NVIDIA and AMD GPU Linux compute benchmarks December 2018 by Michael Larabel for a future article, review of the NVIDIA TITAN RTX.
Compare your own system(s) to this result file with the
Phoronix Test Suite by running the command:
phoronix-test-suite benchmark 1812224-SP-GPUCOMPUT75 NVIDIA TITAN RTX Linux GPU Compute Benchmarks - Phoronix Test Suite NVIDIA TITAN RTX Linux GPU Compute Benchmarks NVIDIA and AMD GPU Linux compute benchmarks December 2018 by Michael Larabel for a future article, review of the NVIDIA TITAN RTX.
HTML result view exported from: https://openbenchmarking.org/result/1812224-SP-GPUCOMPUT75&sor&grr .
NVIDIA TITAN RTX Linux GPU Compute Benchmarks Processor Motherboard Chipset Memory Disk Graphics Audio Monitor Network OS Kernel Desktop Display Server Display Driver OpenGL OpenCL Vulkan Compiler File-System Screen Resolution GTX 980 GTX 980 Ti GTX TITAN X GM200 GTX 1070 GTX 1070 Ti GTX 1080 GTX 1080 Ti RTX 2070 RTX 2080 RTX 2080 Ti TITAN RTX RX Vega 56 RX Vega 64 Intel Core i9-9900K @ 5.00GHz (8 Cores / 16 Threads) ASUS PRIME Z390-A (0602 BIOS) Intel Cannon Lake PCH Shared SRAM 16384MB 2000GB SABRENT + Samsung SSD 970 EVO 250GB NVIDIA GeForce GTX 980 4GB (1126/3505MHz) Realtek ALC1220 Acer B286HK Intel Connection Ubuntu 18.04 4.19.5-041905-generic (x86_64) GNOME Shell 3.28.3 X Server 1.19.6 NVIDIA 415.23 4.6.0 OpenCL 1.2 CUDA 10.0.132 1.1.84 GCC 7.3.0 + CUDA 10.0 ext4 3840x2160 NVIDIA GeForce GTX 980 Ti 6GB (999/3505MHz) NVIDIA GeForce GTX TITAN X 12GB (1001/3505MHz) NVIDIA GeForce GTX 1070 8GB (1506/4006MHz) NVIDIA 415.22 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) Zotac NVIDIA GeForce RTX 2080 8GB (1515/7000MHz) NVIDIA GeForce RTX 2080 Ti 11GB (1350/7000MHz) NVIDIA TITAN RTX 24GB (1350/7000MHz) NVIDIA 415.23 AMD Radeon RX Vega 8GB (1590/800MHz) 4.5 Mesa 19.0.0-devel padoka PPA (LLVM 8.0.0) OpenCL 2.1 AMD-APP (2679.0) 1.1.70 GCC 7.3.0 AMD Radeon RX Vega 8GB (1630/945MHz) OpenBenchmarking.org Compiler 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 performance OpenCL Details - GTX 980: GPU Compute Cores: 2048 - GTX 980 Ti: GPU Compute Cores: 2816 - GTX TITAN X GM200: 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: GPU Compute Cores: 2944 - RTX 2080 Ti: GPU Compute Cores: 4352 - TITAN RTX: GPU Compute Cores: 4608 Security Details - __user pointer sanitization + Full generic retpoline IBPB IBRS_FW + SSB disabled via prctl and seccomp
NVIDIA TITAN RTX Linux GPU Compute Benchmarks luxmark: GPU - Luxball HDR ngc-tensorflow: Inception v4, FP16 v-ray: CUDA GPU ngc-tensorflow: Googlenet, FP16 ngc-tensorflow: ResNet-50, FP32 ngc-tensorflow: VGG-16, FP32 ngc-tensorflow: ResNet-50, FP16 ngc-tensorflow: VGG-16, FP16 ngc-tensorflow: AlexNet, FP32 ngc-tensorflow: AlexNet, FP16 cl-mem: Copy shoc: OpenCL - FFT SP GTX 980 GTX 980 Ti GTX TITAN X GM200 GTX 1070 GTX 1070 Ti GTX 1080 GTX 1080 Ti RTX 2070 RTX 2080 RTX 2080 Ti TITAN RTX RX Vega 56 RX Vega 64 13242 106.51 1154 1208 143 468 16910 40.90 77.70 356 150 77.57 1501 1552 217 728 17299 43.23 80.62 372 125 72.77 156 79.20 1587 1662 218 726 17288 44.77 90.43 375 125 71.57 160 76.93 1516 1563 187 452 16886 49.23 86.30 413 133 76.40 175 84.43 1591 1683 188 497 13823 55.03 102.07 458 143 82.90 193 93.13 1764 1875 209 575 21562 74.63 66.41 629 210 119.50 271 131.37 2539 2674 317 972 30091 66.02 309 2174 330 998 29641 102.77 72.07 738 205 108.57 335 153.33 2419 3153 328 1083 42693 135.90 56.09 1015 285 152.40 449 206.97 3344 4432 454 1443 45932 152.80 50.08 1132 299 162.33 520 244.40 3576 5032 484 1548 31179 203 926 32815 221 1070 OpenBenchmarking.org
