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&grr&rdt.

NVIDIA AMD Linux GPU Compute December 2018ProcessorMotherboardChipsetMemoryDiskGraphicsAudioMonitorNetworkOSKernelDesktopDisplay ServerOpenGLOpenCLVulkanCompilerFile-SystemScreen ResolutionDisplay DriverRX Vega 56RX Vega 64R9 FuryGTX 1080RTX 2080 TiRTX 2080RTX 2070GTX 1080 TiGTX 1070 TiGTX 1070Intel 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 250GBAMD Radeon RX Vega 8GB (1590/800MHz)Realtek ALC1220Acer B286HKIntel ConnectionUbuntu 18.044.19.5-041905-generic (x86_64)GNOME Shell 3.28.3X Server 1.19.64.5 Mesa 19.0.0-devel padoka PPA (LLVM 8.0.0)OpenCL 2.1 AMD-APP (2679.0)1.1.70GCC 7.3.0ext43840x2160AMD Radeon RX Vega 8GB (1630/945MHz)Sapphire AMD Radeon R9 FURY / NANO 4GB (1000/500MHz)NVIDIA GeForce GTX 1080 8GB (1607/5005MHz)NVIDIA 415.224.6.0OpenCL 1.2 CUDA 10.0.1321.1.84GCC 7.3.0 + CUDA 10.0NVIDIA GeForce RTX 2080 Ti 11GB (1350/7000MHz)Zotac NVIDIA GeForce RTX 2080 8GB (1515/7000MHz)eVGA NVIDIA GeForce RTX 2070 8GB (1410/7000MHz)NVIDIA GeForce GTX 1080 Ti 11GB (1480/5508MHz)Zotac NVIDIA GeForce GTX 1070 Ti 8GB (1607/4006MHz)NVIDIA GeForce GTX 1070 8GB (1506/4006MHz)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 performanceSecurity Details- __user pointer sanitization + Full generic retpoline IBPB IBRS_FW + SSB disabled via prctl and seccompOpenCL Details- GTX 1080: GPU Compute Cores: 2560- RTX 2080 Ti: GPU Compute Cores: 4352- RTX 2080: GPU Compute Cores: 2944- RTX 2070: GPU Compute Cores: 2304- GTX 1080 Ti: GPU Compute Cores: 3584- GTX 1070 Ti: GPU Compute Cores: 2432- GTX 1070: GPU Compute Cores: 1920

NVIDIA AMD Linux GPU Compute December 2018luxmark: GPU - Luxball HDRngc-tensorflow: Inception v4, FP16v-ray: CUDA GPUngc-tensorflow: Googlenet, FP16ngc-tensorflow: ResNet-50, FP32ngc-tensorflow: VGG-16, FP32ngc-tensorflow: ResNet-50, FP16ngc-tensorflow: VGG-16, FP16clpeak: Integer Compute INTclpeak: Kernel Latencyngc-tensorflow: AlexNet, FP32cuda-mini-nbody: Originalngc-tensorflow: AlexNet, FP16shoc: OpenCL - Texture Read Bandwidthcl-mem: Copyshoc: OpenCL - FFT SPshoc: OpenCL - MD5 HashRX Vega 56RX Vega 64R9 FuryGTX 1080RTX 2080 TiRTX 2080RTX 2070GTX 1080 TiGTX 1070 TiGTX 10703117919916.9838420392614.033281524916.94442221107016.532344814305.682502058469.201382355.03102.0745814382.9019393.1324373.721764111187553020957514.1742693135.9056.091015285152.40449206.97143853.57334442644321134454144335.8629641102.7772.07738205108.57335153.33100593.48241930431531119328108324.373009166.0230980073.522174244110133099819.292156274.6366.41629210119.50271131.3733213.802539186267459531797219.961688649.2386.3041313376.4017584.4320823.661591112168343318849711.631728844.7790.4337512571.5716076.9316923.74151691.99156345118745210.72OpenBenchmarking.org

LuxMark

OpenCL Device: GPU - Scene: Luxball HDR

OpenBenchmarking.orgScore, More Is BetterLuxMark 3.1OpenCL Device: GPU - Scene: Luxball HDRRX Vega 56RX Vega 64R9 FuryGTX 1080RTX 2080 TiRTX 2080RTX 2070GTX 1080 TiGTX 1070 TiGTX 10709K18K27K36K45KSE +/- 20.53, N = 3SE +/- 570.76, N = 3SE +/- 36.02, N = 3SE +/- 29.04, N = 3SE +/- 66.64, N = 3SE +/- 2.73, N = 3SE +/- 119.86, N = 3SE +/- 0.67, N = 3SE +/- 0.58, N = 331179328152344813823426932964130091215621688617288

NVIDIA GPU Cloud TensorFlow

Test: Inception v4, FP16

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA GPU Cloud TensorFlow 18.09Test: Inception v4, FP16GTX 1080RTX 2080 TiRTX 2080GTX 1080 TiGTX 1070 TiGTX 1070306090120150SE +/- 0.03, N = 3SE +/- 0.10, N = 3SE +/- 0.07, N = 3SE +/- 0.07, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 355.03135.90102.7774.6349.2344.77

