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.

HTML result view exported from: https://openbenchmarking.org/result/2308012-NE-VULKANREM18&sor.

vulkan remProcessorMotherboardChipsetMemoryDiskGraphicsAudioNetworkOSKernelDesktopDisplay ServerOpenGLCompilerFile-SystemScreen ResolutionabcAMD Ryzen 7 PRO 6850U @ 2.70GHz (8 Cores / 16 Threads)LENOVO 21CM0001US (R22ET51W 1.21 BIOS)AMD 17h-19h PCIe Root Complex16GB512GB Micron MTFDKBA512TFKAMD Radeon 680M 1GB (2200/400MHz)AMD Rembrandt Radeon HD AudioQualcomm QCNFA765Ubuntu 23.046.2.0-23-generic (x86_64)GNOME Shell 44.0X Server + Wayland4.6 Mesa 23.0.2 (LLVM 15.0.7 DRM 3.49)GCC 12.2.0ext41920x1200OpenBenchmarking.orgKernel Details- Transparent Huge Pages: madviseCompiler Details- --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-12-Pa930Z/gcc-12-12.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-12-Pa930Z/gcc-12-12.2.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v Processor Details- Scaling Governor: acpi-cpufreq schedutil (Boost: Enabled) - Platform Profile: balanced - CPU Microcode: 0xa404102 - ACPI Profile: balanced Graphics Details- BAR1 / Visible vRAM Size: 1024 MB - vBIOS Version: 113-REMBRANDT-036Security Details- itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected

vulkan remvkpeak: fp32-scalarvkpeak: fp32-vec4vkpeak: fp16-scalarvkpeak: fp16-vec4vkpeak: fp64-scalarvkpeak: fp64-vec4vkpeak: int32-scalarvkpeak: int32-vec4vkpeak: int16-scalarvkpeak: int16-vec4vkfft: FFT + iFFT R2C / C2Rvkfft: FFT + iFFT C2C 1D batched in half precisionvkresample: 2x - Singlencnn: CPU - mobilenetncnn: CPU-v2-v2 - mobilenet-v2ncnn: CPU-v3-v3 - mobilenet-v3ncnn: CPU - shufflenet-v2ncnn: CPU - mnasnetncnn: CPU - efficientnet-b0ncnn: CPU - blazefacencnn: CPU - googlenetncnn: CPU - vgg16ncnn: CPU - resnet18ncnn: CPU - alexnetncnn: CPU - resnet50ncnn: CPU - yolov4-tinyncnn: CPU - squeezenet_ssdncnn: CPU - regnety_400mncnn: CPU - vision_transformerncnn: CPU - FastestDetncnn: Vulkan GPU - mobilenetncnn: Vulkan GPU-v2-v2 - mobilenet-v2ncnn: Vulkan GPU-v3-v3 - mobilenet-v3ncnn: Vulkan GPU - shufflenet-v2ncnn: Vulkan GPU - mnasnetncnn: Vulkan GPU - efficientnet-b0ncnn: Vulkan GPU - blazefacencnn: Vulkan GPU - googlenetncnn: Vulkan GPU - vgg16ncnn: Vulkan GPU - resnet18ncnn: Vulkan GPU - alexnetncnn: Vulkan GPU - resnet50ncnn: Vulkan GPU - yolov4-tinyncnn: Vulkan GPU - squeezenet_ssdncnn: Vulkan GPU - regnety_400mncnn: Vulkan GPU - vision_transformerncnn: Vulkan GPU - FastestDetabc2944.082243.242642.573807.71212.10211.33524.70574.372593.433663.4362831994356.22412.843.132.551.932.614.760.689.7850.177.257.5216.9421.968.486.32126.102.5912.963.112.611.952.624.820.689.6750.247.177.5716.9122.168.426.23126.512.703103.052351.212740.424015.65211.74211.42529.13562.502710.103870.3862831981456.46212.813.142.591.962.624.800.699.8250.327.277.4916.9122.098.446.35126.332.5612.833.152.622.002.674.830.699.7650.287.137.4617.0722.008.436.37126.342.693197.22617.932787.134177.12212.1211.79579.33597.522745.023988.1762821990456.00212.773.082.551.892.564.720.669.6950.157.127.4116.8321.968.416.24125.842.6312.683.082.531.92.544.650.659.2850.227.087.4616.8421.928.446.03126.042.85OpenBenchmarking.org

