Tigerlake Xe Gen12 to Gen9

Tests for a future article

Compare your own system(s) to this result file with the Phoronix Test Suite by running the command: phoronix-test-suite benchmark 2010223-FI-GEN48446330
Jump To Table - Results

View

Do Not Show Noisy Results
Do Not Show Results With Incomplete Data
Do Not Show Results With Little Change/Spread
List Notable Results
Show Result Confidence Charts

Limit displaying results to tests within:

CPU Massive 2 Tests
Desktop Graphics 4 Tests
HPC - High Performance Computing 4 Tests
Machine Learning 4 Tests
NVIDIA GPU Compute 11 Tests
OpenCL 6 Tests
OpenGL Demos Test Suite 3 Tests
Unigine Test Suite 3 Tests
Vulkan Compute 3 Tests

Statistics

Show Overall Harmonic Mean(s)
Show Overall Geometric Mean
Show Geometric Means Per-Suite/Category
Show Wins / Losses Counts (Pie Chart)
Normalize Results
Remove Outliers Before Calculating Averages

Graph Settings

Force Line Graphs Where Applicable
Convert To Scalar Where Applicable
Prefer Vertical Bar Graphs
No Box Plots
On Line Graphs With Missing Data, Connect The Line Gaps

Additional Graphs

Show Perf Per Clock Calculation Graphs Where Applicable

Multi-Way Comparison

Condense Multi-Option Tests Into Single Result Graphs
Condense Test Profiles With Multiple Version Results Into Single Result Graphs

Table

Show Detailed System Result Table

Run Management

Highlight
Result
Hide
Result
Result
Identifier
View Logs
Performance Per
Dollar
Date
Run
  Test
  Duration
Gen9 - i7-8565U
October 21 2020
  9 Hours, 58 Minutes
Gen11 - i7-1065G7
October 20 2020
  8 Hours, 51 Minutes
Gen12 Xe - i7-1165G7
October 21 2020
  5 Hours, 34 Minutes
Invert Hiding All Results Option
  8 Hours, 8 Minutes

Only show results where is faster than
Only show results matching title/arguments (delimit multiple options with a comma):
Do not show results matching title/arguments (delimit multiple options with a comma):


Tigerlake Xe Gen12 to Gen9ProcessorMotherboardChipsetMemoryDiskGraphicsAudioNetworkOSKernelDesktopDisplay ServerDisplay DriverOpenGLOpenCLVulkanCompilerFile-SystemScreen ResolutionGen11 - i7-1065G7Gen12 Xe - i7-1165G7Gen9 - i7-8565UIntel Core i7-1065G7 @ 3.90GHz (4 Cores / 8 Threads)Dell 06CDVY (1.0.9 BIOS)Intel Device 34ef16GBKBG40ZPZ512G NVMe TOSHIBA 512GBIntel Iris Plus G7 3GB (1100MHz)Realtek ALC289Intel Killer Wi-Fi 6 AX1650i 160MHzUbuntu 20.105.9.1-050901-generic (x86_64)GNOME Shell 3.38.1X Server 1.20.9modesetting 1.20.94.6 Mesa 20.3.0-devel (git-4408131 2020-10-20 groovy-oibaf-ppa)OpenCL 3.01.2.145GCC 10.2.0ext41920x1200Intel Core i7-1165G7 @ 4.70GHz (4 Cores / 8 Threads)Dell 0GG9PT (1.0.3 BIOS)Intel Tiger Lake-LPKIOXIA KBG40ZNS256G NVMe 256GBIntel UHD 3GB (1300MHz)Intel Wi-Fi 6 AX2014.6 Mesa 20.3.0-devel (git-fdbc45d 2020-10-21 groovy-oibaf-ppa)Intel Core i7-8565U @ 4.60GHz (4 Cores / 8 Threads)Dell 0KTW76 (1.0.0 BIOS)Intel Cannon Point-LPSK hynix PC401 NVMe 256GBIntel UHD 620 3GB (1150MHz)Realtek ALC3271Qualcomm Atheros QCA6174 802.11ac1920x1080OpenBenchmarking.orgCompiler Details- --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++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-10-JvwpWM/gcc-10-10.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-10-JvwpWM/gcc-10-10.2.0/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-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- Gen11 - i7-1065G7: Scaling Governor: intel_pstate powersave - CPU Microcode: 0x78 - Thermald 2.3- Gen12 Xe - i7-1165G7: Scaling Governor: intel_pstate powersave - CPU Microcode: 0x60 - Thermald 2.3- Gen9 - i7-8565U: Scaling Governor: intel_pstate powersave - CPU Microcode: 0xd6 - Thermald 2.3Python Details- Python 3.8.6Security Details- Gen11 - i7-1065G7: itlb_multihit: KVM: Mitigation of VMX disabled + 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 - Gen12 Xe - i7-1165G7: 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 - Gen9 - i7-8565U: itlb_multihit: KVM: Mitigation of VMX disabled + l1tf: Not affected + mds: Mitigation of Clear buffers; SMT vulnerable + 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 generic retpoline IBPB: conditional IBRS_FW STIBP: conditional RSB filling + srbds: Mitigation of Microcode + tsx_async_abort: Not affected

Gen11 - i7-1065G7Gen12 Xe - i7-1165G7Gen9 - i7-8565ULogarithmic Result OverviewPhoronix Test SuiteFinanceBenchMandelGPULeelaChessZeroSHOC Scalable HeterOgeneous ComputingViennaCLRealSR-NCNNPlaidMLJuliaGPUUnigine HeavenUnigine ValleyWaifu2x-NCNN VulkanUnigine SuperpositionGpuTestNCNNoneAPI Level Zero Testscl-memTesseractclpeakET: LegacyXonotic

Gen11 - i7-1065G7Gen12 Xe - i7-1165G7Gen9 - i7-8565UPer Watt Result OverviewPhoronix Test Suite100%200%299%399%499%LeelaChessZeroJuliaGPUPlaidMLMandelGPUoneAPI Level Zero TestsViennaCLSHOC Scalable HeterOgeneous ComputingUnigine HeavenGpuTestUnigine ValleyUnigine SuperpositionclpeakTesseractcl-memXonoticET: LegacyP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.M

