dddd AMD Ryzen AI 9 365 testing with a ASUS Zenbook S 16 UM5606WA_UM5606WA UM5606WA v1.0 (UM5606WA.308 BIOS) and AMD Radeon 512MB on Ubuntu 24.10 via the Phoronix Test Suite. a: Processor: AMD Ryzen AI 9 365 @ 4.31GHz (10 Cores / 20 Threads), Motherboard: ASUS Zenbook S 16 UM5606WA_UM5606WA UM5606WA v1.0 (UM5606WA.308 BIOS), Chipset: AMD Device 1507, Memory: 4 x 6GB LPDDR5-7500MT/s Micron MT62F1536M32D4DS-026, Disk: 1024GB MTFDKBA1T0QFM-1BD1AABGB, Graphics: AMD Radeon 512MB, Audio: AMD Rembrandt Radeon HD Audio, Network: MEDIATEK Device 7925 OS: Ubuntu 24.10, Kernel: 6.11.0-rc6-phx (x86_64), Desktop: GNOME Shell 47.0, Display Server: X Server + Wayland, OpenGL: 4.6 Mesa 24.2.3-1ubuntu1 (LLVM 19.1.0 DRM 3.58), Compiler: GCC 14.2.0, File-System: ext4, Screen Resolution: 2880x1800 b: Processor: AMD Ryzen AI 9 365 @ 4.31GHz (10 Cores / 20 Threads), Motherboard: ASUS Zenbook S 16 UM5606WA_UM5606WA UM5606WA v1.0 (UM5606WA.308 BIOS), Chipset: AMD Device 1507, Memory: 4 x 6GB LPDDR5-7500MT/s Micron MT62F1536M32D4DS-026, Disk: 1024GB MTFDKBA1T0QFM-1BD1AABGB, Graphics: AMD Radeon 512MB, Audio: AMD Rembrandt Radeon HD Audio, Network: MEDIATEK Device 7925 OS: Ubuntu 24.10, Kernel: 6.11.0-rc6-phx (x86_64), Desktop: GNOME Shell 47.0, Display Server: X Server + Wayland, OpenGL: 4.6 Mesa 24.2.3-1ubuntu1 (LLVM 19.1.0 DRM 3.58), Compiler: GCC 14.2.0, File-System: ext4, Screen Resolution: 2880x1800 c: Processor: AMD Ryzen AI 9 365 @ 4.31GHz (10 Cores / 20 Threads), Motherboard: ASUS Zenbook S 16 UM5606WA_UM5606WA UM5606WA v1.0 (UM5606WA.308 BIOS), Chipset: AMD Device 1507, Memory: 4 x 6GB LPDDR5-7500MT/s Micron MT62F1536M32D4DS-026, Disk: 1024GB MTFDKBA1T0QFM-1BD1AABGB, Graphics: AMD Radeon 512MB, Audio: AMD Rembrandt Radeon HD Audio, Network: MEDIATEK Device 7925 OS: Ubuntu 24.10, Kernel: 6.11.0-rc6-phx (x86_64), Desktop: GNOME Shell 47.0, Display Server: X Server + Wayland, OpenGL: 4.6 Mesa 24.2.3-1ubuntu1 (LLVM 19.1.0 DRM 3.58), Compiler: GCC 14.2.0, File-System: ext4, Screen Resolution: 2880x1800 LiteRT 2024-10-15 Model: DeepLab V3 Microseconds < Lower Is Better a . 3316.22 |================================================================== b . 3156.09 |=============================================================== c . 3121.29 |============================================================== LiteRT 2024-10-15 Model: SqueezeNet Microseconds < Lower Is Better a . 3395.84 |================================================================== b . 3071.99 |============================================================ c . 2824.06 |======================================================= LiteRT 2024-10-15 Model: Inception V4 Microseconds < Lower Is Better a . 44473.3 |================================================================== b . 43747.7 |================================================================= c . 40354.9 |============================================================ LiteRT 2024-10-15 Model: NASNet Mobile Microseconds < Lower Is Better a . 10175.3 |============================================================= b . 11035.8 |================================================================== c . 11060.1 |================================================================== LiteRT 2024-10-15 Model: Mobilenet Float Microseconds < Lower Is Better a . 2168.31 |=========================================================== b . 2273.80 |============================================================== c . 2415.31 |================================================================== LiteRT 2024-10-15 Model: Mobilenet Quant Microseconds < Lower Is Better a . 1668.50 |============================================================= b . 1710.54 |=============================================================== c . 1799.12 |================================================================== LiteRT 2024-10-15 Model: Inception ResNet V2 Microseconds < Lower Is Better a . 36956.9 |================================================================== b . 36371.8 |================================================================= c . 36440.2 |================================================================= LiteRT 2024-10-15 Model: Quantized COCO SSD MobileNet v1 Microseconds < Lower Is Better a . 2664.35 |================================================================== b . 2546.05 |=============================================================== c . 2477.80 |============================================================= XNNPACK b7b048 Model: FP32MobileNetV1 us < Lower Is Better a . 2288 |===================================================================== b . 2213 |=================================================================== c . 