600 4500 SE +/- 1.33, N = 3 4414.94 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
OpenVINO Model: Face Detection FP16-INT8 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2022.2.dev Model: Face Detection FP16-INT8 - Device: CPU CentOS Stream 9 50 100 150 200 250 SE +/- 0.22, N = 3 239.86 MIN: 178.86 / MAX: 348.97 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
OpenVINO Model: Face Detection FP16-INT8 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2022.2.dev Model: Face Detection FP16-INT8 - Device: CPU CentOS Stream 9 20 40 60 80 100 SE +/- 0.07, N = 3 83.26 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
OpenVINO Model: Vehicle Detection FP16 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2022.2.dev Model: Vehicle Detection FP16 - Device: CPU CentOS Stream 9 5 10 15 20 25 SE +/- 0.29, N = 12 18.67 MIN: 11.54 / MAX: 79.43 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
OpenVINO Model: Vehicle Detection FP16 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2022.2.dev Model: Vehicle Detection FP16 - Device: CPU CentOS Stream 9 200 400 600 800 1000 SE +/- 14.44, N = 12 1071.70 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
OpenVINO Model: Person Detection FP32 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2022.2.dev Model: Person Detection FP32 - Device: CPU CentOS Stream 9 300 600 900 1200 1500 SE +/- 1.03, N = 3 1451.62 MIN: 1039.96 / MAX: 1708.95 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
OpenVINO Model: Person Detection FP32 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2022.2.dev Model: Person Detection FP32 - Device: CPU CentOS Stream 9 4 8 12 16 20 SE +/- 0.02, N = 3 13.67 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
OpenVINO Model: Person Detection FP16 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2022.2.dev Model: Person Detection FP16 - Device: CPU CentOS Stream 9 300 600 900 1200 1500 SE +/- 0.41, N = 3 1424.57 MIN: 1046.08 / MAX: 1657.29 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
OpenVINO Model: Person Detection FP16 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2022.2.dev Model: Person Detection FP16 - Device: CPU CentOS Stream 9 4 8 12 16 20 SE +/- 0.00, N = 3 13.92 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
OpenVINO Model: Face Detection FP16 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2022.2.dev Model: Face Detection FP16 - Device: CPU CentOS Stream 9 200 400 600 800 1000 SE +/- 0.67, N = 3 819.63 MIN: 519.3 / MAX: 967.18 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
OpenVINO Model: Face Detection FP16 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2022.2.dev Model: Face Detection FP16 - Device: CPU CentOS Stream 9 6 12 18 24 30 SE +/- 0.02, N = 3 24.29 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
KeyDB OpenBenchmarking.org Ops/sec, More Is Better KeyDB 6.2.0 Clear Linux 36990 100K 200K 300K 400K 500K SE +/- 1855.84, N = 3 485587.54 1. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre
WebP2 Image Encode Encode Settings: Quality 95, Compression Effort 7 OpenBenchmarking.org Seconds, Fewer Is Better WebP2 Image Encode 20220422 Encode Settings: Quality 95, Compression Effort 7 CentOS Stream 9 50 100 150 200 250 SE +/- 0.09, N = 3 233.75 1. (CXX) g++ options: -fno-rtti -O3
WebP2 Image Encode Encode Settings: Quality 75, Compression Effort 7 OpenBenchmarking.org Seconds, Fewer Is Better WebP2 Image Encode 20220422 Encode Settings: Quality 75, Compression Effort 7 CentOS Stream 9 30 60 90 120 150 SE +/- 0.09, N = 3 111.92 1. (CXX) g++ options: -fno-rtti -O3
WebP2 Image Encode Encode Settings: Default OpenBenchmarking.org Seconds, Fewer Is Better WebP2 Image Encode 20220422 Encode Settings: Default CentOS Stream 9 0.6001 1.2002 1.8003 2.4004 3.0005 SE +/- 0.033, N = 15 2.667 1. (CXX) g++ options: -fno-rtti -O3
Timed Linux Kernel Compilation Build: defconfig OpenBenchmarking.org Seconds, Fewer Is Better Timed Linux Kernel Compilation 5.18 Build: defconfig CentOS Stream 9 7 14 21 28 35 SE +/- 0.39, N = 13 29.67
