2

KVM testing on Ubuntu 20.04 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 2402237-NE-20860178071
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:

BLAS (Basic Linear Algebra Sub-Routine) Tests 3 Tests
C++ Boost Tests 2 Tests
CPU Massive 4 Tests
Creator Workloads 3 Tests
HPC - High Performance Computing 8 Tests
Machine Learning 5 Tests
Multi-Core 6 Tests
NVIDIA GPU Compute 20 Tests
OpenCL 6 Tests
OpenMPI Tests 2 Tests
Python Tests 2 Tests
Renderers 2 Tests
Scientific Computing 2 Tests
Server CPU Tests 2 Tests
Common Workstation Benchmarks 2 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
Performance Per
Dollar
Date
Run
  Test
  Duration
NVIDIA A100 80GB PCIe
February 23
  8 Hours, 52 Minutes
14 x Intel Xeon Gold 6342 - NVIDIA A100 80GB PCIe -
February 23
  6 Hours, 6 Minutes
Invert Hiding All Results Option
  7 Hours, 29 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):


2OpenBenchmarking.orgPhoronix Test Suite14 x Intel Xeon Gold 6342 (14 Cores)Nutanix AHV (nutanix-ahv-2.20220304.0.2619.el7 BIOS)Intel 440FX 82441FX PMC4 x 16384 MB RAM428GB VDISKNVIDIA A100 80GB PCIeRed Hat Virtio deviceUbuntu 20.045.4.0-172-generic (x86_64)NVIDIAOpenCL 3.0 CUDA 12.2.1481.3.242GCC 9.4.0 + CUDA 12.3ext41024x768KVMProcessorMotherboardChipsetMemoryDiskGraphicsNetworkOSKernelDisplay DriverOpenCLVulkanCompilerFile-SystemScreen ResolutionSystem Layer2 BenchmarksSystem Logs- Transparent Huge Pages: madvise- --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,gm2 --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-9-9QDOt0/gcc-9-9.4.0/debian/tmp-nvptx/usr,hsa --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v - CPU Microcode: 0x1- NVIDIA A100 80GB PCIe: BAR1 / Visible vRAM Size: 131072 MiB - vBIOS Version: 92.00.90.00.0f - NVIDIA A100 80GB PCIe: Python 3.8.10- gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Unknown: No mitigations + retbleed: 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 PBRSB-eIBRS: SW sequence + srbds: Not affected + tsx_async_abort: Not affected

NVIDIA A100 80GB PCIe vs. 14 x Intel Xeon Gold 6342 - NVIDIA A100 80GB PCIe - ComparisonPhoronix Test SuiteBaseline+1.7%+1.7%+3.4%+3.4%+5.1%+5.1%+6.8%+6.8%3.4%Vulkan GPU - FastestDet6.9%Vulkan GPU - blazeface5.1%Vulkan GPU - mnasnet5%Vulkan GPU-v2-v2 - mobilenet-v24.6%Vulkan GPU-v3-v3 - mobilenet-v33.8%Vulkan GPU - alexnetVulkan GPU - efficientnet-b02.9%Vulkan GPU - shufflenet-v22.1%NCNNNCNNNCNNNCNNNCNNNCNNNCNNNCNNNVIDIA A100 80GB PCIe14 x Intel Xeon Gold 6342 - NVIDIA A100 80GB PCIe -

