12400 march Intel Core i5-12400 testing with a MSI PRO Z690-A WIFI DDR4(MS-7D25) v1.0 (Dasharo coreboot+UEFI v1.0.0 BIOS) and MSI Intel ADL-S GT1 14GB on Ubuntu 22.04 via the Phoronix Test Suite.
HTML result view exported from: https://openbenchmarking.org/result/2303066-NE-12400MARC37&grs .
12400 march Processor Motherboard Chipset Memory Disk Graphics Audio Monitor Network OS Kernel Desktop Display Server OpenGL Vulkan Compiler File-System Screen Resolution a b c Intel Core i5-12400 @ 5.60GHz (6 Cores / 12 Threads) MSI PRO Z690-A WIFI DDR4(MS-7D25) v1.0 (Dasharo coreboot+UEFI v1.0.0 BIOS) Intel Device 7aa7 16GB Western Digital WD_BLACK SN750 SE 500GB MSI Intel ADL-S GT1 14GB (1450MHz) Realtek ALC897 DELL S2409W Intel I225-V + Intel Device 7af0 Ubuntu 22.04 5.15.0-47-generic (x86_64) GNOME Shell 42.2 X Server + Wayland 4.6 Mesa 22.0.1 1.2.204 GCC 11.2.0 ext4 1920x1080 GCC 11.3.0 OpenBenchmarking.org Kernel Details - Transparent Huge Pages: madvise Compiler Details - a: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-11-gBFGDP/gcc-11-11.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-gBFGDP/gcc-11-11.2.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v - b: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-11-xKiWfi/gcc-11-11.3.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-xKiWfi/gcc-11-11.3.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v - c: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-11-xKiWfi/gcc-11-11.3.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-xKiWfi/gcc-11-11.3.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v Processor Details - Scaling Governor: intel_pstate powersave (EPP: balance_performance) - CPU Microcode: 0x1f - Thermald 2.4.9 Python Details - Python 3.10.6 Security Details - itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced IBRS IBPB: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected
12400 march rocksdb: Rand Fill Sync pgbench: 100 - 800 - Read Write - Average Latency pgbench: 100 - 800 - Read Write onednn: Recurrent Neural Network Inference - bf16bf16bf16 - CPU svt-av1: Preset 12 - Bosphorus 4K pgbench: 100 - 1000 - Read Write pgbench: 100 - 1000 - Read Write - Average Latency deepsparse: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Asynchronous Multi-Stream deepsparse: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Asynchronous Multi-Stream deepsparse: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Synchronous Single-Stream deepsparse: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Synchronous Single-Stream openvino: Vehicle Detection FP16 - CPU openvino: Vehicle Detection FP16 - CPU encode-flac: WAV To FLAC encodec: 1.5 kbps vpxenc: Speed 0 - Bosphorus 1080p cockroach: MoVR - 128 keydb: SET - 100 keydb: GET - 100 deepsparse: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Asynchronous Multi-Stream deepsparse: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Asynchronous Multi-Stream onednn: Deconvolution Batch shapes_1d - u8s8f32 - CPU aom-av1: Speed 0 Two-Pass - Bosphorus 1080p cpuminer-opt: Blake-2 S cpuminer-opt: x25x encodec: 6 kbps cpuminer-opt: LBC, LBRY Credits aom-av1: Speed 0 Two-Pass - Bosphorus 4K encodec: 3 kbps ffmpeg: libx264 - Video On Demand ffmpeg: libx264 - Video On Demand rocksdb: Update Rand vpxenc: Speed 5 - Bosphorus 4K keydb: LPUSH - 50 stress-ng: Glibc C String Functions pgbench: 1 - 1000 - Read Write - Average Latency deepsparse: CV Classification, ResNet-50 ImageNet - Asynchronous Multi-Stream deepsparse: CV Classification, ResNet-50 ImageNet - Asynchronous Multi-Stream deepsparse: NLP Text Classification, DistilBERT mnli - Synchronous Single-Stream deepsparse: NLP Text Classification, DistilBERT mnli - Synchronous Single-Stream pgbench: 1 - 1000 - Read Write keydb: HMSET - 100 keydb: SADD - 100 pgbench: 1 - 500 - Read Only - Average Latency pgbench: 1 - 500 - Read Only kvazaar: Bosphorus 4K - Very Fast clickhouse: 100M Rows Hits Dataset, Third Run cockroach: MoVR - 256 kvazaar: Bosphorus 4K - Ultra Fast pgbench: 1 - 800 - Read Write - Average Latency pgbench: 1 - 800 - Read Write keydb: LPUSH - 100 pgbench: 100 - 800 - Read Only - Average Latency pgbench: 100 - 800 - Read Only pgbench: 1 - 500 - Read Write - Average Latency pgbench: 100 - 250 - Read Only pgbench: 100 - 250 - Read Only - Average Latency onednn: IP Shapes 1D - f32 - CPU jpegxl-decode: All minibude: OpenMP - BM1 encodec: 24 kbps minibude: OpenMP - BM1 pgbench: 1 - 500 - Read Write pgbench: 1 - 800 - Read Only - Average Latency pgbench: 1 - 800 - Read Only cpuminer-opt: Garlicoin clickhouse: 100M Rows Hits Dataset, Second Run pgbench: 100 - 1000 - Read Only deepsparse: NLP Text Classification, BERT base uncased SST2 - Synchronous Single-Stream deepsparse: NLP Text Classification, BERT base uncased SST2 - Synchronous Single-Stream uvg266: Bosphorus 1080p - Medium pgbench: 100 - 1000 - Read Only - Average Latency uvg266: Bosphorus 1080p - Slow cockroach: KV, 10% Reads - 512 rocksdb: Rand Read build-ffmpeg: Time To Compile vvenc: Bosphorus 4K - Faster deepsparse: NLP Text Classification, BERT base uncased SST2 - Asynchronous Multi-Stream cockroach: KV, 60% Reads - 128 vvenc: Bosphorus 1080p - Faster deepsparse: NLP Text Classification, BERT base uncased SST2 - Asynchronous Multi-Stream rocksdb: Seq Fill pgbench: 1 - 100 - Read Write - Average Latency stress-ng: Forking pgbench: 1 - 100 - Read Write svt-av1: Preset 4 - Bosphorus 4K pgbench: 1 - 100 - Read Only kvazaar: Bosphorus 4K - Super Fast pgbench: 1 - 100 - Read Only - Average Latency deepsparse: NLP Text Classification, DistilBERT mnli - Asynchronous Multi-Stream pgbench: 1 - 250 - Read Write - Average Latency pgbench: 1 - 250 - Read Write cockroach: KV, 50% Reads - 128 deepsparse: NLP Text Classification, DistilBERT mnli - Asynchronous Multi-Stream ffmpeg: libx265 - Video On Demand ffmpeg: libx265 - Video On Demand uvg266: Bosphorus 4K - Ultra Fast uvg266: Bosphorus 1080p - Very Fast nekrs: TurboPipe Periodic onednn: IP Shapes 3D - u8s8f32 - CPU kvazaar: Bosphorus 4K - Slow cockroach: KV, 95% Reads - 128 stress-ng: Pthread embree: Pathtracer - Crown deepsparse: CV Detection, YOLOv5s COCO - Asynchronous Multi-Stream deepsparse: CV Detection, YOLOv5s COCO - Asynchronous Multi-Stream uvg266: Bosphorus 4K - Slow ffmpeg: libx264 - Live cockroach: KV, 50% Reads - 256 openvino: Person Detection FP16 - CPU ffmpeg: libx264 - Live aom-av1: Speed 6 Two-Pass - Bosphorus 1080p openvino: Face Detection FP16-INT8 - CPU compress-zstd: 19 - Compression Speed uvg266: Bosphorus 4K - Very Fast keydb: HMSET - 50 deepsparse: NLP Document Classification, oBERT base uncased on IMDB - Asynchronous Multi-Stream uvg266: Bosphorus 4K - Super Fast openvino: Age Gender Recognition Retail 0013 FP16 - CPU kvazaar: Bosphorus 1080p - Slow pgbench: 1 - 250 - Read Only - Average Latency nginx: 20 onednn: Recurrent Neural Network Training - f32 - CPU pgbench: 1 - 250 - Read Only jpegxl: JPEG - 90 embree: Pathtracer ISPC - Crown deepsparse: NLP Document Classification, oBERT base uncased on IMDB - Asynchronous Multi-Stream openvino: Face Detection FP16-INT8 - CPU jpegxl: PNG - 80 avifenc: 2 cockroach: KV, 60% Reads - 256 deepsparse: NLP Token Classification, BERT base uncased conll2003 - Asynchronous Multi-Stream jpegxl: JPEG - 80 cockroach: MoVR - 512 avifenc: 6, Lossless aom-av1: Speed 4 Two-Pass - Bosphorus 4K openvino: Age Gender Recognition Retail 0013 FP16 - CPU jpegxl: PNG - 90 cockroach: KV, 60% Reads - 1024 pgbench: 1 - 1000 - Read Only pgbench: 1 - 1000 - Read Only - Average Latency onednn: IP Shapes 3D - f32 - CPU deepsparse: NLP Token Classification, BERT base uncased conll2003 - Asynchronous Multi-Stream xmrig: Monero - 1M tensorflow: CPU - 16 - GoogLeNet clickhouse: 100M Rows Hits Dataset, First Run / Cold Cache cpuminer-opt: Ringcoin cpuminer-opt: Skeincoin vvenc: Bosphorus 4K - Fast kvazaar: Bosphorus 4K - Medium onednn: Matrix Multiply Batch Shapes Transformer - u8s8f32 - CPU cockroach: KV, 60% Reads - 512 onednn: Recurrent Neural Network Inference - f32 - CPU pgbench: 100 - 100 - Read Only - Average Latency openvino: Machine Translation EN To DE FP16 - CPU svt-av1: Preset 13 - Bosphorus 4K cockroach: KV, 10% Reads - 128 jpegxl-decode: 1 pgbench: 100 - 100 - Read Only ffmpeg: libx265 - Live build-linux-kernel: allmodconfig openvino: Machine Translation EN To DE FP16 - CPU ffmpeg: libx265 - Live cockroach: KV, 95% Reads - 256 onednn: Recurrent Neural Network Training - bf16bf16bf16 - CPU cpuminer-opt: Magi openvkl: vklBenchmark Scalar jpegxl: JPEG - 100 jpegxl: PNG - 100 openradioss: Rubber O-Ring Seal Installation deepsparse: CV Detection, YOLOv5s COCO - Synchronous Single-Stream rocksdb: Read Rand Write Rand cockroach: KV, 10% Reads - 256 vvenc: Bosphorus 1080p - Fast compress-zstd: 3 - Compression Speed cpuminer-opt: Myriad-Groestl uvg266: Bosphorus 4K - Medium vpxenc: Speed 5 - Bosphorus 1080p deepsparse: CV Detection, YOLOv5s COCO - Synchronous Single-Stream stress-ng: Glibc Qsort Data Sorting openvino: Person Detection FP32 - CPU deepsparse: CV Classification, ResNet-50 ImageNet - Synchronous Single-Stream deepsparse: CV Classification, ResNet-50 ImageNet - Synchronous Single-Stream svt-av1: Preset 8 - Bosphorus 4K kvazaar: Bosphorus 1080p - Ultra Fast nginx: 100 onednn: Recurrent Neural Network Training - u8s8f32 - CPU stargate: 480000 - 512 blender: BMW27 - CPU-Only deepsparse: NLP Document Classification, oBERT base uncased on IMDB - Synchronous Single-Stream deepsparse: NLP Document Classification, oBERT base uncased on IMDB - Synchronous Single-Stream openvino: Person Detection FP16 - CPU openvino: Face Detection FP16 - CPU avifenc: 6 stargate: 96000 - 1024 aom-av1: Speed 6 Two-Pass - Bosphorus 4K openvino: Weld Porosity Detection FP16-INT8 - CPU openvino: Weld Porosity Detection FP16 - CPU openvino: Weld Porosity Detection FP16 - CPU openvino: Age Gender Recognition Retail 0013 FP16-INT8 - CPU deepsparse: CV Segmentation, 90% Pruned YOLACT Pruned - Synchronous Single-Stream deepsparse: CV Segmentation, 90% Pruned YOLACT Pruned - Synchronous Single-Stream aom-av1: Speed 8 Realtime - Bosphorus 1080p openvino: Weld Porosity Detection FP16-INT8 - CPU compress-zstd: 8, Long Mode - Compression Speed cockroach: KV, 50% Reads - 512 stress-ng: NUMA openradioss: INIVOL and Fluid Structure Interaction Drop Container stargate: 480000 - 1024 build-linux-kernel: defconfig onednn: Convolution Batch Shapes Auto - u8s8f32 - CPU cpuminer-opt: Deepcoin svt-av1: Preset 4 - Bosphorus 1080p embree: Pathtracer - Asian Dragon rocksdb: Read While Writing nginx: 200 openvino: Person Vehicle Bike Detection FP16 - CPU openvino: Person Vehicle Bike Detection FP16 - CPU tensorflow: CPU - 16 - AlexNet openvino: Person Detection FP32 - CPU ffmpeg: libx264 - Platform compress-zstd: 19, Long Mode - Compression Speed ffmpeg: libx264 - Platform tensorflow: CPU - 256 - AlexNet nginx: 1000 stargate: 192000 - 1024 openvkl: vklBenchmark ISPC aom-av1: Speed 9 Realtime - Bosphorus 4K stress-ng: Malloc openvino: Face Detection FP16 - CPU scikit-learn: TSNE MNIST Dataset scikit-learn: MNIST Dataset embree: Pathtracer ISPC - Asian Dragon uvg266: Bosphorus 1080p - Ultra Fast avifenc: 0 minibude: OpenMP - BM2 minibude: OpenMP - BM2 cockroach: MoVR - 1024 onednn: Recurrent Neural Network Inference - u8s8f32 - CPU aom-av1: Speed 6 Realtime - Bosphorus 4K aom-av1: Speed 8 Realtime - Bosphorus 4K cpuminer-opt: scrypt tensorflow: CPU - 64 - AlexNet stress-ng: Memory Copying vpxenc: Speed 0 - Bosphorus 4K brl-cad: VGR Performance Metric tensorflow: CPU - 32 - AlexNet stargate: 44100 - 1024 stargate: 96000 - 512 openradioss: Bird Strike on Windshield stress-ng: SENDFILE openradioss: Cell Phone Drop Test openvino: Vehicle Detection FP16-INT8 - CPU embree: Pathtracer ISPC - Asian Dragon Obj ffmpeg: libx265 - Upload tensorflow: CPU - 64 - GoogLeNet ffmpeg: libx265 - Upload openvino: Vehicle Detection FP16-INT8 - CPU deepsparse: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Synchronous Single-Stream deepsparse: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Synchronous Single-Stream tensorflow: CPU - 32 - GoogLeNet openems: pyEMS Coupler cockroach: KV, 10% Reads - 1024 onednn: Deconvolution Batch shapes_3d - u8s8f32 - CPU uvg266: Bosphorus 1080p - Super Fast svt-av1: Preset 8 - Bosphorus 1080p tensorflow: CPU - 256 - GoogLeNet xmrig: Wownero - 1M deepsparse: CV Segmentation, 90% Pruned YOLACT Pruned - Asynchronous Multi-Stream deepsparse: CV Segmentation, 90% Pruned YOLACT Pruned - Asynchronous Multi-Stream tensorflow: CPU - 512 - AlexNet deepsparse: NLP Token Classification, BERT base uncased conll2003 - Synchronous Single-Stream deepsparse: NLP Token Classification, BERT base uncased conll2003 - Synchronous Single-Stream ffmpeg: libx264 - Upload pgbench: 100 - 500 - Read Only - Average Latency compress-zstd: 19, Long Mode - Decompression Speed pgbench: 100 - 500 - Read Only ffmpeg: libx264 - Upload compress-zstd: 8 - Compression Speed svt-av1: Preset 12 - Bosphorus 1080p stress-ng: Mutex svt-av1: Preset 13 - Bosphorus 1080p blender: Pabellon Barcelona - CPU-Only openvino: Age Gender Recognition Retail 0013 FP16-INT8 - CPU kvazaar: Bosphorus 1080p - Very Fast stargate: 192000 - 512 stress-ng: System V Message Passing aom-av1: Speed 10 Realtime - Bosphorus 4K blender: Barbershop - CPU-Only ffmpeg: libx265 - Platform ffmpeg: libx265 - Platform onednn: Matrix Multiply Batch Shapes Transformer - f32 - CPU compress-zstd: 3, Long Mode - Compression Speed compress-zstd: 3 - Decompression Speed nginx: 500 gromacs: MPI CPU - water_GMX50_bare stress-ng: Matrix Math stargate: 44100 - 512 openradioss: Bumper Beam cockroach: KV, 95% Reads - 512 cpuminer-opt: Triple SHA-256, Onecoin blender: Classroom - CPU-Only compress-zstd: 19 - Decompression Speed compress-zstd: 12 - Compression Speed kvazaar: Bosphorus 1080p - Super Fast cockroach: KV, 50% Reads - 1024 unvanquished: 1920 x 1080 - High stress-ng: Zlib unvanquished: 1920 x 1080 - Ultra cockroach: KV, 95% Reads - 1024 compress-zstd: 12 - Decompression Speed tensorflow: CPU - 512 - GoogLeNet kvazaar: Bosphorus 1080p - Medium compress-zstd: 8, Long Mode - Decompression Speed openems: openEMS MSL_NotchFilter scikit-learn: Sparse Rand Projections, 100 Iterations cpuminer-opt: Quad SHA-256, Pyrite blender: Fishy Cat - CPU-Only onednn: Convolution Batch Shapes Auto - f32 - CPU stress-ng: Semaphores stress-ng: Vector Math compress-zstd: 8 - Decompression Speed stress-ng: Crypto stress-ng: Hash stress-ng: Poll compress-zstd: 3, Long Mode - Decompression Speed embree: Pathtracer - Asian Dragon Obj stress-ng: Function Call unvanquished: 1920 x 1080 - Medium stress-ng: CPU Stress stress-ng: x86_64 RdRand aom-av1: Speed 4 Two-Pass - Bosphorus 1080p rocksdb: Rand Fill stress-ng: Context Switching stress-ng: Socket Activity stress-ng: CPU Cache stress-ng: IO_uring stress-ng: Atomic stress-ng: MEMFD stress-ng: Futex stress-ng: MMAP pgbench: 100 - 500 - Read Write - Average Latency pgbench: 100 - 500 - Read Write pgbench: 100 - 250 - Read Write - Average Latency pgbench: 100 - 250 - Read Write pgbench: 100 - 100 - Read Write - Average Latency pgbench: 100 - 100 - Read Write keydb: LPOP - 100 keydb: SADD - 50 keydb: LPOP - 50 keydb: SET - 50 keydb: GET - 50 onednn: Deconvolution Batch shapes_3d - f32 - CPU onednn: Deconvolution Batch shapes_1d - f32 - CPU onednn: IP Shapes 1D - u8s8f32 - CPU avifenc: 10, Lossless aom-av1: Speed 10 Realtime - Bosphorus 1080p aom-av1: Speed 9 Realtime - Bosphorus 1080p aom-av1: Speed 6 Realtime - Bosphorus 1080p a b c 1351 188.706 4252 2437.96 88.426 4070 246.313 70.8341 42.3370 20.1421 49.6401 27.97 143.21 17.324 36.915 12.18 176.4 1069422.99 1283175.58 22.0196 136.2739 1.52665 0.50 282207 344.30 38.516 18438 0.15 38.663 155.27 48.80 629944 12.73 1323318.97 1220179.93 3797.314 74.0988 40.4680 38.3366 26.0851 263 361525.21 1148270.29 1.393 359165 16.45 133.73 181.6 27.83 2891.941 277 976117.59 3.031 263950 1561.269 394526 0.634 4.09853 217.33 244.489 44.558 9.780 321 2.606 307018 1836.59 130.84 241540 51.1472 19.5514 24.11 4.141 21.53 25625.0 41614110 61.468 6.065 129.7351 20255.7 20.155 23.1401 1502792 258.427 54276.34 387 2.185 617706 20.38 0.162 65.1167 681.418 367 16123.0 46.1009 43.25 175.13 16.99 62.33 29844655556 2.50462 6.34 52512.6 128698.01 8.4875 91.1945 32.8927 4.11 21.05 30043.8 1.17 239.86 31.69 7.21 12.6 13.25 511218.21 5.6401 13.98 5560.27 32.53 0.541 62961.45 4329.65 462071 7.79 9.3366 530.8351 552.79 8.05 88.246 34782.8 5.6434 7.93 177.4 13.461 5.12 1.06 7.94 32151.8 289205 3.458 10.3722 530.1789 2901.8 38.89 112.08 1560.09 47853 2.696 6.53 1.20219 35029.4 2438.21 0.185 184.37 95.565 9270.5 50.05 541410 42.02 1605.965 21.68 120.17 49613.5 4334.97 331.49 68 0.68 0.69 236.87 32.7332 1546655 17827.6 7.977 1567.8 11237 4.58 32.75 30.5731 101.42 3438.18 15.5670 64.2327 27.441 123.26 67993.52 4341.92 2.624567 172.01 5.4650 182.9823 3384.14 1.75 9.175 2.071669 9.11 8.41 188.17 31.87 0.95 125.2707 7.9821 139.13 712.70 198.4 32781.2 244.13 862.76 2.743784 117.653 18.2750 6392.10 7.737 9.6958 1518515 61096.58 276.78 14.44 60.81 1.15 145.95 7.00 51.90 107.91 41663.17 1.398663 120 57.99 5226456.99 2257.17 26.914 90.146 11.0588 80.01 195.068 243.662 9.747 177.4 2406.13 55.33 45.87 110.87 88.60 2301.69 5.76 132931 77.95 2.705122 1.930960 378.02 177365.84 141.00 348.49 9.5706 21.20 41.05 119.13 11.47 20.3269 49.1789 40.17 39.72 26050.8 2.00020 67.09 81.453 43.37 5359.8 371.2707 8.0798 117.88 184.6546 5.4154 13.50 1.573 1444.4 317872 187.09 202.6 348.114 4254720.23 398.861 602.17 6331.01 74.79 1.272677 8216877.60 58.76 1913.71 44.40 170.61 3.59719 869.3 1592.6 51922.48 0.852 45892.79 2.578599 187.49 43281.7 78157 493.25 1516.3 77.1 93.48 30338.7 170.8 717.35 100.6 40249.9 1758.9 44.65 34.46 1727.9 98.88 142.729 48250 242.51 16.5925 1189258.32 41733.97 1732.4 14276.39 1548492.99 823762.13 1619.4 8.7102 49787.62 248.2 17781.86 81909.45 13.31 846457 1897936.07 8703.54 83.60 1965.75 146.11 58.57 1579624.88 74.70 113.076 4472 60.802 4148 24.552 4114 1301994.00 1345962.36 1403220.97 1249454.75 1481042.42 8.93885 8.69748 1.251871 6.571 175.80 188.81 147.69 1239 217.462 3679 2403.19 69.565 3652 273.835 58.9625 50.8421 16.973 58.9068 31.54 126.78 19.297 41.029 11.57 161.5 1146000.38 1382055.38 20.4372 146.7171 1.41538 0.54 302980 367.28 41.175 19200 0.16 38.375 145.95 51.90 624540 12.02 1252473.62 1273002.92 4001.537 78.0436 38.4298 37.6351 26.5668 250 360477.28 1137811.75 1.329 376302 17.22 130.95 173.6 29.11 2861.265 280 1010733.94 2.903 275540 1536.855 407921 0.613 3.9326 226.31 254.507 43.528 10.18 325 2.654 301467 1908.99 129.64 240426 52.8025 18.9371 25.05 4.159 22.34 24787.3 43152112 59.353 5.893 126.3428 19591.8 20.859 23.743 1511361 260.581 52494.81 384 2.257 624238 21.04 0.16 64.2317 702.475 356 15644.6 46.6993 44.31 170.95 17.49 64.1 30699700000 2.45278 6.52 51610.2 130862.38 8.7189 88.7828 33.7778 4.22 20.87 30151.3 1.18 241.95 31.54 7.39 12.3 13.57 518247.5 5.7386 14.3 5661.39 33.27 0.529 64372.01 4234.91 472171 7.89 9.5395 522.759 541.21 8.19 87.041 34070.8 5.6888 8.06 177.3 13.724 5.22 1.04 8.09 32001.2 284352 3.517 10.557 526.9595 2943.7 39.2 114.01 1583.58 48410 2.742 6.64 1.19925 34456.3 2398.62 0.182 182.53 96.58 9148.7 50.83 549838 42.21 1581.695 21.87 119.65 49024 4270.75 327.09 69 0.69 0.69 233.55 32.2883 1562812 17639.6 8.085 1588.6 11090 4.64 32.33 30.9632 102.53 3394.57 15.3717 65.0336 27.782 121.82 68835.78 4289.21 2.593242 169.97 5.4027 185.0876 3363.57 1.77 9.277 2.048931 9.15 8.32 190.2 31.53 0.94 123.9679 8.0658 139.06 719.91 199.8 32901.1 246.58 855.12 2.722846 117.843 18.4063 6428.9 7.809 9.7857 1531157 61654.77 279.3 14.31 61.24 1.16 146.92 7.06 51.56 108.69 42015.72 1.387099 120 58.45 5241054.32 2239.72 26.708 90.819 11.1432 79.81 193.626 245.471 9.819 177.4 2394.33 54.93 46.2 111.65 88.45 2295.12 5.72 132058 77.8 2.697438 1.918443 375.59 176973.24 141.91 347.83 9.6296 21.11 40.8 119.626569107 11.49 20.3874 49.0317 40.32 39.86 26158.4 2.01154 67.46 81.399 43.6 5362.5 371.9694 8.0647 118.22 183.8898 5.4379 13.43 1.581 1451.7 316288 188.02 203.6 348.913 4273551.98 399.081 601.73 6344.82 74.73 1.272057 8225295.79 58.66 1918.11 44.36 170.76 3.59364 866.5 1596.2 51890.45 0.851 46046.48 2.570597 187.53 43180.1 77950 491.93 1512.3 77.2 93.52 30358.1 171.1 717.62 100.5 40176.2 1761.7 44.7 34.52 1725.8 98.72 142.603 48310 242.4 16.6124 1190334.27 41733.47 1733.2 14261.23 1549710.05 823948.19 1618.7 8.7168 49807.05 248.1 17780.76 81907.97 13.31 866381 1941869.46 9385.83 89.5 1723.13 145.01 41.65 1723742.38 50.26 103.714 4821 68.072 3673 23.642 4230 1336505.38 1920122.88 1585238.25 1253729.88 1373626.38 8.13373 8.37239 1.64076 6.438 177.46 171.53 145.58 3193 124.508 6425 4000.34 68.862 4518 221.36 71.6306 41.8658 20.6062 48.5207 26.79 149.21 19.609 38.706 12.69 161.5 1049912.88 1273333.88 22.1491 135.4278 1.4093 0.54 295250 368.41 40.12 19710 0.16 40.903 146.45 51.73 664157 12.25 1317870.38 1288214.51 3967.365 76.8831 39.0101 39.5957 25.2518 252 343680.41 1193659.25 1.368 365485 17.13 137.07 173.8 28.85 2990.051 268 967773.12 3.025 264500 1495.631 411468 0.608 3.95246 225.63 254.306 45.309 10.172 334 2.552 313503 1895.32 134.75 232445 50.8162 19.6773 24.96 4.302 22.14 25709 42975995 59.453 5.857 125.3122 19566.6 20.592 23.9381 1461566 252.003 54204.65 397 2.25 638011 20.92 0.157 63.1436 697.892 358 15733 47.5035 44.55 170.03 17.41 64.13 30696900000 2.43532 6.45 51080.3 132268.72 8.6301 90.1585 33.2636 4.2 21.42 29377.9 1.15 235.80 32.35 7.28 12.4 13.5 506124.09 5.7729 14.24 5687.23 33.22 0.537 64314.45 4253.17 465619 7.96 9.482 519.6558 549.42 8.22 86.434 34301.1 5.7586 8.09 173.9 13.727 5.17 1.04 8.09 31560.1 283973 3.521 10.4342 520.9494 2952.3 38.53 112.44 1586.86 48670 2.725 6.6 1.18228 34933.3 2410.16 0.184 185.48 95.093 9128.1 50.48 544459 42.67 1591.758 21.54 118.36 49764.2 4291.98 326.58 68 0.69 0.7 235.09 32.2818 1568201 17585.4 8.02 1583.6 11100 4.62 32.38 30.97 102.73 3413.87 15.3825 64.9894 27.504 123.33 68707.49 4303.62 2.60295 169.98 5.4023 185.1037 3402.11 1.75 9.268 2.05266 9.21 8.35 189.32 31.68 0.94 123.9547 8.0666 140.47 717.7 200.4 32572.9 245 854.21 2.717116 118.795 18.2347 6368.98 7.75 9.7544 1532546 61396.93 278.2 14.37 60.69 1.16 145.67 7.02 52.00 108.83 42016.88 1.392746 121 58.38 5200128.82 2256.4 26.864 90.838 11.1121 79.41 195.07 245.226 9.809 176.1 2388.51 55.31 46.08 111.66 89.08 2285.43 5.73 132368 77.44 2.687449 1.923352 376.26 178115.64 141.1 346.34 9.5837 21.24 40.83 118.90 11.54 20.2639 49.3305 40.08 39.95 26199.1 2.0105 67.36 81.021 43.37 5388.2 373.2362 8.0373 118.5 183.6924 5.4437 13.45 1.573 1447.2 317863 187.76 203.6 347.219 4254389.29 397.306 604.27 6357.31 75.04 1.267444 8192747.72 58.53 1921.09 44.53 170.11 3.60705 866.1 1598.4 51737.26 0.849 45978.84 2.575363 188.06 43303.9 77940 492.05 1515.1 77.3 93.3 30286.7 170.7 716.14 100.7 40255.3 1762.2 44.62 34.5 1728.6 98.77 142.501 48320 242.75 16.5893 1188758.84 41779.98 1734.3 14271.88 1548182.16 823174.05 1620.2 8.7124 49784.19 248.2 17782.21 81907.39 13.31 1102439 1906264.57 9379.73 72.1 2856.89 162.65 52.99 1689762.38 49.73 82.83 6036 41.632 6005 19.602 5102 1303645 1225640.5 1479465 1422030.12 1690102.75 9.3367 8.4404 0.959942 6.439 168.56 201.29 169.96 OpenBenchmarking.org
RocksDB Test: Random Fill Sync OpenBenchmarking.org Op/s, More Is Better RocksDB 7.9.2 Test: Random Fill Sync a b c 700 1400 2100 2800 3500 SE +/- 15.17, N = 3 1351 1239 3193 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
PostgreSQL Scaling Factor: 100 - Clients: 800 - Mode: Read Write - Average Latency OpenBenchmarking.org ms, Fewer Is Better PostgreSQL 15 Scaling Factor: 100 - Clients: 800 - Mode: Read Write - Average Latency a b c 50 100 150 200 250 SE +/- 3.52, N = 9 188.71 217.46 124.51 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
PostgreSQL Scaling Factor: 100 - Clients: 800 - Mode: Read Write OpenBenchmarking.org TPS, More Is Better PostgreSQL 15 Scaling Factor: 100 - Clients: 800 - Mode: Read Write a b c 1400 2800 4200 5600 7000 SE +/- 83.04, N = 9 4252 3679 6425 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
oneDNN Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.0 Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPU a b c 900 1800 2700 3600 4500 SE +/- 4.94, N = 3 2437.96 2403.19 4000.34 MIN: 2279.1 MIN: 2251.07 MIN: 3992.83 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl
SVT-AV1 Encoder Mode: Preset 12 - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.4 Encoder Mode: Preset 12 - Input: Bosphorus 4K a b c 20 40 60 80 100 SE +/- 0.17, N = 3 88.43 69.57 68.86 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
PostgreSQL Scaling Factor: 100 - Clients: 1000 - Mode: Read Write OpenBenchmarking.org TPS, More Is Better PostgreSQL 15 Scaling Factor: 100 - Clients: 1000 - Mode: Read Write a b c 1000 2000 3000 4000 5000 SE +/- 59.66, N = 12 4070 3652 4518 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
PostgreSQL Scaling Factor: 100 - Clients: 1000 - Mode: Read Write - Average Latency OpenBenchmarking.org ms, Fewer Is Better PostgreSQL 15 Scaling Factor: 100 - Clients: 1000 - Mode: Read Write - Average Latency a b c 60 120 180 240 300 SE +/- 3.72, N = 12 246.31 273.84 221.36 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
Neural Magic DeepSparse Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.3.2 Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Asynchronous Multi-Stream a b c 16 32 48 64 80 SE +/- 0.07, N = 3 70.83 58.96 71.63
Neural Magic DeepSparse Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.3.2 Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Asynchronous Multi-Stream a b c 11 22 33 44 55 SE +/- 0.04, N = 3 42.34 50.84 41.87
Neural Magic DeepSparse Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Synchronous Single-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.3.2 Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Synchronous Single-Stream a b c 5 10 15 20 25 SE +/- 0.06, N = 3 20.14 16.97 20.61
Neural Magic DeepSparse Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Synchronous Single-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.3.2 Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Synchronous Single-Stream a b c 13 26 39 52 65 SE +/- 0.15, N = 3 49.64 58.91 48.52
OpenVINO Model: Vehicle Detection FP16 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2022.3 Model: Vehicle Detection FP16 - Device: CPU a b c 7 14 21 28 35 SE +/- 0.37, N = 14 27.97 31.54 26.79 MIN: 19.8 / MAX: 50.33 MIN: 19.58 / MAX: 49.19 MIN: 21.9 / MAX: 44.22 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared
OpenVINO Model: Vehicle Detection FP16 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2022.3 Model: Vehicle Detection FP16 - Device: CPU a b c 30 60 90 120 150 SE +/- 1.79, N = 14 143.21 126.78 149.21 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared
FLAC Audio Encoding WAV To FLAC OpenBenchmarking.org Seconds, Fewer Is Better FLAC Audio Encoding 1.4 WAV To FLAC a b c 5 10 15 20 25 SE +/- 0.15, N = 25 17.32 19.30 19.61 1. (CXX) g++ options: -O3 -fvisibility=hidden -logg -lm
EnCodec Target Bandwidth: 1.5 kbps OpenBenchmarking.org Seconds, Fewer Is Better EnCodec 0.1.1 Target Bandwidth: 1.5 kbps a b c 9 18 27 36 45 SE +/- 0.20, N = 3 36.92 41.03 38.71
VP9 libvpx Encoding Speed: Speed 0 - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better VP9 libvpx Encoding 1.13 Speed: Speed 0 - Input: Bosphorus 1080p a b c 3 6 9 12 15 SE +/- 0.13, N = 3 12.18 11.57 12.69 1. (CXX) g++ options: -m64 -lm -lpthread -O3 -fPIC -U_FORTIFY_SOURCE -std=gnu++11
CockroachDB Workload: MoVR - Concurrency: 128 OpenBenchmarking.org ops/s, More Is Better CockroachDB 22.2 Workload: MoVR - Concurrency: 128 a b c 40 80 120 160 200 SE +/- 1.32, N = 11 176.4 161.5 161.5
KeyDB Test: SET - Parallel Connections: 100 OpenBenchmarking.org Requests Per Second, More Is Better KeyDB 6.3.2 Test: SET - Parallel Connections: 100 a b c 200K 400K 600K 800K 1000K SE +/- 12223.15, N = 4 1069422.99 1146000.38 1049912.88 1. (CXX) g++ options: -ggdb -rdynamic -lm -lz -lcrypto -lbz2 -lzstd -llz4 -lsnappy -latomic -ldl -pthread -lrt -luuid -lcurl -lssl -std=c++14 -pedantic -fno-rtti -O2 -flto -MMD
KeyDB Test: GET - Parallel Connections: 100 OpenBenchmarking.org Requests Per Second, More Is Better KeyDB 6.3.2 Test: GET - Parallel Connections: 100 a b c 300K 600K 900K 1200K 1500K SE +/- 15206.41, N = 3 1283175.58 1382055.38 1273333.88 1. (CXX) g++ options: -ggdb -rdynamic -lm -lz -lcrypto -lbz2 -lzstd -llz4 -lsnappy -latomic -ldl -pthread -lrt -luuid -lcurl -lssl -std=c++14 -pedantic -fno-rtti -O2 -flto -MMD
Neural Magic DeepSparse Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.3.2 Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Asynchronous Multi-Stream a b c 5 10 15 20 25 SE +/- 0.30, N = 3 22.02 20.44 22.15
Neural Magic DeepSparse Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.3.2 Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Asynchronous Multi-Stream a b c 30 60 90 120 150 SE +/- 1.91, N = 3 136.27 146.72 135.43
oneDNN Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.0 Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPU a b c 0.3435 0.687 1.0305 1.374 1.7175 SE +/- 0.01138, N = 15 1.52665 1.41538 1.40930 MIN: 1.39 MIN: 1.39 MIN: 1.39 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl
AOM AV1 Encoder Mode: Speed 0 Two-Pass - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.6 Encoder Mode: Speed 0 Two-Pass - Input: Bosphorus 1080p a b c 0.1215 0.243 0.3645 0.486 0.6075 SE +/- 0.00, N = 15 0.50 0.54 0.54 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm
Cpuminer-Opt Algorithm: Blake-2 S OpenBenchmarking.org kH/s, More Is Better Cpuminer-Opt 3.20.3 Algorithm: Blake-2 S a b c 60K 120K 180K 240K 300K SE +/- 791.71, N = 3 282207 302980 295250 1. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
Cpuminer-Opt Algorithm: x25x OpenBenchmarking.org kH/s, More Is Better Cpuminer-Opt 3.20.3 Algorithm: x25x a b c 80 160 240 320 400 SE +/- 0.59, N = 3 344.30 367.28 368.41 1. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
EnCodec Target Bandwidth: 6 kbps OpenBenchmarking.org Seconds, Fewer Is Better EnCodec 0.1.1 Target Bandwidth: 6 kbps a b c 9 18 27 36 45 SE +/- 0.47, N = 3 38.52 41.18 40.12
Cpuminer-Opt Algorithm: LBC, LBRY Credits OpenBenchmarking.org kH/s, More Is Better Cpuminer-Opt 3.20.3 Algorithm: LBC, LBRY Credits a b c 4K 8K 12K 16K 20K SE +/- 186.26, N = 5 18438 19200 19710 1. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
AOM AV1 Encoder Mode: Speed 0 Two-Pass - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.6 Encoder Mode: Speed 0 Two-Pass - Input: Bosphorus 4K a b c 0.036 0.072 0.108 0.144 0.18 SE +/- 0.00, N = 7 0.15 0.16 0.16 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm
EnCodec Target Bandwidth: 3 kbps OpenBenchmarking.org Seconds, Fewer Is Better EnCodec 0.1.1 Target Bandwidth: 3 kbps a b c 9 18 27 36 45 SE +/- 0.60, N = 15 38.66 38.38 40.90
FFmpeg Encoder: libx264 - Scenario: Video On Demand OpenBenchmarking.org Seconds, Fewer Is Better FFmpeg 6.0 Encoder: libx264 - Scenario: Video On Demand a b c 30 60 90 120 150 SE +/- 2.11, N = 3 155.27 145.95 146.45 1. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma
FFmpeg Encoder: libx264 - Scenario: Video On Demand OpenBenchmarking.org FPS, More Is Better FFmpeg 6.0 Encoder: libx264 - Scenario: Video On Demand a b c 12 24 36 48 60 SE +/- 0.66, N = 3 48.80 51.90 51.73 1. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma
RocksDB Test: Update Random OpenBenchmarking.org Op/s, More Is Better RocksDB 7.9.2 Test: Update Random a b c 140K 280K 420K 560K 700K SE +/- 6561.15, N = 5 629944 624540 664157 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
VP9 libvpx Encoding Speed: Speed 5 - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better VP9 libvpx Encoding 1.13 Speed: Speed 5 - Input: Bosphorus 4K a b c 3 6 9 12 15 SE +/- 0.07, N = 3 12.73 12.02 12.25 1. (CXX) g++ options: -m64 -lm -lpthread -O3 -fPIC -U_FORTIFY_SOURCE -std=gnu++11
KeyDB Test: LPUSH - Parallel Connections: 50 OpenBenchmarking.org Requests Per Second, More Is Better KeyDB 6.3.2 Test: LPUSH - Parallel Connections: 50 a b c 300K 600K 900K 1200K 1500K SE +/- 14149.76, N = 4 1323318.97 1252473.62 1317870.38 1. (CXX) g++ options: -ggdb -rdynamic -lm -lz -lcrypto -lbz2 -lzstd -llz4 -lsnappy -latomic -ldl -pthread -lrt -luuid -lcurl -lssl -std=c++14 -pedantic -fno-rtti -O2 -flto -MMD
Stress-NG Test: Glibc C String Functions OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.15.04 Test: Glibc C String Functions a b c 300K 600K 900K 1200K 1500K SE +/- 9938.23, N = 9 1220179.93 1273002.92 1288214.51 1. (CC) gcc options: -std=gnu99 -O2 -lm -lapparmor -latomic -lc -lcrypt -ldl -lEGL -lGLESv2 -ljpeg -lrt -lsctp -lz -pthread
PostgreSQL Scaling Factor: 1 - Clients: 1000 - Mode: Read Write - Average Latency OpenBenchmarking.org ms, Fewer Is Better PostgreSQL 15 Scaling Factor: 1 - Clients: 1000 - Mode: Read Write - Average Latency a b c 900 1800 2700 3600 4500 SE +/- 35.63, N = 3 3797.31 4001.54 3967.37 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
Neural Magic DeepSparse Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.3.2 Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream a b c 20 40 60 80 100 SE +/- 0.23, N = 3 74.10 78.04 76.88
Neural Magic DeepSparse Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.3.2 Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream a b c 9 18 27 36 45 SE +/- 0.13, N = 3 40.47 38.43 39.01
Neural Magic DeepSparse Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.3.2 Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Stream a b c 9 18 27 36 45 SE +/- 0.34, N = 3 38.34 37.64 39.60
Neural Magic DeepSparse Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.3.2 Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Stream a b c 6 12 18 24 30 SE +/- 0.23, N = 3 26.09 26.57 25.25
PostgreSQL Scaling Factor: 1 - Clients: 1000 - Mode: Read Write OpenBenchmarking.org TPS, More Is Better PostgreSQL 15 Scaling Factor: 1 - Clients: 1000 - Mode: Read Write a b c 60 120 180 240 300 SE +/- 2.49, N = 3 263 250 252 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
KeyDB Test: HMSET - Parallel Connections: 100 OpenBenchmarking.org Requests Per Second, More Is Better KeyDB 6.3.2 Test: HMSET - Parallel Connections: 100 a b c 80K 160K 240K 320K 400K SE +/- 3780.33, N = 12 361525.21 360477.28 343680.41 1. (CXX) g++ options: -ggdb -rdynamic -lm -lz -lcrypto -lbz2 -lzstd -llz4 -lsnappy -latomic -ldl -pthread -lrt -luuid -lcurl -lssl -std=c++14 -pedantic -fno-rtti -O2 -flto -MMD
KeyDB Test: SADD - Parallel Connections: 100 OpenBenchmarking.org Requests Per Second, More Is Better KeyDB 6.3.2 Test: SADD - Parallel Connections: 100 a b c 300K 600K 900K 1200K 1500K SE +/- 8944.31, N = 3 1148270.29 1137811.75 1193659.25 1. (CXX) g++ options: -ggdb -rdynamic -lm -lz -lcrypto -lbz2 -lzstd -llz4 -lsnappy -latomic -ldl -pthread -lrt -luuid -lcurl -lssl -std=c++14 -pedantic -fno-rtti -O2 -flto -MMD
PostgreSQL Scaling Factor: 1 - Clients: 500 - Mode: Read Only - Average Latency OpenBenchmarking.org ms, Fewer Is Better PostgreSQL 15 Scaling Factor: 1 - Clients: 500 - Mode: Read Only - Average Latency a b c 0.3134 0.6268 0.9402 1.2536 1.567 SE +/- 0.016, N = 4 1.393 1.329 1.368 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
PostgreSQL Scaling Factor: 1 - Clients: 500 - Mode: Read Only OpenBenchmarking.org TPS, More Is Better PostgreSQL 15 Scaling Factor: 1 - Clients: 500 - Mode: Read Only a b c 80K 160K 240K 320K 400K SE +/- 3941.00, N = 4 359165 376302 365485 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
Kvazaar Video Input: Bosphorus 4K - Video Preset: Very Fast OpenBenchmarking.org Frames Per Second, More Is Better Kvazaar 2.2 Video Input: Bosphorus 4K - Video Preset: Very Fast a b c 4 8 12 16 20 SE +/- 0.12, N = 3 16.45 17.22 17.13 1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
ClickHouse 100M Rows Hits Dataset, Third Run OpenBenchmarking.org Queries Per Minute, Geo Mean, More Is Better ClickHouse 22.12.3.5 100M Rows Hits Dataset, Third Run a b c 30 60 90 120 150 SE +/- 0.37, N = 9 133.73 130.95 137.07 MIN: 6.54 / MAX: 8571.43 MIN: 7.08 / MAX: 6000 MIN: 7.03 / MAX: 7500
CockroachDB Workload: MoVR - Concurrency: 256 OpenBenchmarking.org ops/s, More Is Better CockroachDB 22.2 Workload: MoVR - Concurrency: 256 a b c 40 80 120 160 200 SE +/- 0.00, N = 3 181.6 173.6 173.8
Kvazaar Video Input: Bosphorus 4K - Video Preset: Ultra Fast OpenBenchmarking.org Frames Per Second, More Is Better Kvazaar 2.2 Video Input: Bosphorus 4K - Video Preset: Ultra Fast a b c 7 14 21 28 35 SE +/- 0.21, N = 3 27.83 29.11 28.85 1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
PostgreSQL Scaling Factor: 1 - Clients: 800 - Mode: Read Write - Average Latency OpenBenchmarking.org ms, Fewer Is Better PostgreSQL 15 Scaling Factor: 1 - Clients: 800 - Mode: Read Write - Average Latency a b c 600 1200 1800 2400 3000 SE +/- 26.55, N = 12 2891.94 2861.27 2990.05 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
PostgreSQL Scaling Factor: 1 - Clients: 800 - Mode: Read Write OpenBenchmarking.org TPS, More Is Better PostgreSQL 15 Scaling Factor: 1 - Clients: 800 - Mode: Read Write a b c 60 120 180 240 300 SE +/- 2.63, N = 12 277 280 268 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
KeyDB Test: LPUSH - Parallel Connections: 100 OpenBenchmarking.org Requests Per Second, More Is Better KeyDB 6.3.2 Test: LPUSH - Parallel Connections: 100 a b c 200K 400K 600K 800K 1000K SE +/- 10077.27, N = 15 976117.59 1010733.94 967773.12 1. (CXX) g++ options: -ggdb -rdynamic -lm -lz -lcrypto -lbz2 -lzstd -llz4 -lsnappy -latomic -ldl -pthread -lrt -luuid -lcurl -lssl -std=c++14 -pedantic -fno-rtti -O2 -flto -MMD
PostgreSQL Scaling Factor: 100 - Clients: 800 - Mode: Read Only - Average Latency OpenBenchmarking.org ms, Fewer Is Better PostgreSQL 15 Scaling Factor: 100 - Clients: 800 - Mode: Read Only - Average Latency a b c 0.682 1.364 2.046 2.728 3.41 SE +/- 0.027, N = 3 3.031 2.903 3.025 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
PostgreSQL Scaling Factor: 100 - Clients: 800 - Mode: Read Only OpenBenchmarking.org TPS, More Is Better PostgreSQL 15 Scaling Factor: 100 - Clients: 800 - Mode: Read Only a b c 60K 120K 180K 240K 300K SE +/- 2360.08, N = 3 263950 275540 264500 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
PostgreSQL Scaling Factor: 1 - Clients: 500 - Mode: Read Write - Average Latency OpenBenchmarking.org ms, Fewer Is Better PostgreSQL 15 Scaling Factor: 1 - Clients: 500 - Mode: Read Write - Average Latency a b c 300 600 900 1200 1500 SE +/- 15.49, N = 12 1561.27 1536.86 1495.63 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
PostgreSQL Scaling Factor: 100 - Clients: 250 - Mode: Read Only OpenBenchmarking.org TPS, More Is Better PostgreSQL 15 Scaling Factor: 100 - Clients: 250 - Mode: Read Only a b c 90K 180K 270K 360K 450K SE +/- 2783.61, N = 3 394526 407921 411468 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
PostgreSQL Scaling Factor: 100 - Clients: 250 - Mode: Read Only - Average Latency OpenBenchmarking.org ms, Fewer Is Better PostgreSQL 15 Scaling Factor: 100 - Clients: 250 - Mode: Read Only - Average Latency a b c 0.1427 0.2854 0.4281 0.5708 0.7135 SE +/- 0.005, N = 3 0.634 0.613 0.608 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
oneDNN Harness: IP Shapes 1D - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.0 Harness: IP Shapes 1D - Data Type: f32 - Engine: CPU a b c 0.9222 1.8444 2.7666 3.6888 4.611 SE +/- 0.02631, N = 15 4.09853 3.93260 3.95246 MIN: 3.8 MIN: 3.81 MIN: 3.82 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl
JPEG XL Decoding libjxl CPU Threads: All OpenBenchmarking.org MP/s, More Is Better JPEG XL Decoding libjxl 0.7 CPU Threads: All a b c 50 100 150 200 250 SE +/- 0.07, N = 3 217.33 226.31 225.63
miniBUDE Implementation: OpenMP - Input Deck: BM1 OpenBenchmarking.org GFInst/s, More Is Better miniBUDE 20210901 Implementation: OpenMP - Input Deck: BM1 a b c 60 120 180 240 300 SE +/- 2.17, N = 7 244.49 254.51 254.31 1. (CC) gcc options: -std=c99 -Ofast -ffast-math -fopenmp -march=native -lm
EnCodec Target Bandwidth: 24 kbps OpenBenchmarking.org Seconds, Fewer Is Better EnCodec 0.1.1 Target Bandwidth: 24 kbps a b c 10 20 30 40 50 SE +/- 0.52, N = 15 44.56 43.53 45.31
miniBUDE Implementation: OpenMP - Input Deck: BM1 OpenBenchmarking.org Billion Interactions/s, More Is Better miniBUDE 20210901 Implementation: OpenMP - Input Deck: BM1 a b c 3 6 9 12 15 SE +/- 0.087, N = 7 9.780 10.180 10.172 1. (CC) gcc options: -std=c99 -Ofast -ffast-math -fopenmp -march=native -lm
PostgreSQL Scaling Factor: 1 - Clients: 500 - Mode: Read Write OpenBenchmarking.org TPS, More Is Better PostgreSQL 15 Scaling Factor: 1 - Clients: 500 - Mode: Read Write a b c 70 140 210 280 350 SE +/- 3.20, N = 12 321 325 334 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
PostgreSQL Scaling Factor: 1 - Clients: 800 - Mode: Read Only - Average Latency OpenBenchmarking.org ms, Fewer Is Better PostgreSQL 15 Scaling Factor: 1 - Clients: 800 - Mode: Read Only - Average Latency a b c 0.5972 1.1944 1.7916 2.3888 2.986 SE +/- 0.012, N = 3 2.606 2.654 2.552 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
PostgreSQL Scaling Factor: 1 - Clients: 800 - Mode: Read Only OpenBenchmarking.org TPS, More Is Better PostgreSQL 15 Scaling Factor: 1 - Clients: 800 - Mode: Read Only a b c 70K 140K 210K 280K 350K SE +/- 1379.07, N = 3 307018 301467 313503 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
Cpuminer-Opt Algorithm: Garlicoin OpenBenchmarking.org kH/s, More Is Better Cpuminer-Opt 3.20.3 Algorithm: Garlicoin a b c 400 800 1200 1600 2000 SE +/- 21.45, N = 4 1836.59 1908.99 1895.32 1. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
ClickHouse 100M Rows Hits Dataset, Second Run OpenBenchmarking.org Queries Per Minute, Geo Mean, More Is Better ClickHouse 22.12.3.5 100M Rows Hits Dataset, Second Run a b c 30 60 90 120 150 SE +/- 0.66, N = 9 130.84 129.64 134.75 MIN: 6.51 / MAX: 8571.43 MIN: 7.07 / MAX: 6000 MIN: 7.04 / MAX: 8571.43
PostgreSQL Scaling Factor: 100 - Clients: 1000 - Mode: Read Only OpenBenchmarking.org TPS, More Is Better PostgreSQL 15 Scaling Factor: 100 - Clients: 1000 - Mode: Read Only a b c 50K 100K 150K 200K 250K SE +/- 1961.46, N = 3 241540 240426 232445 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
Neural Magic DeepSparse Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Synchronous Single-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.3.2 Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Synchronous Single-Stream a b c 12 24 36 48 60 SE +/- 0.32, N = 3 51.15 52.80 50.82
Neural Magic DeepSparse Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Synchronous Single-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.3.2 Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Synchronous Single-Stream a b c 5 10 15 20 25 SE +/- 0.12, N = 3 19.55 18.94 19.68
uvg266 Video Input: Bosphorus 1080p - Video Preset: Medium OpenBenchmarking.org Frames Per Second, More Is Better uvg266 0.4.1 Video Input: Bosphorus 1080p - Video Preset: Medium a b c 6 12 18 24 30 SE +/- 0.14, N = 3 24.11 25.05 24.96
PostgreSQL Scaling Factor: 100 - Clients: 1000 - Mode: Read Only - Average Latency OpenBenchmarking.org ms, Fewer Is Better PostgreSQL 15 Scaling Factor: 100 - Clients: 1000 - Mode: Read Only - Average Latency a b c 0.968 1.936 2.904 3.872 4.84 SE +/- 0.034, N = 3 4.141 4.159 4.302 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
uvg266 Video Input: Bosphorus 1080p - Video Preset: Slow OpenBenchmarking.org Frames Per Second, More Is Better uvg266 0.4.1 Video Input: Bosphorus 1080p - Video Preset: Slow a b c 5 10 15 20 25 SE +/- 0.02, N = 3 21.53 22.34 22.14
CockroachDB Workload: KV, 10% Reads - Concurrency: 512 OpenBenchmarking.org ops/s, More Is Better CockroachDB 22.2 Workload: KV, 10% Reads - Concurrency: 512 a b c 6K 12K 18K 24K 30K SE +/- 297.75, N = 3 25625.0 24787.3 25709.0
RocksDB Test: Random Read OpenBenchmarking.org Op/s, More Is Better RocksDB 7.9.2 Test: Random Read a b c 9M 18M 27M 36M 45M SE +/- 414703.47, N = 6 41614110 43152112 42975995 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
Timed FFmpeg Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed FFmpeg Compilation 6.0 Time To Compile a b c 14 28 42 56 70 SE +/- 0.68, N = 3 61.47 59.35 59.45
VVenC Video Input: Bosphorus 4K - Video Preset: Faster OpenBenchmarking.org Frames Per Second, More Is Better VVenC 1.7 Video Input: Bosphorus 4K - Video Preset: Faster a b c 2 4 6 8 10 SE +/- 0.017, N = 3 6.065 5.893 5.857 1. (CXX) g++ options: -O3 -flto -fno-fat-lto-objects -flto=auto
Neural Magic DeepSparse Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.3.2 Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-Stream a b c 30 60 90 120 150 SE +/- 1.18, N = 12 129.74 126.34 125.31
CockroachDB Workload: KV, 60% Reads - Concurrency: 128 OpenBenchmarking.org ops/s, More Is Better CockroachDB 22.2 Workload: KV, 60% Reads - Concurrency: 128 a b c 4K 8K 12K 16K 20K SE +/- 104.08, N = 3 20255.7 19591.8 19566.6
VVenC Video Input: Bosphorus 1080p - Video Preset: Faster OpenBenchmarking.org Frames Per Second, More Is Better VVenC 1.7 Video Input: Bosphorus 1080p - Video Preset: Faster a b c 5 10 15 20 25 SE +/- 0.07, N = 3 20.16 20.86 20.59 1. (CXX) g++ options: -O3 -flto -fno-fat-lto-objects -flto=auto
Neural Magic DeepSparse Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.3.2 Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-Stream a b c 6 12 18 24 30 SE +/- 0.20, N = 12 23.14 23.74 23.94
RocksDB Test: Sequential Fill OpenBenchmarking.org Op/s, More Is Better RocksDB 7.9.2 Test: Sequential Fill a b c 300K 600K 900K 1200K 1500K SE +/- 3413.48, N = 3 1502792 1511361 1461566 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
PostgreSQL Scaling Factor: 1 - Clients: 100 - Mode: Read Write - Average Latency OpenBenchmarking.org ms, Fewer Is Better PostgreSQL 15 Scaling Factor: 1 - Clients: 100 - Mode: Read Write - Average Latency a b c 60 120 180 240 300 SE +/- 1.27, N = 3 258.43 260.58 252.00 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
