icelake 2023

Tests for a future article. Intel Core i7-1065G7 testing with a Dell 06CDVY (1.0.9 BIOS) and Intel Iris Plus ICL GT2 16GB on Ubuntu 23.04 via the Phoronix Test Suite.

Compare your own system(s) to this result file with the Phoronix Test Suite by running the command: phoronix-test-suite benchmark 2310252-NE-ICELAKE2057
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

Limit displaying results to tests within:

AV1 3 Tests
C/C++ Compiler Tests 2 Tests
CPU Massive 3 Tests
Creator Workloads 6 Tests
Encoding 3 Tests
HPC - High Performance Computing 3 Tests
Machine Learning 2 Tests
Multi-Core 6 Tests
Intel oneAPI 3 Tests
Server CPU Tests 3 Tests
Video Encoding 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

Multi-Way Comparison

Condense Multi-Option Tests 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
a
October 24 2023
  5 Hours, 52 Minutes
b
October 24 2023
  5 Hours, 43 Minutes
Invert Hiding All Results Option
  5 Hours, 48 Minutes
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):


icelake 2023OpenBenchmarking.orgPhoronix Test SuiteIntel Core i7-1065G7 @ 3.90GHz (4 Cores / 8 Threads)Dell 06CDVY (1.0.9 BIOS)Intel Ice Lake-LP DRAM16GBToshiba KBG40ZPZ512G NVMe 512GBIntel Iris Plus ICL GT2 16GB (1100MHz)Realtek ALC289Intel Ice Lake-LP PCH CNVi WiFiUbuntu 23.046.2.0-24-generic (x86_64)GNOME Shell 44.0X Server + Wayland4.6 Mesa 23.0.4-0ubuntu1~23.04.1OpenCL 3.0GCC 12.3.0ext41920x1200ProcessorMotherboardChipsetMemoryDiskGraphicsAudioNetworkOSKernelDesktopDisplay ServerOpenGLOpenCLCompilerFile-SystemScreen ResolutionIcelake 2023 BenchmarksSystem Logs- Transparent Huge Pages: madvise- --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,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-defaulted --enable-offload-targets=nvptx-none=/build/gcc-12-DAPbBt/gcc-12-12.3.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-12-DAPbBt/gcc-12-12.3.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-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 (EPP: balance_performance) - CPU Microcode: 0xb8 - Thermald 2.5.2 - itlb_multihit: KVM: Mitigation of VMX disabled + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Mitigation of Clear buffers; SMT vulnerable + retbleed: Mitigation of Enhanced IBRS + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced IBRS IBPB: conditional RSB filling PBRSB-eIBRS: SW sequence + srbds: Mitigation of Microcode + tsx_async_abort: Not affected

