Intel Core i9-13900K testing with a ASUS PRIME Z790-P WIFI (0812 BIOS) and AMD Radeon RX 6800 XT 16GB on Ubuntu 22.04 via the Phoronix Test Suite.
Compare your own system(s) to this result file with the
Phoronix Test Suite by running the command:
phoronix-test-suite benchmark 2308019-NE-VULKAN68087 vulkan 6800XT - Phoronix Test Suite vulkan 6800XT Intel Core i9-13900K testing with a ASUS PRIME Z790-P WIFI (0812 BIOS) and AMD Radeon RX 6800 XT 16GB on Ubuntu 22.04 via the Phoronix Test Suite.
HTML result view exported from: https://openbenchmarking.org/result/2308019-NE-VULKAN68087&gru .
vulkan 6800XT Processor Motherboard Chipset Memory Disk Graphics Audio Monitor OS Kernel Desktop Display Server OpenGL Vulkan Compiler File-System Screen Resolution a b Intel Core i9-13900K @ 5.50GHz (24 Cores / 32 Threads) ASUS PRIME Z790-P WIFI (0812 BIOS) Intel Device 7a27 32GB 1000GB Western Digital WDS100T1X0E-00AFY0 + 2 x 64GB Flash Drive AMD Radeon RX 6800 XT 16GB (2575/1000MHz) Realtek ALC897 ASUS VP28U Ubuntu 22.04 5.19.0-50-generic (x86_64) GNOME Shell 42.9 X Server + Wayland 4.6 Mesa 22.2.5-0ubuntu0.1~22.04.3 (LLVM 15.0.7 DRM 3.47) 1.3.224 GCC 11.4.0 ext4 3840x2160 OpenBenchmarking.org Kernel Details - Transparent Huge Pages: madvise Compiler Details - --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-11-XeT9lY/gcc-11-11.4.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-XeT9lY/gcc-11-11.4.0/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-build-config=bootstrap-lto-lean --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: intel_pstate powersave (EPP: balance_performance) - CPU Microcode: 0x10e - Thermald 2.4.9 Graphics Details - BAR1 / Visible vRAM Size: 16368 MB - vBIOS Version: 113-D4120500-101 Security 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 Enhanced IBRS IBPB: conditional RSB filling PBRSB-eIBRS: SW sequence + srbds: Not affected + tsx_async_abort: Not affected
vulkan 6800XT vkfft: FFT + iFFT R2C / C2R vkfft: FFT + iFFT C2C 1D batched in half precision vkfft: FFT + iFFT C2C Bluestein in single precision vkfft: FFT + iFFT C2C 1D batched in double precision vkfft: FFT + iFFT C2C 1D batched in single precision vkfft: FFT + iFFT C2C multidimensional in single precision vkfft: FFT + iFFT C2C Bluestein benchmark in double precision vkfft: FFT + iFFT C2C 1D batched in single precision, no reshuffling vkpeak: fp32-scalar vkpeak: fp32-vec4 vkpeak: fp16-scalar vkpeak: fp16-vec4 vkpeak: fp64-scalar vkpeak: fp64-vec4 vkpeak: int32-scalar vkpeak: int32-vec4 vkpeak: int16-scalar vkpeak: int16-vec4 vkresample: 2x - Single ncnn: CPU - mobilenet ncnn: CPU-v2-v2 - mobilenet-v2 ncnn: CPU-v3-v3 - mobilenet-v3 ncnn: CPU - shufflenet-v2 ncnn: CPU - mnasnet ncnn: CPU - efficientnet-b0 ncnn: CPU - blazeface ncnn: CPU - googlenet ncnn: CPU - vgg16 ncnn: CPU - resnet18 ncnn: CPU - alexnet ncnn: CPU - resnet50 ncnn: CPU - yolov4-tiny ncnn: CPU - squeezenet_ssd ncnn: CPU - regnety_400m ncnn: CPU - vision_transformer ncnn: CPU - FastestDet ncnn: Vulkan GPU - mobilenet ncnn: Vulkan GPU-v2-v2 - mobilenet-v2 ncnn: Vulkan GPU-v3-v3 - mobilenet-v3 ncnn: Vulkan GPU - shufflenet-v2 ncnn: Vulkan GPU - mnasnet ncnn: Vulkan GPU - efficientnet-b0 ncnn: Vulkan GPU - blazeface ncnn: Vulkan GPU - googlenet ncnn: Vulkan GPU - vgg16 ncnn: Vulkan GPU - resnet18 ncnn: Vulkan GPU - alexnet ncnn: Vulkan GPU - resnet50 ncnn: Vulkan GPU - yolov4-tiny ncnn: Vulkan GPU - squeezenet_ssd ncnn: Vulkan GPU - regnety_400m ncnn: Vulkan GPU - vision_transformer ncnn: Vulkan GPU - FastestDet a b 59316 127229 14811 28285 65298 45096 6949 69116 22073.26 21484.21 21527.05 33775.49 1413.6 1411.86 3834.89 4477.62 21383.73 33053.14 8.492 7.51 2.02 1.79 1.77 1.9 3.37 0.65 5.51 40.26 4.1 3.84 8.47 10.84 5.65 5.4 1336.94 2.17 7.22 2.24 1.81 1.83 2.02 3.69 0.87 6.31 19.05 4.16 3.94 8.25 11.19 5.28 6.86 1249.17 2.45 57474 128044 14334 28242 65337 43591 6926 69137 21822.47 22328.13 22233.82 34040.48 1416.24 1414.33 3850.03 4497.58 22064.23 33941.93 8.491 7.06 1.9 2.35 2.37 2.38 4.08 0.91 6.35 19.08 4.16 3.87 8.2 10.7 4.82 7.07 1018.84 2.46 8.04 1.9 1.64 1.71 1.68 3.29 0.6 5.17 20.02 3.72 4.07 8.49 11.4 5.28 5.36 1158.57 2.17 OpenBenchmarking.org