Timed GDB GNU Debugger Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed GDB GNU Debugger Compilation 10.2 Time To Compile CentOS Stream 9 20 40 60 80 100 SE +/- 0.27, N = 3 95.42
Zstd Compression Compression Level: 3, Long Mode - Decompression Speed OpenBenchmarking.org MB/s, More Is Better Zstd Compression Compression Level: 3, Long Mode - Decompression Speed CentOS Stream 9 700 1400 2100 2800 3500 SE +/- 13.60, N = 3 3208.0 1. *** zstd command line interface 64-bits v1.5.1, by Yann Collet ***
Renaissance Test: In-Memory Database Shootout OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.14 Test: In-Memory Database Shootout CentOS Stream 9 4K 8K 12K 16K 20K SE +/- 197.42, N = 3 17787.2 MIN: 17444.33 / MAX: 21383.13
DaCapo Benchmark Java Test: Tradebeans OpenBenchmarking.org msec, Fewer Is Better DaCapo Benchmark 9.12-MR1 Java Test: Tradebeans CentOS Stream 9 3K 6K 9K 12K 15K SE +/- 116.64, N = 4 16070
ONNX Runtime Model: super-resolution-10 - Device: CPU - Executor: Standard OpenBenchmarking.org Inferences Per Minute, More Is Better ONNX Runtime 1.11 Model: super-resolution-10 - Device: CPU - Executor: Standard CentOS Stream 9 Clear Linux 36990 3K 6K 9K 12K 15K SE +/- 43.63, N = 3 SE +/- 690.46, N = 12 12260 10151 -flto -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake -mrelax-cmpxchg-loop -flto=auto 1. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -fno-fat-lto-objects -ldl -lrt
ONNX Runtime Model: fcn-resnet101-11 - Device: CPU - Executor: Standard OpenBenchmarking.org Inferences Per Minute, More Is Better ONNX Runtime 1.11 Model: fcn-resnet101-11 - Device: CPU - Executor: Standard Clear Linux 36990 CentOS Stream 9 110 220 330 440 550 SE +/- 17.65, N = 12 SE +/- 1.17, N = 3 521 443 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake -mrelax-cmpxchg-loop -flto=auto -flto 1. (CXX) g++ options: -O3 -ffunction-sections -fdata-sections -march=native -mtune=native -fno-fat-lto-objects -ldl -lrt
ONNX Runtime Model: yolov4 - Device: CPU - Executor: Standard OpenBenchmarking.org Inferences Per Minute, More Is Better ONNX Runtime 1.11 Model: yolov4 - Device: CPU - Executor: Standard CentOS Stream 9 Clear Linux 36990 150 300 450 600 750 SE +/- 1.17, N = 3 SE +/- 12.00, N = 12 694 636 -flto -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake -mrelax-cmpxchg-loop -flto=auto 1. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -fno-fat-lto-objects -ldl -lrt
ONNX Runtime Model: GPT-2 - Device: CPU - Executor: Standard OpenBenchmarking.org Inferences Per Minute, More Is Better ONNX Runtime 1.11 Model: GPT-2 - Device: CPU - Executor: Standard CentOS Stream 9 Clear Linux 36990 2K 4K 6K 8K 10K SE +/- 388.59, N = 12 SE +/- 346.22, N = 9 11045 10211 -flto -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake -mrelax-cmpxchg-loop -flto=auto 1. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -fno-fat-lto-objects -ldl -lrt
OpenVINO Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2022.2.dev Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU CentOS Stream 9 0.3375 0.675 1.0125 1.35 1.6875 SE +/- 0.05, N = 15 1.50 MIN: 0.34 / MAX: 29.48 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
OpenVINO Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2022.2.dev Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU CentOS Stream 9 9K 18K 27K 36K 45K SE +/- 1567.95, N = 15 42731.93 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
OpenVINO Model: Person Vehicle Bike Detection FP16 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2022.2.dev Model: Person Vehicle Bike Detection FP16 - Device: CPU CentOS Stream 9 3 6 9 12 15 SE +/- 0.30, N = 15 13.60 MIN: 8.57 / MAX: 68.28 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
OpenVINO Model: Person Vehicle Bike Detection FP16 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2022.2.dev Model: Person Vehicle Bike Detection FP16 - Device: CPU CentOS Stream 9 300 600 900 1200 1500 SE +/- 39.85, N = 15 1478.64 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