a vs. b ComparisonPhoronix Test SuiteBaseline+16.5%+16.5%+33%+33%+49.5%+49.5%65.8%58.6%45.6%45%25.2%25%24.8%22.2%16.5%14.6%12.7%12.5%12.1%11.9%11.1%11.1%11.1%11%10.9%10.8%10.8%10.4%9.9%9.7%9.6%9.6%9.6%9.5%9.3%9.3%8.5%8.4%8.3%8.3%8.3%7.9%7.7%7.5%7.2%7.2%6.9%6.6%6.6%6.6%6.3%6.3%6.3%5.9%5.8%5.8%5.8%5.5%5.2%5.2%5%5%5%4.8%4.1%3.1%3%2.7%2.4%D.B.s - f32 - CPUCPU - shufflenet-v2Vulkan GPU - mnasnetCPU - mnasnetIP Shapes 3D - u8s8f32 - CPURTLightmap.hdr.4096x4096 - CPU-OnlyIP Shapes 1D - f32 - CPUIP Shapes 1D - u8s8f32 - CPUVulkan GPU - FastestDetC.B.S.A - u8s8f32 - CPUPreset 12 - Bosphorus 4KIP Shapes 3D - f32 - CPUPreset 8 - Bosphorus 1080pD.B.s - u8s8f32 - CPURT.hdr_alb_nrm.3840x2160 - CPU-OnlyRT.ldr_alb_nrm.3840x2160 - CPU-OnlyR.N.N.T - bf16bf16bf16 - CPUR.N.N.I - u8s8f32 - CPUR.N.N.T - f32 - CPUR.N.N.I - bf16bf16bf16 - CPUVulkan GPU - resnet18R.N.N.I - f32 - CPUCPU - resnet18Preset 8 - Bosphorus 4KPreset 4 - Bosphorus 1080pWide Vector MathCloningCPU - blazeface10, Lossless6Vulkan GPU - alexnetCPU - resnet50Vulkan GPU - blazeface6, LosslessPreset 13 - Bosphorus 4K2Vulkan GPU - vgg16CPU - vgg16CPU - alexnetVector ShuffleCPU - googlenetVulkan GPU - vision_transformerVulkan GPU - googlenetVulkan GPU - efficientnet-b0CPU - regnety_400mVulkan GPU - resnet50Vulkan GPU - squeezenet_ssdR.N.N.T - u8s8f32 - CPUVulkan GPU - mobilenetPreset 4 - Bosphorus 4KVulkan GPU - regnety_400mCPU - mobilenetCPU - yolov4-tinyVulkan GPU - yolov4-tinyCPU - squeezenet_ssdCPU - vision_transformerCPU - efficientnet-b0Pathtracer ISPC - Asian DragonB.S.o.W3.5%Pathtracer ISPC - Asian Dragon ObjPathtracer - CrownVulkan GPU - shufflenet-v23%Vulkan GPU-v2-v2 - mobilenet-v22.8%FP32-FP32Speed 10 Realtime - Bosphorus 4KCPU-v2-v2 - mobilenet-v22.1%oneDNNNCNNNCNNNCNNoneDNNIntel Open Image DenoiseoneDNNoneDNNNCNNoneDNNSVT-AV1oneDNNSVT-AV1oneDNNIntel Open Image DenoiseIntel Open Image DenoiseoneDNNoneDNNoneDNNoneDNNNCNNoneDNNNCNNSVT-AV1SVT-AV1Stress-NGStress-NGNCNNlibavif avifenclibavif avifencNCNNNCNNNCNNlibavif avifencSVT-AV1libavif avifencNCNNlibavif avifencNCNNNCNNStress-NGNCNNNCNNNCNNNCNNNCNNNCNNNCNNoneDNNNCNNSVT-AV1NCNNNCNNNCNNNCNNNCNNNCNNNCNNEmbreeOpenRadiossEmbreeEmbreeNCNNNCNNFluidX3DAOM AV1NCNNab

