ncnn mnn 2022 AMD Ryzen 9 5950X 16-Core testing with a ASUS ROG CROSSHAIR VIII HERO (WI-FI) (4006 BIOS) and AMD Radeon RX 6700/6700 XT / 6800M on Ubuntu 22.04 via the Phoronix Test Suite. A: Processor: AMD Ryzen 9 5950X 16-Core @ 3.40GHz (16 Cores / 32 Threads), Motherboard: ASUS ROG CROSSHAIR VIII HERO (WI-FI) (4006 BIOS), Chipset: AMD Starship/Matisse, Memory: 32GB, Disk: 1000GB Sabrent Rocket 4.0 Plus, Graphics: AMD Radeon RX 6700/6700 XT / 6800M (2880/1124MHz), Audio: AMD Navi 21 HDMI Audio, Monitor: ASUS MG28U, Network: Realtek RTL8125 2.5GbE + Intel I211 + Intel Wi-Fi 6 AX200 OS: Ubuntu 22.04, Kernel: 5.15.0-46-generic (x86_64), Desktop: GNOME Shell 42.2, Display Server: X Server 1.21.1.3 + Wayland, OpenGL: 4.6 Mesa 22.0.1 (LLVM 13.0.1 DRM 3.42), Vulkan: 1.3.204, Compiler: GCC 11.2.0, File-System: ext4, Screen Resolution: 3840x2160 B: Processor: AMD Ryzen 9 5950X 16-Core @ 3.40GHz (16 Cores / 32 Threads), Motherboard: ASUS ROG CROSSHAIR VIII HERO (WI-FI) (4006 BIOS), Chipset: AMD Starship/Matisse, Memory: 32GB, Disk: 1000GB Sabrent Rocket 4.0 Plus, Graphics: AMD Radeon RX 6700/6700 XT / 6800M (2880/1124MHz), Audio: AMD Navi 21 HDMI Audio, Monitor: ASUS MG28U, Network: Realtek RTL8125 2.5GbE + Intel I211 + Intel Wi-Fi 6 AX200 OS: Ubuntu 22.04, Kernel: 5.15.0-46-generic (x86_64), Desktop: GNOME Shell 42.2, Display Server: X Server 1.21.1.3 + Wayland, OpenGL: 4.6 Mesa 22.0.1 (LLVM 13.0.1 DRM 3.42), Vulkan: 1.3.204, Compiler: GCC 11.2.0, File-System: ext4, Screen Resolution: 3840x2160 C: Processor: AMD Ryzen 9 5950X 16-Core @ 3.40GHz (16 Cores / 32 Threads), Motherboard: ASUS ROG CROSSHAIR VIII HERO (WI-FI) (4006 BIOS), Chipset: AMD Starship/Matisse, Memory: 32GB, Disk: 1000GB Sabrent Rocket 4.0 Plus, Graphics: AMD Radeon RX 6700/6700 XT / 6800M (2880/1124MHz), Audio: AMD Navi 21 HDMI Audio, Monitor: ASUS MG28U, Network: Realtek RTL8125 2.5GbE + Intel I211 + Intel Wi-Fi 6 AX200 OS: Ubuntu 22.04, Kernel: 5.15.0-46-generic (x86_64), Desktop: GNOME Shell 42.2, Display Server: X Server 1.21.1.3 + Wayland, OpenGL: 4.6 Mesa 22.0.1 (LLVM 13.0.1 DRM 3.42), Vulkan: 1.3.204, Compiler: GCC 11.2.0, File-System: ext4, Screen Resolution: 3840x2160 D: Processor: AMD Ryzen 9 5950X 16-Core @ 3.40GHz (16 Cores / 32 Threads), Motherboard: ASUS ROG CROSSHAIR VIII HERO (WI-FI) (4006 BIOS), Chipset: AMD Starship/Matisse, Memory: 32GB, Disk: 1000GB Sabrent Rocket 4.0 Plus, Graphics: AMD Radeon RX 6700/6700 XT / 6800M (2880/1124MHz), Audio: AMD Navi 21 HDMI Audio, Monitor: ASUS MG28U, Network: Realtek RTL8125 2.5GbE + Intel I211 + Intel Wi-Fi 6 AX200 OS: Ubuntu 22.04, Kernel: 5.15.0-46-generic (x86_64), Desktop: GNOME Shell 42.2, Display Server: X Server 1.21.1.3 + Wayland, OpenGL: 4.6 Mesa 22.0.1 (LLVM 13.0.1 DRM 3.42), Vulkan: 1.3.204, Compiler: GCC 11.2.0, File-System: ext4, Screen Resolution: 3840x2160 E: Processor: AMD Ryzen 9 5950X 16-Core @ 3.40GHz (16 Cores / 32 Threads), Motherboard: ASUS ROG CROSSHAIR VIII HERO (WI-FI) (4006 BIOS), Chipset: AMD Starship/Matisse, Memory: 32GB, Disk: 1000GB Sabrent Rocket 4.0 Plus, Graphics: AMD Radeon RX 6700/6700 XT / 6800M (2880/1124MHz), Audio: AMD Navi 21 HDMI Audio, Monitor: ASUS MG28U, Network: Realtek RTL8125 2.5GbE + Intel I211 + Intel Wi-Fi 6 AX200 OS: Ubuntu 22.04, Kernel: 5.15.0-46-generic (x86_64), Desktop: GNOME Shell 42.2, Display Server: X Server 1.21.1.3 + Wayland, OpenGL: 4.6 Mesa 22.0.1 (LLVM 13.0.1 DRM 3.42), Vulkan: 1.3.204, Compiler: GCC 11.2.0, File-System: ext4, Screen Resolution: 3840x2160 Mobile Neural Network 2.0 Model: mobilenetV3 ms < Lower Is Better A . 1.903 |==================================================================== B . 1.860 |================================================================== C . 1.865 |================================================================== D . 1.913 |==================================================================== E . 1.902 |==================================================================== Mobile Neural Network 2.0 Model: squeezenetv1.1 ms < Lower Is Better A . 3.209 |================================================================== B . 3.227 |=================================================================== C . 3.278 |==================================================================== D . 3.298 |==================================================================== E . 3.296 |==================================================================== Mobile Neural Network 2.0 Model: resnet-v2-50 ms < Lower Is Better A . 21.96 |==================================================================== B . 21.56 |=================================================================== C . 21.10 |================================================================= D . 21.70 |=================================================================== E . 21.54 |=================================================================== Mobile Neural Network 2.0 Model: SqueezeNetV1.0 ms < Lower Is Better A . 5.234 |================================================================== B . 5.144 |================================================================= C . 5.350 |==================================================================== D . 5.302 |=================================================================== E . 5.382 |==================================================================== Mobile Neural Network 2.0 Model: MobileNetV2_224 ms < Lower Is Better A . 3.449 |==================================================================== B . 3.422 |=================================================================== C . 3.468 |==================================================================== D . 