NVIDIA AMD Linux GPU Compute December 2018

NVIDIA and AMD GPU Linux compute benchmarks December 2018 by Michael Larabel for a future article..

HTML result view exported from: https://openbenchmarking.org/result/1812085-SK-GPUCOMPUT99&grw&sor.

NVIDIA AMD Linux GPU Compute December 2018ProcessorMotherboardChipsetMemoryDiskGraphicsAudioMonitorNetworkOSKernelDesktopDisplay ServerDisplay DriverOpenGLOpenCLVulkanCompilerFile-SystemScreen ResolutionGTX 1070GTX 1070 TiGTX 1080GTX 1080 TiRTX 2070RTX 2080RTX 2080 TiR9 FuryRX Vega 56RX Vega 64Intel Core i9-9900K @ 5.00GHz (8 Cores / 16 Threads)ASUS PRIME Z390-A (0602 BIOS)Intel Cannon Lake PCH Shared SRAM16384MB2000GB SABRENT + Samsung SSD 970 EVO 250GBNVIDIA GeForce GTX 1070 8GB (1506/4006MHz)Realtek ALC1220Acer B286HKIntel ConnectionUbuntu 18.044.19.5-041905-generic (x86_64)GNOME Shell 3.28.3X Server 1.19.6NVIDIA 415.224.6.0OpenCL 1.2 CUDA 10.0.1321.1.84GCC 7.3.0 + CUDA 10.0ext43840x2160Zotac 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)Zotac NVIDIA GeForce RTX 2080 8GB (1515/7000MHz)NVIDIA GeForce RTX 2080 Ti 11GB (1350/7000MHz)Sapphire AMD Radeon R9 FURY / NANO 4GB (1000/500MHz)4.5 Mesa 19.0.0-devel padoka PPA (LLVM 8.0.0)OpenCL 2.1 AMD-APP (2679.0)1.1.70GCC 7.3.0AMD Radeon RX Vega 8GB (1590/800MHz)AMD Radeon RX Vega 8GB (1630/945MHz)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: intel_pstate performanceOpenCL Details- 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: GPU Compute Cores: 2944- RTX 2080 Ti: GPU Compute Cores: 4352Security Details- __user pointer sanitization + Full generic retpoline IBPB IBRS_FW + SSB disabled via prctl and seccomp

NVIDIA AMD Linux GPU Compute December 2018ngc-tensorflow: AlexNet, FP32ngc-tensorflow: VGG-16, FP16ngc-tensorflow: ResNet-50, FP16shoc: OpenCL - FFT SPshoc: OpenCL - Texture Read Bandwidthngc-tensorflow: Inception v4, FP16clpeak: Integer Compute INTclpeak: Kernel Latencycuda-mini-nbody: Originalngc-tensorflow: Googlenet, FP16ngc-tensorflow: ResNet-50, FP32ngc-tensorflow: VGG-16, FP32ngc-tensorflow: AlexNet, FP16shoc: OpenCL - MD5 Hashv-ray: CUDA GPUcl-mem: Copyluxmark: GPU - Luxball HDRGTX 1070GTX 1070 TiGTX 1080GTX 1080 TiRTX 2070RTX 2080RTX 2080 TiR9 FuryRX Vega 56RX Vega 64151676.9316045245144.7716923.7491.9937512571.57156310.7290.4318717288159184.4317549743349.2320823.6611241313376.40168311.6386.3018816886176493.1319357553055.0324373.7211145814382.90187514.17102.07209138232539131.3727197259574.6333213.80186629210119.50267419.9666.41317215622174309998110180073.5224419.2966.02330300912419153.3333510831119102.77100593.48304738205108.57315324.3772.07328296413344206.9744914431134135.90143853.574261015285152.40443235.8656.094544269384625014305.689.202052344892638419916.9814.0320331179107044224916.9416.5322132815OpenBenchmarking.org

NVIDIA GPU Cloud TensorFlow

Test: AlexNet, FP32

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA GPU Cloud TensorFlow 18.09Test: AlexNet, FP32RTX 2080 TiGTX 1080 TiRTX 2080RTX 2070GTX 1080GTX 1070 TiGTX 10707001400210028003500SE +/- 6.99, N = 3SE +/- 1.83, N = 3SE +/- 1.84, N = 3SE +/- 1.62, N = 3SE +/- 0.32, N = 3SE +/- 0.44, N = 33344253924192174176415911516

NVIDIA GPU Cloud TensorFlow

Test: VGG-16, FP16

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA GPU Cloud TensorFlow 18.09Test: VGG-16, FP16RTX 2080 TiRTX 2080GTX 1080 TiGTX 1080GTX 1070 TiGTX 107050100150200250SE +/- 0.07, N = 3SE +/- 0.09, N = 3SE +/- 0.12, N = 3SE +/- 0.24, N = 3SE +/- 0.03, N = 3SE +/- 0.07, N = 3206.97153.33131.3793.1384.4376.93

NVIDIA GPU Cloud TensorFlow

Test: ResNet-50, FP16

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA GPU Cloud TensorFlow 18.09Test: ResNet-50, FP16RTX 2080 TiRTX 2080RTX 2070GTX 1080 TiGTX 1080GTX 1070 TiGTX 1070100200300400500SE +/- 0.28, N = 3SE +/- 0.85, N = 3SE +/- 0.15, N = 3SE +/- 0.10, N = 3SE +/- 0.07, N = 3SE +/- 0.03, N = 3449335309271193175160