LuxMark OpenCL Device: GPU - Scene: Luxball HDR OpenBenchmarking.org Score, More Is Better LuxMark 3.1 OpenCL Device: GPU - Scene: Luxball HDR TITAN RTX RTX 2080 Ti RX Vega 64 RX Vega 56 RTX 2070 RTX 2080 GTX 1080 Ti GTX TITAN X GM200 GTX 1070 GTX 980 Ti GTX 1070 Ti GTX 1080 GTX 980 10K 20K 30K 40K 50K SE +/- 41.88, N = 3 SE +/- 66.64, N = 3 SE +/- 570.76, N = 3 SE +/- 20.53, N = 3 SE +/- 2.73, N = 3 SE +/- 119.86, N = 3 SE +/- 11.50, N = 3 SE +/- 0.58, N = 3 SE +/- 26.00, N = 3 SE +/- 0.67, N = 3 SE +/- 29.04, N = 3 SE +/- 33.13, N = 3 45932 42693 32815 31179 30091 29641 21562 17299 17288 16910 16886 13823 13242
NVIDIA GPU Cloud TensorFlow Test: Inception v4, FP16 OpenBenchmarking.org Images Per Second, More Is Better NVIDIA GPU Cloud TensorFlow 18.09 Test: Inception v4, FP16 TITAN RTX RTX 2080 Ti RTX 2080 GTX 1080 Ti GTX 1080 GTX 1070 Ti GTX 1070 GTX TITAN X GM200 GTX 980 Ti 30 60 90 120 150 SE +/- 0.21, N = 3 SE +/- 0.10, N = 3 SE +/- 0.07, N = 3 SE +/- 0.07, N = 3 SE +/- 0.03, N = 3 SE +/- 0.03, N = 3 SE +/- 0.03, N = 3 SE +/- 0.12, N = 3 SE +/- 0.12, N = 3 152.80 135.90 102.77 74.63 55.03 49.23 44.77 43.23 40.90
Chaos Group V-RAY Mode: CUDA GPU OpenBenchmarking.org Seconds, Fewer Is Better Chaos Group V-RAY 1.1.0 Mode: CUDA GPU TITAN RTX RTX 2080 Ti RTX 2070 GTX 1080 Ti RTX 2080 GTX 980 Ti GTX TITAN X GM200 GTX 1070 Ti GTX 1070 GTX 1080 GTX 980 20 40 60 80 100 SE +/- 0.02, N = 3 SE +/- 3.00, N = 3 SE +/- 0.03, N = 3 SE +/- 0.03, N = 3 SE +/- 0.04, N = 3 SE +/- 0.14, N = 3 SE +/- 2.94, N = 3 SE +/- 0.04, N = 3 SE +/- 0.03, N = 3 SE +/- 3.08, N = 3 SE +/- 0.16, N = 3 50.08 56.09 66.02 66.41 72.07 77.70 80.62 86.30 90.43 102.07 106.51
NVIDIA GPU Cloud TensorFlow Test: Googlenet, FP16 OpenBenchmarking.org Images Per Second, More Is Better NVIDIA GPU Cloud TensorFlow 18.09 Test: Googlenet, FP16 TITAN RTX RTX 2080 Ti RTX 2080 GTX 1080 Ti GTX 1080 GTX 1070 Ti GTX 1070 GTX TITAN X GM200 GTX 980 Ti 200 400 600 800 1000 SE +/- 0.35, N = 3 SE +/- 0.49, N = 3 SE +/- 0.58, N = 3 SE +/- 2.49, N = 3 SE +/- 0.21, N = 3 SE +/- 0.09, N = 3 SE +/- 0.35, N = 3 SE +/- 1.00, N = 3 SE +/- 1.37, N = 3 1132 1015 738 629 458 413 375 372 356
NVIDIA GPU Cloud TensorFlow Test: ResNet-50, FP32 OpenBenchmarking.org Images Per Second, More Is Better NVIDIA GPU Cloud TensorFlow 18.09 Test: ResNet-50, FP32 TITAN RTX RTX 2080 Ti GTX 1080 Ti RTX 2080 GTX 1080 GTX 1070 Ti GTX 1070 GTX TITAN X GM200 70 140 210 280 350 SE +/- 0.31, N = 3 SE +/- 0.44, N = 3 SE +/- 0.19, N = 3 SE +/- 0.28, N = 3 SE +/- 0.07, N = 3 SE +/- 0.06, N = 3 SE +/- 0.09, N = 3 SE +/- 0.20, N = 3 299 285 210 205 143 133 125 125
NVIDIA GPU Cloud TensorFlow Test: VGG-16, FP32 OpenBenchmarking.org Images Per Second, More Is Better NVIDIA GPU Cloud TensorFlow 18.09 Test: VGG-16, FP32 TITAN RTX RTX 2080 Ti GTX 1080 Ti RTX 2080 GTX 1080 GTX 1070 Ti GTX TITAN X GM200 GTX 1070 40 80 120 160 200 SE +/- 0.19, N = 3 SE +/- 0.12, N = 3 SE +/- 0.12, N = 3 SE +/- 0.07, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.64, N = 3 SE +/- 0.13, N = 3 162.33 152.40 119.50 108.57 82.90 76.40 72.77 71.57