2shoc: OpenCL - Max SP Flopsncnn: Vulkan GPU - mnasnetncnn: Vulkan GPU - FastestDetncnn: Vulkan GPU - vision_transformerncnn: Vulkan GPU - regnety_400mncnn: Vulkan GPU - squeezenet_ssdncnn: Vulkan GPU - yolov4-tinyncnn: Vulkan GPU - resnet50ncnn: Vulkan GPU - alexnetncnn: Vulkan GPU - resnet18ncnn: Vulkan GPU - vgg16ncnn: Vulkan GPU - googlenetncnn: Vulkan GPU - blazefacencnn: Vulkan GPU - efficientnet-b0ncnn: Vulkan GPU - shufflenet-v2ncnn: Vulkan GPU-v3-v3 - mobilenet-v3ncnn: Vulkan GPU-v2-v2 - mobilenet-v2ncnn: Vulkan GPU - mobilenetviennacl: CPU BLAS - dGEMM-TTviennacl: CPU BLAS - dGEMM-TNviennacl: CPU BLAS - dGEMM-NTviennacl: CPU BLAS - dGEMM-NNviennacl: CPU BLAS - dGEMV-Tviennacl: CPU BLAS - dGEMV-Nviennacl: CPU BLAS - dDOTviennacl: CPU BLAS - dAXPYviennacl: CPU BLAS - dCOPYviennacl: CPU BLAS - sDOTviennacl: CPU BLAS - sAXPYviennacl: CPU BLAS - sCOPYblender: BMW27 - NVIDIA OptiXfahbench: blender: Barbershop - NVIDIA OptiXblender: Fishy Cat - NVIDIA OptiXblender: Pabellon Barcelona - NVIDIA OptiXgromacs: NVIDIA CUDA GPU - water_GMX50_barecaffe: GoogleNet - NVIDIA CUDA - 1000blender: Classroom - NVIDIA OptiXviennacl: OpenCL BLAS - dGEMM-TTviennacl: OpenCL BLAS - dGEMM-TNviennacl: OpenCL BLAS - dGEMM-NTviennacl: OpenCL BLAS - dGEMM-NNviennacl: OpenCL BLAS - dGEMV-Tviennacl: OpenCL BLAS - dGEMV-Nviennacl: OpenCL BLAS - dDOTviennacl: OpenCL BLAS - dAXPYviennacl: OpenCL BLAS - dCOPYviennacl: OpenCL BLAS - sDOTviennacl: OpenCL BLAS - sAXPYviennacl: OpenCL BLAS - sCOPYcaffe: AlexNet - NVIDIA CUDA - 1000shoc: OpenCL - Texture Read Bandwidthcaffe: GoogleNet - NVIDIA CUDA - 200arrayfire: Conjugate Gradient OpenCLcaffe: GoogleNet - NVIDIA CUDA - 100mixbench: OpenCL - Integercl-mem: Writecl-mem: Copycl-mem: Readshoc: OpenCL - Triadfinancebench: Black-Scholes OpenCLclpeak: Global Memory Bandwidthcaffe: AlexNet - NVIDIA CUDA - 200clpeak: Single-Precision Floatshoc: OpenCL - Reductionshoc: OpenCL - FFT SPshoc: OpenCL - S3Dshoc: OpenCL - Bus Speed Readbackshoc: OpenCL - GEMM SGEMM_Ncaffe: AlexNet - NVIDIA CUDA - 100shoc: OpenCL - Bus Speed Downloadclpeak: Double-Precision Doubleclpeak: Integer Compute INTmixbench: OpenCL - Single Precisionmixbench: OpenCL - Double Precisionshoc: OpenCL - MD5 Hashredshift: NVIDIA A100 80GB PCIe14 x Intel Xeon Gold 6342 - NVIDIA A100 80GB PCIe -19366.24.405.1083.8211.3810.9322.4918.195.548.0032.1212.481.575.954.364.244.9914.7026.425.926.126.375.897.110711873.084.1178147.427.52258.597183.6422.3644.9925.61331538.720.82427042204653424324568.24355724402273122328505.731582.126316.841.9883190.9918824.221405.8234.8796.124.79601.0351495.361709.2319311.06236.0284423.01815.72626.401013470.7857.69225.30529689.0319208.7018866.429542.0942.75894.625.4585.1111.5111.0322.2018.235.368.0131.6712.591.656.124.454.405.2214.79OpenBenchmarking.org

SHOC Scalable HeterOgeneous Computing

The CUDA and OpenCL version of Vetter's Scalable HeterOgeneous Computing benchmark suite. SHOC provides a number of different benchmark programs for evaluating the performance and stability of compute devices. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGFLOPS, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: Max SP FlopsNVIDIA A100 80GB PCIe4K8K12K16K20KSE +/- 4.11, N = 319366.21. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -lmpi_cxx -lmpi

