Tiger Lake Xe Graphics Performance

Intel Core i7-1165G7 testing with a Dell 0GG9PT (1.0.3 BIOS) and Intel Xe 3GB on Ubuntu 20.04 via the Phoronix Test Suite.

HTML result view exported from: https://openbenchmarking.org/result/2010228-FI-TIGERLAKE89.

Tiger Lake Xe Graphics PerformanceProcessorMotherboardChipsetMemoryDiskGraphicsAudioNetworkOSKernelDesktopDisplay ServerDisplay DriverOpenGLOpenCLVulkanCompilerFile-SystemScreen ResolutionXe GraphicsIntel Core i7-1165G7 @ 4.70GHz (4 Cores / 8 Threads)Dell 0GG9PT (1.0.3 BIOS)Intel Device a0ef16GBKioxia KBG40ZNS256G NVMe 256GBIntel Xe 3GB (1300MHz)Realtek ALC289Intel Device a0f0Ubuntu 20.045.9.0-050900daily20201021-generic (x86_64)GNOME Shell 3.36.4X Server 1.20.8modesetting 1.20.84.6 Mesa 20.3.0-devel (git-3d51c27 2020-10-21 focal-oibaf-ppa)OpenCL 3.01.2.145GCC 9.3.0ext41920x1200OpenBenchmarking.org- --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --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++,gm2 --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-9-HskZEa/gcc-9-9.3.0/debian/tmp-nvptx/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-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: intel_pstate powersave - CPU Microcode: 0x60 - Thermald 1.9.1- Python 2.7.18 + Python 3.8.5- 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 Enhanced IBRS IBPB: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected

Tiger Lake Xe Graphics Performancerealsr-ncnn: 4x - Norealsr-ncnn: 4x - Yeswaifu2x-ncnn: 2x - 3 - Nowaifu2x-ncnn: 2x - 3 - Yesfinancebench: Monte-Carlo OpenCLfinancebench: Black-Scholes OpenCLshoc: OpenCL - Triadshoc: OpenCL - FFT SPshoc: OpenCL - MD5 Hashshoc: OpenCL - Max SP Flopsshoc: OpenCL - Bus Speed Downloadshoc: OpenCL - Bus Speed Readbackshoc: OpenCL - Texture Read Bandwidthviennacl: OpenCL LU Factorizationcl-mem: Copycl-mem: Readcl-mem: Writeetlegacy: Renderer2 - 1920 x 1200tesseract: 1920 x 1200unigine-heaven: 1920 x 1200 - Fullscreen - OpenGLunigine-super: 1920 x 1200 - Fullscreen - Low - OpenGLunigine-super: 1920 x 1200 - Fullscreen - Medium - OpenGLunigine-valley: 1920 x 1200 - Fullscreen - OpenGLxonotic: 1920 x 1200 - Lowxonotic: 1920 x 1200 - Highxonotic: 1920 x 1200 - Ultraxonotic: 1920 x 1200 - Ultimategputest: GiMark - 1920 x 1200 - Fullscreengputest: Furmark - 1920 x 1200 - Fullscreengputest: TessMark - 1920 x 1200 - Fullscreengputest: Triangle - 1920 x 1200 - Fullscreengputest: Pixmark Piano - 1920 x 1200 - Fullscreengputest: Pixmark Volplosion - 1920 x 1200 - Fullscreenlczero: OpenCLrodinia: OpenCL Myocytencnn: Vulkan GPU - squeezenetncnn: 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-tinyplaidml: No - Inference - VGG16 - OpenCLplaidml: No - Inference - VGG19 - OpenCLplaidml: No - Inference - IMDB LSTM - OpenCLplaidml: No - Inference - Mobilenet - OpenCLplaidml: No - Inference - ResNet 50 - OpenCLplaidml: No - Inference - DenseNet 201 - OpenCLplaidml: No - Inference - Inception V3 - OpenCLplaidml: No - Inference - NASNer Large - OpenCLmandelgpu: GPUsmallpt-gpu: GPU - Complexsmallpt-gpu: GPU - Cornellsmallpt-gpu: GPU - Caustic3clpeak: Kernel Latencyclpeak: Single-Precision Floatclpeak: Global Memory Bandwidthclpeak: Transfer Bandwidth enqueueWriteBufferoneapi-level-zero: Peak Integer Computeoneapi-level-zero: Device-To-Host Bandwidthoneapi-level-zero: Device-To-Host Bandwidthoneapi-level-zero: Host-To-Device Bandwidthoneapi-level-zero: Host-To-Device Bandwidthoneapi-level-zero: Peak Kernel Launch Latencyoneapi-level-zero: Peak Half-Precision Computeoneapi-level-zero: Peak Single-Precision Computeoneapi-level-zero: Host-To-Device-To-Host Image Copyoneapi-level-zero: Peak Float16 Global Memory Bandwidthoneapi-level-zero: Peak System Memory Copy to Shared MemoryXe Graphics73.636581.9644.71228.601451.4659934.32615.2003155.6231.67827820.1853.174855.8650189.59853.250647.756.447.3106.7132.919328.010129.216.230.5298279.3196982188.2008468160.8638948121.5502594201417945076788015861590145278.04312.0210.764.635.683.144.6311.151.3110.6141.157.4510.1015.5917.0919.8115.2630.66358.1595.3519.3043.974.3445778725.416033456371603345763160334589837.011775.8356.6830.49399.61325.76338110419.2825.76430110418.9124.64213036.911219.5121.264960.283812.6809OpenBenchmarking.org

