compulab-airtop-3-rtx-4000-compute

Intel Xeon E-2288G testing with a Compulab SBC-ATCFL v1.2 (ATOP3.PRD.0.29.2 BIOS) and NVIDIA Quadro RTX 4000 8GB on Ubuntu 20.10 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 2010311-FI-COMPULABA24
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:

CPU Massive 2 Tests
Creator Workloads 2 Tests
HPC - High Performance Computing 3 Tests
Machine Learning 2 Tests
Multi-Core 3 Tests
NVIDIA GPU Compute 16 Tests
OpenCL 4 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

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
1
October 30 2020
  9 Minutes
1a
October 30 2020
  9 Minutes
2
October 30 2020
 
1b
October 30 2020
  9 Minutes
1c
October 30 2020
  6 Minutes
1d
October 30 2020
  1 Hour, 19 Minutes
1e
October 30 2020
  3 Hours, 54 Minutes
NVIDIA Quadro RTX 4000
October 30 2020
  3 Hours, 48 Minutes
RTX 4000
October 30 2020
  3 Hours, 47 Minutes
NVIDIA RTX 4000
October 31 2020
  28 Minutes
Invert Hiding All Results Option
  1 Hour, 23 Minutes

Only show results where is faster than
Only show results matching title/arguments (delimit multiple options with a comma):


compulab-airtop-3-rtx-4000-compute ProcessorMotherboardChipsetMemoryDiskGraphicsAudioMonitorNetworkOSKernelDesktopDisplay ServerDisplay DriverOpenGLOpenCLVulkanCompilerFile-SystemScreen Resolution11a21b1c1d1eNVIDIA Quadro RTX 4000RTX 4000NVIDIA RTX 4000Intel Xeon E-2288G @ 5.00GHz (8 Cores / 16 Threads)Compulab SBC-ATCFL v1.2 (ATOP3.PRD.0.29.2 BIOS)Intel Cannon Lake PCH64GBSamsung SSD 970 EVO Plus 250GBNVIDIA Quadro RTX 4000 8GB (1005/6500MHz)Intel Cannon Lake PCH cAVSVE228Intel I219-LM + Intel I210Ubuntu 20.105.8.0-26-generic (x86_64)GNOME Shell 3.38.1X Server 1.20.9NVIDIA 455.284.6.0OpenCL 1.2 CUDA 11.1.961.2.142GCC 10.2.0ext41920x1080NVIDIA Quadro RTX 4000 8GB (300/405MHz)NVIDIA Quadro RTX 4000 8GB (1005/6500MHz)NVIDIA Quadro RTX 4000 8GB (300/405MHz)NVIDIA Quadro RTX 4000 8GB (1005/6500MHz)OpenBenchmarking.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- Scaling Governor: intel_pstate powersave - CPU Microcode: 0xd6 - Thermald 2.3OpenCL Details- GPU Compute Cores: 2304Python Details- 1, 1a, 1b, 1d, 1e, NVIDIA Quadro RTX 4000, RTX 4000, NVIDIA RTX 4000: Python 3.8.6Security Details- 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: Mitigation of TSX disabled + tsx_async_abort: Mitigation of TSX disabled

compulab-airtop-3-rtx-4000-compute realsr-ncnn: 4x - Yesclpeak: Single-Precision Floathashcat: 7-Ziphashcat: MD5realsr-ncnn: 4x - Nowaifu2x-ncnn: 2x - 3 - Yeshashcat: SHA1hashcat: TrueCrypt RIPEMD160 + XTShashcat: SHA-512clpeak: Integer Compute INTncnn: Vulkan GPU - resnet50vkfft: ncnn: Vulkan GPU - alexnetncnn: Vulkan GPU - vgg16redshift: blender: Classroom - CUDAncnn: Vulkan GPU - googlenetncnn: Vulkan GPU - shufflenet-v2blender: Classroom - NVIDIA OptiXcl-mem: Writeblender: Barbershop - CUDAncnn: Vulkan GPU-v3-v3 - mobilenet-v3ncnn: Vulkan GPU - blazefacecl-mem: Copyclpeak: Global Memory Bandwidthncnn: Vulkan GPU - mnasnetblender: Fishy Cat - NVIDIA OptiXplaidml: No - Inference - DenseNet 201 - OpenCLblender: Pabellon Barcelona - NVIDIA OptiXblender: Barbershop - NVIDIA OptiXblender: Fishy Cat - CUDAncnn: Vulkan GPU - efficientnet-b0blender: BMW27 - CUDAplaidml: No - Inference - Mobilenet - OpenCLplaidml: Yes - Inference - Mobilenet - OpenCLncnn: Vulkan GPU - squeezenetviennacl: OpenCL LU Factorizationplaidml: No - Inference - IMDB LSTM - OpenCLfahbench: mandelgpu: GPUarrayfire: Conjugate Gradient OpenCLblender: Pabellon Barcelona - CUDAcl-mem: Readclpeak: Double-Precision Doublefinancebench: Black-Scholes OpenCLncnn: Vulkan GPU-v2-v2 - mobilenet-v2neatbench: GPUblender: BMW27 - NVIDIA OptiXncnn: Vulkan GPU - yolov4-tinyncnn: Vulkan GPU - resnet18ncnn: Vulkan GPU - mobilenetluxcorerender-cl: Rainbow Colors and Prismluxcorerender-cl: LuxCore Benchmarkluxcorerender-cl: Foodluxcorerender-cl: DLSC11a21b1c1d1eNVIDIA Quadro RTX 4000RTX 4000NVIDIA RTX 400080.4454469002512196666712.5525.5028704500000327233110226666725694325.5283.068.2883379.714.03481.1294443002494470000012.6045.5518642000000326300109526666725585320.4282.668.4737379.214.03281.5444426672483896666712.6655.5728615933333324033109103333325486321.1282.168.2546379.214.03782.46412.7015.67184.1744333002425903333312.9785.6948426866667317867107006666725027382321.1281.168.3795191.6264379.314.03610.423.401.523.9981.1746033.104430002487690000012.5805.571863350000032426710922000005712.253.89254572.188.79381218.663.321.33115.78322.5756.641.710.63282.1346.091.5258.38140.54160.821307.24112.742.7357.801490.381843.843.7768.4059423.50191.8417248122412.92.247459.35379.3259.6614.0341.4831.032.148.621.84.6610.783.501.574.0985.9266004.484246332384096666713.0785.785825403333331223310497333335741.923.93246842.219.14391224.853.401.35118.39318.4771.191.740.63278.7340.911.5459.12138.91160.951321.89114.002.7558.101475.981834.203.7868.0188421.03190.7594248177151.42.255460.64379.3259.5014.0341.4830.929.238.331.954.6710.793.471.554.0187.7936536.454177672350686666713.3505.861818156666730940010415000006013.594.08245382.279.02393223.813.371.36117.20319.4764.301.740.64278.8342.371.5458.69139.15159.091307.37113.882.7658.411480.201829.243.8068.0204420.80190.8199246857018.02.257459.08379.3259.3314.0341.4830.229.148.221.774.8610.733.471.554.0280.5494464002507546666712.4945.5408700533333327567110043333325593379323.0282.168.2894379.314.032OpenBenchmarking.org

