NN TR 3960X + Radeon RX 5500 XT AMD Ryzen Threadripper 3960X 24-Core testing with a MSI Creator TRX40 (MS-7C59) v1.0 (1.12N1 BIOS) and Sapphire AMD Radeon RX 5500/5500M / Pro 5500M 4GB on Ubuntu 20.04 via the Phoronix Test Suite. 1: Processor: AMD Ryzen Threadripper 3960X 24-Core @ 3.80GHz (24 Cores / 48 Threads), Motherboard: MSI Creator TRX40 (MS-7C59) v1.0 (1.12N1 BIOS), Chipset: AMD Starship/Matisse, Memory: 32GB, Disk: 1000GB Sabrent Rocket 4.0 1TB, Graphics: Sapphire AMD Radeon RX 5500/5500M / Pro 5500M 4GB (1900/875MHz), Audio: AMD Navi 10 HDMI Audio, Monitor: ASUS MG28U, Network: Aquantia AQC107 NBase-T/IEEE + Intel I211 + Intel Wi-Fi 6 AX200 OS: Ubuntu 20.04, Kernel: 5.9.0-rc5-14sep-patch (x86_64) 20200914, 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 (LLVM 10.0.0), Vulkan: 1.2.128, Compiler: GCC 9.3.0, File-System: ext4, Screen Resolution: 3840x2160 2: Processor: AMD Ryzen Threadripper 3960X 24-Core @ 3.80GHz (24 Cores / 48 Threads), Motherboard: MSI Creator TRX40 (MS-7C59) v1.0 (1.12N1 BIOS), Chipset: AMD Starship/Matisse, Memory: 32GB, Disk: 1000GB Sabrent Rocket 4.0 1TB, Graphics: Sapphire AMD Radeon RX 5500/5500M / Pro 5500M 4GB (1900/875MHz), Audio: AMD Navi 10 HDMI Audio, Monitor: ASUS MG28U, Network: Aquantia AQC107 NBase-T/IEEE + Intel I211 + Intel Wi-Fi 6 AX200 OS: Ubuntu 20.04, Kernel: 5.9.0-rc5-14sep-patch (x86_64) 20200914, 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 (LLVM 10.0.0), Vulkan: 1.2.128, Compiler: GCC 9.3.0, File-System: ext4, Screen Resolution: 3840x2160 3: Processor: AMD Ryzen Threadripper 3960X 24-Core @ 3.80GHz (24 Cores / 48 Threads), Motherboard: MSI Creator TRX40 (MS-7C59) v1.0 (1.12N1 BIOS), Chipset: AMD Starship/Matisse, Memory: 32GB, Disk: 1000GB Sabrent Rocket 4.0 1TB, Graphics: Sapphire AMD Radeon RX 5500/5500M / Pro 5500M 4GB (1900/875MHz), Audio: AMD Navi 10 HDMI Audio, Monitor: ASUS MG28U, Network: Aquantia AQC107 NBase-T/IEEE + Intel I211 + Intel Wi-Fi 6 AX200 OS: Ubuntu 20.04, Kernel: 5.9.0-rc5-14sep-patch (x86_64) 20200914, 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 (LLVM 10.0.0), Vulkan: 1.2.128, Compiler: GCC 9.3.0, File-System: ext4, Screen Resolution: 3840x2160 NCNN 20200916 Target: CPU - Model: resnet18 ms < Lower Is Better 1 . 20.25 |================================================================== 2 . 19.80 |================================================================ 3 . 21.01 |==================================================================== NCNN 20200916 Target: CPU - Model: googlenet ms < Lower Is Better 1 . 39.53 |================================================================= 2 . 39.27 |================================================================= 3 . 41.22 |==================================================================== NCNN 20200916 Target: CPU - Model: alexnet ms < Lower Is Better 1 . 11.43 |================================================================= 2 . 11.71 |=================================================================== 3 . 11.88 |==================================================================== NCNN 20200916 Target: CPU - Model: resnet50 ms < Lower Is Better 1 . 56.97 |=================================================================== 2 . 56.35 |================================================================== 3 . 58.16 |==================================================================== NCNN 20200916 Target: CPU - Model: yolov4-tiny ms < Lower Is Better 1 . 27.38 |================================================================== 2 . 28.00 |=================================================================== 3 . 28.21 |==================================================================== NCNN 20200916 Target: CPU - Model: vgg16 ms < Lower Is Better 1 . 69.58 |================================================================== 2 . 69.73 |================================================================== 3 . 71.61 |==================================================================== NCNN 20200916 Target: CPU-v3-v3 - Model: mobilenet-v3 ms < Lower Is Better 1 . 6.74 |=================================================================== 2 . 6.71 |=================================================================== 3 . 6.90 |===================================================================== NCNN 20200916 Target: Vulkan GPU - Model: squeezenet ms < Lower Is Better 1 . 36.30 |================================================================== 2 . 37.23 |==================================================================== 3 . 36.78 |=================================================================== NCNN 20200916 Target: CPU - Model: squeezenet ms < Lower Is Better 1 . 34.16 |==================================================================== 2 . 33.51 |=================================================================== 3 . 34.17 |==================================================================== NCNN 20200916 Target: Vulkan GPU - Model: alexnet ms < Lower Is Better 1 . 28.16 |=================================================================== 2 . 28.60 |==================================================================== 3 . 28.45 |==================================================================== NCNN 20200916 Target: Vulkan GPU - Model: resnet18 ms < Lower Is Better 1 . 20.82 |==================================================================== 2 . 20.92 |==================================================================== 3 . 20.60 |=================================================================== NCNN 20200916 Target: Vulkan GPU - Model: resnet50 ms < Lower Is Better 1 . 58.79 |==================================================================== 2 . 58.78 |==================================================================== 3 . 58.06 |=================================================================== NCNN 20200916 Target: Vulkan GPU - Model: blazeface ms < Lower Is Better 1 . 0.89 |==================================================================== 2 . 