icelake 2023fluidx3d: FP32-FP32fluidx3d: FP32-FP16Cfluidx3d: FP32-FP16Squantlib: Multi-Threadedquantlib: Single-Threadedopenradioss: Bumper Beamopenradioss: Chrysler Neon 1Mopenradioss: Cell Phone Drop Testopenradioss: Bird Strike on Windshieldopenradioss: Rubber O-Ring Seal Installationopenradioss: INIVOL and Fluid Structure Interaction Drop Containereasywave: e2Asean Grid + BengkuluSept2007 Source - 240easywave: e2Asean Grid + BengkuluSept2007 Source - 1200easywave: e2Asean Grid + BengkuluSept2007 Source - 2400aom-av1: Speed 9 Realtime - Bosphorus 4Kaom-av1: Speed 10 Realtime - Bosphorus 4Kaom-av1: Speed 11 Realtime - Bosphorus 4Kaom-av1: Speed 9 Realtime - Bosphorus 1080paom-av1: Speed 10 Realtime - Bosphorus 1080paom-av1: Speed 11 Realtime - Bosphorus 1080pembree: Pathtracer - Crownembree: Pathtracer ISPC - Crownembree: Pathtracer - Asian Dragonembree: Pathtracer - Asian Dragon Objembree: Pathtracer ISPC - Asian Dragonembree: Pathtracer ISPC - Asian Dragon Objsvt-av1: Preset 4 - Bosphorus 4Ksvt-av1: Preset 8 - Bosphorus 4Ksvt-av1: Preset 12 - Bosphorus 4Ksvt-av1: Preset 13 - Bosphorus 4Ksvt-av1: Preset 4 - Bosphorus 1080psvt-av1: Preset 8 - Bosphorus 1080psvt-av1: Preset 12 - Bosphorus 1080psvt-av1: Preset 13 - Bosphorus 1080poidn: RT.hdr_alb_nrm.3840x2160 - CPU-Onlyoidn: RT.ldr_alb_nrm.3840x2160 - CPU-Onlyoidn: RTLightmap.hdr.4096x4096 - CPU-Onlyavifenc: 0avifenc: 2avifenc: 6avifenc: 6, Losslessavifenc: 10, Losslessonednn: IP Shapes 1D - f32 - CPUonednn: IP Shapes 3D - f32 - CPUonednn: IP Shapes 1D - u8s8f32 - CPUonednn: IP Shapes 3D - u8s8f32 - CPUonednn: Convolution Batch Shapes Auto - f32 - CPUonednn: Deconvolution Batch shapes_1d - f32 - CPUonednn: Deconvolution Batch shapes_3d - f32 - CPUonednn: Convolution Batch Shapes Auto - u8s8f32 - CPUonednn: Deconvolution Batch shapes_1d - u8s8f32 - CPUonednn: Deconvolution Batch shapes_3d - u8s8f32 - CPUonednn: Recurrent Neural Network Training - f32 - CPUonednn: Recurrent Neural Network Inference - f32 - CPUonednn: Recurrent Neural Network Training - u8s8f32 - CPUonednn: Recurrent Neural Network Inference - u8s8f32 - CPUonednn: Recurrent Neural Network Training - bf16bf16bf16 - CPUonednn: Recurrent Neural Network Inference - bf16bf16bf16 - CPUstress-ng: Cloningstress-ng: Vector Shufflestress-ng: Wide Vector Mathncnn: CPU - mobilenetncnn: CPU-v2-v2 - mobilenet-v2ncnn: CPU-v3-v3 - mobilenet-v3ncnn: CPU - shufflenet-v2ncnn: CPU - mnasnetncnn: CPU - efficientnet-b0ncnn: CPU - blazefacencnn: CPU - googlenetncnn: CPU - vgg16ncnn: CPU - resnet18ncnn: CPU - alexnetncnn: CPU - resnet50ncnn: CPU - yolov4-tinyncnn: CPU - squeezenet_ssdncnn: CPU - regnety_400mncnn: CPU - vision_transformerncnn: CPU - FastestDetncnn: Vulkan GPU - mobilenetncnn: Vulkan GPU-v2-v2 - mobilenet-v2ncnn: Vulkan GPU-v3-v3 - mobilenet-v3ncnn: Vulkan GPU - shufflenet-v2ncnn: Vulkan GPU - mnasnetncnn: Vulkan GPU - efficientnet-b0ncnn: Vulkan GPU - blazefacencnn: Vulkan GPU - googlenetncnn: Vulkan GPU - vgg16ncnn: Vulkan GPU - resnet18ncnn: Vulkan GPU - alexnetncnn: Vulkan GPU - resnet50ncnn: Vulkan GPU - yolov4-tinyncnn: Vulkan GPU - squeezenet_ssdncnn: Vulkan GPU - regnety_400mncnn: Vulkan GPU - vision_transformerncnn: Vulkan GPU - FastestDetab2572105007472.82898.3512.22917.08337.47921.19693.041818.2111.91225.678560.79434.3234.3233.21146.87144.8150.752.56412.80933.26572.98283.67243.20880.7279.09527.93930.0932.72625.293191.279255.3970.090.090.04581.559257.0828.75739.91213.1413.39039.057156.001773.8117513.132821.440515.177217.7159.485118.1622214396.77400.6414373.97378.414376.47398.63641.542156.5188229.824.144.373.544.335.8310.721.1517.1870.0812.9810.334.1932.2213.8111.97267.055.1524.154.353.542.715.2410.781.1717.1970.2113.0610.3834.2832.213.8911.95268.475.642642094967336.62894.4516.662947.38338.36953.64694.011824.1311.933225.755560.99134.3735.1333.31147.01143.67150.932.64092.83573.26763.0353.82333.30910.7699.97431.48332.5822.98928.357190.598252.1580.100.100.05540.786238.24626.30936.84512.0210.73028.049144.911463.043913.130912.932515.082515.46358.474148.14912976.66701.813583.86648.2712945.56677.03702.932306.1196693.2322.944.463.542.734.0210.231.0516.1165.3611.819.6131.5530.6213.1511.26254.375.2522.834.473.482.793.610.141.0816.1365.2211.799.5732.2530.6613.1211.33251.884.84OpenBenchmarking.org