Stress-NG Test: Forking OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.15.04 Test: Forking a b c 12K 24K 36K 48K 60K SE +/- 302.19, N = 3 54276.34 52494.81 54204.65 1. (CC) gcc options: -std=gnu99 -O2 -lm -lapparmor -latomic -lc -lcrypt -ldl -lEGL -lGLESv2 -ljpeg -lrt -lsctp -lz -pthread
PostgreSQL Scaling Factor: 1 - Clients: 100 - Mode: Read Write OpenBenchmarking.org TPS, More Is Better PostgreSQL 15 Scaling Factor: 1 - Clients: 100 - Mode: Read Write a b c 90 180 270 360 450 SE +/- 1.90, N = 3 387 384 397 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
SVT-AV1 Encoder Mode: Preset 4 - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.4 Encoder Mode: Preset 4 - Input: Bosphorus 4K a b c 0.5078 1.0156 1.5234 2.0312 2.539 SE +/- 0.007, N = 3 2.185 2.257 2.250 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
PostgreSQL Scaling Factor: 1 - Clients: 100 - Mode: Read Only OpenBenchmarking.org TPS, More Is Better PostgreSQL 15 Scaling Factor: 1 - Clients: 100 - Mode: Read Only a b c 140K 280K 420K 560K 700K SE +/- 4488.67, N = 3 617706 624238 638011 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
Kvazaar Video Input: Bosphorus 4K - Video Preset: Super Fast OpenBenchmarking.org Frames Per Second, More Is Better Kvazaar 2.2 Video Input: Bosphorus 4K - Video Preset: Super Fast a b c 5 10 15 20 25 SE +/- 0.11, N = 3 20.38 21.04 20.92 1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
PostgreSQL Scaling Factor: 1 - Clients: 100 - Mode: Read Only - Average Latency OpenBenchmarking.org ms, Fewer Is Better PostgreSQL 15 Scaling Factor: 1 - Clients: 100 - Mode: Read Only - Average Latency a b c 0.0365 0.073 0.1095 0.146 0.1825 SE +/- 0.001, N = 3 0.162 0.160 0.157 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
Neural Magic DeepSparse Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.3.2 Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream a b c 15 30 45 60 75 SE +/- 0.58, N = 12 65.12 64.23 63.14
PostgreSQL Scaling Factor: 1 - Clients: 250 - Mode: Read Write - Average Latency OpenBenchmarking.org ms, Fewer Is Better PostgreSQL 15 Scaling Factor: 1 - Clients: 250 - Mode: Read Write - Average Latency a b c 150 300 450 600 750 SE +/- 4.83, N = 3 681.42 702.48 697.89 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
PostgreSQL Scaling Factor: 1 - Clients: 250 - Mode: Read Write OpenBenchmarking.org TPS, More Is Better PostgreSQL 15 Scaling Factor: 1 - Clients: 250 - Mode: Read Write a b c 80 160 240 320 400 SE +/- 2.61, N = 3 367 356 358 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
CockroachDB Workload: KV, 50% Reads - Concurrency: 128 OpenBenchmarking.org ops/s, More Is Better CockroachDB 22.2 Workload: KV, 50% Reads - Concurrency: 128 a b c 3K 6K 9K 12K 15K SE +/- 199.13, N = 3 16123.0 15644.6 15733.0
Neural Magic DeepSparse Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.3.2 Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream a b c 11 22 33 44 55 SE +/- 0.38, N = 12 46.10 46.70 47.50
FFmpeg Encoder: libx265 - Scenario: Video On Demand OpenBenchmarking.org FPS, More Is Better FFmpeg 6.0 Encoder: libx265 - Scenario: Video On Demand a b c 10 20 30 40 50 SE +/- 0.04, N = 3 43.25 44.31 44.55 1. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma
FFmpeg Encoder: libx265 - Scenario: Video On Demand OpenBenchmarking.org Seconds, Fewer Is Better FFmpeg 6.0 Encoder: libx265 - Scenario: Video On Demand a b c 40 80 120 160 200 SE +/- 0.16, N = 3 175.13 170.95 170.03 1. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma
uvg266 Video Input: Bosphorus 4K - Video Preset: Ultra Fast OpenBenchmarking.org Frames Per Second, More Is Better uvg266 0.4.1 Video Input: Bosphorus 4K - Video Preset: Ultra Fast a b c 4 8 12 16 20 SE +/- 0.04, N = 3 16.99 17.49 17.41
uvg266 Video Input: Bosphorus 1080p - Video Preset: Very Fast OpenBenchmarking.org Frames Per Second, More Is Better uvg266 0.4.1 Video Input: Bosphorus 1080p - Video Preset: Very Fast a b c 14 28 42 56 70 SE +/- 0.17, N = 3 62.33 64.10 64.13
nekRS Input: TurboPipe Periodic OpenBenchmarking.org FLOP/s, More Is Better nekRS 22.0 Input: TurboPipe Periodic a b c 7000M 14000M 21000M 28000M 35000M SE +/- 533119138.01, N = 9 29844655556 30699700000 30696900000 1. (CXX) g++ options: -fopenmp -O2 -march=native -mtune=native -ftree-vectorize -lmpi_cxx -lmpi
oneDNN Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.0 Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPU a b c 0.5635 1.127 1.6905 2.254 2.8175 SE +/- 0.02403, N = 15 2.50462 2.45278 2.43532 MIN: 2.34 MIN: 2.41 MIN: 2.39 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl
Kvazaar Video Input: Bosphorus 4K - Video Preset: Slow OpenBenchmarking.org Frames Per Second, More Is Better Kvazaar 2.2 Video Input: Bosphorus 4K - Video Preset: Slow a b c 2 4 6 8 10 SE +/- 0.03, N = 3 6.34 6.52 6.45 1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
CockroachDB Workload: KV, 95% Reads - Concurrency: 128 OpenBenchmarking.org ops/s, More Is Better CockroachDB 22.2 Workload: KV, 95% Reads - Concurrency: 128 a b c 11K 22K 33K 44K 55K SE +/- 345.86, N = 3 52512.6 51610.2 51080.3
Stress-NG Test: Pthread OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.15.04 Test: Pthread a b c 30K 60K 90K 120K 150K SE +/- 1404.99, N = 4 128698.01 130862.38 132268.72 1. (CC) gcc options: -std=gnu99 -O2 -lm -lapparmor -latomic -lc -lcrypt -ldl -lEGL -lGLESv2 -ljpeg -lrt -lsctp -lz -pthread
Embree Binary: Pathtracer - Model: Crown OpenBenchmarking.org Frames Per Second, More Is Better Embree 4.0 Binary: Pathtracer - Model: Crown a b c 2 4 6 8 10 SE +/- 0.0433, N = 3 8.4875 8.7189 8.6301 MIN: 8.32 / MAX: 8.82 MIN: 8.66 / MAX: 8.9 MIN: 8.56 / MAX: 8.78
Neural Magic DeepSparse Model: CV Detection, YOLOv5s COCO - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.3.2 Model: CV Detection, YOLOv5s COCO - Scenario: Asynchronous Multi-Stream a b c 20 40 60 80 100 SE +/- 0.97, N = 3 91.19 88.78 90.16
Neural Magic DeepSparse Model: CV Detection, YOLOv5s COCO - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.3.2 Model: CV Detection, YOLOv5s COCO - Scenario: Asynchronous Multi-Stream a b c 8 16 24 32 40 SE +/- 0.35, N = 3 32.89 33.78 33.26
uvg266 Video Input: Bosphorus 4K - Video Preset: Slow OpenBenchmarking.org Frames Per Second, More Is Better uvg266 0.4.1 Video Input: Bosphorus 4K - Video Preset: Slow a b c 0.9495 1.899 2.8485 3.798 4.7475 SE +/- 0.05, N = 3 4.11 4.22 4.20
FFmpeg Encoder: libx264 - Scenario: Live OpenBenchmarking.org Seconds, Fewer Is Better FFmpeg 6.0 Encoder: libx264 - Scenario: Live a b c 5 10 15 20 25 SE +/- 0.01, N = 3 21.05 20.87 21.42 1. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma
CockroachDB Workload: KV, 50% Reads - Concurrency: 256 OpenBenchmarking.org ops/s, More Is Better CockroachDB 22.2 Workload: KV, 50% Reads - Concurrency: 256 a b c 6K 12K 18K 24K 30K SE +/- 375.67, N = 3 30043.8 30151.3 29377.9
OpenVINO Model: Person Detection FP16 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2022.3 Model: Person Detection FP16 - Device: CPU a b c 0.2655 0.531 0.7965 1.062 1.3275 SE +/- 0.01, N = 3 1.17 1.18 1.15 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared
FFmpeg Encoder: libx264 - Scenario: Live OpenBenchmarking.org FPS, More Is Better FFmpeg 6.0 Encoder: libx264 - Scenario: Live a b c 50 100 150 200 250 SE +/- 0.14, N = 3 239.86 241.95 235.80 1. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma
AOM AV1 Encoder Mode: Speed 6 Two-Pass - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.6 Encoder Mode: Speed 6 Two-Pass - Input: Bosphorus 1080p a b c 8 16 24 32 40 SE +/- 0.42, N = 3 31.69 31.54 32.35 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm
OpenVINO Model: Face Detection FP16-INT8 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2022.3 Model: Face Detection FP16-INT8 - Device: CPU a b c 2 4 6 8 10 SE +/- 0.04, N = 3 7.21 7.39 7.28 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared
Zstd Compression Compression Level: 19 - Compression Speed OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.5.4 Compression Level: 19 - Compression Speed a b c 3 6 9 12 15 SE +/- 0.10, N = 15 12.6 12.3 12.4 1. (CC) gcc options: -O3 -pthread -lz -llzma -llz4
uvg266 Video Input: Bosphorus 4K - Video Preset: Very Fast OpenBenchmarking.org Frames Per Second, More Is Better uvg266 0.4.1 Video Input: Bosphorus 4K - Video Preset: Very Fast a b c 3 6 9 12 15 SE +/- 0.08, N = 3 13.25 13.57 13.50
KeyDB Test: HMSET - Parallel Connections: 50 OpenBenchmarking.org Requests Per Second, More Is Better KeyDB 6.3.2 Test: HMSET - Parallel Connections: 50 a b c 110K 220K 330K 440K 550K SE +/- 2335.08, N = 3 511218.21 518247.50 506124.09 1. (CXX) g++ options: -ggdb -rdynamic -lm -lz -lcrypto -lbz2 -lzstd -llz4 -lsnappy -latomic -ldl -pthread -lrt -luuid -lcurl -lssl -std=c++14 -pedantic -fno-rtti -O2 -flto -MMD
Neural Magic DeepSparse Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.3.2 Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Stream a b c 1.2989 2.5978 3.8967 5.1956 6.4945 SE +/- 0.0204, N = 3 5.6401 5.7386 5.7729
uvg266 Video Input: Bosphorus 4K - Video Preset: Super Fast OpenBenchmarking.org Frames Per Second, More Is Better uvg266 0.4.1 Video Input: Bosphorus 4K - Video Preset: Super Fast a b c 4 8 12 16 20 SE +/- 0.08, N = 3 13.98 14.30 14.24
OpenVINO Model: Age Gender Recognition Retail 0013 FP16 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2022.3 Model: Age Gender Recognition Retail 0013 FP16 - Device: CPU a b c 1200 2400 3600 4800 6000 SE +/- 27.53, N = 3 5560.27 5661.39 5687.23 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared
Kvazaar Video Input: Bosphorus 1080p - Video Preset: Slow OpenBenchmarking.org Frames Per Second, More Is Better Kvazaar 2.2 Video Input: Bosphorus 1080p - Video Preset: Slow a b c 8 16 24 32 40 SE +/- 0.14, N = 3 32.53 33.27 33.22 1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
PostgreSQL Scaling Factor: 1 - Clients: 250 - Mode: Read Only - Average Latency OpenBenchmarking.org ms, Fewer Is Better PostgreSQL 15 Scaling Factor: 1 - Clients: 250 - Mode: Read Only - Average Latency a b c 0.1217 0.2434 0.3651 0.4868 0.6085 SE +/- 0.008, N = 3 0.541 0.529 0.537 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
nginx Connections: 20 OpenBenchmarking.org Requests Per Second, More Is Better nginx 1.23.2 Connections: 20 a b c 14K 28K 42K 56K 70K SE +/- 804.71, N = 3 62961.45 64372.01 64314.45 1. (CC) gcc options: -lluajit-5.1 -lm -lssl -lcrypto -lpthread -ldl -std=c99 -O2
oneDNN Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.0 Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPU a b c 900 1800 2700 3600 4500 SE +/- 15.35, N = 3 4329.65 4234.91 4253.17 MIN: 4088.59 MIN: 4027.35 MIN: 4043.25 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl
PostgreSQL Scaling Factor: 1 - Clients: 250 - Mode: Read Only OpenBenchmarking.org TPS, More Is Better PostgreSQL 15 Scaling Factor: 1 - Clients: 250 - Mode: Read Only a b c 100K 200K 300K 400K 500K SE +/- 6603.78, N = 3 462071 472171 465619 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
JPEG XL libjxl Input: JPEG - Quality: 90 OpenBenchmarking.org MP/s, More Is Better JPEG XL libjxl 0.7 Input: JPEG - Quality: 90 a b c 2 4 6 8 10 SE +/- 0.01, N = 3 7.79 7.89 7.96 1. (CXX) g++ options: -fno-rtti -funwind-tables -O3 -O2 -fPIE -pie -lm -latomic
Embree Binary: Pathtracer ISPC - Model: Crown OpenBenchmarking.org Frames Per Second, More Is Better Embree 4.0 Binary: Pathtracer ISPC - Model: Crown a b c 3 6 9 12 15 SE +/- 0.0598, N = 3 9.3366 9.5395 9.4820 MIN: 9.13 / MAX: 9.88 MIN: 9.33 / MAX: 9.85 MIN: 9.26 / MAX: 9.81
Neural Magic DeepSparse Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.3.2 Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Stream a b c 110 220 330 440 550 SE +/- 1.89, N = 3 530.84 522.76 519.66
OpenVINO Model: Face Detection FP16-INT8 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2022.3 Model: Face Detection FP16-INT8 - Device: CPU a b c 120 240 360 480 600 SE +/- 2.23, N = 3 552.79 541.21 549.42 MIN: 501.54 / MAX: 634.83 MIN: 503.72 / MAX: 633.37 MIN: 502.92 / MAX: 645.96 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared
JPEG XL libjxl Input: PNG - Quality: 80 OpenBenchmarking.org MP/s, More Is Better JPEG XL libjxl 0.7 Input: PNG - Quality: 80 a b c 2 4 6 8 10 SE +/- 0.00, N = 3 8.05 8.19 8.22 1. (CXX) g++ options: -fno-rtti -funwind-tables -O3 -O2 -fPIE -pie -lm -latomic
libavif avifenc Encoder Speed: 2 OpenBenchmarking.org Seconds, Fewer Is Better libavif avifenc 0.11 Encoder Speed: 2 a b c 20 40 60 80 100 SE +/- 0.11, N = 3 88.25 87.04 86.43 1. (CXX) g++ options: -O3 -fPIC -lm
CockroachDB Workload: KV, 60% Reads - Concurrency: 256 OpenBenchmarking.org ops/s, More Is Better CockroachDB 22.2 Workload: KV, 60% Reads - Concurrency: 256 a b c 7K 14K 21K 28K 35K SE +/- 405.43, N = 3 34782.8 34070.8 34301.1
Neural Magic DeepSparse Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.3.2 Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Stream a b c 1.2957 2.5914 3.8871 5.1828 6.4785 SE +/- 0.0208, N = 3 5.6434 5.6888 5.7586
JPEG XL libjxl Input: JPEG - Quality: 80 OpenBenchmarking.org MP/s, More Is Better JPEG XL libjxl 0.7 Input: JPEG - Quality: 80 a b c 2 4 6 8 10 SE +/- 0.01, N = 3 7.93 8.06 8.09 1. (CXX) g++ options: -fno-rtti -funwind-tables -O3 -O2 -fPIE -pie -lm -latomic
CockroachDB Workload: MoVR - Concurrency: 512 OpenBenchmarking.org ops/s, More Is Better CockroachDB 22.2 Workload: MoVR - Concurrency: 512 a b c 40 80 120 160 200 SE +/- 0.00, N = 3 177.4 177.3 173.9
libavif avifenc Encoder Speed: 6, Lossless OpenBenchmarking.org Seconds, Fewer Is Better libavif avifenc 0.11 Encoder Speed: 6, Lossless a b c 4 8 12 16 20 SE +/- 0.14, N = 3 13.46 13.72 13.73 1. (CXX) g++ options: -O3 -fPIC -lm
AOM AV1 Encoder Mode: Speed 4 Two-Pass - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.6 Encoder Mode: Speed 4 Two-Pass - Input: Bosphorus 4K a b c 1.1745 2.349 3.5235 4.698 5.8725 SE +/- 0.00, N = 3 5.12 5.22 5.17 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm
OpenVINO Model: Age Gender Recognition Retail 0013 FP16 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2022.3 Model: Age Gender Recognition Retail 0013 FP16 - Device: CPU a b c 0.2385 0.477 0.7155 0.954 1.1925 SE +/- 0.01, N = 3 1.06 1.04 1.04 MIN: 0.92 / MAX: 68.14 MIN: 0.92 / MAX: 7.17 MIN: 0.92 / MAX: 4.88 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared
JPEG XL libjxl Input: PNG - Quality: 90 OpenBenchmarking.org MP/s, More Is Better JPEG XL libjxl 0.7 Input: PNG - Quality: 90 a b c 2 4 6 8 10 SE +/- 0.01, N = 3 7.94 8.09 8.09 1. (CXX) g++ options: -fno-rtti -funwind-tables -O3 -O2 -fPIE -pie -lm -latomic
CockroachDB Workload: KV, 60% Reads - Concurrency: 1024 OpenBenchmarking.org ops/s, More Is Better CockroachDB 22.2 Workload: KV, 60% Reads - Concurrency: 1024 a b c 7K 14K 21K 28K 35K SE +/- 47.74, N = 3 32151.8 32001.2 31560.1
PostgreSQL Scaling Factor: 1 - Clients: 1000 - Mode: Read Only OpenBenchmarking.org TPS, More Is Better PostgreSQL 15 Scaling Factor: 1 - Clients: 1000 - Mode: Read Only a b c 60K 120K 180K 240K 300K SE +/- 2823.16, N = 3 289205 284352 283973 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
