POWER9 44c 176t 2021 Tests for a future article Run 1: Processor: POWER9 @ 3.80GHz (44 Cores / 176 Threads), Motherboard: PowerNV T2P9D01 REV 1.01, Memory: 64GB, Disk: 500GB Samsung SSD 860, Graphics: ASPEED, Monitor: VE228, Network: 2 x Broadcom NetXtreme BCM5719 PCIe OS: Ubuntu 20.10, Kernel: 5.9.10-050910-generic (ppc64le), Display Server: X Server, Compiler: GCC 10.2.0, File-System: ext4, Screen Resolution: 1920x1080 Run 2: Processor: POWER9 @ 3.80GHz (44 Cores / 176 Threads), Motherboard: PowerNV T2P9D01 REV 1.01, Memory: 64GB, Disk: 500GB Samsung SSD 860, Graphics: ASPEED, Monitor: VE228, Network: 2 x Broadcom NetXtreme BCM5719 PCIe OS: Ubuntu 20.10, Kernel: 5.9.10-050910-generic (ppc64le), Display Server: X Server, Compiler: GCC 10.2.0, File-System: ext4, Screen Resolution: 1920x1080 Run 3: Processor: POWER9 @ 3.80GHz (44 Cores / 176 Threads), Motherboard: PowerNV T2P9D01 REV 1.01, Memory: 64GB, Disk: 500GB Samsung SSD 860, Graphics: ASPEED, Monitor: VE228, Network: 2 x Broadcom NetXtreme BCM5719 PCIe OS: Ubuntu 20.10, Kernel: 5.9.10-050910-generic (ppc64le), Display Server: X Server, Compiler: GCC 10.2.0, File-System: ext4, Screen Resolution: 1920x1080 Run 4: Processor: POWER9 @ 3.80GHz (44 Cores / 176 Threads), Motherboard: PowerNV T2P9D01 REV 1.01, Memory: 64GB, Disk: 500GB Samsung SSD 860, Graphics: ASPEED, Monitor: VE228, Network: 2 x Broadcom NetXtreme BCM5719 PCIe OS: Ubuntu 20.10, Kernel: 5.9.10-050910-generic (ppc64le), Display Server: X Server, Compiler: GCC 10.2.0, File-System: ext4, Screen Resolution: 1920x1080 xx2: Processor: POWER9 @ 3.80GHz (44 Cores / 176 Threads), Motherboard: PowerNV T2P9D01 REV 1.01, Memory: 64GB, Disk: 500GB Samsung SSD 860, Graphics: ASPEED, Monitor: VE228, Network: 2 x Broadcom NetXtreme BCM5719 PCIe OS: Ubuntu 20.10, Kernel: 5.9.10-050910-generic (ppc64le), Display Server: X Server, Compiler: GCC 10.2.0, File-System: ext4, Screen Resolution: 1920x1080 Caffe 2020-02-13 Model: GoogleNet - Acceleration: CPU - Iterations: 1000 Milli-Seconds < Lower Is Better Run 1 . 1968783 |============================================================== Caffe 2020-02-13 Model: AlexNet - Acceleration: CPU - Iterations: 1000 Milli-Seconds < Lower Is Better Run 1 . 654412 |=============================================================== G'MIC Test: 2D Function Plotting, 1000 Times Seconds < Lower Is Better Run 1 . 2959.77 |============================================================== Run 2 . 2942.76 |============================================================= Run 3 . 2975.57 |============================================================== Caffe 2020-02-13 Model: GoogleNet - Acceleration: CPU - Iterations: 200 Milli-Seconds < Lower Is Better Run 1 . 364395 |=============================================================== Mobile Neural Network 2020-09-17 Model: inception-v3 ms < Lower Is Better Run 1 . 471.08 |=============================================================== Run 2 . 470.66 |============================================================== Run 3 . 474.54 |=============================================================== Mobile Neural Network 2020-09-17 Model: mobilenet-v1-1.0 ms < Lower Is Better Run 1 . 116.43 |=============================================================== Run 2 . 114.13 |============================================================== Run 3 . 116.29 |=============================================================== Mobile Neural Network 2020-09-17 Model: MobileNetV2_224 ms < Lower Is Better Run 1 . 56.51 |=============================================================== Run 2 . 56.15 |=============================================================== Run 3 . 56.96 |================================================================ Mobile Neural Network 2020-09-17 Model: resnet-v2-50 ms < Lower Is Better Run 1 . 654.28 |============================================================== Run 2 . 654.39 |============================================================== Run 3 . 663.97 |=============================================================== Mobile Neural Network 2020-09-17 Model: SqueezeNetV1.0 ms < Lower Is Better Run 1 . 91.85 |=============================================================== Run 2 . 93.45 |================================================================ Run 3 . 91.88 |=============================================================== Timed GCC Compilation 9.3.0 Time To Compile Seconds < Lower Is Better Run 1 . 1431.91 |============================================================== Run 2 . 1434.53 |============================================================== Run 3 . 1434.12 |============================================================== Numenta Anomaly Benchmark 1.1 Detector: EXPoSE Seconds < Lower Is Better Run 1 . 1409.87 |============================================================= Run 2 . 1439.88 |============================================================== Run 3 . 1437.63 |============================================================== Caffe 2020-02-13 Model: GoogleNet - Acceleration: CPU - Iterations: 100 Milli-Seconds < Lower Is Better Run 1 . 186059 |=============================================================== Timed LLVM Compilation 10.0 Time To Compile Seconds < Lower Is Better Run 1 . 536.17 |=========================================================== Run 2 . 568.01 |=============================================================== Run 3 . 562.21 |============================================================== Basis Universal 1.12 Settings: UASTC Level 2 + RDO Post-Processing Seconds < Lower Is Better Run 1 . 1081.06 |============================================================== Run 2 . 1078.21 |============================================================== Run 3 . 1077.83 |============================================================== VP9 libvpx Encoding 1.8.2 Speed: Speed 0 Frames Per Second > Higher Is Better Run 1 . 0.58 |================================================================= Run 2 . 0.58 |================================================================= Run 3 . 0.58 |================================================================= LAMMPS Molecular Dynamics Simulator 29Oct2020 Model: 20k Atoms ns/day > Higher Is Better Run 1 . 15.33 |============================================================== Run 2 . 14.44 |========================================================== Run 3 . 15.89 |================================================================ xx2 ... 15.87 |================================================================ Caffe 2020-02-13 Model: AlexNet - Acceleration: CPU - Iterations: 200 Milli-Seconds < Lower Is Better Run 1 . 125007 |=============================================================== C-Blosc 2.0 Beta 5 Compressor: blosclz MB/s > Higher Is Better Run 1 . 2982.6 |============================================================== Run 2 . 2968.5 |============================================================== Run 3 . 2980.4 |============================================================== Run 4 . 3013.5 |=============================================================== xx2 ... 2993.6 |=============================================================== LeelaChessZero 0.26 Backend: BLAS Nodes Per Second > Higher Is Better Run 1 . 946 |=============================================================== Run 2 . 942 |=============================================================== Run 3 . 984 |================================================================== xx2 ... 989 |================================================================== Caffe 2020-02-13 Model: AlexNet - Acceleration: CPU - Iterations: 100 Milli-Seconds < Lower Is Better Run 1 . 70400 |================================================================ Numpy Benchmark Score > Higher Is Better Run 1 . 167.76 |=============================================================== Run 2 . 168.59 |=============================================================== Run 3 . 168.52 |=============================================================== libgav1 2019-10-05 Video Input: Chimera 1080p 10-bit FPS > Higher Is Better Run 1 . 13.76 |================================================================ Run 2 . 13.42 |============================================================== Run 3 . 13.78 |================================================================ xx2 ... 13.57 |=============================================================== AOM AV1 2.0 Encoder Mode: Speed 0 Two-Pass Frames Per Second > Higher Is Better Run 1 . 0.02 |================================================================= Run 2 . 0.02 |================================================================= Run 3 . 0.02 |================================================================= xx2 ... 0.02 |================================================================= Blender 2.83.5 Blend File: Barbershop - Compute: CPU-Only Seconds < Lower Is Better Run 1 . 424.42 |=============================================================== Run 2 . 426.94 |=============================================================== Run 3 . 427.26 |=============================================================== High Performance Conjugate Gradient 3.1 GFLOP/s > Higher Is Better Run 1 . 15.05 |================================================== Run 2 . 