Vulkan Compute AMD Ryzen 9 5900X 12-Core testing with a ASUS ROG CROSSHAIR VIII HERO (3501 BIOS) and eVGA NVIDIA GeForce RTX 3060 12GB on Ubuntu 21.04 via the Phoronix Test Suite.
HTML result view exported from: https://openbenchmarking.org/result/2107307-PTS-VULKANCO44&grs .
Vulkan Compute Processor Motherboard Chipset Memory Disk Graphics Audio Monitor Network OS Kernel Desktop Display Server Display Driver OpenGL Vulkan Compiler File-System Screen Resolution NVIDIA RTX 3060 AMD Ryzen 9 5900X 12-Core @ 3.70GHz (12 Cores / 24 Threads) ASUS ROG CROSSHAIR VIII HERO (3501 BIOS) AMD Starship/Matisse 16GB 1000GB Sabrent Rocket 4.0 Plus + 2000GB eVGA NVIDIA GeForce RTX 3060 12GB NVIDIA Device 228e ASUS VP28U Realtek RTL8125 2.5GbE + Intel I211 Ubuntu 21.04 5.11.0-25-generic (x86_64) GNOME Shell 3.38.4 X Server 1.20.11 NVIDIA 470.57.02 4.6.0 1.2.175 GCC 10.3.0 ext4 3840x2160 OpenBenchmarking.org - Transparent Huge Pages: madvise - --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --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-mutex --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-10-gDeRY6/gcc-10-10.3.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-10-gDeRY6/gcc-10-10.3.0/debian/tmp-gcn/usr,hsa --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 - Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa201009 - itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional IBRS_FW STIBP: always-on RSB filling + srbds: Not affected + tsx_async_abort: Not affected
Vulkan Compute ncnn: Vulkan GPU - resnet18 ncnn: Vulkan GPU - regnety_400m ncnn: Vulkan GPU - squeezenet_ssd ncnn: Vulkan GPU - yolov4-tiny ncnn: Vulkan GPU - resnet50 ncnn: Vulkan GPU - alexnet ncnn: Vulkan GPU - vgg16 ncnn: Vulkan GPU - googlenet ncnn: Vulkan GPU - blazeface ncnn: Vulkan GPU - efficientnet-b0 ncnn: Vulkan GPU - mnasnet ncnn: Vulkan GPU - shufflenet-v2 ncnn: Vulkan GPU-v3-v3 - mobilenet-v3 ncnn: Vulkan GPU-v2-v2 - mobilenet-v2 ncnn: Vulkan GPU - mobilenet vkresample: 2x - Single vkfft: waifu2x-ncnn: 2x - 3 - Yes realsr-ncnn: 4x - Yes realsr-ncnn: 4x - No vkpeak: int16-vec4 vkpeak: int16-scalar vkpeak: int32-vec4 vkpeak: int32-scalar vkpeak: fp64-vec4 vkpeak: fp64-scalar vkpeak: fp16-vec4 vkpeak: fp16-scalar vkpeak: fp32-vec4 vkpeak: fp32-scalar NVIDIA RTX 3060 1.93 2.44 4.88 7.21 4.19 2.10 7.3 4.27 0.98 3.25 2.04 1.74 2.18 1.95 4.57 23.149 27337 4.974 67.903 10.505 5957.52 4480.11 6766.46 6830.28 214.29 214.25 13242.60 6849.64 9079.50 6829.75 OpenBenchmarking.org
NCNN Target: Vulkan GPU - Model: resnet18 OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: Vulkan GPU - Model: resnet18 NVIDIA RTX 3060 0.4343 0.8686 1.3029 1.7372 2.1715 SE +/- 0.00, N = 2 1.93 MIN: 1.91 / MAX: 2.25 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
NCNN Target: Vulkan GPU - Model: regnety_400m OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: Vulkan GPU - Model: regnety_400m NVIDIA RTX 3060 0.549 1.098 1.647 2.196 2.745 SE +/- 0.00, N = 3 2.44 MIN: 2.41 / MAX: 3.44 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