PostgreSQL Scaling Factor: 1 - Clients: 1000 - Mode: Read Only - Average Latency OpenBenchmarking.org ms, Fewer Is Better PostgreSQL 15 Scaling Factor: 1 - Clients: 1000 - Mode: Read Only - Average Latency a b c 0.7922 1.5844 2.3766 3.1688 3.961 SE +/- 0.034, N = 3 3.458 3.517 3.521 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
oneDNN Harness: IP Shapes 3D - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.0 Harness: IP Shapes 3D - Data Type: f32 - Engine: CPU a b c 3 6 9 12 15 SE +/- 0.00, N = 3 10.37 10.56 10.43 MIN: 10.1 MIN: 10.29 MIN: 10.17 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl
Neural Magic DeepSparse Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.3.2 Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Stream a b c 110 220 330 440 550 SE +/- 1.42, N = 3 530.18 526.96 520.95
Xmrig Variant: Monero - Hash Count: 1M OpenBenchmarking.org H/s, More Is Better Xmrig 6.18.1 Variant: Monero - Hash Count: 1M a b c 600 1200 1800 2400 3000 SE +/- 10.62, N = 3 2901.8 2943.7 2952.3 1. (CXX) g++ options: -fexceptions -fno-rtti -maes -O3 -Ofast -static-libgcc -static-libstdc++ -rdynamic -lssl -lcrypto -luv -lpthread -lrt -ldl -lhwloc
TensorFlow Device: CPU - Batch Size: 16 - Model: GoogLeNet OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.10 Device: CPU - Batch Size: 16 - Model: GoogLeNet a b c 9 18 27 36 45 SE +/- 0.03, N = 3 38.89 39.20 38.53
ClickHouse 100M Rows Hits Dataset, First Run / Cold Cache OpenBenchmarking.org Queries Per Minute, Geo Mean, More Is Better ClickHouse 22.12.3.5 100M Rows Hits Dataset, First Run / Cold Cache a b c 30 60 90 120 150 SE +/- 1.04, N = 9 112.08 114.01 112.44 MIN: 6.36 / MAX: 6666.67 MIN: 6.89 / MAX: 5000 MIN: 6.91 / MAX: 5454.55
Cpuminer-Opt Algorithm: Ringcoin OpenBenchmarking.org kH/s, More Is Better Cpuminer-Opt 3.20.3 Algorithm: Ringcoin a b c 300 600 900 1200 1500 SE +/- 14.19, N = 3 1560.09 1583.58 1586.86 1. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
Cpuminer-Opt Algorithm: Skeincoin OpenBenchmarking.org kH/s, More Is Better Cpuminer-Opt 3.20.3 Algorithm: Skeincoin a b c 10K 20K 30K 40K 50K SE +/- 360.94, N = 3 47853 48410 48670 1. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
VVenC Video Input: Bosphorus 4K - Video Preset: Fast OpenBenchmarking.org Frames Per Second, More Is Better VVenC 1.7 Video Input: Bosphorus 4K - Video Preset: Fast a b c 0.617 1.234 1.851 2.468 3.085 SE +/- 0.016, N = 3 2.696 2.742 2.725 1. (CXX) g++ options: -O3 -flto -fno-fat-lto-objects -flto=auto
Kvazaar Video Input: Bosphorus 4K - Video Preset: Medium OpenBenchmarking.org Frames Per Second, More Is Better Kvazaar 2.2 Video Input: Bosphorus 4K - Video Preset: Medium a b c 2 4 6 8 10 SE +/- 0.02, N = 3 6.53 6.64 6.60 1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
oneDNN Harness: Matrix Multiply Batch Shapes Transformer - Data Type: u8s8f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.0 Harness: Matrix Multiply Batch Shapes Transformer - Data Type: u8s8f32 - Engine: CPU a b c 0.2705 0.541 0.8115 1.082 1.3525 SE +/- 0.00770, N = 3 1.20219 1.19925 1.18228 MIN: 1.13 MIN: 1.13 MIN: 1.12 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl
CockroachDB Workload: KV, 60% Reads - Concurrency: 512 OpenBenchmarking.org ops/s, More Is Better CockroachDB 22.2 Workload: KV, 60% Reads - Concurrency: 512 a b c 8K 16K 24K 32K 40K SE +/- 342.69, N = 3 35029.4 34456.3 34933.3
oneDNN Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.0 Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPU a b c 500 1000 1500 2000 2500 SE +/- 3.98, N = 3 2438.21 2398.62 2410.16 MIN: 2279.8 MIN: 2251.99 MIN: 2254.61 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl
PostgreSQL Scaling Factor: 100 - Clients: 100 - Mode: Read Only - Average Latency OpenBenchmarking.org ms, Fewer Is Better PostgreSQL 15 Scaling Factor: 100 - Clients: 100 - Mode: Read Only - Average Latency a b c 0.0416 0.0832 0.1248 0.1664 0.208 SE +/- 0.001, N = 3 0.185 0.182 0.184 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
OpenVINO Model: Machine Translation EN To DE FP16 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2022.3 Model: Machine Translation EN To DE FP16 - Device: CPU a b c 40 80 120 160 200 SE +/- 0.73, N = 3 184.37 182.53 185.48 MIN: 164.97 / MAX: 226.63 MIN: 165.34 / MAX: 243.94 MIN: 166.33 / MAX: 257.37 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared
SVT-AV1 Encoder Mode: Preset 13 - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.4 Encoder Mode: Preset 13 - Input: Bosphorus 4K a b c 20 40 60 80 100 SE +/- 0.27, N = 3 95.57 96.58 95.09 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
CockroachDB Workload: KV, 10% Reads - Concurrency: 128 OpenBenchmarking.org ops/s, More Is Better CockroachDB 22.2 Workload: KV, 10% Reads - Concurrency: 128 a b c 2K 4K 6K 8K 10K SE +/- 11.01, N = 3 9270.5 9148.7 9128.1
JPEG XL Decoding libjxl CPU Threads: 1 OpenBenchmarking.org MP/s, More Is Better JPEG XL Decoding libjxl 0.7 CPU Threads: 1 a b c 11 22 33 44 55 SE +/- 0.34, N = 3 50.05 50.83 50.48
PostgreSQL Scaling Factor: 100 - Clients: 100 - Mode: Read Only OpenBenchmarking.org TPS, More Is Better PostgreSQL 15 Scaling Factor: 100 - Clients: 100 - Mode: Read Only a b c 120K 240K 360K 480K 600K SE +/- 1426.41, N = 3 541410 549838 544459 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
FFmpeg Encoder: libx265 - Scenario: Live OpenBenchmarking.org Seconds, Fewer Is Better FFmpeg 6.0 Encoder: libx265 - Scenario: Live a b c 10 20 30 40 50 SE +/- 0.15, N = 3 42.02 42.21 42.67 1. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma
Timed Linux Kernel Compilation Build: allmodconfig OpenBenchmarking.org Seconds, Fewer Is Better Timed Linux Kernel Compilation 6.1 Build: allmodconfig a b c 300 600 900 1200 1500 SE +/- 2.13, N = 3 1605.97 1581.70 1591.76
OpenVINO Model: Machine Translation EN To DE FP16 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2022.3 Model: Machine Translation EN To DE FP16 - Device: CPU a b c 5 10 15 20 25 SE +/- 0.09, N = 3 21.68 21.87 21.54 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared
FFmpeg Encoder: libx265 - Scenario: Live OpenBenchmarking.org FPS, More Is Better FFmpeg 6.0 Encoder: libx265 - Scenario: Live a b c 30 60 90 120 150 SE +/- 0.43, N = 3 120.17 119.65 118.36 1. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma
CockroachDB Workload: KV, 95% Reads - Concurrency: 256 OpenBenchmarking.org ops/s, More Is Better CockroachDB 22.2 Workload: KV, 95% Reads - Concurrency: 256 a b c 11K 22K 33K 44K 55K SE +/- 168.75, N = 3 49613.5 49024.0 49764.2
oneDNN Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.0 Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPU a b c 900 1800 2700 3600 4500 SE +/- 5.86, N = 3 4334.97 4270.75 4291.98 MIN: 4122.67 MIN: 4043.43 MIN: 4067.51 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl
Cpuminer-Opt Algorithm: Magi OpenBenchmarking.org kH/s, More Is Better Cpuminer-Opt 3.20.3 Algorithm: Magi a b c 70 140 210 280 350 SE +/- 2.70, N = 3 331.49 327.09 326.58 1. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
OpenVKL Benchmark: vklBenchmark Scalar OpenBenchmarking.org Items / Sec, More Is Better OpenVKL 1.3.1 Benchmark: vklBenchmark Scalar a b c 15 30 45 60 75 SE +/- 0.33, N = 3 68 69 68 MIN: 7 / MAX: 1212 MIN: 7 / MAX: 1201 MIN: 7 / MAX: 1202
JPEG XL libjxl Input: JPEG - Quality: 100 OpenBenchmarking.org MP/s, More Is Better JPEG XL libjxl 0.7 Input: JPEG - Quality: 100 a b c 0.1553 0.3106 0.4659 0.6212 0.7765 SE +/- 0.00, N = 3 0.68 0.69 0.69 1. (CXX) g++ options: -fno-rtti -funwind-tables -O3 -O2 -fPIE -pie -lm -latomic
JPEG XL libjxl Input: PNG - Quality: 100 OpenBenchmarking.org MP/s, More Is Better JPEG XL libjxl 0.7 Input: PNG - Quality: 100 a b c 0.1575 0.315 0.4725 0.63 0.7875 SE +/- 0.00, N = 3 0.69 0.69 0.70 1. (CXX) g++ options: -fno-rtti -funwind-tables -O3 -O2 -fPIE -pie -lm -latomic
OpenRadioss Model: Rubber O-Ring Seal Installation OpenBenchmarking.org Seconds, Fewer Is Better OpenRadioss 2022.10.13 Model: Rubber O-Ring Seal Installation a b c 50 100 150 200 250 SE +/- 1.23, N = 3 236.87 233.55 235.09
Neural Magic DeepSparse Model: CV Detection, YOLOv5s COCO - Scenario: Synchronous Single-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.3.2 Model: CV Detection, YOLOv5s COCO - Scenario: Synchronous Single-Stream a b c 8 16 24 32 40 SE +/- 0.33, N = 12 32.73 32.29 32.28
RocksDB Test: Read Random Write Random OpenBenchmarking.org Op/s, More Is Better RocksDB 7.9.2 Test: Read Random Write Random a b c 300K 600K 900K 1200K 1500K SE +/- 6061.26, N = 3 1546655 1562812 1568201 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
CockroachDB Workload: KV, 10% Reads - Concurrency: 256 OpenBenchmarking.org ops/s, More Is Better CockroachDB 22.2 Workload: KV, 10% Reads - Concurrency: 256 a b c 4K 8K 12K 16K 20K SE +/- 126.23, N = 3 17827.6 17639.6 17585.4
VVenC Video Input: Bosphorus 1080p - Video Preset: Fast OpenBenchmarking.org Frames Per Second, More Is Better VVenC 1.7 Video Input: Bosphorus 1080p - Video Preset: Fast a b c 2 4 6 8 10 SE +/- 0.014, N = 3 7.977 8.085 8.020 1. (CXX) g++ options: -O3 -flto -fno-fat-lto-objects -flto=auto
Zstd Compression Compression Level: 3 - Compression Speed OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.5.4 Compression Level: 3 - Compression Speed a b c 300 600 900 1200 1500 SE +/- 1.71, N = 3 1567.8 1588.6 1583.6 1. (CC) gcc options: -O3 -pthread -lz -llzma -llz4
Cpuminer-Opt Algorithm: Myriad-Groestl OpenBenchmarking.org kH/s, More Is Better Cpuminer-Opt 3.20.3 Algorithm: Myriad-Groestl a b c 2K 4K 6K 8K 10K SE +/- 68.39, N = 3 11237 11090 11100 1. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
uvg266 Video Input: Bosphorus 4K - Video Preset: Medium OpenBenchmarking.org Frames Per Second, More Is Better uvg266 0.4.1 Video Input: Bosphorus 4K - Video Preset: Medium a b c 1.044 2.088 3.132 4.176 5.22 SE +/- 0.01, N = 3 4.58 4.64 4.62
VP9 libvpx Encoding Speed: Speed 5 - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better VP9 libvpx Encoding 1.13 Speed: Speed 5 - Input: Bosphorus 1080p a b c 8 16 24 32 40 SE +/- 0.02, N = 3 32.75 32.33 32.38 1. (CXX) g++ options: -m64 -lm -lpthread -O3 -fPIC -U_FORTIFY_SOURCE -std=gnu++11
Neural Magic DeepSparse Model: CV Detection, YOLOv5s COCO - Scenario: Synchronous Single-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.3.2 Model: CV Detection, YOLOv5s COCO - Scenario: Synchronous Single-Stream a b c 7 14 21 28 35 SE +/- 0.28, N = 12 30.57 30.96 30.97
Stress-NG Test: Glibc Qsort Data Sorting OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.15.04 Test: Glibc Qsort Data Sorting a b c 20 40 60 80 100 SE +/- 0.60, N = 3 101.42 102.53 102.73 1. (CC) gcc options: -std=gnu99 -O2 -lm -lapparmor -latomic -lc -lcrypt -ldl -lEGL -lGLESv2 -ljpeg -lrt -lsctp -lz -pthread
OpenVINO Model: Person Detection FP32 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2022.3 Model: Person Detection FP32 - Device: CPU a b c 700 1400 2100 2800 3500 SE +/- 29.12, N = 3 3438.18 3394.57 3413.87 MIN: 3203.29 / MAX: 4311.69 MIN: 3178.76 / MAX: 3780.74 MIN: 3197.21 / MAX: 4433.43 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared
Neural Magic DeepSparse Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.3.2 Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Stream a b c 4 8 12 16 20 SE +/- 0.17, N = 3 15.57 15.37 15.38
Neural Magic DeepSparse Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.3.2 Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Stream a b c 15 30 45 60 75 SE +/- 0.70, N = 3 64.23 65.03 64.99
SVT-AV1 Encoder Mode: Preset 8 - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.4 Encoder Mode: Preset 8 - Input: Bosphorus 4K a b c 7 14 21 28 35 SE +/- 0.22, N = 3 27.44 27.78 27.50 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
Kvazaar Video Input: Bosphorus 1080p - Video Preset: Ultra Fast OpenBenchmarking.org Frames Per Second, More Is Better Kvazaar 2.2 Video Input: Bosphorus 1080p - Video Preset: Ultra Fast a b c 30 60 90 120 150 SE +/- 0.14, N = 3 123.26 121.82 123.33 1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
nginx Connections: 100 OpenBenchmarking.org Requests Per Second, More Is Better nginx 1.23.2 Connections: 100 a b c 15K 30K 45K 60K 75K SE +/- 335.89, N = 3 67993.52 68835.78 68707.49 1. (CC) gcc options: -lluajit-5.1 -lm -lssl -lcrypto -lpthread -ldl -std=c99 -O2
oneDNN Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.0 Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPU a b c 900 1800 2700 3600 4500 SE +/- 2.56, N = 3 4341.92 4289.21 4303.62 MIN: 4124.68 MIN: 4045.19 MIN: 4079.69 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl
Stargate Digital Audio Workstation Sample Rate: 480000 - Buffer Size: 512 OpenBenchmarking.org Render Ratio, More Is Better Stargate Digital Audio Workstation 22.11.5 Sample Rate: 480000 - Buffer Size: 512 a b c 0.5905 1.181 1.7715 2.362 2.9525 SE +/- 0.002482, N = 3 2.624567 2.593242 2.602950 1. (CXX) g++ options: -lpthread -lsndfile -lm -O3 -march=native -ffast-math -funroll-loops -fstrength-reduce -fstrict-aliasing -finline-functions
Blender Blend File: BMW27 - Compute: CPU-Only OpenBenchmarking.org Seconds, Fewer Is Better Blender 3.4 Blend File: BMW27 - Compute: CPU-Only a b c 40 80 120 160 200 SE +/- 1.22, N = 3 172.01 169.97 169.98
Neural Magic DeepSparse Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.3.2 Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Stream a b c 1.2296 2.4592 3.6888 4.9184 6.148 SE +/- 0.0157, N = 3 5.4650 5.4027 5.4023
Neural Magic DeepSparse Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.3.2 Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Stream a b c 40 80 120 160 200 SE +/- 0.52, N = 3 182.98 185.09 185.10
OpenVINO Model: Person Detection FP16 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2022.3 Model: Person Detection FP16 - Device: CPU a b c 700 1400 2100 2800 3500 SE +/- 16.56, N = 3 3384.14 3363.57 3402.11 MIN: 3150.48 / MAX: 4797.77 MIN: 3197.76 / MAX: 3701.88 MIN: 3157.9 / MAX: 5910.28 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared
OpenVINO Model: Face Detection FP16 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2022.3 Model: Face Detection FP16 - Device: CPU a b c 0.3983 0.7966 1.1949 1.5932 1.9915 SE +/- 0.02, N = 3 1.75 1.77 1.75 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared
libavif avifenc Encoder Speed: 6 OpenBenchmarking.org Seconds, Fewer Is Better libavif avifenc 0.11 Encoder Speed: 6 a b c 3 6 9 12 15 SE +/- 0.071, N = 3 9.175 9.277 9.268 1. (CXX) g++ options: -O3 -fPIC -lm
Stargate Digital Audio Workstation Sample Rate: 96000 - Buffer Size: 1024 OpenBenchmarking.org Render Ratio, More Is Better Stargate Digital Audio Workstation 22.11.5 Sample Rate: 96000 - Buffer Size: 1024 a b c 0.4661 0.9322 1.3983 1.8644 2.3305 SE +/- 0.001510, N = 3 2.071669 2.048931 2.052660 1. (CXX) g++ options: -lpthread -lsndfile -lm -O3 -march=native -ffast-math -funroll-loops -fstrength-reduce -fstrict-aliasing -finline-functions
AOM AV1 Encoder Mode: Speed 6 Two-Pass - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.6 Encoder Mode: Speed 6 Two-Pass - Input: Bosphorus 4K a b c 3 6 9 12 15 SE +/- 0.03, N = 3 9.11 9.15 9.21 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm
OpenVINO Model: Weld Porosity Detection FP16-INT8 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2022.3 Model: Weld Porosity Detection FP16-INT8 - Device: CPU a b c 2 4 6 8 10 SE +/- 0.04, N = 3 8.41 8.32 8.35 MIN: 7.49 / MAX: 16.85 MIN: 7.49 / MAX: 14.34 MIN: 7.49 / MAX: 38.94 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared
OpenVINO Model: Weld Porosity Detection FP16 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2022.3 Model: Weld Porosity Detection FP16 - Device: CPU a b c 40 80 120 160 200 SE +/- 0.88, N = 3 188.17 190.20 189.32 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared
OpenVINO Model: Weld Porosity Detection FP16 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2022.3 Model: Weld Porosity Detection FP16 - Device: CPU a b c 7 14 21 28 35 SE +/- 0.15, N = 3 31.87 31.53 31.68 MIN: 28.47 / MAX: 39.41 MIN: 28.51 / MAX: 38.58 MIN: 28.34 / MAX: 39.14 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared
OpenVINO Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2022.3 Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU a b c 0.2138 0.4276 0.6414 0.8552 1.069 SE +/- 0.00, N = 3 0.95 0.94 0.94 MIN: 0.85 / MAX: 7.32 MIN: 0.85 / MAX: 6.61 MIN: 0.84 / MAX: 7.1 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared
Neural Magic DeepSparse Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Synchronous Single-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.3.2 Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Synchronous Single-Stream a b c 30 60 90 120 150 SE +/- 0.41, N = 3 125.27 123.97 123.95
Neural Magic DeepSparse Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Synchronous Single-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.3.2 Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Synchronous Single-Stream a b c 2 4 6 8 10 SE +/- 0.0263, N = 3 7.9821 8.0658 8.0666
AOM AV1 Encoder Mode: Speed 8 Realtime - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.6 Encoder Mode: Speed 8 Realtime - Input: Bosphorus 1080p a b c 30 60 90 120 150 SE +/- 1.01, N = 11 139.13 139.06 140.47 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm
OpenVINO Model: Weld Porosity Detection FP16-INT8 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2022.3 Model: Weld Porosity Detection FP16-INT8 - Device: CPU a b c 160 320 480 640 800 SE +/- 3.68, N = 3 712.70 719.91 717.70 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared
Zstd Compression Compression Level: 8, Long Mode - Compression Speed OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.5.4 Compression Level: 8, Long Mode - Compression Speed a b c 40 80 120 160 200 SE +/- 0.15, N = 3 198.4 199.8 200.4 1. (CC) gcc options: -O3 -pthread -lz -llzma -llz4
CockroachDB Workload: KV, 50% Reads - Concurrency: 512 OpenBenchmarking.org ops/s, More Is Better CockroachDB 22.2 Workload: KV, 50% Reads - Concurrency: 512 a b c 7K 14K 21K 28K 35K SE +/- 338.62, N = 3 32781.2 32901.1 32572.9
Stress-NG Test: NUMA OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.15.04 Test: NUMA a b c 50 100 150 200 250 SE +/- 0.70, N = 3 244.13 246.58 245.00 1. (CC) gcc options: -std=gnu99 -O2 -lm -lapparmor -latomic -lc -lcrypt -ldl -lEGL -lGLESv2 -ljpeg -lrt -lsctp -lz -pthread
OpenRadioss Model: INIVOL and Fluid Structure Interaction Drop Container OpenBenchmarking.org Seconds, Fewer Is Better OpenRadioss 2022.10.13 Model: INIVOL and Fluid Structure Interaction Drop Container a b c 200 400 600 800 1000 SE +/- 5.89, N = 3 862.76 855.12 854.21
Stargate Digital Audio Workstation Sample Rate: 480000 - Buffer Size: 1024 OpenBenchmarking.org Render Ratio, More Is Better Stargate Digital Audio Workstation 22.11.5 Sample Rate: 480000 - Buffer Size: 1024 a b c 0.6174 1.2348 1.8522 2.4696 3.087 SE +/- 0.003205, N = 3 2.743784 2.722846 2.717116 1. (CXX) g++ options: -lpthread -lsndfile -lm -O3 -march=native -ffast-math -funroll-loops -fstrength-reduce -fstrict-aliasing -finline-functions
Timed Linux Kernel Compilation Build: defconfig OpenBenchmarking.org Seconds, Fewer Is Better Timed Linux Kernel Compilation 6.1 Build: defconfig a b c 30 60 90 120 150 SE +/- 1.00, N = 8 117.65 117.84 118.80
oneDNN Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.0 Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPU a b c 5 10 15 20 25 SE +/- 0.03, N = 3 18.28 18.41 18.23 MIN: 17.89 MIN: 18.02 MIN: 17.93 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl
Cpuminer-Opt Algorithm: Deepcoin OpenBenchmarking.org kH/s, More Is Better Cpuminer-Opt 3.20.3 Algorithm: Deepcoin a b c 1400 2800 4200 5600 7000 SE +/- 12.35, N = 3 6392.10 6428.90 6368.98 1. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
SVT-AV1 Encoder Mode: Preset 4 - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.4 Encoder Mode: Preset 4 - Input: Bosphorus 1080p a b c 2 4 6 8 10 SE +/- 0.018, N = 3 7.737 7.809 7.750 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
Embree Binary: Pathtracer - Model: Asian Dragon OpenBenchmarking.org Frames Per Second, More Is Better Embree 4.0 Binary: Pathtracer - Model: Asian Dragon a b c 3 6 9 12 15 SE +/- 0.0065, N = 3 9.6958 9.7857 9.7544 MIN: 9.6 / MAX: 9.92 MIN: 9.73 / MAX: 9.93 MIN: 9.7 / MAX: 9.87
RocksDB Test: Read While Writing OpenBenchmarking.org Op/s, More Is Better RocksDB 7.9.2 Test: Read While Writing a b c 300K 600K 900K 1200K 1500K SE +/- 18612.51, N = 3 1518515 1531157 1532546 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
nginx Connections: 200 OpenBenchmarking.org Requests Per Second, More Is Better nginx 1.23.2 Connections: 200 a b c 13K 26K 39K 52K 65K SE +/- 149.19, N = 3 61096.58 61654.77 61396.93 1. (CC) gcc options: -lluajit-5.1 -lm -lssl -lcrypto -lpthread -ldl -std=c99 -O2
OpenVINO Model: Person Vehicle Bike Detection FP16 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2022.3 Model: Person Vehicle Bike Detection FP16 - Device: CPU a b c 60 120 180 240 300 SE +/- 1.32, N = 3 276.78 279.30 278.20 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared
OpenVINO Model: Person Vehicle Bike Detection FP16 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2022.3 Model: Person Vehicle Bike Detection FP16 - Device: CPU a b c 4 8 12 16 20 SE +/- 0.07, N = 3 14.44 14.31 14.37 MIN: 12.82 / MAX: 32.76 MIN: 12.84 / MAX: 26.05 MIN: 12.83 / MAX: 26.08 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared
TensorFlow Device: CPU - Batch Size: 16 - Model: AlexNet OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.10 Device: CPU - Batch Size: 16 - Model: AlexNet a b c 14 28 42 56 70 SE +/- 0.10, N = 3 60.81 61.24 60.69
OpenVINO Model: Person Detection FP32 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2022.3 Model: Person Detection FP32 - Device: CPU a b c 0.261 0.522 0.783 1.044 1.305 SE +/- 0.01, N = 3 1.15 1.16 1.16 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared
FFmpeg Encoder: libx264 - Scenario: Platform OpenBenchmarking.org Seconds, Fewer Is Better FFmpeg 6.0 Encoder: libx264 - Scenario: Platform a b c 30 60 90 120 150 SE +/- 0.75, N = 3 145.95 146.92 145.67 1. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma
Zstd Compression Compression Level: 19, Long Mode - Compression Speed OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.5.4 Compression Level: 19, Long Mode - Compression Speed a b c 2 4 6 8 10 SE +/- 0.01, N = 3 7.00 7.06 7.02 1. (CC) gcc options: -O3 -pthread -lz -llzma -llz4
FFmpeg Encoder: libx264 - Scenario: Platform OpenBenchmarking.org FPS, More Is Better FFmpeg 6.0 Encoder: libx264 - Scenario: Platform a b c 12 24 36 48 60 SE +/- 0.27, N = 3 51.90 51.56 52.00 1. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma
TensorFlow Device: CPU - Batch Size: 256 - Model: AlexNet OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.10 Device: CPU - Batch Size: 256 - Model: AlexNet a b c 20 40 60 80 100 SE +/- 0.09, N = 3 107.91 108.69 108.83
nginx Connections: 1000 OpenBenchmarking.org Requests Per Second, More Is Better nginx 1.23.2 Connections: 1000 a b c 9K 18K 27K 36K 45K SE +/- 203.43, N = 3 41663.17 42015.72 42016.88 1. (CC) gcc options: -lluajit-5.1 -lm -lssl -lcrypto -lpthread -ldl -std=c99 -O2
Stargate Digital Audio Workstation Sample Rate: 192000 - Buffer Size: 1024 OpenBenchmarking.org Render Ratio, More Is Better Stargate Digital Audio Workstation 22.11.5 Sample Rate: 192000 - Buffer Size: 1024 a b c 0.3147 0.6294 0.9441 1.2588 1.5735 SE +/- 0.005117, N = 3 1.398663 1.387099 1.392746 1. (CXX) g++ options: -lpthread -lsndfile -lm -O3 -march=native -ffast-math -funroll-loops -fstrength-reduce -fstrict-aliasing -finline-functions
OpenVKL Benchmark: vklBenchmark ISPC OpenBenchmarking.org Items / Sec, More Is Better OpenVKL 1.3.1 Benchmark: vklBenchmark ISPC a b c 30 60 90 120 150 SE +/- 0.67, N = 3 120 120 121 MIN: 15 / MAX: 1750 MIN: 15 / MAX: 1749 MIN: 15 / MAX: 1739
AOM AV1 Encoder Mode: Speed 9 Realtime - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.6 Encoder Mode: Speed 9 Realtime - Input: Bosphorus 4K a b c 13 26 39 52 65 SE +/- 0.04, N = 3 57.99 58.45 58.38 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm
Stress-NG Test: Malloc OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.15.04 Test: Malloc a b c 1.1M 2.2M 3.3M 4.4M 5.5M SE +/- 19639.79, N = 3 5226456.99 5241054.32 5200128.82 1. (CC) gcc options: -std=gnu99 -O2 -lm -lapparmor -latomic -lc -lcrypt -ldl -lEGL -lGLESv2 -ljpeg -lrt -lsctp -lz -pthread
OpenVINO Model: Face Detection FP16 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2022.3 Model: Face Detection FP16 - Device: CPU a b c 500 1000 1500 2000 2500 SE +/- 12.95, N = 3 2257.17 2239.72 2256.40 MIN: 2132.88 / MAX: 3216.45 MIN: 2149.54 / MAX: 2500.68 MIN: 2134.57 / MAX: 2467.9 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared
Scikit-Learn Benchmark: TSNE MNIST Dataset OpenBenchmarking.org Seconds, Fewer Is Better Scikit-Learn 1.1.3 Benchmark: TSNE MNIST Dataset a b c 6 12 18 24 30 SE +/- 0.22, N = 3 26.91 26.71 26.86
Scikit-Learn Benchmark: MNIST Dataset OpenBenchmarking.org Seconds, Fewer Is Better Scikit-Learn 1.1.3 Benchmark: MNIST Dataset a b c 20 40 60 80 100 SE +/- 0.23, N = 3 90.15 90.82 90.84
Embree Binary: Pathtracer ISPC - Model: Asian Dragon OpenBenchmarking.org Frames Per Second, More Is Better Embree 4.0 Binary: Pathtracer ISPC - Model: Asian Dragon a b c 3 6 9 12 15 SE +/- 0.03, N = 3 11.06 11.14 11.11 MIN: 10.93 / MAX: 11.31 MIN: 11.05 / MAX: 11.33 MIN: 11.03 / MAX: 11.35
uvg266 Video Input: Bosphorus 1080p - Video Preset: Ultra Fast OpenBenchmarking.org Frames Per Second, More Is Better uvg266 0.4.1 Video Input: Bosphorus 1080p - Video Preset: Ultra Fast a b c 20 40 60 80 100 SE +/- 0.06, N = 3 80.01 79.81 79.41
libavif avifenc Encoder Speed: 0 OpenBenchmarking.org Seconds, Fewer Is Better libavif avifenc 0.11 Encoder Speed: 0 a b c 40 80 120 160 200 SE +/- 0.94, N = 3 195.07 193.63 195.07 1. (CXX) g++ options: -O3 -fPIC -lm
miniBUDE Implementation: OpenMP - Input Deck: BM2 OpenBenchmarking.org GFInst/s, More Is Better miniBUDE 20210901 Implementation: OpenMP - Input Deck: BM2 a b c 50 100 150 200 250 SE +/- 0.41, N = 3 243.66 245.47 245.23 1. (CC) gcc options: -std=c99 -Ofast -ffast-math -fopenmp -march=native -lm
miniBUDE Implementation: OpenMP - Input Deck: BM2 OpenBenchmarking.org Billion Interactions/s, More Is Better miniBUDE 20210901 Implementation: OpenMP - Input Deck: BM2 a b c 3 6 9 12 15 SE +/- 0.016, N = 3 9.747 9.819 9.809 1. (CC) gcc options: -std=c99 -Ofast -ffast-math -fopenmp -march=native -lm
CockroachDB Workload: MoVR - Concurrency: 1024 OpenBenchmarking.org ops/s, More Is Better CockroachDB 22.2 Workload: MoVR - Concurrency: 1024 a b c 40 80 120 160 200 SE +/- 0.06, N = 3 177.4 177.4 176.1
oneDNN Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.0 Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPU a b c 500 1000 1500 2000 2500 SE +/- 22.77, N = 3 2406.13 2394.33 2388.51 MIN: 2255.86 MIN: 2261.91 MIN: 2252.37 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl
AOM AV1 Encoder Mode: Speed 6 Realtime - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.6 Encoder Mode: Speed 6 Realtime - Input: Bosphorus 4K a b c 12 24 36 48 60 SE +/- 0.37, N = 14 55.33 54.93 55.31 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm
AOM AV1 Encoder Mode: Speed 8 Realtime - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.6 Encoder Mode: Speed 8 Realtime - Input: Bosphorus 4K a b c 10 20 30 40 50 SE +/- 0.05, N = 3 45.87 46.20 46.08 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm
Cpuminer-Opt Algorithm: scrypt OpenBenchmarking.org kH/s, More Is Better Cpuminer-Opt 3.20.3 Algorithm: scrypt a b c 20 40 60 80 100 SE +/- 0.41, N = 3 110.87 111.65 111.66 1. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
TensorFlow Device: CPU - Batch Size: 64 - Model: AlexNet OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.10 Device: CPU - Batch Size: 64 - Model: AlexNet a b c 20 40 60 80 100 SE +/- 0.49, N = 3 88.60 88.45 89.08
Stress-NG Test: Memory Copying OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.15.04 Test: Memory Copying a b c 500 1000 1500 2000 2500 SE +/- 14.39, N = 3 2301.69 2295.12 2285.43 1. (CC) gcc options: -std=gnu99 -O2 -lm -lapparmor -latomic -lc -lcrypt -ldl -lEGL -lGLESv2 -ljpeg -lrt -lsctp -lz -pthread
VP9 libvpx Encoding Speed: Speed 0 - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better VP9 libvpx Encoding 1.13 Speed: Speed 0 - Input: Bosphorus 4K a b c 1.296 2.592 3.888 5.184 6.48 SE +/- 0.02, N = 3 5.76 5.72 5.73 1. (CXX) g++ options: -m64 -lm -lpthread -O3 -fPIC -U_FORTIFY_SOURCE -std=gnu++11
BRL-CAD VGR Performance Metric OpenBenchmarking.org VGR Performance Metric, More Is Better BRL-CAD 7.34 VGR Performance Metric a b c 30K 60K 90K 120K 150K 132931 132058 132368 1. (CXX) g++ options: -std=c++14 -pipe -fvisibility=hidden -fno-strict-aliasing -fno-common -fexceptions -ftemplate-depth-128 -m64 -ggdb3 -O3 -fipa-pta -fstrength-reduce -finline-functions -flto -ltcl8.6 -lregex_brl -lz_brl -lnetpbm -ldl -lm -ltk8.6
TensorFlow Device: CPU - Batch Size: 32 - Model: AlexNet OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.10 Device: CPU - Batch Size: 32 - Model: AlexNet a b c 20 40 60 80 100 SE +/- 0.36, N = 3 77.95 77.80 77.44
Stargate Digital Audio Workstation Sample Rate: 44100 - Buffer Size: 1024 OpenBenchmarking.org Render Ratio, More Is Better Stargate Digital Audio Workstation 22.11.5 Sample Rate: 44100 - Buffer Size: 1024 a b c 0.6087 1.2174 1.8261 2.4348 3.0435 SE +/- 0.000534, N = 3 2.705122 2.697438 2.687449 1. (CXX) g++ options: -lpthread -lsndfile -lm -O3 -march=native -ffast-math -funroll-loops -fstrength-reduce -fstrict-aliasing -finline-functions
Stargate Digital Audio Workstation Sample Rate: 96000 - Buffer Size: 512 OpenBenchmarking.org Render Ratio, More Is Better Stargate Digital Audio Workstation 22.11.5 Sample Rate: 96000 - Buffer Size: 512 a b c 0.4345 0.869 1.3035 1.738 2.1725 SE +/- 0.000948, N = 3 1.930960 1.918443 1.923352 1. (CXX) g++ options: -lpthread -lsndfile -lm -O3 -march=native -ffast-math -funroll-loops -fstrength-reduce -fstrict-aliasing -finline-functions
OpenRadioss Model: Bird Strike on Windshield OpenBenchmarking.org Seconds, Fewer Is Better OpenRadioss 2022.10.13 Model: Bird Strike on Windshield a b c 80 160 240 320 400 SE +/- 1.35, N = 3 378.02 375.59 376.26
Stress-NG Test: SENDFILE OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.15.04 Test: SENDFILE a b c 40K 80K 120K 160K 200K SE +/- 184.17, N = 3 177365.84 176973.24 178115.64 1. (CC) gcc options: -std=gnu99 -O2 -lm -lapparmor -latomic -lc -lcrypt -ldl -lEGL -lGLESv2 -ljpeg -lrt -lsctp -lz -pthread