Tigerlake Xe Gen12 to Gen9financebench: Black-Scholes OpenCLshoc: OpenCL - Max SP Flopsshoc: OpenCL - MD5 Hashoneapi-level-zero: Host-To-Device-To-Host Image Copymandelgpu: GPUncnn: Vulkan GPU - yolov4-tinygputest: Pixmark Volplosion - 1920 x 1200 - Fullscreenclpeak: Single-Precision Floatoneapi-level-zero: Peak Half-Precision Computeshoc: OpenCL - FFT SPncnn: Vulkan GPU - vgg16lczero: OpenCLgputest: Pixmark Piano - 1920 x 1200 - Fullscreenplaidml: No - Inference - IMDB LSTM - OpenCLplaidml: No - Inference - DenseNet 201 - OpenCLshoc: OpenCL - Texture Read Bandwidthncnn: Vulkan GPU - resnet18ncnn: Vulkan GPU - resnet50oneapi-level-zero: Peak Integer Computerealsr-ncnn: 4x - Yesviennacl: OpenCL LU Factorizationrealsr-ncnn: 4x - Noplaidml: No - Inference - Inception V3 - OpenCLoneapi-level-zero: Peak Single-Precision Computeunigine-super: 1920 x 1200 - Fullscreen - Medium - OpenGLplaidml: No - Inference - NASNer Large - OpenCLwaifu2x-ncnn: 2x - 3 - Yesjuliagpu: GPUunigine-heaven: 1920 x 1200 - Fullscreen - OpenGLplaidml: No - Inference - VGG19 - OpenCLncnn: Vulkan GPU - alexnetplaidml: No - Inference - VGG16 - OpenCLunigine-valley: 1920 x 1200 - Fullscreen - OpenGLgputest: Furmark - 1920 x 1200 - Fullscreenncnn: Vulkan GPU - mobilenetplaidml: No - Inference - Mobilenet - OpenCLplaidml: No - Inference - ResNet 50 - OpenCLcl-mem: Readwaifu2x-ncnn: 2x - 3 - Noncnn: Vulkan GPU - squeezenetunigine-super: 1920 x 1200 - Fullscreen - Low - OpenGLoneapi-level-zero: Peak Float16 Global Memory Bandwidthncnn: Vulkan GPU - googlenetcl-mem: Copyncnn: Vulkan GPU - shufflenet-v2tesseract: 1920 x 1200clpeak: Global Memory Bandwidthcl-mem: Writeoneapi-level-zero: Device-To-Host Bandwidthoneapi-level-zero: Device-To-Host Bandwidthoneapi-level-zero: Host-To-Device Bandwidthoneapi-level-zero: Host-To-Device Bandwidthncnn: Vulkan GPU - blazefacencnn: Vulkan GPU-v2-v2 - mobilenet-v2gputest: TessMark - 1920 x 1200 - Fullscreenxonotic: 1920 x 1200 - Ultimatencnn: Vulkan GPU-v3-v3 - mobilenet-v3xonotic: 1920 x 1200 - Lowxonotic: 1920 x 1200 - Ultraxonotic: 1920 x 1200 - Highgputest: GiMark - 1920 x 1200 - Fullscreenncnn: Vulkan GPU - efficientnet-b0oneapi-level-zero: Peak System Memory Copy to Shared Memoryclpeak: Kernel Latencyetlegacy: Renderer2 - 1920 x 1200clpeak: Transfer Bandwidth enqueueWriteBufferncnn: Vulkan GPU - mnasnetshoc: OpenCL - Bus Speed Readbackshoc: OpenCL - Bus Speed Downloadshoc: OpenCL - Triadfinancebench: Monte-Carlo OpenCLoneapi-level-zero: Peak Kernel Launch LatencyGen11 - i7-1065G7Gen12 Xe - i7-1165G7Gen9 - i7-8565U6.3435322.990.677810.573623689428.638.957611038.541352.09140.16296.3257928820.1011.30174.16217.1235.91153.1471120.00148.9117143.98834.82920.2079.03.3153.10385184313.216.136316.0316.6319.9317.7436106222.36242.8375.5741.37.06224.6517.034.752218.6235.95.71109.466945.9434.412232.8021.94393912241.3721.9286121.817.53360299.23650898.65209.1609960123.2383929144.1207832172416.7213.808536.8986.439.487.6541.740640.164014.0210579.52373328.95684.1797820.561.677521.634544609194.615.2615951774.813036.68156.16238.44153558430.5222.44189.7577.1815.49439.002538.06573.816268.31146.371219.5216.45.1427.216132508055.128.645317.499.4722.1830.605417829.74299.6087.2957.14.09511.5129.656.939110.5148.03.05140.348657.0247.910057.4826.69018710048.5026.7141620.984.625080121.90413775.47307.6345501155.3708840183.8028138201711.0515.085929.53122.352.155.1460.404858.414321.3040433.37085822.313025.8269231681.190.36914.8377910702352.562.81390438.06751.62338.9719152.793891497.845.8154.262523.8951.46138.5161614.84324.6746202.60115.90418.8625.81.8475.25247930812.610.37016.4225.778.1811.406767225.74116.0834.5222.710.28828.2712.224.527623.7221.66.7565.2225126.7324.019941.1913.46218319750.4713.5921191.818.27284071.60678049.19183.621122993.2094800111.6753218131416.5210.788334.1272.131.648.3623.931923.304810.92362584.71044931.4224OpenBenchmarking.org

FinanceBench

FinanceBench is a collection of financial program benchmarks with support for benchmarking on the GPU. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterFinanceBench 2016-06-06Benchmark: Black-Scholes OpenCLGen11 - i7-1065G7Gen12 Xe - i7-1165G7Gen9 - i7-8565U612182430SE +/- 0.051661, N = 15SE +/- 0.005073, N = 14SE +/- 0.046004, N = 136.3430004.17900025.8269231. (CXX) g++ options: -O3 -lOpenCL

SHOC Scalable HeterOgeneous Computing

The CUDA and OpenCL version of Vetter's Scalable HeterOgeneous Computing benchmark suite. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGFLOPS, More Is BetterSHOC Scalable HeterOgeneous Computing 2015-11-10Target: OpenCL - Benchmark: Max SP FlopsGen11 - i7-1065G7Gen12 Xe - i7-1165G7Gen9 - i7-8565U2K4K6K8K10KSE +/- 4.39, N = 3SE +/- 0.11, N = 3SE +/- 0.77, N = 35322.997820.561681.191. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -lmpi_cxx -lmpi

OpenBenchmarking.orgGHash/s, More Is BetterSHOC Scalable HeterOgeneous Computing 2015-11-10Target: OpenCL - Benchmark: MD5 HashGen11 - i7-1065G7Gen12 Xe - i7-1165G7Gen9 - i7-8565U0.37740.75481.13221.50961.887SE +/- 0.0004, N = 3SE +/- 0.0003, N = 5SE +/- 0.0000, N = 30.67781.67750.36911. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -lmpi_cxx -lmpi

oneAPI Level Zero Tests

This is benchmarking the collection of Intel oneAPI Level Zero Tests. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGB/s, More Is BetteroneAPI Level Zero TestsTest: Host-To-Device-To-Host Image CopyGen11 - i7-1065G7Gen12 Xe - i7-1165G7Gen9 - i7-8565U510152025SE +/- 0.13517, N = 5SE +/- 0.08874, N = 5SE +/- 0.01750, N = 310.5736021.634504.837791. (CXX) g++ options: -ldl -pthread

