AMD Radeon VII OpenCL GPU Compute Benchmarks

Benchmarks for Radeon VII launch day by Michael Larabel for a future article. Radeon tests with ROCm 2.0 on Linux 5.0 kernel.

HTML result view exported from: https://openbenchmarking.org/result/1902066-SP-VIICOMPUT16&grw&sor&rro.

AMD Radeon VII OpenCL GPU Compute BenchmarksProcessorMotherboardChipsetMemoryDiskGraphicsAudioMonitorNetworkOSKernelDesktopDisplay ServerOpenGLOpenCLVulkanCompilerFile-SystemScreen ResolutionDisplay DriverRX 580RX 590RX Vega 56RX Vega 64Radeon VIIGTX 1060GTX 1070GTX 1070 TiGTX 1080GTX 1080 TiRTX 2060RTX 2070RTX 2080RTX 2080 TiTITAN RTXIntel Core i9-9900K @ 5.00GHz (8 Cores / 16 Threads)ASUS PRIME Z390-A (0602 BIOS)Intel Cannon Lake PCH Shared SRAM16384MBSamsung SSD 970 EVO 250GB + 2000GB SABRENTMSI AMD Radeon RX 470/480/570/570X/580/580X 8GB (1366/2000MHz)Realtek ALC1220Acer B286HKIntel I219-VUbuntu 18.105.0.0-050000rc4-generic (x86_64) 20190127GNOME Shell 3.30.1X Server 1.20.14.5 Mesa 19.0.0-devel padoka PPA (LLVM 9.0.0)OpenCL 2.1 AMD-APP (2783.0)1.1.90GCC 8.2.0ext43840x2160Sapphire AMD Radeon RX 470/480/570/570X/580/580X 8GB (1560/2100MHz)AMD Radeon RX 64 8GB (1590/800MHz)AMD Radeon RX 64 8GB (1630/945MHz)AMD Vega 20 16GB (1801/1000MHz)NVIDIA GeForce GTX 1060 6GB (1506/4006MHz)4.20.3-042003-generic (x86_64)NVIDIA 415.274.6.0OpenCL 1.2 CUDA 10.0.1321.1.84NVIDIA 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)NVIDIA GeForce RTX 2060 6GB (1365/7000MHz)ASUS NVIDIA GeForce RTX 2070 8GB (1410/7000MHz)Zotac NVIDIA GeForce RTX 2080 8GB (1515/7000MHz)NVIDIA GeForce RTX 2080 Ti 11GB (1350/7000MHz)NVIDIA TITAN RTX 24GB (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 -vProcessor Details- Scaling Governor: intel_pstate performancePython Details- Python 2.7.15+ + Python 3.6.7Security Details- __user pointer sanitization + Full generic retpoline IBPB: conditional IBRS_FW STIBP: conditional RSB filling + SSB disabled via prctl and seccompOpenCL Details- GTX 1060: GPU Compute Cores: 1280- 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 2060: GPU Compute Cores: 1920- RTX 2070: GPU Compute Cores: 2304- RTX 2080: GPU Compute Cores: 2944- RTX 2080 Ti: GPU Compute Cores: 4352- TITAN RTX: GPU Compute Cores: 4608

AMD Radeon VII OpenCL GPU Compute Benchmarksplaidml: Yes - Inference - Mobilenet - OpenCLplaidml: Yes - Inference - Inception V3 - OpenCLplaidml: Yes - Inference - ResNet 50 - OpenCLplaidml: Yes - Inference - VGG16 - OpenCLplaidml: No - Training - IMDB LSTM - OpenCLplaidml: No - Inference - Mobilenet - OpenCLplaidml: No - Inference - ResNet 50 - OpenCLplaidml: No - Inference - VGG16 - OpenCLlczero: OpenCLclpeak: Global Memory Bandwidthclpeak: Single-Precision Floatluxmark: GPU - Luxball HDRRX 580RX 590RX Vega 56RX Vega 64Radeon VIIGTX 1060GTX 1070GTX 1070 TiGTX 1080GTX 1080 TiRTX 2060RTX 2070RTX 2080RTX 2080 TiTITAN RTX56376.5912860.9813041413365.1864020662021527159982.7113764.0414445314268.69683217706917221575109.03195106.66178720228120.447583171035731079587120.03213119.99184835270137.628563621246932565904166.30353197.632001233403224.771391807134535557055288.8518394.6213459219494.0889914542391225666411723712615676425712914301965878172876451202371281537552621311478197677616776686132264139167801292143175022279341380377416733419418788333918923333291085321682779134282148188863309150148427666302135683015733317919810083761891729365796829532893168354192216104540020322593681027029146971211458250246129153727331075051535242787977215474264244133655628932755251638646022OpenBenchmarking.org