SHOC Scalable HeterOgeneous Computing

Target: OpenCL - Benchmark: FFT SP

OpenBenchmarking.orgGFLOPS, More Is BetterSHOC Scalable HeterOgeneous Computing 2015-11-10Target: OpenCL - Benchmark: FFT SPRTX 2080 TiRTX 2080RX Vega 64RTX 2070GTX 1080 TiRX Vega 56R9 FuryGTX 1080GTX 1070 TiGTX 107030060090012001500SE +/- 14.24, N = 3SE +/- 5.95, N = 3SE +/- 0.64, N = 3SE +/- 40.79, N = 3SE +/- 1.23, N = 3SE +/- 1.57, N = 3SE +/- 0.09, N = 3SE +/- 2.68, N = 3SE +/- 0.73, N = 3SE +/- 0.94, N = 3144310831070998972926846575497452-std=c++14 -lcudadevrt -lcudart_static -lpthread -ldl -lcufft-std=c++14 -lcudadevrt -lcudart_static -lpthread -ldl -lcufft-lSHOCCommonOpenCL -lOpenCL-std=c++14 -lcudadevrt -lcudart_static -lpthread -ldl -lcufft-std=c++14 -lcudadevrt -lcudart_static -lpthread -ldl -lcufft-lSHOCCommonOpenCL -lOpenCL-lSHOCCommonOpenCL -lOpenCL-std=c++14 -lcudadevrt -lcudart_static -lpthread -ldl -lcufft-std=c++14 -lcudadevrt -lcudart_static -lpthread -ldl -lcufft-std=c++14 -lcudadevrt -lcudart_static -lpthread -ldl -lcufft1. (CXX) g++ options: -O2 -lSHOCCommon -lrt

SHOC Scalable HeterOgeneous Computing

Target: OpenCL - Benchmark: Texture Read Bandwidth

OpenBenchmarking.orgGB/s, More Is BetterSHOC Scalable HeterOgeneous Computing 2015-11-10Target: OpenCL - Benchmark: Texture Read BandwidthRTX 2080 TiRTX 2080RTX 2070GTX 1080 TiGTX 1080GTX 1070RX Vega 64GTX 1070 TiRX Vega 56R9 Fury2004006008001000SE +/- 3.81, N = 3SE +/- 3.18, N = 3SE +/- 1.33, N = 3SE +/- 2.41, N = 3SE +/- 0.39, N = 3SE +/- 0.06, N = 3SE +/- 1.72, N = 3SE +/- 0.09, N = 3SE +/- 0.54, N = 3SE +/- 1.14, N = 3113411191101595530451442433384250-std=c++14 -lcudadevrt -lcudart_static -lpthread -ldl -lcufft-std=c++14 -lcudadevrt -lcudart_static -lpthread -ldl -lcufft-std=c++14 -lcudadevrt -lcudart_static -lpthread -ldl -lcufft-std=c++14 -lcudadevrt -lcudart_static -lpthread -ldl -lcufft-std=c++14 -lcudadevrt -lcudart_static -lpthread -ldl -lcufft-std=c++14 -lcudadevrt -lcudart_static -lpthread -ldl -lcufft-lSHOCCommonOpenCL -lOpenCL-std=c++14 -lcudadevrt -lcudart_static -lpthread -ldl -lcufft-lSHOCCommonOpenCL -lOpenCL-lSHOCCommonOpenCL -lOpenCL1. (CXX) g++ options: -O2 -lSHOCCommon -lrt

NVIDIA GPU Cloud TensorFlow

Test: Inception v4, FP16

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA GPU Cloud TensorFlow 18.09Test: Inception v4, FP16RTX 2080 TiRTX 2080GTX 1080 TiGTX 1080GTX 1070 TiGTX 1070306090120150SE +/- 0.10, N = 3SE +/- 0.07, N = 3SE +/- 0.07, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 3135.90102.7774.6355.0349.2344.77

clpeak

OpenCL Test: Integer Compute INT

OpenBenchmarking.orgGIOPS, More Is BetterclpeakOpenCL Test: Integer Compute INTRTX 2080 TiRTX 2080RTX 2070GTX 1080 TiRX Vega 64GTX 1080GTX 1070 TiRX Vega 56GTX 1070R9 Fury3K6K9K12K15KSE +/- 946.18, N = 3SE +/- 601.95, N = 3SE +/- 552.67, N = 3SE +/- 12.10, N = 3SE +/- 1.38, N = 3SE +/- 8.46, N = 3SE +/- 0.67, N = 3SE +/- 1.96, N = 3SE +/- 9.42, N = 3SE +/- 0.00, N = 3143851005980073321249124372082199116921430

clpeak

OpenCL Test: Kernel Latency

OpenBenchmarking.orgus, Fewer Is BetterclpeakOpenCL Test: Kernel LatencyRTX 2080RTX 2070RTX 2080 TiGTX 1070 TiGTX 1080GTX 1070GTX 1080 TiR9 FuryRX Vega 64RX Vega 56246810SE +/- 0.05, N = 3SE +/- 0.06, N = 3SE +/- 0.12, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.05, N = 3SE +/- 0.03, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 33.483.523.573.663.723.743.805.686.946.98

CUDA Mini-Nbody

Test: Original

OpenBenchmarking.org(NBody^2)/s, More Is BetterCUDA Mini-Nbody 2015-11-10Test: OriginalRTX 2080 TiRTX 2080RTX 2070GTX 1080 TiGTX 1070 TiGTX 1080GTX 107090180270360450SE +/- 0.80, N = 3SE +/- 0.92, N = 3SE +/- 0.61, N = 3SE +/- 0.19, N = 3SE +/- 0.07, N = 3SE +/- 0.17, N = 3SE +/- 0.16, N = 3426.00304.00244.00186.00112.00111.0091.99

NVIDIA GPU Cloud TensorFlow

Test: Googlenet, FP16

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA GPU Cloud TensorFlow 18.09Test: Googlenet, FP16RTX 2080 TiRTX 2080GTX 1080 TiGTX 1080GTX 1070 TiGTX 10702004006008001000SE +/- 0.49, N = 3SE +/- 0.58, N = 3SE +/- 2.49, N = 3SE +/- 0.21, N = 3SE +/- 0.09, N = 3SE +/- 0.35, N = 31015738629458413375