NCNN

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

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: mnasnet14 x Intel Xeon Gold 6342 - NVIDIA A100 80GB PCIe -NVIDIA A100 80GB PCIe1.03952.0793.11854.1585.1975SE +/- 0.07, N = 15SE +/- 0.07, N = 144.624.40MIN: 4.03 / MAX: 5.52MIN: 3.88 / MAX: 5.281. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: FastestDet14 x Intel Xeon Gold 6342 - NVIDIA A100 80GB PCIe -NVIDIA A100 80GB PCIe1.22632.45263.67894.90526.1315SE +/- 0.13, N = 15SE +/- 0.16, N = 145.455.10MIN: 4.21 / MAX: 7.84MIN: 3.96 / MAX: 7.171. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: vision_transformer14 x Intel Xeon Gold 6342 - NVIDIA A100 80GB PCIe -NVIDIA A100 80GB PCIe20406080100SE +/- 0.43, N = 15SE +/- 0.54, N = 1585.1183.82MIN: 80.72 / MAX: 98.92MIN: 80.45 / MAX: 98.961. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: regnety_400m14 x Intel Xeon Gold 6342 - NVIDIA A100 80GB PCIe -NVIDIA A100 80GB PCIe3691215SE +/- 0.12, N = 15SE +/- 0.06, N = 1511.5111.38MIN: 10.62 / MAX: 12.43MIN: 10.87 / MAX: 14.111. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: squeezenet_ssd14 x Intel Xeon Gold 6342 - NVIDIA A100 80GB PCIe -NVIDIA A100 80GB PCIe3691215SE +/- 0.12, N = 15SE +/- 0.08, N = 1511.0310.93MIN: 10.02 / MAX: 13.51MIN: 10.12 / MAX: 11.681. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: yolov4-tiny14 x Intel Xeon Gold 6342 - NVIDIA A100 80GB PCIe -NVIDIA A100 80GB PCIe510152025SE +/- 0.17, N = 15SE +/- 0.06, N = 1522.2022.49MIN: 20.51 / MAX: 26.86MIN: 21.4 / MAX: 30.451. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: resnet5014 x Intel Xeon Gold 6342 - NVIDIA A100 80GB PCIe -NVIDIA A100 80GB PCIe48121620SE +/- 0.13, N = 15SE +/- 0.11, N = 1518.2318.19MIN: 17.21 / MAX: 33.45MIN: 17.46 / MAX: 19.771. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: alexnet14 x Intel Xeon Gold 6342 - NVIDIA A100 80GB PCIe -NVIDIA A100 80GB PCIe1.24652.4933.73954.9866.2325SE +/- 0.05, N = 15SE +/- 0.04, N = 155.365.54MIN: 4.8 / MAX: 6.09MIN: 5.23 / MAX: 8.321. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: resnet1814 x Intel Xeon Gold 6342 - NVIDIA A100 80GB PCIe -NVIDIA A100 80GB PCIe246810SE +/- 0.08, N = 15SE +/- 0.08, N = 158.018.00MIN: 7.25 / MAX: 10.22MIN: 7.36 / MAX: 13.061. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: vgg1614 x Intel Xeon Gold 6342 - NVIDIA A100 80GB PCIe -NVIDIA A100 80GB PCIe714212835SE +/- 0.13, N = 15SE +/- 0.20, N = 1531.6732.12MIN: 29.72 / MAX: 41.37MIN: 30.68 / MAX: 41.361. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: googlenet14 x Intel Xeon Gold 6342 - NVIDIA A100 80GB PCIe -NVIDIA A100 80GB PCIe3691215SE +/- 0.19, N = 15SE +/- 0.12, N = 1512.5912.48MIN: 11.13 / MAX: 14.43MIN: 11.64 / MAX: 14.981. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: blazeface14 x Intel Xeon Gold 6342 - NVIDIA A100 80GB PCIe -NVIDIA A100 80GB PCIe0.37130.74261.11391.48521.8565SE +/- 0.03, N = 15SE +/- 0.03, N = 151.651.57MIN: 1.4 / MAX: 2.22MIN: 1.39 / MAX: 1.851. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: efficientnet-b014 x Intel Xeon Gold 6342 - NVIDIA A100 80GB PCIe -NVIDIA A100 80GB PCIe246810SE +/- 0.06, N = 15SE +/- 0.04, N = 156.125.95MIN: 5.57 / MAX: 6.88MIN: 5.48 / MAX: 6.651. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: shufflenet-v214 x Intel Xeon Gold 6342 - NVIDIA A100 80GB PCIe -NVIDIA A100 80GB PCIe1.00132.00263.00394.00525.0065SE +/- 0.04, N = 14SE +/- 0.04, N = 154.454.36MIN: 4.05 / MAX: 5.16MIN: 3.94 / MAX: 4.81. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU-v3-v3 - Model: mobilenet-v314 x Intel Xeon Gold 6342 - NVIDIA A100 80GB PCIe -NVIDIA A100 80GB PCIe0.991.982.973.964.95SE +/- 0.05, N = 15SE +/- 0.05, N = 154.404.24MIN: 3.99 / MAX: 5.34MIN: 3.74 / MAX: 4.841. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU-v2-v2 - Model: mobilenet-v214 x Intel Xeon Gold 6342 - NVIDIA A100 80GB PCIe -NVIDIA A100 80GB PCIe1.17452.3493.52354.6985.8725SE +/- 0.10, N = 15SE +/- 0.07, N = 155.224.99MIN: 4.03 / MAX: 13.71MIN: 4.53 / MAX: 6.411. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: Vulkan GPU - Model: mobilenet14 x Intel Xeon Gold 6342 - NVIDIA A100 80GB PCIe -NVIDIA A100 80GB PCIe48121620SE +/- 0.20, N = 15SE +/- 0.10, N = 1514.7914.70MIN: 13.45 / MAX: 16.57MIN: 13.6 / MAX: 50.61. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