PlaidML

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

OpenBenchmarking.orgExamples Per Second, More Is BetterPlaidMLFP16: Yes - Mode: Inference - Network: Mobilenet - Device: OpenCLGTX 1060RX 580RX Vega 56RX Vega 64RX 590GTX 1070 TiGTX 1070GTX 1080GTX 1080 TiRTX 2060RTX 2070RTX 2080Radeon VIIRTX 2080 TiTITAN RTX2004006008001000SE +/- 0.87, N = 3SE +/- 1.03, N = 3SE +/- 6.73, N = 3SE +/- 9.53, N = 3SE +/- 1.00, N = 3SE +/- 3.15, N = 3SE +/- 4.06, N = 3SE +/- 5.02, N = 3SE +/- 3.70, N = 3SE +/- 1.27, N = 3SE +/- 1.07, N = 3SE +/- 1.63, N = 3SE +/- 4.52, N = 3SE +/- 2.70, N = 3SE +/- 3.45, N = 3552563575587599645664686774779830893904971977

PlaidML

FP16: Yes - Mode: Inference - Network: Inception V3 - Device: OpenCL

OpenBenchmarking.orgExamples Per Second, More Is BetterPlaidMLFP16: Yes - Mode: Inference - Network: Inception V3 - Device: OpenCLRX 580RX 590GTX 1060RX Vega 56GTX 1070GTX 1070 TiRX Vega 64GTX 1080RTX 2060RTX 2070Radeon VIIGTX 1080 TiRTX 2080RTX 2080 TiTITAN RTX50100150200250SE +/- 0.04, N = 3SE +/- 0.11, N = 3SE +/- 0.05, N = 3SE +/- 0.06, N = 3SE +/- 0.07, N = 3SE +/- 0.30, N = 3SE +/- 0.02, N = 3SE +/- 0.07, N = 3SE +/- 0.44, N = 3SE +/- 0.18, N = 3SE +/- 0.20, N = 3SE +/- 0.58, N = 3SE +/- 0.40, N = 3SE +/- 0.48, N = 3SE +/- 1.30, N = 376.5982.7188.85109.03117.00120.00120.03132.00134.00157.00166.30167.00168.00211.00215.00

PlaidML

FP16: Yes - Mode: Inference - Network: ResNet 50 - Device: OpenCL

OpenBenchmarking.orgExamples Per Second, More Is BetterPlaidMLFP16: Yes - Mode: Inference - Network: ResNet 50 - Device: OpenCLRX 580RX 590GTX 1060RX Vega 56RX Vega 64GTX 1070GTX 1070 TiGTX 1080RTX 2060RTX 2070GTX 1080 TiRadeon VIIRTX 2080RTX 2080 TiTITAN RTX100200300400500SE +/- 0.01, N = 3SE +/- 0.04, N = 3SE +/- 0.17, N = 3SE +/- 0.07, N = 3SE +/- 0.13, N = 3SE +/- 0.38, N = 3SE +/- 0.16, N = 3SE +/- 0.24, N = 3SE +/- 0.26, N = 3SE +/- 0.76, N = 3SE +/- 0.34, N = 3SE +/- 0.96, N = 3SE +/- 0.40, N = 3SE +/- 1.03, N = 3SE +/- 1.16, N = 3128137183195213237237264282333334353354458474

PlaidML

FP16: Yes - Mode: Inference - Network: VGG16 - Device: OpenCL

OpenBenchmarking.orgExamples Per Second, More Is BetterPlaidMLFP16: Yes - Mode: Inference - Network: VGG16 - Device: OpenCLRX 580RX 590GTX 1060RX Vega 56RX Vega 64GTX 1070GTX 1070 TiGTX 1080RTX 2060RTX 2070RTX 2080GTX 1080 TiRadeon VIIRTX 2080 TiTITAN RTX60120180240300SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.03, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.12, N = 3SE +/- 0.06, N = 3SE +/- 0.09, N = 3SE +/- 0.15, N = 3SE +/- 0.26, N = 3SE +/- 0.32, N = 3SE +/- 0.32, N = 3SE +/- 0.03, N = 3SE +/- 0.20, N = 3SE +/- 0.43, N = 360.9864.0494.62106.66119.99126.00128.00139.00148.00179.00192.00194.00197.63250.00264.00

PlaidML

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

OpenBenchmarking.orgExamples Per Second, More Is BetterPlaidMLFP16: No - Mode: Training - Network: IMDB LSTM - Device: OpenCLRX 580GTX 1060RX 590GTX 1070 TiGTX 1070GTX 1080RX Vega 56RX Vega 64GTX 1080 TiRTX 2060RTX 2070Radeon VIIRTX 2080TITAN RTXRTX 2080 Ti50100150200250SE +/- 0.25, N = 3SE +/- 0.17, N = 3SE +/- 0.19, N = 3SE +/- 0.03, N = 3SE +/- 0.50, N = 3SE +/- 0.60, N = 3SE +/- 0.24, N = 3SE +/- 0.19, N = 3SE +/- 0.49, N = 3SE +/- 0.38, N = 3SE +/- 0.82, N = 3SE +/- 0.32, N = 3SE +/- 0.27, N = 3SE +/- 0.96, N = 3SE +/- 0.72, N = 3130134144153156167178184187188198200216244246