19.29 |================================================================ Run 3 . 19.28 |================================================================ Run 4 . 19.24 |================================================================ xx2 ... 19.17 |================================================================ AOM AV1 2.0 Encoder Mode: Speed 6 Two-Pass Frames Per Second > Higher Is Better Run 1 . 0.25 |================================================================= Run 2 . 0.25 |================================================================= Run 3 . 0.25 |================================================================= xx2 ... 0.25 |================================================================= Blender 2.83.5 Blend File: Pabellon Barcelona - Compute: CPU-Only Seconds < Lower Is Better Run 1 . 356.47 |=============================================================== Run 2 . 358.10 |=============================================================== Run 3 . 356.07 |=============================================================== 7-Zip Compression 16.02 Compress Speed Test MIPS > Higher Is Better Run 1 . 168456 |============================================================== Run 2 . 170626 |=============================================================== Run 3 . 170105 |=============================================================== rav1e 0.4 Alpha Speed: 5 Frames Per Second > Higher Is Better Run 1 . 0.179 |================================================================ Run 2 . 0.179 |================================================================ Run 3 . 0.179 |================================================================ xx2 ... 0.180 |================================================================ libgav1 2019-10-05 Video Input: Chimera 1080p FPS > Higher Is Better Run 1 . 27.70 |=============================================================== Run 2 . 27.63 |=============================================================== Run 3 . 27.94 |================================================================ xx2 ... 28.11 |================================================================ Kvazaar 2.0 Video Input: Bosphorus 4K - Video Preset: Medium Frames Per Second > Higher Is Better Run 1 . 1.87 |================================================================= Run 2 . 1.87 |================================================================= Run 3 . 1.87 |================================================================= xx2 ... 1.87 |================================================================= rav1e 0.4 Alpha Speed: 6 Frames Per Second > Higher Is Better Run 1 . 0.209 |================================================================ Run 2 . 0.208 |================================================================ Run 3 . 0.209 |================================================================ Kvazaar 2.0 Video Input: Bosphorus 4K - Video Preset: Slow Frames Per Second > Higher Is Better Run 1 . 1.89 |================================================================= Run 2 . 1.89 |================================================================= Run 3 . 1.89 |================================================================= xx2 ... 1.89 |================================================================= Blender 2.83.5 Blend File: Classroom - Compute: CPU-Only Seconds < Lower Is Better Run 1 . 264.29 |=============================================================== Run 2 . 264.31 |=============================================================== Run 3 . 264.49 |=============================================================== Mlpack Benchmark Benchmark: scikit_qda Seconds < Lower Is Better Run 1 . 45.63 |=============================================================== Run 2 . 46.12 |================================================================ Run 3 . 43.96 |============================================================= AOM AV1 2.0 Encoder Mode: Speed 4 Two-Pass Frames Per Second > Higher Is Better Run 1 . 0.17 |================================================================= Run 2 . 0.17 |================================================================= Run 3 . 0.17 |================================================================= xx2 ... 0.17 |================================================================= libgav1 2019-10-05 Video Input: Summer Nature 4K FPS > Higher Is Better Run 1 . 13.56 |=============================================================== Run 2 . 13.42 |=============================================================== Run 3 . 13.72 |================================================================ xx2 ... 13.31 |============================================================== Blender 2.83.5 Blend File: Fishy Cat - Compute: CPU-Only Seconds < Lower Is Better Run 1 . 233.85 |=============================================================== Run 2 . 229.33 |============================================================== Run 3 . 225.99 |============================================================= AOM AV1 2.0 Encoder Mode: Speed 6 Realtime Frames Per Second > Higher Is Better Run 1 . 2.32 |================================================================= Run 2 . 2.33 |================================================================= Run 3 . 2.31 |================================================================ xx2 ... 2.33 |================================================================= PyPerformance 1.0.0 Benchmark: raytrace Milliseconds < Lower Is Better Run 1 . 1.39 |================================================================= Run 2 . 1.38 |================================================================= Run 3 . 1.39 |================================================================= Numenta Anomaly Benchmark 1.1 Detector: Earthgecko Skyline Seconds < Lower Is Better Run 1 . 228.37 |============================================================== Run 2 . 228.69 |============================================================== Run 3 . 231.40 |=============================================================== rav1e 0.4 Alpha Speed: 10 Frames Per Second > Higher Is Better Run 1 . 0.401 |================================================================ Run 2 . 0.402 |================================================================ Run 3 . 0.401 |================================================================ VP9 libvpx Encoding 1.8.2 Speed: Speed 5 Frames Per Second > Higher Is Better Run 1 . 2.71 |================================================================= Run 2 . 2.69 |================================================================= Run 3 . 2.71 |================================================================= rav1e 0.4 Alpha Speed: 1 Frames Per Second > Higher Is Better Run 1 . 0.084 |================================================================ Run 2 . 0.084 |================================================================ Run 3 . 0.084 |================================================================ xx2 ... 0.084 |================================================================ Node.js V8 Web Tooling Benchmark runs/s > Higher Is Better Run 1 . 4.01 |================================================================ Run 2 . 4.05 |================================================================= Run 3 . 4.06 |================================================================= GEGL Operation: Cartoon Seconds < Lower Is Better Run 1 . 205.82 |============================================================== Run 2 . 208.29 |=============================================================== Run 3 . 207.47 |=============================================================== WavPack Audio Encoding 5.3 WAV To WavPack Seconds < Lower Is Better Run 1 . 128.76 |=============================================================== Run 2 . 129.06 |=============================================================== Run 3 . 129.19 |=============================================================== SQLite Speedtest 3.30 Timed Time - Size 1,000 Seconds < Lower Is Better Run 1 . 170.62 |=============================================================== Run 2 . 170.85 |=============================================================== Run 3 . 171.61 |=============================================================== GraphicsMagick 1.3.33 Operation: HWB Color Space Iterations Per Minute > Higher Is Better Run 1 . 1423 |============================================================ Run 2 . 1479 |============================================================== Run 3 . 1489 |=============================================================== xx2 ... 1546 |================================================================= Stockfish 12 Total Time Nodes Per Second > Higher Is Better Run 1 . 31660332 |============================================================= Run 2 . 31552898 |============================================================= Run 3 . 29938062 |========================================================== PyPerformance 1.0.0 Benchmark: 2to3 Milliseconds < Lower Is Better Run 1 . 798 |================================================================== Run 2 . 798 |================================================================== Run 3 . 798 |================================================================== Zstd Compression 1.4.5 Compression Level: 19 MB/s > Higher Is Better Run 1 . 