ViennaCL

ViennaCL is an open-source linear algebra library written in C++ and with support for OpenCL and OpenMP. This test profile makes use of ViennaCL's built-in benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGFLOPs/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - dGEMM-TTNVIDIA A100 80GB PCIe612182430SE +/- 0.09, N = 1526.41. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGFLOPs/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - dGEMM-TNNVIDIA A100 80GB PCIe612182430SE +/- 0.08, N = 1425.91. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGFLOPs/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - dGEMM-NTNVIDIA A100 80GB PCIe612182430SE +/- 0.08, N = 1526.11. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGFLOPs/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - dGEMM-NNNVIDIA A100 80GB PCIe612182430SE +/- 0.09, N = 1526.31. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - dGEMV-TNVIDIA A100 80GB PCIe20406080100SE +/- 0.26, N = 1575.81. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - dGEMV-NNVIDIA A100 80GB PCIe20406080100SE +/- 0.78, N = 1597.11. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - dDOTNVIDIA A100 80GB PCIe20406080100SE +/- 1.25, N = 151071. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - dAXPYNVIDIA A100 80GB PCIe306090120150SE +/- 1.03, N = 151181. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - dCOPYNVIDIA A100 80GB PCIe1632486480SE +/- 0.65, N = 1573.01. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - sDOTNVIDIA A100 80GB PCIe20406080100SE +/- 0.26, N = 1584.11. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - sAXPYNVIDIA A100 80GB PCIe4080120160200SE +/- 5.09, N = 141781. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: CPU BLAS - sCOPYNVIDIA A100 80GB PCIe306090120150SE +/- 11.32, N = 15147.41. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

Blender

Blender is an open-source 3D creation and modeling software project. This test is of Blender's Cycles performance with various sample files. GPU computing via NVIDIA OptiX and NVIDIA CUDA is currently supported as well as HIP for AMD Radeon GPUs and Intel oneAPI for Intel Graphics. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.0Blend File: BMW27 - Compute: NVIDIA OptiXNVIDIA A100 80GB PCIe612182430SE +/- 16.82, N = 1427.52

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 2.3.2NVIDIA A100 80GB PCIe60120180240300SE +/- 0.28, N = 3258.60

Blender

Blender is an open-source 3D creation and modeling software project. This test is of Blender's Cycles performance with various sample files. GPU computing via NVIDIA OptiX and NVIDIA CUDA is currently supported as well as HIP for AMD Radeon GPUs and Intel oneAPI for Intel Graphics. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.0Blend File: Barbershop - Compute: NVIDIA OptiXNVIDIA A100 80GB PCIe20406080100SE +/- 0.14, N = 383.64

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.0Blend File: Fishy Cat - Compute: NVIDIA OptiXNVIDIA A100 80GB PCIe510152025SE +/- 0.20, N = 822.36

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.0Blend File: Pabellon Barcelona - Compute: NVIDIA OptiXNVIDIA A100 80GB PCIe1020304050SE +/- 0.02, N = 344.99

GROMACS

The GROMACS (GROningen MAchine for Chemical Simulations) molecular dynamics package testing with the water_GMX50 data. This test profile allows selecting between CPU and GPU-based GROMACS builds. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgNs Per Day, More Is BetterGROMACS 2024Implementation: NVIDIA CUDA GPU - Input: water_GMX50_bareNVIDIA A100 80GB PCIe612182430SE +/- 0.03, N = 325.611. (CXX) g++ options: -O3 -lm

Caffe

This is a benchmark of the Caffe deep learning framework and currently supports the AlexNet and Googlenet model and execution on both CPUs and NVIDIA GPUs. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMilli-Seconds, Fewer Is BetterCaffe 2020-02-13Model: GoogleNet - Acceleration: NVIDIA CUDA - Iterations: 1000NVIDIA A100 80GB PCIe7K14K21K28K35KSE +/- 22.82, N = 331538.71. (CXX) g++ options: -fPIC -O3 -rdynamic -lglog -lgflags -lprotobuf -lpthread -lsz -lz -ldl -lm -llmdb -lopenblas

Blender

Blender is an open-source 3D creation and modeling software project. This test is of Blender's Cycles performance with various sample files. GPU computing via NVIDIA OptiX and NVIDIA CUDA is currently supported as well as HIP for AMD Radeon GPUs and Intel oneAPI for Intel Graphics. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.0Blend File: Classroom - Compute: NVIDIA OptiXNVIDIA A100 80GB PCIe510152025SE +/- 0.02, N = 320.82

ViennaCL

ViennaCL is an open-source linear algebra library written in C++ and with support for OpenCL and OpenMP. This test profile makes use of ViennaCL's built-in benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGFLOPs/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - dGEMM-TTNVIDIA A100 80GB PCIe900180027003600450042701. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGFLOPs/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - dGEMM-TNNVIDIA A100 80GB PCIe900180027003600450042201. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGFLOPs/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - dGEMM-NTNVIDIA A100 80GB PCIe10002000300040005000SE +/- 3.33, N = 346531. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGFLOPs/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - dGEMM-NNNVIDIA A100 80GB PCIe9001800270036004500SE +/- 3.33, N = 342431. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - dGEMV-TNVIDIA A100 80GB PCIe501001502002502451. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - dGEMV-NNVIDIA A100 80GB PCIe1530456075SE +/- 0.03, N = 368.21. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - dDOTNVIDIA A100 80GB PCIe901802703604504351. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - dAXPYNVIDIA A100 80GB PCIe1202403604806005721. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - dCOPYNVIDIA A100 80GB PCIe1002003004005004401. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - sDOTNVIDIA A100 80GB PCIe501001502002502271. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - sAXPYNVIDIA A100 80GB PCIe701402102803503121. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