NVIDIA GPU Cloud TensorFlow Test: ResNet-50, FP16 OpenBenchmarking.org Images Per Second, More Is Better NVIDIA GPU Cloud TensorFlow 18.09 Test: ResNet-50, FP16 TITAN RTX RTX 2080 Ti RTX 2080 RTX 2070 GTX 1080 Ti GTX 1080 GTX 1070 Ti GTX 1070 GTX TITAN X GM200 GTX 980 Ti 110 220 330 440 550 SE +/- 0.06, N = 3 SE +/- 0.28, N = 3 SE +/- 0.85, N = 3 SE +/- 0.15, N = 3 SE +/- 0.10, N = 3 SE +/- 0.07, N = 3 SE +/- 0.03, N = 3 SE +/- 4.74, N = 3 SE +/- 1.68, N = 3 520 449 335 309 271 193 175 160 156 150
NVIDIA GPU Cloud TensorFlow Test: VGG-16, FP16 OpenBenchmarking.org Images Per Second, More Is Better NVIDIA GPU Cloud TensorFlow 18.09 Test: VGG-16, FP16 TITAN RTX RTX 2080 Ti RTX 2080 GTX 1080 Ti GTX 1080 GTX 1070 Ti GTX TITAN X GM200 GTX 980 Ti GTX 1070 50 100 150 200 250 SE +/- 0.46, N = 3 SE +/- 0.07, N = 3 SE +/- 0.09, N = 3 SE +/- 0.12, N = 3 SE +/- 0.24, N = 3 SE +/- 0.03, N = 3 SE +/- 0.40, N = 3 SE +/- 0.92, N = 3 SE +/- 0.07, N = 3 244.40 206.97 153.33 131.37 93.13 84.43 79.20 77.57 76.93
NVIDIA GPU Cloud TensorFlow Test: AlexNet, FP32 OpenBenchmarking.org Images Per Second, More Is Better NVIDIA GPU Cloud TensorFlow 18.09 Test: AlexNet, FP32 TITAN RTX RTX 2080 Ti GTX 1080 Ti RTX 2080 RTX 2070 GTX 1080 GTX 1070 Ti GTX TITAN X GM200 GTX 1070 GTX 980 Ti GTX 980 800 1600 2400 3200 4000 SE +/- 1.48, N = 3 SE +/- 6.99, N = 3 SE +/- 1.83, N = 3 SE +/- 1.84, N = 3 SE +/- 1.62, N = 3 SE +/- 0.32, N = 3 SE +/- 0.78, N = 3 SE +/- 0.44, N = 3 SE +/- 4.76, N = 3 SE +/- 1.06, N = 3 3576 3344 2539 2419 2174 1764 1591 1587 1516 1501 1154
NVIDIA GPU Cloud TensorFlow Test: AlexNet, FP16 OpenBenchmarking.org Images Per Second, More Is Better NVIDIA GPU Cloud TensorFlow 18.09 Test: AlexNet, FP16 TITAN RTX RTX 2080 Ti RTX 2080 GTX 1080 Ti GTX 1080 GTX 1070 Ti GTX TITAN X GM200 GTX 1070 GTX 980 Ti GTX 980 1100 2200 3300 4400 5500 SE +/- 4.39, N = 3 SE +/- 2.27, N = 3 SE +/- 3.35, N = 3 SE +/- 1.32, N = 3 SE +/- 2.60, N = 3 SE +/- 0.50, N = 3 SE +/- 2.24, N = 3 SE +/- 2.26, N = 3 SE +/- 6.83, N = 3 SE +/- 2.04, N = 3 5032 4432 3153 2674 1875 1683 1662 1563 1552 1208
cl-mem Benchmark: Copy OpenBenchmarking.org GB/s, More Is Better cl-mem 2017-01-13 Benchmark: Copy TITAN RTX RTX 2080 Ti RTX 2070 RTX 2080 GTX 1080 Ti RX Vega 64 GTX TITAN X GM200 GTX 980 Ti GTX 1080 RX Vega 56 GTX 1070 Ti GTX 1070 GTX 980 100 200 300 400 500 SE +/- 0.24, N = 3 SE +/- 0.39, N = 3 SE +/- 0.12, N = 3 SE +/- 0.09, N = 3 SE +/- 0.07, N = 3 SE +/- 0.07, N = 3 SE +/- 0.03, N = 3 SE +/- 0.00, N = 3 SE +/- 0.07, N = 3 SE +/- 0.21, N = 3 SE +/- 0.07, N = 3 SE +/- 0.07, N = 3 SE +/- 0.00, N = 3 484 454 330 328 317 221 218 217 209 203 188 187 143 1. (CC) gcc options: -O2 -flto -lOpenCL
SHOC Scalable HeterOgeneous Computing Target: OpenCL - Benchmark: FFT SP OpenBenchmarking.org GFLOPS, More Is Better SHOC Scalable HeterOgeneous Computing 2015-11-10 Target: OpenCL - Benchmark: FFT SP TITAN RTX RTX 2080 Ti RTX 2080 RX Vega 64 RTX 2070 GTX 1080 Ti RX Vega 56 GTX 980 Ti GTX TITAN X GM200 GTX 1080 GTX 1070 Ti GTX 980 GTX 1070 300 600 900 1200 1500 SE +/- 11.44, N = 3 SE +/- 14.24, N = 3 SE +/- 5.95, N = 3 SE +/- 0.64, N = 3 SE +/- 40.79, N = 3 SE +/- 1.23, N = 3 SE +/- 1.57, N = 3 SE +/- 0.20, N = 3 SE +/- 0.60, N = 3 SE +/- 2.68, N = 3 SE +/- 0.73, N = 3 SE +/- 0.27, N = 3 SE +/- 0.94, N = 3 1548 1443 1083 1070 998 972 926 728 726 575 497 468 452 -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 -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 -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 1. (CXX) g++ options: -O2 -lSHOCCommon -lrt