OpenRadioss Model: Cell Phone Drop Test OpenBenchmarking.org Seconds, Fewer Is Better OpenRadioss 2022.10.13 Model: Cell Phone Drop Test a b c 30 60 90 120 150 SE +/- 0.15, N = 3 141.00 141.91 141.10
OpenVINO Model: Vehicle Detection FP16-INT8 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2022.3 Model: Vehicle Detection FP16-INT8 - Device: CPU a b c 80 160 240 320 400 SE +/- 1.63, N = 3 348.49 347.83 346.34 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared
Embree Binary: Pathtracer ISPC - Model: Asian Dragon Obj OpenBenchmarking.org Frames Per Second, More Is Better Embree 4.0 Binary: Pathtracer ISPC - Model: Asian Dragon Obj a b c 3 6 9 12 15 SE +/- 0.0123, N = 3 9.5706 9.6296 9.5837 MIN: 9.47 / MAX: 9.79 MIN: 9.56 / MAX: 9.84 MIN: 9.5 / MAX: 9.8
FFmpeg Encoder: libx265 - Scenario: Upload OpenBenchmarking.org FPS, More Is Better FFmpeg 6.0 Encoder: libx265 - Scenario: Upload a b c 5 10 15 20 25 SE +/- 0.03, N = 3 21.20 21.11 21.24 1. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma
TensorFlow Device: CPU - Batch Size: 64 - Model: GoogLeNet OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.10 Device: CPU - Batch Size: 64 - Model: GoogLeNet a b c 9 18 27 36 45 SE +/- 0.09, N = 3 41.05 40.80 40.83
FFmpeg Encoder: libx265 - Scenario: Upload OpenBenchmarking.org Seconds, Fewer Is Better FFmpeg 6.0 Encoder: libx265 - Scenario: Upload a b c 30 60 90 120 150 SE +/- 0.17, N = 3 119.13 119.63 118.90 1. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma
OpenVINO Model: Vehicle Detection FP16-INT8 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2022.3 Model: Vehicle Detection FP16-INT8 - Device: CPU a b c 3 6 9 12 15 SE +/- 0.05, N = 3 11.47 11.49 11.54 MIN: 10.23 / MAX: 55.04 MIN: 10.24 / MAX: 17.75 MIN: 10.23 / MAX: 58.55 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared
Neural Magic DeepSparse Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Synchronous Single-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.3.2 Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Synchronous Single-Stream a b c 5 10 15 20 25 SE +/- 0.08, N = 3 20.33 20.39 20.26
Neural Magic DeepSparse Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Synchronous Single-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.3.2 Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Synchronous Single-Stream a b c 11 22 33 44 55 SE +/- 0.19, N = 3 49.18 49.03 49.33
TensorFlow Device: CPU - Batch Size: 32 - Model: GoogLeNet OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.10 Device: CPU - Batch Size: 32 - Model: GoogLeNet a b c 9 18 27 36 45 SE +/- 0.11, N = 3 40.17 40.32 40.08
OpenEMS Test: pyEMS Coupler OpenBenchmarking.org MCells/s, More Is Better OpenEMS 0.0.35-86 Test: pyEMS Coupler a b c 9 18 27 36 45 SE +/- 0.06, N = 3 39.72 39.86 39.95 1. (CXX) g++ options: -O3 -rdynamic -ltinyxml -lcrypto -lcurl -lpthread -lsz -lz -ldl -lm -lexpat
CockroachDB Workload: KV, 10% Reads - Concurrency: 1024 OpenBenchmarking.org ops/s, More Is Better CockroachDB 22.2 Workload: KV, 10% Reads - Concurrency: 1024 a b c 6K 12K 18K 24K 30K SE +/- 369.95, N = 3 26050.8 26158.4 26199.1
oneDNN Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.0 Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPU a b c 0.4526 0.9052 1.3578 1.8104 2.263 SE +/- 0.01841, N = 15 2.00020 2.01154 2.01050 MIN: 1.92 MIN: 2 MIN: 2 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl
uvg266 Video Input: Bosphorus 1080p - Video Preset: Super Fast OpenBenchmarking.org Frames Per Second, More Is Better uvg266 0.4.1 Video Input: Bosphorus 1080p - Video Preset: Super Fast a b c 15 30 45 60 75 SE +/- 0.36, N = 3 67.09 67.46 67.36
SVT-AV1 Encoder Mode: Preset 8 - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.4 Encoder Mode: Preset 8 - Input: Bosphorus 1080p a b c 20 40 60 80 100 SE +/- 0.56, N = 3 81.45 81.40 81.02 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
TensorFlow Device: CPU - Batch Size: 256 - Model: GoogLeNet OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.10 Device: CPU - Batch Size: 256 - Model: GoogLeNet a b c 10 20 30 40 50 SE +/- 0.04, N = 3 43.37 43.60 43.37
Xmrig Variant: Wownero - Hash Count: 1M OpenBenchmarking.org H/s, More Is Better Xmrig 6.18.1 Variant: Wownero - Hash Count: 1M a b c 1200 2400 3600 4800 6000 SE +/- 13.58, N = 3 5359.8 5362.5 5388.2 1. (CXX) g++ options: -fexceptions -fno-rtti -maes -O3 -Ofast -static-libgcc -static-libstdc++ -rdynamic -lssl -lcrypto -luv -lpthread -lrt -ldl -lhwloc
Neural Magic DeepSparse Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.3.2 Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Stream a b c 80 160 240 320 400 SE +/- 0.80, N = 3 371.27 371.97 373.24
Neural Magic DeepSparse Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.3.2 Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Stream a b c 2 4 6 8 10 SE +/- 0.0174, N = 3 8.0798 8.0647 8.0373
TensorFlow Device: CPU - Batch Size: 512 - Model: AlexNet OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.10 Device: CPU - Batch Size: 512 - Model: AlexNet a b c 30 60 90 120 150 SE +/- 0.47, N = 3 117.88 118.22 118.50
Neural Magic DeepSparse Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Stream OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.3.2 Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Stream a b c 40 80 120 160 200 SE +/- 0.43, N = 3 184.65 183.89 183.69
Neural Magic DeepSparse Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Stream OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.3.2 Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Stream a b c 1.2248 2.4496 3.6744 4.8992 6.124 SE +/- 0.0127, N = 3 5.4154 5.4379 5.4437
FFmpeg Encoder: libx264 - Scenario: Upload OpenBenchmarking.org FPS, More Is Better FFmpeg 6.0 Encoder: libx264 - Scenario: Upload a b c 3 6 9 12 15 SE +/- 0.02, N = 3 13.50 13.43 13.45 1. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma
PostgreSQL Scaling Factor: 100 - Clients: 500 - Mode: Read Only - Average Latency OpenBenchmarking.org ms, Fewer Is Better PostgreSQL 15 Scaling Factor: 100 - Clients: 500 - Mode: Read Only - Average Latency a b c 0.3557 0.7114 1.0671 1.4228 1.7785 SE +/- 0.012, N = 3 1.573 1.581 1.573 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
Zstd Compression Compression Level: 19, Long Mode - Decompression Speed OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.5.4 Compression Level: 19, Long Mode - Decompression Speed a b c 300 600 900 1200 1500 SE +/- 1.17, N = 3 1444.4 1451.7 1447.2 1. (CC) gcc options: -O3 -pthread -lz -llzma -llz4
PostgreSQL Scaling Factor: 100 - Clients: 500 - Mode: Read Only OpenBenchmarking.org TPS, More Is Better PostgreSQL 15 Scaling Factor: 100 - Clients: 500 - Mode: Read Only a b c 70K 140K 210K 280K 350K SE +/- 2326.54, N = 3 317872 316288 317863 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
FFmpeg Encoder: libx264 - Scenario: Upload OpenBenchmarking.org Seconds, Fewer Is Better FFmpeg 6.0 Encoder: libx264 - Scenario: Upload a b c 40 80 120 160 200 SE +/- 0.26, N = 3 187.09 188.02 187.76 1. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma
Zstd Compression Compression Level: 8 - Compression Speed OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.5.4 Compression Level: 8 - Compression Speed a b c 40 80 120 160 200 SE +/- 0.20, N = 3 202.6 203.6 203.6 1. (CC) gcc options: -O3 -pthread -lz -llzma -llz4
SVT-AV1 Encoder Mode: Preset 12 - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.4 Encoder Mode: Preset 12 - Input: Bosphorus 1080p a b c 80 160 240 320 400 SE +/- 1.08, N = 3 348.11 348.91 347.22 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
Stress-NG Test: Mutex OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.15.04 Test: Mutex a b c 900K 1800K 2700K 3600K 4500K SE +/- 2569.53, N = 3 4254720.23 4273551.98 4254389.29 1. (CC) gcc options: -std=gnu99 -O2 -lm -lapparmor -latomic -lc -lcrypt -ldl -lEGL -lGLESv2 -ljpeg -lrt -lsctp -lz -pthread
SVT-AV1 Encoder Mode: Preset 13 - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.4 Encoder Mode: Preset 13 - Input: Bosphorus 1080p a b c 90 180 270 360 450 SE +/- 0.84, N = 3 398.86 399.08 397.31 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
Blender Blend File: Pabellon Barcelona - Compute: CPU-Only OpenBenchmarking.org Seconds, Fewer Is Better Blender 3.4 Blend File: Pabellon Barcelona - Compute: CPU-Only a b c 130 260 390 520 650 SE +/- 0.41, N = 3 602.17 601.73 604.27
OpenVINO Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2022.3 Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU a b c 1400 2800 4200 5600 7000 SE +/- 19.43, N = 3 6331.01 6344.82 6357.31 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared
Kvazaar Video Input: Bosphorus 1080p - Video Preset: Very Fast OpenBenchmarking.org Frames Per Second, More Is Better Kvazaar 2.2 Video Input: Bosphorus 1080p - Video Preset: Very Fast a b c 20 40 60 80 100 SE +/- 0.07, N = 3 74.79 74.73 75.04 1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
Stargate Digital Audio Workstation Sample Rate: 192000 - Buffer Size: 512 OpenBenchmarking.org Render Ratio, More Is Better Stargate Digital Audio Workstation 22.11.5 Sample Rate: 192000 - Buffer Size: 512 a b c 0.2864 0.5728 0.8592 1.1456 1.432 SE +/- 0.003098, N = 3 1.272677 1.272057 1.267444 1. (CXX) g++ options: -lpthread -lsndfile -lm -O3 -march=native -ffast-math -funroll-loops -fstrength-reduce -fstrict-aliasing -finline-functions
Stress-NG Test: System V Message Passing OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.15.04 Test: System V Message Passing a b c 2M 4M 6M 8M 10M SE +/- 10695.76, N = 3 8216877.60 8225295.79 8192747.72 1. (CC) gcc options: -std=gnu99 -O2 -lm -lapparmor -latomic -lc -lcrypt -ldl -lEGL -lGLESv2 -ljpeg -lrt -lsctp -lz -pthread
AOM AV1 Encoder Mode: Speed 10 Realtime - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.6 Encoder Mode: Speed 10 Realtime - Input: Bosphorus 4K a b c 13 26 39 52 65 SE +/- 0.42, N = 12 58.76 58.66 58.53 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm
Blender Blend File: Barbershop - Compute: CPU-Only OpenBenchmarking.org Seconds, Fewer Is Better Blender 3.4 Blend File: Barbershop - Compute: CPU-Only a b c 400 800 1200 1600 2000 SE +/- 2.57, N = 3 1913.71 1918.11 1921.09
FFmpeg Encoder: libx265 - Scenario: Platform OpenBenchmarking.org FPS, More Is Better FFmpeg 6.0 Encoder: libx265 - Scenario: Platform a b c 10 20 30 40 50 SE +/- 0.03, N = 3 44.40 44.36 44.53 1. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma
FFmpeg Encoder: libx265 - Scenario: Platform OpenBenchmarking.org Seconds, Fewer Is Better FFmpeg 6.0 Encoder: libx265 - Scenario: Platform a b c 40 80 120 160 200 SE +/- 0.12, N = 3 170.61 170.76 170.11 1. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma
oneDNN Harness: Matrix Multiply Batch Shapes Transformer - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.0 Harness: Matrix Multiply Batch Shapes Transformer - Data Type: f32 - Engine: CPU a b c 0.8116 1.6232 2.4348 3.2464 4.058 SE +/- 0.00059, N = 3 3.59719 3.59364 3.60705 MIN: 3.53 MIN: 3.53 MIN: 3.54 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl
Zstd Compression Compression Level: 3, Long Mode - Compression Speed OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.5.4 Compression Level: 3, Long Mode - Compression Speed a b c 200 400 600 800 1000 SE +/- 6.47, N = 3 869.3 866.5 866.1 1. (CC) gcc options: -O3 -pthread -lz -llzma -llz4
Zstd Compression Compression Level: 3 - Decompression Speed OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.5.4 Compression Level: 3 - Decompression Speed a b c 300 600 900 1200 1500 SE +/- 0.86, N = 3 1592.6 1596.2 1598.4 1. (CC) gcc options: -O3 -pthread -lz -llzma -llz4
nginx Connections: 500 OpenBenchmarking.org Requests Per Second, More Is Better nginx 1.23.2 Connections: 500 a b c 11K 22K 33K 44K 55K SE +/- 61.89, N = 3 51922.48 51890.45 51737.26 1. (CC) gcc options: -lluajit-5.1 -lm -lssl -lcrypto -lpthread -ldl -std=c99 -O2
GROMACS Implementation: MPI CPU - Input: water_GMX50_bare OpenBenchmarking.org Ns Per Day, More Is Better GROMACS 2023 Implementation: MPI CPU - Input: water_GMX50_bare a b c 0.1917 0.3834 0.5751 0.7668 0.9585 SE +/- 0.003, N = 3 0.852 0.851 0.849 1. (CXX) g++ options: -O3
Stress-NG Test: Matrix Math OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.15.04 Test: Matrix Math a b c 10K 20K 30K 40K 50K SE +/- 69.96, N = 3 45892.79 46046.48 45978.84 1. (CC) gcc options: -std=gnu99 -O2 -lm -lapparmor -latomic -lc -lcrypt -ldl -lEGL -lGLESv2 -ljpeg -lrt -lsctp -lz -pthread
Stargate Digital Audio Workstation Sample Rate: 44100 - Buffer Size: 512 OpenBenchmarking.org Render Ratio, More Is Better Stargate Digital Audio Workstation 22.11.5 Sample Rate: 44100 - Buffer Size: 512 a b c 0.5802 1.1604 1.7406 2.3208 2.901 SE +/- 0.005177, N = 3 2.578599 2.570597 2.575363 1. (CXX) g++ options: -lpthread -lsndfile -lm -O3 -march=native -ffast-math -funroll-loops -fstrength-reduce -fstrict-aliasing -finline-functions
OpenRadioss Model: Bumper Beam OpenBenchmarking.org Seconds, Fewer Is Better OpenRadioss 2022.10.13 Model: Bumper Beam a b c 40 80 120 160 200 SE +/- 0.32, N = 3 187.49 187.53 188.06
CockroachDB Workload: KV, 95% Reads - Concurrency: 512 OpenBenchmarking.org ops/s, More Is Better CockroachDB 22.2 Workload: KV, 95% Reads - Concurrency: 512 a b c 9K 18K 27K 36K 45K SE +/- 83.04, N = 3 43281.7 43180.1 43303.9
Cpuminer-Opt Algorithm: Triple SHA-256, Onecoin OpenBenchmarking.org kH/s, More Is Better Cpuminer-Opt 3.20.3 Algorithm: Triple SHA-256, Onecoin a b c 20K 40K 60K 80K 100K SE +/- 108.37, N = 3 78157 77950 77940 1. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
Blender Blend File: Classroom - Compute: CPU-Only OpenBenchmarking.org Seconds, Fewer Is Better Blender 3.4 Blend File: Classroom - Compute: CPU-Only a b c 110 220 330 440 550 SE +/- 0.90, N = 3 493.25 491.93 492.05
Zstd Compression Compression Level: 19 - Decompression Speed OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.5.4 Compression Level: 19 - Decompression Speed a b c 300 600 900 1200 1500 SE +/- 0.83, N = 15 1516.3 1512.3 1515.1 1. (CC) gcc options: -O3 -pthread -lz -llzma -llz4
Zstd Compression Compression Level: 12 - Compression Speed OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.5.4 Compression Level: 12 - Compression Speed a b c 20 40 60 80 100 SE +/- 0.23, N = 3 77.1 77.2 77.3 1. (CC) gcc options: -O3 -pthread -lz -llzma -llz4
Kvazaar Video Input: Bosphorus 1080p - Video Preset: Super Fast OpenBenchmarking.org Frames Per Second, More Is Better Kvazaar 2.2 Video Input: Bosphorus 1080p - Video Preset: Super Fast a b c 20 40 60 80 100 SE +/- 0.19, N = 3 93.48 93.52 93.30 1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
CockroachDB Workload: KV, 50% Reads - Concurrency: 1024 OpenBenchmarking.org ops/s, More Is Better CockroachDB 22.2 Workload: KV, 50% Reads - Concurrency: 1024 a b c 7K 14K 21K 28K 35K SE +/- 65.26, N = 3 30338.7 30358.1 30286.7
Unvanquished Resolution: 1920 x 1080 - Effects Quality: High OpenBenchmarking.org Frames Per Second, More Is Better Unvanquished 0.54 Resolution: 1920 x 1080 - Effects Quality: High a b c 40 80 120 160 200 SE +/- 0.20, N = 3 170.8 171.1 170.7