NCNN Target: Vulkan GPU - Model: squeezenet_ssd OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: Vulkan GPU - Model: squeezenet_ssd NVIDIA RTX 3060 1.098 2.196 3.294 4.392 5.49 SE +/- 0.07, N = 3 4.88 MIN: 4.67 / MAX: 10.31 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
NCNN Target: Vulkan GPU - Model: yolov4-tiny OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: Vulkan GPU - Model: yolov4-tiny NVIDIA RTX 3060 2 4 6 8 10 SE +/- 0.01, N = 3 7.21 MIN: 7.02 / MAX: 7.52 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
NCNN Target: Vulkan GPU - Model: resnet50 OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: Vulkan GPU - Model: resnet50 NVIDIA RTX 3060 0.9428 1.8856 2.8284 3.7712 4.714 SE +/- 0.01, N = 3 4.19 MIN: 4.17 / MAX: 4.84 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
NCNN Target: Vulkan GPU - Model: alexnet OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: Vulkan GPU - Model: alexnet NVIDIA RTX 3060 0.4725 0.945 1.4175 1.89 2.3625 SE +/- 0.00, N = 3 2.10 MIN: 2.07 / MAX: 4.52 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
NCNN Target: Vulkan GPU - Model: vgg16 OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: Vulkan GPU - Model: vgg16 NVIDIA RTX 3060 2 4 6 8 10 SE +/- 0.00, N = 3 7.3 MIN: 7.17 / MAX: 15.83 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
NCNN Target: Vulkan GPU - Model: googlenet OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: Vulkan GPU - Model: googlenet NVIDIA RTX 3060 0.9608 1.9216 2.8824 3.8432 4.804 SE +/- 0.08, N = 3 4.27 MIN: 3.95 / MAX: 15.21 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
NCNN Target: Vulkan GPU - Model: blazeface OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: Vulkan GPU - Model: blazeface NVIDIA RTX 3060 0.2205 0.441 0.6615 0.882 1.1025 SE +/- 0.00, N = 3 0.98 MIN: 0.95 / MAX: 2.33 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
NCNN Target: Vulkan GPU - Model: efficientnet-b0 OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: Vulkan GPU - Model: efficientnet-b0 NVIDIA RTX 3060 0.7313 1.4626 2.1939 2.9252 3.6565 SE +/- 0.01, N = 3 3.25 MIN: 3.22 / MAX: 3.7 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
NCNN Target: Vulkan GPU - Model: mnasnet OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: Vulkan GPU - Model: mnasnet NVIDIA RTX 3060 0.459 0.918 1.377 1.836 2.295 SE +/- 0.01, N = 3 2.04 MIN: 2.02 / MAX: 4.46 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
NCNN Target: Vulkan GPU - Model: shufflenet-v2 OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: Vulkan GPU - Model: shufflenet-v2 NVIDIA RTX 3060 0.3915 0.783 1.1745 1.566 1.9575 SE +/- 0.00, N = 3 1.74 MIN: 1.71 / MAX: 3.74 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
NCNN Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3 OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3 NVIDIA RTX 3060 0.4905 0.981 1.4715 1.962 2.4525 SE +/- 0.00, N = 3 2.18 MIN: 2.16 / MAX: 3.53 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
