Intel Linux Rocket Lake Graphics

Intel Gen12 Rocket Lake Linux graphics performance 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 2103291-IB-INTELLINU95
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 2 Tests
HPC - High Performance Computing 4 Tests
Machine Learning 4 Tests
NVIDIA GPU Compute 11 Tests
OpenCL 5 Tests
Python Tests 2 Tests
Vulkan Compute 4 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
Disable Color Branding
Prefer Vertical Bar Graphs
No Box Plots
On Line Graphs With Missing Data, Connect The Line Gaps

Additional Graphs

Show Perf Per Core/Thread Calculation Graphs Where Applicable
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
Performance Per
Dollar
Date
Run
  Test
  Duration
Core i5 10600K
March 22 2021
  3 Hours, 48 Minutes
Core i9 10900K
March 21 2021
  3 Hours, 41 Minutes
Core i5 11600K
March 24 2021
  2 Hours, 55 Minutes
Core i9 11900K
March 25 2021
  3 Hours, 55 Minutes
Invert Hiding All Results Option
  3 Hours, 35 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):


Intel Linux Rocket Lake GraphicsProcessorMotherboardChipsetMemoryDiskGraphicsAudioMonitorNetworkOSKernelDesktopDisplay ServerOpenGLOpenCLCompilerFile-SystemScreen ResolutionCore i5 10600KCore i9 10900KCore i5 11600KCore i9 11900KIntel Core i5-10600K @ 4.80GHz (6 Cores / 12 Threads)Gigabyte Z490 AORUS MASTER (F20d BIOS)Intel Comet Lake PCH32GB1000GB Western Digital WD_BLACK SN850 1TB + 2000GBGigabyte Intel CometLake-S GT2 [UHD 630] 3GB (1200MHz)Realtek ALC1220DELL P2415QIntel I225-V + Intel Comet Lake PCH CNVi WiFiUbuntu 21.045.12.0-051200rc3daily20210315-generic (x86_64) 20210314GNOME Shell 3.38.3X Server 1.20.9 + Wayland4.6 Mesa 21.1.0-devel (git-616720d 2021-03-16 hirsute-oibaf-ppa)OpenCL 3.0GCC 10.2.1 20210312ext43840x2160Intel Core i9-10900K @ 5.30GHz (10 Cores / 20 Threads)Intel Core i5-11600K @ 4.90GHz (6 Cores / 12 Threads)ASUS ROG MAXIMUS XIII HERO (0610 BIOS)Intel Device 43efASUS Intel 3GB (1300MHz)Intel Device 43c82 x Intel I225-V + Intel Device 2725X Server 1.20.10 + WaylandIntel Core i9-11900K @ 5.10GHz (8 Cores / 16 Threads)Intel Tiger Lake-HIntel Tiger Lake-H HD AudioOpenBenchmarking.orgKernel Details- Core i5 10600K: Transparent Huge Pages: madvise- Core i9 10900K: Transparent Huge Pages: madvise- Core i5 11600K: i915.force_probe=4c8a - Transparent Huge Pages: madvise- Core i9 11900K: i915.force_probe=4c8a - Transparent Huge Pages: madviseEnvironment Details- DEBUGINFOD_URLS=Compiler Details- --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-p9aljy/gcc-10-10.2.1/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-10-p9aljy/gcc-10-10.2.1/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 Processor Details- Core i5 10600K: Scaling Governor: intel_pstate powersave - CPU Microcode: 0xe2 - Thermald 2.4.3- Core i9 10900K: Scaling Governor: intel_pstate powersave - CPU Microcode: 0xe2 - Thermald 2.4.3- Core i5 11600K: Scaling Governor: intel_pstate powersave - CPU Microcode: 0x39 - Thermald 2.4.3- Core i9 11900K: Scaling Governor: intel_pstate powersave - CPU Microcode: 0x39 - Thermald 2.4.3Graphics Details- Core i5 10600K, Core i9 10900K: GLAMORPython Details- Python 3.9.2Security Details- Core i5 10600K: 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 - Core i9 10900K: 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 - Core i5 11600K: 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 - Core i9 11900K: 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

Core i5 10600KCore i9 10900KCore i5 11600KCore i9 11900KResult OverviewPhoronix Test Suite100%172%245%317%FinanceBenchLeelaChessZeroPlaidMLParaViewViennaCLVkResampleSHOC Scalable HeterOgeneous ComputingRealSR-NCNNGpuTestMandelGPUWaifu2x-NCNN VulkanNCNNBasemark GPUclpeakJuliaGPUTesseract