77.6 |=============================================================== Run 2 . 79.5 |================================================================= Run 3 . 79.6 |================================================================= xx2 ... 73.3 |============================================================ Build2 0.13 Time To Compile Seconds < Lower Is Better Run 1 . 135.40 |============================================================== Run 2 . 135.60 |=============================================================== Run 3 . 136.68 |=============================================================== Timed Eigen Compilation 3.3.9 Time To Compile Seconds < Lower Is Better Run 1 . 129.90 |=============================================================== Run 2 . 129.73 |=============================================================== Run 3 . 129.66 |=============================================================== Blender 2.83.5 Blend File: BMW27 - Compute: CPU-Only Seconds < Lower Is Better Run 1 . 123.91 |============================================================== Run 2 . 125.57 |=============================================================== Run 3 . 122.66 |============================================================== PyPerformance 1.0.0 Benchmark: go Milliseconds < Lower Is Better Run 1 . 714 |================================================================== Run 2 . 714 |================================================================== Run 3 . 715 |================================================================== Mlpack Benchmark Benchmark: scikit_linearridgeregression Seconds < Lower Is Better Run 1 . 3.75 |=============================================================== Run 2 . 3.85 |================================================================= Run 3 . 3.75 |=============================================================== oneDNN 2.0 Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better Run 1 . 13142.0 |============================================================= Run 2 . 13133.1 |============================================================= Run 3 . 13254.5 |============================================================== xx2 ... 13302.3 |============================================================== oneDNN 2.0 Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better Run 1 . 13161.3 |============================================================== Run 2 . 13188.2 |============================================================== Run 3 . 13157.2 |============================================================== xx2 ... 13107.9 |============================================================== oneDNN 2.0 Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPU ms < Lower Is Better Run 1 . 13101.1 |============================================================== Run 2 . 13011.5 |============================================================= Run 3 . 13147.2 |============================================================== xx2 ... 13137.9 |============================================================== dcraw RAW To PPM Image Conversion Seconds < Lower Is Better Run 1 . 113.31 |=============================================================== Run 2 . 113.31 |=============================================================== Run 3 . 113.59 |=============================================================== BYTE Unix Benchmark 3.6 Computational Test: Dhrystone 2 LPS > Higher Is Better Run 1 . 27089795.2 |=========================================================== Run 2 . 27261721.5 |=========================================================== Run 3 . 27275695.0 |=========================================================== xx2 ... 26979748.1 |========================================================== GEGL Operation: Color Enhance Seconds < Lower Is Better Run 1 . 106.51 |=============================================================== Run 2 . 106.83 |=============================================================== Run 3 . 106.81 |=============================================================== GEGL Operation: Wavelet Blur Seconds < Lower Is Better Run 1 . 106.16 |=============================================================== Run 2 . 106.64 |=============================================================== Run 3 . 106.70 |=============================================================== AOM AV1 2.0 Encoder Mode: Speed 8 Realtime Frames Per Second > Higher Is Better Run 1 . 5.10 |================================================================= Run 2 . 5.10 |================================================================= Run 3 . 5.10 |================================================================= xx2 ... 5.11 |================================================================= Hugin Panorama Photo Assistant + Stitching Time Seconds < Lower Is Better Run 1 . 104.45 |============================================================= Run 2 . 107.33 |============================================================== Run 3 . 108.53 |=============================================================== dav1d 0.7.0 Video Input: Chimera 1080p 10-bit FPS > Higher Is Better Run 1 . 109.32 |=============================================================== Run 2 . 109.23 |=============================================================== Run 3 . 108.70 |=============================================================== xx2 ... 107.87 |============================================================== x265 3.4 Video Input: Bosphorus 4K Frames Per Second > Higher Is Better Run 1 . 6.24 |================================================================= Run 2 . 6.17 |================================================================ Run 3 . 6.23 |================================================================= Mlpack Benchmark Benchmark: scikit_ica Seconds < Lower Is Better Run 1 . 89.89 |================================================================ Run 2 . 89.38 |================================================================ Run 3 . 88.72 |=============================================================== Kvazaar 2.0 Video Input: Bosphorus 4K - Video Preset: Very Fast Frames Per Second > Higher Is Better Run 1 . 5.65 |================================================================= Run 2 . 5.66 |================================================================= Run 3 . 5.66 |================================================================= xx2 ... 5.64 |================================================================= PyPerformance 1.0.0 Benchmark: regex_compile Milliseconds < Lower Is Better Run 1 . 453 |================================================================== Run 2 . 453 |================================================================== Run 3 . 453 |================================================================== XZ Compression 5.2.4 Compressing ubuntu-16.04.3-server-i386.img, Compression Level 9 Seconds < Lower Is Better Run 1 . 27.96 |================================================================ Run 2 . 25.04 |========================================================= Run 3 . 27.65 |=============================================================== PyPerformance 1.0.0 Benchmark: python_startup Milliseconds < Lower Is Better Run 1 . 14.5 |=============================================================== Run 2 . 14.9 |================================================================= Run 3 . 14.5 |=============================================================== Git Time To Complete Common Git Commands Seconds < Lower Is Better Run 1 . 92.52 |================================================================ Run 2 . 92.17 |================================================================ Run 3 . 92.25 |================================================================ OpenCV 4.4 Test: DNN - Deep Neural Network ms < Lower Is Better Run 1 . 25792 |=============================================================== Run 2 . 25951 |=============================================================== Run 3 . 26397 |================================================================ G'MIC Test: 3D Elevated Function In Random Colors, 100 Times Seconds < Lower Is Better Run 1 . 86.90 |================================================================ Run 2 . 87.39 |================================================================ Run 3 . 87.16 |================================================================ Timed PHP Compilation 7.4.2 Time To Compile Seconds < Lower Is Better Run 1 . 86.39 |================================================================ Run 2 . 86.05 |================================================================ Run 3 . 86.35 |================================================================ oneDNN 2.0 Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better Run 1 . 7566.40 |============================================================= Run 2 . 7667.00 |============================================================== Run 3 . 7693.28 |============================================================== xx2 ... 7699.03 |============================================================== oneDNN 2.0 Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPU ms < Lower Is Better Run 1 . 7532.05 |============================================================= Run 2 . 