MandelGPU

MandelGPU is an OpenCL benchmark and this test runs with the OpenCL rendering float4 kernel with a maximum of 4096 iterations. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSamples/sec, More Is BetterMandelGPU 1.3pts1OpenCL Device: GPUGen11 - i7-1065G7Gen12 Xe - i7-1165G7Gen9 - i7-8565U10M20M30M40M50MSE +/- 231636.76, N = 3SE +/- 304086.94, N = 3SE +/- 1337.29, N = 323689428.644609194.610702352.51. (CC) gcc options: -O3 -lm -ftree-vectorize -funroll-loops -lglut -lOpenCL -lGL

NCNN

NCNN is a high performance neural network inference framework optimized for mobile and other platforms developed by Tencent. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: yolov4-tinyGen11 - i7-1065G7Gen12 Xe - i7-1165G7Gen9 - i7-8565U1428425670SE +/- 0.17, N = 3SE +/- 0.02, N = 3SE +/- 0.27, N = 338.9515.2662.81MIN: 32.02 / MAX: 43.37MIN: 14.84 / MAX: 15.7MIN: 48.56 / MAX: 92.551. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

GpuTest

GpuTest is a cross-platform OpenGL benchmark developed at Geeks3D.com that offers tech demos such as FurMark, TessMark, and other workloads to stress various areas of GPUs and drivers. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgPoints, More Is BetterGpuTest 0.7.0Test: Pixmark Volplosion - Resolution: 1920 x 1200 - Mode: FullscreenGen11 - i7-1065G7Gen12 Xe - i7-1165G7Gen9 - i7-8565U30060090012001500SE +/- 5.03, N = 3SE +/- 14.67, N = 37611595390

clpeak

Clpeak is designed to test the peak capabilities of OpenCL devices. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGFLOPS, More Is BetterclpeakOpenCL Test: Single-Precision FloatGen11 - i7-1065G7Gen12 Xe - i7-1165G7Gen9 - i7-8565U400800120016002000SE +/- 0.62, N = 3SE +/- 0.10, N = 4SE +/- 0.06, N = 41038.541774.81438.061. (CXX) g++ options: -O3 -rdynamic -lOpenCL

oneAPI Level Zero Tests

This is benchmarking the collection of Intel oneAPI Level Zero Tests. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGFLOPS, More Is BetteroneAPI Level Zero TestsTest: Peak Half-Precision ComputeGen11 - i7-1065G7Gen12 Xe - i7-1165G7Gen9 - i7-8565U7001400210028003500SE +/- 19.85, N = 3SE +/- 1.09, N = 3SE +/- 0.53, N = 31352.093036.68751.621. (CXX) g++ options: -ldl -pthread

SHOC Scalable HeterOgeneous Computing

The CUDA and OpenCL version of Vetter's Scalable HeterOgeneous Computing benchmark suite. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGFLOPS, More Is BetterSHOC Scalable HeterOgeneous Computing 2015-11-10Target: OpenCL - Benchmark: FFT SPGen11 - i7-1065G7Gen12 Xe - i7-1165G7Gen9 - i7-8565U306090120150SE +/- 0.23, N = 11SE +/- 0.34, N = 12SE +/- 0.05, N = 7140.16156.1638.971. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -lmpi_cxx -lmpi

NCNN

NCNN is a high performance neural network inference framework optimized for mobile and other platforms developed by Tencent. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: vgg16Gen11 - i7-1065G7Gen12 Xe - i7-1165G7Gen9 - i7-8565U306090120150SE +/- 0.04, N = 3SE +/- 0.01, N = 3SE +/- 0.05, N = 396.3238.44152.79MIN: 92.64 / MAX: 97.57MIN: 38.09 / MAX: 38.78MIN: 151.88 / MAX: 153.671. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

LeelaChessZero

LeelaChessZero (lc0 / lczero) is a chess engine automated vian neural networks. This test profile can be used for OpenCL, CUDA + cuDNN, and BLAS (CPU-based) benchmarking. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgNodes Per Second, More Is BetterLeelaChessZero 0.26Backend: OpenCLGen11 - i7-1065G7Gen12 Xe - i7-1165G7Gen9 - i7-8565U30060090012001500SE +/- 8.08, N = 3SE +/- 7.84, N = 3SE +/- 5.24, N = 357915353891. (CXX) g++ options: -flto -pthread

GpuTest

GpuTest is a cross-platform OpenGL benchmark developed at Geeks3D.com that offers tech demos such as FurMark, TessMark, and other workloads to stress various areas of GPUs and drivers. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgPoints, More Is BetterGpuTest 0.7.0Test: Pixmark Piano - Resolution: 1920 x 1200 - Mode: FullscreenGen11 - i7-1065G7Gen12 Xe - i7-1165G7Gen9 - i7-8565U130260390520650SE +/- 1.67, N = 3SE +/- 6.51, N = 3288584149

PlaidML

This test profile uses PlaidML deep learning framework developed by Intel for offering up various benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: IMDB LSTM - Device: OpenCLGen11 - i7-1065G7Gen12 Xe - i7-1165G7Gen9 - i7-8565U714212835SE +/- 0.11, N = 3SE +/- 0.40, N = 3SE +/- 0.02, N = 320.1030.527.84

OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: DenseNet 201 - Device: OpenCLGen11 - i7-1065G7Gen12 Xe - i7-1165G7Gen9 - i7-8565U510152025SE +/- 0.08, N = 3SE +/- 0.10, N = 3SE +/- 0.01, N = 311.3022.445.81

SHOC Scalable HeterOgeneous Computing

The CUDA and OpenCL version of Vetter's Scalable HeterOgeneous Computing benchmark suite. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGB/s, More Is BetterSHOC Scalable HeterOgeneous Computing 2015-11-10Target: OpenCL - Benchmark: Texture Read BandwidthGen11 - i7-1065G7Gen12 Xe - i7-1165G7Gen9 - i7-8565U4080120160200SE +/- 1.66, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3174.16189.7654.261. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -lmpi_cxx -lmpi