PlaidML

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

OpenBenchmarking.orgExamples Per Second, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: Mobilenet - Device: OpenCLRX 580RX 590GTX 1060RX Vega 56GTX 1070 TiGTX 1070GTX 1080RX Vega 64RTX 2060GTX 1080 TiRTX 2070RTX 2080Radeon VIIRTX 2080 TiTITAN RTX30060090012001500SE +/- 0.26, N = 3SE +/- 0.24, N = 3SE +/- 3.04, N = 3SE +/- 9.70, N = 3SE +/- 0.31, N = 3SE +/- 1.02, N = 3SE +/- 0.61, N = 3SE +/- 7.40, N = 3SE +/- 1.86, N = 3SE +/- 4.51, N = 3SE +/- 1.43, N = 3SE +/- 0.31, N = 3SE +/- 3.74, N = 3SE +/- 1.39, N = 3SE +/- 3.01, N = 341445359272075576480183586388310081045123312911336

PlaidML

FP16: No - Mode: Inference - Network: ResNet 50 - Device: OpenCL

OpenBenchmarking.orgExamples Per Second, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: ResNet 50 - Device: OpenCLRX 580RX 590GTX 1060RX Vega 56GTX 1070GTX 1070 TiRX Vega 64GTX 1080RTX 2060GTX 1080 TiRTX 2070RTX 2080Radeon VIIRTX 2080 TiTITAN RTX120240360480600SE +/- 0.04, N = 3SE +/- 0.07, N = 3SE +/- 0.11, N = 3SE +/- 2.52, N = 3SE +/- 0.45, N = 3SE +/- 0.24, N = 3SE +/- 1.40, N = 3SE +/- 0.41, N = 3SE +/- 0.26, N = 3SE +/- 0.55, N = 3SE +/- 0.33, N = 3SE +/- 0.45, N = 3SE +/- 0.30, N = 3SE +/- 0.31, N = 3SE +/- 1.67, N = 3133142194228257262270292309339376400403537556

PlaidML

FP16: No - Mode: Inference - Network: VGG16 - Device: OpenCL

OpenBenchmarking.orgExamples Per Second, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: VGG16 - Device: OpenCLRX 580RX 590GTX 1060RX Vega 56GTX 1070GTX 1070 TiRX Vega 64GTX 1080RTX 2060GTX 1080 TiRTX 2070RTX 2080Radeon VIIRTX 2080 TiTITAN RTX60120180240300SE +/- 0.05, N = 3SE +/- 0.01, N = 3SE +/- 0.04, N = 3SE +/- 0.18, N = 3SE +/- 0.04, N = 3SE +/- 0.01, N = 3SE +/- 0.11, N = 3SE +/- 0.06, N = 3SE +/- 0.16, N = 3SE +/- 0.12, N = 3SE +/- 0.27, N = 3SE +/- 0.17, N = 3SE +/- 0.38, N = 3SE +/- 0.36, N = 3SE +/- 0.72, N = 365.1868.6994.08120.44129.00131.00137.62143.00150.00189.00189.00203.00224.77273.00289.00

LeelaChessZero

Backend: OpenCL

OpenBenchmarking.orgNodes Per Second, More Is BetterLeelaChessZero 0.20.1Backend: OpenCLRX 580RX 590RX Vega 56RX Vega 64GTX 1060Radeon VIIGTX 1070GTX 1070 TiRTX 2060RTX 2070GTX 1080RTX 2080GTX 1080 TiRTX 2080 TiTITAN RTX7001400210028003500SE +/- 2.68, N = 3SE +/- 2.57, N = 3SE +/- 2.66, N = 3SE +/- 5.51, N = 3SE +/- 6.27, N = 3SE +/- 8.64, N = 3SE +/- 9.63, N = 3SE +/- 13.26, N = 3SE +/- 13.06, N = 3SE +/- 20.57, N = 3SE +/- 32.06, N = 3SE +/- 22.18, N = 3SE +/- 25.14, N = 3SE +/- 20.98, N = 3SE +/- 28.14, N = 364068375885689913911430147814841729175022592333310732751. (CXX) g++ options: -lpthread

clpeak

OpenCL Test: Global Memory Bandwidth

OpenBenchmarking.orgGBPS, More Is BetterclpeakOpenCL Test: Global Memory BandwidthGTX 1060GTX 1070GTX 1070 TiRX 580RX 590GTX 1080RTX 2060RX Vega 56GTX 1080 TiRX Vega 64RTX 2070RTX 2080RTX 2080 TiTITAN RTXRadeon VII2004006008001000SE +/- 0.95, N = 3SE +/- 0.02, N = 3SE +/- 0.22, N = 3SE +/- 1.46, N = 3SE +/- 1.82, N = 3SE +/- 0.05, N = 3SE +/- 0.19, N = 3SE +/- 0.01, N = 3SE +/- 0.68, N = 3SE +/- 0.05, N = 3SE +/- 2.69, N = 3SE +/- 0.37, N = 3SE +/- 0.48, N = 3SE +/- 1.70, N = 3SE +/- 0.10, N = 31451961972062172222763173293623653685055258071. (CXX) g++ options: -O3 -rdynamic -lOpenCL

