NVIDIA GeForce RTX 2070 Linux Compute Benchmarks

NVIDIA GeForce RTX 2070 Ubuntu Linux compute OpenCL CUDA TensorFlow benchmarks. Tests by Michael Larabel for a future article on Phoronix.com.

HTML result view exported from: https://openbenchmarking.org/result/1810180-SK-GPGPUCOMP97&sro&grt.

NVIDIA GeForce RTX 2070 Linux Compute BenchmarksProcessorMotherboardChipsetMemoryDiskGraphicsAudioMonitorNetworkOSKernelDesktopDisplay ServerDisplay DriverOpenGLOpenCLCompilerFile-SystemScreen ResolutionRX 580R9 FuryRX Vega 56RX Vega 64GTX 970GTX 980GTX TITAN XGTX 1070GTX 1070 TiGTX 1080GTX 1080 TiRTX 2070RTX 2080 TiAMD Ryzen Threadripper 2990WX 32-Core @ 3.00GHz (32 Cores / 64 Threads)ASUS ROG ZENITH EXTREME (1402 BIOS)AMD Family 17h32768MBSamsung SSD 970 EVO 500GBMSI AMD Radeon RX 580 8GBRealtek ALC1220ASUS VP28UIntel I211 Gigabit ConnectionUbuntu 18.044.18.0-041800-generic (x86_64)GNOME Shell 3.28.3X Server 1.19.6modesetting 1.19.64.5 Mesa 18.0.5 (LLVM 6.0.0)OpenCL 2.1 AMD-APP (2679.0)GCC 7.3.0ext43840x2160Sapphire AMD Radeon 4GBAMD Radeon RX Vega 8GBeVGA NVIDIA GeForce GTX 970 4GB (1163/3505MHz)NVIDIA 410.664.6.0OpenCL 1.2 CUDA 10.0.175GCC 7.3.0 + CUDA 10.0NVIDIA GeForce GTX 980 4GB (1126/3505MHz)NVIDIA GeForce GTX TITAN X 12GB (1001/3505MHz)NVIDIA GeForce GTX 1070 8GB (1506/4006MHz)Zotac NVIDIA GeForce GTX 1070 Ti 8GB (1607/4006MHz)NVIDIA GeForce GTX 1080 8GB (1607/5005MHz)NVIDIA GeForce GTX 1080 Ti 11GB (1480/5508MHz)eVGA NVIDIA GeForce RTX 2070 8GB (1410/7000MHz)NVIDIA GeForce RTX 2080 Ti 11GB (1350/7000MHz)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++ --enable-libmpx --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none --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 --with-tune=generic --without-cuda-driver -v Processor Details- Scaling Governor: acpi-cpufreq ondemandSecurity Details- __user pointer sanitization + Full AMD retpoline IBPB + SSB disabled via prctl and seccompOpenCL Details- GTX 970: GPU Compute Cores: 1664- GTX 980: GPU Compute Cores: 2048- GTX TITAN X: GPU Compute Cores: 3072- GTX 1070: GPU Compute Cores: 1920- GTX 1070 Ti: GPU Compute Cores: 2432- GTX 1080: GPU Compute Cores: 2560- GTX 1080 Ti: GPU Compute Cores: 3584- RTX 2070: GPU Compute Cores: 2304- RTX 2080 Ti: GPU Compute Cores: 4352Python Details- GTX 970, GTX 980, GTX TITAN X, GTX 1070, GTX 1070 Ti, GTX 1080, GTX 1080 Ti, RTX 2070: Python 2.7.15rc1 + Python 3.6.6

NVIDIA GeForce RTX 2070 Linux Compute Benchmarksaskap: Degriddingv-ray: CUDA GPUclpeak: Integer Compute INTcuda-mini-nbody: Originalngc-tensorflow: ResNet-50, FP16ngc-tensorflow: ResNet-50, FP32ngc-tensorflow: AlexNet, FP16ngc-tensorflow: AlexNet, FP32ngc-tensorflow: Googlenet, FP16ngc-tensorflow: Inception v4, FP16ngc-tensorflow: VGG-16, FP16ngc-tensorflow: VGG-16, FP32parboil: OpenCL TPACFshoc: OpenCL - FFT SPshoc: OpenCL - MD5 HashRX 580R9 FuryRX Vega 56RX Vega 64GTX 970GTX 980GTX TITAN XGTX 1070GTX 1070 TiGTX 1080GTX 1080 TiRTX 2070RTX 2080 Ti12535468.0614308219.20198492912.41250293116.439291120.57114251.7110459981.594076.4710650107.78131445.90120311461.554597.491775078.72180533.551521231648157537142.6378.2772.831.4972610.301354687.99171039.691581241549150437443.9077.1371.701.2455010.671378083.03233931.911851361773166044852.9389.3379.031.2055613.661427383.41243932.761901411856174645453.8392.9782.771.2165414.312218866.85329221.232652072635249962272.17131.27119.270.9398319.962581966.55815017.712951812714211064185.20138.3390.671.03101519.283803753.911467911.22428276433032779861232041500.82144334.87OpenBenchmarking.org