NVIDIA GPU Cloud TensorFlow System Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better NVIDIA GPU Cloud TensorFlow 18.09 System Power Consumption Monitor GTX 1070 Ti GTX 1070 GTX 1080 RTX 2080 GTX 1080 Ti GTX TITAN X GM200 RTX 2080 Ti TITAN RTX 60 120 180 240 300 Min: 58.5 / Avg: 162.02 / Max: 191 Min: 54.1 / Avg: 170.77 / Max: 203.5 Min: 46.3 / Avg: 198.19 / Max: 236.2 Min: 55.7 / Avg: 239.26 / Max: 287.8 Min: 51.2 / Avg: 241.65 / Max: 309.7 Min: 53 / Avg: 261.76 / Max: 321.8 Min: 50.2 / Avg: 270.5 / Max: 342.3 Min: 60 / Avg: 281.79 / Max: 357.7
NVIDIA GPU Cloud TensorFlow GPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better NVIDIA GPU Cloud TensorFlow 18.09 GPU Temperature Monitor GTX 1070 Ti RTX 2080 Ti GTX 1070 TITAN RTX GTX 1080 GTX 1080 Ti RTX 2080 GTX TITAN X GM200 16 32 48 64 80 Min: 46 / Avg: 52.21 / Max: 55 Min: 56 / Avg: 65.52 / Max: 71 Min: 58 / Avg: 66.1 / Max: 70 Min: 56 / Avg: 67.15 / Max: 73 Min: 60 / Avg: 69.33 / Max: 74 Min: 61 / Avg: 70.55 / Max: 77 Min: 61 / Avg: 74.1 / Max: 80 Min: 67 / Avg: 79.62 / Max: 84
NVIDIA GPU Cloud TensorFlow Test: VGG-16, FP32 OpenBenchmarking.org Images Per Second Per Watt, More Is Better NVIDIA GPU Cloud TensorFlow 18.09 Test: VGG-16, FP32 TITAN RTX RTX 2080 Ti GTX 1080 Ti GTX 1070 Ti RTX 2080 GTX 1080 GTX 1070 GTX TITAN X GM200 0.1305 0.261 0.3915 0.522 0.6525 0.58 0.56 0.49 0.47 0.45 0.42 0.42 0.28
NVIDIA GPU Cloud TensorFlow System Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better NVIDIA GPU Cloud TensorFlow 18.09 System Power Consumption Monitor GTX 1070 Ti GTX 1070 GTX 1080 RTX 2080 Ti RTX 2080 GTX 1080 Ti GTX 980 Ti TITAN RTX GTX TITAN X GM200 60 120 180 240 300 Min: 46.8 / Avg: 160.44 / Max: 192 Min: 43.7 / Avg: 168.53 / Max: 201.8 Min: 90.8 / Avg: 194.86 / Max: 239.8 Min: 51 / Avg: 219.66 / Max: 332.2 Min: 48.1 / Avg: 223.76 / Max: 283.3 Min: 51.7 / Avg: 242.51 / Max: 313.1 Min: 52.4 / Avg: 254.36 / Max: 318.4 Min: 49.3 / Avg: 256.56 / Max: 354.6 Min: 81.5 / Avg: 277.12 / Max: 327.7
NVIDIA GPU Cloud TensorFlow GPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better NVIDIA GPU Cloud TensorFlow 18.09 GPU Temperature Monitor GTX 1070 Ti RTX 2080 Ti TITAN RTX GTX 1080 GTX 1070 RTX 2080 GTX 1080 Ti GTX TITAN X GM200 GTX 980 Ti 16 32 48 64 80 Min: 45 / Avg: 52.18 / Max: 55 Min: 54 / Avg: 61.56 / Max: 68 Min: 55 / Avg: 62.56 / Max: 68 Min: 50 / Avg: 65.84 / Max: 74 Min: 59 / Avg: 66.13 / Max: 70 Min: 59 / Avg: 69.86 / Max: 77 Min: 61 / Avg: 70.1 / Max: 76 Min: 67 / Avg: 79 / Max: 84 Min: 67 / Avg: 79.22 / Max: 84
NVIDIA GPU Cloud TensorFlow Test: VGG-16, FP16 OpenBenchmarking.org Images Per Second Per Watt, More Is Better NVIDIA GPU Cloud TensorFlow 18.09 Test: VGG-16, FP16 TITAN RTX RTX 2080 Ti RTX 2080 GTX 1080 Ti GTX 1070 Ti GTX 1080 GTX 1070 GTX 980 Ti GTX TITAN X GM200 0.2138 0.4276 0.6414 0.8552 1.069 0.95 0.94 0.69 0.54 0.53 0.48 0.46 0.30 0.29