Core i5 10600KCore i9 10900KCore i5 11600KCore i9 11900KPer Watt Result OverviewPhoronix Test Suite100%137%173%210%LeelaChessZeroMandelGPUPlaidMLViennaCLParaViewJuliaGPUTesseractclpeakSHOC Scalable HeterOgeneous ComputingBasemark GPUGpuTestP.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

Intel Linux Rocket Lake Graphicsplaidml: No - Inference - VGG19 - OpenCLbasemark: Vulkan - 1920 x 1080 - Mediumplaidml: No - Inference - VGG16 - OpenCLparaview: Wavelet Volume - 1920 x 1080tesseract: 1920 x 1080tesseract: 3840 x 2160shoc: OpenCL - Triadshoc: OpenCL - Bus Speed Downloadshoc: OpenCL - Bus Speed Readbackshoc: OpenCL - Texture Read Bandwidthclpeak: Global Memory Bandwidthclpeak: Transfer Bandwidth enqueueReadBuffershoc: OpenCL - Max SP Flopsshoc: OpenCL - FFT SPclpeak: Single-Precision Floatviennacl: OpenCL LU Factorizationshoc: OpenCL - MD5 Hashparaview: Wavelet Volume - 1920 x 1080lczero: OpenCLgputest: TessMark - 1920 x 1080 - Fullscreengputest: GiMark - 1920 x 1080 - Fullscreengputest: Triangle - 1920 x 1080 - Fullscreengputest: Plot3D - 1920 x 1080 - Fullscreenjuliagpu: GPUmandelgpu: GPUncnn: 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 - regnety_400mvkresample: 2x - Singlefinancebench: Black-Scholes OpenCLfinancebench: Monte-Carlo OpenCLrealsr-ncnn: 4x - Yesrealsr-ncnn: 4x - Nowaifu2x-ncnn: 2x - 3 - Yeswaifu2x-ncnn: 2x - 3 - Noclpeak: Kernel LatencyCore i5 10600KCore i9 10900KCore i5 11600KCore i9 11900K7.5366.679.4922.1667.2127824.1882013.266526.359226.282456.770435.9615.721762.4280.3437457.8227.06810.386354.589341158382584380581201155087705.111927302.320.225.774.505.664.467.471.7615.5168.4015.6913.1331.0828.8912.51375.80636.5806004870.5466311413.585179.06668.6549.34329.067.5568.639.5122.4268.7580824.3685315.784328.942628.491556.780936.1315.411762.7880.7951458.8127.93800.3861358.695227159582686724783896256271716.711929384.916.184.903.814.333.835.891.5712.8264.9214.5512.0525.2823.9212.94368.20336.6952674845.7642821388.349175.64568.0969.22629.0813.8280.1416.8543.8974.6755626.1389016.819941.129741.778682.933741.6217.522613.23112.972593.8852.48270.715702.212622204210601084965105982465819712.515526059.718.015.024.094.433.856.421.413.9059.4713.8611.929.1725.6710.90223.2538.9261317.316016969.247123.13654.4737.52124.2717.6281.6421.4644.4674.4257326.0543618.559944.461445.975482.842041.5117.482613.33113.671593.9153.11010.715711.402495206110611110929107611764289425.515377731.116.144.673.763.783.675.851.3912.6456.7412.8411.2524.6323.2811.09222.9429.0161307.693799959.889121.99554.1897.47223.42OpenBenchmarking.org

CPU Power Consumption Monitor

OpenBenchmarking.orgWattsCPU Power Consumption MonitorPhoronix Test Suite System MonitoringCore i9 11900KCore i5 10600KCore i9 10900K4080120160200Min: 10.16 / Avg: 41.63 / Max: 229.07Min: 0.65 / Avg: 24.26 / Max: 56.19Min: 0.71 / Avg: 14.3 / Max: 46.03

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: OpenCLCore i5 10600KCore i9 10900KCore i5 11600KCore i9 11900K48121620SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 37.537.5513.8217.62

Basemark GPU

OpenBenchmarking.orgFPS Per Watt, More Is BetterBasemark GPU 1.2Renderer: Vulkan - Resolution: 1920 x 1080 - Graphics Preset: MediumCore i5 11600KCore i9 11900KCore i5 10600KCore i9 10900K1.02832.05663.08494.11325.14153.974.174.224.57

OpenBenchmarking.orgFPS, More Is BetterBasemark GPU 1.2Renderer: Vulkan - Resolution: 1920 x 1080 - Graphics Preset: MediumCore i5 10600KCore i9 10900KCore i5 11600KCore i9 11900K20406080100SE +/- 0.08, N = 3SE +/- 0.08, N = 3SE +/- 0.08, N = 3SE +/- 0.13, N = 366.6768.6380.1481.64MIN: 34.31 / MAX: 148.53MIN: 34.64 / MAX: 154.93MIN: 41.37 / MAX: 145.25MIN: 38.28 / MAX: 148