ASKAP tConvolveCuda

Processing: Degridding

OpenBenchmarking.orgMillion Grid Points Per Second, More Is BetterASKAP tConvolveCuda 2015-11-10Processing: DegriddingGTX 1070GTX 1070 TiGTX 1080GTX 1080 TiGTX 970GTX 980GTX TITAN XRTX 2070RTX 2080 Ti8K16K24K32K40KSE +/- 233.57, N = 3SE +/- 233.57, N = 3SE +/- 259.50, N = 3SE +/- 109.30, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 806.83, N = 3SE +/- 0.00, N = 3135461378014273221889291106501775025819380371. (CXX) g++ options: -fPIC -O3 -m64 -std=c++14 -lcudadevrt -lcudart_static -lrt -lpthread -ldl

ASKAP tConvolveCuda

Performance / Cost - Processing: Degridding

OpenBenchmarking.orgMillion Grid Points Per Second Per Dollar, More Is BetterASKAP tConvolveCuda 2015-11-10Performance / Cost - Processing: DegriddingGTX 1070 TiGTX 1080GTX 1080 TiRTX 2070RTX 2080 Ti112233445532.8928.6031.7447.0331.721. GTX 1070 Ti: $419 reported cost.2. GTX 1080: $499 reported cost.3. GTX 1080 Ti: $699 reported cost.4. RTX 2070: $549 reported cost.5. RTX 2080 Ti: $1199 reported cost.

Chaos Group V-RAY

Mode: CUDA GPU

OpenBenchmarking.orgSeconds, Fewer Is BetterChaos Group V-RAY 1.1.0Mode: CUDA GPUGTX 1070GTX 1070 TiGTX 1080GTX 1080 TiGTX 970GTX 980GTX TITAN XRTX 2070RTX 2080 Ti306090120150SE +/- 0.15, N = 3SE +/- 0.06, N = 3SE +/- 0.03, N = 3SE +/- 0.29, N = 3SE +/- 0.38, N = 3SE +/- 0.02, N = 3SE +/- 0.25, N = 3SE +/- 0.04, N = 387.9983.0383.4166.85120.57107.7878.7266.5553.91

Chaos Group V-RAY

System Power Consumption Monitor

OpenBenchmarking.orgWatts, Fewer Is BetterChaos Group V-RAY 1.1.0System Power Consumption MonitorGTX 1070GTX 1070 TiGTX 1080GTX 1080 TiGTX 970GTX 980GTX TITAN XRTX 2070RTX 2080 Ti60120180240300Min: 130.8 / Avg: 219.79 / Max: 228.1Min: 136 / Avg: 229.75 / Max: 241.9Min: 162.9 / Avg: 219.51 / Max: 227.5Min: 168.6 / Avg: 277.93 / Max: 303.6Min: 157.1 / Avg: 222.29 / Max: 231.6Min: 96.2 / Avg: 233.17 / Max: 245.5Min: 170.3 / Avg: 297.26 / Max: 311.3Min: 91.4 / Avg: 260.71 / Max: 281.6Min: 99.6 / Avg: 298.13 / Max: 341.2

clpeak

OpenCL Test: Integer Compute INT

OpenBenchmarking.orgGIOPS, More Is BetterclpeakOpenCL Test: Integer Compute INTGTX 1070GTX 1070 TiGTX 1080GTX 1080 TiGTX 970GTX 980GTX TITAN XR9 FuryRTX 2070RTX 2080 TiRX 580RX Vega 56RX Vega 643K6K9K12K15KSE +/- 6.94, N = 3SE +/- 28.40, N = 3SE +/- 23.15, N = 3SE +/- 104.07, N = 3SE +/- 17.17, N = 3SE +/- 3.45, N = 3SE +/- 19.05, N = 3SE +/- 0.08, N = 3SE +/- 495.02, N = 3SE +/- 947.36, N = 3SE +/- 0.03, N = 3SE +/- 1.34, N = 3SE +/- 2.43, N = 317102339243932921142131418051430815014679125319842502

clpeak

Performance / Cost - OpenCL Test: Integer Compute INT

OpenBenchmarking.orgGIOPS Per Dollar, More Is BetterclpeakPerformance / Cost - OpenCL Test: Integer Compute INTGTX 1070 TiGTX 1080GTX 1080 TiRTX 2070RTX 2080 TiRX 580RX Vega 56RX Vega 64481216205.584.894.7114.8512.244.194.974.821. GTX 1070 Ti: $419 reported cost.2. GTX 1080: $499 reported cost.3. GTX 1080 Ti: $699 reported cost.4. RTX 2070: $549 reported cost.5. RTX 2080 Ti: $1199 reported cost.6. RX 580: $299 reported cost.7. RX Vega 56: $399 reported cost.8. RX Vega 64: $519 reported cost.