Chaos Group V-RAY

Mode: CUDA GPU

OpenBenchmarking.orgSeconds, Fewer Is BetterChaos Group V-RAY 1.1.0Mode: CUDA GPUGTX 1080RTX 2080 TiRTX 2080RTX 2070GTX 1080 TiGTX 1070 TiGTX 107020406080100SE +/- 3.08, N = 3SE +/- 3.00, N = 3SE +/- 0.04, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.04, N = 3SE +/- 0.03, N = 3102.0756.0972.0766.0266.4186.3090.43

NVIDIA GPU Cloud TensorFlow

Test: Googlenet, FP16

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA GPU Cloud TensorFlow 18.09Test: Googlenet, FP16GTX 1080RTX 2080 TiRTX 2080GTX 1080 TiGTX 1070 TiGTX 10702004006008001000SE +/- 0.21, N = 3SE +/- 0.49, N = 3SE +/- 0.58, N = 3SE +/- 2.49, N = 3SE +/- 0.09, N = 3SE +/- 0.35, N = 34581015738629413375

NVIDIA GPU Cloud TensorFlow

Test: ResNet-50, FP32

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA GPU Cloud TensorFlow 18.09Test: ResNet-50, FP32GTX 1080RTX 2080 TiRTX 2080GTX 1080 TiGTX 1070 TiGTX 107060120180240300SE +/- 0.07, N = 3SE +/- 0.44, N = 3SE +/- 0.28, N = 3SE +/- 0.19, N = 3SE +/- 0.06, N = 3SE +/- 0.09, N = 3143285205210133125

NVIDIA GPU Cloud TensorFlow

Test: VGG-16, FP32

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA GPU Cloud TensorFlow 18.09Test: VGG-16, FP32GTX 1080RTX 2080 TiRTX 2080GTX 1080 TiGTX 1070 TiGTX 1070306090120150SE +/- 0.00, N = 3SE +/- 0.12, N = 3SE +/- 0.07, N = 3SE +/- 0.12, N = 3SE +/- 0.00, N = 3SE +/- 0.13, N = 382.90152.40108.57119.5076.4071.57

NVIDIA GPU Cloud TensorFlow

Test: ResNet-50, FP16

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA GPU Cloud TensorFlow 18.09Test: ResNet-50, FP16GTX 1080RTX 2080 TiRTX 2080RTX 2070GTX 1080 TiGTX 1070 TiGTX 1070100200300400500SE +/- 0.10, N = 3SE +/- 0.28, N = 3SE +/- 0.85, N = 3SE +/- 0.15, N = 3SE +/- 0.07, N = 3SE +/- 0.03, N = 3193449335309271175160

NVIDIA GPU Cloud TensorFlow

Test: VGG-16, FP16

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA GPU Cloud TensorFlow 18.09Test: VGG-16, FP16GTX 1080RTX 2080 TiRTX 2080GTX 1080 TiGTX 1070 TiGTX 107050100150200250SE +/- 0.24, N = 3SE +/- 0.07, N = 3SE +/- 0.09, N = 3SE +/- 0.12, N = 3SE +/- 0.03, N = 3SE +/- 0.07, N = 393.13206.97153.33131.3784.4376.93

clpeak

OpenCL Test: Integer Compute INT

OpenBenchmarking.orgGIOPS, More Is BetterclpeakOpenCL Test: Integer Compute INTRX Vega 56RX Vega 64R9 FuryGTX 1080RTX 2080 TiRTX 2080RTX 2070GTX 1080 TiGTX 1070 TiGTX 10703K6K9K12K15KSE +/- 1.96, N = 3SE +/- 1.38, N = 3SE +/- 0.00, N = 3SE +/- 8.46, N = 3SE +/- 946.18, N = 3SE +/- 601.95, N = 3SE +/- 552.67, N = 3SE +/- 12.10, N = 3SE +/- 0.67, N = 3SE +/- 9.42, N = 3199124911430243714385100598007332120821692

clpeak

OpenCL Test: Kernel Latency

OpenBenchmarking.orgus, Fewer Is BetterclpeakOpenCL Test: Kernel LatencyRX Vega 56RX Vega 64R9 FuryGTX 1080RTX 2080 TiRTX 2080RTX 2070GTX 1080 TiGTX 1070 TiGTX 1070246810SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.03, N = 3SE +/- 0.02, N = 3SE +/- 0.12, N = 3SE +/- 0.05, N = 3SE +/- 0.06, N = 3SE +/- 0.05, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 36.986.945.683.723.573.483.523.803.663.74

NVIDIA GPU Cloud TensorFlow

Test: AlexNet, FP32

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA GPU Cloud TensorFlow 18.09Test: AlexNet, FP32GTX 1080RTX 2080 TiRTX 2080RTX 2070GTX 1080 TiGTX 1070 TiGTX 10707001400210028003500SE +/- 1.62, N = 3SE +/- 6.99, N = 3SE +/- 1.84, N = 3SE +/- 1.83, N = 3SE +/- 0.32, N = 3SE +/- 0.44, N = 31764334424192174253915911516

