vulkan compute dg2

AMD Ryzen 7 5700G testing with a ASUS TUF GAMING B550M-PLUS (WI-FI) (2423 BIOS) and i915drmfb on Ubuntu 22.04 via the Phoronix Test Suite.

HTML result view exported from: https://openbenchmarking.org/result/2208279-NE-VULKANCOM68.

vulkan compute dg2ProcessorMotherboardChipsetMemoryDiskGraphicsAudioMonitorNetworkOSKernelDesktopDisplay ServerOpenGLOpenCLVulkanCompilerFile-SystemScreen ResolutionABCDAMD Ryzen 7 5700G @ 4.67GHz (8 Cores / 16 Threads)ASUS TUF GAMING B550M-PLUS (WI-FI) (2423 BIOS)AMD Renoir/Cezanne16GB1000GB Samsung SSD 980 PRO 1TB + 2000GBi915drmfb (2450MHz)Intel Device 4f92MX279Realtek RTL8125 2.5GbE + Intel Wi-Fi 6 AX200Ubuntu 22.045.18.0-rc2-drm-intel-gt-next (x86_64)GNOME Shell 42.2X Server 1.21.1.34.6 Mesa 22.3.0-devel (git-0c8492c 2022-08-24 jammy-oibaf-ppa)OpenCL 3.01.3.224GCC 11.2.0ext41920x1080OpenBenchmarking.orgKernel Details- i915.force_probe=56a5 - Transparent Huge Pages: madviseCompiler 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-gBFGDP/gcc-11-11.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-gBFGDP/gcc-11-11.2.0/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-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: amd-pstate performance (Boost: Enabled) - CPU Microcode: 0xa50000cSecurity Details- 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 usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling + srbds: Not affected + tsx_async_abort: Not affected

vulkan compute dg2realsr-ncnn: 4x - Norealsr-ncnn: 4x - Yeswaifu2x-ncnn: 2x - 3 - Nowaifu2x-ncnn: 2x - 3 - Yesvkresample: 2x - Singlencnn: 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 - FastestDetABCD34.516211.4063.11912.21542.81338.859.3113.9712.7710.5419.455.4418.8733.9911.315.2719.08114.02121.7617.453673.5923.9834.479211.2213.08612.2742.78839.510.9915.9615.611020.765.2620.4433.969.44.7416.9112.74118.3917.393675.9123.9634.472211.8553.0812.19842.78538.9510.4214.7613.7810.9420.485.2719.7933.9611.654.8416.94116.61124.7217.433676.6823.934.46211.3623.14712.20342.79239.38.5714.215.3111.420.315.4720.3633.959.374.7316.9117.64118.8517.393673.6223.93OpenBenchmarking.org

RealSR-NCNN

Scale: 4x - TAA: No

OpenBenchmarking.orgSeconds, Fewer Is BetterRealSR-NCNN 20200818Scale: 4x - TAA: NoABCD816243240SE +/- 0.11, N = 334.5234.4834.4734.46

RealSR-NCNN

Scale: 4x - TAA: Yes

OpenBenchmarking.orgSeconds, Fewer Is BetterRealSR-NCNN 20200818Scale: 4x - TAA: YesABCD50100150200250SE +/- 0.04, N = 3211.41211.22211.86211.36

Waifu2x-NCNN Vulkan

Scale: 2x - Denoise: 3 - TAA: No

OpenBenchmarking.orgSeconds, Fewer Is BetterWaifu2x-NCNN Vulkan 20200818Scale: 2x - Denoise: 3 - TAA: NoABCD0.70811.41622.12432.83243.5405SE +/- 0.036, N = 33.1193.0863.0803.147

Waifu2x-NCNN Vulkan

Scale: 2x - Denoise: 3 - TAA: Yes

OpenBenchmarking.orgSeconds, Fewer Is BetterWaifu2x-NCNN Vulkan 20200818Scale: 2x - Denoise: 3 - TAA: YesABCD3691215SE +/- 0.01, N = 312.2212.2712.2012.20

VkResample

Upscale: 2x - Precision: Single

OpenBenchmarking.orgms, Fewer Is BetterVkResample 1.0Upscale: 2x - Precision: SingleABCD1020304050SE +/- 0.02, N = 342.8142.7942.7942.791. (CXX) g++ options: -O3

NCNN

Target: Vulkan GPU - Model: mobilenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: mobilenetABCD918273645SE +/- 0.50, N = 938.8539.5038.9539.30MIN: 29.66 / MAX: 71.78MIN: 30.59 / MAX: 52.51MIN: 30.01 / MAX: 52.99MIN: 32.85 / MAX: 53.081. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

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

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2ABCD3691215SE +/- 0.50, N = 99.3110.9910.428.57MIN: 5.77 / MAX: 23.25MIN: 10.54 / MAX: 11.74MIN: 9.92 / MAX: 10.88MIN: 7.84 / MAX: 91. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