PlaidML

OpenBenchmarking.orgFPS Per Watt, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: VGG16 - Device: OpenCLCore i5 11600KCore i9 11900KCore i5 10600KCore i9 10900K0.04280.08560.12840.17120.2140.110.110.190.19

OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: VGG16 - Device: OpenCLCore i5 10600KCore i9 10900KCore i5 11600KCore i9 11900K510152025SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.04, N = 39.499.5116.8521.46

ParaView

This test runs ParaView benchmarks: an open-source data analytics and visualization application. Paraview describes itself as "an open-source, multi-platform data analysis and visualization application. ParaView users can quickly build visualizations to analyze their data using qualitative and quantitative techniques." Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames / Sec, More Is BetterParaView 5.9Test: Wavelet Volume - Resolution: 1920 x 1080Core i5 10600KCore i9 10900KCore i5 11600KCore i9 11900K1020304050SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.09, N = 322.1622.4243.8944.46

Tesseract

OpenBenchmarking.orgFrames Per Second Per Watt, More Is BetterTesseract 2014-05-12Resolution: 3840 x 2160Core i5 11600KCore i9 11900KCore i5 10600KCore i9 10900K0.32850.6570.98551.3141.64251.211.261.391.46

OpenBenchmarking.orgFrames Per Second, More Is BetterTesseract 2014-05-12Resolution: 1920 x 1080Core i5 10600KCore i9 10900KCore i9 11900KCore i5 11600K20406080100SE +/- 0.19, N = 3SE +/- 0.06, N = 3SE +/- 0.51, N = 3SE +/- 0.58, N = 367.2168.7674.4374.68

OpenBenchmarking.orgFrames Per Second, More Is BetterTesseract 2014-05-12Resolution: 3840 x 2160Core i5 10600KCore i9 10900KCore i9 11900KCore i5 11600K612182430SE +/- 0.05, N = 3SE +/- 0.02, N = 3SE +/- 0.06, N = 3SE +/- 0.06, N = 324.1924.3726.0526.14

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: TriadCore i5 10600KCore i9 10900KCore i5 11600KCore i9 11900K510152025SE +/- 0.06, N = 11SE +/- 0.03, N = 11SE +/- 0.03, N = 11SE +/- 0.02, N = 1113.2715.7816.8218.561. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -lmpi_cxx -lmpi

OpenBenchmarking.orgGB/s Per Watt, More Is BetterSHOC Scalable HeterOgeneous Computing 2015-11-10Target: OpenCL - Benchmark: Bus Speed DownloadCore i5 11600KCore i9 11900KCore i5 10600KCore i9 10900K0.73581.47162.20742.94323.6792.592.873.083.27

OpenBenchmarking.orgGB/s Per Watt, More Is BetterSHOC Scalable HeterOgeneous Computing 2015-11-10Target: OpenCL - Benchmark: Bus Speed ReadbackCore i5 11600KCore i9 11900KCore i5 10600KCore i9 10900K0.68851.3772.06552.7543.44252.562.892.933.06

OpenBenchmarking.orgGB/s Per Watt, More Is BetterSHOC Scalable HeterOgeneous Computing 2015-11-10Target: OpenCL - Benchmark: Texture Read BandwidthCore i5 11600KCore i9 11900KCore i5 10600KCore i9 10900K0.76281.52562.28843.05123.8142.292.413.283.39

OpenBenchmarking.orgGB/s, More Is BetterSHOC Scalable HeterOgeneous Computing 2015-11-10Target: OpenCL - Benchmark: Bus Speed DownloadCore i5 10600KCore i9 10900KCore i5 11600KCore i9 11900K1020304050SE +/- 0.01, N = 13SE +/- 0.07, N = 13SE +/- 0.30, N = 15SE +/- 0.10, N = 1326.3628.9441.1344.461. (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 ReadbackCore i5 10600KCore i9 10900KCore i5 11600KCore i9 11900K1020304050SE +/- 0.11, N = 15SE +/- 0.23, N = 15SE +/- 0.74, N = 15SE +/- 0.08, N = 1326.2828.4941.7845.981. (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: Texture Read BandwidthCore i5 10600KCore i9 10900KCore i9 11900KCore i5 11600K20406080100SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.03, N = 3SE +/- 0.01, N = 356.7756.7882.8482.931. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -lmpi_cxx -lmpi