VkFFT Test: FFT + iFFT R2C / C2R OpenBenchmarking.org Benchmark Score, More Is Better VkFFT 1.2.31 Test: FFT + iFFT R2C / C2R a b 13K 26K 39K 52K 65K 59316 57474 1. (CXX) g++ options: -O3
VkFFT Test: FFT + iFFT C2C 1D batched in half precision OpenBenchmarking.org Benchmark Score, More Is Better VkFFT 1.2.31 Test: FFT + iFFT C2C 1D batched in half precision a b 30K 60K 90K 120K 150K 127229 128044 1. (CXX) g++ options: -O3
VkFFT Test: FFT + iFFT C2C Bluestein in single precision OpenBenchmarking.org Benchmark Score, More Is Better VkFFT 1.2.31 Test: FFT + iFFT C2C Bluestein in single precision a b 3K 6K 9K 12K 15K 14811 14334 1. (CXX) g++ options: -O3
VkFFT Test: FFT + iFFT C2C 1D batched in double precision OpenBenchmarking.org Benchmark Score, More Is Better VkFFT 1.2.31 Test: FFT + iFFT C2C 1D batched in double precision a b 6K 12K 18K 24K 30K 28285 28242 1. (CXX) g++ options: -O3
VkFFT Test: FFT + iFFT C2C 1D batched in single precision OpenBenchmarking.org Benchmark Score, More Is Better VkFFT 1.2.31 Test: FFT + iFFT C2C 1D batched in single precision a b 14K 28K 42K 56K 70K 65298 65337 1. (CXX) g++ options: -O3
VkFFT Test: FFT + iFFT C2C multidimensional in single precision OpenBenchmarking.org Benchmark Score, More Is Better VkFFT 1.2.31 Test: FFT + iFFT C2C multidimensional in single precision a b 10K 20K 30K 40K 50K 45096 43591 1. (CXX) g++ options: -O3
VkFFT Test: FFT + iFFT C2C Bluestein benchmark in double precision OpenBenchmarking.org Benchmark Score, More Is Better VkFFT 1.2.31 Test: FFT + iFFT C2C Bluestein benchmark in double precision a b 1500 3000 4500 6000 7500 6949 6926 1. (CXX) g++ options: -O3
VkFFT Test: FFT + iFFT C2C 1D batched in single precision, no reshuffling OpenBenchmarking.org Benchmark Score, More Is Better VkFFT 1.2.31 Test: FFT + iFFT C2C 1D batched in single precision, no reshuffling a b 15K 30K 45K 60K 75K 69116 69137 1. (CXX) g++ options: -O3
vkpeak fp32-scalar OpenBenchmarking.org GFLOPS, More Is Better vkpeak 20230730 fp32-scalar a b 5K 10K 15K 20K 25K 22073.26 21822.47
vkpeak fp32-vec4 OpenBenchmarking.org GFLOPS, More Is Better vkpeak 20230730 fp32-vec4 a b 5K 10K 15K 20K 25K 21484.21 22328.13
vkpeak fp16-scalar OpenBenchmarking.org GFLOPS, More Is Better vkpeak 20230730 fp16-scalar a b 5K 10K 15K 20K 25K 21527.05 22233.82
vkpeak fp16-vec4 OpenBenchmarking.org GFLOPS, More Is Better vkpeak 20230730 fp16-vec4 a b 7K 14K 21K 28K 35K 33775.49 34040.48
vkpeak fp64-scalar OpenBenchmarking.org GFLOPS, More Is Better vkpeak 20230730 fp64-scalar a b 300 600 900 1200 1500 1413.60 1416.24
vkpeak fp64-vec4 OpenBenchmarking.org GFLOPS, More Is Better vkpeak 20230730 fp64-vec4 a b 300 600 900 1200 1500 1411.86 1414.33
vkpeak int32-scalar OpenBenchmarking.org GIOPS, More Is Better vkpeak 20230730 int32-scalar a b 800 1600 2400 3200 4000 3834.89 3850.03
vkpeak int32-vec4 OpenBenchmarking.org GIOPS, More Is Better vkpeak 20230730 int32-vec4 a b 1000 2000 3000 4000 5000 4477.62 4497.58
vkpeak int16-scalar OpenBenchmarking.org GIOPS, More Is Better vkpeak 20230730 int16-scalar a b 5K 10K 15K 20K 25K 21383.73 22064.23
vkpeak int16-vec4 OpenBenchmarking.org GIOPS, More Is Better vkpeak 20230730 int16-vec4 a b 7K 14K 21K 28K 35K 33053.14 33941.93
VkResample Upscale: 2x - Precision: Single OpenBenchmarking.org ms, Fewer Is Better VkResample 1.0 Upscale: 2x - Precision: Single a b 2 4 6 8 10 8.492 8.491 1. (CXX) g++ options: -O3