3.456 |==================================================================== E . 3.472 |==================================================================== Mobile Neural Network 2.0 Model: mobilenet-v1-1.0 ms < Lower Is Better A . 2.625 |==================================================================== B . 2.542 |================================================================== C . 2.556 |================================================================== D . 2.592 |=================================================================== E . 2.581 |=================================================================== Mobile Neural Network 2.0 Model: inception-v3 ms < Lower Is Better A . 26.07 |==================================================================== B . 25.81 |=================================================================== C . 25.91 |==================================================================== D . 25.92 |==================================================================== E . 25.99 |==================================================================== NCNN 20220729 Target: CPU - Model: mobilenet ms < Lower Is Better A . 11.46 |================================================================= B . 11.92 |==================================================================== C . 11.71 |=================================================================== D . 11.84 |==================================================================== E . 11.64 |================================================================== NCNN 20220729 Target: CPU-v2-v2 - Model: mobilenet-v2 ms < Lower Is Better A . 4.29 |==================================================================== B . 4.33 |===================================================================== C . 4.28 |==================================================================== D . 4.31 |===================================================================== E . 4.30 |===================================================================== NCNN 20220729 Target: CPU-v3-v3 - Model: mobilenet-v3 ms < Lower Is Better A . 3.78 |==================================================================== B . 3.82 |===================================================================== C . 3.77 |==================================================================== D . 3.77 |==================================================================== E . 3.76 |==================================================================== NCNN 20220729 Target: CPU - Model: shufflenet-v2 ms < Lower Is Better A . 4.30 |===================================================================== B . 4.30 |===================================================================== C . 4.30 |===================================================================== D . 4.26 |==================================================================== E . 4.28 |===================================================================== NCNN 20220729 Target: CPU - Model: mnasnet ms < Lower Is Better A . 3.89 |==================================================================== B . 3.97 |===================================================================== C . 3.89 |==================================================================== D . 3.90 |==================================================================== E . 3.90 |==================================================================== NCNN 20220729 Target: CPU - Model: efficientnet-b0 ms < Lower Is Better A . 5.91 |==================================================================== B . 5.97 |==================================================================== C . 5.90 |==================================================================== D . 6.02 |===================================================================== E . 5.90 |==================================================================== NCNN 20220729 Target: CPU - Model: blazeface ms < Lower Is Better A . 1.82 |=================================================================== B . 1.80 |================================================================== C . 1.82 |=================================================================== D . 1.88 |===================================================================== E . 1.83 |=================================================================== NCNN 20220729 Target: CPU - Model: googlenet ms < Lower Is Better A . 12.19 |==================================================================== B . 11.69 |================================================================= C . 11.38 |=============================================================== D . 11.56 |================================================================ E . 11.53 |================================================================ NCNN 20220729 Target: CPU - Model: vgg16 ms < Lower Is Better A . 47.58 |=================================================================== B . 47.52 |=================================================================== C . 47.58 |=================================================================== D . 47.34 |=================================================================== E . 47.94 |==================================================================== NCNN 20220729 Target: CPU - Model: resnet18 ms < Lower Is Better A . 12.17 |==================================================================== B . 12.21 |==================================================================== C . 12.08 |=================================================================== D . 12.16 |==================================================================== E . 