FluidX3D

FluidX3D is a speedy and memory efficient Boltzmann CFD (Computational Fluid Dynamics) software package implemented using OpenCL and intended for GPU acceleration. FluidX3D is developed by Moritz Lehmann and written free for non-commercial use. This is a test profile measuring the system OpenCL performance using the FluidX3D benchmark. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMLUPs/s, More Is BetterFluidX3D 2.9Test: FP32-FP32ab60120180240300257264

OpenBenchmarking.orgMLUPs/s, More Is BetterFluidX3D 2.9Test: FP32-FP16Cab50100150200250210209

OpenBenchmarking.orgMLUPs/s, More Is BetterFluidX3D 2.9Test: FP32-FP16Sab110220330440550500496

QuantLib

QuantLib is an open-source library/framework around quantitative finance for modeling, trading and risk management scenarios. QuantLib is written in C++ with Boost and its built-in benchmark used reports the QuantLib Benchmark Index benchmark score. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMFLOPS, More Is BetterQuantLib 1.32Configuration: Multi-Threadedab160032004800640080007472.87336.61. (CXX) g++ options: -O3 -march=native -fPIE -pie

OpenBenchmarking.orgMFLOPS, More Is BetterQuantLib 1.32Configuration: Single-Threadedab60012001800240030002898.32894.41. (CXX) g++ options: -O3 -march=native -fPIE -pie

OpenRadioss

OpenRadioss is an open-source AGPL-licensed finite element solver for dynamic event analysis OpenRadioss is based on Altair Radioss and open-sourced in 2022. This open-source finite element solver is benchmarked with various example models available from https://www.openradioss.org/models/ and https://github.com/OpenRadioss/ModelExchange/tree/main/Examples. This test is currently using a reference OpenRadioss binary build offered via GitHub. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterOpenRadioss 2023.09.15Model: Bumper Beamab110220330440550512.20516.66

OpenBenchmarking.orgSeconds, Fewer Is BetterOpenRadioss 2023.09.15Model: Chrysler Neon 1Mab60012001800240030002917.082947.38

OpenBenchmarking.orgSeconds, Fewer Is BetterOpenRadioss 2023.09.15Model: Cell Phone Drop Testab70140210280350337.47338.36

OpenBenchmarking.orgSeconds, Fewer Is BetterOpenRadioss 2023.09.15Model: Bird Strike on Windshieldab2004006008001000921.19953.64

OpenBenchmarking.orgSeconds, Fewer Is BetterOpenRadioss 2023.09.15Model: Rubber O-Ring Seal Installationab150300450600750693.04694.01

OpenBenchmarking.orgSeconds, Fewer Is BetterOpenRadioss 2023.09.15Model: INIVOL and Fluid Structure Interaction Drop Containerab4008001200160020001818.211824.13

easyWave

The easyWave software allows simulating tsunami generation and propagation in the context of early warning systems. EasyWave supports making use of OpenMP for CPU multi-threading and there are also GPU ports available but not currently incorporated as part of this test profile. The easyWave tsunami generation software is run with one of the example/reference input files for measuring the CPU execution time. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BettereasyWave r34Input: e2Asean Grid + BengkuluSept2007 Source - Time: 240ab369121511.9111.931. (CXX) g++ options: -O3 -fopenmp

OpenBenchmarking.orgSeconds, Fewer Is BettereasyWave r34Input: e2Asean Grid + BengkuluSept2007 Source - Time: 1200ab50100150200250225.68225.761. (CXX) g++ options: -O3 -fopenmp

OpenBenchmarking.orgSeconds, Fewer Is BettereasyWave r34Input: e2Asean Grid + BengkuluSept2007 Source - Time: 2400ab120240360480600560.79560.991. (CXX) g++ options: -O3 -fopenmp