7670.66 |============================================================== Run 3 . 7679.57 |============================================================== xx2 ... 7690.46 |============================================================== oneDNN 2.0 Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better Run 1 . 7568.89 |============================================================= Run 2 . 7676.79 |============================================================== Run 3 . 7534.57 |============================================================= xx2 ... 7682.60 |============================================================== PyPerformance 1.0.0 Benchmark: nbody Milliseconds < Lower Is Better Run 1 . 476 |================================================================== Run 2 . 475 |================================================================== Run 3 . 476 |================================================================== RawTherapee Total Benchmark Time Seconds < Lower Is Better Run 1 . 83.60 |================================================================ Run 2 . 83.68 |================================================================ Run 3 . 83.36 |================================================================ PyBench 2018-02-16 Total For Average Test Times Milliseconds < Lower Is Better Run 1 . 3600 |================================================================= Run 2 . 3605 |================================================================= Run 3 . 3597 |================================================================= libgav1 2019-10-05 Video Input: Summer Nature 1080p FPS > Higher Is Better Run 1 . 42.27 |=============================================================== Run 2 . 42.66 |================================================================ Run 3 . 42.43 |================================================================ xx2 ... 42.24 |=============================================================== Basis Universal 1.12 Settings: ETC1S Seconds < Lower Is Better Run 1 . 78.75 |================================================================ Run 2 . 79.29 |================================================================ Run 3 . 78.98 |================================================================ GEGL Operation: Rotate 90 Degrees Seconds < Lower Is Better Run 1 . 77.41 |================================================================ Run 2 . 77.59 |================================================================ Run 3 . 77.83 |================================================================ Kvazaar 2.0 Video Input: Bosphorus 1080p - Video Preset: Slow Frames Per Second > Higher Is Better Run 1 . 7.05 |================================================================ Run 2 . 6.97 |================================================================ Run 3 . 7.04 |================================================================ xx2 ... 7.12 |================================================================= Kvazaar 2.0 Video Input: Bosphorus 1080p - Video Preset: Medium Frames Per Second > Higher Is Better Run 1 . 7.07 |================================================================ Run 2 . 7.03 |================================================================ Run 3 . 7.05 |================================================================ xx2 ... 7.14 |================================================================= LZ4 Compression 1.9.3 Compression Level: 9 - Decompression Speed MB/s > Higher Is Better Run 1 . 9250.9 |=============================================================== Run 2 . 9243.0 |=============================================================== Run 3 . 9224.7 |============================================================== xx2 ... 9306.6 |=============================================================== LZ4 Compression 1.9.3 Compression Level: 9 - Compression Speed MB/s > Higher Is Better Run 1 . 38.06 |================================================================ Run 2 . 38.05 |================================================================ Run 3 . 38.03 |================================================================ xx2 ... 38.12 |================================================================ LZ4 Compression 1.9.3 Compression Level: 3 - Decompression Speed MB/s > Higher Is Better Run 1 . 9240.5 |=============================================================== Run 2 . 9299.5 |=============================================================== Run 3 . 9183.2 |============================================================== xx2 ... 9187.7 |============================================================== LZ4 Compression 1.9.3 Compression Level: 3 - Compression Speed MB/s > Higher Is Better Run 1 . 39.71 |================================================================ Run 2 . 39.66 |================================================================ Run 3 . 39.66 |================================================================ xx2 ... 39.72 |================================================================ GEGL Operation: Antialias Seconds < Lower Is Better Run 1 . 70.75 |================================================================ Run 2 . 70.98 |================================================================ Run 3 . 70.84 |================================================================ GIMP 2.10.18 Test: resize Seconds < Lower Is Better Run 1 . 20.62 |=========================================================== Run 2 . 22.24 |================================================================ Run 3 . 21.84 |=============================================================== Numenta Anomaly Benchmark 1.1 Detector: Bayesian Changepoint Seconds < Lower Is Better Run 1 . 70.33 |=============================================================== Run 2 . 69.87 |============================================================== Run 3 . 71.75 |================================================================ PyPerformance 1.0.0 Benchmark: float Milliseconds < Lower Is Better Run 1 . 384 |================================================================== Run 2 . 384 |================================================================== Run 3 . 383 |================================================================== Timed Linux Kernel Compilation 5.4 Time To Compile Seconds < Lower Is Better Run 1 . 67.86 |=============================================================== Run 2 . 69.43 |================================================================ Run 3 . 69.14 |================================================================ eSpeak-NG Speech Engine 20200907 Text-To-Speech Synthesis Seconds < Lower Is Better Run 1 . 54.41 |=============================================================== Run 2 . 54.92 |================================================================ Run 3 . 54.79 |================================================================ AOBench Size: 2048 x 2048 - Total Time Seconds < Lower Is Better Run 1 . 63.88 |================================================================ Run 2 . 62.83 |=============================================================== Run 3 . 62.59 |=============================================================== GraphicsMagick 1.3.33 Operation: Noise-Gaussian Iterations Per Minute > Higher Is Better Run 1 . 414 |================================================================= Run 2 . 421 |================================================================== Run 3 . 396 |============================================================== xx2 ... 392 |============================================================= PyPerformance 1.0.0 Benchmark: chaos Milliseconds < Lower Is Better Run 1 . 314 |================================================================== Run 2 . 314 |================================================================== Run 3 . 314 |================================================================== dav1d 0.7.0 Video Input: Chimera 1080p FPS > Higher Is Better Run 1 . 173.02 |============================================================== Run 2 . 172.06 |============================================================== Run 3 . 174.53 |=============================================================== xx2 ... 169.27 |============================================================= PyPerformance 1.0.0 Benchmark: crypto_pyaes Milliseconds < Lower Is Better Run 1 . 327 |================================================================== Run 2 . 326 |================================================================== Run 3 . 328 |================================================================== Opus Codec Encoding 1.3.1 WAV To Opus Encode Seconds < Lower Is Better Run 1 . 43.18 |================================================================ Run 2 . 43.20 |================================================================ Run 3 . 43.21 |================================================================ GEGL Operation: Tile Glass Seconds < Lower Is Better Run 1 . 59.86 |================================================================ Run 2 . 59.87 |================================================================ Run 3 . 60.17 |================================================================ LibRaw 0.20 Post-Processing Benchmark Mpix/sec > Higher Is Better Run 1 . 18.82 |================================================================ Run 2 . 