12.14 |==================================================================== NCNN 20220729 Target: CPU - Model: alexnet ms < Lower Is Better A . 7.79 |========================================================== B . 7.73 |========================================================= C . 7.67 |========================================================= D . 7.72 |========================================================= E . 9.30 |===================================================================== NCNN 20220729 Target: CPU - Model: resnet50 ms < Lower Is Better A . 21.47 |=================================================================== B . 20.98 |================================================================== C . 21.70 |==================================================================== D . 21.48 |=================================================================== E . 21.39 |=================================================================== NCNN 20220729 Target: CPU - Model: yolov4-tiny ms < Lower Is Better A . 21.51 |==================================================================== B . 21.33 |=================================================================== C . 21.57 |==================================================================== D . 21.30 |=================================================================== E . 21.43 |==================================================================== NCNN 20220729 Target: CPU - Model: squeezenet_ssd ms < Lower Is Better A . 18.32 |=================================================================== B . 18.53 |==================================================================== C . 18.59 |==================================================================== D . 18.39 |=================================================================== E . 18.17 |================================================================== NCNN 20220729 Target: CPU - Model: regnety_400m ms < Lower Is Better A . 12.83 |==================================================================== B . 12.81 |==================================================================== C . 12.90 |==================================================================== D . 12.85 |==================================================================== E . 12.79 |=================================================================== NCNN 20220729 Target: CPU - Model: vision_transformer ms < Lower Is Better A . 123.55 |=================================================================== B . 122.89 |================================================================== C . 122.63 |================================================================== D . 123.87 |=================================================================== E . 123.44 |=================================================================== NCNN 20220729 Target: CPU - Model: FastestDet ms < Lower Is Better A . 4.98 |===================================================================== B . 4.90 |==================================================================== C . 4.93 |==================================================================== D . 4.86 |=================================================================== E . 4.84 |=================================================================== NCNN 20220729 Target: Vulkan GPU - Model: mobilenet ms < Lower Is Better A . 9.45 |================================================================ B . 9.34 |=============================================================== C . 9.84 |=================================================================== D . 9.90 |=================================================================== E . 10.05 |==================================================================== NCNN 20220729 Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2 ms < Lower Is Better A . 1.92 |================================================================== B . 1.95 |=================================================================== C . 1.99 |===================================================================== D . 1.98 |==================================================================== E . 2.00 |===================================================================== NCNN 20220729 Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3 ms < Lower Is Better A . 2.35 |=================================================================== B . 2.36 |==================================================================== C . 2.34 |=================================================================== D . 2.36 |==================================================================== E . 2.41 |===================================================================== NCNN 20220729 Target: Vulkan GPU - Model: shufflenet-v2 ms < Lower Is Better A . 2.04 |================================================================== B . 2.12 |===================================================================== C . 2.09 |==================================================================== D . 2.09 |==================================================================== E . 2.09 |==================================================================== NCNN 20220729 Target: Vulkan GPU - Model: mnasnet ms < Lower Is Better A . 1.97 |=================================================================== B . 2.04 |===================================================================== C . 2.01 |==================================================================== D . 2.04 |===================================================================== E . 