RealSR-NCNN

Scale: 4x - TAA: No

OpenBenchmarking.orgSeconds, Fewer Is BetterRealSR-NCNN 20200818Scale: 4x - TAA: NoXe Graphics1632486480SE +/- 0.67, N = 373.64

RealSR-NCNN

Scale: 4x - TAA: Yes

OpenBenchmarking.orgSeconds, Fewer Is BetterRealSR-NCNN 20200818Scale: 4x - TAA: YesXe Graphics130260390520650SE +/- 0.56, N = 3581.96

Waifu2x-NCNN Vulkan

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

OpenBenchmarking.orgSeconds, Fewer Is BetterWaifu2x-NCNN Vulkan 20200818Scale: 2x - Denoise: 3 - TAA: NoXe Graphics1.06022.12043.18064.24085.301SE +/- 0.004, N = 34.712

Waifu2x-NCNN Vulkan

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

OpenBenchmarking.orgSeconds, Fewer Is BetterWaifu2x-NCNN Vulkan 20200818Scale: 2x - Denoise: 3 - TAA: YesXe Graphics714212835SE +/- 0.03, N = 328.60

FinanceBench

Benchmark: Monte-Carlo OpenCL

OpenBenchmarking.orgms, Fewer Is BetterFinanceBench 2016-06-06Benchmark: Monte-Carlo OpenCLXe Graphics100200300400500SE +/- 1.24, N = 3451.471. (CXX) g++ options: -O3 -lOpenCL

FinanceBench

Benchmark: Black-Scholes OpenCL

OpenBenchmarking.orgms, Fewer Is BetterFinanceBench 2016-06-06Benchmark: Black-Scholes OpenCLXe Graphics0.97341.94682.92023.89364.867SE +/- 0.001, N = 34.3261. (CXX) g++ options: -O3 -lOpenCL

SHOC Scalable HeterOgeneous Computing

Target: OpenCL - Benchmark: Triad

OpenBenchmarking.orgGB/s, More Is BetterSHOC Scalable HeterOgeneous Computing 2015-11-10Target: OpenCL - Benchmark: TriadXe Graphics48121620SE +/- 0.06, N = 315.201. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -lmpi_cxx -lmpi

SHOC Scalable HeterOgeneous Computing

Target: OpenCL - Benchmark: FFT SP

OpenBenchmarking.orgGFLOPS, More Is BetterSHOC Scalable HeterOgeneous Computing 2015-11-10Target: OpenCL - Benchmark: FFT SPXe Graphics306090120150SE +/- 0.52, N = 3155.621. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -lmpi_cxx -lmpi