NVIDIA GPU Cloud TensorFlow System Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better NVIDIA GPU Cloud TensorFlow 18.09 System Power Consumption Monitor GTX 1070 Ti GTX 1070 RTX 2080 RTX 2080 Ti GTX 1080 TITAN RTX GTX 1080 Ti GTX 980 Ti GTX TITAN X GM200 60 120 180 240 300 Min: 47.2 / Avg: 146.22 / Max: 188.6 Min: 44.1 / Avg: 157.87 / Max: 210.2 Min: 47.6 / Avg: 177.11 / Max: 285.3 Min: 50 / Avg: 183.11 / Max: 341.1 Min: 71.3 / Avg: 185.89 / Max: 249.7 Min: 58.3 / Avg: 196.21 / Max: 353.3 Min: 52.2 / Avg: 211.84 / Max: 320.9 Min: 52.9 / Avg: 226.01 / Max: 305.4 Min: 55.1 / Avg: 232.58 / Max: 323
NVIDIA GPU Cloud TensorFlow GPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better NVIDIA GPU Cloud TensorFlow 18.09 GPU Temperature Monitor GTX 1070 Ti RTX 2080 Ti TITAN RTX GTX 1070 GTX 1080 RTX 2080 GTX 1080 Ti GTX 980 Ti GTX TITAN X GM200 16 32 48 64 80 Min: 43 / Avg: 49.56 / Max: 55 Min: 53 / Avg: 57.76 / Max: 65 Min: 54 / Avg: 59.11 / Max: 66 Min: 55 / Avg: 64.07 / Max: 72 Min: 51 / Avg: 64.33 / Max: 76 Min: 57 / Avg: 64.7 / Max: 74 Min: 56 / Avg: 66.24 / Max: 77 Min: 61 / Avg: 74.85 / Max: 84 Min: 62 / Avg: 75.61 / Max: 85
NVIDIA GPU Cloud TensorFlow Test: Inception v4, FP16 OpenBenchmarking.org Images Per Second Per Watt, More Is Better NVIDIA GPU Cloud TensorFlow 18.09 Test: Inception v4, FP16 TITAN RTX RTX 2080 Ti RTX 2080 GTX 1080 Ti GTX 1070 Ti GTX 1080 GTX 1070 GTX TITAN X GM200 GTX 980 Ti 0.1755 0.351 0.5265 0.702 0.8775 0.78 0.74 0.58 0.35 0.34 0.30 0.28 0.19 0.18
NVIDIA GPU Cloud TensorFlow System Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better NVIDIA GPU Cloud TensorFlow 18.09 System Power Consumption Monitor GTX 1070 Ti GTX 1070 GTX 1080 RTX 2080 RTX 2080 Ti GTX 1080 Ti GTX 980 Ti GTX TITAN X GM200 TITAN RTX 60 120 180 240 300 Min: 46.8 / Avg: 163.6 / Max: 187.8 Min: 43.4 / Avg: 181.99 / Max: 210.5 Min: 76.2 / Avg: 215.22 / Max: 247 Min: 47.7 / Avg: 229.8 / Max: 284.5 Min: 49.5 / Avg: 249.29 / Max: 343.1 Min: 64 / Avg: 257.4 / Max: 319.4 Min: 124.1 / Avg: 260.98 / Max: 317 Min: 102.1 / Avg: 265.29 / Max: 320.1 Min: 50.7 / Avg: 275.3 / Max: 360
NVIDIA GPU Cloud TensorFlow GPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better NVIDIA GPU Cloud TensorFlow 18.09 GPU Temperature Monitor GTX 1070 Ti RTX 2080 Ti TITAN RTX GTX 1070 GTX 1080 GTX 1080 Ti RTX 2080 GTX 980 Ti GTX TITAN X GM200 16 32 48 64 80 Min: 43 / Avg: 52.93 / Max: 56 Min: 55 / Avg: 64.78 / Max: 71 Min: 55 / Avg: 65.27 / Max: 72 Min: 56 / Avg: 69 / Max: 74 Min: 58 / Avg: 72.23 / Max: 79 Min: 60 / Avg: 72.84 / Max: 80 Min: 60 / Avg: 73.17 / Max: 80 Min: 70 / Avg: 80.35 / Max: 84 Min: 72 / Avg: 80.77 / Max: 85
NVIDIA GPU Cloud TensorFlow Test: Googlenet, FP16 OpenBenchmarking.org Images Per Second Per Watt, More Is Better NVIDIA GPU Cloud TensorFlow 18.09 Test: Googlenet, FP16 TITAN RTX RTX 2080 Ti RTX 2080 GTX 1070 Ti GTX 1080 Ti GTX 1080 GTX 1070 GTX TITAN X GM200 GTX 980 Ti 0.9248 1.8496 2.7744 3.6992 4.624 4.11 4.07 3.21 2.53 2.45 2.13 2.06 1.40 1.36
NVIDIA GPU Cloud TensorFlow System Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better NVIDIA GPU Cloud TensorFlow 18.09 System Power Consumption Monitor GTX 1070 Ti GTX 1070 GTX 1080 RTX 2070 GTX 980 GTX 1080 Ti RTX 2080 GTX 980 Ti TITAN RTX GTX TITAN X GM200 RTX 2080 Ti 60 120 180 240 300 Min: 48.2 / Avg: 144.76 / Max: 185.9 Min: 87.1 / Avg: 157.65 / Max: 201.5 Min: 100.9 / Avg: 178.22 / Max: 229 Min: 64.2 / Avg: 185.45 / Max: 243.7 Min: 101.5 / Avg: 186.05 / Max: 232.5 Min: 126 / Avg: 208.21 / Max: 307.4 Min: 48 / Avg: 211.46 / Max: 284.1 Min: 122.8 / Avg: 227.61 / Max: 318.8 Min: 78.6 / Avg: 243.91 / Max: 357 Min: 136.3 / Avg: 252.18 / Max: 313.2 Min: 48.9 / Avg: 257.45 / Max: 338.7