Mobile Neural Network Model: mobilenet-v1-1.0 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 2.1 Model: mobilenet-v1-1.0 CentOS Stream 9 Clear Linux 36990 0.4903 0.9806 1.4709 1.9612 2.4515 SE +/- 0.047, N = 15 SE +/- 0.016, N = 3 2.090 2.179 MIN: 1.76 / MAX: 3.93 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake -mrelax-cmpxchg-loop - MIN: 2.08 / MAX: 2.41 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 2.1 Model: SqueezeNetV1.0 CentOS Stream 9 Clear Linux 36990 0.9549 1.9098 2.8647 3.8196 4.7745 SE +/- 0.075, N = 15 SE +/- 0.058, N = 3 3.956 4.244 MIN: 3.51 / MAX: 9.33 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake -mrelax-cmpxchg-loop - MIN: 3.95 / MAX: 8.29 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 2.1 Model: squeezenetv1.1 CentOS Stream 9 Clear Linux 36990 0.569 1.138 1.707 2.276 2.845 SE +/- 0.050, N = 15 SE +/- 0.014, N = 3 2.356 2.529 MIN: 2.03 / MAX: 5.76 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake -mrelax-cmpxchg-loop - MIN: 2.48 / MAX: 2.83 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: nasnet OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 2.1 Model: nasnet CentOS Stream 9 Clear Linux 36990 3 6 9 12 15 SE +/- 0.23, N = 15 SE +/- 0.09, N = 3 12.10 12.81 MIN: 10.54 / MAX: 23.03 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake -mrelax-cmpxchg-loop - MIN: 12.47 / MAX: 16.42 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: Socket Activity OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14 Test: Socket Activity Clear Linux 36990 CentOS Stream 9 8K 16K 24K 32K 40K SE +/- 324.72, N = 3 SE +/- 900.65, N = 15 36452.69 2460.37 -O3 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake -mrelax-cmpxchg-loop -laio -latomic 1. (CC) gcc options: -O2 -std=gnu99 -lm -lc -lcrypt -ldl -ljpeg -lrt -lz -pthread
Stress-NG Test: Atomic OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14 Test: Atomic CentOS Stream 9 Clear Linux 36990 40K 80K 120K 160K 200K SE +/- 3961.98, N = 15 SE +/- 3304.16, N = 15 187775.77 145035.86 -O3 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake -mrelax-cmpxchg-loop -laio -latomic 1. (CC) gcc options: -O2 -std=gnu99 -lm -lc -lcrypt -ldl -ljpeg -lrt -lz -pthread
Stress-NG Test: Futex OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14 Test: Futex Clear Linux 36990 CentOS Stream 9 200K 400K 600K 800K 1000K SE +/- 60890.67, N = 15 SE +/- 73263.26, N = 15 1140633.72 1088788.92 -O3 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake -mrelax-cmpxchg-loop -laio -latomic 1. (CC) gcc options: -O2 -std=gnu99 -lm -lc -lcrypt -ldl -ljpeg -lrt -lz -pthread
memtier_benchmark Protocol: Redis - Clients: 50 - Set To Get Ratio: 1:10 OpenBenchmarking.org Ops/sec, More Is Better memtier_benchmark 1.4 Protocol: Redis - Clients: 50 - Set To Get Ratio: 1:10 Clear Linux 36990 CentOS Stream 9 400K 800K 1200K 1600K 2000K SE +/- 83568.62, N = 13 SE +/- 67672.39, N = 12 1994991.48 1398073.70 1. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre
memtier_benchmark Protocol: Redis - Clients: 50 - Set To Get Ratio: 5:1 OpenBenchmarking.org Ops/sec, More Is Better memtier_benchmark 1.4 Protocol: Redis - Clients: 50 - Set To Get Ratio: 5:1 Clear Linux 36990 CentOS Stream 9 400K 800K 1200K 1600K 2000K SE +/- 66661.35, N = 12 SE +/- 63962.41, N = 12 1760873.07 1339297.91 1. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre
PostgreSQL pgbench Scaling Factor: 100 - Clients: 500 - Mode: Read Only - Average Latency OpenBenchmarking.org ms, Fewer Is Better PostgreSQL pgbench 14.0 Scaling Factor: 100 - Clients: 500 - Mode: Read Only - Average Latency CentOS Stream 9 Clear Linux 36990 0.0619 0.1238 0.1857 0.2476 0.3095 SE +/- 0.005, N = 12 SE +/- 0.007, N = 12 0.270 0.275 -O2 -O3 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake -mrelax-cmpxchg-loop 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -lpgcommon -lpgport -lpq -lm