SHOC Scalable HeterOgeneous Computing

Target: OpenCL - Benchmark: MD5 Hash

OpenBenchmarking.orgGHash/s, More Is BetterSHOC Scalable HeterOgeneous Computing 2015-11-10Target: OpenCL - Benchmark: MD5 HashXe Graphics0.37760.75521.13281.51041.888SE +/- 0.0000, N = 31.67821. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -lmpi_cxx -lmpi

SHOC Scalable HeterOgeneous Computing

Target: OpenCL - Benchmark: Max SP Flops

OpenBenchmarking.orgGFLOPS, More Is BetterSHOC Scalable HeterOgeneous Computing 2015-11-10Target: OpenCL - Benchmark: Max SP FlopsXe Graphics2K4K6K8K10KSE +/- 0.05, N = 37820.181. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -lmpi_cxx -lmpi

SHOC Scalable HeterOgeneous Computing

Target: OpenCL - Benchmark: Bus Speed Download

OpenBenchmarking.orgGB/s, More Is BetterSHOC Scalable HeterOgeneous Computing 2015-11-10Target: OpenCL - Benchmark: Bus Speed DownloadXe Graphics1224364860SE +/- 0.37, N = 353.171. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -lmpi_cxx -lmpi

SHOC Scalable HeterOgeneous Computing

Target: OpenCL - Benchmark: Bus Speed Readback

OpenBenchmarking.orgGB/s, More Is BetterSHOC Scalable HeterOgeneous Computing 2015-11-10Target: OpenCL - Benchmark: Bus Speed ReadbackXe Graphics1326395265SE +/- 0.36, N = 355.871. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -lmpi_cxx -lmpi

SHOC Scalable HeterOgeneous Computing

Target: OpenCL - Benchmark: Texture Read Bandwidth

OpenBenchmarking.orgGB/s, More Is BetterSHOC Scalable HeterOgeneous Computing 2015-11-10Target: OpenCL - Benchmark: Texture Read BandwidthXe Graphics4080120160200SE +/- 0.02, N = 3189.601. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -lmpi_cxx -lmpi

ViennaCL

OpenCL LU Factorization

OpenBenchmarking.orgGFLOPS, More Is BetterViennaCL 1.4.2OpenCL LU FactorizationXe Graphics1224364860SE +/- 0.06, N = 353.251. (CXX) g++ options: -rdynamic -lOpenCL

cl-mem

Benchmark: Copy

OpenBenchmarking.orgGB/s, More Is Bettercl-mem 2017-01-13Benchmark: CopyXe Graphics1122334455SE +/- 0.03, N = 347.71. (CC) gcc options: -O2 -flto -lOpenCL

cl-mem

Benchmark: Read

OpenBenchmarking.orgGB/s, More Is Bettercl-mem 2017-01-13Benchmark: ReadXe Graphics1326395265SE +/- 0.64, N = 356.41. (CC) gcc options: -O2 -flto -lOpenCL

cl-mem

Benchmark: Write

OpenBenchmarking.orgGB/s, More Is Bettercl-mem 2017-01-13Benchmark: WriteXe Graphics1122334455SE +/- 0.09, N = 347.31. (CC) gcc options: -O2 -flto -lOpenCL

ET: Legacy

Renderer: Renderer2 - Resolution: 1920 x 1200

OpenBenchmarking.orgFrames Per Second, More Is BetterET: Legacy 2.75Renderer: Renderer2 - Resolution: 1920 x 1200Xe Graphics20406080100SE +/- 0.52, N = 3106.7

Tesseract

Resolution: 1920 x 1200

OpenBenchmarking.orgFrames Per Second, More Is BetterTesseract 2014-05-12Resolution: 1920 x 1200Xe Graphics306090120150SE +/- 0.68, N = 3132.92