Stress-NG Test: Zlib OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.15.04 Test: Zlib a b c 150 300 450 600 750 SE +/- 0.29, N = 3 717.35 717.62 716.14 1. (CC) gcc options: -std=gnu99 -O2 -lm -lapparmor -latomic -lc -lcrypt -ldl -lEGL -lGLESv2 -ljpeg -lrt -lsctp -lz -pthread
Unvanquished Resolution: 1920 x 1080 - Effects Quality: Ultra OpenBenchmarking.org Frames Per Second, More Is Better Unvanquished 0.54 Resolution: 1920 x 1080 - Effects Quality: Ultra a b c 20 40 60 80 100 SE +/- 0.03, N = 3 100.6 100.5 100.7
CockroachDB Workload: KV, 95% Reads - Concurrency: 1024 OpenBenchmarking.org ops/s, More Is Better CockroachDB 22.2 Workload: KV, 95% Reads - Concurrency: 1024 a b c 9K 18K 27K 36K 45K SE +/- 52.10, N = 3 40249.9 40176.2 40255.3
Zstd Compression Compression Level: 12 - Decompression Speed OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.5.4 Compression Level: 12 - Decompression Speed a b c 400 800 1200 1600 2000 SE +/- 3.74, N = 3 1758.9 1761.7 1762.2 1. (CC) gcc options: -O3 -pthread -lz -llzma -llz4
TensorFlow Device: CPU - Batch Size: 512 - Model: GoogLeNet OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.10 Device: CPU - Batch Size: 512 - Model: GoogLeNet a b c 10 20 30 40 50 SE +/- 0.04, N = 3 44.65 44.70 44.62
Kvazaar Video Input: Bosphorus 1080p - Video Preset: Medium OpenBenchmarking.org Frames Per Second, More Is Better Kvazaar 2.2 Video Input: Bosphorus 1080p - Video Preset: Medium a b c 8 16 24 32 40 SE +/- 0.14, N = 3 34.46 34.52 34.50 1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
Zstd Compression Compression Level: 8, Long Mode - Decompression Speed OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.5.4 Compression Level: 8, Long Mode - Decompression Speed a b c 400 800 1200 1600 2000 SE +/- 1.39, N = 3 1727.9 1725.8 1728.6 1. (CC) gcc options: -O3 -pthread -lz -llzma -llz4
OpenEMS Test: openEMS MSL_NotchFilter OpenBenchmarking.org MCells/s, More Is Better OpenEMS 0.0.35-86 Test: openEMS MSL_NotchFilter a b c 20 40 60 80 100 SE +/- 0.06, N = 3 98.88 98.72 98.77 1. (CXX) g++ options: -O3 -rdynamic -ltinyxml -lcrypto -lcurl -lpthread -lsz -lz -ldl -lm -lexpat
Scikit-Learn Benchmark: Sparse Random Projections, 100 Iterations OpenBenchmarking.org Seconds, Fewer Is Better Scikit-Learn 1.1.3 Benchmark: Sparse Random Projections, 100 Iterations a b c 30 60 90 120 150 SE +/- 0.14, N = 3 142.73 142.60 142.50
Cpuminer-Opt Algorithm: Quad SHA-256, Pyrite OpenBenchmarking.org kH/s, More Is Better Cpuminer-Opt 3.20.3 Algorithm: Quad SHA-256, Pyrite a b c 10K 20K 30K 40K 50K SE +/- 70.24, N = 3 48250 48310 48320 1. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
Blender Blend File: Fishy Cat - Compute: CPU-Only OpenBenchmarking.org Seconds, Fewer Is Better Blender 3.4 Blend File: Fishy Cat - Compute: CPU-Only a b c 50 100 150 200 250 SE +/- 0.25, N = 3 242.51 242.40 242.75
oneDNN Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.0 Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPU a b c 4 8 12 16 20 SE +/- 0.00, N = 3 16.59 16.61 16.59 MIN: 16.45 MIN: 16.47 MIN: 16.43 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl
Stress-NG Test: Semaphores OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.15.04 Test: Semaphores a b c 300K 600K 900K 1200K 1500K SE +/- 593.53, N = 3 1189258.32 1190334.27 1188758.84 1. (CC) gcc options: -std=gnu99 -O2 -lm -lapparmor -latomic -lc -lcrypt -ldl -lEGL -lGLESv2 -ljpeg -lrt -lsctp -lz -pthread
Stress-NG Test: Vector Math OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.15.04 Test: Vector Math a b c 9K 18K 27K 36K 45K SE +/- 3.69, N = 3 41733.97 41733.47 41779.98 1. (CC) gcc options: -std=gnu99 -O2 -lm -lapparmor -latomic -lc -lcrypt -ldl -lEGL -lGLESv2 -ljpeg -lrt -lsctp -lz -pthread
Zstd Compression Compression Level: 8 - Decompression Speed OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.5.4 Compression Level: 8 - Decompression Speed a b c 400 800 1200 1600 2000 SE +/- 0.97, N = 3 1732.4 1733.2 1734.3 1. (CC) gcc options: -O3 -pthread -lz -llzma -llz4
Stress-NG Test: Crypto OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.15.04 Test: Crypto a b c 3K 6K 9K 12K 15K SE +/- 2.58, N = 3 14276.39 14261.23 14271.88 1. (CC) gcc options: -std=gnu99 -O2 -lm -lapparmor -latomic -lc -lcrypt -ldl -lEGL -lGLESv2 -ljpeg -lrt -lsctp -lz -pthread
Stress-NG Test: Hash OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.15.04 Test: Hash a b c 300K 600K 900K 1200K 1500K SE +/- 854.18, N = 3 1548492.99 1549710.05 1548182.16 1. (CC) gcc options: -std=gnu99 -O2 -lm -lapparmor -latomic -lc -lcrypt -ldl -lEGL -lGLESv2 -ljpeg -lrt -lsctp -lz -pthread
Stress-NG Test: Poll OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.15.04 Test: Poll a b c 200K 400K 600K 800K 1000K SE +/- 379.65, N = 3 823762.13 823948.19 823174.05 1. (CC) gcc options: -std=gnu99 -O2 -lm -lapparmor -latomic -lc -lcrypt -ldl -lEGL -lGLESv2 -ljpeg -lrt -lsctp -lz -pthread
Zstd Compression Compression Level: 3, Long Mode - Decompression Speed OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.5.4 Compression Level: 3, Long Mode - Decompression Speed a b c 300 600 900 1200 1500 SE +/- 0.35, N = 3 1619.4 1618.7 1620.2 1. (CC) gcc options: -O3 -pthread -lz -llzma -llz4
Embree Binary: Pathtracer - Model: Asian Dragon Obj OpenBenchmarking.org Frames Per Second, More Is Better Embree 4.0 Binary: Pathtracer - Model: Asian Dragon Obj a b c 2 4 6 8 10 SE +/- 0.0103, N = 3 8.7102 8.7168 8.7124 MIN: 8.64 / MAX: 8.85 MIN: 8.66 / MAX: 8.83 MIN: 8.66 / MAX: 8.86
Stress-NG Test: Function Call OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.15.04 Test: Function Call a b c 11K 22K 33K 44K 55K SE +/- 1.32, N = 3 49787.62 49807.05 49784.19 1. (CC) gcc options: -std=gnu99 -O2 -lm -lapparmor -latomic -lc -lcrypt -ldl -lEGL -lGLESv2 -ljpeg -lrt -lsctp -lz -pthread
Unvanquished Resolution: 1920 x 1080 - Effects Quality: Medium OpenBenchmarking.org Frames Per Second, More Is Better Unvanquished 0.54 Resolution: 1920 x 1080 - Effects Quality: Medium a b c 50 100 150 200 250 SE +/- 0.09, N = 3 248.2 248.1 248.2
Stress-NG Test: CPU Stress OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.15.04 Test: CPU Stress a b c 4K 8K 12K 16K 20K SE +/- 32.25, N = 3 17781.86 17780.76 17782.21 1. (CC) gcc options: -std=gnu99 -O2 -lm -lapparmor -latomic -lc -lcrypt -ldl -lEGL -lGLESv2 -ljpeg -lrt -lsctp -lz -pthread
Stress-NG Test: x86_64 RdRand OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.15.04 Test: x86_64 RdRand a b c 20K 40K 60K 80K 100K SE +/- 0.57, N = 3 81909.45 81907.97 81907.39 1. (CC) gcc options: -std=gnu99 -O2 -lm -lapparmor -latomic -lc -lcrypt -ldl -lEGL -lGLESv2 -ljpeg -lrt -lsctp -lz -pthread
AOM AV1 Encoder Mode: Speed 4 Two-Pass - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.6 Encoder Mode: Speed 4 Two-Pass - Input: Bosphorus 1080p a b c 3 6 9 12 15 SE +/- 0.13, N = 3 13.31 13.31 13.31 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm
RocksDB Test: Random Fill OpenBenchmarking.org Op/s, More Is Better RocksDB 7.9.2 Test: Random Fill a b c 200K 400K 600K 800K 1000K SE +/- 20633.51, N = 15 846457 866381 1102439 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
Stress-NG Test: Context Switching OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.15.04 Test: Context Switching a b c 400K 800K 1200K 1600K 2000K SE +/- 48908.21, N = 15 1897936.07 1941869.46 1906264.57 1. (CC) gcc options: -std=gnu99 -O2 -lm -lapparmor -latomic -lc -lcrypt -ldl -lEGL -lGLESv2 -ljpeg -lrt -lsctp -lz -pthread
Stress-NG Test: Socket Activity OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.15.04 Test: Socket Activity a b c 2K 4K 6K 8K 10K SE +/- 146.72, N = 15 8703.54 9385.83 9379.73 1. (CC) gcc options: -std=gnu99 -O2 -lm -lapparmor -latomic -lc -lcrypt -ldl -lEGL -lGLESv2 -ljpeg -lrt -lsctp -lz -pthread
Stress-NG Test: CPU Cache OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.15.04 Test: CPU Cache a b c 20 40 60 80 100 SE +/- 2.33, N = 12 83.60 89.50 72.10 1. (CC) gcc options: -std=gnu99 -O2 -lm -lapparmor -latomic -lc -lcrypt -ldl -lEGL -lGLESv2 -ljpeg -lrt -lsctp -lz -pthread
Stress-NG Test: IO_uring OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.15.04 Test: IO_uring a b c 600 1200 1800 2400 3000 SE +/- 36.56, N = 15 1965.75 1723.13 2856.89 1. (CC) gcc options: -std=gnu99 -O2 -lm -lapparmor -latomic -lc -lcrypt -ldl -lEGL -lGLESv2 -ljpeg -lrt -lsctp -lz -pthread
Stress-NG Test: Atomic OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.15.04 Test: Atomic a b c 40 80 120 160 200 SE +/- 3.12, N = 15 146.11 145.01 162.65 1. (CC) gcc options: -std=gnu99 -O2 -lm -lapparmor -latomic -lc -lcrypt -ldl -lEGL -lGLESv2 -ljpeg -lrt -lsctp -lz -pthread
Stress-NG Test: MEMFD OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.15.04 Test: MEMFD a b c 13 26 39 52 65 SE +/- 3.98, N = 12 58.57 41.65 52.99 1. (CC) gcc options: -std=gnu99 -O2 -lm -lapparmor -latomic -lc -lcrypt -ldl -lEGL -lGLESv2 -ljpeg -lrt -lsctp -lz -pthread
Stress-NG Test: Futex OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.15.04 Test: Futex a b c 400K 800K 1200K 1600K 2000K SE +/- 41062.68, N = 15 1579624.88 1723742.38 1689762.38 1. (CC) gcc options: -std=gnu99 -O2 -lm -lapparmor -latomic -lc -lcrypt -ldl -lEGL -lGLESv2 -ljpeg -lrt -lsctp -lz -pthread
Stress-NG Test: MMAP OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.15.04 Test: MMAP a b c 20 40 60 80 100 SE +/- 2.50, N = 15 74.70 50.26 49.73 1. (CC) gcc options: -std=gnu99 -O2 -lm -lapparmor -latomic -lc -lcrypt -ldl -lEGL -lGLESv2 -ljpeg -lrt -lsctp -lz -pthread
PostgreSQL Scaling Factor: 100 - Clients: 500 - Mode: Read Write - Average Latency OpenBenchmarking.org ms, Fewer Is Better PostgreSQL 15 Scaling Factor: 100 - Clients: 500 - Mode: Read Write - Average Latency a b c 30 60 90 120 150 SE +/- 3.53, N = 12 113.08 103.71 82.83 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
PostgreSQL Scaling Factor: 100 - Clients: 500 - Mode: Read Write OpenBenchmarking.org TPS, More Is Better PostgreSQL 15 Scaling Factor: 100 - Clients: 500 - Mode: Read Write a b c 1300 2600 3900 5200 6500 SE +/- 146.05, N = 12 4472 4821 6036 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
PostgreSQL Scaling Factor: 100 - Clients: 250 - Mode: Read Write - Average Latency OpenBenchmarking.org ms, Fewer Is Better PostgreSQL 15 Scaling Factor: 100 - Clients: 250 - Mode: Read Write - Average Latency a b c 15 30 45 60 75 SE +/- 1.63, N = 12 60.80 68.07 41.63 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
PostgreSQL Scaling Factor: 100 - Clients: 250 - Mode: Read Write OpenBenchmarking.org TPS, More Is Better PostgreSQL 15 Scaling Factor: 100 - Clients: 250 - Mode: Read Write a b c 1300 2600 3900 5200 6500 SE +/- 122.04, N = 12 4148 3673 6005 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
PostgreSQL Scaling Factor: 100 - Clients: 100 - Mode: Read Write - Average Latency OpenBenchmarking.org ms, Fewer Is Better PostgreSQL 15 Scaling Factor: 100 - Clients: 100 - Mode: Read Write - Average Latency a b c 6 12 18 24 30 SE +/- 0.75, N = 12 24.55 23.64 19.60 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
PostgreSQL Scaling Factor: 100 - Clients: 100 - Mode: Read Write OpenBenchmarking.org TPS, More Is Better PostgreSQL 15 Scaling Factor: 100 - Clients: 100 - Mode: Read Write a b c 1100 2200 3300 4400 5500 SE +/- 122.37, N = 12 4114 4230 5102 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
KeyDB Test: LPOP - Parallel Connections: 100 OpenBenchmarking.org Requests Per Second, More Is Better KeyDB 6.3.2 Test: LPOP - Parallel Connections: 100 a b c 300K 600K 900K 1200K 1500K SE +/- 37181.44, N = 12 1301994.00 1336505.38 1303645.00 1. (CXX) g++ options: -ggdb -rdynamic -lm -lz -lcrypto -lbz2 -lzstd -llz4 -lsnappy -latomic -ldl -pthread -lrt -luuid -lcurl -lssl -std=c++14 -pedantic -fno-rtti -O2 -flto -MMD
KeyDB Test: SADD - Parallel Connections: 50 OpenBenchmarking.org Requests Per Second, More Is Better KeyDB 6.3.2 Test: SADD - Parallel Connections: 50 a b c 400K 800K 1200K 1600K 2000K SE +/- 44518.65, N = 15 1345962.36 1920122.88 1225640.50 1. (CXX) g++ options: -ggdb -rdynamic -lm -lz -lcrypto -lbz2 -lzstd -llz4 -lsnappy -latomic -ldl -pthread -lrt -luuid -lcurl -lssl -std=c++14 -pedantic -fno-rtti -O2 -flto -MMD
KeyDB Test: LPOP - Parallel Connections: 50 OpenBenchmarking.org Requests Per Second, More Is Better KeyDB 6.3.2 Test: LPOP - Parallel Connections: 50 a b c 300K 600K 900K 1200K 1500K SE +/- 22923.50, N = 15 1403220.97 1585238.25 1479465.00 1. (CXX) g++ options: -ggdb -rdynamic -lm -lz -lcrypto -lbz2 -lzstd -llz4 -lsnappy -latomic -ldl -pthread -lrt -luuid -lcurl -lssl -std=c++14 -pedantic -fno-rtti -O2 -flto -MMD
KeyDB Test: SET - Parallel Connections: 50 OpenBenchmarking.org Requests Per Second, More Is Better KeyDB 6.3.2 Test: SET - Parallel Connections: 50 a b c 300K 600K 900K 1200K 1500K SE +/- 40517.71, N = 12 1249454.75 1253729.88 1422030.12 1. (CXX) g++ options: -ggdb -rdynamic -lm -lz -lcrypto -lbz2 -lzstd -llz4 -lsnappy -latomic -ldl -pthread -lrt -luuid -lcurl -lssl -std=c++14 -pedantic -fno-rtti -O2 -flto -MMD
KeyDB Test: GET - Parallel Connections: 50 OpenBenchmarking.org Requests Per Second, More Is Better KeyDB 6.3.2 Test: GET - Parallel Connections: 50 a b c 400K 800K 1200K 1600K 2000K SE +/- 63048.39, N = 15 1481042.42 1373626.38 1690102.75 1. (CXX) g++ options: -ggdb -rdynamic -lm -lz -lcrypto -lbz2 -lzstd -llz4 -lsnappy -latomic -ldl -pthread -lrt -luuid -lcurl -lssl -std=c++14 -pedantic -fno-rtti -O2 -flto -MMD
oneDNN Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.0 Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPU a b c 3 6 9 12 15 SE +/- 0.66035, N = 15 8.93885 8.13373 9.33670 MIN: 7.53 MIN: 8.1 MIN: 9.28 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl
oneDNN Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.0 Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPU a b c 2 4 6 8 10 SE +/- 0.17183, N = 15 8.69748 8.37239 8.44040 MIN: 5.76 MIN: 5.85 MIN: 5.8 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl
oneDNN Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.0 Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPU a b c 0.3692 0.7384 1.1076 1.4768 1.846 SE +/- 0.105801, N = 15 1.251871 1.640760 0.959942 MIN: 0.91 MIN: 1.59 MIN: 0.91 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl
libavif avifenc Encoder Speed: 10, Lossless OpenBenchmarking.org Seconds, Fewer Is Better libavif avifenc 0.11 Encoder Speed: 10, Lossless a b c 2 4 6 8 10 SE +/- 0.185, N = 15 6.571 6.438 6.439 1. (CXX) g++ options: -O3 -fPIC -lm
AOM AV1 Encoder Mode: Speed 10 Realtime - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.6 Encoder Mode: Speed 10 Realtime - Input: Bosphorus 1080p a b c 40 80 120 160 200 SE +/- 3.61, N = 15 175.80 177.46 168.56 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm
AOM AV1 Encoder Mode: Speed 9 Realtime - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.6 Encoder Mode: Speed 9 Realtime - Input: Bosphorus 1080p a b c 40 80 120 160 200 SE +/- 3.99, N = 15 188.81 171.53 201.29 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm
AOM AV1 Encoder Mode: Speed 6 Realtime - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.6 Encoder Mode: Speed 6 Realtime - Input: Bosphorus 1080p a b c 40 80 120 160 200 SE +/- 2.71, N = 15 147.69 145.58 169.96 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm
Phoronix Test Suite v10.8.5