rt up AMD Ryzen 9 9950X 16-Core testing with a ASUS ROG STRIX X670E-E GAMING WIFI (2401 BIOS) and AMD Radeon PRO W7900 45GB on Ubuntu 24.04 via the Phoronix Test Suite. a: Processor: AMD Ryzen 9 9950X 16-Core @ 5.75GHz (16 Cores / 32 Threads), Motherboard: ASUS ROG STRIX X670E-E GAMING WIFI (2401 BIOS), Chipset: AMD Device 14d8, Memory: 2 x 32GB DDR5-6400MT/s Corsair CMK64GX5M2B6400C32, Disk: Western Digital WD_BLACK SN850X 2000GB + 257GB Flash Drive, Graphics: AMD Radeon PRO W7900 45GB (2200/3200MHz), Audio: AMD Navi 31 HDMI/DP, Monitor: DELL U2723QE, Network: Intel I225-V + Intel Wi-Fi 6E OS: Ubuntu 24.04, Kernel: 6.10.1-061001-generic (x86_64), Desktop: GNOME Shell 46.0, Display Server: X Server 1.21.1.11 + Wayland, OpenGL: 4.6 Mesa 24.2.0-devel (LLVM 18.1.7 DRM 3.57), OpenCL: OpenCL 2.1 AMD-APP (3625.0), Compiler: GCC 13.2.0, File-System: ext4, Screen Resolution: 3840x2160 b: Processor: AMD Ryzen 9 9950X 16-Core @ 5.75GHz (16 Cores / 32 Threads), Motherboard: ASUS ROG STRIX X670E-E GAMING WIFI (2401 BIOS), Chipset: AMD Device 14d8, Memory: 2 x 32GB DDR5-6400MT/s Corsair CMK64GX5M2B6400C32, Disk: Western Digital WD_BLACK SN850X 2000GB + 257GB Flash Drive, Graphics: AMD Radeon PRO W7900 45GB (2200/3200MHz), Audio: AMD Navi 31 HDMI/DP, Monitor: DELL U2723QE, Network: Intel I225-V + Intel Wi-Fi 6E OS: Ubuntu 24.04, Kernel: 6.10.1-061001-generic (x86_64), Desktop: GNOME Shell 46.0, Display Server: X Server 1.21.1.11 + Wayland, OpenGL: 4.6 Mesa 24.2.0-devel (LLVM 18.1.7 DRM 3.57), OpenCL: OpenCL 2.1 AMD-APP (3625.0), Compiler: GCC 13.2.0, File-System: ext4, Screen Resolution: 3840x2160 c: Processor: AMD Ryzen 9 9950X 16-Core @ 5.75GHz (16 Cores / 32 Threads), Motherboard: ASUS ROG STRIX X670E-E GAMING WIFI (2401 BIOS), Chipset: AMD Device 14d8, Memory: 2 x 32GB DDR5-6400MT/s Corsair CMK64GX5M2B6400C32, Disk: Western Digital WD_BLACK SN850X 2000GB + 257GB Flash Drive, Graphics: AMD Radeon PRO W7900 45GB (2200/3200MHz), Audio: AMD Navi 31 HDMI/DP, Monitor: DELL U2723QE, Network: Intel I225-V + Intel Wi-Fi 6E OS: Ubuntu 24.04, Kernel: 6.10.1-061001-generic (x86_64), Desktop: GNOME Shell 46.0, Display Server: X Server 1.21.1.11 + Wayland, OpenGL: 4.6 Mesa 24.2.0-devel (LLVM 18.1.7 DRM 3.57), OpenCL: OpenCL 2.1 AMD-APP (3625.0), Compiler: GCC 13.2.0, File-System: ext4, Screen Resolution: 3840x2160 d: Processor: AMD Ryzen 9 9950X 16-Core @ 5.75GHz (16 Cores / 32 Threads), Motherboard: ASUS ROG STRIX X670E-E GAMING WIFI (2401 BIOS), Chipset: AMD Device 14d8, Memory: 2 x 32GB DDR5-6400MT/s Corsair CMK64GX5M2B6400C32, Disk: Western Digital WD_BLACK SN850X 2000GB + 257GB Flash Drive, Graphics: AMD Radeon PRO W7900 45GB (2200/3200MHz), Audio: AMD Navi 31 HDMI/DP, Monitor: DELL U2723QE, Network: Intel I225-V + Intel Wi-Fi 6E OS: Ubuntu 24.04, Kernel: 6.10.1-061001-generic (x86_64), Desktop: GNOME Shell 46.0, Display Server: X Server 1.21.1.11 + Wayland, OpenGL: 4.6 Mesa 24.2.0-devel (LLVM 18.1.7 DRM 3.57), OpenCL: OpenCL 2.1 AMD-APP (3625.0), Compiler: GCC 13.2.0, File-System: ext4, Screen Resolution: 3840x2160 oneDNN 3.6 Harness: IP Shapes 1D - Engine: CPU ms < Lower Is Better a . 0.636587 |============================================================== b . 0.637647 |============================================================== c . 0.638661 |============================================================== d . 0.669839 |================================================================= oneDNN 3.6 Harness: IP Shapes 3D - Engine: CPU ms < Lower Is Better a . 3.17092 |============================================================== b . 3.18695 |=============================================================== c . 3.17892 |============================================================== d . 3.35833 |================================================================== oneDNN 3.6 Harness: Convolution Batch Shapes Auto - Engine: CPU ms < Lower Is Better a . 5.24008 |=============================================================== b . 5.23454 |=============================================================== c . 5.24225 |=============================================================== d . 5.45077 |================================================================== oneDNN 3.6 Harness: Deconvolution Batch shapes_1d - Engine: CPU ms < Lower Is Better a . 1.82100 |================================================================ b . 1.81784 |================================================================ c . 1.81460 |================================================================ d . 1.86755 |================================================================== oneDNN 3.6 Harness: Deconvolution Batch shapes_3d - Engine: CPU ms < Lower Is Better a . 1.40825 |================================================================ b . 1.41365 |================================================================= c . 1.40659 |================================================================ d . 1.44600 |================================================================== oneDNN 3.6 Harness: Recurrent Neural Network Training - Engine: CPU ms < Lower Is Better a . 752.85 |=============================================================== b . 753.33 |=============================================================== c . 752.46 |=============================================================== d . 795.02 |=================================================================== oneDNN 3.6 Harness: Recurrent Neural Network Inference - Engine: CPU ms < Lower Is Better a . 401.08 |================================================================ b . 401.05 |================================================================ c . 399.15 |=============================================================== d . 422.91 |=================================================================== LiteRT 2024-10-15 Model: DeepLab V3 Microseconds < Lower Is Better a . 1993.85 |========================================================== b . 1916.71 |======================================================== c . 1971.80 |========================================================== d . 