PostgreSQL pgbench Scaling Factor: 100 - Clients: 500 - Mode: Read Only OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 14.0 Scaling Factor: 100 - Clients: 500 - Mode: Read Only CentOS Stream 9 Clear Linux 36990 400K 800K 1200K 1600K 2000K SE +/- 30425.21, N = 12 SE +/- 42947.24, N = 12 1855656 1831665 -O2 -O3 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake -mrelax-cmpxchg-loop 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -lpgcommon -lpgport -lpq -lm
PostgreSQL pgbench Scaling Factor: 100 - Clients: 250 - Mode: Read Only - Average Latency OpenBenchmarking.org ms, Fewer Is Better PostgreSQL pgbench 14.0 Scaling Factor: 100 - Clients: 250 - Mode: Read Only - Average Latency Clear Linux 36990 CentOS Stream 9 0.0338 0.0676 0.1014 0.1352 0.169 SE +/- 0.004, N = 12 SE +/- 0.001, N = 3 0.132 0.150 -O3 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake -mrelax-cmpxchg-loop -O2 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -lpgcommon -lpgport -lpq -lm
PostgreSQL pgbench Scaling Factor: 100 - Clients: 250 - Mode: Read Only OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 14.0 Scaling Factor: 100 - Clients: 250 - Mode: Read Only Clear Linux 36990 CentOS Stream 9 400K 800K 1200K 1600K 2000K SE +/- 57458.70, N = 12 SE +/- 9583.19, N = 3 1913115 1669388 -O3 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake -mrelax-cmpxchg-loop -O2 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -lpgcommon -lpgport -lpq -lm
TensorFlow Lite Model: Mobilenet Float OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2022-05-18 Model: Mobilenet Float Clear Linux 36990 CentOS Stream 9 900 1800 2700 3600 4500 SE +/- 75.96, N = 15 SE +/- 499.70, N = 12 3701.27 4240.41
TensorFlow Lite Model: NASNet Mobile OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2022-05-18 Model: NASNet Mobile Clear Linux 36990 CentOS Stream 9 15K 30K 45K 60K 75K SE +/- 935.16, N = 15 SE +/- 3728.57, N = 12 68566.7 68713.0
TensorFlow Lite Model: Inception V4 OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2022-05-18 Model: Inception V4 Clear Linux 36990 CentOS Stream 9 16K 32K 48K 64K 80K SE +/- 2536.95, N = 15 SE +/- 21727.22, N = 15 42370.3 73896.5
TensorFlow Lite Model: SqueezeNet OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2022-05-18 Model: SqueezeNet Clear Linux 36990 CentOS Stream 9 4K 8K 12K 16K 20K SE +/- 370.01, N = 12 SE +/- 5506.54, N = 12 6244.19 16614.41
Redis Test: SET - Parallel Connections: 1000 OpenBenchmarking.org Requests Per Second, More Is Better Redis 7.0.4 Test: SET - Parallel Connections: 1000 Clear Linux 36990 CentOS Stream 9 400K 800K 1200K 1600K 2000K SE +/- 21642.05, N = 5 SE +/- 55692.46, N = 12 2078925.13 1847194.12 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake -mrelax-cmpxchg-loop 1. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3
Redis Test: SET - Parallel Connections: 500 OpenBenchmarking.org Requests Per Second, More Is Better Redis 7.0.4 Test: SET - Parallel Connections: 500 Clear Linux 36990 CentOS Stream 9 400K 800K 1200K 1600K 2000K SE +/- 26407.67, N = 15 SE +/- 47157.16, N = 12 2083152.81 1931278.62 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake -mrelax-cmpxchg-loop 1. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3
Redis Test: GET - Parallel Connections: 500 OpenBenchmarking.org Requests Per Second, More Is Better Redis 7.0.4 Test: GET - Parallel Connections: 500 Clear Linux 36990 CentOS Stream 9 600K 1200K 1800K 2400K 3000K SE +/- 22655.99, N = 3 SE +/- 89203.76, N = 15 2765192.67 2018201.09 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake -mrelax-cmpxchg-loop 1. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3
Apache Spark Row Count: 40000000 - Partitions: 500 - Calculate Pi Benchmark Using Dataframe OpenBenchmarking.org Seconds, Fewer Is Better Apache Spark 3.3 Row Count: 40000000 - Partitions: 500 - Calculate Pi Benchmark Using Dataframe Clear Linux 36990 CentOS Stream 9 0.6278 1.2556 1.8834 2.5112 3.139 SE +/- 0.04, N = 15 SE +/- 0.09, N = 3 2.04 2.79