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 BandwidthCore i5 10600KCore i9 10900KCore i9 11900KCore i5 11600K918273645SE +/- 0.03, N = 3SE +/- 0.14, N = 3SE +/- 0.08, N = 3SE +/- 0.03, N = 335.9636.1341.5141.621. (CXX) g++ options: -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGBPS, More Is BetterclpeakOpenCL Test: Transfer Bandwidth enqueueReadBufferCore i9 10900KCore i5 10600KCore i9 11900KCore i5 11600K48121620SE +/- 0.06, N = 6SE +/- 0.05, N = 6SE +/- 0.01, N = 6SE +/- 0.02, N = 615.4115.7217.4817.521. (CXX) g++ options: -O3 -rdynamic -lOpenCL

SHOC Scalable HeterOgeneous Computing

OpenBenchmarking.orgGFLOPS Per Watt, More Is BetterSHOC Scalable HeterOgeneous Computing 2015-11-10Target: OpenCL - Benchmark: FFT SPCore i5 10600KCore i9 10900KCore i5 11600KCore i9 11900K2468103.713.726.306.64

OpenBenchmarking.orgGFLOPS, More Is BetterSHOC Scalable HeterOgeneous Computing 2015-11-10Target: OpenCL - Benchmark: Max SP FlopsCore i5 10600KCore i9 10900KCore i5 11600KCore i9 11900K6001200180024003000SE +/- 0.15, N = 3SE +/- 0.30, N = 3SE +/- 0.00, N = 3SE +/- 0.03, N = 31762.421762.782613.232613.331. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -lmpi_cxx -lmpi

clpeak

OpenBenchmarking.orgGFLOPS Per Watt, More Is BetterclpeakOpenCL Test: Single-Precision FloatCore i9 10900KCore i5 10600KCore i5 11600KCore i9 11900K51015202518.0918.1919.7420.44

ViennaCL

OpenBenchmarking.orgGFLOPS Per Watt, More Is BetterViennaCL 1.4.2OpenCL LU FactorizationCore i5 10600KCore i9 10900KCore i5 11600KCore i9 11900K0.64351.2871.93052.5743.21751.861.962.682.86

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 SPCore i5 10600KCore i9 10900KCore i5 11600KCore i9 11900K306090120150SE +/- 0.04, N = 6SE +/- 0.07, N = 7SE +/- 0.06, N = 12SE +/- 0.05, N = 1280.3480.80112.97113.671. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -lmpi_cxx -lmpi

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 FloatCore i5 10600KCore i9 10900KCore i5 11600KCore i9 11900K130260390520650SE +/- 0.28, N = 4SE +/- 0.04, N = 4SE +/- 0.00, N = 3SE +/- 0.01, N = 3457.82458.81593.88593.911. (CXX) g++ options: -O3 -rdynamic -lOpenCL

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 FactorizationCore i5 10600KCore i9 10900KCore i5 11600KCore i9 11900K1224364860SE +/- 0.03, N = 10SE +/- 0.01, N = 10SE +/- 0.07, N = 11SE +/- 0.04, N = 1127.0727.9452.4853.111. (CXX) g++ options: -rdynamic -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.orgGHash/s, More Is BetterSHOC Scalable HeterOgeneous Computing 2015-11-10Target: OpenCL - Benchmark: MD5 HashCore i5 10600KCore i9 10900KCore i5 11600KCore i9 11900K0.16090.32180.48270.64360.8045SE +/- 0.0000, N = 3SE +/- 0.0000, N = 3SE +/- 0.0000, N = 3SE +/- 0.0000, N = 30.38600.38610.71500.71501. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -lmpi_cxx -lmpi

ParaView

This test runs ParaView benchmarks: an open-source data analytics and visualization application. Paraview describes itself as "an open-source, multi-platform data analysis and visualization application. ParaView users can quickly build visualizations to analyze their data using qualitative and quantitative techniques." Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMiVoxels / Sec, More Is BetterParaView 5.9Test: Wavelet Volume - Resolution: 1920 x 1080Core i5 10600KCore i9 10900KCore i5 11600KCore i9 11900K150300450600750SE +/- 0.19, N = 3SE +/- 0.25, N = 3SE +/- 0.20, N = 3SE +/- 1.41, N = 3354.59358.70702.21711.40

LeelaChessZero

OpenBenchmarking.orgNodes Per Second Per Watt, More Is BetterLeelaChessZero 0.26Backend: OpenCLCore i9 10900KCore i5 10600KCore i9 11900KCore i5 11600K481216205.748.4411.7114.16

OpenBenchmarking.orgNodes Per Second, More Is BetterLeelaChessZero 0.26Backend: OpenCLCore i9 10900KCore i5 10600KCore i9 11900KCore i5 11600K130260390520650SE +/- 2.33, N = 3SE +/- 3.71, N = 3SE +/- 5.53, N = 4SE +/- 4.51, N = 32273414956221. (CXX) g++ options: -flto -pthread