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: Yes11a1b1c1d1eNVIDIA Quadro RTX 4000RTX 4000NVIDIA RTX 400020406080100SE +/- 0.35, N = 3SE +/- 0.36, N = 3SE +/- 0.40, N = 3SE +/- 0.40, N = 3SE +/- 0.36, N = 3SE +/- 0.36, N = 3SE +/- 0.45, N = 3SE +/- 0.27, N = 3SE +/- 0.37, N = 380.4581.1381.5482.4684.1781.1785.9387.7980.55
OpenBenchmarking.orgSeconds, Fewer Is BetterRealSR-NCNN 20200818Scale: 4x - TAA: Yes11a1b1c1d1eNVIDIA Quadro RTX 4000RTX 4000NVIDIA RTX 400020406080100Min: 79.84 / Avg: 80.45 / Max: 81.04Min: 80.49 / Avg: 81.13 / Max: 81.73Min: 80.83 / Avg: 81.54 / Max: 82.22Min: 81.75 / Avg: 82.46 / Max: 83.12Min: 83.5 / Avg: 84.17 / Max: 84.74Min: 80.53 / Avg: 81.17 / Max: 81.79Min: 85.1 / Avg: 85.93 / Max: 86.64Min: 87.29 / Avg: 87.79 / Max: 88.22Min: 79.88 / Avg: 80.55 / Max: 81.15

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 Float1eNVIDIA Quadro RTX 4000RTX 400014002800420056007000SE +/- 35.64, N = 3SE +/- 55.06, N = 3SE +/- 97.61, N = 36033.106004.486536.451. (CXX) g++ options: -O3 -rdynamic -lOpenCL
OpenBenchmarking.orgGFLOPS, More Is BetterclpeakOpenCL Test: Single-Precision Float1eNVIDIA Quadro RTX 4000RTX 400011002200330044005500Min: 5996.87 / Avg: 6033.1 / Max: 6104.38Min: 5897.91 / Avg: 6004.48 / Max: 6081.8Min: 6378.8 / Avg: 6536.45 / Max: 67151. (CXX) g++ options: -O3 -rdynamic -lOpenCL

Hashcat

Hashcat is an open-source, advanced password recovery tool supporting GPU acceleration with OpenCL, NVIDIA CUDA, and Radeon ROCm. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgH/s, More Is BetterHashcat 6.1.1Benchmark: 7-Zip11a1b1d1eNVIDIA Quadro RTX 4000RTX 4000NVIDIA RTX 4000100K200K300K400K500KSE +/- 208.17, N = 3SE +/- 556.78, N = 3SE +/- 202.76, N = 3SE +/- 321.46, N = 3SE +/- 1365.04, N = 3SE +/- 463.08, N = 3SE +/- 233.33, N = 3SE +/- 200.00, N = 3446900444300442667433300443000424633417767446400
OpenBenchmarking.orgH/s, More Is BetterHashcat 6.1.1Benchmark: 7-Zip11a1b1d1eNVIDIA Quadro RTX 4000RTX 4000NVIDIA RTX 400080K160K240K320K400KMin: 446500 / Avg: 446900 / Max: 447200Min: 443200 / Avg: 444300 / Max: 445000Min: 442300 / Avg: 442666.67 / Max: 443000Min: 432800 / Avg: 433300 / Max: 433900Min: 440300 / Avg: 443000 / Max: 444700Min: 423800 / Avg: 424633.33 / Max: 425400Min: 417300 / Avg: 417766.67 / Max: 418000Min: 446000 / Avg: 446400 / Max: 446600

OpenBenchmarking.orgH/s, More Is BetterHashcat 6.1.1Benchmark: MD511a1b1d1eNVIDIA Quadro RTX 4000RTX 4000NVIDIA RTX 40005000M10000M15000M20000M25000MSE +/- 25031801.99, N = 3SE +/- 2051828.45, N = 3SE +/- 12651789.51, N = 3SE +/- 2643440.52, N = 3SE +/- 12698162.60, N = 3SE +/- 13574649.58, N = 3SE +/- 2355372.11, N = 3SE +/- 24626025.08, N = 32512196666724944700000248389666672425903333324876900000238409666672350686666725075466667
OpenBenchmarking.orgH/s, More Is BetterHashcat 6.1.1Benchmark: MD511a1b1d1eNVIDIA Quadro RTX 4000RTX 4000NVIDIA RTX 40004000M8000M12000M16000M20000MMin: 25086500000 / Avg: 25121966666.67 / Max: 25170300000Min: 24942500000 / Avg: 24944700000 / Max: 24948800000Min: 24814400000 / Avg: 24838966666.67 / Max: 24856500000Min: 24253800000 / Avg: 24259033333.33 / Max: 24262300000Min: 24853600000 / Avg: 24876900000 / Max: 24897300000Min: 23823500000 / Avg: 23840966666.67 / Max: 23867700000Min: 23503100000 / Avg: 23506866666.67 / Max: 23511200000Min: 25032500000 / Avg: 25075466666.67 / Max: 25117800000

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: No11a1b1c1d1eNVIDIA Quadro RTX 4000RTX 4000NVIDIA RTX 40003691215SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.04, N = 3SE +/- 0.03, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 312.5512.6012.6712.7012.9812.5813.0813.3512.49
OpenBenchmarking.orgSeconds, Fewer Is BetterRealSR-NCNN 20200818Scale: 4x - TAA: No11a1b1c1d1eNVIDIA Quadro RTX 4000RTX 4000NVIDIA RTX 400048121620Min: 12.53 / Avg: 12.55 / Max: 12.58Min: 12.57 / Avg: 12.6 / Max: 12.63Min: 12.59 / Avg: 12.66 / Max: 12.71Min: 12.66 / Avg: 12.7 / Max: 12.77Min: 12.97 / Avg: 12.98 / Max: 12.99Min: 12.57 / Avg: 12.58 / Max: 12.6Min: 13.05 / Avg: 13.08 / Max: 13.12Min: 13.32 / Avg: 13.35 / Max: 13.37Min: 12.47 / Avg: 12.49 / Max: 12.52