clpeak

OpenCL Test: Single-Precision Float

OpenBenchmarking.orgGFLOPS, More Is BetterclpeakOpenCL Test: Single-Precision FloatGTX 1060GTX 1070RX 580RTX 2060GTX 1070 TiRX 590GTX 1080RTX 2070RTX 2080RX Vega 56GTX 1080 TiRX Vega 64Radeon VIIRTX 2080 TiTITAN RTX4K8K12K16K20KSE +/- 3.56, N = 3SE +/- 393.27, N = 3SE +/- 1.21, N = 3SE +/- 657.16, N = 3SE +/- 14.43, N = 3SE +/- 15.75, N = 3SE +/- 396.02, N = 3SE +/- 495.99, N = 3SE +/- 732.21, N = 3SE +/- 38.50, N = 3SE +/- 782.31, N = 3SE +/- 41.13, N = 3SE +/- 1.83, N = 3SE +/- 1065.18, N = 3SE +/- 688.69, N = 342395878620266306776706979347968102701035710853124691345315352163861. (CXX) g++ options: -O3 -rdynamic -lOpenCL

LuxMark

OpenCL Device: GPU - Scene: Luxball HDR

OpenBenchmarking.orgScore, More Is BetterLuxMark 3.1OpenCL Device: GPU - Scene: Luxball HDRGTX 1060GTX 1080RX 580GTX 1070 TiRX 590GTX 1070RTX 2060GTX 1080 TiRTX 2080RTX 2070RX Vega 56RX Vega 64RTX 2080 TiTITAN RTXRadeon VII12K24K36K48K60KSE +/- 46.58, N = 3SE +/- 42.00, N = 3SE +/- 17.84, N = 3SE +/- 14.90, N = 3SE +/- 74.83, N = 3SE +/- 1.33, N = 3SE +/- 31.58, N = 3SE +/- 8.33, N = 3SE +/- 25.12, N = 3SE +/- 107.00, N = 3SE +/- 65.67, N = 3SE +/- 583.87, N = 3SE +/- 155.67, N = 3SE +/- 103.04, N = 3SE +/- 258.00, N = 3122561380315271167761722117287213562168229146295323107932565427874602255570

LeelaChessZero

Backend: OpenCL

OpenBenchmarking.orgNodes Per Second Per Watt, More Is BetterLeelaChessZero 0.20.1Backend: OpenCLRX Vega 64RX 590RX 580RX Vega 56GTX 1060RTX 2060GTX 1070GTX 1080 TiRTX 2070Radeon VIIGTX 1070 TiRTX 2080GTX 1080RTX 2080 TiTITAN RTX5101520252.733.623.744.385.977.577.778.809.279.389.4510.1311.8115.1022.11

LeelaChessZero

System Power Consumption Monitor

OpenBenchmarking.orgWatts, Fewer Is BetterLeelaChessZero 0.20.1System Power Consumption MonitorRX Vega 64GTX 1080 TiRTX 2080RTX 2080 TiRTX 2060RX 590RTX 2070GTX 1070RX Vega 56RX 580GTX 1070 TiGTX 1060Radeon VIITITAN RTXGTX 108060120180240300Min: 50.2 / Avg: 313.27 / Max: 342.7Min: 96.9 / Avg: 265.17 / Max: 323.1Min: 88.3 / Avg: 222.99 / Max: 288.3Min: 48.2 / Avg: 205.76 / Max: 349.4Min: 69.4 / Avg: 196.01 / Max: 230Min: 75.2 / Avg: 188.72 / Max: 253.3Min: 75.1 / Avg: 186.61 / Max: 251.7Min: 42.6 / Avg: 184.04 / Max: 213.3Min: 47.2 / Avg: 173.2 / Max: 262.2Min: 69.3 / Avg: 171.21 / Max: 229.5Min: 80 / Avg: 156.39 / Max: 189.7Min: 41.9 / Avg: 150.59 / Max: 180Min: 56 / Avg: 148.33 / Max: 269Min: 97.7 / Avg: 148.16 / Max: 357.7Min: 40.2 / Avg: 148.14 / Max: 249.5

PlaidML

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

OpenBenchmarking.orgExamples Per Second Per Watt, More Is BetterPlaidMLFP16: Yes - Mode: Inference - Network: Mobilenet - Device: OpenCLRX 590GTX 1060RX 580GTX 1080 TiRX Vega 56RTX 2060GTX 1070 TiRTX 2080GTX 1070GTX 1080RX Vega 64TITAN RTXRTX 2070RTX 2080 TiRadeon VII36912154.745.125.145.196.236.416.576.827.227.348.488.828.8710.2811.54