NCNN

NCNN is a high performance neural network inference framework optimized for mobile and other platforms developed by Tencent. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: resnet18Gen11 - i7-1065G7Gen12 Xe - i7-1165G7Gen9 - i7-8565U612182430SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.00, N = 317.127.1823.89MIN: 16.86 / MAX: 17.76MIN: 6.79 / MAX: 7.65MIN: 23.4 / MAX: 24.31. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: resnet50Gen11 - i7-1065G7Gen12 Xe - i7-1165G7Gen9 - i7-8565U1224364860SE +/- 0.04, N = 3SE +/- 0.01, N = 3SE +/- 0.03, N = 335.9115.4951.46MIN: 35.46 / MAX: 36.57MIN: 15.23 / MAX: 15.68MIN: 50.23 / MAX: 52.981. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

oneAPI Level Zero Tests

This is benchmarking the collection of Intel oneAPI Level Zero Tests. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGFLOPS, More Is BetteroneAPI Level Zero TestsTest: Peak Integer ComputeGen11 - i7-1065G7Gen12 Xe - i7-1165G7Gen9 - i7-8565U100200300400500SE +/- 2.13, N = 3SE +/- 1.34, N = 3SE +/- 1.20, N = 12153.15439.00138.521. (CXX) g++ options: -ldl -pthread

RealSR-NCNN

RealSR-NCNN is an NCNN neural network implementation of the RealSR project and accelerated using the Vulkan API. RealSR is the Real-World Super Resolution via Kernel Estimation and Noise Injection. NCNN is a high performance neural network inference framework optimized for mobile and other platforms developed by Tencent. This test profile times how long it takes to increase the resolution of a sample image by a scale of 4x with Vulkan. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterRealSR-NCNN 20200818Scale: 4x - TAA: YesGen11 - i7-1065G7Gen12 Xe - i7-1165G7Gen9 - i7-8565U30060090012001500SE +/- 3.12, N = 3SE +/- 1.30, N = 3SE +/- 2.33, N = 31120.00538.071614.84

ViennaCL

ViennaCL is an open-source linear algebra library written in C++ and with support for OpenCL and OpenMP. This test profile uses ViennaCL OpenCL support and runs the included computational benchmark. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGFLOPS, More Is BetterViennaCL 1.4.2OpenCL LU FactorizationGen11 - i7-1065G7Gen12 Xe - i7-1165G7Gen9 - i7-8565U1632486480SE +/- 0.20, N = 10SE +/- 0.09, N = 11SE +/- 0.03, N = 948.9173.8224.671. (CXX) g++ options: -rdynamic -lOpenCL

RealSR-NCNN

RealSR-NCNN is an NCNN neural network implementation of the RealSR project and accelerated using the Vulkan API. RealSR is the Real-World Super Resolution via Kernel Estimation and Noise Injection. NCNN is a high performance neural network inference framework optimized for mobile and other platforms developed by Tencent. This test profile times how long it takes to increase the resolution of a sample image by a scale of 4x with Vulkan. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterRealSR-NCNN 20200818Scale: 4x - TAA: NoGen11 - i7-1065G7Gen12 Xe - i7-1165G7Gen9 - i7-8565U4080120160200SE +/- 0.34, N = 3SE +/- 0.44, N = 3SE +/- 0.57, N = 3143.9968.31202.60

PlaidML

This test profile uses PlaidML deep learning framework developed by Intel for offering up various benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: Inception V3 - Device: OpenCLGen11 - i7-1065G7Gen12 Xe - i7-1165G7Gen9 - i7-8565U1122334455SE +/- 0.07, N = 3SE +/- 0.04, N = 3SE +/- 0.16, N = 334.8246.3715.90

oneAPI Level Zero Tests

This is benchmarking the collection of Intel oneAPI Level Zero Tests. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGB/s, More Is BetteroneAPI Level Zero TestsTest: Peak Single-Precision ComputeGen11 - i7-1065G7Gen12 Xe - i7-1165G7Gen9 - i7-8565U30060090012001500SE +/- 0.06, N = 3SE +/- 0.00, N = 3SE +/- 1.60, N = 3920.211219.52418.861. (CXX) g++ options: -ldl -pthread

Unigine Superposition

This test calculates the average frame-rate within the Superposition demo for the Unigine engine, released in 2017. This engine is extremely demanding on the system's graphics card. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterUnigine Superposition 1.0Resolution: 1920 x 1200 - Mode: Fullscreen - Quality: Medium - Renderer: OpenGLGen11 - i7-1065G7Gen12 Xe - i7-1165G7Gen9 - i7-8565U48121620SE +/- 0.03, N = 3SE +/- 0.00, N = 3SE +/- 0.03, N = 39.016.45.8MAX: 10.8MAX: 21.3MAX: 7.5

PlaidML

This test profile uses PlaidML deep learning framework developed by Intel for offering up various benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: NASNer Large - Device: OpenCLGen11 - i7-1065G7Gen12 Xe - i7-1165G7Gen9 - i7-8565U1.15652.3133.46954.6265.7825SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 33.315.141.84

Waifu2x-NCNN Vulkan

Waifu2x-NCNN is an NCNN neural network implementation of the Waifu2x converter project and accelerated using the Vulkan API. NCNN is a high performance neural network inference framework optimized for mobile and other platforms developed by Tencent. This test profile times how long it takes to increase the resolution of a sample image with Vulkan. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterWaifu2x-NCNN Vulkan 20200818Scale: 2x - Denoise: 3 - TAA: YesGen11 - i7-1065G7Gen12 Xe - i7-1165G7Gen9 - i7-8565U20406080100SE +/- 0.64, N = 6SE +/- 0.03, N = 3SE +/- 0.03, N = 353.1027.2275.25

JuliaGPU

JuliaGPU is an OpenCL benchmark with this version containing various PTS-specific enhancements. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSamples/sec, More Is BetterJuliaGPU 1.2pts1OpenCL Device: GPUGen11 - i7-1065G7Gen12 Xe - i7-1165G7Gen9 - i7-8565U30M60M90M120M150MSE +/- 1031557.09, N = 6SE +/- 1753385.91, N = 4SE +/- 3375.98, N = 385184313.2132508055.147930812.61. (CC) gcc options: -O3 -march=native -ftree-vectorize -funroll-loops -lglut -lOpenCL -lGL -lm

Unigine Heaven

This test calculates the average frame-rate within the Heaven demo for the Unigine engine. This engine is extremely demanding on the system's graphics card. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterUnigine Heaven 4.0Resolution: 1920 x 1200 - Mode: Fullscreen - Renderer: OpenGLGen11 - i7-1065G7Gen12 Xe - i7-1165G7Gen9 - i7-8565U714212835SE +/- 0.24, N = 9SE +/- 0.07, N = 3SE +/- 0.02, N = 316.1428.6510.37

PlaidML

This test profile uses PlaidML deep learning framework developed by Intel for offering up various benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: VGG19 - Device: OpenCLGen11 - i7-1065G7Gen12 Xe - i7-1165G7Gen9 - i7-8565U48121620SE +/- 0.20, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 316.0317.496.42

