new t Intel Core i7-8700K testing with a ASUS TUF Z370-PLUS GAMING (2001 BIOS) and ASUS Intel UHD 630 3GB on Ubuntu 20.04 via the Phoronix Test Suite. 1: Processor: Intel Core i7-8700K @ 4.70GHz (6 Cores / 12 Threads), Motherboard: ASUS TUF Z370-PLUS GAMING (2001 BIOS), Chipset: Intel 8th Gen Core, Memory: 16GB, Disk: 128GB THNSN5128GPU7 TOSHIBA, Graphics: ASUS Intel UHD 630 3GB (1200MHz), Audio: Realtek ALC887-VD, Monitor: VA2431, Network: Intel I219-V OS: Ubuntu 20.04, Kernel: 5.9.0-050900rc6daily20200923-generic (x86_64) 20200922, Desktop: GNOME Shell 3.36.4, Display Server: X Server 1.20.8, Display Driver: modesetting 1.20.8, OpenGL: 4.6 Mesa 20.0.8, OpenCL: OpenCL 2.1, Compiler: GCC 9.3.0, File-System: ext4, Screen Resolution: 1920x1080 2: Processor: Intel Core i7-8700K @ 4.70GHz (6 Cores / 12 Threads), Motherboard: ASUS TUF Z370-PLUS GAMING (2001 BIOS), Chipset: Intel 8th Gen Core, Memory: 16GB, Disk: 128GB THNSN5128GPU7 TOSHIBA, Graphics: ASUS Intel UHD 630 3GB (1200MHz), Audio: Realtek ALC887-VD, Monitor: VA2431, Network: Intel I219-V OS: Ubuntu 20.04, Kernel: 5.9.0-050900rc6daily20200923-generic (x86_64) 20200922, Desktop: GNOME Shell 3.36.4, Display Server: X Server 1.20.8, Display Driver: modesetting 1.20.8, OpenGL: 4.6 Mesa 20.0.8, OpenCL: OpenCL 2.1, Compiler: GCC 9.3.0, File-System: ext4, Screen Resolution: 1920x1080 3: Processor: Intel Core i7-8700K @ 4.70GHz (6 Cores / 12 Threads), Motherboard: ASUS TUF Z370-PLUS GAMING (2001 BIOS), Chipset: Intel 8th Gen Core, Memory: 16GB, Disk: 128GB THNSN5128GPU7 TOSHIBA, Graphics: ASUS Intel UHD 630 3GB (1200MHz), Audio: Realtek ALC887-VD, Monitor: VA2431, Network: Intel I219-V OS: Ubuntu 20.04, Kernel: 5.9.0-050900rc6daily20200923-generic (x86_64) 20200922, Desktop: GNOME Shell 3.36.4, Display Server: X Server 1.20.8, Display Driver: modesetting 1.20.8, OpenGL: 4.6 Mesa 20.0.8, OpenCL: OpenCL 2.1, Compiler: GCC 9.3.0, File-System: ext4, Screen Resolution: 1920x1080 VKMark 2020-05-21 Resolution: 800 x 600 VKMark Score > Higher Is Better 1 . 3591 |===================================================================== 2 . 3559 |==================================================================== 3 . 3580 |===================================================================== VKMark 2020-05-21 Resolution: 1024 x 768 VKMark Score > Higher Is Better 1 . 2332 |=================================================================== 2 . 2350 |==================================================================== 3 . 2385 |===================================================================== VKMark 2020-05-21 Resolution: 1280 x 1024 VKMark Score > Higher Is Better 1 . 1238 |===================================================================== 2 . 1218 |==================================================================== 3 . 1193 |================================================================== VKMark 2020-05-21 Resolution: 1920 x 1080 VKMark Score > Higher Is Better 1 . 748 |====================================================================== 2 . 743 |====================================================================== 3 . 743 |====================================================================== CLOMP 1.2 Static OMP Speedup Speedup > Higher Is Better 1 . 2.6 |====================================================================== 2 . 2.6 |====================================================================== 3 . 2.6 |====================================================================== oneDNN 2.0 Harness: IP Shapes 1D - Data Type: f32 - Engine: CPU ms < Lower Is Better 1 . 4.60490 |================================================================== 2 . 4.59836 |================================================================== 3 . 4.59793 |================================================================== oneDNN 2.0 Harness: IP Shapes 3D - Data Type: f32 - Engine: CPU ms < Lower Is Better 1 . 9.38610 |================================================================== 2 . 9.40831 |================================================================== 3 . 9.37952 |================================================================== oneDNN 2.0 Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better 1 . 2.15093 |================================================================== 2 . 2.15289 |================================================================== 3 . 2.15051 |================================================================== oneDNN 2.0 Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better 1 . 2.36631 |================================================================== 2 . 2.36740 |================================================================== 3 . 2.35204 |================================================================== oneDNN 2.0 Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPU ms < Lower Is Better 1 . 17.07 |==================================================================== 2 . 17.06 |==================================================================== 3 . 17.06 |==================================================================== oneDNN 2.0 Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPU ms < Lower Is Better 1 . 6.34173 |================================================================== 2 . 6.36630 |================================================================== 3 . 6.34882 |================================================================== oneDNN 2.0 Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPU ms < Lower Is Better 1 . 9.03110 |================================================================== 2 . 9.02182 |================================================================== 3 . 9.00867 |================================================================== oneDNN 2.0 Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better 1 . 15.98 |==================================================================== 2 . 16.00 |==================================================================== 3 . 15.99 |==================================================================== oneDNN 2.0 Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better 1 . 6.84431 |================================================================= 2 . 6.90904 |================================================================== 3 . 6.86786 |================================================================== oneDNN 2.0 Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better 1 . 4.24873 |================================================================== 2 . 4.25392 |================================================================== 3 . 