NVIDIA GPU Cloud TensorFlow GPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better NVIDIA GPU Cloud TensorFlow 18.09 GPU Temperature Monitor GTX 1070 Ti RTX 2070 RTX 2080 Ti TITAN RTX GTX 1070 GTX 1080 GTX 1080 Ti RTX 2080 GTX 980 GTX 980 Ti GTX TITAN X GM200 16 32 48 64 80 Min: 44 / Avg: 49.07 / Max: 52 Min: 46 / Avg: 55.88 / Max: 61 Min: 53 / Avg: 61.36 / Max: 67 Min: 55 / Avg: 61.71 / Max: 67 Min: 61 / Avg: 64.2 / Max: 68 Min: 63 / Avg: 66.8 / Max: 71 Min: 64 / Avg: 67.58 / Max: 71 Min: 59 / Avg: 69.81 / Max: 76 Min: 63 / Avg: 72.44 / Max: 77 Min: 71 / Avg: 77.5 / Max: 82 Min: 72 / Avg: 78.81 / Max: 84
NVIDIA GPU Cloud TensorFlow Test: AlexNet, FP32 OpenBenchmarking.org Images Per Second Per Watt, More Is Better NVIDIA GPU Cloud TensorFlow 18.09 Test: AlexNet, FP32 TITAN RTX RTX 2080 Ti GTX 1080 Ti RTX 2070 RTX 2080 GTX 1070 Ti GTX 1080 GTX 1070 GTX 980 Ti GTX TITAN X GM200 GTX 980 4 8 12 16 20 14.66 12.99 12.19 11.72 11.44 10.99 9.90 9.61 6.59 6.29 6.20
NVIDIA GPU Cloud TensorFlow System Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better NVIDIA GPU Cloud TensorFlow 18.09 System Power Consumption Monitor GTX 1070 Ti GTX 1070 GTX 1080 RTX 2080 Ti GTX 980 RTX 2080 TITAN RTX GTX 1080 Ti GTX TITAN X GM200 GTX 980 Ti 60 120 180 240 300 Min: 46.9 / Avg: 135.79 / Max: 175 Min: 68.9 / Avg: 158.49 / Max: 192.3 Min: 44.1 / Avg: 167.55 / Max: 234.8 Min: 49.3 / Avg: 177.62 / Max: 332.6 Min: 48.6 / Avg: 187.19 / Max: 240.4 Min: 47.3 / Avg: 190.7 / Max: 270.1 Min: 50.6 / Avg: 195.26 / Max: 352.6 Min: 51.3 / Avg: 213.37 / Max: 303.2 Min: 55.1 / Avg: 236.59 / Max: 321.2 Min: 135.2 / Avg: 237.19 / Max: 295.5
NVIDIA GPU Cloud TensorFlow GPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better NVIDIA GPU Cloud TensorFlow 18.09 GPU Temperature Monitor GTX 1070 Ti RTX 2080 Ti TITAN RTX GTX 1070 GTX 980 GTX 1080 GTX 1080 Ti RTX 2080 GTX 980 Ti GTX TITAN X GM200 16 32 48 64 80 Min: 46 / Avg: 49.93 / Max: 53 Min: 57 / Avg: 60.36 / Max: 64 Min: 58 / Avg: 61.4 / Max: 65 Min: 59 / Avg: 64.06 / Max: 67 Min: 51 / Avg: 65.82 / Max: 74 Min: 62 / Avg: 66.46 / Max: 70 Min: 63 / Avg: 67.2 / Max: 70 Min: 63 / Avg: 67.57 / Max: 72 Min: 62 / Avg: 73.47 / Max: 81 Min: 68 / Avg: 77.07 / Max: 85
NVIDIA GPU Cloud TensorFlow Test: AlexNet, FP16 OpenBenchmarking.org Images Per Second Per Watt, More Is Better NVIDIA GPU Cloud TensorFlow 18.09 Test: AlexNet, FP16 TITAN RTX RTX 2080 Ti RTX 2080 GTX 1080 Ti GTX 1070 Ti GTX 1080 GTX 1070 GTX TITAN X GM200 GTX 980 Ti GTX 980 6 12 18 24 30 25.77 24.95 16.53 12.53 12.39 11.19 9.86 7.03 6.54 6.45
NVIDIA GPU Cloud TensorFlow System Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better NVIDIA GPU Cloud TensorFlow 18.09 System Power Consumption Monitor GTX 1070 Ti GTX 1070 GTX 1080 RTX 2080 GTX 1080 Ti RTX 2080 Ti TITAN RTX GTX TITAN X GM200 70 140 210 280 350 Min: 48 / Avg: 157.29 / Max: 187.8 Min: 45.9 / Avg: 172.02 / Max: 213.8 Min: 44.1 / Avg: 196.38 / Max: 249.7 Min: 48 / Avg: 206.72 / Max: 285 Min: 79.7 / Avg: 234.81 / Max: 318.6 Min: 50.5 / Avg: 248.25 / Max: 346.7 Min: 50.5 / Avg: 252.59 / Max: 364.6 Min: 56.2 / Avg: 255.72 / Max: 321