18.76 |=============================================================== Run 3 . 18.91 |================================================================ xx2 ... 18.82 |================================================================ Cryptsetup Twofish-XTS 512b Encryption MiB/s > Higher Is Better Run 1 . 133.9 |================================================================ Cryptsetup Serpent-XTS 512b Encryption MiB/s > Higher Is Better Run 1 . 62.7 |================================================================= FLAC Audio Encoding 1.3.2 WAV To FLAC Seconds < Lower Is Better Run 1 . 40.18 |================================================================ Run 2 . 40.18 |================================================================ Run 3 . 40.28 |================================================================ WebP Image Encode 1.1 Encode Settings: Quality 100, Lossless, Highest Compression Encode Time - Seconds < Lower Is Better Run 1 . 62.11 |================================================================ Run 2 . 62.10 |================================================================ Run 3 . 62.07 |================================================================ xx2 ... 62.08 |================================================================ Timed FFmpeg Compilation 4.2.2 Time To Compile Seconds < Lower Is Better Run 1 . 55.54 |================================================================ Run 2 . 55.27 |================================================================ Run 3 . 55.67 |================================================================ simdjson 0.7.1 Throughput Test: Kostya GB/s > Higher Is Better Run 1 . 1.06 |================================================================= Run 2 . 1.06 |================================================================= Run 3 . 1.06 |================================================================= xx2 ... 1.06 |================================================================= GraphicsMagick 1.3.33 Operation: Sharpen Iterations Per Minute > Higher Is Better Run 1 . 417 |================================================================== Run 2 . 417 |================================================================== Run 3 . 414 |================================================================== xx2 ... 417 |================================================================== GraphicsMagick 1.3.33 Operation: Enhanced Iterations Per Minute > Higher Is Better Run 1 . 534 |================================================================== Run 2 . 534 |================================================================== Run 3 . 535 |================================================================== xx2 ... 536 |================================================================== GraphicsMagick 1.3.33 Operation: Rotate Iterations Per Minute > Higher Is Better Run 1 . 638 |================================================================ Run 2 . 640 |================================================================ Run 3 . 633 |=============================================================== xx2 ... 658 |================================================================== GraphicsMagick 1.3.33 Operation: Swirl Iterations Per Minute > Higher Is Better Run 1 . 1203 |================================================================ Run 2 . 1205 |================================================================ Run 3 . 1201 |================================================================ xx2 ... 1218 |================================================================= GraphicsMagick 1.3.33 Operation: Resizing Iterations Per Minute > Higher Is Better Run 1 . 1821 |================================================================= Run 2 . 1818 |================================================================= Run 3 . 1820 |================================================================= xx2 ... 1804 |================================================================ Mlpack Benchmark Benchmark: scikit_svm Seconds < Lower Is Better Run 1 . 44.76 |================================================================ Run 2 . 44.72 |================================================================ Run 3 . 44.68 |================================================================ GEGL Operation: Reflect Seconds < Lower Is Better Run 1 . 51.94 |================================================================ Run 2 . 52.04 |================================================================ Run 3 . 52.11 |================================================================ GIMP 2.10.18 Test: unsharp-mask Seconds < Lower Is Better Run 1 . 51.21 |=============================================================== Run 2 . 51.90 |================================================================ Run 3 . 51.23 |=============================================================== simdjson 0.7.1 Throughput Test: LargeRandom GB/s > Higher Is Better Run 1 . 0.48 |================================================================= Run 2 . 0.48 |================================================================= Run 3 . 0.48 |================================================================= xx2 ... 0.48 |================================================================= Gzip Compression Linux Source Tree Archiving To .tar.gz Seconds < Lower Is Better Run 1 . 49.93 |=============================================================== Run 2 . 50.47 |================================================================ Run 3 . 50.23 |================================================================ x265 3.4 Video Input: Bosphorus 1080p Frames Per Second > Higher Is Better Run 1 . 12.90 |================================================================ Run 2 . 12.70 |=============================================================== Run 3 . 12.32 |============================================================= Tesseract OCR 4.1.1 Time To OCR 7 Images Seconds < Lower Is Better Run 1 . 46.53 |================================================================ Run 2 . 46.64 |================================================================ Run 3 . 46.33 |================================================================ G'MIC Test: Plotting Isosurface Of A 3D Volume, 1000 Times Seconds < Lower Is Better Run 1 . 45.12 |================================================================ Run 2 . 45.13 |================================================================ Run 3 . 45.10 |================================================================ Timed Apache Compilation 2.4.41 Time To Compile Seconds < Lower Is Better Run 1 . 44.89 |================================================================ Run 2 . 44.72 |================================================================ Run 3 . 44.97 |================================================================ TNN 0.2.3 Target: CPU - Model: MobileNet v2 ms < Lower Is Better Run 1 . 637.13 |=============================================================== Run 2 . 637.09 |=============================================================== Run 3 . 637.08 |=============================================================== Tachyon 0.99b6 Total Time Seconds < Lower Is Better Run 1 . 43.43 |================================================================ Run 2 . 43.24 |================================================================ Run 3 . 42.97 |=============================================================== simdjson 0.7.1 Throughput Test: PartialTweets GB/s > Higher Is Better Run 1 . 1.19 |================================================================= Run 2 . 1.19 |================================================================= Run 3 . 1.19 |================================================================= xx2 ... 1.19 |================================================================= simdjson 0.7.1 Throughput Test: DistinctUserID GB/s > Higher Is Better Run 1 . 1.23 |================================================================ Run 2 . 1.24 |================================================================= Run 3 . 1.24 |================================================================= xx2 ... 1.23 |================================================================ TNN 0.2.3 Target: CPU - Model: SqueezeNet v1.1 ms < Lower Is Better Run 1 . 611.71 |=============================================================== Run 2 . 612.03 |=============================================================== Run 3 . 611.77 |=============================================================== x264 2019-12-17 H.264 Video Encoding Frames Per Second > Higher Is Better Run 1 . 53.85 |================================================================ Run 2 . 36.66 |============================================ Run 3 . 35.53 |========================================== GIMP 2.10.18 Test: auto-levels Seconds < Lower Is Better Run 1 . 39.53 |============================================================== Run 2 . 39.38 |============================================================== Run 3 . 40.54 |================================================================ Redis 6.0.9 Test: SADD Requests Per Second > Higher Is Better Run 1 . 682251.35 |=========================================================== Run 2 . 689655.12 |============================================================ Run 3 . 