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: Yes11a1b1c1d1eNVIDIA Quadro RTX 4000RTX 4000NVIDIA RTX 40001.31872.63743.95615.27486.5935SE +/- 0.008, N = 3SE +/- 0.023, N = 3SE +/- 0.022, N = 3SE +/- 0.047, N = 3SE +/- 0.008, N = 3SE +/- 0.017, N = 3SE +/- 0.018, N = 3SE +/- 0.014, N = 3SE +/- 0.041, N = 35.5025.5515.5725.6715.6945.5715.7855.8615.540
OpenBenchmarking.orgSeconds, Fewer Is BetterWaifu2x-NCNN Vulkan 20200818Scale: 2x - Denoise: 3 - TAA: Yes11a1b1c1d1eNVIDIA Quadro RTX 4000RTX 4000NVIDIA RTX 4000246810Min: 5.49 / Avg: 5.5 / Max: 5.51Min: 5.51 / Avg: 5.55 / Max: 5.59Min: 5.53 / Avg: 5.57 / Max: 5.6Min: 5.61 / Avg: 5.67 / Max: 5.76Min: 5.68 / Avg: 5.69 / Max: 5.71Min: 5.55 / Avg: 5.57 / Max: 5.6Min: 5.76 / Avg: 5.79 / Max: 5.82Min: 5.84 / Avg: 5.86 / Max: 5.89Min: 5.49 / Avg: 5.54 / Max: 5.62

Hashcat

Hashcat is an open-source, advanced password recovery tool supporting GPU acceleration with OpenCL, NVIDIA CUDA, and Radeon ROCm. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgH/s, More Is BetterHashcat 6.1.1Benchmark: SHA111a1b1d1eNVIDIA Quadro RTX 4000RTX 4000NVIDIA RTX 40002000M4000M6000M8000M10000MSE +/- 9832090.32, N = 3SE +/- 6847870.72, N = 3SE +/- 3773739.67, N = 3SE +/- 7846938.54, N = 3SE +/- 6005275.46, N = 3SE +/- 5691026.07, N = 3SE +/- 6590228.46, N = 3SE +/- 2630800.47, N = 387045000008642000000861593333384268666678633500000825403333381815666678700533333
OpenBenchmarking.orgH/s, More Is BetterHashcat 6.1.1Benchmark: SHA111a1b1d1eNVIDIA Quadro RTX 4000RTX 4000NVIDIA RTX 40001500M3000M4500M6000M7500MMin: 8686600000 / Avg: 8704500000 / Max: 8720500000Min: 8633800000 / Avg: 8642000000 / Max: 8655600000Min: 8608400000 / Avg: 8615933333.33 / Max: 8620100000Min: 8415700000 / Avg: 8426866666.67 / Max: 8442000000Min: 8623000000 / Avg: 8633500000 / Max: 8643800000Min: 8247000000 / Avg: 8254033333.33 / Max: 8265300000Min: 8170500000 / Avg: 8181566666.67 / Max: 8193300000Min: 8695400000 / Avg: 8700533333.33 / Max: 8704100000

OpenBenchmarking.orgH/s, More Is BetterHashcat 6.1.1Benchmark: TrueCrypt RIPEMD160 + XTS11a1b1d1eNVIDIA Quadro RTX 4000RTX 4000NVIDIA RTX 400070K140K210K280K350KSE +/- 533.33, N = 3SE +/- 185.59, N = 3SE +/- 88.19, N = 3SE +/- 233.33, N = 3SE +/- 317.98, N = 3SE +/- 683.94, N = 3327233326300324033317867324267312233309400327567
OpenBenchmarking.orgH/s, More Is BetterHashcat 6.1.1Benchmark: TrueCrypt RIPEMD160 + XTS11a1b1d1eNVIDIA Quadro RTX 4000RTX 4000NVIDIA RTX 400060K120K180K240K300KMin: 326700 / Avg: 327233.33 / Max: 328300Min: 323800 / Avg: 324033.33 / Max: 324400Min: 317700 / Avg: 317866.67 / Max: 318000Min: 323900 / Avg: 324266.67 / Max: 324700Min: 311600 / Avg: 312233.33 / Max: 312600Min: 326200 / Avg: 327566.67 / Max: 328300

OpenBenchmarking.orgH/s, More Is BetterHashcat 6.1.1Benchmark: SHA-51211a1b1d1eNVIDIA Quadro RTX 4000RTX 4000NVIDIA RTX 4000200M400M600M800M1000MSE +/- 819213.72, N = 3SE +/- 491030.66, N = 3SE +/- 643773.60, N = 3SE +/- 1017076.42, N = 3SE +/- 1021436.90, N = 3SE +/- 1260070.54, N = 3SE +/- 953939.20, N = 3SE +/- 240370.09, N = 311022666671095266667109103333310700666671092200000104973333310415000001100433333
OpenBenchmarking.orgH/s, More Is BetterHashcat 6.1.1Benchmark: SHA-51211a1b1d1eNVIDIA Quadro RTX 4000RTX 4000NVIDIA RTX 4000200M400M600M800M1000MMin: 1101000000 / Avg: 1102266666.67 / Max: 1103800000Min: 1094300000 / Avg: 1095266666.67 / Max: 1095900000Min: 1090200000 / Avg: 1091033333.33 / Max: 1092300000Min: 1068200000 / Avg: 1070066666.67 / Max: 1071700000Min: 1090300000 / Avg: 1092200000 / Max: 1093800000Min: 1047800000 / Avg: 1049733333.33 / Max: 1052100000Min: 1039900000 / Avg: 1041500000 / Max: 1043200000Min: 1100100000 / Avg: 1100433333.33 / Max: 1100900000

clpeak

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

OpenBenchmarking.orgGIOPS, More Is BetterclpeakOpenCL Test: Integer Compute INT1eNVIDIA Quadro RTX 4000RTX 400013002600390052006500SE +/- 68.26, N = 12SE +/- 46.13, N = 3SE +/- 102.19, N = 35712.255741.926013.591. (CXX) g++ options: -O3 -rdynamic -lOpenCL
OpenBenchmarking.orgGIOPS, More Is BetterclpeakOpenCL Test: Integer Compute INT1eNVIDIA Quadro RTX 4000RTX 400010002000300040005000Min: 5039.83 / Avg: 5712.25 / Max: 6051.86Min: 5678.83 / Avg: 5741.92 / Max: 5831.77Min: 5900.36 / Avg: 6013.59 / Max: 6217.551. (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: resnet501eNVIDIA Quadro RTX 4000RTX 40000.9181.8362.7543.6724.59SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.14, N = 33.893.934.08MIN: 3.86 / MAX: 3.99MIN: 3.91 / MAX: 4.04MIN: 3.92 / MAX: 40.551. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: resnet501eNVIDIA Quadro RTX 4000RTX 4000246810Min: 3.87 / Avg: 3.89 / Max: 3.9Min: 3.92 / Avg: 3.93 / Max: 3.94Min: 3.94 / Avg: 4.08 / Max: 4.361. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