GpuTest

OpenBenchmarking.orgPoints Per Watt, More Is BetterGpuTest 0.7.0Test: TessMark - Resolution: 1920 x 1080 - Mode: FullscreenCore i5 10600KCore i9 10900KCore i5 11600KCore i9 11900K2040608010082.0985.4292.4895.96

OpenBenchmarking.orgPoints Per Watt, More Is BetterGpuTest 0.7.0Test: GiMark - Resolution: 1920 x 1080 - Mode: FullscreenCore i5 10600KCore i5 11600KCore i9 10900KCore i9 11900K112233445545.8248.7548.9050.34

OpenBenchmarking.orgPoints Per Watt, More Is BetterGpuTest 0.7.0Test: Triangle - Resolution: 1920 x 1080 - Mode: FullscreenCore i9 11900KCore i5 11600KCore i5 10600KCore i9 10900K5K10K15K20K25K24062.8424178.9524357.9424530.38

OpenBenchmarking.orgPoints Per Watt, More Is BetterGpuTest 0.7.0Test: Plot3D - Resolution: 1920 x 1080 - Mode: FullscreenCore i9 10900KCore i5 10600KCore i5 11600KCore i9 11900K5K10K15K20K25K23448.3823448.8723921.8923963.12

OpenBenchmarking.orgPoints, More Is BetterGpuTest 0.7.0Test: TessMark - Resolution: 1920 x 1080 - Mode: FullscreenCore i5 10600KCore i9 10900KCore i5 11600KCore i9 11900K400800120016002000SE +/- 0.33, N = 3SE +/- 1.00, N = 31583159520422061

OpenBenchmarking.orgPoints, More Is BetterGpuTest 0.7.0Test: GiMark - Resolution: 1920 x 1080 - Mode: FullscreenCore i5 10600KCore i9 10900KCore i5 11600KCore i9 11900K2004006008001000SE +/- 0.33, N = 382582610601061

OpenBenchmarking.orgPoints, More Is BetterGpuTest 0.7.0Test: Triangle - Resolution: 1920 x 1080 - Mode: FullscreenCore i5 10600KCore i9 10900KCore i5 11600KCore i9 11900K200K400K600K800K1000KSE +/- 2213.55, N = 3SE +/- 1718.00, N = 3SE +/- 4298.32, N = 3SE +/- 2363.25, N = 384380586724710849651110929

OpenBenchmarking.orgPoints, More Is BetterGpuTest 0.7.0Test: Plot3D - Resolution: 1920 x 1080 - Mode: FullscreenCore i5 10600KCore i9 10900KCore i5 11600KCore i9 11900K200K400K600K800K1000KSE +/- 1476.15, N = 3SE +/- 3908.37, N = 3SE +/- 4354.08, N = 3SE +/- 4064.55, N = 381201183896210598241076117

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: GPUCore i5 10600KCore i9 10900KCore i9 11900KCore i5 11600K14M28M42M56M70MSE +/- 729961.08, N = 3SE +/- 564264.90, N = 3SE +/- 825108.54, N = 3SE +/- 53910.03, N = 355087705.156271716.764289425.565819712.51. (CC) gcc options: -O3 -march=native -ftree-vectorize -funroll-loops -lglut -lOpenCL -lGL -lm

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: GPUCore i5 10600KCore i9 10900KCore i9 11900KCore i5 11600K3M6M9M12M15MSE +/- 2138.82, N = 3SE +/- 1044.15, N = 3SE +/- 540.65, N = 3SE +/- 730.66, N = 311927302.311929384.915377731.115526059.71. (CC) gcc options: -O3 -lm -ftree-vectorize -funroll-loops -lglut -lOpenCL -lGL

NCNN

MinAvgMaxCore i9 11900K29.052.163.0Core i5 11600K30.048.558.0OpenBenchmarking.orgCelsius, Fewer Is BetterNCNN 20201218CPU Temperature Monitor20406080100

RealSR-NCNN

OpenBenchmarking.orgCelsius, Fewer Is BetterRealSR-NCNN 20200818CPU Temperature MonitorCore i5 11600KCore i9 11900K918273645Min: 28 / Avg: 32.63 / Max: 45Min: 26 / Avg: 30.79 / Max: 43

MinAvgMaxCore i5 11600K29.032.844.0Core i9 11900K28.031.542.0OpenBenchmarking.orgCelsius, Fewer Is BetterRealSR-NCNN 20200818CPU Temperature Monitor1224364860