2250.63 |================================================================== LiteRT 2024-10-15 Model: SqueezeNet Microseconds < Lower Is Better a . 1399.04 |================================================================== b . 1377.42 |================================================================= c . 1390.86 |================================================================= d . 1408.46 |================================================================== LiteRT 2024-10-15 Model: Inception V4 Microseconds < Lower Is Better a . 15724.4 |============================================================ b . 15880.3 |============================================================= c . 15836.1 |============================================================= d . 17160.6 |================================================================== LiteRT 2024-10-15 Model: NASNet Mobile Microseconds < Lower Is Better a . 10524.1 |====================================================== b . 10303.4 |===================================================== c . 10342.5 |===================================================== d . 12903.4 |================================================================== LiteRT 2024-10-15 Model: Mobilenet Float Microseconds < Lower Is Better a . 1002.97 |============================================================== b . 1004.00 |============================================================== c . 1008.93 |=============================================================== d . 1060.57 |================================================================== LiteRT 2024-10-15 Model: Mobilenet Quant Microseconds < Lower Is Better a . 593.87 |====================================================== b . 599.29 |====================================================== c . 585.76 |===================================================== d . 738.07 |=================================================================== LiteRT 2024-10-15 Model: Inception ResNet V2 Microseconds < Lower Is Better a . 14335.0 |============================================================= b . 14386.0 |============================================================== c . 14366.4 |============================================================== d . 15403.4 |================================================================== LiteRT 2024-10-15 Model: Quantized COCO SSD MobileNet v1 Microseconds < Lower Is Better a . 1237.78 |======================================================== b . 1265.69 |========================================================== c . 1273.91 |========================================================== d . 1448.45 |================================================================== XNNPACK b7b048 Model: FP32MobileNetV1 us < Lower Is Better a . 1024 |================================================================== b . 995 |================================================================ c . 1001 |================================================================ d . 1072 |===================================================================== XNNPACK b7b048 Model: FP32MobileNetV2 us < Lower Is Better a . 1385 |==================================================================== b . 1355 |================================================================== c . 1355 |================================================================== d . 1409 |===================================================================== XNNPACK b7b048 Model: FP32MobileNetV3Large us < Lower Is Better a . 1601 |================================================================= b . 1622 |================================================================== c . 1618 |================================================================== d . 1693 |===================================================================== XNNPACK b7b048 Model: FP32MobileNetV3Small us < Lower Is Better a . 902 |================================================================== b . 913 |=================================================================== c . 907 |=================================================================== d . 950 |====================================================================== XNNPACK b7b048 Model: FP16MobileNetV1 us < Lower Is Better a . 1008 |=================================================================== b . 1008 |=================================================================== c . 1000 |================================================================== d . 1038 |===================================================================== XNNPACK b7b048 Model: FP16MobileNetV2 us < Lower Is Better a . 1070 |================================================================== b . 1066 |================================================================== c . 1075 |=================================================================== d . 1112 |===================================================================== XNNPACK b7b048 Model: FP16MobileNetV3Large us < Lower Is Better a . 1395 |=================================================================== b . 1397 |=================================================================== c . 1398 |=================================================================== d . 1440 |===================================================================== XNNPACK b7b048 Model: FP16MobileNetV3Small us < Lower Is Better a . 851 |=================================================================== b . 858 |==================================================================== c . 861 |==================================================================== d . 884 |====================================================================== XNNPACK b7b048 Model: QS8MobileNetV2 us < Lower Is Better a . 747 |================================================================== b . 759 |=================================================================== c . 752 |=================================================================== d . 791 |======================================================================