OpenBenchmarking.orgGB/s, More Is BetterViennaCL 1.7.1Test: OpenCL BLAS - sCOPYNVIDIA A100 80GB PCIe501001502002502321. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL

LuxCoreRender

LuxCoreRender is an open-source 3D physically based renderer formerly known as LuxRender. LuxCoreRender supports CPU-based rendering as well as GPU acceleration via OpenCL, NVIDIA CUDA, and NVIDIA OptiX interfaces. Learn more via the OpenBenchmarking.org test page.

Scene: LuxCore Benchmark - Acceleration: GPU

NVIDIA A100 80GB PCIe: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: RUNTIME ERROR: CUDA driver API error CUDA_ERROR_UNSUPPORTED_PTX_VERSION (code: 222, file:/home/vsts/work/1/s/LinuxCompile/LuxCore-sdk/src/luxrays/utils/cuda.cpp, line: 251): the provided PTX was compiled with an unsupported toolchain.

Scene: Danish Mood - Acceleration: GPU

NVIDIA A100 80GB PCIe: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: RUNTIME ERROR: CUDA driver API error CUDA_ERROR_UNSUPPORTED_PTX_VERSION (code: 222, file:/home/vsts/work/1/s/LinuxCompile/LuxCore-sdk/src/luxrays/utils/cuda.cpp, line: 251): the provided PTX was compiled with an unsupported toolchain.

Caffe

This is a benchmark of the Caffe deep learning framework and currently supports the AlexNet and Googlenet model and execution on both CPUs and NVIDIA GPUs. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMilli-Seconds, Fewer Is BetterCaffe 2020-02-13Model: AlexNet - Acceleration: NVIDIA CUDA - Iterations: 1000NVIDIA A100 80GB PCIe2K4K6K8K10KSE +/- 15.42, N = 38505.731. (CXX) g++ options: -fPIC -O3 -rdynamic -lglog -lgflags -lprotobuf -lpthread -lsz -lz -ldl -lm -llmdb -lopenblas

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.

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

NVIDIA A100 80GB PCIe: The test run did not produce a result. The test run did not produce a result. The test run did not produce a result.

SHOC Scalable HeterOgeneous Computing

The CUDA and OpenCL version of Vetter's Scalable HeterOgeneous Computing benchmark suite. SHOC provides a number of different benchmark programs for evaluating the performance and stability of compute devices. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGB/s, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: Texture Read BandwidthNVIDIA A100 80GB PCIe30060090012001500SE +/- 0.32, N = 31582.121. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -lmpi_cxx -lmpi

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.

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

NVIDIA A100 80GB PCIe: The test run did not produce a result. The test run did not produce a result. The test run did not produce a result.

Caffe

This is a benchmark of the Caffe deep learning framework and currently supports the AlexNet and Googlenet model and execution on both CPUs and NVIDIA GPUs. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMilli-Seconds, Fewer Is BetterCaffe 2020-02-13Model: GoogleNet - Acceleration: NVIDIA CUDA - Iterations: 200NVIDIA A100 80GB PCIe14002800420056007000SE +/- 3.90, N = 36316.841. (CXX) g++ options: -fPIC -O3 -rdynamic -lglog -lgflags -lprotobuf -lpthread -lsz -lz -ldl -lm -llmdb -lopenblas

LuxCoreRender

LuxCoreRender is an open-source 3D physically based renderer formerly known as LuxRender. LuxCoreRender supports CPU-based rendering as well as GPU acceleration via OpenCL, NVIDIA CUDA, and NVIDIA OptiX interfaces. Learn more via the OpenBenchmarking.org test page.

Scene: DLSC - Acceleration: GPU

NVIDIA A100 80GB PCIe: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: RUNTIME ERROR: CUDA driver API error CUDA_ERROR_UNSUPPORTED_PTX_VERSION (code: 222, file:/home/vsts/work/1/s/LinuxCompile/LuxCore-sdk/src/luxrays/utils/cuda.cpp, line: 251): the provided PTX was compiled with an unsupported toolchain.

Scene: Orange Juice - Acceleration: GPU

NVIDIA A100 80GB PCIe: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: RUNTIME ERROR: CUDA driver API error CUDA_ERROR_UNSUPPORTED_PTX_VERSION (code: 222, file:/home/vsts/work/1/s/LinuxCompile/LuxCore-sdk/src/luxrays/utils/cuda.cpp, line: 251): the provided PTX was compiled with an unsupported toolchain.

