vulkan rem AMD Ryzen 7 PRO 6850U testing with a LENOVO 21CM0001US (R22ET51W 1.21 BIOS) and AMD Radeon 680M 1GB on Ubuntu 23.04 via the Phoronix Test Suite. a: Processor: AMD Ryzen 7 PRO 6850U @ 2.70GHz (8 Cores / 16 Threads), Motherboard: LENOVO 21CM0001US (R22ET51W 1.21 BIOS), Chipset: AMD 17h-19h PCIe Root Complex, Memory: 16GB, Disk: 512GB Micron MTFDKBA512TFK, Graphics: AMD Radeon 680M 1GB (2200/400MHz), Audio: AMD Rembrandt Radeon HD Audio, Network: Qualcomm QCNFA765 OS: Ubuntu 23.04, Kernel: 6.2.0-23-generic (x86_64), Desktop: GNOME Shell 44.0, Display Server: X Server + Wayland, OpenGL: 4.6 Mesa 23.0.2 (LLVM 15.0.7 DRM 3.49), Compiler: GCC 12.2.0, File-System: ext4, Screen Resolution: 1920x1200 b: Processor: AMD Ryzen 7 PRO 6850U @ 2.70GHz (8 Cores / 16 Threads), Motherboard: LENOVO 21CM0001US (R22ET51W 1.21 BIOS), Chipset: AMD 17h-19h PCIe Root Complex, Memory: 16GB, Disk: 512GB Micron MTFDKBA512TFK, Graphics: AMD Radeon 680M 1GB (2200/400MHz), Audio: AMD Rembrandt Radeon HD Audio, Network: Qualcomm QCNFA765 OS: Ubuntu 23.04, Kernel: 6.2.0-23-generic (x86_64), Desktop: GNOME Shell 44.0, Display Server: X Server + Wayland, OpenGL: 4.6 Mesa 23.0.2 (LLVM 15.0.7 DRM 3.49), Compiler: GCC 12.2.0, File-System: ext4, Screen Resolution: 1920x1200 c: Processor: AMD Ryzen 7 PRO 6850U @ 2.70GHz (8 Cores / 16 Threads), Motherboard: LENOVO 21CM0001US (R22ET51W 1.21 BIOS), Chipset: AMD 17h-19h PCIe Root Complex, Memory: 16GB, Disk: 512GB Micron MTFDKBA512TFK, Graphics: AMD Radeon 680M 1GB (2200/400MHz), Audio: AMD Rembrandt Radeon HD Audio, Network: Qualcomm QCNFA765 OS: Ubuntu 23.04, Kernel: 6.2.0-23-generic (x86_64), Desktop: GNOME Shell 44.0, Display Server: X Server + Wayland, OpenGL: 4.6 Mesa 23.0.2 (LLVM 15.0.7 DRM 3.49), Compiler: GCC 12.2.0, File-System: ext4, Screen Resolution: 1920x1200 VkFFT 1.2.31 Test: FFT + iFFT C2C 1D batched in half precision Benchmark Score > Higher Is Better a . 19943 |==================================================================== b . 19814 |==================================================================== c . 19904 |==================================================================== vkpeak 20230730 int16-vec4 GIOPS > Higher Is Better a . 3663.43 |============================================================= a . 3628.61 |============================================================ b . 3870.38 |================================================================ c . 3988.17 |================================================================== vkpeak 20230730 int16-scalar GIOPS > Higher Is Better a . 2593.43 |============================================================== a . 2469.93 |=========================================================== b . 2710.10 |================================================================= c . 2745.02 |================================================================== vkpeak 20230730 int32-vec4 GIOPS > Higher Is Better a . 574.37 |================================================================ a . 572.29 |================================================================ b . 562.50 |=============================================================== c . 597.52 |=================================================================== vkpeak 20230730 int32-scalar GIOPS > Higher Is Better a . 524.70 |============================================================= a . 508.88 |=========================================================== b . 529.13 |============================================================= c . 579.33 |=================================================================== vkpeak 20230730 fp64-vec4 GFLOPS > Higher Is Better a . 211.33 |=================================================================== a . 206.80 |================================================================= b . 211.42 |=================================================================== c . 211.79 |=================================================================== vkpeak 20230730 fp64-scalar GFLOPS > Higher Is Better a . 212.10 |=================================================================== a . 209.84 |================================================================== b . 211.74 |=================================================================== c . 212.10 |=================================================================== vkpeak 20230730 fp16-vec4 GFLOPS > Higher Is Better a . 3807.71 |============================================================ a . 3644.38 |========================================================== b . 4015.65 |=============================================================== c . 4177.12 |================================================================== vkpeak 20230730 fp16-scalar GFLOPS > Higher Is Better a . 2642.57 |=============================================================== a . 2479.90 |=========================================================== b . 2740.42 |================================================================= c . 2787.13 |================================================================== vkpeak 20230730 fp32-vec4 GFLOPS > Higher Is Better a . 2243.24 |========================================================= a . 2246.90 |========================================================= b . 2351.21 |=========================================================== c . 2617.93 |================================================================== vkpeak 20230730 fp32-scalar GFLOPS > Higher Is Better a . 2944.08 |============================================================= a . 2718.37 |======================================================== b . 