NVIDIA GPU Cloud TensorFlow

Test: ResNet-50, FP32

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA GPU Cloud TensorFlow 18.09Test: ResNet-50, FP32RTX 2080 TiGTX 1080 TiRTX 2080GTX 1080GTX 1070 TiGTX 107060120180240300SE +/- 0.44, N = 3SE +/- 0.19, N = 3SE +/- 0.28, N = 3SE +/- 0.07, N = 3SE +/- 0.06, N = 3SE +/- 0.09, N = 3285210205143133125

NVIDIA GPU Cloud TensorFlow

Test: VGG-16, FP32

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA GPU Cloud TensorFlow 18.09Test: VGG-16, FP32RTX 2080 TiGTX 1080 TiRTX 2080GTX 1080GTX 1070 TiGTX 1070306090120150SE +/- 0.12, N = 3SE +/- 0.12, N = 3SE +/- 0.07, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.13, N = 3152.40119.50108.5782.9076.4071.57

NVIDIA GPU Cloud TensorFlow

Test: AlexNet, FP16

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA GPU Cloud TensorFlow 18.09Test: AlexNet, FP16RTX 2080 TiRTX 2080GTX 1080 TiGTX 1080GTX 1070 TiGTX 107010002000300040005000SE +/- 2.27, N = 3SE +/- 3.35, N = 3SE +/- 1.32, N = 3SE +/- 2.60, N = 3SE +/- 0.50, N = 3SE +/- 2.26, N = 3443231532674187516831563

SHOC Scalable HeterOgeneous Computing

Target: OpenCL - Benchmark: MD5 Hash

OpenBenchmarking.orgGHash/s, More Is BetterSHOC Scalable HeterOgeneous Computing 2015-11-10Target: OpenCL - Benchmark: MD5 HashRTX 2080 TiRTX 2080GTX 1080 TiRTX 2070RX Vega 64GTX 1080RX Vega 56GTX 1070 TiGTX 1070R9 Fury816243240SE +/- 0.34, N = 3SE +/- 0.02, N = 3SE +/- 0.06, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.02, N = 3SE +/- 0.00, N = 335.8624.3719.9619.2916.5314.1714.0311.6310.729.20-std=c++14 -lcudadevrt -lcudart_static -lpthread -ldl -lcufft-std=c++14 -lcudadevrt -lcudart_static -lpthread -ldl -lcufft-std=c++14 -lcudadevrt -lcudart_static -lpthread -ldl -lcufft-std=c++14 -lcudadevrt -lcudart_static -lpthread -ldl -lcufft-lSHOCCommonOpenCL -lOpenCL-std=c++14 -lcudadevrt -lcudart_static -lpthread -ldl -lcufft-lSHOCCommonOpenCL -lOpenCL-std=c++14 -lcudadevrt -lcudart_static -lpthread -ldl -lcufft-std=c++14 -lcudadevrt -lcudart_static -lpthread -ldl -lcufft-lSHOCCommonOpenCL -lOpenCL1. (CXX) g++ options: -O2 -lSHOCCommon -lrt

Chaos Group V-RAY

Mode: CUDA GPU

OpenBenchmarking.orgSeconds, Fewer Is BetterChaos Group V-RAY 1.1.0Mode: CUDA GPURTX 2080 TiRTX 2070GTX 1080 TiRTX 2080GTX 1070 TiGTX 1070GTX 108020406080100SE +/- 3.00, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.04, N = 3SE +/- 0.04, N = 3SE +/- 0.03, N = 3SE +/- 3.08, N = 356.0966.0266.4172.0786.3090.43102.07

cl-mem

Benchmark: Copy

OpenBenchmarking.orgGB/s, More Is Bettercl-mem 2017-01-13Benchmark: CopyRTX 2080 TiRTX 2070RTX 2080GTX 1080 TiRX Vega 64GTX 1080R9 FuryRX Vega 56GTX 1070 TiGTX 1070100200300400500SE +/- 0.39, N = 3SE +/- 0.12, N = 3SE +/- 0.09, N = 3SE +/- 0.07, N = 3SE +/- 0.07, N = 3SE +/- 0.07, N = 3SE +/- 0.47, N = 3SE +/- 0.21, N = 3SE +/- 0.07, N = 3SE +/- 0.07, N = 34543303283172212092052031881871. (CC) gcc options: -O2 -flto -lOpenCL

LuxMark

OpenCL Device: GPU - Scene: Luxball HDR

OpenBenchmarking.orgScore, More Is BetterLuxMark 3.1OpenCL Device: GPU - Scene: Luxball HDRRTX 2080 TiRX Vega 64RX Vega 56RTX 2070RTX 2080R9 FuryGTX 1080 TiGTX 1070GTX 1070 TiGTX 10809K18K27K36K45KSE +/- 66.64, N = 3SE +/- 570.76, N = 3SE +/- 20.53, N = 3SE +/- 2.73, N = 3SE +/- 36.02, N = 3SE +/- 119.86, N = 3SE +/- 0.58, N = 3SE +/- 0.67, N = 3SE +/- 29.04, N = 342693328153117930091296412344821562172881688613823

SHOC Scalable HeterOgeneous Computing

Target: OpenCL - Benchmark: Texture Read Bandwidth

OpenBenchmarking.orgGB/s Per Watt, More Is BetterSHOC Scalable HeterOgeneous Computing 2015-11-10Target: OpenCL - Benchmark: Texture Read BandwidthRTX 2070RTX 2080RTX 2080 TiGTX 1080GTX 1070 TiGTX 1070GTX 1080 TiRX Vega 64RX Vega 56R9 Fury2468106.766.595.083.663.533.353.131.981.941.45