693377.69 |============================================================ PyPerformance 1.0.0 Benchmark: django_template Milliseconds < Lower Is Better Run 1 . 150 |================================================================== Run 2 . 150 |================================================================== Run 3 . 150 |================================================================== Kvazaar 2.0 Video Input: Bosphorus 4K - Video Preset: Ultra Fast Frames Per Second > Higher Is Better Run 1 . 14.04 |================================================================ Run 2 . 14.04 |================================================================ Run 3 . 14.00 |================================================================ xx2 ... 14.01 |================================================================ RNNoise 2020-06-28 Seconds < Lower Is Better Run 1 . 38.31 |================================================================ Run 2 . 38.11 |================================================================ Run 3 . 38.08 |================================================================ OCRMyPDF 10.3.1+dfsg Processing 60 Page PDF Document Seconds < Lower Is Better Run 1 . 37.70 |============================================================== Run 2 . 38.99 |================================================================ Run 3 . 38.53 |=============================================================== LZ4 Compression 1.9.3 Compression Level: 1 - Decompression Speed MB/s > Higher Is Better Run 1 . 10342.4 |============================================================== Run 2 . 10337.9 |============================================================== Run 3 . 10333.6 |============================================================== xx2 ... 10310.5 |============================================================== LZ4 Compression 1.9.3 Compression Level: 1 - Compression Speed MB/s > Higher Is Better Run 1 . 9087.53 |============================================================== Run 2 . 9061.86 |============================================================== Run 3 . 9062.33 |============================================================== xx2 ... 9046.51 |============================================================== CLOMP 1.2 Static OMP Speedup Speedup > Higher Is Better Run 1 . 5.8 |================================================================ Run 2 . 6.0 |================================================================== Run 3 . 6.0 |================================================================== xx2 ... 5.9 |================================================================= Unpacking Firefox 84.0 Extracting: firefox-84.0.source.tar.xz Seconds < Lower Is Better Run 1 . 30.91 |================================================================ Run 2 . 30.01 |============================================================== Run 3 . 30.82 |================================================================ Zstd Compression 1.4.5 Compression Level: 3 MB/s > Higher Is Better Run 1 . 4022.5 |====================================================== Run 2 . 4657.7 |=============================================================== Run 3 . 4228.7 |========================================================= xx2 ... 3982.5 |====================================================== Cryptsetup Twofish-XTS 512b Decryption MiB/s > Higher Is Better Run 1 . 132.7 |================================================================ Run 2 . 132.9 |================================================================ Run 3 . 132.9 |================================================================ PyPerformance 1.0.0 Benchmark: json_loads Milliseconds < Lower Is Better Run 1 . 65.1 |================================================================= Run 2 . 65.2 |================================================================= Run 3 . 65.1 |================================================================= Numenta Anomaly Benchmark 1.1 Detector: Relative Entropy Seconds < Lower Is Better Run 1 . 34.69 |================================================================ Run 2 . 34.54 |================================================================ Run 3 . 34.06 |=============================================================== Dolfyn 0.527 Computational Fluid Dynamics Seconds < Lower Is Better Run 1 . 38.07 |================================================================ Run 2 . 38.09 |================================================================ Run 3 . 38.15 |================================================================ xx2 ... 38.07 |================================================================ Cryptsetup Serpent-XTS 256b Decryption MiB/s > Higher Is Better Run 1 . 75.1 |================================================================= Run 2 . 75.1 |================================================================= Run 3 . 75.1 |================================================================= Cryptsetup Serpent-XTS 256b Encryption MiB/s > Higher Is Better Run 1 . 62.2 |================================================================ Run 2 . 62.7 |================================================================= Run 3 . 62.7 |================================================================= Cryptsetup PBKDF2-whirlpool Iterations Per Second > Higher Is Better Run 1 . 343870 |=============================================================== Run 2 . 344020 |=============================================================== Run 3 . 344020 |=============================================================== Cryptsetup PBKDF2-sha512 Iterations Per Second > Higher Is Better Run 1 . 1091132 |============================================================== Run 2 . 1091130 |============================================================== Run 3 . 1092266 |============================================================== PyPerformance 1.0.0 Benchmark: pathlib Milliseconds < Lower Is Better Run 1 . 51.9 |================================================================= Run 2 . 51.6 |================================================================= Run 3 . 51.8 |================================================================= dav1d 0.7.0 Video Input: Summer Nature 4K FPS > Higher Is Better Run 1 . 89.15 |================================================================ Run 2 . 89.47 |================================================================ Run 3 . 89.69 |================================================================ xx2 ... 88.78 |=============================================================== librsvg Operation: SVG Files To PNG Seconds < Lower Is Better Run 1 . 32.53 |================================================================ Run 2 . 31.95 |=============================================================== Run 3 . 32.50 |================================================================ POV-Ray 3.7.0.7 Trace Time Seconds < Lower Is Better Run 1 . 25.97 |================================================================ Run 2 . 26.05 |================================================================ Run 3 . 25.29 |============================================================== Monkey Audio Encoding 3.99.6 WAV To APE Seconds < Lower Is Better Run 1 . 21.67 |================================================================ Run 2 . 21.80 |================================================================ Run 3 . 21.83 |================================================================ Kvazaar 2.0 Video Input: Bosphorus 1080p - Video Preset: Very Fast Frames Per Second > Higher Is Better Run 1 . 18.41 |================================================================ Run 2 . 18.27 |================================================================ Run 3 . 18.37 |================================================================ xx2 ... 18.41 |================================================================ Timed ImageMagick Compilation 6.9.0 Time To Compile Seconds < Lower Is Better Run 1 . 29.04 |================================================================ Run 2 . 28.95 |================================================================ Run 3 . 29.10 |================================================================ Cryptsetup Twofish-XTS 256b Decryption MiB/s > Higher Is Better Run 2 . 133.0 |================================================================ Run 3 . 132.9 |================================================================ Run 1 . 133.0 |================================================================ Run 2 . 132.9 |================================================================ Run 3 . 133.0 |================================================================ Cryptsetup Twofish-XTS 256b Encryption MiB/s > Higher Is Better Run 2 . 133.9 |================================================================ Run 3 . 133.8 |================================================================ Run 1 . 132.6 |=============================================================== Run 2 . 133.8 |================================================================ Run 3 . 133.9 |================================================================ GIMP 2.10.18 Test: rotate Seconds < Lower Is Better Run 1 . 28.24 |================================================================ Run 2 . 