Unigine Heaven

Resolution: 1920 x 1200 - Mode: Fullscreen - Renderer: OpenGL

OpenBenchmarking.orgFrames Per Second, More Is BetterUnigine Heaven 4.0Resolution: 1920 x 1200 - Mode: Fullscreen - Renderer: OpenGLXe Graphics714212835SE +/- 0.04, N = 328.01

Unigine Superposition

Resolution: 1920 x 1200 - Mode: Fullscreen - Quality: Low - Renderer: OpenGL

OpenBenchmarking.orgFrames Per Second, More Is BetterUnigine Superposition 1.0Resolution: 1920 x 1200 - Mode: Fullscreen - Quality: Low - Renderer: OpenGLXe Graphics714212835SE +/- 0.03, N = 329.2MAX: 37.7

Unigine Superposition

Resolution: 1920 x 1200 - Mode: Fullscreen - Quality: Medium - Renderer: OpenGL

OpenBenchmarking.orgFrames Per Second, More Is BetterUnigine Superposition 1.0Resolution: 1920 x 1200 - Mode: Fullscreen - Quality: Medium - Renderer: OpenGLXe Graphics48121620SE +/- 0.00, N = 316.2MAX: 20

Unigine Valley

Resolution: 1920 x 1200 - Mode: Fullscreen - Renderer: OpenGL

OpenBenchmarking.orgFrames Per Second, More Is BetterUnigine Valley 1.0Resolution: 1920 x 1200 - Mode: Fullscreen - Renderer: OpenGLXe Graphics714212835SE +/- 0.06, N = 330.53

Xonotic

Resolution: 1920 x 1200 - Effects Quality: Low

OpenBenchmarking.orgFrames Per Second, More Is BetterXonotic 0.8.2Resolution: 1920 x 1200 - Effects Quality: LowXe Graphics60120180240300SE +/- 0.76, N = 3279.32MIN: 172 / MAX: 641

Xonotic

Resolution: 1920 x 1200 - Effects Quality: High

OpenBenchmarking.orgFrames Per Second, More Is BetterXonotic 0.8.2Resolution: 1920 x 1200 - Effects Quality: HighXe Graphics4080120160200SE +/- 0.24, N = 3188.20MIN: 90 / MAX: 305

Xonotic

Resolution: 1920 x 1200 - Effects Quality: Ultra

OpenBenchmarking.orgFrames Per Second, More Is BetterXonotic 0.8.2Resolution: 1920 x 1200 - Effects Quality: UltraXe Graphics4080120160200SE +/- 0.06, N = 3160.86MIN: 70 / MAX: 252

Xonotic

Resolution: 1920 x 1200 - Effects Quality: Ultimate

OpenBenchmarking.orgFrames Per Second, More Is BetterXonotic 0.8.2Resolution: 1920 x 1200 - Effects Quality: UltimateXe Graphics306090120150SE +/- 0.37, N = 3121.55MIN: 35 / MAX: 211

GpuTest

Test: GiMark - Resolution: 1920 x 1200 - Mode: Fullscreen

OpenBenchmarking.orgPoints, More Is BetterGpuTest 0.7.0Test: GiMark - Resolution: 1920 x 1200 - Mode: FullscreenXe Graphics4008001200160020002014

GpuTest

Test: Furmark - Resolution: 1920 x 1200 - Mode: Fullscreen

OpenBenchmarking.orgPoints, More Is BetterGpuTest 0.7.0Test: Furmark - Resolution: 1920 x 1200 - Mode: FullscreenXe Graphics400800120016002000SE +/- 24.66, N = 31794

GpuTest

Test: TessMark - Resolution: 1920 x 1200 - Mode: Fullscreen

OpenBenchmarking.orgPoints, More Is BetterGpuTest 0.7.0Test: TessMark - Resolution: 1920 x 1200 - Mode: FullscreenXe Graphics11002200330044005500SE +/- 14.40, N = 35076

GpuTest

Test: Triangle - Resolution: 1920 x 1200 - Mode: Fullscreen

OpenBenchmarking.orgPoints, More Is BetterGpuTest 0.7.0Test: Triangle - Resolution: 1920 x 1200 - Mode: FullscreenXe Graphics20K40K60K80K100KSE +/- 70.44, N = 378801