Waifu2x-NCNN Vulkan

MinAvgMaxCore i5 11600K28.032.041.0Core i9 11900K28.030.732.0OpenBenchmarking.orgCelsius, Fewer Is BetterWaifu2x-NCNN Vulkan 20200818CPU Temperature Monitor1122334455

MinAvgMaxCore i5 11600K28.031.143.0Core i9 11900K27.030.643.0OpenBenchmarking.orgCelsius, Fewer Is BetterWaifu2x-NCNN Vulkan 20200818CPU Temperature Monitor1224364860

VkResample

MinAvgMaxCore i5 11600K29.034.245.0Core i9 11900K28.032.342.0OpenBenchmarking.orgCelsius, Fewer Is BetterVkResample 1.0CPU Temperature Monitor1224364860

FinanceBench

MinAvgMaxCore i5 11600K28.030.545.0Core i9 11900K28.029.639.0OpenBenchmarking.orgCelsius, Fewer Is BetterFinanceBench 2016-07-25CPU Temperature Monitor1224364860

MinAvgMaxCore i5 11600K28.039.946.0Core i9 11900K27.036.743.0OpenBenchmarking.orgCelsius, Fewer Is BetterFinanceBench 2016-07-25CPU Temperature Monitor1224364860

clpeak

MinAvgMaxCore i5 11600K29.034.945.0Core i9 11900K27.031.940.0OpenBenchmarking.orgCelsius, Fewer Is BetterclpeakCPU Temperature Monitor1224364860

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 20201218Target: Vulkan GPU - Model: mobilenetCore i5 10600KCore i5 11600KCore i9 10900KCore i9 11900K510152025SE +/- 0.01, N = 3SE +/- 0.04, N = 3SE +/- 0.04, N = 3SE +/- 0.13, N = 820.2218.0116.1816.14MIN: 20.06 / MAX: 27.72MIN: 17.59 / MAX: 18.64MIN: 15.74 / MAX: 17.45MIN: 15.48 / MAX: 21.11. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2Core i5 10600KCore i5 11600KCore i9 10900KCore i9 11900K1.29832.59663.89495.19326.4915SE +/- 0.02, N = 3SE +/- 0.00, N = 3SE +/- 0.03, N = 3SE +/- 0.10, N = 85.775.024.904.67MIN: 5.53 / MAX: 8.53MIN: 4.81 / MAX: 6.54MIN: 4.73 / MAX: 5.76MIN: 4.26 / MAX: 5.961. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3Core i5 10600KCore i5 11600KCore i9 10900KCore i9 11900K1.01252.0253.03754.055.0625SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.06, N = 84.504.093.813.76MIN: 4.43 / MAX: 5.45MIN: 3.98 / MAX: 5.01MIN: 3.74 / MAX: 4.75MIN: 3.43 / MAX: 4.471. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU - Model: shufflenet-v2Core i5 10600KCore i5 11600KCore i9 10900KCore i9 11900K1.27352.5473.82055.0946.3675SE +/- 0.02, N = 3SE +/- 0.00, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 85.664.434.333.78MIN: 5.6 / MAX: 6.6MIN: 4.34 / MAX: 5.45MIN: 4.27 / MAX: 5.11MIN: 3.67 / MAX: 4.841. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU - Model: mnasnetCore i5 10600KCore i5 11600KCore i9 10900KCore i9 11900K1.00352.0073.01054.0145.0175SE +/- 0.03, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.08, N = 84.463.853.833.67MIN: 4.38 / MAX: 5.53MIN: 3.74 / MAX: 5.02MIN: 3.78 / MAX: 10.74MIN: 3.36 / MAX: 4.851. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU - Model: efficientnet-b0Core i5 10600KCore i5 11600KCore i9 10900KCore i9 11900K246810SE +/- 0.04, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.08, N = 87.476.425.895.85MIN: 7.37 / MAX: 8.32MIN: 6.27 / MAX: 7.37MIN: 5.83 / MAX: 6.72MIN: 5.5 / MAX: 7.131. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU - Model: blazefaceCore i5 10600KCore i9 10900KCore i5 11600KCore i9 11900K0.3960.7921.1881.5841.98SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.03, N = 81.761.571.401.39MIN: 1.72 / MAX: 2.02MIN: 1.56 / MAX: 1.67MIN: 1.36 / MAX: 1.76MIN: 1.26 / MAX: 1.81. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU - Model: googlenetCore i5 10600KCore i5 11600KCore i9 10900KCore i9 11900K48121620SE +/- 0.03, N = 3SE +/- 0.01, N = 3SE +/- 0.07, N = 3SE +/- 0.23, N = 815.5113.9012.8212.64MIN: 15.41 / MAX: 15.73MIN: 13.71 / MAX: 14.89MIN: 12.48 / MAX: 13.1MIN: 11.69 / MAX: 13.71. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU - Model: vgg16Core i5 10600KCore i9 10900KCore i5 11600KCore i9 11900K1530456075SE +/- 0.10, N = 3SE +/- 0.16, N = 3SE +/- 0.07, N = 3SE +/- 0.08, N = 868.4064.9259.4756.74MIN: 67.98 / MAX: 70.38MIN: 64.37 / MAX: 65.6MIN: 58.99 / MAX: 66.61MIN: 56.02 / MAX: 58.061. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU - Model: resnet18Core i5 10600KCore i9 10900KCore i5 11600KCore i9 11900K48121620SE +/- 0.03, N = 3SE +/- 0.10, N = 3SE +/- 0.03, N = 3SE +/- 0.12, N = 815.6914.5513.8612.84MIN: 15.5 / MAX: 16.02MIN: 14.17 / MAX: 17.09MIN: 13.63 / MAX: 21.03MIN: 11.84 / MAX: 13.411. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU - Model: alexnetCore i5 10600KCore i9 10900KCore i5 11600KCore i9 11900K3691215SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.06, N = 813.1312.0511.9011.25MIN: 12.98 / MAX: 13.35MIN: 11.9 / MAX: 12.46MIN: 11.74 / MAX: 12.33MIN: 11 / MAX: 12.391. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU - Model: resnet50Core i5 10600KCore i5 11600KCore i9 10900KCore i9 11900K714212835SE +/- 0.04, N = 3SE +/- 0.04, N = 3SE +/- 0.13, N = 3SE +/- 0.02, N = 831.0829.1725.2824.63MIN: 30.74 / MAX: 31.77MIN: 28.81 / MAX: 29.96MIN: 24.66 / MAX: 25.79MIN: 24.23 / MAX: 25.31. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU - Model: yolov4-tinyCore i5 10600KCore i5 11600KCore i9 10900KCore i9 11900K714212835SE +/- 0.02, N = 3SE +/- 0.18, N = 3SE +/- 0.30, N = 3SE +/- 0.12, N = 828.8925.6723.9223.28MIN: 28.77 / MAX: 29.42MIN: 25.07 / MAX: 26.41MIN: 23.28 / MAX: 31.1MIN: 22.54 / MAX: 25.271. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20201218Target: Vulkan GPU - Model: regnety_400mCore i9 10900KCore i5 10600KCore i9 11900KCore i5 11600K3691215SE +/- 0.08, N = 3SE +/- 0.06, N = 3SE +/- 0.04, N = 8SE +/- 0.04, N = 312.9412.5111.0910.90MIN: 12.73 / MAX: 13.89MIN: 12.35 / MAX: 20.33MIN: 10.78 / MAX: 12.21MIN: 10.67 / MAX: 12.871. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