NVIDIA GPU Cloud TensorFlow GPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better NVIDIA GPU Cloud TensorFlow 18.09 GPU Temperature Monitor GTX 1070 Ti RTX 2080 Ti TITAN RTX GTX 1070 GTX 1080 GTX 1080 Ti RTX 2080 GTX TITAN X GM200 16 32 48 64 80 Min: 44 / Avg: 50.85 / Max: 54 Min: 54 / Avg: 61.16 / Max: 67 Min: 54 / Avg: 62.76 / Max: 70 Min: 57 / Avg: 65.61 / Max: 71 Min: 60 / Avg: 68.77 / Max: 75 Min: 62 / Avg: 70.04 / Max: 77 Min: 59 / Avg: 70.41 / Max: 77 Min: 65 / Avg: 77.91 / Max: 84
NVIDIA GPU Cloud TensorFlow Test: ResNet-50, FP32 OpenBenchmarking.org Images Per Second Per Watt, More Is Better NVIDIA GPU Cloud TensorFlow 18.09 Test: ResNet-50, FP32 TITAN RTX RTX 2080 Ti RTX 2080 GTX 1080 Ti GTX 1070 Ti GTX 1080 GTX 1070 GTX TITAN X GM200 0.2655 0.531 0.7965 1.062 1.3275 1.18 1.15 0.99 0.89 0.84 0.73 0.73 0.49
NVIDIA GPU Cloud TensorFlow System Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better NVIDIA GPU Cloud TensorFlow 18.09 System Power Consumption Monitor GTX 1070 Ti RTX 2070 GTX 1070 RTX 2080 GTX 1080 TITAN RTX RTX 2080 Ti GTX 1080 Ti GTX 980 Ti GTX TITAN X GM200 60 120 180 240 300 Min: 47 / Avg: 153.76 / Max: 192.3 Min: 71.1 / Avg: 162.36 / Max: 246.8 Min: 42.7 / Avg: 174.04 / Max: 212.6 Min: 47.3 / Avg: 179.59 / Max: 284.7 Min: 44.7 / Avg: 189.85 / Max: 248.8 Min: 51 / Avg: 203.63 / Max: 350.6 Min: 56.1 / Avg: 213.62 / Max: 342.3 Min: 54.6 / Avg: 222.3 / Max: 319.6 Min: 52.8 / Avg: 244.09 / Max: 310.7 Min: 55.5 / Avg: 252.42 / Max: 326.9
NVIDIA GPU Cloud TensorFlow GPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better NVIDIA GPU Cloud TensorFlow 18.09 GPU Temperature Monitor RTX 2070 GTX 1070 Ti RTX 2080 Ti TITAN RTX GTX 1070 RTX 2080 GTX 1080 Ti GTX 1080 GTX 980 Ti GTX TITAN X GM200 16 32 48 64 80 Min: 32 / Avg: 45.47 / Max: 58 Min: 46 / Avg: 50.94 / Max: 55 Min: 55 / Avg: 59.52 / Max: 65 Min: 57 / Avg: 61.37 / Max: 67 Min: 58 / Avg: 65.55 / Max: 70 Min: 60 / Avg: 67.05 / Max: 75 Min: 61 / Avg: 68.17 / Max: 75 Min: 61 / Avg: 68.3 / Max: 75 Min: 65 / Avg: 76.82 / Max: 83 Min: 66 / Avg: 77.41 / Max: 84
NVIDIA GPU Cloud TensorFlow Test: ResNet-50, FP16 OpenBenchmarking.org Images Per Second Per Watt, More Is Better NVIDIA GPU Cloud TensorFlow 18.09 Test: ResNet-50, FP16 TITAN RTX RTX 2080 Ti RTX 2070 RTX 2080 GTX 1080 Ti GTX 1070 Ti GTX 1080 GTX 1070 GTX TITAN X GM200 GTX 980 Ti 0.5738 1.1476 1.7214 2.2952 2.869 2.55 2.10 1.90 1.86 1.22 1.14 1.02 0.92 0.62 0.61
Chaos Group V-RAY System Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better Chaos Group V-RAY 1.1.0 System Power Consumption Monitor GTX 1070 Ti GTX 1070 GTX 1080 GTX 980 RTX 2070 RTX 2080 GTX 980 Ti GTX 1080 Ti GTX TITAN X GM200 RTX 2080 Ti TITAN RTX 50 100 150 200 250 Min: 46.1 / Avg: 130.78 / Max: 135.6 Min: 43.4 / Avg: 151.17 / Max: 164.2 Min: 43.6 / Avg: 153.26 / Max: 165.9 Min: 47.6 / Avg: 170.22 / Max: 175.3 Min: 53.7 / Avg: 185.77 / Max: 199.3 Min: 63 / Avg: 191.71 / Max: 202.8 Min: 52.1 / Avg: 218.49 / Max: 231.5 Min: 120.4 / Avg: 218.99 / Max: 231.8 Min: 55.7 / Avg: 230.04 / Max: 248.4 Min: 69.5 / Avg: 242.72 / Max: 272 Min: 57.5 / Avg: 262.41 / Max: 287.8