CUDA Mini-Nbody

Test: Original

OpenBenchmarking.org(NBody^2)/s, More Is BetterCUDA Mini-Nbody 2015-11-10Test: OriginalGTX 1080RTX 2080 TiRTX 2080RTX 2070GTX 1080 TiGTX 1070 TiGTX 107090180270360450SE +/- 0.17, N = 3SE +/- 0.80, N = 3SE +/- 0.92, N = 3SE +/- 0.61, N = 3SE +/- 0.19, N = 3SE +/- 0.07, N = 3SE +/- 0.16, N = 3111.00426.00304.00244.00186.00112.0091.99

NVIDIA GPU Cloud TensorFlow

Test: AlexNet, FP16

OpenBenchmarking.orgImages Per Second, More Is BetterNVIDIA GPU Cloud TensorFlow 18.09Test: AlexNet, FP16GTX 1080RTX 2080 TiRTX 2080GTX 1080 TiGTX 1070 TiGTX 107010002000300040005000SE +/- 2.60, N = 3SE +/- 2.27, N = 3SE +/- 3.35, N = 3SE +/- 1.32, N = 3SE +/- 0.50, N = 3SE +/- 2.26, N = 3187544323153267416831563

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 BandwidthRX Vega 56RX Vega 64R9 FuryGTX 1080RTX 2080 TiRTX 2080RTX 2070GTX 1080 TiGTX 1070 TiGTX 10702004006008001000SE +/- 0.54, N = 3SE +/- 1.72, N = 3SE +/- 1.14, N = 3SE +/- 0.39, N = 3SE +/- 3.81, N = 3SE +/- 3.18, N = 3SE +/- 1.33, N = 3SE +/- 2.41, N = 3SE +/- 0.09, N = 3SE +/- 0.06, N = 3384442250530113411191101595433451-lSHOCCommonOpenCL -lOpenCL-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 -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 -lcufft1. (CXX) g++ options: -O2 -lSHOCCommon -lrt

cl-mem

Benchmark: Copy

OpenBenchmarking.orgGB/s, More Is Bettercl-mem 2017-01-13Benchmark: CopyRX Vega 56RX Vega 64R9 FuryGTX 1080RTX 2080 TiRTX 2080RTX 2070GTX 1080 TiGTX 1070 TiGTX 1070100200300400500SE +/- 0.21, N = 3SE +/- 0.07, N = 3SE +/- 0.47, N = 3SE +/- 0.07, N = 3SE +/- 0.39, N = 3SE +/- 0.09, N = 3SE +/- 0.12, N = 3SE +/- 0.07, N = 3SE +/- 0.07, N = 3SE +/- 0.07, N = 32032212052094543283303171881871. (CC) gcc options: -O2 -flto -lOpenCL

SHOC Scalable HeterOgeneous Computing

Target: OpenCL - Benchmark: FFT SP

OpenBenchmarking.orgGFLOPS, More Is BetterSHOC Scalable HeterOgeneous Computing 2015-11-10Target: OpenCL - Benchmark: FFT SPRX Vega 56RX Vega 64R9 FuryGTX 1080RTX 2080 TiRTX 2080RTX 2070GTX 1080 TiGTX 1070 TiGTX 107030060090012001500SE +/- 1.57, N = 3SE +/- 0.64, N = 3SE +/- 0.09, N = 3SE +/- 2.68, N = 3SE +/- 14.24, N = 3SE +/- 5.95, N = 3SE +/- 40.79, N = 3SE +/- 1.23, N = 3SE +/- 0.73, N = 3SE +/- 0.94, N = 3926107084657514431083998972497452-lSHOCCommonOpenCL -lOpenCL-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 -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 -lcufft1. (CXX) g++ options: -O2 -lSHOCCommon -lrt

SHOC Scalable HeterOgeneous Computing

Target: OpenCL - Benchmark: MD5 Hash

OpenBenchmarking.orgGHash/s, More Is BetterSHOC Scalable HeterOgeneous Computing 2015-11-10Target: OpenCL - Benchmark: MD5 HashRX Vega 56RX Vega 64R9 FuryGTX 1080RTX 2080 TiRTX 2080RTX 2070GTX 1080 TiGTX 1070 TiGTX 1070816243240SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.00, N = 3SE +/- 0.02, N = 3SE +/- 0.34, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.06, N = 3SE +/- 0.00, N = 3SE +/- 0.02, N = 314.0316.539.2014.1735.8624.3719.2919.9611.6310.72-lSHOCCommonOpenCL -lOpenCL-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 -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 -lcufft1. (CXX) g++ options: -O2 -lSHOCCommon -lrt

clpeak

Performance / Cost - OpenCL Test: Integer Compute INT

OpenBenchmarking.orgGIOPS Per Dollar, More Is BetterclpeakPerformance / Cost - OpenCL Test: Integer Compute INTRX Vega 56RX Vega 64GTX 1080RTX 2080 TiRTX 2080RTX 2070GTX 1080 TiGTX 1070 TiGTX 107036912154.875.244.4412.0012.6113.374.754.644.241. RX Vega 56: $409 reported cost.2. RX Vega 64: $475 reported cost.3. GTX 1080: $549 reported cost.4. RTX 2080 Ti: $1199 reported cost.5. RTX 2080: $798 reported cost.6. RTX 2070: $599 reported cost.7. GTX 1080 Ti: $699 reported cost.8. GTX 1070 Ti: $449 reported cost.9. GTX 1070: $399 reported cost.

