NVIDIA GeForce RTX SUPER Linux OpenCL/CUDA GPU compute benchmarks by Michael Larabel for a future article.
RTX 2070 SUPER Processor: Intel Core i9-9900K @ 5.00GHz (8 Cores / 16 Threads), Motherboard: ASUS PRIME Z390-A (0802 BIOS), Chipset: Intel Cannon Lake PCH, Memory: 16384MB, Disk: Samsung SSD 970 EVO 250GB, Graphics: NVIDIA GeForce RTX 2070 SUPER 8GB (1605/7000MHz), Audio: Realtek ALC1220, Monitor: Acer B286HK, Network: Intel I219-V
OS: Ubuntu 19.04, Kernel: 5.3.0-999-generic (x86_64) 20190914, Desktop: GNOME Shell 3.32.2, Display Server: X Server 1.20.4, Display Driver: NVIDIA 435.21, OpenGL: 4.6.0, Compiler: GCC 8.3.0, File-System: ext4, Screen Resolution: 3840x2160
Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --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 Notes: Scaling Governor: intel_pstate performanceOpenCL Notes: GPU Compute Cores: 2560Python Notes: Python 2.7.16 + Python 3.7.3Security Notes: l1tf: Not affected + mds: Mitigation of Clear buffers; SMT vulnerable + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full generic retpoline IBPB: conditional IBRS_FW STIBP: conditional RSB filling
RTX 2060 SUPER Changed Graphics to NVIDIA GeForce RTX 2060 SUPER 8GB (1470/7000MHz) .
OpenCL Change: GPU Compute Cores: 2176
GTX 980 Ti Changed Graphics to NVIDIA GeForce GTX 980 Ti 6GB (999/3505MHz) .
OpenCL Change: GPU Compute Cores: 2816
RTX 2080 SUPER Changed Graphics to NVIDIA GeForce RTX 2080 SUPER 8GB (1650/7750MHz) .
OpenCL Change: GPU Compute Cores: 3072
TITAN RTX Changed Graphics to NVIDIA TITAN RTX 24GB (1350/7000MHz) .
OpenCL Change: GPU Compute Cores: 4608
RTX 2070 Processor: Intel Core i9-9900K @ 5.00GHz (8 Cores / 16 Threads), Motherboard: ASUS PRIME Z390-A (0802 BIOS), Chipset: Intel Cannon Lake PCH, Memory: 16384MB, Disk: Samsung SSD 970 EVO 250GB, Graphics: ASUS NVIDIA GeForce RTX 2070 8GB (1410/7000MHz)Audio: Realtek ALC1220, Monitor: Acer B286HK, Network: Intel I219-V
OS: Ubuntu 19.04, Kernel: 5.0.0-29-generic (x86_64), Desktop: GNOME Shell 3.32.2, Display Server: X Server 1.20.4, Display Driver: NVIDIA 435.21, OpenGL: 4.6.0, Compiler: GCC 8.3.0, File-System: ext4, Screen Resolution: 3840x2160
Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --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 Notes: Scaling Governor: intel_pstate performanceOpenCL Notes: GPU Compute Cores: 2304Python Notes: Python 2.7.16 + Python 3.7.3Security Notes: l1tf: Not affected + mds: Mitigation of Clear buffers; SMT vulnerable + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full generic retpoline IBPB: conditional IBRS_FW STIBP: conditional RSB filling
GTX 1070 Ti Changed Graphics to Zotac NVIDIA GeForce GTX 1070 Ti 8GB (1607/4006MHz) .
OpenCL Change: GPU Compute Cores: 2432
RTX 2080 Changed Graphics to Zotac NVIDIA GeForce RTX 2080 8GB (795/810MHz) .
OpenCL Change: GPU Compute Cores: 2944
RTX 2060 Changed Graphics to NVIDIA GeForce RTX 2060 6GB (1365/7000MHz) .