VkFFT

VkFFT is a Fast Fourier Transform (FFT) Library that is GPU accelerated by means of the Vulkan API. The VkFFT benchmark runs FFT performance differences of many different sizes before returning an overall benchmark score. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgBenchmark Score, More Is BetterVkFFT 2020-09-2911a1b1d1eNVIDIA Quadro RTX 4000RTX 4000NVIDIA RTX 40006K12K18K24K30KSE +/- 28.39, N = 3SE +/- 16.51, N = 3SE +/- 27.82, N = 3SE +/- 17.21, N = 3SE +/- 32.54, N = 3SE +/- 4.04, N = 3SE +/- 20.11, N = 32569425585254862502725457246842453825593
OpenBenchmarking.orgBenchmark Score, More Is BetterVkFFT 2020-09-2911a1b1d1eNVIDIA Quadro RTX 4000RTX 4000NVIDIA RTX 40004K8K12K16K20KMin: 25639 / Avg: 25694.33 / Max: 25733Min: 25560 / Avg: 25584.67 / Max: 25616Min: 25450 / Avg: 25486.33 / Max: 25541Min: 25000 / Avg: 25027 / Max: 25059Min: 25412 / Avg: 25456.67 / Max: 25520Min: 24533 / Avg: 24538 / Max: 24546Min: 25554 / Avg: 25593 / Max: 25621

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: alexnet1eNVIDIA Quadro RTX 4000RTX 40000.51081.02161.53242.04322.554SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.03, N = 32.182.212.27MIN: 1.91 / MAX: 11.43MIN: 1.91 / MAX: 6.96MIN: 2.15 / MAX: 23.821. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: alexnet1eNVIDIA Quadro RTX 4000RTX 4000246810Min: 2.16 / Avg: 2.18 / Max: 2.21Min: 2.2 / Avg: 2.21 / Max: 2.22Min: 2.21 / Avg: 2.27 / Max: 2.331. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: vgg161eNVIDIA Quadro RTX 4000RTX 40003691215SE +/- 0.04, N = 3SE +/- 0.13, N = 3SE +/- 0.04, N = 38.799.149.02MIN: 8.1 / MAX: 20.83MIN: 8.49 / MAX: 36.48MIN: 8.35 / MAX: 20.341. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: vgg161eNVIDIA Quadro RTX 4000RTX 40003691215Min: 8.72 / Avg: 8.79 / Max: 8.84Min: 8.98 / Avg: 9.14 / Max: 9.39Min: 8.98 / Avg: 9.02 / Max: 9.11. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

RedShift Demo

This is a test of MAXON's RedShift demo build that currently requires NVIDIA GPU acceleration. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterRedShift Demo 3.01d1eNVIDIA Quadro RTX 4000RTX 4000NVIDIA RTX 400090180270360450SE +/- 2.60, N = 3SE +/- 2.31, N = 3SE +/- 4.63, N = 3SE +/- 4.91, N = 3SE +/- 2.33, N = 3382381391393379
OpenBenchmarking.orgSeconds, Fewer Is BetterRedShift Demo 3.01d1eNVIDIA Quadro RTX 4000RTX 4000NVIDIA RTX 400070140210280350Min: 377 / Avg: 381.67 / Max: 386Min: 377 / Avg: 381 / Max: 385Min: 383 / Avg: 390.67 / Max: 399Min: 384 / Avg: 392.67 / Max: 401Min: 375 / Avg: 379.33 / Max: 383

Blender

Blender is an open-source 3D creation software project. This test is of Blender's Cycles benchmark with various sample files. GPU computing via OpenCL or CUDA is supported. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.90Blend File: Classroom - Compute: CUDA1eNVIDIA Quadro RTX 4000RTX 400050100150200250SE +/- 1.49, N = 3SE +/- 3.62, N = 3SE +/- 3.26, N = 3218.66224.85223.81
OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.90Blend File: Classroom - Compute: CUDA1eNVIDIA Quadro RTX 4000RTX 40004080120160200Min: 216.02 / Avg: 218.66 / Max: 221.16Min: 219.03 / Avg: 224.85 / Max: 231.5Min: 218.62 / Avg: 223.81 / Max: 229.82

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: googlenet1eNVIDIA Quadro RTX 4000RTX 40000.7651.532.2953.063.825SE +/- 0.00, N = 3SE +/- 0.02, N = 3SE +/- 0.00, N = 33.323.403.37MIN: 3.29 / MAX: 3.43MIN: 3.33 / MAX: 20.26MIN: 3.35 / MAX: 3.441. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: googlenet1eNVIDIA Quadro RTX 4000RTX 4000246810Min: 3.31 / Avg: 3.32 / Max: 3.32Min: 3.36 / Avg: 3.4 / Max: 3.44Min: 3.37 / Avg: 3.37 / Max: 3.371. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: shufflenet-v21eNVIDIA Quadro RTX 4000RTX 40000.3060.6120.9181.2241.53SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 31.331.351.36MIN: 1.32 / MAX: 1.4MIN: 1.33 / MAX: 1.4MIN: 1.34 / MAX: 1.411. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: shufflenet-v21eNVIDIA Quadro RTX 4000RTX 4000246810Min: 1.33 / Avg: 1.33 / Max: 1.34Min: 1.35 / Avg: 1.35 / Max: 1.36Min: 1.35 / Avg: 1.36 / Max: 1.361. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

Blender

Blender is an open-source 3D creation software project. This test is of Blender's Cycles benchmark with various sample files. GPU computing via OpenCL or CUDA is supported. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.90Blend File: Classroom - Compute: NVIDIA OptiX1eNVIDIA Quadro RTX 4000RTX 4000306090120150SE +/- 0.87, N = 3SE +/- 0.55, N = 3SE +/- 0.57, N = 3115.78118.39117.20
OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.90Blend File: Classroom - Compute: NVIDIA OptiX1eNVIDIA Quadro RTX 4000RTX 400020406080100Min: 114.1 / Avg: 115.78 / Max: 117.01Min: 117.29 / Avg: 118.39 / Max: 118.95Min: 116.06 / Avg: 117.2 / Max: 117.88

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: Write11a1b1d1eNVIDIA Quadro RTX 4000RTX 4000NVIDIA RTX 400070140210280350SE +/- 1.79, N = 3SE +/- 1.48, N = 3SE +/- 0.78, N = 3SE +/- 0.96, N = 3SE +/- 0.58, N = 3SE +/- 2.17, N = 3SE +/- 1.44, N = 3SE +/- 1.47, N = 3325.5320.4321.1321.1322.5318.4319.4323.01. (CC) gcc options: -O2 -flto -lOpenCL
OpenBenchmarking.orgGB/s, More Is Bettercl-mem 2017-01-13Benchmark: Write11a1b1d1eNVIDIA Quadro RTX 4000RTX 4000NVIDIA RTX 400060120180240300Min: 322.3 / Avg: 325.5 / Max: 328.5Min: 318.9 / Avg: 320.43 / Max: 323.4Min: 319.8 / Avg: 321.13 / Max: 322.5Min: 319.9 / Avg: 321.1 / Max: 323Min: 321.4 / Avg: 322.47 / Max: 323.4Min: 314.1 / Avg: 318.43 / Max: 320.8Min: 316.9 / Avg: 319.43 / Max: 321.9Min: 320.5 / Avg: 322.97 / Max: 325.61. (CC) gcc options: -O2 -flto -lOpenCL