SHOC Scalable HeterOgeneous Computing

System Power Consumption Monitor

OpenBenchmarking.orgWatts, Fewer Is BetterSHOC Scalable HeterOgeneous Computing 2015-11-10System Power Consumption MonitorGTX 1070 TiGTX 1070GTX 1080RTX 2070RTX 2080R9 FuryGTX 1080 TiRX Vega 56RTX 2080 TiRX Vega 6450100150200250Min: 47 / Avg: 122.6 / Max: 141.5Min: 82.6 / Avg: 134.72 / Max: 155.3Min: 89.7 / Avg: 144.76 / Max: 164.6Min: 53.7 / Avg: 162.86 / Max: 198.7Min: 47.1 / Avg: 169.8 / Max: 202.9Min: 113.9 / Avg: 172.33 / Max: 220.8Min: 120.8 / Avg: 190.06 / Max: 216.8Min: 49.4 / Avg: 197.63 / Max: 234.4Min: 47.5 / Avg: 222.96 / Max: 282.7Min: 51.8 / Avg: 223.18 / Max: 249.9

cl-mem

Benchmark: Copy

OpenBenchmarking.orgGB/s Per Watt, More Is Bettercl-mem 2017-01-13Benchmark: CopyRTX 2070RTX 2080RTX 2080 TiGTX 1080 TiGTX 1070 TiGTX 1080GTX 1070R9 FuryRX Vega 56RX Vega 640.8731.7462.6193.4924.3653.883.532.521.771.771.401.361.241.031.02

cl-mem

System Power Consumption Monitor

OpenBenchmarking.orgWatts, Fewer Is Bettercl-mem 2017-01-13System Power Consumption MonitorRTX 2070RTX 2080GTX 1070 TiGTX 1070GTX 1080R9 FuryGTX 1080 TiRTX 2080 TiRX Vega 56RX Vega 6460120180240300Min: 43.3 / Avg: 85.23 / Max: 108.2Min: 46.4 / Avg: 92.77 / Max: 122Min: 46.1 / Avg: 105.92 / Max: 138.1Min: 82.6 / Avg: 137.43 / Max: 149.2Min: 115.3 / Avg: 149.23 / Max: 161.8Min: 90.3 / Avg: 165.77 / Max: 211.3Min: 120.7 / Avg: 179.53 / Max: 209Min: 47.1 / Avg: 180.3 / Max: 248.8Min: 49.6 / Avg: 196.84 / Max: 261.2Min: 52.4 / Avg: 216.5 / Max: 318.8

LuxMark

System Power Consumption Monitor

OpenBenchmarking.orgWatts, Fewer Is BetterLuxMark 3.1System Power Consumption MonitorGTX 1070 TiGTX 1080GTX 1070RTX 2070RTX 2080GTX 1080 TiR9 FuryRX Vega 56RTX 2080 TiRX Vega 6460120180240300Min: 146.8 / Avg: 148.92 / Max: 149.4Min: 90.8 / Avg: 174.24 / Max: 176.2Min: 83.1 / Avg: 176.9 / Max: 181.3Min: 78 / Avg: 225.33 / Max: 232.6Min: 101.9 / Avg: 240.83 / Max: 247.3Min: 122.9 / Avg: 241.59 / Max: 247.8Min: 90.4 / Avg: 249.15 / Max: 256.6Min: 51.8 / Avg: 251.16 / Max: 263.3Min: 111.1 / Avg: 315.29 / Max: 328.4Min: 53 / Avg: 323.35 / Max: 337.9

GPU Temperature Monitor

Phoronix Test Suite System Monitoring

OpenBenchmarking.orgCelsiusGPU Temperature MonitorPhoronix Test Suite System MonitoringGTX 1070 TiRX Vega 56RX Vega 64RTX 2070RTX 2080 TiGTX 1070GTX 1080GTX 1080 TiRTX 2080R9 Fury1632486480Min: 36 / Avg: 46.92 / Max: 60Min: 31 / Avg: 51.02 / Max: 75Min: 28 / Avg: 52.98 / Max: 85Min: 33 / Avg: 54.57 / Max: 64Min: 34 / Avg: 60.3 / Max: 76Min: 31 / Avg: 61.13 / Max: 75Min: 45 / Avg: 63.06 / Max: 79Min: 33 / Avg: 66.46 / Max: 80Min: 35 / Avg: 66.5 / Max: 80Min: 33 / Avg: 66.96 / Max: 79

System Power Consumption Monitor

Phoronix Test Suite System Monitoring

OpenBenchmarking.orgWattsSystem Power Consumption MonitorPhoronix Test Suite System MonitoringGTX 1070 TiRX Vega 56GTX 1070RTX 2070GTX 1080R9 FuryRX Vega 64RTX 2080GTX 1080 TiRTX 2080 Ti70140210280350Min: 45.9 / Avg: 127.84 / Max: 213.8Min: 48.8 / Avg: 143.52 / Max: 284.1Min: 41.9 / Avg: 143.92 / Max: 213.8Min: 42.1 / Avg: 146.13 / Max: 247.2Min: 42.2 / Avg: 154.56 / Max: 251.7Min: 79.9 / Avg: 160.12 / Max: 365.3Min: 48.4 / Avg: 169.45 / Max: 358.6Min: 43.9 / Avg: 175.16 / Max: 287.8Min: 43.4 / Avg: 200.91 / Max: 320.9Min: 45.5 / Avg: 208.03 / Max: 346.7

Chaos Group V-RAY

GPU Temperature Monitor

OpenBenchmarking.orgCelsius, Fewer Is BetterChaos Group V-RAY 1.1.0GPU Temperature MonitorGTX 1070 TiRTX 2080 TiRTX 2070GTX 1070GTX 1080GTX 1080 TiRTX 20801428425670Min: 38 / Avg: 47.77 / Max: 50Min: 46 / Avg: 60.03 / Max: 68Min: 53 / Avg: 60.72 / Max: 62Min: 46 / Avg: 62.55 / Max: 68Min: 48 / Avg: 62.93 / Max: 67Min: 54 / Avg: 68.11 / Max: 73Min: 50 / Avg: 68.2 / Max: 74