OpenCL Change: GPU Compute Cores: 1920
GTX 1060 Changed Graphics to NVIDIA GeForce GTX 1060 6GB (1506/4006MHz) .
OpenCL Change: GPU Compute Cores: 1280
GTX 1080 Changed Graphics to NVIDIA GeForce GTX 1080 8GB (1607/5005MHz) .
OpenCL Change: GPU Compute Cores: 2560
GTX 1080 Ti Changed Graphics to NVIDIA GeForce GTX 1080 Ti 11GB (1480/5508MHz) .
OpenCL Change: GPU Compute Cores: 3584
GTX 1660 Ti Changed Graphics to eVGA NVIDIA GeForce GTX 1660 Ti 6GB (1500/6000MHz) .
OpenCL Change: GPU Compute Cores: 1536
GTX 980 Changed Graphics to NVIDIA GeForce GTX 980 4GB (1126/3505MHz) .
OpenCL Change: GPU Compute Cores: 2048
GTX 1660 Changed Graphics to ASUS NVIDIA GeForce GTX 1660 6GB (1530/4001MHz) .
OpenCL Change: GPU Compute Cores: 1408
GTX 1070 Changed Graphics to NVIDIA GeForce GTX 1070 8GB (1506/4006MHz) .
OpenCL Change: GPU Compute Cores: 1920
GTX 970 Changed Graphics to eVGA NVIDIA GeForce GTX 970 4GB (1163/3505MHz) .
OpenCL Change: GPU Compute Cores: 1664
RTX 2080 Ti Changed Graphics to NVIDIA GeForce RTX 2080 Ti 11GB (1350/7000MHz) .
OpenCL Change: GPU Compute Cores: 4352
NVIDIA Linux OpenCL CUDA RTX SUPER Compute OpenBenchmarking.org Phoronix Test Suite Intel Core i9-9900K @ 5.00GHz (8 Cores / 16 Threads) ASUS PRIME Z390-A (0802 BIOS) Intel Cannon Lake PCH 16384MB Samsung SSD 970 EVO 250GB NVIDIA GeForce RTX 2070 SUPER 8GB (1605/7000MHz) NVIDIA GeForce RTX 2060 SUPER 8GB (1470/7000MHz) NVIDIA GeForce GTX 980 Ti 6GB (999/3505MHz) NVIDIA GeForce RTX 2080 SUPER 8GB (1650/7750MHz) NVIDIA TITAN RTX 24GB (1350/7000MHz) ASUS NVIDIA GeForce RTX 2070 8GB (1410/7000MHz) Zotac NVIDIA GeForce GTX 1070 Ti 8GB (1607/4006MHz) Zotac NVIDIA GeForce RTX 2080 8GB (795/810MHz) NVIDIA GeForce RTX 2060 6GB (1365/7000MHz) NVIDIA GeForce GTX 1060 6GB (1506/4006MHz) NVIDIA GeForce GTX 1080 8GB (1607/5005MHz) NVIDIA GeForce GTX 1080 Ti 11GB (1480/5508MHz) eVGA NVIDIA GeForce GTX 1660 Ti 6GB (1500/6000MHz) NVIDIA GeForce GTX 980 4GB (1126/3505MHz) ASUS NVIDIA GeForce GTX 1660 6GB (1530/4001MHz) NVIDIA GeForce GTX 1070 8GB (1506/4006MHz) eVGA NVIDIA GeForce GTX 970 4GB (1163/3505MHz) NVIDIA GeForce RTX 2080 Ti 11GB (1350/7000MHz) Realtek ALC1220 Acer B286HK Intel I219-V Ubuntu 19.04 5.3.0-999-generic (x86_64) 20190914 5.0.0-29-generic (x86_64) GNOME Shell 3.32.2 X Server 1.20.4 NVIDIA 435.21 4.6.0 GCC 8.3.0 ext4 3840x2160 Processor Motherboard Chipset Memory Disk Graphics Audio Monitor Network OS Kernels Desktop Display Server Display Driver OpenGL Compiler File-System Screen Resolution NVIDIA Linux OpenCL