2194 |================================================================== XNNPACK b7b048 Model: FP32MobileNetV2 us < Lower Is Better a . 1847 |===================================================================== b . 1792 |=================================================================== c . 1773 |================================================================== XNNPACK b7b048 Model: FP32MobileNetV3Large us < Lower Is Better a . 2142 |===================================================================== b . 2147 |===================================================================== c . 2068 |================================================================== XNNPACK b7b048 Model: FP32MobileNetV3Small us < Lower Is Better a . 988 |=================================================================== b . 1007 |===================================================================== c . 1010 |===================================================================== XNNPACK b7b048 Model: FP16MobileNetV1 us < Lower Is Better a . 3055 |==================================================================== b . 3038 |==================================================================== c . 3087 |===================================================================== XNNPACK b7b048 Model: FP16MobileNetV2 us < Lower Is Better a . 2371 |=================================================================== b . 2363 |=================================================================== c . 2441 |===================================================================== XNNPACK b7b048 Model: FP16MobileNetV3Large us < Lower Is Better a . 2527 |==================================================================== b . 2533 |===================================================================== c . 2547 |===================================================================== XNNPACK b7b048 Model: FP16MobileNetV3Small us < Lower Is Better a . 1205 |===================================================================== b . 1206 |===================================================================== c . 1207 |===================================================================== XNNPACK b7b048 Model: QS8MobileNetV2 us < Lower Is Better a . 1084 |==================================================================== b . 1099 |==================================================================== c . 1108 |===================================================================== oneDNN 3.6 Harness: IP Shapes 1D - Engine: CPU ms < Lower Is Better a . 3.02556 |================================================================== b . 2.69059 |=========================================================== c . 2.72287 |=========================================================== oneDNN 3.6 Harness: IP Shapes 3D - Engine: CPU ms < Lower Is Better a . 3.04251 |================================================================== b . 3.02972 |================================================================== c . 3.01948 |================================================================== oneDNN 3.6 Harness: Convolution Batch Shapes Auto - Engine: CPU ms < Lower Is Better a . 8.47480 |================================================================== b . 8.39592 |================================================================= c . 8.47544 |================================================================== oneDNN 3.6 Harness: Deconvolution Batch shapes_1d - Engine: CPU ms < Lower Is Better a . 5.44277 |================================================================== b . 5.41282 |================================================================== c . 5.40451 |================================================================== oneDNN 3.6 Harness: Deconvolution Batch shapes_3d - Engine: CPU ms < Lower Is Better a . 6.25350 |================================================================== b . 6.26640 |================================================================== c . 6.28803 |================================================================== oneDNN 3.6 Harness: Recurrent Neural Network Training - Engine: CPU ms < Lower Is Better a . 3472.41 |================================================================= b . 3521.24 |================================================================== c . 3454.46 |================================================================= oneDNN 3.6 Harness: Recurrent Neural Network Inference - Engine: CPU ms < Lower Is Better a . 1810.44 |================================================================== b . 1808.03 |================================================================== c . 1797.94 |==================================================================