PlaidML

System Power Consumption Monitor

OpenBenchmarking.orgWatts, Fewer Is BetterPlaidMLSystem Power Consumption MonitorGTX 1080 TiRTX 2080RX 590RTX 2060TITAN RTXRX 580GTX 1060GTX 1070 TiRTX 2080 TiRTX 2070GTX 1080RX Vega 56GTX 1070Radeon VIIRX Vega 644080120160200Min: 91.6 / Avg: 149.17 / Max: 203.2Min: 56.3 / Avg: 130.87 / Max: 184.7Min: 82.3 / Avg: 126.56 / Max: 194.9Min: 45.5 / Avg: 121.65 / Max: 166.1Min: 52.9 / Avg: 110.8 / Max: 140.2Min: 75.6 / Avg: 109.4 / Max: 179Min: 42.1 / Avg: 107.84 / Max: 141.6Min: 48.7 / Avg: 98.18 / Max: 132.6Min: 48.4 / Avg: 94.48 / Max: 113.3Min: 46 / Avg: 93.68 / Max: 129.3Min: 43.7 / Avg: 93.48 / Max: 127.3Min: 49.6 / Avg: 92.35 / Max: 157.7Min: 42.8 / Avg: 91.98 / Max: 117.4Min: 58.1 / Avg: 78.39 / Max: 92.6Min: 54 / Avg: 69.27 / Max: 82.4

PlaidML

FP16: Yes - Mode: Inference - Network: Inception V3 - Device: OpenCL

OpenBenchmarking.orgExamples Per Second Per Watt, More Is BetterPlaidMLFP16: Yes - Mode: Inference - Network: Inception V3 - Device: OpenCLRX 590RX 580RX Vega 64GTX 1060RX Vega 56GTX 1070GTX 1080GTX 1080 TiGTX 1070 TiRTX 2060RTX 2070RTX 2080RTX 2080 TiRadeon VIITITAN RTX0.2880.5760.8641.1521.440.510.520.660.670.740.760.780.820.900.921.071.081.121.241.28

PlaidML

System Power Consumption Monitor

OpenBenchmarking.orgWatts, Fewer Is BetterPlaidMLSystem Power Consumption MonitorGTX 1080 TiRTX 2080 TiRX Vega 64TITAN RTXGTX 1080RX 590RTX 2080GTX 1070RX Vega 56RTX 2070RX 580RTX 2060Radeon VIIGTX 1060GTX 1070 Ti50100150200250Min: 120.7 / Avg: 202.56 / Max: 256.6Min: 48.4 / Avg: 188.73 / Max: 275.6Min: 50.6 / Avg: 181.52 / Max: 296Min: 51.5 / Avg: 168.92 / Max: 275.4Min: 89.5 / Avg: 168.75 / Max: 202.8Min: 91.8 / Avg: 163.54 / Max: 221.5Min: 47.5 / Avg: 155.97 / Max: 224.6Min: 81.8 / Avg: 153.87 / Max: 183Min: 58.9 / Avg: 147.82 / Max: 249.5Min: 45.8 / Avg: 146.81 / Max: 206.6Min: 73.1 / Avg: 146.45 / Max: 195.4Min: 45 / Avg: 144.95 / Max: 190.7Min: 69.7 / Avg: 134.1 / Max: 228.1Min: 87.5 / Avg: 132.19 / Max: 156.7Min: 56.1 / Avg: 132.15 / Max: 155

PlaidML

FP16: Yes - Mode: Inference - Network: ResNet 50 - Device: OpenCL

OpenBenchmarking.orgExamples Per Second Per Watt, More Is BetterPlaidMLFP16: Yes - Mode: Inference - Network: ResNet 50 - Device: OpenCLRX 590RX 580RX Vega 64RX Vega 56GTX 1060GTX 1080GTX 1070GTX 1080 TiRTX 2060GTX 1070 TiRTX 2080RTX 2070Radeon VIITITAN RTXRTX 2080 Ti0.66381.32761.99142.65523.3190.890.911.241.381.491.621.761.781.962.082.392.512.752.922.95

PlaidML

System Power Consumption Monitor

OpenBenchmarking.orgWatts, Fewer Is BetterPlaidMLSystem Power Consumption MonitorGTX 1080 TiRX Vega 64TITAN RTXGTX 1080RTX 2080 TiRX 590RTX 2080RTX 2060RX 580RX Vega 56GTX 1070RTX 2070Radeon VIIGTX 1060GTX 1070 Ti60120180240300Min: 122.3 / Avg: 187.68 / Max: 270.3Min: 82.4 / Avg: 172.03 / Max: 313.6Min: 52.6 / Avg: 162.76 / Max: 301.7Min: 91.6 / Avg: 162.7 / Max: 211.1Min: 48.4 / Avg: 155.12 / Max: 292.5Min: 81.1 / Avg: 153.59 / Max: 208.6Min: 47.4 / Avg: 148.19 / Max: 240.2Min: 86.5 / Avg: 143.68 / Max: 202.9Min: 73.6 / Avg: 141.5 / Max: 187.8Min: 50.5 / Avg: 141.19 / Max: 254.3Min: 83.8 / Avg: 134.85 / Max: 189.4Min: 78.4 / Avg: 132.98 / Max: 222.4Min: 70.1 / Avg: 128.33 / Max: 243.5Min: 60.4 / Avg: 122.52 / Max: 164.5Min: 48.5 / Avg: 113.89 / Max: 160.8