2.04 |===================================================================== NCNN 20220729 Target: Vulkan GPU - Model: efficientnet-b0 ms < Lower Is Better A . 4.93 |===================================================================== B . 4.89 |==================================================================== C . 4.90 |===================================================================== D . 4.86 |==================================================================== E . 4.86 |==================================================================== NCNN 20220729 Target: Vulkan GPU - Model: blazeface ms < Lower Is Better A . 1.64 |==================================================================== B . 1.60 |=================================================================== C . 1.65 |===================================================================== D . 1.64 |==================================================================== E . 1.66 |===================================================================== NCNN 20220729 Target: Vulkan GPU - Model: googlenet ms < Lower Is Better A . 3.67 |==================================================================== B . 3.71 |===================================================================== C . 3.66 |==================================================================== D . 3.71 |===================================================================== E . 3.72 |===================================================================== NCNN 20220729 Target: Vulkan GPU - Model: vgg16 ms < Lower Is Better A . 6.77 |=================================================================== B . 6.93 |===================================================================== C . 6.75 |=================================================================== D . 6.75 |=================================================================== E . 6.80 |==================================================================== NCNN 20220729 Target: Vulkan GPU - Model: resnet18 ms < Lower Is Better A . 2.63 |===================================================================== B . 2.54 |=================================================================== C . 2.60 |==================================================================== D . 2.61 |==================================================================== E . 2.62 |===================================================================== NCNN 20220729 Target: Vulkan GPU - Model: alexnet ms < Lower Is Better A . 2.08 |================================================================ B . 2.24 |===================================================================== C . 2.09 |================================================================ D . 2.08 |================================================================ E . 2.12 |================================================================= NCNN 20220729 Target: Vulkan GPU - Model: resnet50 ms < Lower Is Better A . 4.99 |===================================================================== B . 4.94 |==================================================================== C . 5.00 |===================================================================== D . 5.00 |===================================================================== E . 4.97 |===================================================================== NCNN 20220729 Target: Vulkan GPU - Model: yolov4-tiny ms < Lower Is Better A . 14.58 |=================================================================== B . 14.48 |=================================================================== C . 14.56 |=================================================================== D . 14.59 |=================================================================== E . 14.77 |==================================================================== NCNN 20220729 Target: Vulkan GPU - Model: squeezenet_ssd ms < Lower Is Better A . 5.23 |================================================================= B . 5.14 |================================================================ C . 5.47 |==================================================================== D . 5.50 |==================================================================== E . 5.55 |===================================================================== NCNN 20220729 Target: Vulkan GPU - Model: regnety_400m ms < Lower Is Better A . 3.11 |===================================================================== B . 3.03 |=================================================================== C . 3.09 |===================================================================== D . 3.08 |==================================================================== E . 3.06 |==================================================================== NCNN 20220729 Target: Vulkan GPU - Model: vision_transformer ms < Lower Is Better A . 220.75 |=================================================================== B . 219.90 |=================================================================== C . 219.57 |=================================================================== D . 220.31 |=================================================================== E . 220.85 |=================================================================== NCNN 20220729 Target: Vulkan GPU - Model: FastestDet ms < Lower Is Better A . 2.50 |===================================================================== B . 2.28 |=============================================================== C . 2.33 |================================================================ D . 2.38 |================================================================== E . 2.37 |=================================================================