10980XE onednn onnx Intel Core i9-10980XE testing with a ASRock X299 Steel Legend (P1.30 BIOS) and NVIDIA GeForce GTX 1080 Ti 11GB on Ubuntu 22.04 via the Phoronix Test Suite. A: Processor: Intel Core i9-10980XE @ 4.80GHz (18 Cores / 36 Threads), Motherboard: ASRock X299 Steel Legend (P1.30 BIOS), Chipset: Intel Sky Lake-E DMI3 Registers, Memory: 32GB, Disk: Samsung SSD 970 PRO 512GB, Graphics: NVIDIA GeForce GTX 1080 Ti 11GB, Audio: Realtek ALC1220, Monitor: ASUS VP28U, Network: Intel I219-V + Intel I211 OS: Ubuntu 22.04, Kernel: 5.15.0-17-generic (x86_64), Desktop: GNOME Shell 40.5, Display Server: X Server 1.20.13, Display Driver: NVIDIA 495.46, OpenGL: 4.6.0, OpenCL: OpenCL 3.0 CUDA 11.5.103, Vulkan: 1.2.186, Compiler: GCC 11.2.0, File-System: ext4, Screen Resolution: 3840x2160 B: Processor: Intel Core i9-10980XE @ 4.80GHz (18 Cores / 36 Threads), Motherboard: ASRock X299 Steel Legend (P1.30 BIOS), Chipset: Intel Sky Lake-E DMI3 Registers, Memory: 32GB, Disk: Samsung SSD 970 PRO 512GB, Graphics: NVIDIA GeForce GTX 1080 Ti 11GB, Audio: Realtek ALC1220, Monitor: ASUS VP28U, Network: Intel I219-V + Intel I211 OS: Ubuntu 22.04, Kernel: 5.15.0-17-generic (x86_64), Desktop: GNOME Shell 40.5, Display Server: X Server 1.20.13, Display Driver: NVIDIA 495.46, OpenGL: 4.6.0, OpenCL: OpenCL 3.0 CUDA 11.5.103, Vulkan: 1.2.186, Compiler: GCC 11.2.0, File-System: ext4, Screen Resolution: 3840x2160 C: Processor: Intel Core i9-10980XE @ 4.80GHz (18 Cores / 36 Threads), Motherboard: ASRock X299 Steel Legend (P1.30 BIOS), Chipset: Intel Sky Lake-E DMI3 Registers, Memory: 32GB, Disk: Samsung SSD 970 PRO 512GB, Graphics: NVIDIA GeForce GTX 1080 Ti 11GB, Audio: Realtek ALC1220, Monitor: ASUS VP28U, Network: Intel I219-V + Intel I211 OS: Ubuntu 22.04, Kernel: 5.15.0-17-generic (x86_64), Desktop: GNOME Shell 40.5, Display Server: X Server 1.20.13, Display Driver: NVIDIA 495.46, OpenGL: 4.6.0, OpenCL: OpenCL 3.0 CUDA 11.5.103, Vulkan: 1.2.186, Compiler: GCC 11.2.0, File-System: ext4, Screen Resolution: 3840x2160 D: Processor: Intel Core i9-10980XE @ 4.80GHz (18 Cores / 36 Threads), Motherboard: ASRock X299 Steel Legend (P1.30 BIOS), Chipset: Intel Sky Lake-E DMI3 Registers, Memory: 32GB, Disk: Samsung SSD 970 PRO 512GB, Graphics: NVIDIA GeForce GTX 1080 Ti 11GB, Audio: Realtek ALC1220, Monitor: ASUS VP28U, Network: Intel I219-V + Intel I211 OS: Ubuntu 22.04, Kernel: 5.15.0-17-generic (x86_64), Desktop: GNOME Shell 40.5, Display Server: X Server 1.20.13, Display Driver: NVIDIA 495.46, OpenGL: 4.6.0, OpenCL: OpenCL 3.0 CUDA 11.5.103, Vulkan: 1.2.186, Compiler: GCC 11.2.0, File-System: ext4, Screen Resolution: 3840x2160 fast-cli Internet Download Speed Mbit/s > Higher Is Better A . 370 |================================================================== B . 370 |================================================================== C . 390 |====================================================================== D . 360 |================================================================= fast-cli Internet Upload Speed Mbit/s > Higher Is Better A . 6.7 |=========================================================== B . 6.9 |============================================================= C . 7.9 |====================================================================== D . 6.8 |============================================================ fast-cli Internet Latency ms < Lower Is Better A . 8 |============================================ B . 8 |============================================ C . 13 |======================================================================= D . 10 |======================================================= fast-cli Internet Loaded Latency (Bufferbloat) ms < Lower Is Better A . 73 |======================================================================= B . 64 |============================================================== C . 64 |============================================================== D . 70 |==================================================================== speedtest-cli 2.1.3 Internet Download Speed Mbit/s > Higher Is Better A . 324.65 |================================================================== B . 321.74 |================================================================== C . 280.18 |========================================================= D . 327.12 |=================================================================== speedtest-cli 2.1.3 Internet Upload Speed Mbit/s > Higher Is Better A . 9.47 |===================================================================== B . 9.22 |=================================================================== C . 8.40 |============================================================= D . 8.95 |================================================================= speedtest-cli 2.1.3 Internet Latency ms < Lower Is Better A . 23.87 |======================================================== B . 15.49 |===================================== C . 28.78 |==================================================================== D . 22.68 |====================================================== perf-bench Benchmark: Epoll Wait ops/sec > Higher Is Better A . 31157 |============================================================ B . 30615 |=========================================================== C . 35556 |==================================================================== D . 35205 |=================================================================== perf-bench Benchmark: Futex Hash ops/sec > Higher Is Better A . 4494394 |================================================================== B . 4493415 |================================================================== C . 4513944 |================================================================== D . 4499081 |================================================================== perf-bench Benchmark: Memcpy 1MB GB/sec > Higher Is Better A . 17.38 |================================================================== B . 16.77 |================================================================ C . 17.78 |==================================================================== D . 17.28 |================================================================== perf-bench Benchmark: Memset 1MB GB/sec > Higher Is Better A . 66.06 |================================================================= B . 68.32 |=================================================================== C . 69.50 |==================================================================== D . 68.90 |=================================================================== perf-bench Benchmark: Sched Pipe ops/sec > Higher Is Better A . 86982 |==================================================== B . 78301 |=============================================== C . 111014 |=================================================================== D . 76237 |============================================== perf-bench Benchmark: Futex Lock-Pi ops/sec > Higher Is Better A . 236 |====================================================================== B . 215 |================================================================ C . 222 |================================================================== D . 231 |===================================================================== perf-bench Benchmark: Syscall Basic ops/sec > Higher Is Better A . 17140545 |================================================================ B . 