clpeak

Performance / Cost - OpenCL Test: Kernel Latency

OpenBenchmarking.orgus x Dollar, Fewer Is BetterclpeakPerformance / Cost - OpenCL Test: Kernel LatencyRX Vega 56RX Vega 64GTX 1080RTX 2080 TiRTX 2080RTX 2070GTX 1080 TiGTX 1070 TiGTX 107090018002700360045002854.823296.502042.284280.432777.042108.482656.201643.341492.261. RX Vega 56: $409 reported cost.2. RX Vega 64: $475 reported cost.3. GTX 1080: $549 reported cost.4. RTX 2080 Ti: $1199 reported cost.5. RTX 2080: $798 reported cost.6. RTX 2070: $599 reported cost.7. GTX 1080 Ti: $699 reported cost.8. GTX 1070 Ti: $449 reported cost.9. GTX 1070: $399 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 64GTX 1080RTX 2080 TiRTX 2080RTX 2070GTX 1080 TiGTX 1070 TiGTX 10702040608010076.2369.0825.1835.6137.1450.2430.8537.6143.331. RX Vega 56: $409 reported cost.2. RX Vega 64: $475 reported cost.3. GTX 1080: $549 reported cost.4. RTX 2080 Ti: $1199 reported cost.5. RTX 2080: $798 reported cost.6. RTX 2070: $599 reported cost.7. GTX 1080 Ti: $699 reported cost.8. GTX 1070 Ti: $449 reported cost.9. GTX 1070: $399 reported cost.

cl-mem

Performance / Cost - Benchmark: Copy

OpenBenchmarking.orgGB/s Per Dollar, More Is Bettercl-mem 2017-01-13Performance / Cost - Benchmark: CopyRX Vega 56RX Vega 64GTX 1080RTX 2080 TiRTX 2080RTX 2070GTX 1080 TiGTX 1070 TiGTX 10700.12380.24760.37140.49520.6190.500.470.380.380.410.550.450.420.471. RX Vega 56: $409 reported cost.2. RX Vega 64: $475 reported cost.3. GTX 1080: $549 reported cost.4. RTX 2080 Ti: $1199 reported cost.5. RTX 2080: $798 reported cost.6. RTX 2070: $599 reported cost.7. GTX 1080 Ti: $699 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 BandwidthRX Vega 56RX Vega 64GTX 1080RTX 2080 TiRTX 2080RTX 2070GTX 1080 TiGTX 1070 TiGTX 10700.4140.8281.2421.6562.070.940.930.970.951.401.840.850.961.131. RX Vega 56: $409 reported cost.2. RX Vega 64: $475 reported cost.3. GTX 1080: $549 reported cost.4. RTX 2080 Ti: $1199 reported cost.5. RTX 2080: $798 reported cost.6. RTX 2070: $599 reported cost.7. GTX 1080 Ti: $699 reported cost.8. GTX 1070 Ti: $449 reported cost.9. GTX 1070: $399 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 56RX Vega 64GTX 1080RTX 2080 TiRTX 2080RTX 2070GTX 1080 TiGTX 1070 TiGTX 10700.00680.01360.02040.02720.0340.030.030.030.030.030.030.030.030.031. RX Vega 56: $409 reported cost.2. RX Vega 64: $475 reported cost.3. GTX 1080: $549 reported cost.4. RTX 2080 Ti: $1199 reported cost.5. RTX 2080: $798 reported cost.6. RTX 2070: $599 reported cost.7. GTX 1080 Ti: $699 reported cost.8. GTX 1070 Ti: $449 reported cost.9. GTX 1070: $399 reported cost.

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 64GTX 1080RTX 2080 TiRTX 2080RTX 2070GTX 1080 TiGTX 1070 TiGTX 10700.50851.0171.52552.0342.54252.262.251.051.201.361.671.391.111.131. RX Vega 56: $409 reported cost.2. RX Vega 64: $475 reported cost.3. GTX 1080: $549 reported cost.4. RTX 2080 Ti: $1199 reported cost.5. RTX 2080: $798 reported cost.6. RTX 2070: $599 reported cost.7. GTX 1080 Ti: $699 reported cost.8. GTX 1070 Ti: $449 reported cost.9. GTX 1070: $399 reported cost.

NVIDIA GPU Cloud TensorFlow

System Power Consumption Monitor

OpenBenchmarking.orgWatts, Fewer Is BetterNVIDIA GPU Cloud TensorFlow 18.09System Power Consumption MonitorGTX 1080RTX 2080 TiRTX 2080GTX 1080 TiGTX 1070 TiGTX 107060120180240300Min: 46.3 / Avg: 198.19 / Max: 236.2Min: 50.2 / Avg: 270.5 / Max: 342.3Min: 55.7 / Avg: 239.26 / Max: 287.8Min: 51.2 / Avg: 241.65 / Max: 309.7Min: 58.5 / Avg: 162.02 / Max: 191Min: 54.1 / Avg: 170.77 / Max: 203.5

NVIDIA GPU Cloud TensorFlow

GPU Temperature Monitor

OpenBenchmarking.orgCelsius, Fewer Is BetterNVIDIA GPU Cloud TensorFlow 18.09GPU Temperature MonitorGTX 1080RTX 2080 TiRTX 2080GTX 1080 TiGTX 1070 TiGTX 10701530456075Min: 60 / Avg: 69.33 / Max: 74Min: 56 / Avg: 65.52 / Max: 71Min: 61 / Avg: 74.1 / Max: 80Min: 61 / Avg: 70.55 / Max: 77Min: 46 / Avg: 52.21 / Max: 55Min: 58 / Avg: 66.1 / Max: 70