3103.05 |================================================================ c . 3197.20 |================================================================== NCNN 20230517 Target: Vulkan GPU - Model: FastestDet ms < Lower Is Better a . 2.70 |================================================================= b . 2.69 |================================================================= c . 2.85 |===================================================================== NCNN 20230517 Target: Vulkan GPU - Model: vision_transformer ms < Lower Is Better a . 126.51 |=================================================================== b . 126.34 |=================================================================== c . 126.04 |=================================================================== NCNN 20230517 Target: Vulkan GPU - Model: regnety_400m ms < Lower Is Better a . 6.23 |=================================================================== b . 6.37 |===================================================================== c . 6.03 |================================================================= NCNN 20230517 Target: Vulkan GPU - Model: squeezenet_ssd ms < Lower Is Better a . 8.42 |===================================================================== b . 8.43 |===================================================================== c . 8.44 |===================================================================== NCNN 20230517 Target: Vulkan GPU - Model: yolov4-tiny ms < Lower Is Better a . 22.16 |==================================================================== b . 22.00 |==================================================================== c . 21.92 |=================================================================== NCNN 20230517 Target: Vulkan GPU - Model: resnet50 ms < Lower Is Better a . 16.91 |=================================================================== b . 17.07 |==================================================================== c . 16.84 |=================================================================== NCNN 20230517 Target: Vulkan GPU - Model: alexnet ms < Lower Is Better a . 7.57 |===================================================================== b . 7.46 |==================================================================== c . 7.46 |==================================================================== NCNN 20230517 Target: Vulkan GPU - Model: resnet18 ms < Lower Is Better a . 7.17 |===================================================================== b . 7.13 |===================================================================== c . 7.08 |==================================================================== NCNN 20230517 Target: Vulkan GPU - Model: vgg16 ms < Lower Is Better a . 50.24 |==================================================================== b . 50.28 |==================================================================== c . 50.22 |==================================================================== NCNN 20230517 Target: Vulkan GPU - Model: googlenet ms < Lower Is Better a . 9.67 |==================================================================== b . 9.76 |===================================================================== c . 9.28 |================================================================== NCNN 20230517 Target: Vulkan GPU - Model: blazeface ms < Lower Is Better a . 0.68 |==================================================================== b . 0.69 |===================================================================== c . 0.65 |================================================================= NCNN 20230517 Target: Vulkan GPU - Model: efficientnet-b0 ms < Lower Is Better a . 4.82 |===================================================================== b . 4.83 |===================================================================== c . 4.65 |================================================================== NCNN 20230517 Target: Vulkan GPU - Model: mnasnet ms < Lower Is Better a . 2.62 |==================================================================== b . 2.67 |===================================================================== c . 2.54 |================================================================== NCNN 20230517 Target: Vulkan GPU - Model: shufflenet-v2 ms < Lower Is Better a . 1.95 |=================================================================== b . 2.00 |===================================================================== c . 1.90 |================================================================== NCNN 20230517 Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3 ms < Lower Is Better a . 2.61 |===================================================================== b . 2.62 |===================================================================== c . 2.53 |=================================================================== NCNN 20230517 Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2 ms < Lower Is Better a . 3.11 |==================================================================== b . 3.15 |===================================================================== c . 3.08 |=================================================================== NCNN 20230517 Target: Vulkan GPU - Model: mobilenet ms < Lower Is Better a . 12.96 |==================================================================== b . 12.83 |=================================================================== c . 12.68 |=================================================================== NCNN 20230517 Target: CPU - Model: FastestDet ms < Lower Is Better a . 2.59 |==================================================================== b . 2.56 |=================================================================== c . 