CUDA RTX SUPER Compute Benchmarks System Logs - --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --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 - Scaling Governor: intel_pstate performance - RTX 2070 SUPER: GPU Compute Cores: 2560 - RTX 2060 SUPER: GPU Compute Cores: 2176 - GTX 980 Ti: GPU Compute Cores: 2816 - RTX 2080 SUPER: GPU Compute Cores: 3072 - TITAN RTX: GPU Compute Cores: 4608 - RTX 2070: GPU Compute Cores: 2304 - GTX 1070 Ti: GPU Compute Cores: 2432 - RTX 2080: GPU Compute Cores: 2944 - RTX 2060: GPU Compute Cores: 1920 - GTX 1060: GPU Compute Cores: 1280 - GTX 1080: GPU Compute Cores: 2560 - GTX 1080 Ti: GPU Compute Cores: 3584 - GTX 1660 Ti: GPU Compute Cores: 1536 - GTX 980: GPU Compute Cores: 2048 - GTX 1660: GPU Compute Cores: 1408 - GTX 1070: GPU Compute Cores: 1920 - GTX 970: GPU Compute Cores: 1664 - RTX 2080 Ti: GPU Compute Cores: 4352 - RTX 2070 SUPER, GTX 980 Ti, RTX 2080 SUPER, TITAN RTX, RTX 2070, GTX 1070 Ti, RTX 2080, RTX 2060, GTX 1060, GTX 1080, GTX 1080 Ti, GTX 1660 Ti, GTX 980, GTX 1660, GTX 1070, GTX 970, RTX 2080 Ti: Python 2.7.16 + Python 3.7.3 - l1tf: Not affected + mds: Mitigation of Clear buffers; SMT vulnerable + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full generic retpoline IBPB: conditional IBRS_FW STIBP: conditional RSB filling
RTX 2070 SUPER RTX 2060 SUPER GTX 980 Ti RTX 2080 SUPER TITAN RTX RTX 2070 GTX 1070 Ti RTX 2080 RTX 2060 GTX 1060 GTX 1080 GTX 1080 Ti GTX 1660 Ti GTX 980 GTX 1660 GTX 1070 GTX 970 RTX 2080 Ti Logarithmic Result Overview Phoronix Test Suite clpeak SHOC Scalable HeterOgeneous Computing LuxMark PlaidML OctaneBench cl-mem FAHBench Darktable Rodinia LeelaChessZero NAMD CUDA JuliaGPU ViennaCL
RTX 2070 SUPER RTX 2060 SUPER GTX 980 Ti RTX 2080 SUPER TITAN RTX RTX 2070 GTX 1070 Ti RTX 2080 RTX 2060 GTX 1060 GTX 1080 GTX 1080 Ti GTX 1660 Ti GTX 980 GTX 1660 GTX 1070 GTX 970 RTX 2080 Ti Logarithmic Per Watt Result Overview Phoronix Test Suite clpeak PlaidML cl-mem SHOC Scalable HeterOgeneous Computing JuliaGPU ViennaCL FAHBench LuxMark LeelaChessZero OctaneBench P.W.G.M P.W.G.M P.W.G.M P.W.G.M P.W.G.M P.W.G.M P.W.G.M P.W.G.M P.W.G.M P.W.G.M