4.25571 |================================================================== oneDNN 2.0 Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPU ms < Lower Is Better 1 . 4026.06 |================================================================== 2 . 4020.25 |================================================================== 3 . 4022.24 |================================================================== oneDNN 2.0 Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPU ms < Lower Is Better 1 . 2261.96 |================================================================== 2 . 2262.71 |================================================================== 3 . 2261.15 |================================================================== oneDNN 2.0 Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better 1 . 4024.58 |================================================================== 2 . 4022.06 |================================================================== 3 . 4021.82 |================================================================== oneDNN 2.0 Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better 1 . 2261.73 |================================================================== 2 . 2261.38 |================================================================== 3 . 2265.16 |================================================================== oneDNN 2.0 Harness: Matrix Multiply Batch Shapes Transformer - Data Type: f32 - Engine: CPU ms < Lower Is Better 1 . 3.87423 |================================================================== 2 . 3.86130 |================================================================== 3 . 3.87904 |================================================================== oneDNN 2.0 Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better 1 . 4023.72 |================================================================== 2 . 4028.04 |================================================================== 3 . 4031.07 |================================================================== oneDNN 2.0 Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better 1 . 2400.84 |================================================================== 2 . 2261.23 |============================================================== 3 . 2262.48 |============================================================== oneDNN 2.0 Harness: Matrix Multiply Batch Shapes Transformer - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better 1 . 3.95323 |================================================================== 2 . 3.95351 |================================================================== 3 . 3.95503 |================================================================== Timed Eigen Compilation 3.3.9 Time To Compile Seconds < Lower Is Better 1 . 71.07 |==================================================================== 2 . 71.29 |==================================================================== 3 . 71.10 |==================================================================== Monkey Audio Encoding 3.99.6 WAV To APE Seconds < Lower Is Better 1 . 10.48 |==================================================================== 2 . 10.43 |==================================================================== 3 . 10.45 |==================================================================== Opus Codec Encoding 1.3.1 WAV To Opus Encode Seconds < Lower Is Better 1 . 8.172 |==================================================================== 2 . 8.163 |==================================================================== 3 . 8.156 |==================================================================== NCNN 20201218 Target: CPU - Model: mobilenet ms < Lower Is Better 1 . 19.41 |==================================================================== 2 . 19.50 |==================================================================== 3 . 19.47 |==================================================================== NCNN 20201218 Target: CPU-v2-v2 - Model: mobilenet-v2 ms < Lower Is Better 1 . 5.57 |===================================================================== 2 . 5.53 |===================================================================== 3 . 5.54 |===================================================================== NCNN 20201218 Target: CPU-v3-v3 - Model: mobilenet-v3 ms < Lower Is Better 1 . 4.50 |===================================================================== 2 . 4.44 |==================================================================== 3 . 4.47 |===================================================================== NCNN 20201218 Target: CPU - Model: shufflenet-v2 ms < Lower Is Better 1 . 5.89 |===================================================================== 2 . 5.87 |===================================================================== 3 . 5.88 |===================================================================== NCNN 20201218 Target: CPU - Model: mnasnet ms < Lower Is Better 1 . 4.45 |===================================================================== 2 . 4.45 |===================================================================== 3 . 4.45 |===================================================================== NCNN 20201218 Target: CPU - Model: efficientnet-b0 ms < Lower Is Better 1 . 7.32 |===================================================================== 2 . 7.30 |===================================================================== 3 . 7.30 |===================================================================== NCNN 20201218 Target: CPU - Model: blazeface ms < Lower Is Better 1 . 1.86 |===================================================================== 2 . 1.85 |===================================================================== 3 . 1.85 |===================================================================== NCNN 20201218 Target: CPU - Model: googlenet ms < Lower Is Better 1 . 15.62 |==================================================================== 2 . 15.61 |==================================================================== 3 . 15.65 |==================================================================== NCNN 20201218 Target: CPU - Model: vgg16 ms < Lower Is Better 1 . 64.88 |==================================================================== 2 . 64.93 |==================================================================== 3 . 64.84 |==================================================================== NCNN 20201218 Target: CPU - Model: resnet18 ms < Lower Is Better 1 . 16.01 |==================================================================== 2 . 15.98 |==================================================================== 3 . 