2.63 |===================================================================== NCNN 20230517 Target: CPU - Model: vision_transformer ms < Lower Is Better a . 126.10 |=================================================================== b . 126.33 |=================================================================== c . 125.84 |=================================================================== NCNN 20230517 Target: CPU - Model: regnety_400m ms < Lower Is Better a . 6.32 |===================================================================== b . 6.35 |===================================================================== c . 6.24 |==================================================================== NCNN 20230517 Target: CPU - Model: squeezenet_ssd ms < Lower Is Better a . 8.48 |===================================================================== b . 8.44 |===================================================================== c . 8.41 |==================================================================== NCNN 20230517 Target: CPU - Model: yolov4-tiny ms < Lower Is Better a . 21.96 |==================================================================== b . 22.09 |==================================================================== c . 21.96 |==================================================================== NCNN 20230517 Target: CPU - Model: resnet50 ms < Lower Is Better a . 16.94 |==================================================================== b . 16.91 |==================================================================== c . 16.83 |==================================================================== NCNN 20230517 Target: CPU - Model: alexnet ms < Lower Is Better a . 7.52 |===================================================================== b . 7.49 |===================================================================== c . 7.41 |==================================================================== NCNN 20230517 Target: CPU - Model: resnet18 ms < Lower Is Better a . 7.25 |===================================================================== b . 7.27 |===================================================================== c . 7.12 |==================================================================== NCNN 20230517 Target: CPU - Model: vgg16 ms < Lower Is Better a . 50.17 |==================================================================== b . 50.32 |==================================================================== c . 50.15 |==================================================================== NCNN 20230517 Target: CPU - Model: googlenet ms < Lower Is Better a . 9.78 |===================================================================== b . 9.82 |===================================================================== c . 9.69 |==================================================================== NCNN 20230517 Target: CPU - Model: blazeface ms < Lower Is Better a . 0.68 |==================================================================== b . 0.69 |===================================================================== c . 0.66 |================================================================== NCNN 20230517 Target: CPU - Model: efficientnet-b0 ms < Lower Is Better a . 4.76 |==================================================================== b . 4.80 |===================================================================== c . 4.72 |==================================================================== NCNN 20230517 Target: CPU - Model: mnasnet ms < Lower Is Better a . 2.61 |===================================================================== b . 2.62 |===================================================================== c . 2.56 |=================================================================== NCNN 20230517 Target: CPU - Model: shufflenet-v2 ms < Lower Is Better a . 1.93 |==================================================================== b . 1.96 |===================================================================== c . 1.89 |=================================================================== NCNN 20230517 Target: CPU-v3-v3 - Model: mobilenet-v3 ms < Lower Is Better a . 2.55 |==================================================================== b . 2.59 |===================================================================== c . 2.55 |==================================================================== NCNN 20230517 Target: CPU-v2-v2 - Model: mobilenet-v2 ms < Lower Is Better a . 3.13 |===================================================================== b . 3.14 |===================================================================== c . 3.08 |==================================================================== NCNN 20230517 Target: CPU - Model: mobilenet ms < Lower Is Better a . 12.84 |==================================================================== b . 12.81 |==================================================================== c . 12.77 |==================================================================== VkFFT 1.2.31 Test: FFT + iFFT R2C / C2R Benchmark Score > Higher Is Better a . 6283 |===================================================================== b . 6283 |===================================================================== c . 6282 |===================================================================== VkResample 1.0 Upscale: 2x - Precision: Single ms < Lower Is Better a . 56.22 |==================================================================== b . 56.46 |==================================================================== c . 56.00 |===================================================================