17221544 |================================================================ C . 17145832 |================================================================ D . 17504146 |================================================================= oneDNN 2.6 Harness: IP Shapes 1D - Data Type: f32 - Engine: CPU ms < Lower Is Better A . 87.07 |================================================================== B . 89.02 |=================================================================== C . 87.06 |================================================================== D . 90.32 |==================================================================== oneDNN 2.6 Harness: IP Shapes 3D - Data Type: f32 - Engine: CPU ms < Lower Is Better A . 58.08 |==================================================================== B . 58.29 |==================================================================== C . 57.25 |=================================================================== D . 58.44 |==================================================================== oneDNN 2.6 Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better A . 83.90 |================================================================ B . 88.36 |=================================================================== C . 89.52 |==================================================================== D . 89.01 |==================================================================== oneDNN 2.6 Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better A . 44.43 |================================================================== B . 44.22 |================================================================== C . 45.83 |==================================================================== D . 44.40 |================================================================== oneDNN 2.6 Harness: IP Shapes 1D - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better A . 93.31 |==================================================================== B . 93.43 |==================================================================== C . 93.28 |==================================================================== D . 91.70 |=================================================================== oneDNN 2.6 Harness: IP Shapes 3D - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better A . 55.93 |=================================================================== B . 56.06 |=================================================================== C . 56.73 |==================================================================== D . 55.58 |=================================================================== oneDNN 2.6 Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPU ms < Lower Is Better A . 24.06 |=================================================================== B . 24.38 |==================================================================== C . 24.42 |==================================================================== D . 24.35 |==================================================================== oneDNN 2.6 Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPU ms < Lower Is Better A . 99.18 |=========================================================== B . 109.81 |================================================================= C . 107.71 |================================================================ D . 112.62 |=================================================================== oneDNN 2.6 Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPU ms < Lower Is Better A . 19.09 |================================================================== B . 18.70 |================================================================= C . 19.67 |==================================================================== D . 18.94 |================================================================= oneDNN 2.6 Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better A . 23.74 |=================================================================== B . 23.77 |=================================================================== C . 24.06 |==================================================================== D . 23.79 |=================================================================== oneDNN 2.6 Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better A . 50.299600 |============================================================ B . 50.155300 |=========================================================== C . 0.774919 |= D . 54.026200 |================================================================ oneDNN 2.6 Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better A . 9.33345 |================================================================== B . 9.40424 |================================================================== C . 1.62907 |=========== D . 9.35235 |================================================================== oneDNN 2.6 Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPU ms < Lower Is Better A . 23584.2 |================================================================== B . 23366.8 |================================================================= C . 18304.9 |=================================================== D . 23371.5 |================================================================= oneDNN 2.6 Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPU ms < Lower Is Better A . 26069.6 |================================================================ B . 26549.2 |================================================================= C . 26033.7 |================================================================ D . 26872.5 |================================================================== oneDNN 2.6 Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better A . 23516.1 |================================================================= B . 22790.9 |=============================================================== C . 22788.5 |=============================================================== D . 23844.1 |================================================================== oneDNN 2.6 Harness: Convolution Batch Shapes Auto - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better A . 27.00 |==================================================================== B . 25.89 |================================================================= C . 26.18 |================================================================== D . 25.94 |================================================================= oneDNN 2.6 Harness: Deconvolution Batch shapes_1d - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better A . 116.51 |========================================================== B . 135.47 |=================================================================== C . 130.96 |================================================================= D . 118.15 |========================================================== oneDNN 2.6 Harness: Deconvolution Batch shapes_3d - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better A . 22.40 |================================================================ B . 23.90 |==================================================================== C . 22.76 |================================================================= D . 23.02 |================================================================= oneDNN 2.6 Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better A . 