Chaos Group V-RAY

System Power Consumption Monitor

OpenBenchmarking.orgWatts, Fewer Is BetterChaos Group V-RAY 1.1.0System Power Consumption MonitorGTX 1070 TiGTX 1070GTX 1080RTX 2070RTX 2080GTX 1080 TiRTX 2080 Ti50100150200250Min: 46.1 / Avg: 130.78 / Max: 135.6Min: 43.4 / Avg: 151.17 / Max: 164.2Min: 43.6 / Avg: 153.26 / Max: 165.9Min: 53.7 / Avg: 185.77 / Max: 199.3Min: 63 / Avg: 191.71 / Max: 202.8Min: 120.4 / Avg: 218.99 / Max: 231.8Min: 69.5 / Avg: 242.72 / Max: 272

CUDA Mini-Nbody

GPU Temperature Monitor

OpenBenchmarking.orgCelsius, Fewer Is BetterCUDA Mini-Nbody 2015-11-10GPU Temperature MonitorGTX 1070 TiRTX 2070RTX 2080 TiGTX 1070GTX 1080RTX 2080GTX 1080 Ti1530456075Min: 45 / Avg: 56.11 / Max: 60Min: 55 / Avg: 60.44 / Max: 64Min: 58 / Avg: 64 / Max: 67Min: 61 / Avg: 70.86 / Max: 75Min: 64 / Avg: 73.06 / Max: 79Min: 65 / Avg: 73.5 / Max: 78Min: 65 / Avg: 74.42 / Max: 80

CUDA Mini-Nbody

System Power Consumption Monitor

OpenBenchmarking.orgWatts, Fewer Is BetterCUDA Mini-Nbody 2015-11-10System Power Consumption MonitorGTX 1070 TiGTX 1070RTX 2070GTX 1080RTX 2080RTX 2080 TiGTX 1080 Ti60120180240300Min: 47 / Avg: 185.31 / Max: 213.8Min: 43.7 / Avg: 194.09 / Max: 210.9Min: 54.3 / Avg: 215.38 / Max: 246.1Min: 43.7 / Avg: 223.02 / Max: 251.7Min: 48.7 / Avg: 233.61 / Max: 284Min: 49.1 / Avg: 234.64 / Max: 336Min: 50.5 / Avg: 249.72 / Max: 312.9

NVIDIA GPU Cloud TensorFlow

Test: ResNet-50, FP16

OpenBenchmarking.orgImages Per Second Per Watt, More Is BetterNVIDIA GPU Cloud TensorFlow 18.09Test: ResNet-50, FP16RTX 2080 TiRTX 2070RTX 2080GTX 1080 TiGTX 1070 TiGTX 1080GTX 10700.47250.9451.41751.892.36252.101.901.861.221.141.020.92

NVIDIA GPU Cloud TensorFlow

GPU Temperature Monitor

OpenBenchmarking.orgCelsius, Fewer Is BetterNVIDIA GPU Cloud TensorFlow 18.09GPU Temperature MonitorRTX 2070GTX 1070 TiRTX 2080 TiGTX 1070RTX 2080GTX 1080 TiGTX 10801428425670Min: 32 / Avg: 45.47 / Max: 58Min: 46 / Avg: 50.94 / Max: 55Min: 55 / Avg: 59.52 / Max: 65Min: 58 / Avg: 65.55 / Max: 70Min: 60 / Avg: 67.05 / Max: 75Min: 61 / Avg: 68.17 / Max: 75Min: 61 / Avg: 68.3 / Max: 75

NVIDIA GPU Cloud TensorFlow

System Power Consumption Monitor

OpenBenchmarking.orgWatts, Fewer Is BetterNVIDIA GPU Cloud TensorFlow 18.09System Power Consumption MonitorGTX 1070 TiRTX 2070GTX 1070RTX 2080GTX 1080RTX 2080 TiGTX 1080 Ti60120180240300Min: 47 / Avg: 153.76 / Max: 192.3Min: 71.1 / Avg: 162.36 / Max: 246.8Min: 42.7 / Avg: 174.04 / Max: 212.6Min: 47.3 / Avg: 179.59 / Max: 284.7Min: 44.7 / Avg: 189.85 / Max: 248.8Min: 56.1 / Avg: 213.62 / Max: 342.3Min: 54.6 / Avg: 222.3 / Max: 319.6

NVIDIA GPU Cloud TensorFlow

Test: ResNet-50, FP32

OpenBenchmarking.orgImages Per Second Per Watt, More Is BetterNVIDIA GPU Cloud TensorFlow 18.09Test: ResNet-50, FP32RTX 2080 TiRTX 2080GTX 1080 TiGTX 1070 TiGTX 1080GTX 10700.25880.51760.77641.03521.2941.150.990.890.840.730.73

NVIDIA GPU Cloud TensorFlow

GPU Temperature Monitor

OpenBenchmarking.orgCelsius, Fewer Is BetterNVIDIA GPU Cloud TensorFlow 18.09GPU Temperature MonitorGTX 1070 TiRTX 2080 TiGTX 1070GTX 1080GTX 1080 TiRTX 20801530456075Min: 44 / Avg: 50.85 / Max: 54Min: 54 / Avg: 61.16 / Max: 67Min: 57 / Avg: 65.61 / Max: 71Min: 60 / Avg: 68.77 / Max: 75Min: 62 / Avg: 70.04 / Max: 77Min: 59 / Avg: 70.41 / Max: 77