NCNN

NCNN is a high performance neural network inference framework optimized for mobile and other platforms developed by Tencent. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: alexnetGen11 - i7-1065G7Gen12 Xe - i7-1165G7Gen9 - i7-8565U612182430SE +/- 0.03, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 316.639.4725.77MIN: 15.99 / MAX: 17.2MIN: 8.7 / MAX: 9.75MIN: 25.1 / MAX: 26.351. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

PlaidML

This test profile uses PlaidML deep learning framework developed by Intel for offering up various benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: VGG16 - Device: OpenCLGen11 - i7-1065G7Gen12 Xe - i7-1165G7Gen9 - i7-8565U510152025SE +/- 0.34, N = 12SE +/- 0.03, N = 3SE +/- 0.08, N = 319.9322.188.18

Unigine Valley

This test calculates the average frame-rate within the Valley demo for the Unigine engine, released in February 2013. This engine is extremely demanding on the system's graphics card. Unigine Valley relies upon an OpenGL 3 core profile context. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterUnigine Valley 1.0Resolution: 1920 x 1200 - Mode: Fullscreen - Renderer: OpenGLGen11 - i7-1065G7Gen12 Xe - i7-1165G7Gen9 - i7-8565U714212835SE +/- 0.11, N = 3SE +/- 0.08, N = 3SE +/- 0.06, N = 317.7430.6111.41

GpuTest

GpuTest is a cross-platform OpenGL benchmark developed at Geeks3D.com that offers tech demos such as FurMark, TessMark, and other workloads to stress various areas of GPUs and drivers. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgPoints, More Is BetterGpuTest 0.7.0Test: Furmark - Resolution: 1920 x 1200 - Mode: FullscreenGen11 - i7-1065G7Gen12 Xe - i7-1165G7Gen9 - i7-8565U400800120016002000SE +/- 15.32, N = 3SE +/- 23.44, N = 4SE +/- 8.41, N = 310621782672

NCNN

NCNN is a high performance neural network inference framework optimized for mobile and other platforms developed by Tencent. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: mobilenetGen11 - i7-1065G7Gen12 Xe - i7-1165G7Gen9 - i7-8565U612182430SE +/- 0.20, N = 3SE +/- 0.07, N = 3SE +/- 0.39, N = 322.369.7425.74MIN: 19.29 / MAX: 35.76MIN: 9.4 / MAX: 29.44MIN: 24.44 / MAX: 35.251. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

PlaidML

This test profile uses PlaidML deep learning framework developed by Intel for offering up various benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: Mobilenet - Device: OpenCLGen11 - i7-1065G7Gen12 Xe - i7-1165G7Gen9 - i7-8565U70140210280350SE +/- 3.34, N = 3SE +/- 0.92, N = 3SE +/- 0.03, N = 3242.83299.60116.08

OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: ResNet 50 - Device: OpenCLGen11 - i7-1065G7Gen12 Xe - i7-1165G7Gen9 - i7-8565U20406080100SE +/- 1.07, N = 3SE +/- 0.04, N = 3SE +/- 0.36, N = 375.5787.2934.52

cl-mem

A basic OpenCL memory benchmark. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGB/s, More Is Bettercl-mem 2017-01-13Benchmark: ReadGen11 - i7-1065G7Gen12 Xe - i7-1165G7Gen9 - i7-8565U1326395265SE +/- 0.17, N = 3SE +/- 0.75, N = 3SE +/- 0.23, N = 341.357.122.71. (CC) gcc options: -O2 -flto -lOpenCL

Waifu2x-NCNN Vulkan

Waifu2x-NCNN is an NCNN neural network implementation of the Waifu2x converter project and accelerated using the Vulkan API. NCNN is a high performance neural network inference framework optimized for mobile and other platforms developed by Tencent. This test profile times how long it takes to increase the resolution of a sample image with Vulkan. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterWaifu2x-NCNN Vulkan 20200818Scale: 2x - Denoise: 3 - TAA: NoGen11 - i7-1065G7Gen12 Xe - i7-1165G7Gen9 - i7-8565U3691215SE +/- 0.025, N = 6SE +/- 0.013, N = 8SE +/- 0.026, N = 57.0624.09510.288

NCNN

NCNN is a high performance neural network inference framework optimized for mobile and other platforms developed by Tencent. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: squeezenetGen11 - i7-1065G7Gen12 Xe - i7-1165G7Gen9 - i7-8565U714212835SE +/- 0.32, N = 3SE +/- 0.02, N = 3SE +/- 0.06, N = 324.6511.5128.27MIN: 21.12 / MAX: 29.29MIN: 11.25 / MAX: 13.33MIN: 27.92 / MAX: 40.051. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

Unigine Superposition

This test calculates the average frame-rate within the Superposition demo for the Unigine engine, released in 2017. This engine is extremely demanding on the system's graphics card. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterUnigine Superposition 1.0Resolution: 1920 x 1200 - Mode: Fullscreen - Quality: Low - Renderer: OpenGLGen11 - i7-1065G7Gen12 Xe - i7-1165G7Gen9 - i7-8565U714212835SE +/- 0.09, N = 3SE +/- 0.13, N = 3SE +/- 0.03, N = 317.029.612.2MAX: 23.3MAX: 40.6MAX: 15.2

oneAPI Level Zero Tests

This is benchmarking the collection of Intel oneAPI Level Zero Tests. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGB/s, More Is BetteroneAPI Level Zero TestsTest: Peak Float16 Global Memory BandwidthGen11 - i7-1065G7Gen12 Xe - i7-1165G7Gen9 - i7-8565U1326395265SE +/- 0.01, N = 3SE +/- 0.16, N = 3SE +/- 0.30, N = 334.7556.9424.531. (CXX) g++ options: -ldl -pthread

NCNN

NCNN is a high performance neural network inference framework optimized for mobile and other platforms developed by Tencent. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: googlenetGen11 - i7-1065G7Gen12 Xe - i7-1165G7Gen9 - i7-8565U612182430SE +/- 0.01, N = 3SE +/- 0.03, N = 3SE +/- 0.06, N = 318.6210.5123.72MIN: 18.42 / MAX: 19.34MIN: 10.37 / MAX: 11.21MIN: 22.59 / MAX: 27.761. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

cl-mem

A basic OpenCL memory benchmark. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGB/s, More Is Bettercl-mem 2017-01-13Benchmark: CopyGen11 - i7-1065G7Gen12 Xe - i7-1165G7Gen9 - i7-8565U1122334455SE +/- 0.10, N = 3SE +/- 0.03, N = 3SE +/- 0.24, N = 335.948.021.61. (CC) gcc options: -O2 -flto -lOpenCL

NCNN

NCNN is a high performance neural network inference framework optimized for mobile and other platforms developed by Tencent. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: shufflenet-v2Gen11 - i7-1065G7Gen12 Xe - i7-1165G7Gen9 - i7-8565U246810SE +/- 0.03, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 35.713.056.75MIN: 5.41 / MAX: 10.95MIN: 2.89 / MAX: 3.33MIN: 6.07 / MAX: 7.041. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