0.90 |===================================================================== 3 . 0.90 |===================================================================== NCNN 20200916 Target: Vulkan GPU - Model: efficientnet-b0 ms < Lower Is Better 1 . 12.06 |==================================================================== 2 . 11.98 |=================================================================== 3 . 12.11 |==================================================================== NCNN 20200916 Target: CPU-v2-v2 - Model: mobilenet-v2 ms < Lower Is Better 1 . 7.22 |===================================================================== 2 . 7.19 |==================================================================== 3 . 7.25 |===================================================================== NCNN 20200916 Target: CPU - Model: efficientnet-b0 ms < Lower Is Better 1 . 8.57 |==================================================================== 2 . 8.57 |==================================================================== 3 . 8.64 |===================================================================== NCNN 20200916 Target: Vulkan GPU - Model: googlenet ms < Lower Is Better 1 . 41.21 |==================================================================== 2 . 41.37 |==================================================================== 3 . 41.08 |==================================================================== NCNN 20200916 Target: CPU - Model: blazeface ms < Lower Is Better 1 . 2.90 |===================================================================== 2 . 2.88 |===================================================================== 3 . 2.89 |===================================================================== NCNN 20200916 Target: Vulkan GPU - Model: shufflenet-v2 ms < Lower Is Better 1 . 3.20 |===================================================================== 2 . 3.20 |===================================================================== 3 . 3.22 |===================================================================== NCNN 20200916 Target: CPU - Model: mnasnet ms < Lower Is Better 1 . 6.52 |===================================================================== 2 . 6.49 |===================================================================== 3 . 6.50 |===================================================================== NCNN 20200916 Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2 ms < Lower Is Better 1 . 4.37 |===================================================================== 2 . 4.35 |===================================================================== 3 . 4.36 |===================================================================== NCNN 20200916 Target: CPU - Model: mobilenet ms < Lower Is Better 1 . 16.99 |==================================================================== 2 . 16.93 |==================================================================== 3 . 16.93 |==================================================================== NCNN 20200916 Target: Vulkan GPU - Model: yolov4-tiny ms < Lower Is Better 1 . 21.28 |==================================================================== 2 . 21.30 |==================================================================== 3 . 21.35 |==================================================================== NCNN 20200916 Target: CPU - Model: shufflenet-v2 ms < Lower Is Better 1 . 7.13 |===================================================================== 2 . 7.15 |===================================================================== 3 . 7.15 |===================================================================== TNN 0.2.3 Target: CPU - Model: SqueezeNet v1.1 ms < Lower Is Better 1 . 237.82 |=================================================================== 2 . 237.24 |=================================================================== 3 . 237.83 |=================================================================== NCNN 20200916 Target: Vulkan GPU - Model: mnasnet ms < Lower Is Better 1 . 4.44 |===================================================================== 2 . 4.45 |===================================================================== 3 . 4.44 |===================================================================== RealSR-NCNN 20200818 Scale: 4x - TAA: No Seconds < Lower Is Better 1 . 25.18 |==================================================================== 2 . 25.14 |==================================================================== 3 . 25.18 |==================================================================== TNN 0.2.3 Target: CPU - Model: MobileNet v2 ms < Lower Is Better 1 . 257.86 |=================================================================== 2 . 257.62 |=================================================================== 3 . 257.43 |=================================================================== RealSR-NCNN 20200818 Scale: 4x - TAA: Yes Seconds < Lower Is Better 1 . 183.31 |=================================================================== 2 . 183.34 |=================================================================== 3 . 183.38 |=================================================================== NCNN 20200916 Target: Vulkan GPU - Model: vgg16 ms < Lower Is Better 1 . 86.05 |==================================================================== 2 . 70.43 |======================================================== 3 . 69.45 |======================================================= NCNN 20200916 Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3 ms < Lower Is Better 1 . 8.43 |===================================================================== 2 . 8.22 |=================================================================== 3 . 8.21 |=================================================================== NCNN 20200916 Target: Vulkan GPU - Model: mobilenet ms < Lower Is Better 1 . 9.59 |===================================================================== 2 . 9.30 |=================================================================== 3 . 9.54 |=====================================================================