VkResample

VkResample is a Vulkan-based image upscaling library based on VkFFT. The sample input file is upscaling a 4K image to 8K using Vulkan-based GPU acceleration. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterVkResample 1.0Upscale: 2x - Precision: SingleCore i5 10600KCore i9 10900KCore i5 11600KCore i9 11900K80160240320400SE +/- 0.19, N = 3SE +/- 0.15, N = 3SE +/- 0.05, N = 3SE +/- 0.08, N = 3375.81368.20223.25222.941. (CXX) g++ options: -O3 -pthread

FinanceBench

FinanceBench is a collection of financial program benchmarks with support for benchmarking on the GPU via OpenCL and CPU benchmarking with OpenMP. The FinanceBench test cases are focused on Black-Sholes-Merton Process with Analytic European Option engine, QMC (Sobol) Monte-Carlo method (Equity Option Example), Bonds Fixed-rate bond with flat forward curve, and Repo Securities repurchase agreement. FinanceBench was originally written by the Cavazos Lab at University of Delaware. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterFinanceBench 2016-07-25Benchmark: Black-Scholes OpenCLCore i9 10900KCore i5 10600KCore i9 11900KCore i5 11600K816243240SE +/- 0.142549, N = 15SE +/- 0.106999, N = 15SE +/- 0.009309, N = 13SE +/- 0.011899, N = 1336.69526736.5806009.0160008.9260001. (CXX) g++ options: -O3 -march=native -fopenmp

OpenBenchmarking.orgms, Fewer Is BetterFinanceBench 2016-07-25Benchmark: Monte-Carlo OpenCLCore i5 10600KCore i9 10900KCore i5 11600KCore i9 11900K10002000300040005000SE +/- 7.58, N = 4SE +/- 10.19, N = 4SE +/- 0.57, N = 5SE +/- 0.16, N = 54870.554845.761317.321307.691. (CXX) g++ options: -O3 -march=native -fopenmp