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

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3ABCD48121620SE +/- 0.63, N = 913.9715.9614.7614.20MIN: 9.57 / MAX: 20.61MIN: 14.85 / MAX: 16.35MIN: 14.32 / MAX: 15.02MIN: 13.34 / MAX: 15.031. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: shufflenet-v2

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: shufflenet-v2ABCD48121620SE +/- 0.64, N = 912.7715.6113.7815.31MIN: 8.89 / MAX: 28.2MIN: 15.05 / MAX: 15.85MIN: 11.32 / MAX: 15.79MIN: 11.31 / MAX: 15.891. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: mnasnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: mnasnetABCD3691215SE +/- 0.05, N = 910.5410.0010.9411.40MIN: 9.44 / MAX: 15.07MIN: 9.46 / MAX: 10.54MIN: 9.94 / MAX: 12.39MIN: 10.95 / MAX: 11.711. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: efficientnet-b0

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: efficientnet-b0ABCD510152025SE +/- 0.99, N = 919.4520.7620.4820.31MIN: 10.36 / MAX: 25.3MIN: 19.49 / MAX: 21.69MIN: 19.32 / MAX: 21.53MIN: 18.49 / MAX: 21.531. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: blazeface

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: blazefaceABCD1.23082.46163.69244.92326.154SE +/- 0.13, N = 95.445.265.275.47MIN: 4.57 / MAX: 9.25MIN: 4.84 / MAX: 5.54MIN: 4.98 / MAX: 5.85MIN: 5.01 / MAX: 6.151. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: googlenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: googlenetABCD510152025SE +/- 0.79, N = 918.8720.4419.7920.36MIN: 13.1 / MAX: 33.05MIN: 19.93 / MAX: 22.88MIN: 19.28 / MAX: 20.04MIN: 18.59 / MAX: 22.661. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: vgg16

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: vgg16ABCD816243240SE +/- 0.01, N = 933.9933.9633.9633.95MIN: 32.69 / MAX: 51.63MIN: 33.14 / MAX: 34.52MIN: 33.32 / MAX: 34.28MIN: 33.15 / MAX: 34.221. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: resnet18

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: resnet18ABCD3691215SE +/- 0.24, N = 911.319.4011.659.37MIN: 8.7 / MAX: 14.89MIN: 8.64 / MAX: 10.18MIN: 10.91 / MAX: 13.25MIN: 8.7 / MAX: 10.111. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: alexnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: alexnetABCD1.18582.37163.55744.74325.929SE +/- 0.22, N = 95.274.744.844.73MIN: 4.2 / MAX: 9.7MIN: 4.59 / MAX: 4.89MIN: 4.67 / MAX: 5.04MIN: 4.57 / MAX: 4.931. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: resnet50

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: resnet50ABCD510152025SE +/- 0.44, N = 919.0816.9016.9416.90MIN: 16.33 / MAX: 27.2MIN: 16.41 / MAX: 17.47MIN: 16.37 / MAX: 17.42MIN: 16.41 / MAX: 17.431. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: yolov4-tiny

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: yolov4-tinyABCD306090120150SE +/- 1.47, N = 9114.02112.74116.61117.64MIN: 78.35 / MAX: 146.38MIN: 82.49 / MAX: 124.5MIN: 80.94 / MAX: 124.72MIN: 80.52 / MAX: 124.381. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: squeezenet_ssd

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: squeezenet_ssdABCD306090120150SE +/- 0.98, N = 9121.76118.39124.72118.85MIN: 87.88 / MAX: 138.36MIN: 91.67 / MAX: 135.2MIN: 89.72 / MAX: 144.09MIN: 89.52 / MAX: 134.561. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: regnety_400m

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: regnety_400mABCD48121620SE +/- 0.02, N = 917.4517.3917.4317.39MIN: 15.88 / MAX: 30.18MIN: 16.99 / MAX: 19.94MIN: 16.95 / MAX: 17.75MIN: 16.92 / MAX: 21.491. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: vision_transformer

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: vision_transformerABCD8001600240032004000SE +/- 1.75, N = 93673.593675.913676.683673.62MIN: 3104.14 / MAX: 3787.26MIN: 3181.41 / MAX: 3762.17MIN: 3201.78 / MAX: 3750.92MIN: 3131.14 / MAX: 3756.461. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: FastestDet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: Vulkan GPU - Model: FastestDetABCD612182430SE +/- 0.04, N = 923.9823.9623.9023.93MIN: 21.03 / MAX: 36.36MIN: 22.27 / MAX: 24.38MIN: 21.99 / MAX: 24.32MIN: 22.02 / MAX: 24.411. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread


Phoronix Test Suite v10.8.4