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 1080RTX 2080 TiRTX 2080GTX 1080 TiGTX 1070 TiGTX 10700.1260.2520.3780.5040.630.420.560.450.490.470.42

NVIDIA GPU Cloud TensorFlow

System Power Consumption Monitor

OpenBenchmarking.orgWatts, Fewer Is BetterNVIDIA GPU Cloud TensorFlow 18.09System Power Consumption MonitorGTX 1080RTX 2080 TiRTX 2080GTX 1080 TiGTX 1070 TiGTX 107060120180240300Min: 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: 313.1Min: 46.8 / Avg: 160.44 / Max: 192Min: 43.7 / Avg: 168.53 / Max: 201.8

NVIDIA GPU Cloud TensorFlow

GPU Temperature Monitor

OpenBenchmarking.orgCelsius, Fewer Is BetterNVIDIA GPU Cloud TensorFlow 18.09GPU Temperature MonitorGTX 1080RTX 2080 TiRTX 2080GTX 1080 TiGTX 1070 TiGTX 10701530456075Min: 50 / Avg: 65.84 / Max: 74Min: 54 / Avg: 61.56 / Max: 68Min: 59 / Avg: 69.86 / Max: 77Min: 61 / Avg: 70.1 / Max: 76Min: 45 / Avg: 52.18 / Max: 55Min: 59 / Avg: 66.13 / Max: 70

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 1080RTX 2080 TiRTX 2080GTX 1080 TiGTX 1070 TiGTX 10700.21150.4230.63450.8461.05750.480.940.690.540.530.46

NVIDIA GPU Cloud TensorFlow

System Power Consumption Monitor

OpenBenchmarking.orgWatts, Fewer Is BetterNVIDIA GPU Cloud TensorFlow 18.09System Power Consumption MonitorGTX 1080RTX 2080 TiRTX 2080GTX 1080 TiGTX 1070 TiGTX 107060120180240300Min: 71.3 / Avg: 185.89 / Max: 249.7Min: 50 / Avg: 183.11 / Max: 341.1Min: 47.6 / Avg: 177.11 / Max: 285.3Min: 52.2 / Avg: 211.84 / Max: 320.9Min: 47.2 / Avg: 146.22 / Max: 188.6Min: 44.1 / Avg: 157.87 / Max: 210.2

NVIDIA GPU Cloud TensorFlow

GPU Temperature Monitor

OpenBenchmarking.orgCelsius, Fewer Is BetterNVIDIA GPU Cloud TensorFlow 18.09GPU Temperature MonitorGTX 1080RTX 2080 TiRTX 2080GTX 1080 TiGTX 1070 TiGTX 10701530456075Min: 51 / Avg: 64.33 / Max: 76Min: 53 / Avg: 57.76 / Max: 65Min: 57 / Avg: 64.7 / Max: 74Min: 56 / Avg: 66.24 / Max: 77Min: 43 / Avg: 49.56 / Max: 55Min: 55 / Avg: 64.07 / Max: 72

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 1080RTX 2080 TiRTX 2080GTX 1080 TiGTX 1070 TiGTX 10700.16650.3330.49950.6660.83250.300.740.580.350.340.28

NVIDIA GPU Cloud TensorFlow

System Power Consumption Monitor

OpenBenchmarking.orgWatts, Fewer Is BetterNVIDIA GPU Cloud TensorFlow 18.09System Power Consumption MonitorGTX 1080RTX 2080 TiRTX 2080GTX 1080 TiGTX 1070 TiGTX 107060120180240300Min: 76.2 / Avg: 215.22 / Max: 247Min: 49.5 / Avg: 249.29 / Max: 343.1Min: 47.7 / Avg: 229.8 / Max: 284.5Min: 64 / Avg: 257.4 / Max: 319.4Min: 46.8 / Avg: 163.6 / Max: 187.8Min: 43.4 / Avg: 181.99 / Max: 210.5

NVIDIA GPU Cloud TensorFlow

GPU Temperature Monitor

OpenBenchmarking.orgCelsius, Fewer Is BetterNVIDIA GPU Cloud TensorFlow 18.09GPU Temperature MonitorGTX 1080RTX 2080 TiRTX 2080GTX 1080 TiGTX 1070 TiGTX 10701530456075Min: 58 / Avg: 72.23 / Max: 79Min: 55 / Avg: 64.78 / Max: 71Min: 60 / Avg: 73.17 / Max: 80Min: 60 / Avg: 72.84 / Max: 80Min: 43 / Avg: 52.93 / Max: 56Min: 56 / Avg: 69 / Max: 74

NVIDIA GPU Cloud TensorFlow

Test: Googlenet, FP16

OpenBenchmarking.orgImages Per Second Per Watt, More Is BetterNVIDIA GPU Cloud TensorFlow 18.09Test: Googlenet, FP16GTX 1080RTX 2080 TiRTX 2080GTX 1080 TiGTX 1070 TiGTX 10700.91581.83162.74743.66324.5792.134.073.212.452.532.06