NVIDIA GPU Cloud TensorFlow

System Power Consumption Monitor

OpenBenchmarking.orgWatts, Fewer Is BetterNVIDIA GPU Cloud TensorFlow 18.09System Power Consumption MonitorGTX 1070 TiGTX 1070GTX 1080RTX 2080GTX 1080 TiRTX 2080 Ti60120180240300Min: 48 / Avg: 157.29 / Max: 187.8Min: 45.9 / Avg: 172.02 / Max: 213.8Min: 44.1 / Avg: 196.38 / Max: 249.7Min: 48 / Avg: 206.72 / Max: 285Min: 79.7 / Avg: 234.81 / Max: 318.6Min: 50.5 / Avg: 248.25 / Max: 346.7

NVIDIA GPU Cloud TensorFlow

Test: AlexNet, FP16

OpenBenchmarking.orgImages Per Second Per Watt, More Is BetterNVIDIA GPU Cloud TensorFlow 18.09Test: AlexNet, FP16RTX 2080 TiRTX 2080GTX 1080 TiGTX 1070 TiGTX 1080GTX 107061218243024.9516.5312.5312.3911.199.86

NVIDIA GPU Cloud TensorFlow

GPU Temperature Monitor

OpenBenchmarking.orgCelsius, Fewer Is BetterNVIDIA GPU Cloud TensorFlow 18.09GPU Temperature MonitorGTX 1070 TiRTX 2080 TiGTX 1070GTX 1080GTX 1080 TiRTX 20801428425670Min: 46 / Avg: 49.93 / Max: 53Min: 57 / Avg: 60.36 / Max: 64Min: 59 / Avg: 64.06 / Max: 67Min: 62 / Avg: 66.46 / Max: 70Min: 63 / Avg: 67.2 / Max: 70Min: 63 / Avg: 67.57 / Max: 72

NVIDIA GPU Cloud TensorFlow

System Power Consumption Monitor

OpenBenchmarking.orgWatts, Fewer Is BetterNVIDIA GPU Cloud TensorFlow 18.09System Power Consumption MonitorGTX 1070 TiGTX 1070GTX 1080RTX 2080 TiRTX 2080GTX 1080 Ti60120180240300Min: 46.9 / Avg: 135.79 / Max: 175Min: 68.9 / Avg: 158.49 / Max: 192.3Min: 44.1 / Avg: 167.55 / Max: 234.8Min: 49.3 / Avg: 177.62 / Max: 332.6Min: 47.3 / Avg: 190.7 / Max: 270.1Min: 51.3 / Avg: 213.37 / Max: 303.2

NVIDIA GPU Cloud TensorFlow

Test: AlexNet, FP32

OpenBenchmarking.orgImages Per Second Per Watt, More Is BetterNVIDIA GPU Cloud TensorFlow 18.09Test: AlexNet, FP32RTX 2080 TiGTX 1080 TiRTX 2070RTX 2080GTX 1070 TiGTX 1080GTX 1070369121512.9912.1911.7211.4410.999.909.61

NVIDIA GPU Cloud TensorFlow

GPU Temperature Monitor

OpenBenchmarking.orgCelsius, Fewer Is BetterNVIDIA GPU Cloud TensorFlow 18.09GPU Temperature MonitorGTX 1070 TiRTX 2070RTX 2080 TiGTX 1070GTX 1080GTX 1080 TiRTX 20801530456075Min: 44 / Avg: 49.07 / Max: 52Min: 46 / Avg: 55.88 / Max: 61Min: 53 / Avg: 61.36 / Max: 67Min: 61 / Avg: 64.2 / Max: 68Min: 63 / Avg: 66.8 / Max: 71Min: 64 / Avg: 67.58 / Max: 71Min: 59 / Avg: 69.81 / Max: 76

NVIDIA GPU Cloud TensorFlow

System Power Consumption Monitor

OpenBenchmarking.orgWatts, Fewer Is BetterNVIDIA GPU Cloud TensorFlow 18.09System Power Consumption MonitorGTX 1070 TiGTX 1070GTX 1080RTX 2070GTX 1080 TiRTX 2080RTX 2080 Ti60120180240300Min: 48.2 / Avg: 144.76 / Max: 185.9Min: 87.1 / Avg: 157.65 / Max: 201.5Min: 100.9 / Avg: 178.22 / Max: 229Min: 64.2 / Avg: 185.45 / Max: 243.7Min: 126 / Avg: 208.21 / Max: 307.4Min: 48 / Avg: 211.46 / Max: 284.1Min: 48.9 / Avg: 257.45 / Max: 338.7

NVIDIA GPU Cloud TensorFlow

Test: Googlenet, FP16

OpenBenchmarking.orgImages Per Second Per Watt, More Is BetterNVIDIA GPU Cloud TensorFlow 18.09Test: Googlenet, FP16RTX 2080 TiRTX 2080GTX 1070 TiGTX 1080 TiGTX 1080GTX 10700.91581.83162.74743.66324.5794.073.212.532.452.132.06

NVIDIA GPU Cloud TensorFlow

GPU Temperature Monitor

OpenBenchmarking.orgCelsius, Fewer Is BetterNVIDIA GPU Cloud TensorFlow 18.09GPU Temperature MonitorGTX 1070 TiRTX 2080 TiGTX 1070GTX 1080GTX 1080 TiRTX 20801530456075Min: 43 / Avg: 52.93 / Max: 56Min: 55 / Avg: 64.78 / Max: 71Min: 56 / Avg: 69 / Max: 74Min: 58 / Avg: 72.23 / Max: 79Min: 60 / Avg: 72.84 / Max: 80Min: 60 / Avg: 73.17 / Max: 80

NVIDIA GPU Cloud TensorFlow

System Power Consumption Monitor

OpenBenchmarking.orgWatts, Fewer Is BetterNVIDIA GPU Cloud TensorFlow 18.09System Power Consumption MonitorGTX 1070 TiGTX 1070GTX 1080RTX 2080RTX 2080 TiGTX 1080 Ti60120180240300Min: 46.8 / Avg: 163.6 / Max: 187.8Min: 43.4 / Avg: 181.99 / Max: 210.5Min: 76.2 / Avg: 215.22 / Max: 247Min: 47.7 / Avg: 229.8 / Max: 284.5Min: 49.5 / Avg: 249.29 / Max: 343.1Min: 64 / Avg: 257.4 / Max: 319.4