vkpeak

fp32-scalar

OpenBenchmarking.orgGFLOPS, More Is Bettervkpeak 20230730fp32-scalarcba7001400210028003500SE +/- 23.68, N = 3SE +/- 16.26, N = 33197.203103.052944.08

vkpeak

fp32-vec4

OpenBenchmarking.orgGFLOPS, More Is Bettervkpeak 20230730fp32-vec4cba6001200180024003000SE +/- 123.18, N = 3SE +/- 30.23, N = 32617.932351.212246.90

vkpeak

fp16-scalar

OpenBenchmarking.orgGFLOPS, More Is Bettervkpeak 20230730fp16-scalarcba6001200180024003000SE +/- 5.74, N = 3SE +/- 7.27, N = 32787.132740.422642.57

vkpeak

fp16-vec4

OpenBenchmarking.orgGFLOPS, More Is Bettervkpeak 20230730fp16-vec4cba9001800270036004500SE +/- 8.25, N = 3SE +/- 16.34, N = 34177.124015.653807.71

vkpeak

fp64-scalar

OpenBenchmarking.orgGFLOPS, More Is Bettervkpeak 20230730fp64-scalarcab50100150200250SE +/- 0.01, N = 3SE +/- 0.02, N = 3212.10212.10211.74

vkpeak

fp64-vec4

OpenBenchmarking.orgGFLOPS, More Is Bettervkpeak 20230730fp64-vec4cba50100150200250SE +/- 0.01, N = 3SE +/- 0.21, N = 3211.79211.42211.33

vkpeak

int32-scalar

OpenBenchmarking.orgGIOPS, More Is Bettervkpeak 20230730int32-scalarcba130260390520650SE +/- 5.09, N = 3SE +/- 0.57, N = 3579.33529.13524.70

vkpeak

int32-vec4

OpenBenchmarking.orgGIOPS, More Is Bettervkpeak 20230730int32-vec4cab130260390520650SE +/- 0.91, N = 3SE +/- 0.16, N = 3597.52574.37562.50

vkpeak

int16-scalar

OpenBenchmarking.orgGIOPS, More Is Bettervkpeak 20230730int16-scalarcba6001200180024003000SE +/- 2.74, N = 3SE +/- 1.79, N = 32745.022710.102593.43

vkpeak

int16-vec4

OpenBenchmarking.orgGIOPS, More Is Bettervkpeak 20230730int16-vec4cba9001800270036004500SE +/- 1.88, N = 3SE +/- 2.14, N = 33988.173870.383663.43

VkFFT

Test: FFT + iFFT R2C / C2R

OpenBenchmarking.orgBenchmark Score, More Is BetterVkFFT 1.2.31Test: FFT + iFFT R2C / C2Rbac13002600390052006500SE +/- 22.70, N = 3SE +/- 14.84, N = 36283628362821. (CXX) g++ options: -O3

VkFFT

Test: FFT + iFFT C2C 1D batched in half precision

OpenBenchmarking.orgBenchmark Score, More Is BetterVkFFT 1.2.31Test: FFT + iFFT C2C 1D batched in half precisionacb4K8K12K16K20KSE +/- 100.68, N = 3SE +/- 39.59, N = 31994319904198141. (CXX) g++ options: -O3

VkResample

Upscale: 2x - Precision: Single

OpenBenchmarking.orgms, Fewer Is BetterVkResample 1.0Upscale: 2x - Precision: Singlecab1326395265SE +/- 0.11, N = 3SE +/- 0.06, N = 356.0056.2256.461. (CXX) g++ options: -O3

NCNN

Target: CPU - Model: mobilenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: mobilenetcba3691215SE +/- 0.05, N = 3SE +/- 0.07, N = 312.7712.8112.84MIN: 12.53 / MAX: 13.49MIN: 12.4 / MAX: 24.01MIN: 12.39 / MAX: 24.161. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU-v2-v2 - Model: mobilenet-v2

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU-v2-v2 - Model: mobilenet-v2cab0.70651.4132.11952.8263.5325SE +/- 0.01, N = 3SE +/- 0.02, N = 33.083.133.14MIN: 2.87 / MAX: 5.1MIN: 2.84 / MAX: 4.95MIN: 2.82 / MAX: 6.881. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU-v3-v3 - Model: mobilenet-v3

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU-v3-v3 - Model: mobilenet-v3acb0.58281.16561.74842.33122.914SE +/- 0.01, N = 3SE +/- 0.02, N = 32.552.552.59MIN: 2.33 / MAX: 4.5MIN: 2.36 / MAX: 4.15MIN: 2.37 / MAX: 4.441. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: shufflenet-v2