NVIDIA GPU Cloud TensorFlow

System Power Consumption Monitor

OpenBenchmarking.orgWatts, Fewer Is BetterNVIDIA GPU Cloud TensorFlow 18.09System Power Consumption MonitorGTX 1080RTX 2080 TiRTX 2080RTX 2070GTX 1080 TiGTX 1070 TiGTX 107060120180240300Min: 100.9 / Avg: 178.22 / Max: 229Min: 48.9 / Avg: 257.45 / Max: 338.7Min: 48 / Avg: 211.46 / Max: 284.1Min: 64.2 / Avg: 185.45 / Max: 243.7Min: 126 / Avg: 208.21 / Max: 307.4Min: 48.2 / Avg: 144.76 / Max: 185.9Min: 87.1 / Avg: 157.65 / Max: 201.5

NVIDIA GPU Cloud TensorFlow

GPU Temperature Monitor

OpenBenchmarking.orgCelsius, Fewer Is BetterNVIDIA GPU Cloud TensorFlow 18.09GPU Temperature MonitorGTX 1080RTX 2080 TiRTX 2080RTX 2070GTX 1080 TiGTX 1070 TiGTX 10701530456075Min: 63 / Avg: 66.8 / Max: 71Min: 53 / Avg: 61.36 / Max: 67Min: 59 / Avg: 69.81 / Max: 76Min: 46 / Avg: 55.88 / Max: 61Min: 64 / Avg: 67.58 / Max: 71Min: 44 / Avg: 49.07 / Max: 52Min: 61 / Avg: 64.2 / Max: 68

NVIDIA GPU Cloud TensorFlow

Test: AlexNet, FP32

OpenBenchmarking.orgImages Per Second Per Watt, More Is BetterNVIDIA GPU Cloud TensorFlow 18.09Test: AlexNet, FP32GTX 1080RTX 2080 TiRTX 2080RTX 2070GTX 1080 TiGTX 1070 TiGTX 107036912159.9012.9911.4411.7212.1910.999.61

NVIDIA GPU Cloud TensorFlow

System Power Consumption Monitor

OpenBenchmarking.orgWatts, Fewer Is BetterNVIDIA GPU Cloud TensorFlow 18.09System Power Consumption MonitorGTX 1080RTX 2080 TiRTX 2080GTX 1080 TiGTX 1070 TiGTX 107060120180240300Min: 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: 303.2Min: 46.9 / Avg: 135.79 / Max: 175Min: 68.9 / Avg: 158.49 / Max: 192.3

NVIDIA GPU Cloud TensorFlow

GPU Temperature Monitor

OpenBenchmarking.orgCelsius, Fewer Is BetterNVIDIA GPU Cloud TensorFlow 18.09GPU Temperature MonitorGTX 1080RTX 2080 TiRTX 2080GTX 1080 TiGTX 1070 TiGTX 10701428425670Min: 62 / Avg: 66.46 / Max: 70Min: 57 / Avg: 60.36 / Max: 64Min: 63 / Avg: 67.57 / Max: 72Min: 63 / Avg: 67.2 / Max: 70Min: 46 / Avg: 49.93 / Max: 53Min: 59 / Avg: 64.06 / Max: 67

NVIDIA GPU Cloud TensorFlow

Test: AlexNet, FP16

OpenBenchmarking.orgImages Per Second Per Watt, More Is BetterNVIDIA GPU Cloud TensorFlow 18.09Test: AlexNet, FP16GTX 1080RTX 2080 TiRTX 2080GTX 1080 TiGTX 1070 TiGTX 107061218243011.1924.9516.5312.5312.399.86

NVIDIA GPU Cloud TensorFlow

System Power Consumption Monitor

OpenBenchmarking.orgWatts, Fewer Is BetterNVIDIA GPU Cloud TensorFlow 18.09System Power Consumption MonitorGTX 1080RTX 2080 TiRTX 2080GTX 1080 TiGTX 1070 TiGTX 107060120180240300Min: 44.1 / Avg: 196.38 / Max: 249.7Min: 50.5 / Avg: 248.25 / Max: 346.7Min: 48 / Avg: 206.72 / Max: 285Min: 79.7 / Avg: 234.81 / Max: 318.6Min: 48 / Avg: 157.29 / Max: 187.8Min: 45.9 / Avg: 172.02 / Max: 213.8

NVIDIA GPU Cloud TensorFlow

GPU Temperature Monitor

OpenBenchmarking.orgCelsius, Fewer Is BetterNVIDIA GPU Cloud TensorFlow 18.09GPU Temperature MonitorGTX 1080RTX 2080 TiRTX 2080GTX 1080 TiGTX 1070 TiGTX 10701530456075Min: 60 / Avg: 68.77 / Max: 75Min: 54 / Avg: 61.16 / Max: 67Min: 59 / Avg: 70.41 / Max: 77Min: 62 / Avg: 70.04 / Max: 77Min: 44 / Avg: 50.85 / Max: 54Min: 57 / Avg: 65.61 / Max: 71

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 1080RTX 2080 TiRTX 2080GTX 1080 TiGTX 1070 TiGTX 10700.25880.51760.77641.03521.2940.731.150.990.890.840.73