PlaidML

FP16: Yes - Mode: Inference - Network: VGG16 - Device: OpenCL

OpenBenchmarking.orgExamples Per Second Per Watt, More Is BetterPlaidMLFP16: Yes - Mode: Inference - Network: VGG16 - Device: OpenCLRX 590RX 580RX Vega 64RX Vega 56GTX 1060GTX 1080GTX 1070GTX 1070 TiGTX 1080 TiRTX 2060RTX 2080RTX 2070RTX 2080 TiTITAN RTXRadeon VII0.34880.69761.04641.39521.7440.390.410.550.700.720.800.921.021.081.081.211.271.381.501.55

PlaidML

System Power Consumption Monitor

OpenBenchmarking.orgWatts, Fewer Is BetterPlaidMLSystem Power Consumption MonitorRX Vega 64RTX 2080 TiGTX 1080 TiTITAN RTXGTX 1080RX 590RTX 2080RX Vega 56RX 580RTX 2070RTX 2060GTX 1070GTX 1060Radeon VIIGTX 1070 Ti60120180240300Min: 53.4 / Avg: 217.55 / Max: 319.8Min: 47.7 / Avg: 180.78 / Max: 312Min: 65.2 / Avg: 179.46 / Max: 287.9Min: 58.3 / Avg: 176.01 / Max: 322.5Min: 70.3 / Avg: 172.91 / Max: 216.6Min: 79.7 / Avg: 162.83 / Max: 210.1Min: 49.8 / Avg: 158.89 / Max: 252.8Min: 50.2 / Avg: 151.48 / Max: 258.1Min: 73.2 / Avg: 147.27 / Max: 187.1Min: 47.2 / Avg: 141.31 / Max: 234Min: 62.3 / Avg: 137.76 / Max: 208Min: 43.1 / Avg: 136.92 / Max: 191.2Min: 58.2 / Avg: 131.14 / Max: 167.2Min: 57.5 / Avg: 127.89 / Max: 264.7Min: 48.4 / Avg: 125.32 / Max: 169.8

PlaidML

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

OpenBenchmarking.orgExamples Per Second Per Watt, More Is BetterPlaidMLFP16: No - Mode: Training - Network: IMDB LSTM - Device: OpenCLRX 580RX 590RX Vega 56GTX 1060RX Vega 64GTX 1070GTX 1080GTX 1080 TiGTX 1070 TiRadeon VIIRTX 2080 TiRTX 2070RTX 2080TITAN RTXRTX 20600.36450.7291.09351.4581.82250.890.951.071.081.111.141.141.141.241.451.541.561.561.601.62

PlaidML

System Power Consumption Monitor

OpenBenchmarking.orgWatts, Fewer Is BetterPlaidMLSystem Power Consumption MonitorRX Vega 64RX Vega 56GTX 1080 TiRTX 2080 TiRX 590TITAN RTXGTX 1080RX 580RTX 2080Radeon VIIGTX 1070RTX 2070GTX 1060GTX 1070 TiRTX 206050100150200250Min: 52.2 / Avg: 165.89 / Max: 305.6Min: 74.8 / Avg: 165.69 / Max: 271.3Min: 50.4 / Avg: 165.05 / Max: 214.8Min: 48.6 / Avg: 159.87 / Max: 223.7Min: 80.2 / Avg: 152.62 / Max: 212.4Min: 57.5 / Avg: 152.07 / Max: 231.9Min: 90.8 / Avg: 146.71 / Max: 176.8Min: 71.3 / Avg: 146.11 / Max: 185.3Min: 46.4 / Avg: 138.03 / Max: 185.4Min: 87.3 / Avg: 137.45 / Max: 192.4Min: 82.2 / Avg: 136.83 / Max: 164.9Min: 47.1 / Avg: 127.27 / Max: 169.5Min: 70.1 / Avg: 124.21 / Max: 145Min: 104.8 / Avg: 123.57 / Max: 135.6Min: 44.3 / Avg: 116.14 / Max: 162.7

PlaidML

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

OpenBenchmarking.orgExamples Per Second Per Watt, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: Mobilenet - Device: OpenCLRX 590RX 580GTX 1080RX Vega 56TITAN RTXGTX 1080 TiGTX 1070RX Vega 64GTX 1060GTX 1070 TiRTX 2080 TiRTX 2070RTX 2060Radeon VIIRTX 208036912153.293.625.425.826.677.027.127.477.728.068.458.709.009.3410.67