CUDA Mini-Nbody

Test: Original

OpenBenchmarking.orgSeconds, Fewer Is BetterCUDA Mini-Nbody 2015-11-10Test: OriginalGTX 1070GTX 1070 TiGTX 1080GTX 1080 TiGTX 970GTX 980GTX TITAN XRTX 2070RTX 2080 Ti1224364860SE +/- 0.02, N = 3SE +/- 0.03, N = 3SE +/- 0.05, N = 3SE +/- 0.09, N = 3SE +/- 0.04, N = 3SE +/- 0.20, N = 3SE +/- 0.32, N = 3SE +/- 0.04, N = 3SE +/- 0.07, N = 339.6931.9132.7621.2351.7145.9033.5517.7111.22

CUDA Mini-Nbody

System Power Consumption Monitor

OpenBenchmarking.orgWatts, Fewer Is BetterCUDA Mini-Nbody 2015-11-10System Power Consumption MonitorGTX 1070GTX 1070 TiGTX 1080GTX 1080 TiGTX 970GTX 980GTX TITAN XRTX 2070RTX 2080 Ti70140210280350Min: 125.3 / Avg: 258.33 / Max: 276.4Min: 179.2 / Avg: 282.55 / Max: 312.9Min: 137.4 / Avg: 283.52 / Max: 306.4Min: 167.1 / Avg: 312.36 / Max: 369.9Min: 279 / Avg: 295.27 / Max: 300.3Min: 110.9 / Avg: 287.91 / Max: 313.7Min: 198.9 / Avg: 344.61 / Max: 382.3Min: 179 / Avg: 277.58 / Max: 305.7Min: 101.7 / Avg: 291.2 / Max: 393

GPU Temperature Monitor

Phoronix Test Suite System Monitoring

OpenBenchmarking.orgCelsiusGPU Temperature MonitorPhoronix Test Suite System MonitoringGTX 1070GTX 1070 TiGTX 1080GTX 1080 TiGTX 970GTX 980GTX TITAN XRTX 2070RTX 2080 Ti1632486480Min: 34 / Avg: 61.6 / Max: 74Min: 38 / Avg: 54.27 / Max: 66Min: 37 / Avg: 61.56 / Max: 77Min: 39 / Avg: 66.34 / Max: 79Min: 30 / Avg: 44.97 / Max: 71Min: 37 / Avg: 56.32 / Max: 81Min: 41 / Avg: 76.41 / Max: 85Min: 34 / Avg: 54.61 / Max: 65Min: 38 / Avg: 58.82 / Max: 74

NVIDIA GPU Cloud TensorFlow

Test: ResNet-50, FP16

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA GPU Cloud TensorFlow 18.09Test: ResNet-50, FP16GTX 1070GTX 1070 TiGTX 1080GTX 1080 TiGTX TITAN XRTX 2070RTX 2080 Ti90180270360450SE +/- 0.12, N = 3SE +/- 0.28, N = 3SE +/- 0.28, N = 3SE +/- 0.98, N = 3SE +/- 4.87, N = 3SE +/- 0.93, N = 3SE +/- 4.94, N = 3158185190265152295428

NVIDIA GPU Cloud TensorFlow

Test: ResNet-50, FP16

OpenBenchmarking.orgImages Per Second Per Watt, More Is BetterNVIDIA GPU Cloud TensorFlow 18.09Test: ResNet-50, FP16GTX 1070GTX 1070 TiGTX 1080GTX 1080 TiGTX TITAN XRTX 2070RTX 2080 Ti0.38480.76961.15441.53921.9240.690.760.810.930.481.291.71

NVIDIA GPU Cloud TensorFlow

System Power Consumption Monitor

OpenBenchmarking.orgWatts, Fewer Is BetterNVIDIA GPU Cloud TensorFlow 18.09System Power Consumption MonitorGTX 1070GTX 1070 TiGTX 1080GTX 1080 TiGTX TITAN XRTX 2070RTX 2080 Ti70140210280350Min: 125.5 / Avg: 230.02 / Max: 273.2Min: 124.9 / Avg: 242.2 / Max: 307Min: 133.9 / Avg: 235.46 / Max: 308.2Min: 128.1 / Avg: 284.31 / Max: 376Min: 144.3 / Avg: 318.58 / Max: 383.5Min: 96.1 / Avg: 229.19 / Max: 310.5Min: 102.9 / Avg: 249.44 / Max: 398.5

NVIDIA GPU Cloud TensorFlow

Test: ResNet-50, FP32

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA GPU Cloud TensorFlow 18.09Test: ResNet-50, FP32GTX 1070GTX 1070 TiGTX 1080GTX 1080 TiGTX TITAN XRTX 2070RTX 2080 Ti60120180240300SE +/- 0.06, N = 3SE +/- 0.03, N = 3SE +/- 0.10, N = 3SE +/- 0.09, N = 3SE +/- 0.60, N = 3SE +/- 0.35, N = 3SE +/- 0.52, N = 3124136141207123181276