Blender

Blender is an open-source 3D creation software project. This test is of Blender's Cycles benchmark with various sample files. GPU computing via OpenCL or CUDA is supported. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.90Blend File: Barbershop - Compute: CUDA1eNVIDIA Quadro RTX 4000RTX 4000170340510680850SE +/- 2.80, N = 3SE +/- 1.15, N = 3SE +/- 0.87, N = 3756.64771.19764.30
OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.90Blend File: Barbershop - Compute: CUDA1eNVIDIA Quadro RTX 4000RTX 4000140280420560700Min: 751.24 / Avg: 756.64 / Max: 760.61Min: 768.95 / Avg: 771.19 / Max: 772.74Min: 762.69 / Avg: 764.3 / Max: 765.7

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-v31eNVIDIA Quadro RTX 4000RTX 40000.39150.7831.17451.5661.9575SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 31.711.741.74MIN: 1.7 / MAX: 1.75MIN: 1.73 / MAX: 1.81MIN: 1.73 / MAX: 1.81. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU-v3-v3 - Model: mobilenet-v31eNVIDIA Quadro RTX 4000RTX 4000246810Min: 1.71 / Avg: 1.71 / Max: 1.72Min: 1.74 / Avg: 1.74 / Max: 1.75Min: 1.74 / Avg: 1.74 / Max: 1.751. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: blazeface1eNVIDIA Quadro RTX 4000RTX 40000.1440.2880.4320.5760.72SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 30.630.630.64MIN: 0.62 / MAX: 0.68MIN: 0.62 / MAX: 0.65MIN: 0.62 / MAX: 0.841. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: blazeface1eNVIDIA Quadro RTX 4000RTX 4000246810Min: 0.62 / Avg: 0.63 / Max: 0.63Min: 0.62 / Avg: 0.63 / Max: 0.64Min: 0.64 / Avg: 0.64 / Max: 0.641. (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: Copy11a1b1d1eNVIDIA Quadro RTX 4000RTX 4000NVIDIA RTX 400060120180240300SE +/- 0.26, N = 3SE +/- 0.06, N = 3SE +/- 0.12, N = 3SE +/- 0.20, N = 3SE +/- 0.12, N = 3SE +/- 0.20, N = 3SE +/- 0.12, N = 3SE +/- 0.28, N = 3283.0282.6282.1281.1282.1278.7278.8282.11. (CC) gcc options: -O2 -flto -lOpenCL
OpenBenchmarking.orgGB/s, More Is Bettercl-mem 2017-01-13Benchmark: Copy11a1b1d1eNVIDIA Quadro RTX 4000RTX 4000NVIDIA RTX 400050100150200250Min: 282.6 / Avg: 283 / Max: 283.5Min: 282.5 / Avg: 282.6 / Max: 282.7Min: 281.9 / Avg: 282.07 / Max: 282.3Min: 280.7 / Avg: 281.07 / Max: 281.4Min: 281.9 / Avg: 282.07 / Max: 282.3Min: 278.3 / Avg: 278.67 / Max: 279Min: 278.6 / Avg: 278.8 / Max: 279Min: 281.5 / Avg: 282.07 / Max: 282.41. (CC) gcc options: -O2 -flto -lOpenCL

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 Bandwidth1eNVIDIA Quadro RTX 4000RTX 400080160240320400SE +/- 4.72, N = 3SE +/- 4.44, N = 3SE +/- 5.13, N = 3346.09340.91342.371. (CXX) g++ options: -O3 -rdynamic -lOpenCL
OpenBenchmarking.orgGBPS, More Is BetterclpeakOpenCL Test: Global Memory Bandwidth1eNVIDIA Quadro RTX 4000RTX 400060120180240300Min: 337.18 / Avg: 346.09 / Max: 353.27Min: 336.37 / Avg: 340.91 / Max: 349.79Min: 337.23 / Avg: 342.37 / Max: 352.631. (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: mnasnet1eNVIDIA Quadro RTX 4000RTX 40000.34650.6931.03951.3861.7325SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 31.521.541.54MIN: 1.5 / MAX: 1.56MIN: 1.53 / MAX: 1.63MIN: 1.53 / MAX: 1.631. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: mnasnet1eNVIDIA Quadro RTX 4000RTX 4000246810Min: 1.51 / Avg: 1.52 / Max: 1.52Min: 1.54 / Avg: 1.54 / Max: 1.54Min: 1.54 / Avg: 1.54 / Max: 1.541. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

Blender

Blender is an open-source 3D creation software project. This test is of Blender's Cycles benchmark with various sample files. GPU computing via OpenCL or CUDA is supported. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.90Blend File: Fishy Cat - Compute: NVIDIA OptiX1eNVIDIA Quadro RTX 4000RTX 40001326395265SE +/- 0.21, N = 3SE +/- 0.24, N = 3SE +/- 0.22, N = 358.3859.1258.69
OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.90Blend File: Fishy Cat - Compute: NVIDIA OptiX1eNVIDIA Quadro RTX 4000RTX 40001224364860Min: 57.98 / Avg: 58.38 / Max: 58.69Min: 58.65 / Avg: 59.12 / Max: 59.38Min: 58.26 / Avg: 58.69 / Max: 58.95

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: DenseNet 201 - Device: OpenCL1eNVIDIA Quadro RTX 4000RTX 4000306090120150SE +/- 0.18, N = 3SE +/- 0.11, N = 3SE +/- 0.12, N = 3140.54138.91139.15
OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: DenseNet 201 - Device: OpenCL1eNVIDIA Quadro RTX 4000RTX 4000306090120150Min: 140.3 / Avg: 140.54 / Max: 140.89Min: 138.8 / Avg: 138.91 / Max: 139.12Min: 138.95 / Avg: 139.15 / Max: 139.35

Blender

Blender is an open-source 3D creation software project. This test is of Blender's Cycles benchmark with various sample files. GPU computing via OpenCL or CUDA is supported. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.90Blend File: Pabellon Barcelona - Compute: NVIDIA OptiX1eNVIDIA Quadro RTX 4000RTX 40004080120160200SE +/- 0.15, N = 3SE +/- 0.11, N = 3SE +/- 0.48, N = 3160.82160.95159.09
OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.90Blend File: Pabellon Barcelona - Compute: NVIDIA OptiX1eNVIDIA Quadro RTX 4000RTX 4000306090120150Min: 160.54 / Avg: 160.82 / Max: 161.07Min: 160.73 / Avg: 160.95 / Max: 161.06Min: 158.27 / Avg: 159.09 / Max: 159.93