28.27 |================================================================ Run 3 . 28.33 |================================================================ WebP Image Encode 1.1 Encode Settings: Quality 100, Lossless Encode Time - Seconds < Lower Is Better Run 1 . 29.97 |================================================================ Run 2 . 29.93 |================================================================ Run 3 . 29.99 |================================================================ xx2 ... 29.92 |================================================================ Basis Universal 1.12 Settings: UASTC Level 3 Seconds < Lower Is Better Run 1 . 26.55 |================================================================ Run 2 . 26.55 |================================================================ Run 3 . 26.57 |================================================================ Cryptsetup AES-XTS 512b Decryption MiB/s > Higher Is Better Run 2 . 2098.8 |=============================================================== Run 2 . 2100.5 |=============================================================== Run 3 . 2101.0 |=============================================================== Run 3 . 2099.3 |=============================================================== Run 1 . 2100.1 |=============================================================== Run 2 . 2098.4 |=============================================================== Run 3 . 2089.5 |=============================================================== Cryptsetup AES-XTS 512b Encryption MiB/s > Higher Is Better Run 2 . 2098.4 |=============================================================== Run 2 . 2100.1 |=============================================================== Run 3 . 2099.3 |=============================================================== Run 3 . 2097.6 |=============================================================== Run 1 . 2098.1 |=============================================================== Run 2 . 2096.9 |=============================================================== Run 3 . 2087.8 |=============================================================== Cryptsetup AES-XTS 256b Decryption MiB/s > Higher Is Better Run 2 . 2495.2 |=============================================================== Run 2 . 2495.8 |=============================================================== Run 3 . 2497.1 |=============================================================== Run 3 . 2494.3 |=============================================================== Run 1 . 2496.2 |=============================================================== Run 2 . 2494.0 |=============================================================== Run 3 . 2486.0 |=============================================================== Cryptsetup AES-XTS 256b Encryption MiB/s > Higher Is Better Run 2 . 2492.8 |=============================================================== Run 2 . 2494.4 |=============================================================== Run 3 . 2494.5 |=============================================================== Run 3 . 2492.4 |=============================================================== Run 1 . 2473.0 |============================================================== Run 2 . 2488.7 |=============================================================== Run 3 . 2483.2 |=============================================================== PyPerformance 1.0.0 Benchmark: pickle_pure_python Milliseconds < Lower Is Better Run 1 . 1.34 |================================================================= Run 2 . 1.33 |================================================================= Run 3 . 1.33 |================================================================= TTSIOD 3D Renderer 2.3b Phong Rendering With Soft-Shadow Mapping FPS > Higher Is Better Run 1 . 782.07 |=============================================================== Run 2 . 776.94 |=============================================================== Run 3 . 777.73 |=============================================================== xx2 ... 778.70 |=============================================================== Cryptsetup PBKDF2-sha512 MiB/s > Higher Is Better Run 2 . 1092266 |============================================================== Run 2 . 1093405 |============================================================== Run 3 . 1092266 |============================================================== Cryptsetup PBKDF2-whirlpool MiB/s > Higher Is Better Run 2 . 344020 |=============================================================== Run 3 . 344020 |=============================================================== Run 2 . 343570 |=============================================================== Run 3 . 343570 |=============================================================== C-Ray 1.1 Total Time - 4K, 16 Rays Per Pixel Seconds < Lower Is Better Run 1 . 18.53 |=============================================================== Run 2 . 18.64 |================================================================ Run 3 . 18.73 |================================================================ oneDNN 2.0 Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better Run 1 . 42.83 |================================================================ Run 2 . 42.82 |================================================================ Run 3 . 42.94 |================================================================ xx2 ... 42.71 |================================================================ oneDNN 2.0 Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPU ms < Lower Is Better Run 1 . 103.62 |=============================================================== Run 2 . 103.39 |=============================================================== Run 3 . 103.75 |=============================================================== xx2 ... 103.74 |=============================================================== Basis Universal 1.12 Settings: UASTC Level 2 Seconds < Lower Is Better Run 1 . 18.54 |================================================================ Run 2 . 18.44 |================================================================ Run 3 . 18.54 |================================================================ Numenta Anomaly Benchmark 1.1 Detector: Windowed Gaussian Seconds < Lower Is Better Run 1 . 18.09 |================================================================ Run 2 . 18.17 |================================================================ Run 3 . 17.90 |=============================================================== Scikit-Learn 0.22.1 Seconds < Lower Is Better Run 1 . 17.53 |================================================================ Run 2 . 17.50 |================================================================ Run 3 . 17.50 |================================================================ WebP Image Encode 1.1 Encode Settings: Quality 100, Highest Compression Encode Time - Seconds < Lower Is Better Run 1 . 17.66 |================================================================ Run 2 . 17.66 |================================================================ Run 3 . 17.66 |================================================================ xx2 ... 17.66 |================================================================ GEGL Operation: Crop Seconds < Lower Is Better Run 1 . 15.93 |=============================================================== Run 2 . 16.24 |================================================================ Run 3 . 16.25 |================================================================ System GZIP Decompression Seconds < Lower Is Better Run 1 . 4.935 |========================================================= Run 2 . 5.580 |================================================================ Run 3 . 5.587 |================================================================ LAME MP3 Encoding 3.100 WAV To MP3 Seconds < Lower Is Better Run 1 . 14.40 |================================================================ Run 2 . 14.40 |================================================================ Run 3 . 14.40 |================================================================ oneDNN 2.0 Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better Run 1 . 40.83 |================================================================ Run 2 . 40.65 |=============================================================== Run 3 . 41.08 |================================================================ xx2 ... 40.97 |================================================================ oneDNN 2.0 Harness: IP Shapes 1D - Data Type: f32 - Engine: CPU ms < Lower Is Better Run 1 . 29.77 |=============================================================== Run 2 . 30.26 |================================================================ Run 3 . 29.82 |=============================================================== xx2 ... 29.49 |============================================================== GEGL Operation: Scale Seconds < Lower Is Better Run 1 . 12.64 |================================================================ Run 2 . 12.54 |=============================================================== Run 3 . 12.52 |=============================================================== Kvazaar 2.0 Video Input: Bosphorus 1080p - Video Preset: Ultra Fast Frames Per Second > Higher Is Better Run 1 . 