15.98 |==================================================================== NCNN 20201218 Target: CPU - Model: alexnet ms < Lower Is Better 1 . 13.56 |==================================================================== 2 . 13.55 |==================================================================== 3 . 13.56 |==================================================================== NCNN 20201218 Target: CPU - Model: resnet50 ms < Lower Is Better 1 . 31.30 |==================================================================== 2 . 31.36 |==================================================================== 3 . 31.29 |==================================================================== NCNN 20201218 Target: CPU - Model: yolov4-tiny ms < Lower Is Better 1 . 28.49 |==================================================================== 2 . 28.51 |==================================================================== 3 . 28.53 |==================================================================== NCNN 20201218 Target: CPU - Model: squeezenet_ssd ms < Lower Is Better 1 . 20.63 |==================================================================== 2 . 20.69 |==================================================================== 3 . 20.67 |==================================================================== NCNN 20201218 Target: CPU - Model: regnety_400m ms < Lower Is Better 1 . 14.22 |==================================================================== 2 . 14.19 |==================================================================== 3 . 14.17 |==================================================================== NCNN 20201218 Target: Vulkan GPU - Model: mobilenet ms < Lower Is Better 1 . 19.41 |==================================================================== 2 . 19.45 |==================================================================== 3 . 19.55 |==================================================================== NCNN 20201218 Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2 ms < Lower Is Better 1 . 5.57 |===================================================================== 2 . 5.54 |===================================================================== 3 . 5.54 |===================================================================== NCNN 20201218 Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3 ms < Lower Is Better 1 . 4.47 |===================================================================== 2 . 4.48 |===================================================================== 3 . 4.45 |===================================================================== NCNN 20201218 Target: Vulkan GPU - Model: shufflenet-v2 ms < Lower Is Better 1 . 5.87 |===================================================================== 2 . 5.85 |===================================================================== 3 . 5.88 |===================================================================== NCNN 20201218 Target: Vulkan GPU - Model: mnasnet ms < Lower Is Better 1 . 4.41 |==================================================================== 2 . 4.43 |===================================================================== 3 . 4.45 |===================================================================== NCNN 20201218 Target: Vulkan GPU - Model: efficientnet-b0 ms < Lower Is Better 1 . 7.30 |===================================================================== 2 . 7.29 |===================================================================== 3 . 7.29 |===================================================================== NCNN 20201218 Target: Vulkan GPU - Model: blazeface ms < Lower Is Better 1 . 1.85 |===================================================================== 2 . 1.86 |===================================================================== 3 . 1.85 |===================================================================== NCNN 20201218 Target: Vulkan GPU - Model: googlenet ms < Lower Is Better 1 . 15.74 |==================================================================== 2 . 15.59 |=================================================================== 3 . 15.60 |=================================================================== NCNN 20201218 Target: Vulkan GPU - Model: vgg16 ms < Lower Is Better 1 . 64.91 |==================================================================== 2 . 64.85 |==================================================================== 3 . 64.86 |==================================================================== NCNN 20201218 Target: Vulkan GPU - Model: resnet18 ms < Lower Is Better 1 . 15.97 |==================================================================== 2 . 16.01 |==================================================================== 3 . 15.99 |==================================================================== NCNN 20201218 Target: Vulkan GPU - Model: alexnet ms < Lower Is Better 1 . 13.59 |==================================================================== 2 . 13.56 |==================================================================== 3 . 13.58 |==================================================================== NCNN 20201218 Target: Vulkan GPU - Model: resnet50 ms < Lower Is Better 1 . 31.32 |==================================================================== 2 . 31.36 |==================================================================== 3 . 31.39 |==================================================================== NCNN 20201218 Target: Vulkan GPU - Model: yolov4-tiny ms < Lower Is Better 1 . 28.48 |==================================================================== 2 . 28.51 |==================================================================== 3 . 28.69 |==================================================================== NCNN 20201218 Target: Vulkan GPU - Model: squeezenet_ssd ms < Lower Is Better 1 . 20.69 |==================================================================== 2 . 20.63 |=================================================================== 3 . 20.79 |==================================================================== NCNN 20201218 Target: Vulkan GPU - Model: regnety_400m ms < Lower Is Better 1 . 14.19 |==================================================================== 2 . 14.07 |=================================================================== 3 . 14.12 |==================================================================== WavPack Audio Encoding 5.3 WAV To WavPack Seconds < Lower Is Better 1 . 13.84 |==================================================================== 2 . 13.84 |==================================================================== 3 . 13.84 |====================================================================