Tesseract

Tesseract is a fork of Cube 2 Sauerbraten with numerous graphics and game-play improvements. Tesseract has been in development since 2012 while its first release happened in May of 2014. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterTesseract 2014-05-12Resolution: 1920 x 1200Gen11 - i7-1065G7Gen12 Xe - i7-1165G7Gen9 - i7-8565U306090120150SE +/- 1.48, N = 3SE +/- 0.87, N = 3SE +/- 0.46, N = 3109.47140.3565.22

clpeak

Clpeak is designed to test the peak capabilities of OpenCL devices. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGBPS, More Is BetterclpeakOpenCL Test: Global Memory BandwidthGen11 - i7-1065G7Gen12 Xe - i7-1165G7Gen9 - i7-8565U1326395265SE +/- 0.02, N = 4SE +/- 0.02, N = 4SE +/- 0.09, N = 345.9457.0226.731. (CXX) g++ options: -O3 -rdynamic -lOpenCL

cl-mem

A basic OpenCL memory benchmark. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGB/s, More Is Bettercl-mem 2017-01-13Benchmark: WriteGen11 - i7-1065G7Gen12 Xe - i7-1165G7Gen9 - i7-8565U1122334455SE +/- 0.44, N = 15SE +/- 0.22, N = 3SE +/- 0.32, N = 434.447.924.01. (CC) gcc options: -O2 -flto -lOpenCL

oneAPI Level Zero Tests

This is benchmarking the collection of Intel oneAPI Level Zero Tests. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgusec, Fewer Is BetteroneAPI Level Zero TestsTest: Device-To-Host BandwidthGen11 - i7-1065G7Gen12 Xe - i7-1165G7Gen9 - i7-8565U4K8K12K16K20KSE +/- 7.46, N = 4SE +/- 7.70, N = 5SE +/- 110.24, N = 312232.8010057.4819941.191. (CXX) g++ options: -ldl -pthread

OpenBenchmarking.orgGB/s, More Is BetteroneAPI Level Zero TestsTest: Device-To-Host BandwidthGen11 - i7-1065G7Gen12 Xe - i7-1165G7Gen9 - i7-8565U612182430SE +/- 0.01, N = 4SE +/- 0.02, N = 5SE +/- 0.07, N = 321.9426.6913.461. (CXX) g++ options: -ldl -pthread

OpenBenchmarking.orgusec, Fewer Is BetteroneAPI Level Zero TestsTest: Host-To-Device BandwidthGen11 - i7-1065G7Gen12 Xe - i7-1165G7Gen9 - i7-8565U4K8K12K16K20KSE +/- 11.31, N = 4SE +/- 12.59, N = 5SE +/- 105.37, N = 312241.3710048.5019750.471. (CXX) g++ options: -ldl -pthread

OpenBenchmarking.orgGB/s, More Is BetteroneAPI Level Zero TestsTest: Host-To-Device BandwidthGen11 - i7-1065G7Gen12 Xe - i7-1165G7Gen9 - i7-8565U612182430SE +/- 0.02, N = 4SE +/- 0.03, N = 5SE +/- 0.07, N = 321.9326.7113.591. (CXX) g++ options: -ldl -pthread

NCNN

NCNN is a high performance neural network inference framework optimized for mobile and other platforms developed by Tencent. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: blazefaceGen11 - i7-1065G7Gen12 Xe - i7-1165G7Gen9 - i7-8565U0.40730.81461.22191.62922.0365SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.04, N = 31.810.981.81MIN: 1.58 / MAX: 4.55MIN: 0.88 / MAX: 1.17MIN: 1.66 / MAX: 3.111. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2Gen11 - i7-1065G7Gen12 Xe - i7-1165G7Gen9 - i7-8565U246810SE +/- 0.05, N = 3SE +/- 0.06, N = 3SE +/- 0.04, N = 37.534.628.27MIN: 7.07 / MAX: 8.39MIN: 4 / MAX: 5.44MIN: 7.97 / MAX: 8.561. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

GpuTest

GpuTest is a cross-platform OpenGL benchmark developed at Geeks3D.com that offers tech demos such as FurMark, TessMark, and other workloads to stress various areas of GPUs and drivers. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgPoints, More Is BetterGpuTest 0.7.0Test: TessMark - Resolution: 1920 x 1200 - Mode: FullscreenGen11 - i7-1065G7Gen12 Xe - i7-1165G7Gen9 - i7-8565U11002200330044005500SE +/- 27.39, N = 3SE +/- 25.03, N = 3SE +/- 25.17, N = 3360250802840

Xonotic

This is a benchmark of Xonotic, which is a fork of the DarkPlaces-based Nexuiz game. Development began in March of 2010 on the Xonotic game. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterXonotic 0.8.2Resolution: 1920 x 1200 - Effects Quality: UltimateGen11 - i7-1065G7Gen12 Xe - i7-1165G7Gen9 - i7-8565U306090120150SE +/- 1.54, N = 3SE +/- 1.05, N = 3SE +/- 0.44, N = 399.24121.9071.61MIN: 30 / MAX: 197MIN: 37 / MAX: 232MIN: 26 / MAX: 115

NCNN

NCNN is a high performance neural network inference framework optimized for mobile and other platforms developed by Tencent. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3Gen11 - i7-1065G7Gen12 Xe - i7-1165G7Gen9 - i7-8565U3691215SE +/- 0.01, N = 3SE +/- 0.04, N = 3SE +/- 0.02, N = 38.655.479.19MIN: 8.33 / MAX: 9.56MIN: 5.23 / MAX: 6.31MIN: 8.92 / MAX: 9.71. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

Xonotic

This is a benchmark of Xonotic, which is a fork of the DarkPlaces-based Nexuiz game. Development began in March of 2010 on the Xonotic game. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterXonotic 0.8.2Resolution: 1920 x 1200 - Effects Quality: LowGen11 - i7-1065G7Gen12 Xe - i7-1165G7Gen9 - i7-8565U70140210280350SE +/- 2.16, N = 8SE +/- 3.15, N = 8SE +/- 0.13, N = 3209.16307.63183.62MIN: 123 / MAX: 473MIN: 184 / MAX: 693MIN: 122 / MAX: 299

OpenBenchmarking.orgFrames Per Second, More Is BetterXonotic 0.8.2Resolution: 1920 x 1200 - Effects Quality: UltraGen11 - i7-1065G7Gen12 Xe - i7-1165G7Gen9 - i7-8565U306090120150SE +/- 1.82, N = 3SE +/- 1.36, N = 3SE +/- 0.52, N = 3123.24155.3793.21MIN: 71 / MAX: 245MIN: 79 / MAX: 269MIN: 52 / MAX: 133