NVIDIA GPU Cloud TensorFlow

Test: Inception v4, FP16

OpenBenchmarking.orgImages Per Second Per Watt, More Is BetterNVIDIA GPU Cloud TensorFlow 18.09Test: Inception v4, FP16RTX 2080 TiRTX 2080GTX 1080 TiGTX 1070 TiGTX 1080GTX 10700.16650.3330.49950.6660.83250.740.580.350.340.300.28

NVIDIA GPU Cloud TensorFlow

GPU Temperature Monitor

OpenBenchmarking.orgCelsius, Fewer Is BetterNVIDIA GPU Cloud TensorFlow 18.09GPU Temperature MonitorGTX 1070 TiRTX 2080 TiGTX 1070GTX 1080RTX 2080GTX 1080 Ti1530456075Min: 43 / Avg: 49.56 / Max: 55Min: 53 / Avg: 57.76 / Max: 65Min: 55 / Avg: 64.07 / Max: 72Min: 51 / Avg: 64.33 / Max: 76Min: 57 / Avg: 64.7 / Max: 74Min: 56 / Avg: 66.24 / Max: 77

NVIDIA GPU Cloud TensorFlow

System Power Consumption Monitor

OpenBenchmarking.orgWatts, Fewer Is BetterNVIDIA GPU Cloud TensorFlow 18.09System Power Consumption MonitorGTX 1070 TiGTX 1070RTX 2080RTX 2080 TiGTX 1080GTX 1080 Ti60120180240300Min: 47.2 / Avg: 146.22 / Max: 188.6Min: 44.1 / Avg: 157.87 / Max: 210.2Min: 47.6 / Avg: 177.11 / Max: 285.3Min: 50 / Avg: 183.11 / Max: 341.1Min: 71.3 / Avg: 185.89 / Max: 249.7Min: 52.2 / Avg: 211.84 / Max: 320.9

NVIDIA GPU Cloud TensorFlow

Test: VGG-16, FP16

OpenBenchmarking.orgImages Per Second Per Watt, More Is BetterNVIDIA GPU Cloud TensorFlow 18.09Test: VGG-16, FP16RTX 2080 TiRTX 2080GTX 1080 TiGTX 1070 TiGTX 1080GTX 10700.21150.4230.63450.8461.05750.940.690.540.530.480.46

NVIDIA GPU Cloud TensorFlow

GPU Temperature Monitor

OpenBenchmarking.orgCelsius, Fewer Is BetterNVIDIA GPU Cloud TensorFlow 18.09GPU Temperature MonitorGTX 1070 TiRTX 2080 TiGTX 1080GTX 1070RTX 2080GTX 1080 Ti1530456075Min: 45 / Avg: 52.18 / Max: 55Min: 54 / Avg: 61.56 / Max: 68Min: 50 / Avg: 65.84 / Max: 74Min: 59 / Avg: 66.13 / Max: 70Min: 59 / Avg: 69.86 / Max: 77Min: 61 / Avg: 70.1 / Max: 76

NVIDIA GPU Cloud TensorFlow

System Power Consumption Monitor

OpenBenchmarking.orgWatts, Fewer Is BetterNVIDIA GPU Cloud TensorFlow 18.09System Power Consumption MonitorGTX 1070 TiGTX 1070GTX 1080RTX 2080 TiRTX 2080GTX 1080 Ti60120180240300Min: 46.8 / Avg: 160.44 / Max: 192Min: 43.7 / Avg: 168.53 / Max: 201.8Min: 90.8 / Avg: 194.86 / Max: 239.8Min: 51 / Avg: 219.66 / Max: 332.2Min: 48.1 / Avg: 223.76 / Max: 283.3Min: 51.7 / Avg: 242.51 / Max: 313.1

NVIDIA GPU Cloud TensorFlow

Test: VGG-16, FP32

OpenBenchmarking.orgImages Per Second Per Watt, More Is BetterNVIDIA GPU Cloud TensorFlow 18.09Test: VGG-16, FP32RTX 2080 TiGTX 1080 TiGTX 1070 TiRTX 2080GTX 1080GTX 10700.1260.2520.3780.5040.630.560.490.470.450.420.42

NVIDIA GPU Cloud TensorFlow

GPU Temperature Monitor

OpenBenchmarking.orgCelsius, Fewer Is BetterNVIDIA GPU Cloud TensorFlow 18.09GPU Temperature MonitorGTX 1070 TiRTX 2080 TiGTX 1070GTX 1080GTX 1080 TiRTX 20801530456075Min: 46 / Avg: 52.21 / Max: 55Min: 56 / Avg: 65.52 / Max: 71Min: 58 / Avg: 66.1 / Max: 70Min: 60 / Avg: 69.33 / Max: 74Min: 61 / Avg: 70.55 / Max: 77Min: 61 / Avg: 74.1 / Max: 80

NVIDIA GPU Cloud TensorFlow

System Power Consumption Monitor

OpenBenchmarking.orgWatts, Fewer Is BetterNVIDIA GPU Cloud TensorFlow 18.09System Power Consumption MonitorGTX 1070 TiGTX 1070GTX 1080RTX 2080GTX 1080 TiRTX 2080 Ti60120180240300Min: 58.5 / Avg: 162.02 / Max: 191Min: 54.1 / Avg: 170.77 / Max: 203.5Min: 46.3 / Avg: 198.19 / Max: 236.2Min: 55.7 / Avg: 239.26 / Max: 287.8Min: 51.2 / Avg: 241.65 / Max: 309.7Min: 50.2 / Avg: 270.5 / Max: 342.3

