Xeon Platinum 8280 oneDNN 2.0 + More 2 x Intel Xeon Platinum 8280 testing with a GIGABYTE MD61-SC2-00 v01000100 (T15 BIOS) and llvmpipe on Ubuntu 20.04 via the Phoronix Test Suite. 1: Processor: 2 x Intel Xeon Platinum 8280 @ 4.00GHz (56 Cores / 112 Threads), Motherboard: GIGABYTE MD61-SC2-00 v01000100 (T15 BIOS), Chipset: Intel Sky Lake-E DMI3 Registers, Memory: 378GB, Disk: 280GB INTEL SSDPED1D280GA, Graphics: llvmpipe, Monitor: VE228, Network: 2 x Intel X722 for 1GbE + 2 x QLogic FastLinQ QL41000 10/25/40/50GbE OS: Ubuntu 20.04, Kernel: 5.4.0-18-generic (x86_64), Desktop: GNOME Shell 3.36.0, Display Server: X Server 1.20.7, Display Driver: modesetting 1.20.7, OpenGL: 3.3 Mesa 20.0.2 (LLVM 9.0.1 256 bits), Compiler: GCC 9.3.0, File-System: ext4, Screen Resolution: 1920x1080 2: Processor: 2 x Intel Xeon Platinum 8280 @ 4.00GHz (56 Cores / 112 Threads), Motherboard: GIGABYTE MD61-SC2-00 v01000100 (T15 BIOS), Chipset: Intel Sky Lake-E DMI3 Registers, Memory: 378GB, Disk: 280GB INTEL SSDPED1D280GA, Graphics: llvmpipe, Monitor: VE228, Network: 2 x Intel X722 for 1GbE + 2 x QLogic FastLinQ QL41000 10/25/40/50GbE OS: Ubuntu 20.04, Kernel: 5.4.0-18-generic (x86_64), Desktop: GNOME Shell 3.36.0, Display Server: X Server 1.20.7, Display Driver: modesetting 1.20.7, OpenGL: 3.3 Mesa 20.0.2 (LLVM 9.0.1 256 bits), Compiler: GCC 9.3.0, File-System: ext4, Screen Resolution: 1920x1080 2a: Processor: 2 x Intel Xeon Platinum 8280 @ 4.00GHz (56 Cores / 112 Threads), Motherboard: GIGABYTE MD61-SC2-00 v01000100 (T15 BIOS), Chipset: Intel Sky Lake-E DMI3 Registers, Memory: 378GB, Disk: 280GB INTEL SSDPED1D280GA, Graphics: llvmpipe, Monitor: VE228, Network: 2 x Intel X722 for 1GbE + 2 x QLogic FastLinQ QL41000 10/25/40/50GbE OS: Ubuntu 20.04, Kernel: 5.4.0-18-generic (x86_64), Desktop: GNOME Shell 3.36.0, Display Server: X Server 1.20.7, Display Driver: modesetting 1.20.7, OpenGL: 3.3 Mesa 20.0.2 (LLVM 9.0.1 256 bits), Compiler: GCC 9.3.0, File-System: ext4, Screen Resolution: 1920x1080 3: Processor: 2 x Intel Xeon Platinum 8280 @ 4.00GHz (56 Cores / 112 Threads), Motherboard: GIGABYTE MD61-SC2-00 v01000100 (T15 BIOS), Chipset: Intel Sky Lake-E DMI3 Registers, Memory: 378GB, Disk: 280GB INTEL SSDPED1D280GA, Graphics: llvmpipe, Monitor: VE228, Network: 2 x Intel X722 for 1GbE + 2 x QLogic FastLinQ QL41000 10/25/40/50GbE OS: Ubuntu 20.04, Kernel: 5.4.0-18-generic (x86_64), Desktop: GNOME Shell 3.36.0, Display Server: X Server 1.20.7, Display Driver: modesetting 1.20.7, OpenGL: 3.3 Mesa 20.0.2 (LLVM 9.0.1 256 bits), Compiler: GCC 9.3.0, File-System: ext4, Screen Resolution: 1920x1080 LevelDB 1.22 Benchmark: Hot Read Microseconds Per Op < Lower Is Better 1 . 139.48 |=================================================================== LevelDB 1.22 Benchmark: Fill Sync MB/s > Higher Is Better 1 . 7.2 |====================================================================== LevelDB 1.22 Benchmark: Fill Sync Microseconds Per Op < Lower Is Better 1 . 1684.43 |================================================================== LevelDB 1.22 Benchmark: Overwrite MB/s > Higher Is Better 1 . 8.3 |====================================================================== LevelDB 1.22 Benchmark: Overwrite Microseconds Per Op < Lower Is Better 1 . 1484.37 |================================================================== LevelDB 1.22 Benchmark: Random Fill MB/s > Higher Is Better 1 . 8.5 |====================================================================== LevelDB 1.22 Benchmark: Random Fill Microseconds Per Op < Lower Is Better 1 . 1462.05 |================================================================== LevelDB 1.22 Benchmark: Random Read Microseconds Per Op < Lower Is Better 1 . 140.41 |=================================================================== LevelDB 1.22 Benchmark: Seek Random Microseconds Per Op < Lower Is Better 1 . 172.12 |=================================================================== LevelDB 1.22 Benchmark: Random Delete Microseconds Per Op < Lower Is Better 1 . 1483.27 |================================================================== LevelDB 1.22 Benchmark: Sequential Fill MB/s > Higher Is Better 1 . 8.3 |====================================================================== LevelDB 1.22 Benchmark: Sequential Fill Microseconds Per Op < Lower Is Better 1 . 1493.02 |================================================================== Crafty 25.2 Elapsed Time Nodes Per Second > Higher Is Better 1 .. 7814986 |================================================================= 2a . 7828868 |================================================================= 3 .. 7836358 |================================================================= oneDNN 2.0 Harness: IP Shapes 1D - Data Type: f32 - Engine: CPU ms < Lower Is Better 1 .. 1.35473 |================================================================= 2a . 1.35721 |================================================================= 3 .. 1.35578 |================================================================= oneDNN 2.0 Harness: IP Shapes 3D - Data Type: f32 - Engine: CPU ms < Lower Is Better 1 .. 3.11415 |================================================================= 2a . 3.10481 |================================================================= 3 .. 3.11243 |================================================================= oneDNN 2.0 Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better 1 .. 1.42448 |================================================================= 2a . 1.39211 |================================================================ 3 .. 1.40518 |================================================================ oneDNN 2.0 Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better 1 .. 1.09408 |================================================================= 2a . 1.08503 |================================================================ 3 .. 1.09566 |================================================================= oneDNN 2.0 Harness: IP Shapes 1D - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better 1 .. 3.66713 |================================================================= 2a . 3.66501 |================================================================= 3 .. 3.66413 |================================================================= oneDNN 2.0 Harness: IP Shapes 3D - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better 1 .. 