NVIDIA Linux OpenCL CUDA RTX SUPER Compute shoc: OpenCL - Max SP Flops octanebench: Total Score luxmark: GPU - Microphone luxmark: GPU - Luxball HDR luxmark: GPU - Hotel fahbench: plaidml: Yes - Inference - NASNer Large - OpenCL plaidml: Yes - Inference - VGG19 - OpenCL plaidml: Yes - Inference - DenseNet 201 - OpenCL rodinia: OpenCL Myocyte plaidml: Yes - Inference - VGG16 - OpenCL clpeak: Double-Precision Double plaidml: No - Inference - VGG19 - OpenCL plaidml: Yes - Inference - Inception V3 - OpenCL lczero: OpenCL plaidml: No - Inference - VGG16 - OpenCL plaidml: No - Inference - Inception V3 - OpenCL plaidml: Yes - Inference - ResNet 50 - OpenCL namd-cuda: ATPase Simulation - 327,506 Atoms plaidml: No - Inference - ResNet 50 - OpenCL plaidml: No - Inference - IMDB LSTM - OpenCL rodinia: OpenCL Particle Filter cl-mem: Read juliagpu: GPU plaidml: Yes - Inference - Mobilenet - OpenCL cl-mem: Copy cl-mem: Write plaidml: No - Inference - Mobilenet - OpenCL darktable: Masskrug - OpenCL clpeak: Integer Compute INT darktable: Boat - OpenCL clpeak: Single-Precision Float darktable: Server Room - OpenCL viennacl: OpenCL LU Factorization shoc: OpenCL - FFT SP clpeak: Global Memory Bandwidth shoc: OpenCL - MD5 Hash RTX 2070 SUPER RTX 2060 SUPER GTX 980 Ti RTX 2080 SUPER TITAN RTX RTX 2070 GTX 1070 Ti RTX 2080 RTX 2060 GTX 1060 GTX 1080 GTX 1080 Ti GTX 1660 Ti GTX 980 GTX 1660 GTX 1070 GTX 970 RTX 2080 Ti 9869.34 220.76 20499 29734 6565 229.12 55.24 97.82 190.01 30.76 123.20 310.27 122.32 239.61 1604.21 154.64 215.85 283.98 0.19501 421.58 499.69 6.82 395.67 275868151.17 2264.97 291.87 319.57 1649.17 3.71 8570.60 1.93 8502.71 0.80 70.45 1088.17 369.11 21.78 8378.87 205.23 18509 30093 6148 205.20 48.96 80.82 179.51 30.42 102.58 263.11 101.17 219.76 998.17 128.22 199.43 250.98 0.19336 374.71 440.79 7.87 395.67 264172441.47 1983.82 287.80 333.20 1531.01 3.68 7023.07 1.95 7089.50 0.75 69.17 971.24 367.92 18.22 6213.97 142.20 11096 16871 3885 116.02 30.64 56.13 111.46 52.13 71.26 196.60 68.47 116.31 466.84 87.39 135.14 162.63 0.28675 247.47 270.00 9.95 265.33 195653728.47 1202.77 216.83 241.50 990.12 4.12 1610.28 3.27 5538.75 1.51 62.01 725.98 263.22 9.22 12015.50 233.56 20164 30179 6839 256.83 64.80 115.44 200.38 30.63 145.65 378.98 143.02 301.11 2105.26 180.45 259.26 327.80 0.19385 468.70 589.86 5.74 436.27 286818331.27 2437.48 301.23 345.77 1762.00 3.69 10404.71 1.82 10335.50 0.79 71.47 1203.57 405.00 26.56 17334.00 322.76 30756 46546 9836 301.93 87.17 162.05 263.13 31.69 204.67 547.97 196.44 373.71 3126.48 247.83 347.93 433.81 0.18867 648.36 790.77 4.24 566.70 303198573.97 2842.38 322.20 495.37 2466.66 3.66 13841.25 1.64 14203.87 0.74 72.96 1578.29 528.89 36.39 8528.70 206.88 18441 30097 6150 204.71 49.94 83.56 176.49 31.64 105.60 268.32 103.89 220.99 999.75 131.54 198.03 251.07 0.19440 376.73 446.23 7.75 395.70 267086274.53 1969.50 284.43 322.67 1516.96 