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 3.9Test: Conjugate Gradient OpenCLNVIDIA A100 80GB PCIe0.44730.89461.34191.78922.2365SE +/- 0.006, N = 31.9881. (CXX) g++ options: -O3

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.

Benchmark: MD5

NVIDIA A100 80GB PCIe: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ptxas application ptx input, line 9; fatal : Unsupported .version 8.3; current version is '8.2'

Caffe

This is a benchmark of the Caffe deep learning framework and currently supports the AlexNet and Googlenet model and execution on both CPUs and NVIDIA GPUs. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMilli-Seconds, Fewer Is BetterCaffe 2020-02-13Model: GoogleNet - Acceleration: NVIDIA CUDA - Iterations: 100NVIDIA A100 80GB PCIe7001400210028003500SE +/- 11.28, N = 33190.991. (CXX) g++ options: -fPIC -O3 -rdynamic -lglog -lgflags -lprotobuf -lpthread -lsz -lz -ldl -lm -llmdb -lopenblas

Mixbench

A benchmark suite for GPUs on mixed operational intensity kernels. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGIOPS, More Is BetterMixbench 2020-06-23Backend: OpenCL - Benchmark: IntegerNVIDIA A100 80GB PCIe4K8K12K16K20KSE +/- 21.05, N = 318824.221. (CXX) g++ options: -lm -lstdc++ -lOpenCL -lrt -O2

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.

Benchmark: SHA-512

NVIDIA A100 80GB PCIe: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ptxas application ptx input, line 9; fatal : Unsupported .version 8.3; current version is '8.2'

Benchmark: SHA1

NVIDIA A100 80GB PCIe: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ptxas application ptx input, line 9; fatal : Unsupported .version 8.3; current version is '8.2'

Benchmark: 7-Zip

NVIDIA A100 80GB PCIe: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ptxas application ptx input, line 9; fatal : Unsupported .version 8.3; current version is '8.2'

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: WriteNVIDIA A100 80GB PCIe30060090012001500SE +/- 0.65, N = 31405.81. (CC) gcc options: -O2 -flto -lOpenCL

OpenBenchmarking.orgGB/s, More Is Bettercl-mem 2017-01-13Benchmark: CopyNVIDIA A100 80GB PCIe50100150200250SE +/- 0.03, N = 3234.81. (CC) gcc options: -O2 -flto -lOpenCL

OpenBenchmarking.orgGB/s, More Is Bettercl-mem 2017-01-13Benchmark: ReadNVIDIA A100 80GB PCIe2004006008001000SE +/- 0.32, N = 3796.11. (CC) gcc options: -O2 -flto -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.

Benchmark: TrueCrypt RIPEMD160 + XTS

NVIDIA A100 80GB PCIe: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ptxas application ptx input, line 9; fatal : Unsupported .version 8.3; current version is '8.2'

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.

FP16: Yes - Mode: Inference - Network: Mobilenet - Device: OpenCL

NVIDIA A100 80GB PCIe: The test run did not produce a result. The test run did not produce a result. The test run did not produce a result.

SHOC Scalable HeterOgeneous Computing

The CUDA and OpenCL version of Vetter's Scalable HeterOgeneous Computing benchmark suite. SHOC provides a number of different benchmark programs for evaluating the performance and stability of compute devices. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGB/s, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: TriadNVIDIA A100 80GB PCIe612182430SE +/- 0.02, N = 324.801. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -lmpi_cxx -lmpi

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.

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

NVIDIA A100 80GB PCIe: The test run did not produce a result. The test run did not produce a result. The test run did not produce a result.

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

NVIDIA A100 80GB PCIe: The test run did not produce a result. The test run did not produce a result. The test run did not produce a result.

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 OpenCLNVIDIA A100 80GB PCIe0.23290.46580.69870.93161.1645SE +/- 0.009, N = 61.0351. (CXX) g++ options: -O3 -march=native -fopenmp

clpeak

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

OpenBenchmarking.orgGBPS, More Is Betterclpeak 1.1.2OpenCL Test: Global Memory BandwidthNVIDIA A100 80GB PCIe30060090012001500SE +/- 0.08, N = 31495.361. (CXX) g++ options: -O3

Caffe

This is a benchmark of the Caffe deep learning framework and currently supports the AlexNet and Googlenet model and execution on both CPUs and NVIDIA GPUs. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMilli-Seconds, Fewer Is BetterCaffe 2020-02-13Model: AlexNet - Acceleration: NVIDIA CUDA - Iterations: 200NVIDIA A100 80GB PCIe400800120016002000SE +/- 2.64, N = 31709.231. (CXX) g++ options: -fPIC -O3 -rdynamic -lglog -lgflags -lprotobuf -lpthread -lsz -lz -ldl -lm -llmdb -lopenblas

clpeak

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

OpenBenchmarking.orgGFLOPS, More Is Betterclpeak 1.1.2OpenCL Test: Single-Precision FloatNVIDIA A100 80GB PCIe4K8K12K16K20KSE +/- 10.20, N = 319311.061. (CXX) g++ options: -O3