2.47364 |============================================================ 2a . 2.53707 |============================================================= 3 .. 2.68795 |================================================================= oneDNN 2.0 Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPU ms < Lower Is Better 1 .. 3.96134 |================================================================= 2a . 3.99181 |================================================================= 3 .. 3.94281 |================================================================ oneDNN 2.0 Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPU ms < Lower Is Better 1 .. 1.45315 |================================================================= 2a . 1.45003 |================================================================ 3 .. 1.46202 |================================================================= oneDNN 2.0 Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPU ms < Lower Is Better 1 .. 1.21639 |================================================================= 2a . 1.21161 |================================================================= 3 .. 1.21715 |================================================================= oneDNN 2.0 Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better 1 .. 3.70832 |================================================================ 2a . 3.76698 |================================================================= 3 .. 3.70419 |================================================================ oneDNN 2.0 Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better 1 .. 0.425568 |================================================================ 2a . 0.425470 |================================================================ 3 .. 0.424975 |================================================================ oneDNN 2.0 Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better 1 .. 0.349150 |================================================================ 2a . 0.349469 |================================================================ 3 .. 0.349913 |================================================================ oneDNN 2.0 Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPU ms < Lower Is Better 1 .. 989.80 |================================================================= 2a . 995.33 |================================================================== 3 .. 997.88 |================================================================== oneDNN 2.0 Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPU ms < Lower Is Better 1 .. 565.55 |================================================================== 2a . 561.35 |================================================================== 3 .. 563.12 |================================================================== oneDNN 2.0 Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better 1 .. 981.43 |=============================================================== 2a . 1011.76 |================================================================= 3 .. 1007.07 |================================================================= oneDNN 2.0 Harness: Convolution Batch Shapes Auto - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better 1 .. 3.19243 |================================================================= 2a . 3.19695 |================================================================= 3 .. 3.20258 |================================================================= oneDNN 2.0 Harness: Deconvolution Batch shapes_1d - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better 1 .. 4.38392 |================================================================= 2a . 4.38524 |================================================================= 3 .. 4.38139 |================================================================= oneDNN 2.0 Harness: Deconvolution Batch shapes_3d - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better 1 .. 4.44712 |================================================================= 2a . 4.45890 |================================================================= 3 .. 4.44637 |================================================================= oneDNN 2.0 Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better 1 .. 559.66 |================================================================= 2a . 560.97 |================================================================= 3 .. 570.74 |================================================================== oneDNN 2.0 Harness: Matrix Multiply Batch Shapes Transformer - Data Type: f32 - Engine: CPU ms < Lower Is Better 1 .. 0.335755 |================================================================ 2a . 0.337098 |================================================================ 3 .. 0.336753 |================================================================ oneDNN 2.0 Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better 1 .. 979.57 |============================================================= 2a . 1008.34 |============================================================== 3 .. 1050.41 |================================================================= oneDNN 2.0 Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better 1 .. 565.27 |================================================================== 2a . 563.86 |================================================================== 3 .. 562.32 |================================================================== oneDNN 2.0 Harness: Matrix Multiply Batch Shapes Transformer - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better 1 .. 0.271551 |================================================================ 2a . 0.268151 |=============================================================== 3 .. 0.270728 |================================================================ oneDNN 2.0 Harness: Matrix Multiply Batch Shapes Transformer - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better 1 .. 0.817239 |================================================================ 2a . 0.823210 |================================================================ 3 .. 0.822254 |================================================================ rav1e 0.4 Alpha Speed: 1 Frames Per Second > Higher Is Better 1 .. 0.348 |=================================================================== 2a . 