NVIDIA GPU Cloud TensorFlow

System Power Consumption Monitor

OpenBenchmarking.orgWatts, Fewer Is BetterNVIDIA GPU Cloud TensorFlow 18.09System Power Consumption MonitorGTX 1080RTX 2080 TiRTX 2080RTX 2070GTX 1080 TiGTX 1070 TiGTX 107060120180240300Min: 44.7 / Avg: 189.85 / Max: 248.8Min: 56.1 / Avg: 213.62 / Max: 342.3Min: 47.3 / Avg: 179.59 / Max: 284.7Min: 71.1 / Avg: 162.36 / Max: 246.8Min: 54.6 / Avg: 222.3 / Max: 319.6Min: 47 / Avg: 153.76 / Max: 192.3Min: 42.7 / Avg: 174.04 / Max: 212.6

NVIDIA GPU Cloud TensorFlow

GPU Temperature Monitor

OpenBenchmarking.orgCelsius, Fewer Is BetterNVIDIA GPU Cloud TensorFlow 18.09GPU Temperature MonitorGTX 1080RTX 2080 TiRTX 2080RTX 2070GTX 1080 TiGTX 1070 TiGTX 10701428425670Min: 61 / Avg: 68.3 / Max: 75Min: 55 / Avg: 59.52 / Max: 65Min: 60 / Avg: 67.05 / Max: 75Min: 32 / Avg: 45.47 / Max: 58Min: 61 / Avg: 68.17 / Max: 75Min: 46 / Avg: 50.94 / Max: 55Min: 58 / Avg: 65.55 / Max: 70

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 1080RTX 2080 TiRTX 2080RTX 2070GTX 1080 TiGTX 1070 TiGTX 10700.47250.9451.41751.892.36251.022.101.861.901.221.140.92

CUDA Mini-Nbody

System Power Consumption Monitor

OpenBenchmarking.orgWatts, Fewer Is BetterCUDA Mini-Nbody 2015-11-10System Power Consumption MonitorGTX 1080RTX 2080 TiRTX 2080RTX 2070GTX 1080 TiGTX 1070 TiGTX 107060120180240300Min: 43.7 / Avg: 223.02 / Max: 251.7Min: 49.1 / Avg: 234.64 / Max: 336Min: 48.7 / Avg: 233.61 / Max: 284Min: 54.3 / Avg: 215.38 / Max: 246.1Min: 50.5 / Avg: 249.72 / Max: 312.9Min: 47 / Avg: 185.31 / Max: 213.8Min: 43.7 / Avg: 194.09 / Max: 210.9

CUDA Mini-Nbody

GPU Temperature Monitor

OpenBenchmarking.orgCelsius, Fewer Is BetterCUDA Mini-Nbody 2015-11-10GPU Temperature MonitorGTX 1080RTX 2080 TiRTX 2080RTX 2070GTX 1080 TiGTX 1070 TiGTX 10701530456075Min: 64 / Avg: 73.06 / Max: 79Min: 58 / Avg: 64 / Max: 67Min: 65 / Avg: 73.5 / Max: 78Min: 55 / Avg: 60.44 / Max: 64Min: 65 / Avg: 74.42 / Max: 80Min: 45 / Avg: 56.11 / Max: 60Min: 61 / Avg: 70.86 / Max: 75

Chaos Group V-RAY

System Power Consumption Monitor

OpenBenchmarking.orgWatts, Fewer Is BetterChaos Group V-RAY 1.1.0System Power Consumption MonitorGTX 1080RTX 2080 TiRTX 2080RTX 2070GTX 1080 TiGTX 1070 TiGTX 107050100150200250Min: 43.6 / Avg: 153.26 / Max: 165.9Min: 69.5 / Avg: 242.72 / Max: 272Min: 63 / Avg: 191.71 / Max: 202.8Min: 53.7 / Avg: 185.77 / Max: 199.3Min: 120.4 / Avg: 218.99 / Max: 231.8Min: 46.1 / Avg: 130.78 / Max: 135.6Min: 43.4 / Avg: 151.17 / Max: 164.2

Chaos Group V-RAY

GPU Temperature Monitor

OpenBenchmarking.orgCelsius, Fewer Is BetterChaos Group V-RAY 1.1.0GPU Temperature MonitorGTX 1080RTX 2080 TiRTX 2080RTX 2070GTX 1080 TiGTX 1070 TiGTX 10701428425670Min: 48 / Avg: 62.93 / Max: 67Min: 46 / Avg: 60.03 / Max: 68Min: 50 / Avg: 68.2 / Max: 74Min: 53 / Avg: 60.72 / Max: 62Min: 54 / Avg: 68.11 / Max: 73Min: 38 / Avg: 47.77 / Max: 50Min: 46 / Avg: 62.55 / Max: 68

