nvidia-gpu-compute-orin-nano-8g ARMv8 Cortex-A78E testing with a NVIDIA Jetson Orin Nano Developer Kit (36.3.0-gcid-36191598 BIOS) and Orin on Ubuntu 22.04 via the Phoronix Test Suite. baseline: Processor: ARMv8 Cortex-A78E @ 1.51GHz (6 Cores), Motherboard: NVIDIA Jetson Orin Nano Developer Kit (36.3.0-gcid-36191598 BIOS), Memory: 8GB, Disk: 1000GB Western Digital WD_BLACK SN770 1TB, Graphics: Orin, Network: Realtek RTL8111/8168/8411 + Realtek RTL8822CE 802.11ac PCIe OS: Ubuntu 22.04, Kernel: 5.15.136-tegra (aarch64), Desktop: GNOME Shell 42.9, Display Server: X Server 1.21.1.4, Display Driver: NVIDIA, Vulkan: 1.3.251, Compiler: GCC 11.4.0 + CUDA 12.2, File-System: ext4, Screen Resolution: 6582x1234 Betsy GPU Compressor 1.1 Beta Codec: ETC1 - Quality: Highest Seconds < Lower Is Better Betsy GPU Compressor 1.1 Beta Codec: ETC2 RGB - Quality: Highest Seconds < Lower Is Better cl-mem 2017-01-13 Benchmark: Copy cl-mem 2017-01-13 Benchmark: Read cl-mem 2017-01-13 Benchmark: Write FAHBench 2.3.2 Ns Per Day > Higher Is Better Libplacebo 6.338.2 FPS > Higher Is Better NCNN 20230517 Target: Vulkan GPU - Model: mobilenet ms < Lower Is Better baseline . 22.96 |============================================================= NCNN 20230517 Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2 ms < Lower Is Better baseline . 5.25 |============================================================== NCNN 20230517 Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3 ms < Lower Is Better baseline . 4.99 |============================================================== NCNN 20230517 Target: Vulkan GPU - Model: shufflenet-v2 ms < Lower Is Better baseline . 4.06 |============================================================== NCNN 20230517 Target: Vulkan GPU - Model: mnasnet ms < Lower Is Better baseline . 4.85 |============================================================== NCNN 20230517 Target: Vulkan GPU - Model: efficientnet-b0 ms < Lower Is Better baseline . 8.55 |============================================================== NCNN 20230517 Target: Vulkan GPU - Model: blazeface ms < Lower Is Better baseline . 1.60 |============================================================== NCNN 20230517 Target: Vulkan GPU - Model: googlenet ms < Lower Is Better baseline . 16.46 |============================================================= NCNN 20230517 Target: Vulkan GPU - Model: vgg16 ms < Lower Is Better baseline . 64.25 |============================================================= NCNN 20230517 Target: Vulkan GPU - Model: resnet18 ms < Lower Is Better baseline . 12.84 |============================================================= NCNN 20230517 Target: Vulkan GPU - Model: alexnet ms < Lower Is Better baseline . 14.64 |============================================================= NCNN 20230517 Target: Vulkan GPU - Model: resnet50 ms < Lower Is Better baseline . 31.88 |============================================================= NCNN 20230517 Target: Vulkan GPUv2-yolov3v2-yolov3 - Model: mobilenetv2-yolov3 ms < Lower Is Better baseline . 22.96 |============================================================= NCNN 20230517 Target: Vulkan GPU - Model: yolov4-tiny ms < Lower Is Better baseline . 29.87 |============================================================= NCNN 20230517 Target: Vulkan GPU - Model: squeezenet_ssd ms < Lower Is Better baseline . 14.89 |============================================================= NCNN 20230517 Target: Vulkan GPU - Model: regnety_400m ms < Lower Is Better baseline . 12.21 |============================================================= NCNN 20230517 Target: Vulkan GPU - Model: vision_transformer ms < Lower Is Better baseline . 555.20 |============================================================ NCNN 20230517 Target: Vulkan GPU - Model: FastestDet ms < Lower Is Better baseline . 4.50 |============================================================== ViennaCL 1.7.1 Test: CPU BLAS - sCOPY GB/s > Higher Is Better baseline . 27 |================================================================ ViennaCL 1.7.1 Test: CPU BLAS - sAXPY GB/s > Higher Is Better baseline . 28.5 |============================================================== ViennaCL 1.7.1 Test: CPU BLAS - sDOT GB/s > Higher Is Better baseline . 21.6 |============================================================== ViennaCL 1.7.1 Test: CPU BLAS - dCOPY GB/s > Higher Is Better baseline . 27.7 |============================================================== ViennaCL 1.7.1 Test: CPU BLAS - dAXPY GB/s > Higher Is Better baseline . 28.3 |============================================================== ViennaCL 1.7.1 Test: CPU BLAS - dDOT GB/s > Higher Is Better baseline . 21.5 |============================================================== ViennaCL 1.7.1 Test: CPU BLAS - dGEMV-N GB/s > Higher Is Better baseline . 20.8 |============================================================== ViennaCL 1.7.1 Test: CPU BLAS - dGEMV-T GB/s > Higher Is Better baseline . 21.7 |============================================================== ViennaCL 1.7.1 Test: CPU BLAS - dGEMM-NN GFLOPs/s > Higher Is Better baseline . 9.55 |============================================================== ViennaCL 1.7.1 Test: CPU BLAS - dGEMM-NT GFLOPs/s > Higher Is Better baseline . 8.27 |============================================================== ViennaCL 1.7.1 Test: CPU BLAS - dGEMM-TN GFLOPs/s > Higher Is Better baseline . 9.71 |============================================================== ViennaCL 1.7.1 Test: CPU BLAS - dGEMM-TT GFLOPs/s > Higher Is Better baseline . 9.71 |============================================================== VkFFT 1.3.4 Test: FFT + iFFT R2C / C2R Benchmark Score > Higher Is Better baseline . 4137 |============================================================== VkFFT 1.3.4 Test: FFT + iFFT C2C 1D batched in half precision Benchmark Score > Higher Is Better baseline . 12138 |============================================================= VkFFT 1.3.4 Test: FFT + iFFT C2C Bluestein in single precision Benchmark Score > Higher Is Better baseline . 1439 |============================================================== VkFFT 1.3.4 Test: FFT + iFFT C2C 1D batched in double precision Benchmark Score > Higher Is Better baseline . 1020 |============================================================== VkFFT 1.3.4 Test: FFT + iFFT C2C 1D batched in single precision Benchmark Score > Higher Is Better baseline . 9269 |============================================================== VkFFT 1.3.4 Test: FFT + iFFT C2C multidimensional in single precision Benchmark Score > Higher Is Better baseline . 4121 |============================================================== VkFFT 1.3.4 Test: FFT + iFFT C2C Bluestein benchmark in double precision Benchmark Score > Higher Is Better baseline . 228 |=============================================================== VkFFT 1.3.4 Test: FFT + iFFT C2C 1D batched in single precision, no reshuffling Benchmark Score > Higher Is Better baseline . 10170 |============================================================= VkResample 1.0 Upscale: 2x - Precision: Double ms < Lower Is Better baseline . 511.95 |============================================================ VkResample 1.0 Upscale: 2x - Precision: Single ms < Lower Is Better baseline . 195.86 |============================================================