43.25 |================================================================ Run 2 . 42.96 |=============================================================== Run 3 . 43.18 |================================================================ xx2 ... 43.33 |================================================================ Redis 6.0.9 Test: LPOP Requests Per Second > Higher Is Better Run 1 . 519606.57 |============================================================ Run 2 . 500314.16 |========================================================== Run 3 . 521050.00 |============================================================ Redis 6.0.9 Test: LPUSH Requests Per Second > Higher Is Better Run 1 . 509296.11 |============================================================ Run 2 . 501002.00 |=========================================================== Run 3 . 510285.72 |============================================================ Redis 6.0.9 Test: SET Requests Per Second > Higher Is Better Run 1 . 584774.65 |============================================================ Run 2 . 562275.44 |========================================================== Run 3 . 531519.69 |======================================================= GNU Octave Benchmark 5.2.0 Seconds < Lower Is Better Run 1 . 8.337 |=============================================================== Run 2 . 8.496 |================================================================ Run 3 . 8.496 |================================================================ Redis 6.0.9 Test: GET Requests Per Second > Higher Is Better Run 1 . 800110.61 |=========================================================== Run 2 . 811922.06 |============================================================ Run 3 . 791993.69 |=========================================================== Basis Universal 1.12 Settings: UASTC Level 0 Seconds < Lower Is Better Run 1 . 11.27 |================================================================ Run 2 . 11.26 |================================================================ Run 3 . 11.24 |================================================================ dav1d 0.7.0 Video Input: Summer Nature 1080p FPS > Higher Is Better Run 1 . 261.55 |============================================================== Run 2 . 262.22 |============================================================== Run 3 . 253.46 |============================================================ xx2 ... 267.17 |=============================================================== oneDNN 2.0 Harness: Matrix Multiply Batch Shapes Transformer - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better Run 1 . 9.16733 |============================================================== Run 2 . 9.07736 |============================================================= Run 3 . 9.16306 |============================================================== xx2 ... 9.17922 |============================================================== oneDNN 2.0 Harness: Matrix Multiply Batch Shapes Transformer - Data Type: f32 - Engine: CPU ms < Lower Is Better Run 1 . 4.77018 |============================================================== Run 2 . 4.77039 |============================================================== Run 3 . 4.76997 |============================================================== xx2 ... 4.76187 |============================================================== WebP Image Encode 1.1 Encode Settings: Quality 100 Encode Time - Seconds < Lower Is Better Run 1 . 10.96 |================================================================ Run 2 . 10.96 |================================================================ Run 3 . 10.96 |================================================================ xx2 ... 10.96 |================================================================ Timed MAFFT Alignment 7.471 Multiple Sequence Alignment - LSU RNA Seconds < Lower Is Better Run 1 . 11.27 |=============================================================== Run 2 . 11.36 |=============================================================== Run 3 . 11.21 |============================================================== xx2 ... 11.54 |================================================================ oneDNN 2.0 Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better Run 1 . 33.20 |=============================================================== Run 2 . 33.42 |================================================================ Run 3 . 33.11 |=============================================================== xx2 ... 33.49 |================================================================ oneDNN 2.0 Harness: IP Shapes 3D - Data Type: f32 - Engine: CPU ms < Lower Is Better Run 1 . 13.56 |=============================================================== Run 2 . 13.41 |=============================================================== Run 3 . 13.68 |================================================================ xx2 ... 13.45 |=============================================================== WebP Image Encode 1.1 Encode Settings: Default Encode Time - Seconds < Lower Is Better Run 1 . 7.868 |================================================================ Run 2 . 7.869 |================================================================ Run 3 . 7.865 |================================================================ xx2 ... 7.865 |================================================================ System ZLIB Decompression 1.2.7 ms < Lower Is Better Run 1 . 2723.85 |=========================================================== Run 2 . 2886.06 |============================================================== Run 3 . 2874.76 |============================================================== libjpeg-turbo tjbench 2.0.2 Megapixels/sec > Higher Is Better Run 1 . 101.75 |=============================================================== Run 2 . 101.81 |=============================================================== Run 3 . 101.81 |=============================================================== oneDNN 2.0 Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better Run 1 . 55.30 |=============================================================== Run 2 . 55.24 |=============================================================== Run 3 . 55.80 |================================================================ xx2 ... 55.42 |================================================================ LAMMPS Molecular Dynamics Simulator 29Oct2020 Model: Rhodopsin Protein ns/day > Higher Is Better Run 1 . 13.86 |=========================================================== Run 2 . 14.85 |=============================================================== Run 3 . 15.07 |================================================================ xx2 ... 13.87 |=========================================================== oneDNN 2.0 Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPU ms < Lower Is Better Run 1 . 25.61 |================================================================ Run 2 . 25.52 |================================================================ Run 3 . 25.58 |================================================================ xx2 ... 25.58 |================================================================ System XZ Decompression Seconds < Lower Is Better Run 1 . 5.555 |================================================================ Run 2 . 5.561 |================================================================ Run 3 . 5.563 |================================================================ Algebraic Multi-Grid Benchmark Figure Of Merit > Higher Is Better Run 1 . 3472681 |============================================================= Run 2 . 3486278 |============================================================== Run 3 . 3504642 |============================================================== xx2 ... 3504477 |============================================================== Smallpt 1.0 Global Illumination Renderer; 128 Samples Seconds < Lower Is Better Run 1 . 4.417 |================================================================ Run 2 . 4.421 |================================================================ Run 3 . 4.451 |================================================================ oneDNN 2.0 Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better Run 1 . 26.80 |================================================================ Run 2 . 26.05 |============================================================== Run 3 . 26.81 |================================================================ xx2 ... 26.86 |================================================================ oneDNN 2.0 Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPU ms < Lower Is Better Run 1 . 10.35 |================================================================ Run 2 . 10.32 |=============================================================== Run 3 . 10.39 |================================================================ xx2 ... 10.41 |================================================================ Parallel BZIP2 Compression 1.1.12 256MB File Compression Seconds < Lower Is Better Run 1 . 2.078 |================================================================ Run 2 . 2.051 |=============================================================== Run 3 . 2.026 |==============================================================