NVIDIA GPU Cloud TensorFlow

Test: ResNet-50, FP32

OpenBenchmarking.orgImages Per Second Per Watt, More Is BetterNVIDIA GPU Cloud TensorFlow 18.09Test: ResNet-50, FP32GTX 1070GTX 1070 TiGTX 1080GTX 1080 TiGTX TITAN XRTX 2070RTX 2080 Ti0.22280.44560.66840.89121.1140.530.570.570.760.400.710.99

NVIDIA GPU Cloud TensorFlow

System Power Consumption Monitor

OpenBenchmarking.orgWatts, Fewer Is BetterNVIDIA GPU Cloud TensorFlow 18.09System Power Consumption MonitorGTX 1070GTX 1070 TiGTX 1080GTX 1080 TiGTX TITAN XRTX 2070RTX 2080 Ti70140210280350Min: 134.3 / Avg: 235.05 / Max: 274.2Min: 100.5 / Avg: 240.85 / Max: 305.9Min: 94 / Avg: 248.88 / Max: 305.1Min: 110.9 / Avg: 271.47 / Max: 375.5Min: 110.8 / Avg: 305.55 / Max: 380.1Min: 96.4 / Avg: 253.4 / Max: 312Min: 104.2 / Avg: 279.93 / Max: 400.8

NVIDIA GPU Cloud TensorFlow

Test: AlexNet, FP16

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA GPU Cloud TensorFlow 18.09Test: AlexNet, FP16GTX 1070GTX 1070 TiGTX 1080GTX 1080 TiGTX 970GTX 980GTX TITAN XRTX 2070RTX 2080 Ti9001800270036004500SE +/- 0.98, N = 3SE +/- 0.64, N = 3SE +/- 2.12, N = 3SE +/- 2.34, N = 3SE +/- 0.48, N = 3SE +/- 2.27, N = 3SE +/- 0.59, N = 3SE +/- 5.17, N = 3SE +/- 5.30, N = 3154917731856263510451203164827144330

NVIDIA GPU Cloud TensorFlow

Test: AlexNet, FP16

OpenBenchmarking.orgImages Per Second Per Watt, More Is BetterNVIDIA GPU Cloud TensorFlow 18.09Test: AlexNet, FP16GTX 1070GTX 1070 TiGTX 1080GTX 1080 TiGTX 970GTX 980GTX TITAN XRTX 2070RTX 2080 Ti481216207.507.418.7910.904.374.846.0111.3816.39

NVIDIA GPU Cloud TensorFlow

System Power Consumption Monitor

OpenBenchmarking.orgWatts, Fewer Is BetterNVIDIA GPU Cloud TensorFlow 18.09System Power Consumption MonitorGTX 1070GTX 1070 TiGTX 1080GTX 1080 TiGTX 970GTX 980GTX TITAN XRTX 2070RTX 2080 Ti70140210280350Min: 91.3 / Avg: 206.58 / Max: 261.8Min: 140.1 / Avg: 239.23 / Max: 301.2Min: 137.1 / Avg: 211.28 / Max: 282.8Min: 112.5 / Avg: 241.74 / Max: 360.8Min: 138.5 / Avg: 238.83 / Max: 290.6Min: 142.1 / Avg: 248.35 / Max: 303.8Min: 111.2 / Avg: 273.97 / Max: 376.8Min: 140.1 / Avg: 238.56 / Max: 305.1Min: 139.9 / Avg: 264.23 / Max: 398

NVIDIA GPU Cloud TensorFlow

Test: AlexNet, FP32

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA GPU Cloud TensorFlow 18.09Test: AlexNet, FP32GTX 1070GTX 1070 TiGTX 1080GTX 1080 TiGTX 970GTX 980GTX TITAN XRTX 2070RTX 2080 Ti7001400210028003500SE +/- 0.80, N = 3SE +/- 0.85, N = 3SE +/- 0.65, N = 3SE +/- 1.49, N = 3SE +/- 0.27, N = 3SE +/- 0.03, N = 3SE +/- 2.34, N = 3SE +/- 4.62, N = 3SE +/- 5.44, N = 315041660174624999981146157521103277

NVIDIA GPU Cloud TensorFlow

Test: AlexNet, FP32

OpenBenchmarking.orgImages Per Second Per Watt, More Is BetterNVIDIA GPU Cloud TensorFlow 18.09Test: AlexNet, FP32GTX 1070GTX 1070 TiGTX 1080GTX 1080 TiGTX 970GTX 980GTX TITAN XRTX 2070RTX 2080 Ti36912156.957.697.359.394.254.525.009.0711.39