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: shufflenet-v2cab0.4410.8821.3231.7642.205SE +/- 0.01, N = 3SE +/- 0.02, N = 31.891.931.96MIN: 1.75 / MAX: 2.77MIN: 1.78 / MAX: 3.55MIN: 1.76 / MAX: 2.371. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: mnasnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: mnasnetcab0.58951.1791.76852.3582.9475SE +/- 0.01, N = 3SE +/- 0.02, N = 32.562.612.62MIN: 2.43 / MAX: 3.86MIN: 2.4 / MAX: 13.39MIN: 2.41 / MAX: 4.051. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: efficientnet-b0

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: efficientnet-b0cab1.082.163.244.325.4SE +/- 0.01, N = 3SE +/- 0.05, N = 34.724.764.80MIN: 4.48 / MAX: 6.95MIN: 4.52 / MAX: 6.74MIN: 4.43 / MAX: 16.711. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: blazeface

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: blazefacecab0.15530.31060.46590.62120.7765SE +/- 0.02, N = 3SE +/- 0.01, N = 30.660.680.69MIN: 0.58 / MAX: 1.59MIN: 0.61 / MAX: 1.04MIN: 0.62 / MAX: 1.561. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: googlenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: googlenetcab3691215SE +/- 0.13, N = 3SE +/- 0.12, N = 39.699.789.82MIN: 9.1 / MAX: 14.12MIN: 8.97 / MAX: 12.44MIN: 9.05 / MAX: 20.331. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: vgg16

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: vgg16cab1122334455SE +/- 0.05, N = 3SE +/- 0.14, N = 350.1550.1750.32MIN: 49.73 / MAX: 62.35MIN: 49.14 / MAX: 61.46MIN: 48.97 / MAX: 62.151. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: resnet18

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: resnet18cab246810SE +/- 0.03, N = 3SE +/- 0.06, N = 37.127.257.27MIN: 6.81 / MAX: 9.18MIN: 6.86 / MAX: 18.35MIN: 6.79 / MAX: 8.941. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: alexnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: alexnetcba246810SE +/- 0.01, N = 3SE +/- 0.02, N = 37.417.497.52MIN: 7.16 / MAX: 8.77MIN: 7.23 / MAX: 9.71MIN: 7.23 / MAX: 18.521. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: resnet50

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: resnet50cba48121620SE +/- 0.05, N = 3SE +/- 0.06, N = 316.8316.9116.94MIN: 16.52 / MAX: 17.51MIN: 16.24 / MAX: 28.07MIN: 16.46 / MAX: 19.71. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: yolov4-tiny

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: yolov4-tinyacb510152025SE +/- 0.04, N = 3SE +/- 0.03, N = 321.9621.9622.09MIN: 21.38 / MAX: 24.78MIN: 21.3 / MAX: 22.99MIN: 21.39 / MAX: 34.391. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: squeezenet_ssd

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: squeezenet_ssdcba246810SE +/- 0.00, N = 3SE +/- 0.05, N = 38.418.448.48MIN: 8.13 / MAX: 10.22MIN: 8.13 / MAX: 10.76MIN: 7.97 / MAX: 10.911. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: regnety_400m

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: regnety_400mcab246810SE +/- 0.06, N = 3SE +/- 0.07, N = 36.246.326.35MIN: 5.75 / MAX: 17.46MIN: 5.79 / MAX: 8.1MIN: 5.75 / MAX: 8.021. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: vision_transformer

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: vision_transformercab306090120150SE +/- 0.07, N = 3SE +/- 0.11, N = 3125.84126.10126.33MIN: 123.61 / MAX: 158.78MIN: 122.74 / MAX: 136.47MIN: 123.54 / MAX: 135.111. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: CPU - Model: FastestDet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: FastestDetbac0.59181.18361.77542.36722.959SE +/- 0.02, N = 32.562.592.63MIN: 2.44 / MAX: 3MIN: 2.42 / MAX: 4.18MIN: 2.54 / MAX: 3.071. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: mobilenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: mobilenetcba3691215SE +/- 0.01, N = 3SE +/- 0.17, N = 312.6812.8312.96MIN: 12.47 / MAX: 13.53MIN: 12.51 / MAX: 14.26MIN: 12.39 / MAX: 63.671. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

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

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2cab0.70881.41762.12642.83523.544SE +/- 0.01, N = 3SE +/- 0.03, N = 33.083.113.15MIN: 2.8 / MAX: 4.21MIN: 2.87 / MAX: 4.89MIN: 2.86 / MAX: 4.581. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