GpuTest

Test: Pixmark Piano - Resolution: 1920 x 1200 - Mode: Fullscreen

OpenBenchmarking.orgPoints, More Is BetterGpuTest 0.7.0Test: Pixmark Piano - Resolution: 1920 x 1200 - Mode: FullscreenXe Graphics130260390520650SE +/- 3.38, N = 3586

GpuTest

Test: Pixmark Volplosion - Resolution: 1920 x 1200 - Mode: Fullscreen

OpenBenchmarking.orgPoints, More Is BetterGpuTest 0.7.0Test: Pixmark Volplosion - Resolution: 1920 x 1200 - Mode: FullscreenXe Graphics30060090012001500SE +/- 10.17, N = 31590

LeelaChessZero

Backend: OpenCL

OpenBenchmarking.orgNodes Per Second, More Is BetterLeelaChessZero 0.26Backend: OpenCLXe Graphics30060090012001500SE +/- 9.06, N = 314521. (CXX) g++ options: -flto -pthread

Rodinia

Test: OpenCL Myocyte

OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 3.1Test: OpenCL MyocyteXe Graphics20406080100SE +/- 8.81, N = 1378.041. (CXX) g++ options: -O2 -lOpenCL

NCNN

Target: Vulkan GPU - Model: squeezenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: squeezenetXe Graphics3691215SE +/- 0.02, N = 312.02MIN: 11.8 / MAX: 13.41. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: mobilenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: mobilenetXe Graphics3691215SE +/- 0.01, N = 310.76MIN: 10.57 / MAX: 13.061. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

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

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2Xe Graphics1.04182.08363.12544.16725.209SE +/- 0.33, N = 34.63MIN: 4.11 / MAX: 6.021. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

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

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3Xe Graphics1.2782.5563.8345.1126.39SE +/- 0.11, N = 35.68MIN: 5.34 / MAX: 7.81. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: shufflenet-v2

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: shufflenet-v2Xe Graphics0.70651.4132.11952.8263.5325SE +/- 0.01, N = 33.14MIN: 2.97 / MAX: 3.411. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: mnasnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: mnasnetXe Graphics1.04182.08363.12544.16725.209SE +/- 0.03, N = 34.63MIN: 4.43 / MAX: 5.281. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: efficientnet-b0

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: efficientnet-b0Xe Graphics3691215SE +/- 0.02, N = 311.15MIN: 11.04 / MAX: 11.891. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: blazeface

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: blazefaceXe Graphics0.29480.58960.88441.17921.474SE +/- 0.04, N = 31.31MIN: 1.01 / MAX: 5.341. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: googlenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: googlenetXe Graphics3691215SE +/- 0.02, N = 310.61MIN: 10.51 / MAX: 10.951. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: vgg16

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: vgg16Xe Graphics918273645SE +/- 0.03, N = 341.15MIN: 40.8 / MAX: 41.541. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: resnet18

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: resnet18Xe Graphics246810SE +/- 0.12, N = 37.45MIN: 7.13 / MAX: 8.041. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: alexnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: alexnetXe Graphics3691215SE +/- 0.02, N = 310.10MIN: 9.87 / MAX: 10.261. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: resnet50

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: resnet50Xe Graphics48121620SE +/- 0.01, N = 315.59MIN: 15.42 / MAX: 15.861. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NCNN

Target: Vulkan GPU - Model: yolov4-tiny

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: yolov4-tinyXe Graphics48121620SE +/- 0.03, N = 317.09MIN: 16.88 / MAX: 19.591. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

PlaidML

FP16: No - Mode: Inference - Network: VGG16 - Device: OpenCL

OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: VGG16 - Device: OpenCLXe Graphics510152025SE +/- 0.12, N = 319.81

PlaidML

FP16: No - Mode: Inference - Network: VGG19 - Device: OpenCL

OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: VGG19 - Device: OpenCLXe Graphics48121620SE +/- 0.02, N = 315.26