OpenBenchmarking.orgFrames Per Second, More Is BetterXonotic 0.8.2Resolution: 1920 x 1200 - Effects Quality: HighGen11 - i7-1065G7Gen12 Xe - i7-1165G7Gen9 - i7-8565U4080120160200SE +/- 2.36, N = 3SE +/- 2.55, N = 3SE +/- 0.86, N = 3144.12183.80111.68MIN: 94 / MAX: 283MIN: 106 / MAX: 306MIN: 78 / MAX: 154

GpuTest

GpuTest is a cross-platform OpenGL benchmark developed at Geeks3D.com that offers tech demos such as FurMark, TessMark, and other workloads to stress various areas of GPUs and drivers. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgPoints, More Is BetterGpuTest 0.7.0Test: GiMark - Resolution: 1920 x 1200 - Mode: FullscreenGen11 - i7-1065G7Gen12 Xe - i7-1165G7Gen9 - i7-8565U400800120016002000SE +/- 9.94, N = 3SE +/- 1.53, N = 3SE +/- 6.33, N = 3172420171314

NCNN

NCNN is a high performance neural network inference framework optimized for mobile and other platforms developed by Tencent. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: efficientnet-b0Gen11 - i7-1065G7Gen12 Xe - i7-1165G7Gen9 - i7-8565U48121620SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 316.7211.0516.52MIN: 16.57 / MAX: 17.26MIN: 10.93 / MAX: 11.86MIN: 15.6 / MAX: 17.191. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

oneAPI Level Zero Tests

This is benchmarking the collection of Intel oneAPI Level Zero Tests. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGB/s, More Is BetteroneAPI Level Zero TestsTest: Peak System Memory Copy to Shared MemoryGen11 - i7-1065G7Gen12 Xe - i7-1165G7Gen9 - i7-8565U48121620SE +/- 0.03, N = 3SE +/- 0.05, N = 3SE +/- 0.10, N = 913.8115.0910.791. (CXX) g++ options: -ldl -pthread

clpeak

Clpeak is designed to test the peak capabilities of OpenCL devices. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgus, Fewer Is BetterclpeakOpenCL Test: Kernel LatencyGen11 - i7-1065G7Gen12 Xe - i7-1165G7Gen9 - i7-8565U816243240SE +/- 0.08, N = 9SE +/- 0.05, N = 9SE +/- 0.28, N = 836.8929.5334.121. (CXX) g++ options: -O3 -rdynamic -lOpenCL

CPU Power Consumption Monitor

OpenBenchmarking.orgWattsCPU Power Consumption MonitorPhoronix Test Suite System MonitoringGen12 Xe - i7-1165G7Gen9 - i7-8565U1224364860Min: 0.95 / Avg: 20.57 / Max: 63.06Min: 0.31 / Avg: 26.76 / Max: 63.03

ET: Legacy

MinAvgMaxGen11 - i7-1065G71.716.030.9Gen12 Xe - i7-1165G71.521.933.4Gen9 - i7-8565U1.021.125.6OpenBenchmarking.orgWatts, Fewer Is BetterET: Legacy 2.75CPU Power Consumption Monitor1020304050

OpenBenchmarking.orgFrames Per Second Per Watt, More Is BetterET: Legacy 2.75Renderer: Renderer2 - Resolution: 1920 x 1200Gen11 - i7-1065G7Gen12 Xe - i7-1165G7Gen9 - i7-8565U1.25782.51563.77345.03126.2895.405.593.41

clpeak

MinAvgMaxGen11 - i7-1065G71.511.418.0Gen12 Xe - i7-1165G71.315.226.0Gen9 - i7-8565U0.712.221.7OpenBenchmarking.orgWatts, Fewer Is BetterclpeakCPU Power Consumption Monitor816243240

OpenBenchmarking.orgGBPS Per Watt, More Is BetterclpeakOpenCL Test: Transfer Bandwidth enqueueWriteBufferGen11 - i7-1065G7Gen12 Xe - i7-1165G7Gen9 - i7-8565U0.77631.55262.32893.10523.88153.453.442.60

SHOC Scalable HeterOgeneous Computing

MinAvgMaxGen11 - i7-1065G71.06.123.7Gen12 Xe - i7-1165G71.28.226.7Gen9 - i7-8565U0.78.934.7OpenBenchmarking.orgWatts, Fewer Is BetterSHOC Scalable HeterOgeneous Computing 2015-11-10CPU Power Consumption Monitor1020304050

OpenBenchmarking.orgGB/s Per Watt, More Is BetterSHOC Scalable HeterOgeneous Computing 2015-11-10Target: OpenCL - Benchmark: Bus Speed ReadbackGen11 - i7-1065G7Gen12 Xe - i7-1165G7Gen9 - i7-8565U2468106.827.392.69

MinAvgMaxGen11 - i7-1065G70.95.923.7Gen12 Xe - i7-1165G71.08.326.9Gen9 - i7-8565U0.38.835.3OpenBenchmarking.orgWatts, Fewer Is BetterSHOC Scalable HeterOgeneous Computing 2015-11-10CPU Power Consumption Monitor1020304050

OpenBenchmarking.orgGB/s Per Watt, More Is BetterSHOC Scalable HeterOgeneous Computing 2015-11-10Target: OpenCL - Benchmark: Bus Speed DownloadGen11 - i7-1065G7Gen12 Xe - i7-1165G7Gen9 - i7-8565U2468106.847.042.65

MinAvgMaxGen11 - i7-1065G71.08.320.9Gen12 Xe - i7-1165G71.011.131.8Gen9 - i7-8565U0.611.931.2OpenBenchmarking.orgWatts, Fewer Is BetterSHOC Scalable HeterOgeneous Computing 2015-11-10CPU Power Consumption Monitor918273645

OpenBenchmarking.orgGB/s Per Watt, More Is BetterSHOC Scalable HeterOgeneous Computing 2015-11-10Target: OpenCL - Benchmark: TriadGen11 - i7-1065G7Gen12 Xe - i7-1165G7Gen9 - i7-8565U0.4320.8641.2961.7282.161.681.920.92

FinanceBench

MinAvgMaxGen11 - i7-1065G70.912.931.9Gen12 Xe - i7-1165G71.315.932.7Gen9 - i7-8565U0.714.822.7OpenBenchmarking.orgWatts, Fewer Is BetterFinanceBench 2016-06-06CPU Power Consumption Monitor1020304050

oneAPI Level Zero Tests

MinAvgMaxGen11 - i7-1065G71.06.622.9Gen12 Xe - i7-1165G71.38.528.9Gen9 - i7-8565U0.58.333.4OpenBenchmarking.orgWatts, Fewer Is BetteroneAPI Level Zero TestsCPU Power Consumption Monitor1020304050