28356.5 |================================================================= B . 27247.5 |=============================================================== C . 28624.4 |================================================================== D . 28758.8 |================================================================== oneDNN 2.6 Harness: Matrix Multiply Batch Shapes Transformer - Data Type: f32 - Engine: CPU ms < Lower Is Better A . 35.20 |================================================================== B . 36.36 |==================================================================== C . 26.99 |================================================== D . 31.27 |========================================================== oneDNN 2.6 Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better A . 22990.4 |================================================================= B . 22726.7 |================================================================ C . 22605.3 |================================================================ D . 23319.6 |================================================================== oneDNN 2.6 Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better A . 27155.0 |=============================================================== B . 27353.6 |=============================================================== C . 28513.6 |================================================================== D . 28429.2 |================================================================== oneDNN 2.6 Harness: Matrix Multiply Batch Shapes Transformer - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better A . 30.78 |============================================================= B . 34.52 |==================================================================== C . 30.88 |============================================================= D . 33.38 |================================================================== oneDNN 2.6 Harness: Matrix Multiply Batch Shapes Transformer - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better A . 37.79 |================================================================== B . 39.05 |==================================================================== C . 37.78 |================================================================== D . 37.55 |================================================================= Java JMH Throughput Ops/s > Higher Is Better A . 33246015808.70 |=========================================================== B . 33247767440.99 |=========================================================== C . 33236796629.92 |=========================================================== D . 33246121586.08 |=========================================================== ONNX Runtime 1.11 Model: GPT-2 - Device: CPU - Executor: Parallel Inferences Per Minute > Higher Is Better A . 5799 |================================================================= B . 5795 |================================================================= C . 6114 |===================================================================== D . 6072 |===================================================================== ONNX Runtime 1.11 Model: GPT-2 - Device: CPU - Executor: Standard Inferences Per Minute > Higher Is Better A . 8749 |=============================================================== B . 8812 |=============================================================== C . 9595 |===================================================================== D . 9591 |===================================================================== ONNX Runtime 1.11 Model: yolov4 - Device: CPU - Executor: Parallel Inferences Per Minute > Higher Is Better A . 444 |===================================================================== B . 448 |====================================================================== C . 447 |====================================================================== D . 449 |====================================================================== ONNX Runtime 1.11 Model: yolov4 - Device: CPU - Executor: Standard Inferences Per Minute > Higher Is Better A . 665 |==================================================================== B . 663 |==================================================================== C . 680 |====================================================================== D . 569 |=========================================================== ONNX Runtime 1.11 Model: bertsquad-12 - Device: CPU - Executor: Parallel Inferences Per Minute > Higher Is Better A . 782 |===================================================================== B . 774 |==================================================================== C . 786 |===================================================================== D . 796 |====================================================================== ONNX Runtime 1.11 Model: bertsquad-12 - Device: CPU - Executor: Standard Inferences Per Minute > Higher Is Better A . 897 |==================================================================== B . 911 |===================================================================== C . 923 |====================================================================== D . 897 |==================================================================== ONNX Runtime 1.11 Model: fcn-resnet101-11 - Device: CPU - Executor: Parallel Inferences Per Minute > Higher Is Better A . 101 |===================================================================== B . 102 |====================================================================== C . 101 |===================================================================== D . 101 |===================================================================== ONNX Runtime 1.11 Model: fcn-resnet101-11 - Device: CPU - Executor: Standard Inferences Per Minute > Higher Is Better A . 148 |====================================================================== B . 119 |======================================================== D . 148 |====================================================================== ONNX Runtime 1.11 Model: ArcFace ResNet-100 - Device: CPU - Executor: Parallel Inferences Per Minute > Higher Is Better A . 1464 |==================================================================== B . 1474 |==================================================================== D . 1491 |===================================================================== ONNX Runtime 1.11 Model: ArcFace ResNet-100 - Device: CPU - Executor: Standard Inferences Per Minute > Higher Is Better A . 2053 |===================================================================== B . 1538 |==================================================== D . 2014 |==================================================================== ONNX Runtime 1.11 Model: super-resolution-10 - Device: CPU - Executor: Parallel Inferences Per Minute > Higher Is Better A . 5890 |==================================================================== B . 5975 |===================================================================== D . 5969 |===================================================================== ONNX Runtime 1.11 Model: super-resolution-10 - Device: CPU - Executor: Standard Inferences Per Minute > Higher Is Better A . 6168 |========================================= B . 9884 |================================================================== D . 10255 |====================================================================