AOM AV1

This is a test of the AOMedia AV1 encoder (libaom) developed by AOMedia and Google as the AV1 Codec Library. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.7Encoder Mode: Speed 9 Realtime - Input: Bosphorus 4Kab81624324034.3234.371. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.7Encoder Mode: Speed 10 Realtime - Input: Bosphorus 4Kab81624324034.3235.131. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.7Encoder Mode: Speed 11 Realtime - Input: Bosphorus 4Kab81624324033.2133.311. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.7Encoder Mode: Speed 9 Realtime - Input: Bosphorus 1080pab306090120150146.87147.011. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.7Encoder Mode: Speed 10 Realtime - Input: Bosphorus 1080pab306090120150144.80143.671. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.7Encoder Mode: Speed 11 Realtime - Input: Bosphorus 1080pab306090120150150.75150.931. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm

Embree

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 4.3Binary: Pathtracer - Model: Crownab0.59421.18841.78262.37682.9712.56412.6409MIN: 2.54 / MAX: 2.62MIN: 2.53 / MAX: 2.86

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 4.3Binary: Pathtracer ISPC - Model: Crownab0.6381.2761.9142.5523.192.80932.8357MIN: 2.78 / MAX: 2.89MIN: 2.76 / MAX: 3.16

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 4.3Binary: Pathtracer - Model: Asian Dragonab0.73521.47042.20562.94083.6763.26573.2676MIN: 3.23 / MAX: 3.33MIN: 3.2 / MAX: 3.53

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 4.3Binary: Pathtracer - Model: Asian Dragon Objab0.68291.36582.04872.73163.41452.98283.0350MIN: 2.96 / MAX: 3.03MIN: 2.95 / MAX: 3.29

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 4.3Binary: Pathtracer ISPC - Model: Asian Dragonab0.86021.72042.58063.44084.3013.67243.8233MIN: 3.64 / MAX: 3.74MIN: 3.66 / MAX: 4.13

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 4.3Binary: Pathtracer ISPC - Model: Asian Dragon Objab0.74451.4892.23352.9783.72253.20883.3091MIN: 3.18 / MAX: 3.26MIN: 3.19 / MAX: 3.62

SVT-AV1

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.7Encoder Mode: Preset 4 - Input: Bosphorus 4Kab0.1730.3460.5190.6920.8650.7270.7691. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.7Encoder Mode: Preset 8 - Input: Bosphorus 4Kab36912159.0959.9741. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.7Encoder Mode: Preset 12 - Input: Bosphorus 4Kab71421283527.9431.481. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.7Encoder Mode: Preset 13 - Input: Bosphorus 4Kab81624324030.0932.581. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.7Encoder Mode: Preset 4 - Input: Bosphorus 1080pab0.67251.3452.01752.693.36252.7262.9891. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.7Encoder Mode: Preset 8 - Input: Bosphorus 1080pab71421283525.2928.361. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.7Encoder Mode: Preset 12 - Input: Bosphorus 1080pab4080120160200191.28190.601. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.7Encoder Mode: Preset 13 - Input: Bosphorus 1080pab60120180240300255.40252.161. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

Intel Open Image Denoise

OpenBenchmarking.orgImages / Sec, More Is BetterIntel Open Image Denoise 2.1Run: RT.hdr_alb_nrm.3840x2160 - Device: CPU-Onlyab0.02250.0450.06750.090.11250.090.10

OpenBenchmarking.orgImages / Sec, More Is BetterIntel Open Image Denoise 2.1Run: RT.ldr_alb_nrm.3840x2160 - Device: CPU-Onlyab0.02250.0450.06750.090.11250.090.10

OpenBenchmarking.orgImages / Sec, More Is BetterIntel Open Image Denoise 2.1Run: RTLightmap.hdr.4096x4096 - Device: CPU-Onlyab0.01130.02260.03390.04520.05650.040.05

libavif avifenc

This is a test of the AOMedia libavif library testing the encoding of a JPEG image to AV1 Image Format (AVIF). Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 1.0Encoder Speed: 0ab130260390520650581.56540.791. (CXX) g++ options: -O3 -fPIC -lm

OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 1.0Encoder Speed: 2ab60120180240300257.08238.251. (CXX) g++ options: -O3 -fPIC -lm

OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 1.0Encoder Speed: 6ab71421283528.7626.311. (CXX) g++ options: -O3 -fPIC -lm

OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 1.0Encoder Speed: 6, Losslessab91827364539.9136.851. (CXX) g++ options: -O3 -fPIC -lm

OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 1.0Encoder Speed: 10, Losslessab369121513.1412.021. (CXX) g++ options: -O3 -fPIC -lm

oneDNN

This is a test of the Intel oneDNN as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Intel oneDNN was formerly known as DNNL (Deep Neural Network Library) and MKL-DNN before being rebranded as part of the Intel oneAPI toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.3Harness: IP Shapes 1D - Data Type: f32 - Engine: CPUab369121513.3910.73MIN: 7.71MIN: 7.531. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.3Harness: IP Shapes 3D - Data Type: f32 - Engine: CPUab36912159.057158.04914MIN: 7.61MIN: 7.41. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.3Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPUab2468106.001774.91146MIN: 3.57MIN: 3.51. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.3Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPUab0.85761.71522.57283.43044.2883.811753.04390MIN: 2.41MIN: 2.191. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

Harness: IP Shapes 1D - Data Type: bf16bf16bf16 - Engine: CPU

a: The test run did not produce a result.

b: The test run did not produce a result.

Harness: IP Shapes 3D - Data Type: bf16bf16bf16 - Engine: CPU

a: The test run did not produce a result.

b: The test run did not produce a result.

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.3Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPUab369121513.1313.13MIN: 12.76MIN: 12.681. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.3Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPUab51015202521.4412.93MIN: 17.2MIN: 11.011. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.3Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPUab4812162015.1815.08MIN: 14.54MIN: 14.351. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.3Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPUab4812162017.7215.46MIN: 14.78MIN: 14.771. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.3Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPUab36912159.485118.47414MIN: 8.16MIN: 7.221. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.3Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPUab2468108.162228.14900MIN: 7.27MIN: 7.21. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.3Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPUab3K6K9K12K15K14396.712976.6MIN: 14160.6MIN: 12797.41. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.3Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPUab160032004800640080007400.646701.80MIN: 7186.27MIN: 6511.571. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.3Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPUab3K6K9K12K15K14373.913583.8MIN: 14132.5MIN: 13104.31. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

Harness: Convolution Batch Shapes Auto - Data Type: bf16bf16bf16 - Engine: CPU

a: The test run did not produce a result.

b: The test run did not produce a result.

Harness: Deconvolution Batch shapes_1d - Data Type: bf16bf16bf16 - Engine: CPU

a: The test run did not produce a result.

b: The test run did not produce a result.

Harness: Deconvolution Batch shapes_3d - Data Type: bf16bf16bf16 - Engine: CPU

a: The test run did not produce a result.

b: The test run did not produce a result.

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.3Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPUab160032004800640080007378.406648.27MIN: 7171.27MIN: 6485.231. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.3Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPUab3K6K9K12K15K14376.412945.5MIN: 14135.6MIN: 12762.51. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.3Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPUab160032004800640080007398.636677.03MIN: 7210.77MIN: 6521.211. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

Stress-NG

Stress-NG is a Linux stress tool developed by Colin Ian King. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: Cloningab150300450600750641.54702.931. (CXX) g++ options: -lm -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lmpfr -lpthread -lrt -lz

Test: AVX-512 VNNI

a: The test run did not produce a result.

b: The test run did not produce a result.

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: Vector Shuffleab50010001500200025002156.512306.111. (CXX) g++ options: -lm -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lmpfr -lpthread -lrt -lz

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: Wide Vector Mathab20K40K60K80K100K88229.8096693.231. (CXX) g++ options: -lm -lapparmor -latomic -lc -lcrypt -ldl -ljpeg -lmpfr -lpthread -lrt -lz