Chaos Group V-RAY GPU Temperature Monitor OpenBenchmarking.org Celsius, Fewer Is Better Chaos Group V-RAY 1.1.0 GPU Temperature Monitor GTX 1070 Ti RTX 2080 Ti RTX 2070 GTX 1070 GTX 1080 TITAN RTX GTX 1080 Ti RTX 2080 GTX 980 GTX 980 Ti GTX TITAN X GM200 16 32 48 64 80 Min: 38 / Avg: 47.77 / Max: 50 Min: 46 / Avg: 60.03 / Max: 68 Min: 53 / Avg: 60.72 / Max: 62 Min: 46 / Avg: 62.55 / Max: 68 Min: 48 / Avg: 62.93 / Max: 67 Min: 56 / Avg: 67.85 / Max: 72 Min: 54 / Avg: 68.11 / Max: 73 Min: 50 / Avg: 68.2 / Max: 74 Min: 64 / Avg: 72.91 / Max: 75 Min: 69 / Avg: 78.07 / Max: 81 Min: 67 / Avg: 78.35 / Max: 82
System Power Consumption Monitor Phoronix Test Suite System Monitoring OpenBenchmarking.org Watts System Power Consumption Monitor Phoronix Test Suite System Monitoring GTX 980 GTX 1070 Ti RX Vega 56 GTX 1070 RTX 2070 GTX 1080 RX Vega 64 RTX 2080 GTX 1080 Ti RTX 2080 Ti GTX 980 Ti GTX TITAN X GM200 TITAN RTX 70 140 210 280 350 Min: 45.1 / Avg: 126.87 / Max: 240.4 Min: 45.9 / Avg: 127.84 / Max: 213.8 Min: 48.8 / Avg: 143.52 / Max: 284.1 Min: 41.9 / Avg: 143.92 / Max: 213.8 Min: 42.1 / Avg: 146.13 / Max: 247.2 Min: 42.2 / Avg: 154.56 / Max: 251.7 Min: 48.4 / Avg: 169.45 / Max: 358.6 Min: 43.9 / Avg: 175.16 / Max: 287.8 Min: 43.4 / Avg: 200.91 / Max: 320.9 Min: 45.5 / Avg: 208.03 / Max: 346.7 Min: 52.1 / Avg: 218.82 / Max: 321.2 Min: 48.8 / Avg: 240.32 / Max: 327.7 Min: 47.9 / Avg: 242.09 / Max: 364.6
GPU Temperature Monitor Phoronix Test Suite System Monitoring OpenBenchmarking.org Celsius GPU Temperature Monitor Phoronix Test Suite System Monitoring GTX 1070 Ti RX Vega 56 RX Vega 64 RTX 2070 GTX 980 RTX 2080 Ti GTX 1070 GTX 1080 TITAN RTX GTX 1080 Ti RTX 2080 GTX 980 Ti GTX TITAN X GM200 16 32 48 64 80 Min: 36 / Avg: 46.92 / Max: 60 Min: 31 / Avg: 51.02 / Max: 75 Min: 28 / Avg: 52.98 / Max: 85 Min: 33 / Avg: 54.57 / Max: 64 Min: 34 / Avg: 58.36 / Max: 77 Min: 34 / Avg: 60.3 / Max: 76 Min: 31 / Avg: 61.13 / Max: 75 Min: 45 / Avg: 63.06 / Max: 79 Min: 38 / Avg: 63.55 / Max: 77 Min: 33 / Avg: 66.46 / Max: 80 Min: 35 / Avg: 66.5 / Max: 80 Min: 38 / Avg: 74.74 / Max: 84 Min: 35 / Avg: 76.87 / Max: 85
LuxMark System Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better LuxMark 3.1 System Power Consumption Monitor GTX 1070 Ti GTX 1080 GTX 1070 GTX 980 RTX 2070 GTX 980 Ti RTX 2080 GTX 1080 Ti GTX TITAN X GM200 RX Vega 56 RTX 2080 Ti RX Vega 64 TITAN RTX 60 120 180 240 300 Min: 146.8 / Avg: 148.92 / Max: 149.4 Min: 90.8 / Avg: 174.24 / Max: 176.2 Min: 83.1 / Avg: 176.9 / Max: 181.3 Min: 80.2 / Avg: 189.6 / Max: 196.9 Min: 78 / Avg: 225.33 / Max: 232.6 Min: 118.7 / Avg: 233.83 / Max: 241.4 Min: 101.9 / Avg: 240.83 / Max: 247.3 Min: 122.9 / Avg: 241.59 / Max: 247.8 Min: 126.4 / Avg: 249.16 / Max: 256.8 Min: 51.8 / Avg: 251.16 / Max: 263.3 Min: 111.1 / Avg: 315.29 / Max: 328.4 Min: 53 / Avg: 323.35 / Max: 337.9 Min: 48.7 / Avg: 329.43 / Max: 344
SHOC Scalable HeterOgeneous Computing System Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better SHOC Scalable HeterOgeneous Computing 2015-11-10 System Power Consumption Monitor GTX 1070 Ti GTX 1070 GTX 1080 RTX 2070 RTX 2080 GTX 1080 Ti RX Vega 56 RTX 2080 Ti RX Vega 64 TITAN RTX 50 100 150 200 250 Min: 47 / Avg: 122.6 / Max: 141.5 Min: 82.6 / Avg: 134.72 / Max: 155.3 Min: 89.7 / Avg: 144.76 / Max: 164.6 Min: 53.7 / Avg: 162.86 / Max: 198.7 Min: 47.1 / Avg: 169.8 / Max: 202.9 Min: 120.8 / Avg: 190.06 / Max: 216.8 Min: 49.4 / Avg: 197.63 / Max: 234.4 Min: 47.5 / Avg: 222.96 / Max: 282.7 Min: 51.8 / Avg: 223.18 / Max: 249.9 Min: 47.9 / Avg: 232.9 / Max: 281.3
Phoronix Test Suite v10.8.4