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: YesCore i5 10600KCore i9 10900KCore i5 11600KCore i9 11900K30060090012001500SE +/- 0.22, N = 3SE +/- 2.33, N = 3SE +/- 0.27, N = 3SE +/- 0.23, N = 31413.591388.35969.25959.89

OpenBenchmarking.orgSeconds, Fewer Is BetterRealSR-NCNN 20200818Scale: 4x - TAA: NoCore i5 10600KCore i9 10900KCore i5 11600KCore i9 11900K4080120160200SE +/- 0.00, N = 3SE +/- 0.05, N = 3SE +/- 0.06, N = 3SE +/- 0.07, N = 3179.07175.65123.14122.00

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: YesCore i5 10600KCore i9 10900KCore i5 11600KCore i9 11900K1530456075SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.04, N = 3SE +/- 0.02, N = 368.6568.1054.4754.19

OpenBenchmarking.orgSeconds, Fewer Is BetterWaifu2x-NCNN Vulkan 20200818Scale: 2x - Denoise: 3 - TAA: NoCore i5 10600KCore i9 10900KCore i5 11600KCore i9 11900K3691215SE +/- 0.005, N = 5SE +/- 0.006, N = 5SE +/- 0.009, N = 6SE +/- 0.015, N = 69.3439.2267.5217.472

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 LatencyCore i9 10900KCore i5 10600KCore i5 11600KCore i9 11900K714212835SE +/- 0.04, N = 9SE +/- 0.06, N = 8SE +/- 0.12, N = 9SE +/- 0.04, N = 1029.0829.0624.2723.421. (CXX) g++ options: -O3 -rdynamic -lOpenCL

71 Results Shown

CPU Power Consumption Monitor
PlaidML
Basemark GPU
Basemark GPU
PlaidML
PlaidML
ParaView
Tesseract
Tesseract:
  1920 x 1080
  3840 x 2160
SHOC Scalable HeterOgeneous Computing
SHOC Scalable HeterOgeneous Computing:
  OpenCL - Bus Speed Download
  OpenCL - Bus Speed Readback
  OpenCL - Texture Read Bandwidth
SHOC Scalable HeterOgeneous Computing:
  OpenCL - Bus Speed Download
  OpenCL - Bus Speed Readback
  OpenCL - Texture Read Bandwidth
clpeak:
  Global Memory Bandwidth
  Transfer Bandwidth enqueueReadBuffer
SHOC Scalable HeterOgeneous Computing
SHOC Scalable HeterOgeneous Computing
clpeak:
  Single-Precision Float
  OpenCL LU Factorization
SHOC Scalable HeterOgeneous Computing
clpeak
ViennaCL
SHOC Scalable HeterOgeneous Computing
ParaView
LeelaChessZero
LeelaChessZero
GpuTest:
  TessMark - 1920 x 1080 - Fullscreen
  GiMark - 1920 x 1080 - Fullscreen
  Triangle - 1920 x 1080 - Fullscreen
  Plot3D - 1920 x 1080 - Fullscreen
GpuTest:
  TessMark - 1920 x 1080 - Fullscreen
  GiMark - 1920 x 1080 - Fullscreen
  Triangle - 1920 x 1080 - Fullscreen
  Plot3D - 1920 x 1080 - Fullscreen
JuliaGPU
MandelGPU
NCNN:
  CPU Temp Monitor:
    Celsius
    Celsius
    Celsius
    Celsius
    Celsius
    Celsius
    Celsius
    Celsius
    Celsius
NCNN:
  Vulkan GPU - mobilenet
  Vulkan GPU-v2-v2 - mobilenet-v2
  Vulkan GPU-v3-v3 - mobilenet-v3
  Vulkan GPU - shufflenet-v2
  Vulkan GPU - mnasnet
  Vulkan GPU - efficientnet-b0
  Vulkan GPU - blazeface
  Vulkan GPU - googlenet
  Vulkan GPU - vgg16
  Vulkan GPU - resnet18
  Vulkan GPU - alexnet
  Vulkan GPU - resnet50
  Vulkan GPU - yolov4-tiny
  Vulkan GPU - regnety_400m
VkResample
FinanceBench:
  Black-Scholes OpenCL
  Monte-Carlo OpenCL
RealSR-NCNN:
  4x - Yes
  4x - No
Waifu2x-NCNN Vulkan:
  2x - 3 - Yes
  2x - 3 - No
clpeak