NCNN Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2 OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2 NVIDIA RTX 3060 0.4388 0.8776 1.3164 1.7552 2.194 SE +/- 0.00, N = 3 1.95 MIN: 1.92 / MAX: 2.86 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
NCNN Target: Vulkan GPU - Model: mobilenet OpenBenchmarking.org ms, Fewer Is Better NCNN 20210720 Target: Vulkan GPU - Model: mobilenet NVIDIA RTX 3060 1.0283 2.0566 3.0849 4.1132 5.1415 SE +/- 0.01, N = 3 4.57 MIN: 4.52 / MAX: 4.92 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
VkResample Upscale: 2x - Precision: Single OpenBenchmarking.org ms, Fewer Is Better VkResample 1.0 Upscale: 2x - Precision: Single NVIDIA RTX 3060 6 12 18 24 30 SE +/- 0.02, N = 3 23.15 1. (CXX) g++ options: -O3 -pthread
VkFFT OpenBenchmarking.org Benchmark Score, More Is Better VkFFT 1.1.1 NVIDIA RTX 3060 6K 12K 18K 24K 30K SE +/- 308.54, N = 3 27337 1. (CXX) g++ options: -O3 -pthread
Waifu2x-NCNN Vulkan Scale: 2x - Denoise: 3 - TAA: Yes OpenBenchmarking.org Seconds, Fewer Is Better Waifu2x-NCNN Vulkan 20200818 Scale: 2x - Denoise: 3 - TAA: Yes NVIDIA RTX 3060 1.1192 2.2384 3.3576 4.4768 5.596 SE +/- 0.004, N = 3 4.974
RealSR-NCNN Scale: 4x - TAA: Yes OpenBenchmarking.org Seconds, Fewer Is Better RealSR-NCNN 20200818 Scale: 4x - TAA: Yes NVIDIA RTX 3060 15 30 45 60 75 SE +/- 0.06, N = 3 67.90
RealSR-NCNN Scale: 4x - TAA: No OpenBenchmarking.org Seconds, Fewer Is Better RealSR-NCNN 20200818 Scale: 4x - TAA: No NVIDIA RTX 3060 3 6 9 12 15 SE +/- 0.00, N = 3 10.51
vkpeak int16-vec4 OpenBenchmarking.org GIOPS, More Is Better vkpeak 20210424 int16-vec4 NVIDIA RTX 3060 1300 2600 3900 5200 6500 SE +/- 0.03, N = 3 5957.52
vkpeak int16-scalar OpenBenchmarking.org GIOPS, More Is Better vkpeak 20210424 int16-scalar NVIDIA RTX 3060 1000 2000 3000 4000 5000 SE +/- 0.29, N = 3 4480.11
vkpeak int32-vec4 OpenBenchmarking.org GIOPS, More Is Better vkpeak 20210424 int32-vec4 NVIDIA RTX 3060 1500 3000 4500 6000 7500 SE +/- 17.45, N = 3 6766.46
vkpeak int32-scalar OpenBenchmarking.org GIOPS, More Is Better vkpeak 20210424 int32-scalar NVIDIA RTX 3060 1500 3000 4500 6000 7500 SE +/- 0.58, N = 3 6830.28
vkpeak fp64-vec4 OpenBenchmarking.org GFLOPS, More Is Better vkpeak 20210424 fp64-vec4 NVIDIA RTX 3060 50 100 150 200 250 SE +/- 0.01, N = 3 214.29
vkpeak fp64-scalar OpenBenchmarking.org GFLOPS, More Is Better vkpeak 20210424 fp64-scalar NVIDIA RTX 3060 50 100 150 200 250 SE +/- 0.03, N = 3 214.25
vkpeak fp16-vec4 OpenBenchmarking.org GFLOPS, More Is Better vkpeak 20210424 fp16-vec4 NVIDIA RTX 3060 3K 6K 9K 12K 15K SE +/- 2.31, N = 3 13242.60
vkpeak fp16-scalar OpenBenchmarking.org GFLOPS, More Is Better vkpeak 20210424 fp16-scalar NVIDIA RTX 3060 1500 3000 4500 6000 7500 SE +/- 17.95, N = 3 6849.64
vkpeak fp32-vec4 OpenBenchmarking.org GFLOPS, More Is Better vkpeak 20210424 fp32-vec4 NVIDIA RTX 3060 2K 4K 6K 8K 10K SE +/- 0.30, N = 3 9079.50
vkpeak fp32-scalar OpenBenchmarking.org GFLOPS, More Is Better vkpeak 20210424 fp32-scalar NVIDIA RTX 3060 1500 3000 4500 6000 7500 SE +/- 10.62, N = 3 6829.75
Phoronix Test Suite v10.8.4