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 SPRX Vega 56RX Vega 64RTX 2070GTX 1080 TiRTX 2080RTX 2080 TiGTX 1070GTX 1070 TiGTX 10800.50851.0171.52552.0342.54252.262.251.671.391.361.201.131.111.051. RX Vega 56: $409 reported cost.2. RX Vega 64: $475 reported cost.3. RTX 2070: $599 reported cost.4. GTX 1080 Ti: $699 reported cost.5. RTX 2080: $798 reported cost.6. RTX 2080 Ti: $1199 reported cost.7. GTX 1070: $399 reported cost.8. GTX 1070 Ti: $449 reported cost.9. GTX 1080: $549 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 HashRX Vega 64RX Vega 56RTX 2080 TiRTX 2080RTX 2070GTX 1080 TiGTX 1080GTX 1070 TiGTX 10700.00680.01360.02040.02720.0340.030.030.030.030.030.030.030.030.031. RX Vega 64: $475 reported cost.2. RX Vega 56: $409 reported cost.3. RTX 2080 Ti: $1199 reported cost.4. RTX 2080: $798 reported cost.5. RTX 2070: $599 reported cost.6. GTX 1080 Ti: $699 reported cost.7. GTX 1080: $549 reported cost.8. GTX 1070 Ti: $449 reported cost.9. GTX 1070: $399 reported cost.

SHOC Scalable HeterOgeneous Computing

Performance / Cost - Target: OpenCL - Benchmark: Texture Read Bandwidth

OpenBenchmarking.orgGB/s Per Dollar, More Is BetterSHOC Scalable HeterOgeneous Computing 2015-11-10Performance / Cost - Target: OpenCL - Benchmark: Texture Read BandwidthRTX 2070RTX 2080GTX 1070GTX 1080GTX 1070 TiRTX 2080 TiRX Vega 56RX Vega 64GTX 1080 Ti0.4140.8281.2421.6562.071.841.401.130.970.960.950.940.930.851. RTX 2070: $599 reported cost.2. RTX 2080: $798 reported cost.3. GTX 1070: $399 reported cost.4. GTX 1080: $549 reported cost.5. GTX 1070 Ti: $449 reported cost.6. RTX 2080 Ti: $1199 reported cost.7. RX Vega 56: $409 reported cost.8. RX Vega 64: $475 reported cost.9. GTX 1080 Ti: $699 reported cost.

cl-mem

Performance / Cost - Benchmark: Copy

OpenBenchmarking.orgGB/s Per Dollar, More Is Bettercl-mem 2017-01-13Performance / Cost - Benchmark: CopyRTX 2070RX Vega 56RX Vega 64GTX 1070GTX 1080 TiGTX 1070 TiRTX 2080RTX 2080 TiGTX 10800.12380.24760.37140.49520.6190.550.500.470.470.450.420.410.380.381. RTX 2070: $599 reported cost.2. RX Vega 56: $409 reported cost.3. RX Vega 64: $475 reported cost.4. GTX 1070: $399 reported cost.5. GTX 1080 Ti: $699 reported cost.6. GTX 1070 Ti: $449 reported cost.7. RTX 2080: $798 reported cost.8. RTX 2080 Ti: $1199 reported cost.9. GTX 1080: $549 reported cost.

LuxMark

Performance / Cost - OpenCL Device: GPU - Scene: Luxball HDR

OpenBenchmarking.orgScore Per Dollar, More Is BetterLuxMark 3.1Performance / Cost - OpenCL Device: GPU - Scene: Luxball HDRRX Vega 56RX Vega 64RTX 2070GTX 1070GTX 1070 TiRTX 2080RTX 2080 TiGTX 1080 TiGTX 10802040608010076.2369.0850.2443.3337.6137.1435.6130.8525.181. RX Vega 56: $409 reported cost.2. RX Vega 64: $475 reported cost.3. RTX 2070: $599 reported cost.4. GTX 1070: $399 reported cost.5. GTX 1070 Ti: $449 reported cost.6. RTX 2080: $798 reported cost.7. RTX 2080 Ti: $1199 reported cost.8. GTX 1080 Ti: $699 reported cost.9. GTX 1080: $549 reported cost.

clpeak

Performance / Cost - OpenCL Test: Kernel Latency

OpenBenchmarking.orgus x Dollar, Fewer Is BetterclpeakPerformance / Cost - OpenCL Test: Kernel LatencyGTX 1070GTX 1070 TiGTX 1080RTX 2070GTX 1080 TiRTX 2080RX Vega 56RX Vega 64RTX 2080 Ti90018002700360045001492.261643.342042.282108.482656.202777.042854.823296.504280.431. GTX 1070: $399 reported cost.2. GTX 1070 Ti: $449 reported cost.3. GTX 1080: $549 reported cost.4. RTX 2070: $599 reported cost.5. GTX 1080 Ti: $699 reported cost.6. RTX 2080: $798 reported cost.7. RX Vega 56: $409 reported cost.8. RX Vega 64: $475 reported cost.9. RTX 2080 Ti: $1199 reported cost.

clpeak

Performance / Cost - OpenCL Test: Integer Compute INT

OpenBenchmarking.orgGIOPS Per Dollar, More Is BetterclpeakPerformance / Cost - OpenCL Test: Integer Compute INTRTX 2070RTX 2080RTX 2080 TiRX Vega 64RX Vega 56GTX 1080 TiGTX 1070 TiGTX 1080GTX 1070369121513.3712.6112.005.244.874.754.644.444.241. RTX 2070: $599 reported cost.2. RTX 2080: $798 reported cost.3. RTX 2080 Ti: $1199 reported cost.4. RX Vega 64: $475 reported cost.5. RX Vega 56: $409 reported cost.6. GTX 1080 Ti: $699 reported cost.7. GTX 1070 Ti: $449 reported cost.8. GTX 1080: $549 reported cost.9. GTX 1070: $399 reported cost.

Phoronix Test Suite v10.8.5