3.67 7161.48 1.93 7198.64 0.75 69.41 976.78 368.96 18.77 7715.42 141.35 10259 16925 4170 138.21 35.41 73.12 130.15 38.70 92.03 242.63 90.34 147.04 753.69 114.03 153.34 205.85 0.22269 294.36 333.03 7.88 205.27 220447755.87 1371.21 182.70 190.03 1009.26 3.97 2076.93 2.93 6770.97 1.17 64.68 525.89 197.26 11.70 10952.77 222.88 19916 29164 6590 242.75 58.47 105.54 189.28 31.65 133.20 345.81 129.58 268.33 1879.99 164.05 238.73 305.76 0.19307 441.24 548.83 6.22 395.70 280162469.67 2292.38 289.20 331.50 1663.87 3.71 9660.92 1.90 8883.90 0.80 70.96 1100.00 368.47 24.07 7320.73 164.52 13754 21683 4833 183.41 41.11 71.07 154.19 31.11 89.55 231.44 88.04 193.75 704.69 110.93 167.87 220.44 0.20250 319.25 389.40 8.90 296.20 251925176.90 1694.07 237.77 241.20 1232.47 3.73 5269.01 2.22 5329.07 0.83 67.92 818.44 275.86 16.04 4788.92 91.44 7086 12245 2648 102.61 23.16 44.37 91.07 34.69 56.07 149.58 54.78 97.83 262.41 69.31 104.44 130.64 0.31789 196.00 224.89 11.93 153.50 182188318.67 908.43 137.20 144.57 726.30 4.07 1267.89 3.65 4199.71 1.28 58.67 326.68 146.62 7.26 9407.75 147.98 8716 13788 3807 155.22 40.38 83.83 143.53 34.87 106.09 297.94 101.00 173.79 1146.75 128.05 184.80 240.62 0.20978 337.47 399.00 6.49 228.80 237914974.40 1544.50 205.93 214.67 1123.85 3.94 2430.74 2.72 8314.29 1.09 66.67 614.69 222.09 14.25 13230.77 212.04 13721 21689 5649 198.25 56.64 115.03 191.31 35.91 145.42 414.96 138.68 228.68 1886.30 175.37 257.55 333.54 0.19669 496.24 523.98 4.96 337.53 262248899.33 2162.58 283.20 340.27 1672.73 3.92 3301.89 2.29 11720.57 1.05 69.09 982.23 328.90 19.72 5893.41 132.28 11003 16147 3805 139.81 34.12 58.03 114.58 30.67 73.18 185.12 73.35 161.33 420.04 92.45 140.05 172.68 0.23185 259.43 315.83 10.82 250.23 239300837.60 1394.05 208.50 208.67 1002.00 4.02 4775.45 2.92 4793.66 1.15 66.06 665.66 234.67 12.98 5052.73 109.70 8914 13246 3048 102.86 24.24 43.63 92.92 47.38 55.70 159.68 53.49 101.92 280.99 68.95 105.64 142.14 0.33110 203.91 231.66 11.69 164.50 181882709.77 973.39 143.40 151.50 759.43 5.74 1312.06 3.92 4476.69 3.10 59.21 458.35 164.25 7.49 5329.84 118.49 9794 15162 3733 126.64 28.99 52.52 102.83 30.97 66.24 168.44 67.24 137.66 335.86 84.83 116.90 156.50 0.25031 228.14 287.68 11.87 162.90 230919642.13 1160.52 145.37 148.87 814.65 4.01 4657.79 3.35 4610.01 1.18 65.10 452.89 157.60 11.87 7115.39 132.86 9983 17290 3870 140.29 33.07 63.56 127.02 35.10 80.27 223.91 76.89 141.55 642.12 97.32 147.17 196.01 0.23957 276.89 315.37 8.26 205.27 216942144.93 1288.94 182.00 190.90 987.69 3.92 