vulkan-compute_test

Nano_vulkan-compute_test_result

HTML result view exported from: https://openbenchmarking.org/result/2307242-NE-VULKANCOM33&grr.

vulkan-compute_testProcessorMotherboardMemoryDiskGraphicsMonitorNetworkOSKernelDesktopDisplay ServerDisplay DriverOpenGLVulkanCompilerFile-SystemScreen Resolutionvulkan-compute_test_resultARMv8 Cortex-A78E @ 1.51GHz (6 Cores)EDK II 3.1-328277478GB256GB TEAM Ind N745-M80WNVIDIA Tegra OrinBenQ GW2381Realtek RTL8111/8168/8411 + Realtek RTL8822CE 802.11ac PCIeUbuntu 20.045.10.104-tegra (aarch64)GNOME Shell 3.36.9X Server 1.20.13NVIDIA 35.3.14.6.01.3.212GCC 9.4.0 + CUDA 11.4ext41920x1200OpenBenchmarking.org- Transparent Huge Pages: always- --build=aarch64-linux-gnu --disable-libquadmath --disable-libquadmath-support --disable-werror --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-fix-cortex-a53-843419 --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,gm2 --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-nls --enable-objc-gc=auto --enable-plugin --enable-shared --enable-threads=posix --host=aarch64-linux-gnu --program-prefix=aarch64-linux-gnu- --target=aarch64-linux-gnu --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-target-system-zlib=auto -v - Scaling Governor: tegra194 schedutil- Python 2.7.18 + Python 3.8.10- itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of __user pointer sanitization + spectre_v2: Not affected + srbds: Not affected + tsx_async_abort: Not affected

vulkan-compute_testncnn: Vulkan GPU - FastestDetncnn: Vulkan GPU - vision_transformerncnn: Vulkan GPU - regnety_400mncnn: Vulkan GPU - squeezenet_ssdncnn: Vulkan GPU - yolov4-tinyncnn: Vulkan GPU - resnet50ncnn: Vulkan GPU - alexnetncnn: Vulkan GPU - resnet18ncnn: Vulkan GPU - vgg16ncnn: Vulkan GPU - googlenetncnn: Vulkan GPU - blazefacencnn: Vulkan GPU - efficientnet-b0ncnn: Vulkan GPU - mnasnetncnn: Vulkan GPU - shufflenet-v2ncnn: Vulkan GPU-v3-v3 - mobilenet-v3ncnn: Vulkan GPU-v2-v2 - mobilenet-v2ncnn: Vulkan GPU - mobilenetvkresample: 2x - Doublevkresample: 2x - Singlelibplacebo: vulkan-compute_test_result4.83945.306.7814.1922.749.989.075.7219.148.353.069.714.235.295.844.2312.571023.829196.673OpenBenchmarking.org

NCNN

Target: Vulkan GPU - Model: FastestDet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: FastestDetvulkan-compute_test_result1.08682.17363.26044.34725.434SE +/- 0.06, N = 34.83MIN: 4.51 / MAX: 5.551. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: Vulkan GPU - Model: vision_transformer

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: vision_transformervulkan-compute_test_result2004006008001000SE +/- 1.90, N = 3945.30MIN: 914.8 / MAX: 999.381. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: Vulkan GPU - Model: regnety_400m

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: regnety_400mvulkan-compute_test_result246810SE +/- 0.93, N = 36.78MIN: 5.67 / MAX: 10.321. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: Vulkan GPU - Model: squeezenet_ssd

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: squeezenet_ssdvulkan-compute_test_result48121620SE +/- 0.77, N = 314.19MIN: 10.64 / MAX: 19.851. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: Vulkan GPU - Model: yolov4-tiny

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: yolov4-tinyvulkan-compute_test_result510152025SE +/- 0.99, N = 322.74MIN: 19.64 / MAX: 24.981. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: Vulkan GPU - Model: resnet50

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: resnet50vulkan-compute_test_result3691215SE +/- 0.21, N = 39.98MIN: 9.45 / MAX: 10.981. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: Vulkan GPU - Model: alexnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: alexnetvulkan-compute_test_result3691215SE +/- 0.10, N = 39.07MIN: 8.74 / MAX: 9.691. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: Vulkan GPU - Model: resnet18

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: resnet18vulkan-compute_test_result1.2872.5743.8615.1486.435SE +/- 0.32, N = 35.72MIN: 5.27 / MAX: 9.71. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: Vulkan GPU - Model: vgg16

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: vgg16vulkan-compute_test_result510152025SE +/- 0.01, N = 319.14MIN: 18.99 / MAX: 19.771. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: Vulkan GPU - Model: googlenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: googlenetvulkan-compute_test_result246810SE +/- 0.17, N = 38.35MIN: 7.8 / MAX: 15.561. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: Vulkan GPU - Model: blazeface

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: blazefacevulkan-compute_test_result0.68851.3772.06552.7543.4425SE +/- 0.12, N = 33.06MIN: 2.52 / MAX: 3.751. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: Vulkan GPU - Model: efficientnet-b0

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: efficientnet-b0vulkan-compute_test_result3691215SE +/- 1.08, N = 39.71MIN: 8.04 / MAX: 14.261. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: Vulkan GPU - Model: mnasnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: mnasnetvulkan-compute_test_result0.95181.90362.85543.80724.759SE +/- 0.13, N = 34.23MIN: 3.86 / MAX: 4.771. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: Vulkan GPU - Model: shufflenet-v2

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: shufflenet-v2vulkan-compute_test_result1.19032.38063.57094.76125.9515SE +/- 0.19, N = 35.29MIN: 4.77 / MAX: 5.951. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3vulkan-compute_test_result1.3142.6283.9425.2566.57SE +/- 0.08, N = 35.84MIN: 4.84 / MAX: 8.941. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2vulkan-compute_test_result0.95181.90362.85543.80724.759SE +/- 0.14, N = 34.23MIN: 3.83 / MAX: 5.781. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

NCNN

Target: Vulkan GPU - Model: mobilenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: mobilenetvulkan-compute_test_result3691215SE +/- 0.07, N = 312.57MIN: 11.36 / MAX: 14.281. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

VkResample

Upscale: 2x - Precision: Double

OpenBenchmarking.orgms, Fewer Is BetterVkResample 1.0Upscale: 2x - Precision: Doublevulkan-compute_test_result2004006008001000SE +/- 0.02, N = 31023.831. (CXX) g++ options: -O3 -pthread

VkResample

Upscale: 2x - Precision: Single

OpenBenchmarking.orgms, Fewer Is BetterVkResample 1.0Upscale: 2x - Precision: Singlevulkan-compute_test_result4080120160200SE +/- 0.12, N = 3196.671. (CXX) g++ options: -O3 -pthread

Phoronix Test Suite v10.8.5