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.90Blend File: Barbershop - Compute: NVIDIA OptiX1eNVIDIA Quadro RTX 4000RTX 400030060090012001500SE +/- 4.68, N = 3SE +/- 1.05, N = 3SE +/- 0.53, N = 31307.241321.891307.37
OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.90Blend File: Barbershop - Compute: NVIDIA OptiX1eNVIDIA Quadro RTX 4000RTX 40002004006008001000Min: 1298.59 / Avg: 1307.24 / Max: 1314.65Min: 1319.86 / Avg: 1321.89 / Max: 1323.37Min: 1306.52 / Avg: 1307.37 / Max: 1308.35

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.90Blend File: Fishy Cat - Compute: CUDA1eNVIDIA Quadro RTX 4000RTX 4000306090120150SE +/- 0.28, N = 3SE +/- 0.16, N = 3SE +/- 0.21, N = 3112.74114.00113.88
OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.90Blend File: Fishy Cat - Compute: CUDA1eNVIDIA Quadro RTX 4000RTX 400020406080100Min: 112.24 / Avg: 112.74 / Max: 113.21Min: 113.69 / Avg: 114 / Max: 114.22Min: 113.48 / Avg: 113.88 / Max: 114.17

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-b01eNVIDIA Quadro RTX 4000RTX 40000.6211.2421.8632.4843.105SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 32.732.752.76MIN: 2.7 / MAX: 8.24MIN: 2.74 / MAX: 3.38MIN: 2.75 / MAX: 3.231. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: efficientnet-b01eNVIDIA Quadro RTX 4000RTX 4000246810Min: 2.72 / Avg: 2.73 / Max: 2.74Min: 2.75 / Avg: 2.75 / Max: 2.76Min: 2.76 / Avg: 2.76 / Max: 2.761. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

Blender

Blender is an open-source 3D creation software project. This test is of Blender's Cycles benchmark with various sample files. GPU computing via OpenCL or CUDA is supported. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.90Blend File: BMW27 - Compute: CUDA1eNVIDIA Quadro RTX 4000RTX 40001326395265SE +/- 0.09, N = 3SE +/- 0.14, N = 3SE +/- 0.10, N = 357.8058.1058.41
OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.90Blend File: BMW27 - Compute: CUDA1eNVIDIA Quadro RTX 4000RTX 40001224364860Min: 57.66 / Avg: 57.8 / Max: 57.97Min: 57.85 / Avg: 58.1 / Max: 58.32Min: 58.2 / Avg: 58.41 / Max: 58.54

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: OpenCL1eNVIDIA Quadro RTX 4000RTX 400030060090012001500SE +/- 5.16, N = 3SE +/- 5.69, N = 3SE +/- 5.32, N = 31490.381475.981480.20
OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: Mobilenet - Device: OpenCL1eNVIDIA Quadro RTX 4000RTX 400030060090012001500Min: 1484.37 / Avg: 1490.38 / Max: 1500.65Min: 1467.95 / Avg: 1475.98 / Max: 1486.99Min: 1471.62 / Avg: 1480.2 / Max: 1489.95

OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: Yes - Mode: Inference - Network: Mobilenet - Device: OpenCL1eNVIDIA Quadro RTX 4000RTX 4000400800120016002000SE +/- 9.92, N = 3SE +/- 2.10, N = 3SE +/- 8.76, N = 31843.841834.201829.24
OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: Yes - Mode: Inference - Network: Mobilenet - Device: OpenCL1eNVIDIA Quadro RTX 4000RTX 400030060090012001500Min: 1832.86 / Avg: 1843.84 / Max: 1863.64Min: 1830.25 / Avg: 1834.2 / Max: 1837.4Min: 1812.38 / Avg: 1829.24 / Max: 1841.83

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: squeezenet1eNVIDIA Quadro RTX 4000RTX 40000.8551.712.5653.424.275SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 33.773.783.80MIN: 3.71 / MAX: 3.87MIN: 3.72 / MAX: 3.84MIN: 3.74 / MAX: 10.311. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: squeezenet1eNVIDIA Quadro RTX 4000RTX 4000246810Min: 3.75 / Avg: 3.77 / Max: 3.79Min: 3.75 / Avg: 3.78 / Max: 3.79Min: 3.79 / Avg: 3.8 / Max: 3.811. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

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 Factorization11a1b1d1eNVIDIA Quadro RTX 4000RTX 4000NVIDIA RTX 40001530456075SE +/- 0.12, N = 3SE +/- 0.12, N = 3SE +/- 0.28, N = 3SE +/- 0.06, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.06, N = 3SE +/- 0.02, N = 368.2968.4768.2568.3868.4168.0268.0268.291. (CXX) g++ options: -rdynamic -lOpenCL
OpenBenchmarking.orgGFLOPS, More Is BetterViennaCL 1.4.2OpenCL LU Factorization11a1b1d1eNVIDIA Quadro RTX 4000RTX 4000NVIDIA RTX 40001326395265Min: 68.06 / Avg: 68.29 / Max: 68.43Min: 68.3 / Avg: 68.47 / Max: 68.7Min: 67.7 / Avg: 68.25 / Max: 68.6Min: 68.28 / Avg: 68.38 / Max: 68.5Min: 68.37 / Avg: 68.41 / Max: 68.43Min: 67.99 / Avg: 68.02 / Max: 68.04Min: 67.93 / Avg: 68.02 / Max: 68.14Min: 68.27 / Avg: 68.29 / Max: 68.331. (CXX) g++ options: -rdynamic -lOpenCL

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: OpenCL1eNVIDIA Quadro RTX 4000RTX 400090180270360450SE +/- 0.45, N = 3SE +/- 1.26, N = 3SE +/- 0.32, N = 3423.50421.03420.80
OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: IMDB LSTM - Device: OpenCL1eNVIDIA Quadro RTX 4000RTX 400080160240320400Min: 422.94 / Avg: 423.5 / Max: 424.38Min: 419.12 / Avg: 421.03 / Max: 423.41Min: 420.38 / Avg: 420.8 / Max: 421.43