NVIDIA GPU Cloud TensorFlow

System Power Consumption Monitor

OpenBenchmarking.orgWatts, Fewer Is BetterNVIDIA GPU Cloud TensorFlow 18.09System Power Consumption MonitorGTX 1070GTX 1070 TiGTX 1080GTX 1080 TiGTX 970GTX 980GTX TITAN XRTX 2070RTX 2080 Ti70140210280350Min: 160.5 / Avg: 216.33 / Max: 256.6Min: 141 / Avg: 215.98 / Max: 281Min: 140.8 / Avg: 237.52 / Max: 288Min: 173.7 / Avg: 266.19 / Max: 367.3Min: 141.7 / Avg: 234.98 / Max: 287.4Min: 168.7 / Avg: 253.88 / Max: 296.7Min: 207.4 / Avg: 314.76 / Max: 370.5Min: 94.9 / Avg: 232.75 / Max: 306.7Min: 146.4 / Avg: 287.83 / Max: 399.7

NVIDIA GPU Cloud TensorFlow

Test: Googlenet, FP16

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA GPU Cloud TensorFlow 18.09Test: Googlenet, FP16GTX 1070GTX 1070 TiGTX 1080GTX 1080 TiGTX TITAN XRTX 2070RTX 2080 Ti2004006008001000SE +/- 0.67, N = 3SE +/- 0.21, N = 3SE +/- 0.35, N = 3SE +/- 0.09, N = 3SE +/- 1.26, N = 3SE +/- 0.51, N = 3SE +/- 2.13, N = 3374448454622371641986

NVIDIA GPU Cloud TensorFlow

Test: Googlenet, FP16

OpenBenchmarking.orgImages Per Second Per Watt, More Is BetterNVIDIA GPU Cloud TensorFlow 18.09Test: Googlenet, FP16GTX 1070GTX 1070 TiGTX 1080GTX 1080 TiGTX TITAN XRTX 2070RTX 2080 Ti0.7291.4582.1872.9163.6451.531.701.751.961.142.463.24

NVIDIA GPU Cloud TensorFlow

System Power Consumption Monitor

OpenBenchmarking.orgWatts, Fewer Is BetterNVIDIA GPU Cloud TensorFlow 18.09System Power Consumption MonitorGTX 1070GTX 1070 TiGTX 1080GTX 1080 TiGTX TITAN XRTX 2070RTX 2080 Ti70140210280350Min: 133.7 / Avg: 244.62 / Max: 274.7Min: 99.2 / Avg: 263.81 / Max: 307.6Min: 136.4 / Avg: 259.54 / Max: 306.2Min: 144.5 / Avg: 318.02 / Max: 375Min: 151.6 / Avg: 325.99 / Max: 388Min: 136.9 / Avg: 260.13 / Max: 307.7Min: 99.4 / Avg: 304.21 / Max: 401.7

NVIDIA GPU Cloud TensorFlow

Test: Inception v4, FP16

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA GPU Cloud TensorFlow 18.09Test: Inception v4, FP16GTX 1070GTX 1070 TiGTX 1080GTX 1080 TiGTX TITAN XRTX 2070RTX 2080 Ti306090120150SE +/- 0.10, N = 3SE +/- 0.07, N = 3SE +/- 0.12, N = 3SE +/- 0.09, N = 3SE +/- 0.17, N = 3SE +/- 0.72, N = 3SE +/- 0.81, N = 343.9052.9353.8372.1742.6385.20123.00

NVIDIA GPU Cloud TensorFlow

Test: Inception v4, FP16

OpenBenchmarking.orgImages Per Second Per Watt, More Is BetterNVIDIA GPU Cloud TensorFlow 18.09Test: Inception v4, FP16GTX 1070GTX 1070 TiGTX 1080GTX 1080 TiGTX TITAN XRTX 2070RTX 2080 Ti0.11250.2250.33750.450.56250.200.220.220.270.150.400.50

NVIDIA GPU Cloud TensorFlow

System Power Consumption Monitor

OpenBenchmarking.orgWatts, Fewer Is BetterNVIDIA GPU Cloud TensorFlow 18.09System Power Consumption MonitorGTX 1070GTX 1070 TiGTX 1080GTX 1080 TiGTX TITAN XRTX 2070RTX 2080 Ti70140210280350Min: 132.4 / Avg: 221.97 / Max: 272.5Min: 138.9 / Avg: 243.51 / Max: 311.7Min: 132.4 / Avg: 241.44 / Max: 307.7Min: 99.4 / Avg: 272.26 / Max: 380.7Min: 108 / Avg: 278.24 / Max: 380.9Min: 92.5 / Avg: 210.62 / Max: 301.7Min: 140.1 / Avg: 247.2 / Max: 404