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 20230517Target: CPU - Model: mobilenetab61218243024.1422.94MIN: 22.95 / MAX: 34.8MIN: 21.77 / MAX: 34.371. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU-v2-v2 - Model: mobilenet-v2ab1.00352.0073.01054.0145.01754.374.46MIN: 4.21 / MAX: 13.61MIN: 4.22 / MAX: 14.731. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU-v3-v3 - Model: mobilenet-v3ab0.79651.5932.38953.1863.98253.543.54MIN: 3.4 / MAX: 13.43MIN: 3.39 / MAX: 13.391. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: shufflenet-v2ab0.97431.94862.92293.89724.87154.332.73MIN: 3.92 / MAX: 15.31MIN: 2.61 / MAX: 12.221. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: mnasnetab1.31182.62363.93545.24726.5595.834.02MIN: 5.4 / MAX: 19MIN: 3.47 / MAX: 16.721. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: efficientnet-b0ab369121510.7210.23MIN: 10.17 / MAX: 21.68MIN: 9.49 / MAX: 21.731. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: blazefaceab0.25880.51760.77641.03521.2941.151.05MIN: 1.08 / MAX: 7.24MIN: 0.98 / MAX: 5.031. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: googlenetab4812162017.1816.11MIN: 16 / MAX: 29.65MIN: 15.41 / MAX: 27.791. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: vgg16ab163248648070.0865.36MIN: 66.44 / MAX: 80.57MIN: 62.97 / MAX: 77.51. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: resnet18ab369121512.9811.81MIN: 12.11 / MAX: 25.94MIN: 11.4 / MAX: 27.261. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: alexnetab369121510.309.61MIN: 8.89 / MAX: 20.31MIN: 8.48 / MAX: 20.481. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: resnet50ab81624324034.1931.55MIN: 32.53 / MAX: 48.47MIN: 30.01 / MAX: 42.431. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: yolov4-tinyab71421283532.2230.62MIN: 30.8 / MAX: 42.97MIN: 29.78 / MAX: 41.831. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: squeezenet_ssdab4812162013.8113.15MIN: 13.11 / MAX: 25.08MIN: 12.51 / MAX: 24.511. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: regnety_400mab369121511.9711.26MIN: 11.19 / MAX: 23.34MIN: 10.71 / MAX: 22.011. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: vision_transformerab60120180240300267.05254.37MIN: 261.81 / MAX: 284.75MIN: 245.85 / MAX: 753.751. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: FastestDetab1.18132.36263.54394.72525.90655.155.25MIN: 4.89 / MAX: 15.82MIN: 5.09 / MAX: 12.351. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: mobilenetab61218243024.1522.83MIN: 22.83 / MAX: 34.07MIN: 21.89 / MAX: 33.081. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2ab1.00582.01163.01744.02325.0294.354.47MIN: 4.2 / MAX: 14.21MIN: 4.2 / MAX: 14.851. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3ab0.79651.5932.38953.1863.98253.543.48MIN: 3.4 / MAX: 13.64MIN: 3.4 / MAX: 7.461. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: shufflenet-v2ab0.62781.25561.88342.51123.1392.712.79MIN: 2.62 / MAX: 12.47MIN: 2.62 / MAX: 12.191. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: mnasnetab1.1792.3583.5374.7165.8955.243.60MIN: 3.48 / MAX: 17.52MIN: 3.47 / MAX: 8.61. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: efficientnet-b0ab369121510.7810.14MIN: 10.21 / MAX: 21.92MIN: 8.56 / MAX: 21.181. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: blazefaceab0.26330.52660.78991.05321.31651.171.08MIN: 1.07 / MAX: 10.59MIN: 1.03 / MAX: 5.531. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: googlenetab4812162017.1916.13MIN: 15.97 / MAX: 28.67MIN: 15.44 / MAX: 27.071. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: vgg16ab163248648070.2165.22MIN: 66.55 / MAX: 80.56MIN: 63.02 / MAX: 76.031. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: resnet18ab369121513.0611.79MIN: 12.51 / MAX: 26MIN: 11.39 / MAX: 25.811. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: alexnetab369121510.389.57MIN: 8.85 / MAX: 21.96MIN: 8.44 / MAX: 19.551. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: resnet50ab81624324034.2832.25MIN: 32.55 / MAX: 45.96MIN: 30.03 / MAX: 45.131. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: yolov4-tinyab71421283532.2030.66MIN: 31.01 / MAX: 43.29MIN: 29.83 / MAX: 421. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: squeezenet_ssdab4812162013.8913.12MIN: 13.1 / MAX: 28.84MIN: 12.52 / MAX: 24.81. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: regnety_400mab369121511.9511.33MIN: 11.17 / MAX: 23.16MIN: 10.77 / MAX: 21.781. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: vision_transformerab60120180240300268.47251.88MIN: 262.87 / MAX: 279.73MIN: 245.57 / MAX: 275.271. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: FastestDetab1.2692.5383.8075.0766.3455.644.84MIN: 5.29 / MAX: 16.11MIN: 4.59 / MAX: 13.781. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