SHOC Scalable HeterOgeneous Computing

The CUDA and OpenCL version of Vetter's Scalable HeterOgeneous Computing benchmark suite. SHOC provides a number of different benchmark programs for evaluating the performance and stability of compute devices. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGB/s, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: ReductionNVIDIA A100 80GB PCIe50100150200250SE +/- 2.10, N = 3236.031. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -lmpi_cxx -lmpi

OpenBenchmarking.orgGFLOPS, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: FFT SPNVIDIA A100 80GB PCIe9001800270036004500SE +/- 7.20, N = 34423.011. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -lmpi_cxx -lmpi

OpenBenchmarking.orgGFLOPS, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: S3DNVIDIA A100 80GB PCIe2004006008001000SE +/- 2.56, N = 3815.731. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -lmpi_cxx -lmpi

OpenBenchmarking.orgGB/s, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: Bus Speed ReadbackNVIDIA A100 80GB PCIe612182430SE +/- 0.00, N = 326.401. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -lmpi_cxx -lmpi

OpenBenchmarking.orgGFLOPS, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: GEMM SGEMM_NNVIDIA A100 80GB PCIe3K6K9K12K15KSE +/- 2.22, N = 313470.71. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -lmpi_cxx -lmpi

Caffe

This is a benchmark of the Caffe deep learning framework and currently supports the AlexNet and Googlenet model and execution on both CPUs and NVIDIA GPUs. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMilli-Seconds, Fewer Is BetterCaffe 2020-02-13Model: AlexNet - Acceleration: NVIDIA CUDA - Iterations: 100NVIDIA A100 80GB PCIe2004006008001000SE +/- 0.45, N = 3857.691. (CXX) g++ options: -fPIC -O3 -rdynamic -lglog -lgflags -lprotobuf -lpthread -lsz -lz -ldl -lm -llmdb -lopenblas

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.

Acceleration: GPU

NVIDIA A100 80GB PCIe: The test run did not produce a result. The test run did not produce a result. The test run did not produce a result.

Rodinia

Rodinia is a suite focused upon accelerating compute-intensive applications with accelerators. CUDA, OpenMP, and OpenCL parallel models are supported by the included applications. This profile utilizes select OpenCL, NVIDIA CUDA and OpenMP test binaries at the moment. Learn more via the OpenBenchmarking.org test page.

Test: OpenCL Particle Filter

NVIDIA A100 80GB PCIe: The test run did not produce a result. The test run did not produce a result. The test run did not produce a result. E: ERROR: clEnqueueWriteBuffer arrayX_GPU (size:400000) => -2002801765

SHOC Scalable HeterOgeneous Computing

The CUDA and OpenCL version of Vetter's Scalable HeterOgeneous Computing benchmark suite. SHOC provides a number of different benchmark programs for evaluating the performance and stability of compute devices. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGB/s, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: Bus Speed DownloadNVIDIA A100 80GB PCIe612182430SE +/- 0.00, N = 325.311. (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 Betterclpeak 1.1.2OpenCL Test: Double-Precision DoubleNVIDIA A100 80GB PCIe2K4K6K8K10KSE +/- 3.43, N = 39689.031. (CXX) g++ options: -O3

OpenBenchmarking.orgGIOPS, More Is Betterclpeak 1.1.2OpenCL Test: Integer Compute INTNVIDIA A100 80GB PCIe4K8K12K16K20KSE +/- 22.16, N = 319208.701. (CXX) g++ options: -O3

Mixbench

A benchmark suite for GPUs on mixed operational intensity kernels. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGFLOPS, More Is BetterMixbench 2020-06-23Backend: OpenCL - Benchmark: Single PrecisionNVIDIA A100 80GB PCIe4K8K12K16K20KSE +/- 0.00, N = 318866.421. (CXX) g++ options: -lm -lstdc++ -lOpenCL -lrt -O2

OpenBenchmarking.orgGFLOPS, More Is BetterMixbench 2020-06-23Backend: OpenCL - Benchmark: Double PrecisionNVIDIA A100 80GB PCIe2K4K6K8K10KSE +/- 1.80, N = 39542.091. (CXX) g++ options: -lm -lstdc++ -lOpenCL -lrt -O2

SHOC Scalable HeterOgeneous Computing

The CUDA and OpenCL version of Vetter's Scalable HeterOgeneous Computing benchmark suite. SHOC provides a number of different benchmark programs for evaluating the performance and stability of compute devices. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGHash/s, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: MD5 HashNVIDIA A100 80GB PCIe1020304050SE +/- 0.00, N = 342.761. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -lmpi_cxx -lmpi

LuxCoreRender

LuxCoreRender is an open-source 3D physically based renderer formerly known as LuxRender. LuxCoreRender supports CPU-based rendering as well as GPU acceleration via OpenCL, NVIDIA CUDA, and NVIDIA OptiX interfaces. Learn more via the OpenBenchmarking.org test page.