FAHBench

FAHBench is a Folding@Home benchmark on the GPU. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgNs Per Day, More Is BetterFAHBench 2.3.21d1eNVIDIA Quadro RTX 4000RTX 40004080120160200SE +/- 0.40, N = 3SE +/- 0.32, N = 3SE +/- 0.27, N = 3SE +/- 0.37, N = 3191.63191.84190.76190.82
OpenBenchmarking.orgNs Per Day, More Is BetterFAHBench 2.3.21d1eNVIDIA Quadro RTX 4000RTX 40004080120160200Min: 191.09 / Avg: 191.63 / Max: 192.42Min: 191.26 / Avg: 191.84 / Max: 192.37Min: 190.26 / Avg: 190.76 / Max: 191.18Min: 190.42 / Avg: 190.82 / Max: 191.57

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: GPU1eNVIDIA Quadro RTX 4000RTX 400050M100M150M200M250MSE +/- 711502.39, N = 3SE +/- 308768.05, N = 3SE +/- 540319.59, N = 3248122412.9248177151.4246857018.01. (CC) gcc options: -O3 -lm -ftree-vectorize -funroll-loops -lglut -lOpenCL -lGL
OpenBenchmarking.orgSamples/sec, More Is BetterMandelGPU 1.3pts1OpenCL Device: GPU1eNVIDIA Quadro RTX 4000RTX 400040M80M120M160M200MMin: 247045758.1 / Avg: 248122412.93 / Max: 249466542.9Min: 247673467.9 / Avg: 248177151.4 / Max: 248738412.5Min: 246299220.2 / Avg: 246857017.97 / Max: 247937466.61. (CC) gcc options: -O3 -lm -ftree-vectorize -funroll-loops -lglut -lOpenCL -lGL

ArrayFire

ArrayFire is an GPU and CPU numeric processing library, this test uses the built-in CPU and OpenCL ArrayFire benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterArrayFire 3.7Test: Conjugate Gradient OpenCL1eNVIDIA Quadro RTX 4000RTX 40000.50781.01561.52342.03122.539SE +/- 0.008, N = 3SE +/- 0.012, N = 3SE +/- 0.007, N = 32.2472.2552.2571. (CXX) g++ options: -rdynamic
OpenBenchmarking.orgms, Fewer Is BetterArrayFire 3.7Test: Conjugate Gradient OpenCL1eNVIDIA Quadro RTX 4000RTX 4000246810Min: 2.23 / Avg: 2.25 / Max: 2.26Min: 2.24 / Avg: 2.26 / Max: 2.28Min: 2.25 / Avg: 2.26 / Max: 2.271. (CXX) g++ options: -rdynamic

Blender

Blender is an open-source 3D creation software project. This test is of Blender's Cycles benchmark with various sample files. GPU computing via OpenCL or CUDA is supported. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.90Blend File: Pabellon Barcelona - Compute: CUDA1eNVIDIA Quadro RTX 4000RTX 4000100200300400500SE +/- 1.17, N = 3SE +/- 1.47, N = 3SE +/- 0.47, N = 3459.35460.64459.08
OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.90Blend File: Pabellon Barcelona - Compute: CUDA1eNVIDIA Quadro RTX 4000RTX 400080160240320400Min: 457.44 / Avg: 459.35 / Max: 461.49Min: 457.89 / Avg: 460.64 / Max: 462.93Min: 458.58 / Avg: 459.08 / Max: 460.03

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: Read11a1b1d1eNVIDIA Quadro RTX 4000RTX 4000NVIDIA RTX 400080160240320400SE +/- 0.03, N = 3SE +/- 0.06, N = 3SE +/- 0.03, N = 3SE +/- 0.00, N = 3SE +/- 0.03, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.03, N = 3379.7379.2379.2379.3379.3379.3379.3379.31. (CC) gcc options: -O2 -flto -lOpenCL
OpenBenchmarking.orgGB/s, More Is Bettercl-mem 2017-01-13Benchmark: Read11a1b1d1eNVIDIA Quadro RTX 4000RTX 4000NVIDIA RTX 400070140210280350Min: 379.7 / Avg: 379.73 / Max: 379.8Min: 379.1 / Avg: 379.2 / Max: 379.3Min: 379.2 / Avg: 379.23 / Max: 379.3Min: 379.3 / Avg: 379.3 / Max: 379.3Min: 379.2 / Avg: 379.27 / Max: 379.3Min: 379.3 / Avg: 379.3 / Max: 379.3Min: 379.3 / Avg: 379.3 / Max: 379.3Min: 379.2 / Avg: 379.27 / Max: 379.31. (CC) gcc options: -O2 -flto -lOpenCL

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: Double-Precision Double1eNVIDIA Quadro RTX 4000RTX 400060120180240300SE +/- 0.31, N = 3SE +/- 0.18, N = 3SE +/- 0.02, N = 3259.66259.50259.331. (CXX) g++ options: -O3 -rdynamic -lOpenCL
OpenBenchmarking.orgGFLOPS, More Is BetterclpeakOpenCL Test: Double-Precision Double1eNVIDIA Quadro RTX 4000RTX 400050100150200250Min: 259.32 / Avg: 259.66 / Max: 260.28Min: 259.3 / Avg: 259.5 / Max: 259.86Min: 259.31 / Avg: 259.33 / Max: 259.371. (CXX) g++ options: -O3 -rdynamic -lOpenCL

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 OpenCL11a1b1d1eNVIDIA Quadro RTX 4000RTX 4000NVIDIA RTX 400048121620SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 314.0314.0314.0414.0414.0314.0314.0314.031. (CXX) g++ options: -O3 -lOpenCL
OpenBenchmarking.orgms, Fewer Is BetterFinanceBench 2016-06-06Benchmark: Black-Scholes OpenCL11a1b1d1eNVIDIA Quadro RTX 4000RTX 4000NVIDIA RTX 400048121620Min: 14.03 / Avg: 14.03 / Max: 14.04Min: 14.03 / Avg: 14.03 / Max: 14.03Min: 14.03 / Avg: 14.04 / Max: 14.04Min: 14.03 / Avg: 14.04 / Max: 14.04Min: 14.03 / Avg: 14.03 / Max: 14.04Min: 14.03 / Avg: 14.03 / Max: 14.04Min: 14.03 / Avg: 14.03 / Max: 14.04Min: 14.03 / Avg: 14.03 / Max: 14.041. (CXX) g++ options: -O3 -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-v2-v2 - Model: mobilenet-v21eNVIDIA Quadro RTX 4000RTX 40000.3330.6660.9991.3321.665SE +/- 0.03, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 31.481.481.48MIN: 1.44 / MAX: 20.23MIN: 1.46 / MAX: 1.5MIN: 1.47 / MAX: 1.541. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU-v2-v2 - Model: mobilenet-v21eNVIDIA Quadro RTX 4000RTX 4000246810Min: 1.45 / Avg: 1.48 / Max: 1.55Min: 1.47 / Avg: 1.48 / Max: 1.48Min: 1.48 / Avg: 1.48 / Max: 1.481. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