PlaidML

System Power Consumption Monitor

OpenBenchmarking.orgWatts, Fewer Is BetterPlaidMLSystem Power Consumption MonitorTITAN RTXRTX 2080 TiGTX 1080RX 590Radeon VIIGTX 1080 TiRX Vega 56RTX 2070RX 580RX Vega 64GTX 1070RTX 2080RTX 2060GTX 1070 TiGTX 106050100150200250Min: 54 / Avg: 200.17 / Max: 274.2Min: 48.2 / Avg: 152.87 / Max: 274.6Min: 44.3 / Avg: 147.75 / Max: 195.1Min: 82.4 / Avg: 137.7 / Max: 205.5Min: 92.8 / Avg: 132.03 / Max: 241.7Min: 53.3 / Avg: 125.73 / Max: 165.2Min: 72.5 / Avg: 123.7 / Max: 259.6Min: 115.1 / Avg: 115.83 / Max: 116.5Min: 71.7 / Avg: 114.33 / Max: 178.6Min: 52.5 / Avg: 111.85 / Max: 223.9Min: 45.9 / Avg: 107.3 / Max: 155.1Min: 52 / Avg: 97.93 / Max: 121Min: 43.1 / Avg: 95.9 / Max: 118.8Min: 49.7 / Avg: 93.67 / Max: 125.7Min: 41.8 / Avg: 76.7 / Max: 94.4

PlaidML

FP16: No - Mode: Inference - Network: ResNet 50 - Device: OpenCL

OpenBenchmarking.orgExamples Per Second Per Watt, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: ResNet 50 - Device: OpenCLRX 590RX 580RX Vega 56RX Vega 64GTX 1060GTX 1070GTX 1080 TiGTX 1080GTX 1070 TiRTX 2060RTX 2070RTX 2080TITAN RTXRadeon VIIRTX 2080 Ti0.69981.39962.09942.79923.4990.880.921.511.521.591.771.821.921.942.302.442.512.862.973.11

PlaidML

System Power Consumption Monitor

OpenBenchmarking.orgWatts, Fewer Is BetterPlaidMLSystem Power Consumption MonitorTITAN RTXGTX 1080 TiRX Vega 64RTX 2080 TiRX 590RTX 2080RTX 2070GTX 1080RX Vega 56GTX 1070RX 580Radeon VIIGTX 1070 TiRTX 2060GTX 106060120180240300Min: 102.3 / Avg: 194.3 / Max: 332.7Min: 61.2 / Avg: 185.7 / Max: 280.5Min: 81.5 / Avg: 177.38 / Max: 338.2Min: 100.3 / Avg: 172.57 / Max: 323.3Min: 81 / Avg: 162.42 / Max: 220Min: 48.4 / Avg: 158.95 / Max: 257.5Min: 49.8 / Avg: 153.92 / Max: 242.3Min: 91.9 / Avg: 152.34 / Max: 225.3Min: 50.1 / Avg: 150.39 / Max: 271.1Min: 45.2 / Avg: 145.44 / Max: 201.2Min: 73 / Avg: 145.33 / Max: 194.5Min: 58.8 / Avg: 135.42 / Max: 277Min: 48.6 / Avg: 134.71 / Max: 168.9Min: 65 / Avg: 134.41 / Max: 208.9Min: 71.4 / Avg: 121.65 / Max: 172.6

PlaidML

FP16: No - Mode: Inference - Network: VGG16 - Device: OpenCL

OpenBenchmarking.orgExamples Per Second Per Watt, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: VGG16 - Device: OpenCLRX 590RX 580RX Vega 56RX Vega 64GTX 1060GTX 1070GTX 1080GTX 1080 TiGTX 1070 TiRTX 2060RTX 2070RTX 2080RTX 2080 TiTITAN RTXRadeon VII0.29250.5850.87751.171.46250.370.400.640.640.650.790.790.820.890.901.031.081.281.291.30

PlaidML

System Power Consumption Monitor

OpenBenchmarking.orgWatts, Fewer Is BetterPlaidMLSystem Power Consumption MonitorGTX 1080 TiTITAN RTXRX Vega 64RTX 2080 TiRTX 2080RX Vega 56RX 590RTX 2070GTX 1080Radeon VIIRTX 2060RX 580GTX 1070GTX 1070 TiGTX 106060120180240300Min: 127.7 / Avg: 231.45 / Max: 296.9Min: 55.4 / Avg: 223.68 / Max: 345.8Min: 52.7 / Avg: 216.48 / Max: 338.1Min: 47.6 / Avg: 212.98 / Max: 331.1Min: 50.9 / Avg: 188.45 / Max: 269.3Min: 78.5 / Avg: 188.36 / Max: 262.2Min: 86.9 / Avg: 184.98 / Max: 216.4Min: 68.7 / Avg: 183.65 / Max: 245.5Min: 45.1 / Avg: 180.6 / Max: 225Min: 58.2 / Avg: 172.91 / Max: 296.6Min: 44 / Avg: 167.51 / Max: 215.1Min: 73 / Avg: 163.55 / Max: 194.8Min: 43.1 / Avg: 162.78 / Max: 197.9Min: 47.9 / Avg: 146.58 / Max: 171.7Min: 72.7 / Avg: 144.61 / Max: 170.9