NCNN Target: CPU - Model: mobilenet OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU - Model: mobilenet a b 2 4 6 8 10 7.51 7.06 MIN: 6.7 / MAX: 66.34 MIN: 7 / MAX: 8.49 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU-v2-v2 - Model: mobilenet-v2 OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU-v2-v2 - Model: mobilenet-v2 a b 0.4545 0.909 1.3635 1.818 2.2725 2.02 1.90 MIN: 1.99 / MAX: 3.41 MIN: 1.86 / MAX: 3.5 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU-v3-v3 - Model: mobilenet-v3 OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU-v3-v3 - Model: mobilenet-v3 a b 0.5288 1.0576 1.5864 2.1152 2.644 1.79 2.35 MIN: 1.76 / MAX: 2.33 MIN: 2.33 / MAX: 2.7 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: shufflenet-v2 OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU - Model: shufflenet-v2 a b 0.5333 1.0666 1.5999 2.1332 2.6665 1.77 2.37 MIN: 1.74 / MAX: 2.24 MIN: 2.34 / MAX: 3.51 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: mnasnet OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU - Model: mnasnet a b 0.5355 1.071 1.6065 2.142 2.6775 1.90 2.38 MIN: 1.87 / MAX: 2.73 MIN: 2.36 / MAX: 2.96 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: efficientnet-b0 OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU - Model: efficientnet-b0 a b 0.918 1.836 2.754 3.672 4.59 3.37 4.08 MIN: 3.33 / MAX: 4.65 MIN: 4.04 / MAX: 5.6 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: blazeface OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU - Model: blazeface a b 0.2048 0.4096 0.6144 0.8192 1.024 0.65 0.91 MIN: 0.63 / MAX: 0.75 MIN: 0.9 / MAX: 1.38 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: googlenet OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU - Model: googlenet a b 2 4 6 8 10 5.51 6.35 MIN: 5.45 / MAX: 7.83 MIN: 6.29 / MAX: 8.9 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: vgg16 OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU - Model: vgg16 a b 9 18 27 36 45 40.26 19.08 MIN: 19.59 / MAX: 674.5 MIN: 18.91 / MAX: 21.29 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: resnet18 OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU - Model: resnet18 a b 0.936 1.872 2.808 3.744 4.68 4.10 4.16 MIN: 4.07 / MAX: 4.6 MIN: 4.11 / MAX: 5.53 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: alexnet OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU - Model: alexnet a b 0.8708 1.7416 2.6124 3.4832 4.354 3.84 3.87 MIN: 3.8 / MAX: 4.84 MIN: 3.83 / MAX: 4.4 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: resnet50 OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU - Model: resnet50 a b 2 4 6 8 10 8.47 8.20 MIN: 8.38 / MAX: 10.41 MIN: 8.11 / MAX: 10.68 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: yolov4-tiny OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU - Model: yolov4-tiny a b 3 6 9 12 15 10.84 10.70 MIN: 10.74 / MAX: 12.8 MIN: 10.58 / MAX: 12.57 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: squeezenet_ssd OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU - Model: squeezenet_ssd a b 1.2713 2.5426 3.8139 5.0852 6.3565 5.65 4.82 MIN: 5.57 / MAX: 6.77 MIN: 4.75 / MAX: 6.38 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: regnety_400m OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU - Model: regnety_400m a b 2 4 6 8 10 5.40 7.07 MIN: 5.33 / MAX: 6.69 MIN: 6.95 / MAX: 21.91 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: vision_transformer OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU - Model: vision_transformer a b 300 600 900 1200 1500 1336.94 1018.84 MIN: 47.96 / MAX: 2057.96 MIN: 48.19 / MAX: 2067.25 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: FastestDet OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU - Model: FastestDet a b 0.5535 1.107 1.6605 2.214 2.7675 2.17 2.46 MIN: 2.15 / MAX: 2.31 MIN: 2.43 / MAX: 3.53 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: mobilenet OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU - Model: mobilenet a b 2 4 6 8 10 7.22 8.51 MIN: 7.13 / MAX: 8.63 MIN: 8.47 / MAX: 9.9 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2 OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2 a b 0.5558 1.1116 1.6674 2.2232 2.779 2.24 2.47 MIN: 2.21 / MAX: 3.4 MIN: 2.44 / MAX: 3.68 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3 OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3 a b 0.4073 0.8146 1.2219 1.6292 2.0365 1.81 1.73 MIN: 1.78 / MAX: 3.05 MIN: 1.71 / MAX: 2.22 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: shufflenet-v2 OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU - Model: shufflenet-v2 a b 0.4118 0.8236 1.2354 1.6472 2.059 1.83 1.77 MIN: 1.79 / MAX: 2.3 MIN: 1.75 / MAX: 2.23 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: mnasnet OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU - Model: mnasnet a b 0.4545 0.909 1.3635 1.818 2.2725 2.02 1.79 MIN: 1.99 / MAX: 3.48 MIN: 1.77 / MAX: 1.97 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: efficientnet-b0 OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU - Model: efficientnet-b0 a b 0.8303 1.6606 2.4909 3.3212 4.1515 3.69 3.34 MIN: 3.65 / MAX: 4.84 MIN: 3.3 / MAX: 4.58 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: blazeface OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU - Model: blazeface a b 0.1958 0.3916 0.5874 0.7832 0.979 0.87 0.76 MIN: 0.86 / MAX: 1.84 MIN: 0.74 / MAX: 1.75 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: googlenet OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU - Model: googlenet a b 2 4 6 8 10 6.31 5.79 MIN: 6.26 / MAX: 7.77 MIN: 5.72 / MAX: 7.23 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: vgg16 OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU - Model: vgg16 a b 5 10 15 20 25 19.05 18.98 MIN: 18.83 / MAX: 21.09 MIN: 18.83 / MAX: 20.82 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: resnet18 OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU - Model: resnet18 a b 0.9405 1.881 2.8215 3.762 4.7025 4.16 4.18 MIN: 4.13 / MAX: 5.43 MIN: 4.14 / MAX: 5.26 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: alexnet OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU - Model: alexnet a b 0.9158 1.8316 2.7474 3.6632 4.579 3.94 3.94 MIN: 3.89 / MAX: 5.17 MIN: 3.9 / MAX: 5.1 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: resnet50 OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU - Model: resnet50 a b 2 4 6 8 10 8.25 8.27 MIN: 8.17 / MAX: 9.9 MIN: 8.18 / MAX: 10 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: yolov4-tiny OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU - Model: yolov4-tiny a b 4 8 12 16 20 11.19 13.63 MIN: 11.07 / MAX: 13.69 MIN: 13.53 / MAX: 15.51 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: squeezenet_ssd OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU - Model: squeezenet_ssd a b 1.26 2.52 3.78 5.04 6.3 5.28 5.60 MIN: 5.23 / MAX: 6.43 MIN: 5.54 / MAX: 7.61 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: regnety_400m OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU - Model: regnety_400m a b 2 4 6 8 10 6.86 5.86 MIN: 6.8 / MAX: 8.51 MIN: 5.47 / MAX: 7.28 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: vision_transformer OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU - Model: vision_transformer a b 300 600 900 1200 1500 1249.17 1301.13 MIN: 54.34 / MAX: 2059.42 MIN: 53.64 / MAX: 2062.97 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: FastestDet OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU - Model: FastestDet a b 0.5513 1.1026 1.6539 2.2052 2.7565 2.45 2.17 MIN: 2.42 / MAX: 3.92 MIN: 2.14 / MAX: 3.44 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
Phoronix Test Suite v10.8.4