NeatBench

NeatBench is a benchmark of the cross-platform Neat Video software on the CPU and optional GPU (OpenCL / CUDA) support. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterNeatBench 5Acceleration: GPU1eNVIDIA Quadro RTX 4000RTX 4000714212835SE +/- 0.66, N = 15SE +/- 0.69, N = 15SE +/- 0.63, N = 1531.030.930.2
OpenBenchmarking.orgFPS, More Is BetterNeatBench 5Acceleration: GPU1eNVIDIA Quadro RTX 4000RTX 4000714212835Min: 28.5 / Avg: 30.97 / Max: 35.4Min: 28.5 / Avg: 30.9 / Max: 35.3Min: 28.5 / Avg: 30.16 / Max: 34.7

Blender

Blender is an open-source 3D creation software project. This test is of Blender's Cycles benchmark with various sample files. GPU computing via OpenCL or CUDA is supported. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.90Blend File: BMW27 - Compute: NVIDIA OptiX1eNVIDIA Quadro RTX 4000RTX 4000714212835SE +/- 3.24, N = 15SE +/- 0.09, N = 3SE +/- 0.06, N = 332.1429.2329.14
OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.90Blend File: BMW27 - Compute: NVIDIA OptiX1eNVIDIA Quadro RTX 4000RTX 4000714212835Min: 28.81 / Avg: 32.14 / Max: 77.56Min: 29.05 / Avg: 29.23 / Max: 29.33Min: 29.03 / Avg: 29.14 / Max: 29.2

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-tiny1eNVIDIA Quadro RTX 4000RTX 4000246810SE +/- 0.37, N = 3SE +/- 0.09, N = 3SE +/- 0.00, N = 38.628.338.22MIN: 8.1 / MAX: 74.77MIN: 8.13 / MAX: 55.28MIN: 8.15 / MAX: 8.571. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: yolov4-tiny1eNVIDIA Quadro RTX 4000RTX 40003691215Min: 8.23 / Avg: 8.62 / Max: 9.36Min: 8.21 / Avg: 8.33 / Max: 8.51Min: 8.21 / Avg: 8.22 / Max: 8.221. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: resnet181eNVIDIA Quadro RTX 4000RTX 40000.43880.87761.31641.75522.194SE +/- 0.05, N = 2SE +/- 0.13, N = 3SE +/- 0.04, N = 31.801.951.77MIN: 1.69 / MAX: 21.82MIN: 1.7 / MAX: 20.49MIN: 1.71 / MAX: 24.181. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: resnet181eNVIDIA Quadro RTX 4000RTX 4000246810Min: 1.7 / Avg: 1.75 / Max: 1.8Min: 1.8 / Avg: 1.95 / Max: 2.21Min: 1.73 / Avg: 1.77 / Max: 1.851. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: mobilenet1eNVIDIA Quadro RTX 4000RTX 40001.09352.1873.28054.3745.4675SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.17, N = 34.664.674.86MIN: 4.6 / MAX: 4.86MIN: 4.64 / MAX: 4.75MIN: 4.64 / MAX: 71.231. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: Vulkan GPU - Model: mobilenet1eNVIDIA Quadro RTX 4000RTX 4000246810Min: 4.63 / Avg: 4.66 / Max: 4.68Min: 4.66 / Avg: 4.67 / Max: 4.68Min: 4.68 / Avg: 4.86 / Max: 5.21. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

LuxCoreRender OpenCL

LuxCoreRender is an open-source physically based renderer. This test profile is focused on running LuxCoreRender on OpenCL accelerators/GPUs. The alternative luxcorerender test profile is for CPU execution due to a difference in tests, etc. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender OpenCL 2.3Scene: Rainbow Colors and Prism1d1eNVIDIA Quadro RTX 4000RTX 40003691215SE +/- 0.34, N = 12SE +/- 0.02, N = 3SE +/- 0.06, N = 3SE +/- 0.02, N = 310.4210.7810.7910.73MIN: 3.45 / MAX: 11.19MIN: 10.09 / MAX: 11.23MIN: 10.45 / MAX: 11.21MIN: 9.75 / MAX: 11.24
OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender OpenCL 2.3Scene: Rainbow Colors and Prism1d1eNVIDIA Quadro RTX 4000RTX 40003691215Min: 6.73 / Avg: 10.42 / Max: 10.86Min: 10.75 / Avg: 10.78 / Max: 10.82Min: 10.68 / Avg: 10.79 / Max: 10.86Min: 10.71 / Avg: 10.73 / Max: 10.77

OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender OpenCL 2.3Scene: LuxCore Benchmark1d1eNVIDIA Quadro RTX 4000RTX 40000.78751.5752.36253.153.9375SE +/- 0.07, N = 12SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 33.403.503.473.47MIN: 0.17 / MAX: 3.97MIN: 0.27 / MAX: 4MIN: 0.27 / MAX: 3.96MIN: 0.33 / MAX: 3.96
OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender OpenCL 2.3Scene: LuxCore Benchmark1d1eNVIDIA Quadro RTX 4000RTX 4000246810Min: 2.69 / Avg: 3.4 / Max: 3.51Min: 3.46 / Avg: 3.5 / Max: 3.52Min: 3.46 / Avg: 3.47 / Max: 3.5Min: 3.43 / Avg: 3.47 / Max: 3.5

OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender OpenCL 2.3Scene: Food1d1eNVIDIA Quadro RTX 4000RTX 40000.35330.70661.05991.41321.7665SE +/- 0.04, N = 12SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 31.521.571.551.55MIN: 0.14 / MAX: 1.88MIN: 0.26 / MAX: 1.89MIN: 0.25 / MAX: 1.85MIN: 0.26 / MAX: 1.86
OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender OpenCL 2.3Scene: Food1d1eNVIDIA Quadro RTX 4000RTX 4000246810Min: 1.07 / Avg: 1.52 / Max: 1.58Min: 1.55 / Avg: 1.57 / Max: 1.58Min: 1.53 / Avg: 1.55 / Max: 1.56Min: 1.53 / Avg: 1.55 / Max: 1.56

OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender OpenCL 2.3Scene: DLSC1d1eNVIDIA Quadro RTX 4000RTX 40000.92031.84062.76093.68124.6015SE +/- 0.08, N = 12SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 33.994.094.014.02MIN: 1.12 / MAX: 4.22MIN: 3.82 / MAX: 4.25MIN: 3.83 / MAX: 4.21MIN: 3.82 / MAX: 4.2
OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender OpenCL 2.3Scene: DLSC1d1eNVIDIA Quadro RTX 4000RTX 4000246810Min: 3.09 / Avg: 3.99 / Max: 4.09Min: 4.08 / Avg: 4.09 / Max: 4.11Min: 3.99 / Avg: 4.01 / Max: 4.05Min: 4.02 / Avg: 4.02 / Max: 4.03