LuxMark

OpenCL Device: GPU - Scene: Luxball HDR

OpenBenchmarking.orgScore Per Watt, More Is BetterLuxMark 3.1OpenCL Device: GPU - Scene: Luxball HDRRX 590GTX 1080RX 580GTX 1060GTX 1080 TiGTX 1070RX Vega 64RTX 2060GTX 1070 TiRX Vega 56RTX 2080RTX 2070RTX 2080 TiTITAN RTXRadeon VII408012016020078.9079.4280.5385.5389.3498.4898.89110.80114.16120.58123.99131.09133.42137.54188.36

LuxMark

System Power Consumption Monitor

OpenBenchmarking.orgWatts, Fewer Is BetterLuxMark 3.1System Power Consumption MonitorTITAN RTXRX Vega 64RTX 2080 TiRadeon VIIRX Vega 56GTX 1080 TiRTX 2080RTX 2070RX 590RTX 2060RX 580GTX 1070GTX 1080GTX 1070 TiGTX 106060120180240300Min: 50.6 / Avg: 334.61 / Max: 351.7Min: 49.5 / Avg: 329.31 / Max: 338.6Min: 47.7 / Avg: 320.7 / Max: 332Min: 87.3 / Avg: 295.02 / Max: 302.2Min: 60.2 / Avg: 257.74 / Max: 269.1Min: 161.6 / Avg: 242.69 / Max: 248.1Min: 48.9 / Avg: 235.08 / Max: 244.1Min: 46 / Avg: 225.28 / Max: 233.2Min: 82.1 / Avg: 218.27 / Max: 228.9Min: 44 / Avg: 192.74 / Max: 197.4Min: 71.5 / Avg: 189.63 / Max: 196.7Min: 82.6 / Avg: 175.54 / Max: 179.2Min: 89.3 / Avg: 173.79 / Max: 175.8Min: 47.6 / Avg: 146.95 / Max: 149.7Min: 111.3 / Avg: 143.3 / Max: 145.4

GPU Temperature Monitor

Phoronix Test Suite System Monitoring

OpenBenchmarking.orgCelsiusGPU Temperature MonitorPhoronix Test Suite System MonitoringRTX 2080GTX 1080 TiTITAN RTXRTX 2080 TiGTX 1070GTX 1080RTX 2070RTX 2060RX Vega 64Radeon VIIRX Vega 56RX 590GTX 1070 TiRX 58020406080100Min: 48 / Avg: 67.06 / Max: 83Min: 39 / Avg: 66.36 / Max: 82Min: 33 / Avg: 62.56 / Max: 79Min: 43 / Avg: 61.88 / Max: 77Min: 32 / Avg: 61.66 / Max: 76Min: 31 / Avg: 60.14 / Max: 74Min: 32 / Avg: 56.83 / Max: 74Min: 37 / Avg: 55.81 / Max: 70Min: 45 / Avg: 52.93 / Max: 65Min: 36 / Avg: 52.37 / Max: 101Min: 28 / Avg: 47.45 / Max: 74Min: 35 / Avg: 46.18 / Max: 73Min: 38 / Avg: 45.88 / Max: 53Min: 26 / Avg: 39.71 / Max: 61

System Power Consumption Monitor

Phoronix Test Suite System Monitoring

OpenBenchmarking.orgWattsSystem Power Consumption MonitorPhoronix Test Suite System MonitoringTITAN RTXRTX 2080 TiGTX 1080 TiRTX 2080RTX 2070RTX 2060GTX 1080GTX 1070RX 590RX Vega 64RX 580RX Vega 56Radeon VIIGTX 1070 Ti70140210280350Min: 49.4 / Avg: 228.34 / Max: 363.1Min: 47.2 / Avg: 220.83 / Max: 367.7Min: 47.2 / Avg: 198.85 / Max: 370.3Min: 46 / Avg: 176.62 / Max: 334.5Min: 43.9 / Avg: 160.13 / Max: 317.6Min: 42.5 / Avg: 144.37 / Max: 300.1Min: 40.2 / Avg: 143.79 / Max: 318.2Min: 42.3 / Avg: 142.19 / Max: 280.5Min: 75 / Avg: 138.2 / Max: 253.3Min: 49.7 / Avg: 129.09 / Max: 305.4Min: 69 / Avg: 125.65 / Max: 229.5Min: 47.1 / Avg: 125.63 / Max: 271.3Min: 55.7 / Avg: 125.32 / Max: 337.5Min: 47.2 / Avg: 123.43 / Max: 255.8

Phoronix Test Suite v10.8.5