Scene: Rainbow Colors and Prism - Acceleration: GPU

NVIDIA A100 80GB PCIe: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: RUNTIME ERROR: CUDA driver API error CUDA_ERROR_UNSUPPORTED_PTX_VERSION (code: 222, file:/home/vsts/work/1/s/LinuxCompile/LuxCore-sdk/src/luxrays/utils/cuda.cpp, line: 251): the provided PTX was compiled with an unsupported toolchain.

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.

OpenCL Device: GPU

NVIDIA A100 80GB PCIe: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status.

Mixbench

A benchmark suite for GPUs on mixed operational intensity kernels. Learn more via the OpenBenchmarking.org test page.

Backend: NVIDIA CUDA - Benchmark: Single Precision

NVIDIA A100 80GB PCIe: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status.

Backend: NVIDIA CUDA - Benchmark: Half Precision

NVIDIA A100 80GB PCIe: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status.

Backend: NVIDIA CUDA - Benchmark: Double Precision

NVIDIA A100 80GB PCIe: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status.

Backend: NVIDIA CUDA - Benchmark: Integer

NVIDIA A100 80GB PCIe: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status.

LeelaChessZero

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

Backend: OpenCL

NVIDIA A100 80GB PCIe: The test run did not produce a result. The test run did not produce a result. The test run did not produce a result.

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.

NVIDIA A100 80GB PCIe: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ./redshift: 3: /usr/redshift/bin/redshiftBenchmark: not found

76 Results Shown

SHOC Scalable HeterOgeneous Computing
NCNN:
  Vulkan GPU - mnasnet
  Vulkan GPU - FastestDet
  Vulkan GPU - vision_transformer
  Vulkan GPU - regnety_400m
  Vulkan GPU - squeezenet_ssd
  Vulkan GPU - yolov4-tiny
  Vulkan GPU - resnet50
  Vulkan GPU - alexnet
  Vulkan GPU - resnet18
  Vulkan GPU - vgg16
  Vulkan GPU - googlenet
  Vulkan GPU - blazeface
  Vulkan GPU - efficientnet-b0
  Vulkan GPU - shufflenet-v2
  Vulkan GPU-v3-v3 - mobilenet-v3
  Vulkan GPU-v2-v2 - mobilenet-v2
  Vulkan GPU - mobilenet
ViennaCL:
  CPU BLAS - dGEMM-TT
  CPU BLAS - dGEMM-TN
  CPU BLAS - dGEMM-NT
  CPU BLAS - dGEMM-NN
  CPU BLAS - dGEMV-T
  CPU BLAS - dGEMV-N
  CPU BLAS - dDOT
  CPU BLAS - dAXPY
  CPU BLAS - dCOPY
  CPU BLAS - sDOT
  CPU BLAS - sAXPY
  CPU BLAS - sCOPY
Blender
FAHBench
Blender:
  Barbershop - NVIDIA OptiX
  Fishy Cat - NVIDIA OptiX
  Pabellon Barcelona - NVIDIA OptiX
GROMACS
Caffe
Blender
ViennaCL:
  OpenCL BLAS - dGEMM-TT
  OpenCL BLAS - dGEMM-TN
  OpenCL BLAS - dGEMM-NT
  OpenCL BLAS - dGEMM-NN
  OpenCL BLAS - dGEMV-T
  OpenCL BLAS - dGEMV-N
  OpenCL BLAS - dDOT
  OpenCL BLAS - dAXPY
  OpenCL BLAS - dCOPY
  OpenCL BLAS - sDOT
  OpenCL BLAS - sAXPY
  OpenCL BLAS - sCOPY
Caffe
SHOC Scalable HeterOgeneous Computing
Caffe
ArrayFire
Caffe
Mixbench
cl-mem:
  Write
  Copy
  Read
SHOC Scalable HeterOgeneous Computing
FinanceBench
clpeak
Caffe
clpeak
SHOC Scalable HeterOgeneous Computing:
  OpenCL - Reduction
  OpenCL - FFT SP
  OpenCL - S3D
  OpenCL - Bus Speed Readback
  OpenCL - GEMM SGEMM_N
Caffe
SHOC Scalable HeterOgeneous Computing
clpeak:
  Double-Precision Double
  Integer Compute INT
Mixbench:
  OpenCL - Single Precision
  OpenCL - Double Precision
SHOC Scalable HeterOgeneous Computing