NVIDIA GPU Cloud TensorFlow

Test: VGG-16, FP16

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA GPU Cloud TensorFlow 18.09Test: VGG-16, FP16GTX 1070GTX 1070 TiGTX 1080GTX 1080 TiGTX TITAN XRTX 2070RTX 2080 Ti4080120160200SE +/- 0.15, N = 3SE +/- 0.12, N = 3SE +/- 0.09, N = 3SE +/- 0.19, N = 3SE +/- 0.55, N = 3SE +/- 0.20, N = 3SE +/- 0.06, N = 377.1389.3392.97131.2778.27138.33204.00

NVIDIA GPU Cloud TensorFlow

Test: VGG-16, FP16

OpenBenchmarking.orgImages Per Second Per Watt, More Is BetterNVIDIA GPU Cloud TensorFlow 18.09Test: VGG-16, FP16GTX 1070GTX 1070 TiGTX 1080GTX 1080 TiGTX TITAN XRTX 2070RTX 2080 Ti0.1530.3060.4590.6120.7650.340.370.370.420.240.550.68

NVIDIA GPU Cloud TensorFlow

System Power Consumption Monitor

OpenBenchmarking.orgWatts, Fewer Is BetterNVIDIA GPU Cloud TensorFlow 18.09System Power Consumption MonitorGTX 1070GTX 1070 TiGTX 1080GTX 1080 TiGTX TITAN XRTX 2070RTX 2080 Ti70140210280350Min: 91.5 / Avg: 229.25 / Max: 265.4Min: 112.1 / Avg: 242.95 / Max: 294.5Min: 92.5 / Avg: 248.1 / Max: 296.9Min: 190.3 / Avg: 310.17 / Max: 375.6Min: 206.8 / Avg: 322.78 / Max: 378.7Min: 138.7 / Avg: 249.29 / Max: 302.5Min: 101.9 / Avg: 299.78 / Max: 396.1

NVIDIA GPU Cloud TensorFlow

Test: VGG-16, FP32

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA GPU Cloud TensorFlow 18.09Test: VGG-16, FP32GTX 1070GTX 1070 TiGTX 1080GTX 1080 TiGTX TITAN XRTX 2070RTX 2080 Ti306090120150SE +/- 0.12, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.13, N = 3SE +/- 0.37, N = 3SE +/- 9.08, N = 3SE +/- 0.35, N = 371.7079.0382.77119.2772.8390.67150.00

NVIDIA GPU Cloud TensorFlow

Test: VGG-16, FP32

OpenBenchmarking.orgImages Per Second Per Watt, More Is BetterNVIDIA GPU Cloud TensorFlow 18.09Test: VGG-16, FP32GTX 1070GTX 1070 TiGTX 1080GTX 1080 TiGTX TITAN XRTX 2070RTX 2080 Ti0.1080.2160.3240.4320.540.310.320.330.390.230.350.48

NVIDIA GPU Cloud TensorFlow

System Power Consumption Monitor

OpenBenchmarking.orgWatts, Fewer Is BetterNVIDIA GPU Cloud TensorFlow 18.09System Power Consumption MonitorGTX 1070GTX 1070 TiGTX 1080GTX 1080 TiGTX TITAN XRTX 2070RTX 2080 Ti70140210280350Min: 93.5 / Avg: 228.29 / Max: 264.8Min: 99.1 / Avg: 248.3 / Max: 292.9Min: 132.8 / Avg: 251.17 / Max: 299.3Min: 139.5 / Avg: 308.82 / Max: 375Min: 145.5 / Avg: 317.87 / Max: 381.9Min: 92.7 / Avg: 262.66 / Max: 313.7Min: 101.7 / Avg: 311.29 / Max: 404.4

NVIDIA GPU Cloud TensorFlow

Performance / Cost - Test: ResNet-50, FP16

OpenBenchmarking.orgImages Per Second Per Dollar, More Is BetterNVIDIA GPU Cloud TensorFlow 18.09Performance / Cost - Test: ResNet-50, FP16GTX 1070 TiGTX 1080GTX 1080 TiRTX 2070RTX 2080 Ti0.12150.2430.36450.4860.60750.440.380.380.540.361. GTX 1070 Ti: $419 reported cost.2. GTX 1080: $499 reported cost.3. GTX 1080 Ti: $699 reported cost.4. RTX 2070: $549 reported cost.5. RTX 2080 Ti: $1199 reported cost.

NVIDIA GPU Cloud TensorFlow

Performance / Cost - Test: ResNet-50, FP32

OpenBenchmarking.orgImages Per Second Per Dollar, More Is BetterNVIDIA GPU Cloud TensorFlow 18.09Performance / Cost - Test: ResNet-50, FP32GTX 1070 TiGTX 1080GTX 1080 TiRTX 2070RTX 2080 Ti0.07430.14860.22290.29720.37150.320.280.300.330.231. GTX 1070 Ti: $419 reported cost.2. GTX 1080: $499 reported cost.3. GTX 1080 Ti: $699 reported cost.4. RTX 2070: $549 reported cost.5. RTX 2080 Ti: $1199 reported cost.