ET: Legacy

ETLegacy is an open-source engine evolution of Wolfenstein: Enemy Territory, a World War II era first person shooter that was released for free by Splash Damage using the id Tech 3 engine. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterET: Legacy 2.75Renderer: Renderer2 - Resolution: 1920 x 1200Gen11 - i7-1065G7Gen12 Xe - i7-1165G7Gen9 - i7-8565U306090120150SE +/- 1.84, N = 15SE +/- 1.11, N = 10SE +/- 0.06, N = 386.4122.372.1

clpeak

Clpeak is designed to test the peak capabilities of OpenCL devices. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGBPS, More Is BetterclpeakOpenCL Test: Transfer Bandwidth enqueueWriteBufferGen11 - i7-1065G7Gen12 Xe - i7-1165G7Gen9 - i7-8565U1224364860SE +/- 0.65, N = 15SE +/- 0.21, N = 6SE +/- 0.01, N = 539.4852.1531.641. (CXX) g++ options: -O3 -rdynamic -lOpenCL

NCNN

NCNN is a high performance neural network inference framework optimized for mobile and other platforms developed by Tencent. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: mnasnetGen11 - i7-1065G7Gen12 Xe - i7-1165G7Gen9 - i7-8565U246810SE +/- 0.05, N = 3SE +/- 0.29, N = 3SE +/- 0.02, N = 37.655.148.36MIN: 7.11 / MAX: 8.41MIN: 4.27 / MAX: 6.74MIN: 8.28 / MAX: 9.051. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

SHOC Scalable HeterOgeneous Computing

The CUDA and OpenCL version of Vetter's Scalable HeterOgeneous Computing benchmark suite. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGB/s, More Is BetterSHOC Scalable HeterOgeneous Computing 2015-11-10Target: OpenCL - Benchmark: Bus Speed ReadbackGen11 - i7-1065G7Gen12 Xe - i7-1165G7Gen9 - i7-8565U1428425670SE +/- 0.42, N = 15SE +/- 0.18, N = 12SE +/- 0.57, N = 1541.7460.4023.931. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -lmpi_cxx -lmpi

OpenBenchmarking.orgGB/s, More Is BetterSHOC Scalable HeterOgeneous Computing 2015-11-10Target: OpenCL - Benchmark: Bus Speed DownloadGen11 - i7-1065G7Gen12 Xe - i7-1165G7Gen9 - i7-8565U1326395265SE +/- 0.11, N = 13SE +/- 0.44, N = 15SE +/- 0.52, N = 1540.1658.4123.301. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -lmpi_cxx -lmpi

OpenBenchmarking.orgGB/s, More Is BetterSHOC Scalable HeterOgeneous Computing 2015-11-10Target: OpenCL - Benchmark: TriadGen11 - i7-1065G7Gen12 Xe - i7-1165G7Gen9 - i7-8565U510152025SE +/- 0.27, N = 15SE +/- 0.12, N = 11SE +/- 0.19, N = 1514.0221.3010.921. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -lmpi_cxx -lmpi

FinanceBench

FinanceBench is a collection of financial program benchmarks with support for benchmarking on the GPU. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterFinanceBench 2016-06-06Benchmark: Monte-Carlo OpenCLGen11 - i7-1065G7Gen12 Xe - i7-1165G7Gen9 - i7-8565U6001200180024003000SE +/- 11.47, N = 15SE +/- 1.46, N = 7SE +/- 55.58, N = 15579.52433.372584.711. (CXX) g++ options: -O3 -lOpenCL

oneAPI Level Zero Tests

This is benchmarking the collection of Intel oneAPI Level Zero Tests. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgus, Fewer Is BetteroneAPI Level Zero TestsTest: Peak Kernel Launch LatencyGen11 - i7-1065G7Gen12 Xe - i7-1165G7Gen9 - i7-8565U714212835SE +/- 0.83, N = 15SE +/- 0.55, N = 15SE +/- 0.15, N = 1228.9622.3131.421. (CXX) g++ options: -ldl -pthread

85 Results Shown

FinanceBench
SHOC Scalable HeterOgeneous Computing:
  OpenCL - Max SP Flops
  OpenCL - MD5 Hash
oneAPI Level Zero Tests
MandelGPU
NCNN
GpuTest
clpeak
oneAPI Level Zero Tests
SHOC Scalable HeterOgeneous Computing
NCNN
LeelaChessZero
GpuTest
PlaidML:
  No - Inference - IMDB LSTM - OpenCL
  No - Inference - DenseNet 201 - OpenCL
SHOC Scalable HeterOgeneous Computing
NCNN:
  Vulkan GPU - resnet18
  Vulkan GPU - resnet50
oneAPI Level Zero Tests
RealSR-NCNN
ViennaCL
RealSR-NCNN
PlaidML
oneAPI Level Zero Tests
Unigine Superposition
PlaidML
Waifu2x-NCNN Vulkan
JuliaGPU
Unigine Heaven
PlaidML
NCNN
PlaidML
Unigine Valley
GpuTest
NCNN
PlaidML:
  No - Inference - Mobilenet - OpenCL
  No - Inference - ResNet 50 - OpenCL
cl-mem
Waifu2x-NCNN Vulkan
NCNN
Unigine Superposition
oneAPI Level Zero Tests
NCNN
cl-mem
NCNN
Tesseract
clpeak
cl-mem
oneAPI Level Zero Tests:
  Device-To-Host Bandwidth:
    usec
    GB/s
  Host-To-Device Bandwidth:
    usec
    GB/s
NCNN:
  Vulkan GPU - blazeface
  Vulkan GPU-v2-v2 - mobilenet-v2
GpuTest
Xonotic
NCNN
Xonotic:
  1920 x 1200 - Low
  1920 x 1200 - Ultra
  1920 x 1200 - High
GpuTest
NCNN
oneAPI Level Zero Tests
clpeak
CPU Power Consumption Monitor:
  Phoronix Test Suite System Monitoring
  CPU Power Consumption Monitor
  Renderer2 - 1920 x 1200
  CPU Power Consumption Monitor
  Transfer Bandwidth enqueueWriteBuffer
  CPU Power Consumption Monitor
  OpenCL - Bus Speed Readback
  CPU Power Consumption Monitor
  OpenCL - Bus Speed Download
  CPU Power Consumption Monitor
  OpenCL - Triad
  CPU Power Consumption Monitor
  CPU Power Consumption Monitor
ET: Legacy
clpeak
NCNN
SHOC Scalable HeterOgeneous Computing:
  OpenCL - Bus Speed Readback
  OpenCL - Bus Speed Download
  OpenCL - Triad
FinanceBench
oneAPI Level Zero Tests