95 Results Shown

FluidX3D:
  FP32-FP32
  FP32-FP16C
  FP32-FP16S
QuantLib:
  Multi-Threaded
  Single-Threaded
OpenRadioss:
  Bumper Beam
  Chrysler Neon 1M
  Cell Phone Drop Test
  Bird Strike on Windshield
  Rubber O-Ring Seal Installation
  INIVOL and Fluid Structure Interaction Drop Container
easyWave:
  e2Asean Grid + BengkuluSept2007 Source - 240
  e2Asean Grid + BengkuluSept2007 Source - 1200
  e2Asean Grid + BengkuluSept2007 Source - 2400
AOM AV1:
  Speed 9 Realtime - Bosphorus 4K
  Speed 10 Realtime - Bosphorus 4K
  Speed 11 Realtime - Bosphorus 4K
  Speed 9 Realtime - Bosphorus 1080p
  Speed 10 Realtime - Bosphorus 1080p
  Speed 11 Realtime - Bosphorus 1080p
Embree:
  Pathtracer - Crown
  Pathtracer ISPC - Crown
  Pathtracer - Asian Dragon
  Pathtracer - Asian Dragon Obj
  Pathtracer ISPC - Asian Dragon
  Pathtracer ISPC - Asian Dragon Obj
SVT-AV1:
  Preset 4 - Bosphorus 4K
  Preset 8 - Bosphorus 4K
  Preset 12 - Bosphorus 4K
  Preset 13 - Bosphorus 4K
  Preset 4 - Bosphorus 1080p
  Preset 8 - Bosphorus 1080p
  Preset 12 - Bosphorus 1080p
  Preset 13 - Bosphorus 1080p
Intel Open Image Denoise:
  RT.hdr_alb_nrm.3840x2160 - CPU-Only
  RT.ldr_alb_nrm.3840x2160 - CPU-Only
  RTLightmap.hdr.4096x4096 - CPU-Only
libavif avifenc:
  0
  2
  6
  6, Lossless
  10, Lossless
oneDNN:
  IP Shapes 1D - f32 - CPU
  IP Shapes 3D - f32 - CPU
  IP Shapes 1D - u8s8f32 - CPU
  IP Shapes 3D - u8s8f32 - CPU
  Convolution Batch Shapes Auto - f32 - CPU
  Deconvolution Batch shapes_1d - f32 - CPU
  Deconvolution Batch shapes_3d - f32 - CPU
  Convolution Batch Shapes Auto - u8s8f32 - CPU
  Deconvolution Batch shapes_1d - u8s8f32 - CPU
  Deconvolution Batch shapes_3d - u8s8f32 - CPU
  Recurrent Neural Network Training - f32 - CPU
  Recurrent Neural Network Inference - f32 - CPU
  Recurrent Neural Network Training - u8s8f32 - CPU
  Recurrent Neural Network Inference - u8s8f32 - CPU
  Recurrent Neural Network Training - bf16bf16bf16 - CPU
  Recurrent Neural Network Inference - bf16bf16bf16 - CPU
Stress-NG:
  Cloning
  Vector Shuffle
  Wide Vector Math
NCNN:
  CPU - mobilenet
  CPU-v2-v2 - mobilenet-v2
  CPU-v3-v3 - mobilenet-v3
  CPU - shufflenet-v2
  CPU - mnasnet
  CPU - efficientnet-b0
  CPU - blazeface
  CPU - googlenet
  CPU - vgg16
  CPU - resnet18
  CPU - alexnet
  CPU - resnet50
  CPU - yolov4-tiny
  CPU - squeezenet_ssd
  CPU - regnety_400m
  CPU - vision_transformer
  CPU - FastestDet
  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 - squeezenet_ssd
  Vulkan GPU - regnety_400m
  Vulkan GPU - vision_transformer
  Vulkan GPU - FastestDet