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

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3cab0.58951.1791.76852.3582.9475SE +/- 0.02, N = 3SE +/- 0.02, N = 32.532.612.62MIN: 2.32 / MAX: 3.76MIN: 2.39 / MAX: 14.7MIN: 2.46 / MAX: 4.31. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: shufflenet-v2

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: shufflenet-v2cab0.450.91.351.82.25SE +/- 0.01, N = 3SE +/- 0.02, N = 31.901.952.00MIN: 1.84 / MAX: 2.36MIN: 1.85 / MAX: 3MIN: 1.67 / MAX: 3.671. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: mnasnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: mnasnetcab0.60081.20161.80242.40323.004SE +/- 0.01, N = 3SE +/- 0.03, N = 32.542.622.67MIN: 2.43 / MAX: 3.97MIN: 2.35 / MAX: 3.91MIN: 2.51 / MAX: 4.21. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: efficientnet-b0

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: efficientnet-b0cab1.08682.17363.26044.34725.434SE +/- 0.03, N = 3SE +/- 0.03, N = 34.654.824.83MIN: 4.49 / MAX: 6.18MIN: 4.4 / MAX: 18.07MIN: 4.39 / MAX: 7.051. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: blazeface

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: blazefacecab0.15530.31060.46590.62120.7765SE +/- 0.01, N = 3SE +/- 0.01, N = 30.650.680.69MIN: 0.62 / MAX: 0.78MIN: 0.65 / MAX: 1.07MIN: 0.65 / MAX: 1.641. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: googlenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: googlenetcab3691215SE +/- 0.09, N = 3SE +/- 0.10, N = 39.289.679.76MIN: 8.96 / MAX: 11.62MIN: 9.02 / MAX: 11.84MIN: 9.08 / MAX: 20.731. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: vgg16

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: vgg16cab1122334455SE +/- 0.06, N = 3SE +/- 0.15, N = 350.2250.2450.28MIN: 49.37 / MAX: 63.14MIN: 49.26 / MAX: 62.9MIN: 49.14 / MAX: 62.51. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: resnet18

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: resnet18cba246810SE +/- 0.07, N = 3SE +/- 0.12, N = 37.087.137.17MIN: 6.61 / MAX: 11.1MIN: 6.57 / MAX: 9.32MIN: 6.62 / MAX: 9.231. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: alexnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: alexnetbca246810SE +/- 0.04, N = 3SE +/- 0.01, N = 37.467.467.57MIN: 7.1 / MAX: 10.13MIN: 7.2 / MAX: 9.11MIN: 7.1 / MAX: 9.671. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: resnet50

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: resnet50cab48121620SE +/- 0.02, N = 3SE +/- 0.07, N = 316.8416.9117.07MIN: 16.47 / MAX: 19.2MIN: 16.43 / MAX: 27.99MIN: 16.47 / MAX: 28.451. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: yolov4-tiny

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: yolov4-tinycba510152025SE +/- 0.05, N = 3SE +/- 0.14, N = 321.9222.0022.16MIN: 21.18 / MAX: 24.66MIN: 21.31 / MAX: 25.03MIN: 21.38 / MAX: 32.761. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: squeezenet_ssd

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: squeezenet_ssdabc246810SE +/- 0.02, N = 3SE +/- 0.01, N = 38.428.438.44MIN: 8.05 / MAX: 10.16MIN: 8.12 / MAX: 11.62MIN: 8.08 / MAX: 19.621. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: regnety_400m

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: regnety_400mcab246810SE +/- 0.04, N = 3SE +/- 0.03, N = 36.036.236.37MIN: 5.54 / MAX: 7.35MIN: 5.87 / MAX: 8.11MIN: 5.88 / MAX: 8.181. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: vision_transformer

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: vision_transformercba306090120150SE +/- 0.19, N = 3SE +/- 0.07, N = 3126.04126.34126.51MIN: 123.54 / MAX: 133.69MIN: 123.22 / MAX: 135.57MIN: 123.01 / MAX: 136.011. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: FastestDet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: FastestDetbac0.64131.28261.92392.56523.2065SE +/- 0.12, N = 3SE +/- 0.09, N = 32.692.702.85MIN: 2.46 / MAX: 14.64MIN: 2.48 / MAX: 5.38MIN: 2.76 / MAX: 3.261. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

Phoronix Test Suite v10.8.4