PlaidML

FP16: No - Mode: Inference - Network: IMDB LSTM - Device: OpenCL

OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: IMDB LSTM - Device: OpenCLXe Graphics714212835SE +/- 0.32, N = 330.66

PlaidML

FP16: No - Mode: Inference - Network: Mobilenet - Device: OpenCL

OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: Mobilenet - Device: OpenCLXe Graphics80160240320400SE +/- 0.19, N = 3358.15

PlaidML

FP16: No - Mode: Inference - Network: ResNet 50 - Device: OpenCL

OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: ResNet 50 - Device: OpenCLXe Graphics20406080100SE +/- 1.25, N = 495.35

PlaidML

FP16: No - Mode: Inference - Network: DenseNet 201 - Device: OpenCL

OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: DenseNet 201 - Device: OpenCLXe Graphics510152025SE +/- 0.05, N = 319.30

PlaidML

FP16: No - Mode: Inference - Network: Inception V3 - Device: OpenCL

OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: Inception V3 - Device: OpenCLXe Graphics1020304050SE +/- 0.11, N = 343.97

PlaidML

FP16: No - Mode: Inference - Network: NASNer Large - Device: OpenCL

OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: NASNer Large - Device: OpenCLXe Graphics0.97651.9532.92953.9064.8825SE +/- 0.00, N = 34.34

MandelGPU

OpenCL Device: GPU

OpenBenchmarking.orgSamples/sec, More Is BetterMandelGPU 1.3pts1OpenCL Device: GPUXe Graphics10M20M30M40M50MSE +/- 17622.89, N = 345778725.41. (CC) gcc options: -O3 -lm -ftree-vectorize -funroll-loops -lglut -lOpenCL -lGL

SmallPT GPU

OpenCL Device: GPU - Scene: Complex

OpenBenchmarking.orgSamples/sec, More Is BetterSmallPT GPU 1.6pts1OpenCL Device: GPU - Scene: ComplexXe Graphics300M600M900M1200M1500MSE +/- 22.23, N = 316033456371. (CC) gcc options: -O3 -lm -ftree-vectorize -funroll-loops -lglut -lOpenCL -lGL

SmallPT GPU

OpenCL Device: GPU - Scene: Cornell

OpenBenchmarking.orgSamples/sec, More Is BetterSmallPT GPU 1.6pts1OpenCL Device: GPU - Scene: CornellXe Graphics300M600M900M1200M1500MSE +/- 23.67, N = 316033457631. (CC) gcc options: -O3 -lm -ftree-vectorize -funroll-loops -lglut -lOpenCL -lGL

SmallPT GPU

OpenCL Device: GPU - Scene: Caustic3

OpenBenchmarking.orgSamples/sec, More Is BetterSmallPT GPU 1.6pts1OpenCL Device: GPU - Scene: Caustic3Xe Graphics300M600M900M1200M1500MSE +/- 25.12, N = 316033458981. (CC) gcc options: -O3 -lm -ftree-vectorize -funroll-loops -lglut -lOpenCL -lGL

clpeak

OpenCL Test: Kernel Latency

OpenBenchmarking.orgus, Fewer Is BetterclpeakOpenCL Test: Kernel LatencyXe Graphics918273645SE +/- 0.43, N = 1537.011. (CXX) g++ options: -O3 -rdynamic -lOpenCL

clpeak

OpenCL Test: Single-Precision Float

OpenBenchmarking.orgGFLOPS, More Is BetterclpeakOpenCL Test: Single-Precision FloatXe Graphics400800120016002000SE +/- 0.19, N = 31775.831. (CXX) g++ options: -O3 -rdynamic -lOpenCL

clpeak

OpenCL Test: Global Memory Bandwidth

OpenBenchmarking.orgGBPS, More Is BetterclpeakOpenCL Test: Global Memory BandwidthXe Graphics1326395265SE +/- 0.05, N = 356.681. (CXX) g++ options: -O3 -rdynamic -lOpenCL