NVIDIA GPU Cloud TensorFlow

Performance / Cost - Test: AlexNet, FP16

OpenBenchmarking.orgImages Per Second Per Dollar, More Is BetterNVIDIA GPU Cloud TensorFlow 18.09Performance / Cost - Test: AlexNet, FP16GTX 1070 TiGTX 1080GTX 1080 TiRTX 2070RTX 2080 Ti1.11152.2233.33454.4465.55754.233.723.774.943.611. GTX 1070 Ti: $419 reported cost.2. GTX 1080: $499 reported cost.3. GTX 1080 Ti: $699 reported cost.4. RTX 2070: $549 reported cost.5. RTX 2080 Ti: $1199 reported cost.

NVIDIA GPU Cloud TensorFlow

Performance / Cost - Test: AlexNet, FP32

OpenBenchmarking.orgImages Per Second Per Dollar, More Is BetterNVIDIA GPU Cloud TensorFlow 18.09Performance / Cost - Test: AlexNet, FP32GTX 1070 TiGTX 1080GTX 1080 TiRTX 2070RTX 2080 Ti0.8911.7822.6733.5644.4553.963.503.583.842.731. GTX 1070 Ti: $419 reported cost.2. GTX 1080: $499 reported cost.3. GTX 1080 Ti: $699 reported cost.4. RTX 2070: $549 reported cost.5. RTX 2080 Ti: $1199 reported cost.

NVIDIA GPU Cloud TensorFlow

Performance / Cost - Test: Googlenet, FP16

OpenBenchmarking.orgImages Per Second Per Dollar, More Is BetterNVIDIA GPU Cloud TensorFlow 18.09Performance / Cost - Test: Googlenet, FP16GTX 1070 TiGTX 1080GTX 1080 TiRTX 2070RTX 2080 Ti0.26330.52660.78991.05321.31651.070.910.891.170.821. GTX 1070 Ti: $419 reported cost.2. GTX 1080: $499 reported cost.3. GTX 1080 Ti: $699 reported cost.4. RTX 2070: $549 reported cost.5. RTX 2080 Ti: $1199 reported cost.

NVIDIA GPU Cloud TensorFlow

Performance / Cost - Test: Inception v4, FP16

OpenBenchmarking.orgImages Per Second Per Dollar, More Is BetterNVIDIA GPU Cloud TensorFlow 18.09Performance / Cost - Test: Inception v4, FP16GTX 1070 TiGTX 1080GTX 1080 TiRTX 2070RTX 2080 Ti0.0360.0720.1080.1440.180.130.110.100.160.101. GTX 1070 Ti: $419 reported cost.2. GTX 1080: $499 reported cost.3. GTX 1080 Ti: $699 reported cost.4. RTX 2070: $549 reported cost.5. RTX 2080 Ti: $1199 reported cost.

NVIDIA GPU Cloud TensorFlow

Performance / Cost - Test: VGG-16, FP16

OpenBenchmarking.orgImages Per Second Per Dollar, More Is BetterNVIDIA GPU Cloud TensorFlow 18.09Performance / Cost - Test: VGG-16, FP16GTX 1070 TiGTX 1080GTX 1080 TiRTX 2070RTX 2080 Ti0.05630.11260.16890.22520.28150.210.190.190.250.171. GTX 1070 Ti: $419 reported cost.2. GTX 1080: $499 reported cost.3. GTX 1080 Ti: $699 reported cost.4. RTX 2070: $549 reported cost.5. RTX 2080 Ti: $1199 reported cost.

NVIDIA GPU Cloud TensorFlow

Performance / Cost - Test: VGG-16, FP32

OpenBenchmarking.orgImages Per Second Per Dollar, More Is BetterNVIDIA GPU Cloud TensorFlow 18.09Performance / Cost - Test: VGG-16, FP32GTX 1070 TiGTX 1080GTX 1080 TiRTX 2070RTX 2080 Ti0.04280.08560.12840.17120.2140.190.170.170.170.131. GTX 1070 Ti: $419 reported cost.2. GTX 1080: $499 reported cost.3. GTX 1080 Ti: $699 reported cost.4. RTX 2070: $549 reported cost.5. RTX 2080 Ti: $1199 reported cost.