oneDNN Harness: Matrix Multiply Batch Shapes Transformer - Data Type: bf16bf16bf16 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.6 Harness: Matrix Multiply Batch Shapes Transformer - Data Type: bf16bf16bf16 - Engine: CPU Clear Linux 36990 CentOS Stream 9 9 18 27 36 45 SE +/- 0.41, N = 12 SE +/- 5.68, N = 15 12.27 37.96 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake -mrelax-cmpxchg-loop - MIN: 9.86 MIN: 3.48 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl -lpthread
oneDNN Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.6 Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPU CentOS Stream 9 Clear Linux 36990 110 220 330 440 550 SE +/- 7.22, N = 15 SE +/- 4.67, N = 15 447.62 487.12 MIN: 376.51 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake -mrelax-cmpxchg-loop - MIN: 431.07 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl -lpthread
oneDNN Harness: IP Shapes 3D - Data Type: bf16bf16bf16 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.6 Harness: IP Shapes 3D - Data Type: bf16bf16bf16 - Engine: CPU Clear Linux 36990 CentOS Stream 9 0.5368 1.0736 1.6104 2.1472 2.684 SE +/- 0.02882, N = 15 SE +/- 0.07640, N = 15 2.30251 2.38563 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake -mrelax-cmpxchg-loop - MIN: 1.76 MIN: 1.7 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl -lpthread
oneDNN Harness: IP Shapes 1D - Data Type: bf16bf16bf16 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.6 Harness: IP Shapes 1D - Data Type: bf16bf16bf16 - Engine: CPU Clear Linux 36990 CentOS Stream 9 1.2164 2.4328 3.6492 4.8656 6.082 SE +/- 0.07618, N = 15 SE +/- 0.32475, N = 15 4.64086 5.40603 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake -mrelax-cmpxchg-loop - MIN: 3.55 MIN: 3.28 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl -lpthread
Stockfish Total Time OpenBenchmarking.org Nodes Per Second, More Is Better Stockfish 15 Total Time Clear Linux 36990 CentOS Stream 9 40M 80M 120M 160M 200M SE +/- 3123886.35, N = 15 SE +/- 2364357.21, N = 15 186079628 179473129 -pipe -fexceptions -ffat-lto-objects -fno-trapping-math -mtune=skylake -mrelax-cmpxchg-loop 1. (CXX) g++ options: -lgcov -m64 -lpthread -O3 -fno-exceptions -std=c++17 -pedantic -msse -msse3 -mpopcnt -mavx2 -mavx512f -mavx512bw -mavx512vnni -mavx512dq -mavx512vl -msse4.1 -mssse3 -msse2 -mbmi2 -flto -fno-peel-loops -fno-tracer -flto=jobserver
GraphicsMagick Operation: HWB Color Space OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.38 Operation: HWB Color Space Clear Linux 36990 CentOS Stream 9 400 800 1200 1600 2000 SE +/- 4.16, N = 3 SE +/- 28.49, N = 12 1737 1138 -O3 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake -mrelax-cmpxchg-loop -ltiff -lfreetype -lSM -lICE -lxml2 -O2 1. (CC) gcc options: -fopenmp -ljpeg -lXext -lX11 -lbz2 -lz -lm -lpthread
Renaissance Test: Finagle HTTP Requests OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.14 Test: Finagle HTTP Requests Clear Linux 36990 CentOS Stream 9 2K 4K 6K 8K 10K SE +/- 56.01, N = 3 SE +/- 154.17, N = 12 5950.5 8693.9 MIN: 5353.91 / MAX: 6140.39 MIN: 6648.05 / MAX: 15659.82
DaCapo Benchmark Java Test: Jython OpenBenchmarking.org msec, Fewer Is Better DaCapo Benchmark 9.12-MR1 Java Test: Jython Clear Linux 36990 CentOS Stream 9 1200 2400 3600 4800 6000 SE +/- 7.13, N = 4 SE +/- 189.31, N = 16 3683 5600
WebP Image Encode Encode Settings: Quality 100 OpenBenchmarking.org Encode Time - Seconds, Fewer Is Better WebP Image Encode 1.1 Encode Settings: Quality 100 Clear Linux 36990 CentOS Stream 9 0.6849 1.3698 2.0547 2.7396 3.4245 SE +/- 0.002, N = 3 SE +/- 0.065, N = 15 2.656 3.044 -O3 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake -mrelax-cmpxchg-loop -ltiff -O2 1. (CC) gcc options: -fvisibility=hidden -lm -ljpeg -lpng16
WebP Image Encode Encode Settings: Default OpenBenchmarking.org Encode Time - Seconds, Fewer Is Better WebP Image Encode 1.1 Encode Settings: Default Clear Linux 36990 CentOS Stream 9 0.4867 0.9734 1.4601 1.9468 2.4335 SE +/- 0.003, N = 3 SE +/- 0.069, N = 15 1.662 2.163 -O3 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake -mrelax-cmpxchg-loop -ltiff -O2 1. (CC) gcc options: -fvisibility=hidden -lm -ljpeg -lpng16
Phoronix Test Suite v10.8.4