0.346 |=================================================================== 3 .. 0.346 |=================================================================== rav1e 0.4 Alpha Speed: 5 Frames Per Second > Higher Is Better 1 .. 0.937 |================================================================== 2a . 0.956 |=================================================================== 3 .. 0.949 |=================================================================== rav1e 0.4 Alpha Speed: 6 Frames Per Second > Higher Is Better 1 .. 1.208 |================================================================== 2a . 1.221 |=================================================================== 3 .. 1.217 |=================================================================== rav1e 0.4 Alpha Speed: 10 Frames Per Second > Higher Is Better 1 .. 2.450 |================================================================== 2a . 2.486 |=================================================================== 3 .. 2.455 |================================================================== Stockfish 12 Total Time Nodes Per Second > Higher Is Better 1 .. 96447530 |================================================================ 2a . 96807159 |================================================================ 3 .. 95164573 |=============================================================== asmFish 2018-07-23 1024 Hash Memory, 26 Depth Nodes/second > Higher Is Better 1 .. 135035548 |=============================================================== 2a . 133208525 |============================================================== 3 .. 132978753 |============================================================== Timed Clash Compilation Time To Compile Seconds < Lower Is Better 1 .. 488.63 |================================================================= 2a . 496.09 |================================================================== 3 .. 492.78 |================================================================== ASTC Encoder 2.0 Preset: Fast Seconds < Lower Is Better 1 .. 5.63 |==================================================================== 2a . 5.60 |==================================================================== 3 .. 5.62 |==================================================================== ASTC Encoder 2.0 Preset: Medium Seconds < Lower Is Better 1 .. 6.61 |==================================================================== 2a . 6.55 |=================================================================== 3 .. 6.60 |==================================================================== ASTC Encoder 2.0 Preset: Thorough Seconds < Lower Is Better 1 .. 7.16 |==================================================================== 2a . 7.15 |==================================================================== 3 .. 7.16 |==================================================================== ASTC Encoder 2.0 Preset: Exhaustive Seconds < Lower Is Better 1 .. 52.33 |=================================================================== 2a . 52.32 |=================================================================== 3 .. 52.33 |=================================================================== OpenVINO 2021.1 Model: Face Detection 0106 FP16 - Device: CPU FPS > Higher Is Better 1 . 15.51 |==================================================================== 3 . 15.53 |==================================================================== OpenVINO 2021.1 Model: Face Detection 0106 FP16 - Device: CPU ms < Lower Is Better 1 . 1784.48 |================================================================== 3 . 1786.64 |================================================================== OpenVINO 2021.1 Model: Face Detection 0106 FP32 - Device: CPU FPS > Higher Is Better 1 . 15.14 |==================================================================== 3 . 15.19 |==================================================================== OpenVINO 2021.1 Model: Face Detection 0106 FP32 - Device: CPU ms < Lower Is Better 1 . 1814.32 |================================================================== 3 . 1814.55 |================================================================== OpenVINO 2021.1 Model: Person Detection 0106 FP16 - Device: CPU FPS > Higher Is Better 1 . 8.74 |==================================================================== 3 . 8.84 |===================================================================== OpenVINO 2021.1 Model: Person Detection 0106 FP16 - Device: CPU ms < Lower Is Better 1 . 3142.67 |================================================================== 3 . 3107.46 |================================================================= OpenVINO 2021.1 Model: Person Detection 0106 FP32 - Device: CPU FPS > Higher Is Better 1 . 8.68 |===================================================================== 3 . 8.72 |===================================================================== OpenVINO 2021.1 Model: Person Detection 0106 FP32 - Device: CPU ms < Lower Is Better 1 . 3152.61 |================================================================== 3 . 3120.88 |================================================================= OpenVINO 2021.1 Model: Age Gender Recognition Retail 0013 FP16 - Device: CPU FPS > Higher Is Better 1 . 38683.48 |================================================================= 3 . 38792.26 |================================================================= OpenVINO 2021.1 Model: Age Gender Recognition Retail 0013 FP16 - Device: CPU ms < Lower Is Better 1 . 0.62 |===================================================================== 3 . 0.62 |===================================================================== OpenVINO 2021.1 Model: Age Gender Recognition Retail 0013 FP32 - Device: CPU FPS > Higher Is Better 1 . 38607.56 |================================================================= 3 . 38565.64 |================================================================= OpenVINO 2021.1 Model: Age Gender Recognition Retail 0013 FP32 - Device: CPU ms < Lower Is Better 1 . 0.62 |===================================================================== 3 . 0.62 |===================================================================== PHPBench 0.8.1 PHP Benchmark Suite Score > Higher Is Better 1 . 666624 |=================================================================== 3 . 668619 |===================================================================