Parboil

Test: OpenCL TPACF

OpenBenchmarking.orgSeconds, Fewer Is BetterParboil 2.5Test: OpenCL TPACFGTX 1070GTX 1070 TiGTX 1080GTX 1080 TiGTX 970GTX 980GTX TITAN XRTX 2070RTX 2080 Ti0.35780.71561.07341.43121.789SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.05, N = 3SE +/- 0.04, N = 3SE +/- 0.04, N = 3SE +/- 0.02, N = 3SE +/- 0.07, N = 3SE +/- 0.03, N = 3SE +/- 0.07, N = 31.241.201.210.931.591.551.491.030.821. (CXX) g++ options: -lm -lpthread -lgomp -O3 -ffast-math -fopenmp

SHOC Scalable HeterOgeneous Computing

Target: OpenCL - Benchmark: FFT SP

OpenBenchmarking.orgGFLOPS, More Is BetterSHOC Scalable HeterOgeneous Computing 2015-11-10Target: OpenCL - Benchmark: FFT SPGTX 1070GTX 1070 TiGTX 1080GTX 1080 TiGTX 970GTX 980GTX TITAN XR9 FuryRTX 2070RTX 2080 TiRX 580RX Vega 56RX Vega 6430060090012001500SE +/- 1.15, N = 3SE +/- 0.37, N = 3SE +/- 0.71, N = 3SE +/- 1.62, N = 3SE +/- 1.04, N = 3SE +/- 0.36, N = 3SE +/- 1.00, N = 3SE +/- 0.06, N = 3SE +/- 24.94, N = 3SE +/- 14.55, N = 3SE +/- 0.11, N = 3SE +/- 2.01, N = 3SE +/- 0.54, N = 3550556654983407459726821101514435469299311. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -lmpi_cxx -lmpi

SHOC Scalable HeterOgeneous Computing

Target: OpenCL - Benchmark: MD5 Hash

OpenBenchmarking.orgGHash/s, More Is BetterSHOC Scalable HeterOgeneous Computing 2015-11-10Target: OpenCL - Benchmark: MD5 HashGTX 1070GTX 1070 TiGTX 1080GTX 1080 TiGTX 970GTX 980GTX TITAN XR9 FuryRTX 2070RTX 2080 TiRX 580RX Vega 56RX Vega 64816243240SE +/- 0.01, N = 3SE +/- 0.04, N = 3SE +/- 0.01, N = 3SE +/- 0.05, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.02, N = 3SE +/- 0.07, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 310.6713.6614.3119.966.477.4910.309.2019.2834.878.0612.4116.431. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -lmpi_cxx -lmpi

SHOC Scalable HeterOgeneous Computing

Performance / Cost - Target: OpenCL - Benchmark: FFT SP

OpenBenchmarking.orgGFLOPS Per Dollar, More Is BetterSHOC Scalable HeterOgeneous Computing 2015-11-10Performance / Cost - Target: OpenCL - Benchmark: FFT SPGTX 1070 TiGTX 1080GTX 1080 TiRTX 2070RTX 2080 TiRX 580RX Vega 56RX Vega 640.52431.04861.57292.09722.62151.331.311.411.851.201.832.331.791. GTX 1070 Ti: $419 reported cost.2. GTX 1080: $499 reported cost.3. GTX 1080 Ti: $699 reported cost.4. RTX 2070: $549 reported cost.5. RTX 2080 Ti: $1199 reported cost.6. RX 580: $299 reported cost.7. RX Vega 56: $399 reported cost.8. RX Vega 64: $519 reported cost.

SHOC Scalable HeterOgeneous Computing

Performance / Cost - Target: OpenCL - Benchmark: MD5 Hash

OpenBenchmarking.orgGHash/s Per Dollar, More Is BetterSHOC Scalable HeterOgeneous Computing 2015-11-10Performance / Cost - Target: OpenCL - Benchmark: MD5 HashGTX 1070 TiGTX 1080GTX 1080 TiRTX 2070RTX 2080 TiRX 580RX Vega 56RX Vega 640.0090.0180.0270.0360.0450.030.030.030.040.030.030.030.031. GTX 1070 Ti: $419 reported cost.2. GTX 1080: $499 reported cost.3. GTX 1080 Ti: $699 reported cost.4. RTX 2070: $549 reported cost.5. RTX 2080 Ti: $1199 reported cost.6. RX 580: $299 reported cost.7. RX Vega 56: $399 reported cost.8. RX Vega 64: $519 reported cost.

System Power Consumption Monitor

Phoronix Test Suite System Monitoring

OpenBenchmarking.orgWattsSystem Power Consumption MonitorPhoronix Test Suite System MonitoringGTX 1070GTX 1070 TiGTX 1080GTX 1080 TiGTX 970GTX 980GTX TITAN XRTX 2070RTX 2080 Ti70140210280350Min: 91.3 / Avg: 209.2 / Max: 276.4Min: 96.8 / Avg: 223.4 / Max: 312.9Min: 91 / Avg: 211.98 / Max: 308.2Min: 94 / Avg: 268 / Max: 380.7Min: 95.8 / Avg: 176.17 / Max: 300.3Min: 93.6 / Avg: 176.4 / Max: 313.7Min: 104.9 / Avg: 294.18 / Max: 388Min: 91.4 / Avg: 214.35 / Max: 313.7Min: 95.3 / Avg: 264.13 / Max: 406.6

Phoronix Test Suite v10.8.4