System Power Consumption Monitor

Phoronix Test Suite System Monitoring

OpenBenchmarking.orgWattsSystem Power Consumption MonitorPhoronix Test Suite System MonitoringRX Vega 56RX Vega 64R9 FuryGTX 1080RTX 2080 TiRTX 2080RTX 2070GTX 1080 TiGTX 1070 TiGTX 107070140210280350Min: 48.8 / Avg: 143.52 / Max: 284.1Min: 48.4 / Avg: 169.45 / Max: 358.6Min: 79.9 / Avg: 160.12 / Max: 365.3Min: 42.2 / Avg: 154.56 / Max: 251.7Min: 45.5 / Avg: 208.03 / Max: 346.7Min: 43.9 / Avg: 175.16 / Max: 287.8Min: 42.1 / Avg: 146.13 / Max: 247.2Min: 43.4 / Avg: 200.91 / Max: 320.9Min: 45.9 / Avg: 127.84 / Max: 213.8Min: 41.9 / Avg: 143.92 / Max: 213.8

GPU Temperature Monitor

Phoronix Test Suite System Monitoring

OpenBenchmarking.orgCelsiusGPU Temperature MonitorPhoronix Test Suite System MonitoringRX Vega 56RX Vega 64R9 FuryGTX 1080RTX 2080 TiRTX 2080RTX 2070GTX 1080 TiGTX 1070 TiGTX 10701632486480Min: 31 / Avg: 51.02 / Max: 75Min: 28 / Avg: 52.98 / Max: 85Min: 33 / Avg: 66.96 / Max: 79Min: 45 / Avg: 63.06 / Max: 79Min: 34 / Avg: 60.3 / Max: 76Min: 35 / Avg: 66.5 / Max: 80Min: 33 / Avg: 54.57 / Max: 64Min: 33 / Avg: 66.46 / Max: 80Min: 36 / Avg: 46.92 / Max: 60Min: 31 / Avg: 61.13 / Max: 75

LuxMark

System Power Consumption Monitor

OpenBenchmarking.orgWatts, Fewer Is BetterLuxMark 3.1System Power Consumption MonitorRX Vega 56RX Vega 64R9 FuryGTX 1080RTX 2080 TiRTX 2080RTX 2070GTX 1080 TiGTX 1070 TiGTX 107060120180240300Min: 51.8 / Avg: 251.16 / Max: 263.3Min: 53 / Avg: 323.35 / Max: 337.9Min: 90.4 / Avg: 249.15 / Max: 256.6Min: 90.8 / Avg: 174.24 / Max: 176.2Min: 111.1 / Avg: 315.29 / Max: 328.4Min: 101.9 / Avg: 240.83 / Max: 247.3Min: 78 / Avg: 225.33 / Max: 232.6Min: 122.9 / Avg: 241.59 / Max: 247.8Min: 146.8 / Avg: 148.92 / Max: 149.4Min: 83.1 / Avg: 176.9 / Max: 181.3

cl-mem

System Power Consumption Monitor

OpenBenchmarking.orgWatts, Fewer Is Bettercl-mem 2017-01-13System Power Consumption MonitorRX Vega 56RX Vega 64R9 FuryGTX 1080RTX 2080 TiRTX 2080RTX 2070GTX 1080 TiGTX 1070 TiGTX 107060120180240300Min: 49.6 / Avg: 196.84 / Max: 261.2Min: 52.4 / Avg: 216.5 / Max: 318.8Min: 90.3 / Avg: 165.77 / Max: 211.3Min: 115.3 / Avg: 149.23 / Max: 161.8Min: 47.1 / Avg: 180.3 / Max: 248.8Min: 46.4 / Avg: 92.77 / Max: 122Min: 43.3 / Avg: 85.23 / Max: 108.2Min: 120.7 / Avg: 179.53 / Max: 209Min: 46.1 / Avg: 105.92 / Max: 138.1Min: 82.6 / Avg: 137.43 / Max: 149.2

cl-mem

Benchmark: Copy

OpenBenchmarking.orgGB/s Per Watt, More Is Bettercl-mem 2017-01-13Benchmark: CopyRX Vega 56RX Vega 64R9 FuryGTX 1080RTX 2080 TiRTX 2080RTX 2070GTX 1080 TiGTX 1070 TiGTX 10700.8731.7462.6193.4924.3651.031.021.241.402.523.533.881.771.771.36

SHOC Scalable HeterOgeneous Computing

System Power Consumption Monitor

OpenBenchmarking.orgWatts, Fewer Is BetterSHOC Scalable HeterOgeneous Computing 2015-11-10System Power Consumption MonitorRX Vega 56RX Vega 64R9 FuryGTX 1080RTX 2080 TiRTX 2080RTX 2070GTX 1080 TiGTX 1070 TiGTX 107050100150200250Min: 49.4 / Avg: 197.63 / Max: 234.4Min: 51.8 / Avg: 223.18 / Max: 249.9Min: 113.9 / Avg: 172.33 / Max: 220.8Min: 89.7 / Avg: 144.76 / Max: 164.6Min: 47.5 / Avg: 222.96 / Max: 282.7Min: 47.1 / Avg: 169.8 / Max: 202.9Min: 53.7 / Avg: 162.86 / Max: 198.7Min: 120.8 / Avg: 190.06 / Max: 216.8Min: 47 / Avg: 122.6 / Max: 141.5Min: 82.6 / Avg: 134.72 / Max: 155.3

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 BandwidthRX Vega 56RX Vega 64R9 FuryGTX 1080RTX 2080 TiRTX 2080RTX 2070GTX 1080 TiGTX 1070 TiGTX 10702468101.941.981.453.665.086.596.763.133.533.35

Phoronix Test Suite v10.8.5