clpeak

OpenCL Test: Transfer Bandwidth enqueueWriteBuffer

OpenBenchmarking.orgGBPS, More Is BetterclpeakOpenCL Test: Transfer Bandwidth enqueueWriteBufferXe Graphics714212835SE +/- 0.45, N = 430.491. (CXX) g++ options: -O3 -rdynamic -lOpenCL

oneAPI Level Zero Tests

Test: Peak Integer Compute

OpenBenchmarking.orgGFLOPS, More Is BetteroneAPI Level Zero TestsTest: Peak Integer ComputeXe Graphics90180270360450SE +/- 0.72, N = 3399.611. (CXX) g++ options: -ldl -pthread

oneAPI Level Zero Tests

Test: Device-To-Host Bandwidth

OpenBenchmarking.orgGB/s, More Is BetteroneAPI Level Zero TestsTest: Device-To-Host BandwidthXe Graphics612182430SE +/- 0.02, N = 325.761. (CXX) g++ options: -ldl -pthread

oneAPI Level Zero Tests

Test: Device-To-Host Bandwidth

OpenBenchmarking.orgusec, Fewer Is BetteroneAPI Level Zero TestsTest: Device-To-Host BandwidthXe Graphics2K4K6K8K10KSE +/- 7.98, N = 310419.281. (CXX) g++ options: -ldl -pthread

oneAPI Level Zero Tests

Test: Host-To-Device Bandwidth

OpenBenchmarking.orgGB/s, More Is BetteroneAPI Level Zero TestsTest: Host-To-Device BandwidthXe Graphics612182430SE +/- 0.02, N = 325.761. (CXX) g++ options: -ldl -pthread

oneAPI Level Zero Tests

Test: Host-To-Device Bandwidth

OpenBenchmarking.orgusec, Fewer Is BetteroneAPI Level Zero TestsTest: Host-To-Device BandwidthXe Graphics2K4K6K8K10KSE +/- 8.92, N = 310418.911. (CXX) g++ options: -ldl -pthread

oneAPI Level Zero Tests

Test: Peak Kernel Launch Latency

OpenBenchmarking.orgus, Fewer Is BetteroneAPI Level Zero TestsTest: Peak Kernel Launch LatencyXe Graphics612182430SE +/- 1.04, N = 1524.641. (CXX) g++ options: -ldl -pthread

oneAPI Level Zero Tests

Test: Peak Half-Precision Compute

OpenBenchmarking.orgGFLOPS, More Is BetteroneAPI Level Zero TestsTest: Peak Half-Precision ComputeXe Graphics7001400210028003500SE +/- 1.44, N = 33036.911. (CXX) g++ options: -ldl -pthread

oneAPI Level Zero Tests

Test: Peak Single-Precision Compute

OpenBenchmarking.orgGB/s, More Is BetteroneAPI Level Zero TestsTest: Peak Single-Precision ComputeXe Graphics30060090012001500SE +/- 0.00, N = 31219.511. (CXX) g++ options: -ldl -pthread

oneAPI Level Zero Tests

Test: Host-To-Device-To-Host Image Copy

OpenBenchmarking.orgGB/s, More Is BetteroneAPI Level Zero TestsTest: Host-To-Device-To-Host Image CopyXe Graphics510152025SE +/- 0.08, N = 321.261. (CXX) g++ options: -ldl -pthread

oneAPI Level Zero Tests

Test: Peak Float16 Global Memory Bandwidth

OpenBenchmarking.orgGB/s, More Is BetteroneAPI Level Zero TestsTest: Peak Float16 Global Memory BandwidthXe Graphics1326395265SE +/- 0.01, N = 360.281. (CXX) g++ options: -ldl -pthread

oneAPI Level Zero Tests

Test: Peak System Memory Copy to Shared Memory

OpenBenchmarking.orgGB/s, More Is BetteroneAPI Level Zero TestsTest: Peak System Memory Copy to Shared MemoryXe Graphics3691215SE +/- 0.05, N = 312.681. (CXX) g++ options: -ldl -pthread

Phoronix Test Suite v10.8.4