1685.05 2.89 6269.49 1.11 63.86 478.54 196.47 10.61 4362.31 95.60 7985 11732 2730 91.53 21.42 39.34 79.71 45.48 49.76 137.47 47.70 88.16 207.84 60.32 94.72 116.05 0.36368 181.87 204.32 12.99 142.10 169258044.90 841.48 124.77 132.60 671.49 5.78 1140.29 4.42 3888.16 3.16 56.95 411.29 143.48 6.50 16656.20 309.04 28631 42974 9215 301.89 84.97 154.20 254.45 31.05 194.83 521.90 186.19 363.16 3032.10 234.65 343.49 424.07 0.18909 634.09 758.21 4.39 544.33 299834728.80 2750.57 324.40 441.23 2335.46 3.66 13609.33 1.64 13532.74 0.75 72.71 1485.73 506.33 34.91 OpenBenchmarking.org
SHOC Scalable HeterOgeneous Computing The CUDA and OpenCL version of Vetter's Scalable HeterOgeneous Computing benchmark suite. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org GFLOPS, More Is Better SHOC Scalable HeterOgeneous Computing 2015-11-10 Target: OpenCL - Benchmark: Max SP Flops RTX 2070 SUPER RTX 2060 SUPER GTX 980 Ti RTX 2080 SUPER TITAN RTX RTX 2070 GTX 1070 Ti RTX 2080 RTX 2060 GTX 1060 GTX 1080 GTX 1080 Ti GTX 1660 Ti GTX 980 GTX 1660 GTX 1070 GTX 970 RTX 2080 Ti 4K 8K 12K 16K 20K SE +/- 51.02, N = 3 SE +/- 27.40, N = 3 SE +/- 11.70, N = 3 SE +/- 61.30, N = 3 SE +/- 91.95, N = 3 SE +/- 45.97, N = 3 SE +/- 0.84, N = 3 SE +/- 29.32, N = 3 SE +/- 19.13, N = 3 SE +/- 6.34, N = 3 SE +/- 3.00, N = 3 SE +/- 3.93, N = 3 SE +/- 0.04, N = 3 SE +/- 3.92, N = 3 SE +/- 13.79, N = 3 SE +/- 1.89, N = 3 SE +/- 0.74, N = 3 SE +/- 87.95, N = 3 9869.34 8378.87 6213.97 12015.50 17334.00 8528.70 7715.42 10952.77 7320.73 4788.92 9407.75 13230.77 5893.41 5052.73 5329.84 7115.39 4362.31 16656.20 1. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -lmpi_cxx -lmpi Result Confidence
OpenBenchmarking.org GFLOPS, More Is Better SHOC Scalable HeterOgeneous Computing 2015-11-10 Target: OpenCL - Benchmark: Max SP Flops RTX 2070 SUPER RTX 2060 SUPER GTX 980 Ti RTX 2080 SUPER TITAN RTX RTX 2070 GTX 1070 Ti RTX 2080 RTX 2060 GTX 1060 GTX 1080 GTX 1080 Ti GTX 1660 Ti GTX 980 GTX 1660 GTX 1070 GTX 970 RTX 2080 Ti 3K 6K 9K 12K 15K Min: 9818.31 / Avg: 9869.34 / Max: 9971.38 Min: 8351.43 / Avg: 8378.87 / Max: 8433.66 Min: 6201.96 / Avg: 6213.97 / Max: 6237.37 Min: 11954.1 / Avg: 12015.5 / Max: 12138.1 Min: 17242 / Avg: 17334 / Max: 17517.9 Min: 8482.71 / Avg: 8528.7 / Max: 8620.63 Min: 7713.79 / Avg: 7715.42 / Max: 7716.58 Min: 10923.4 / Avg: 10952.77 / Max: 11011.4 Min: 7301.6 / Avg: 7320.73 / Max: 7358.98 Min: 4776.25 / Avg: 4788.92 / Max: 4795.3 Min: 9404.45 / Avg: 9407.75 / Max: 9413.75 Min: 13226.2 / Avg: 13230.77 / Max: 13238.6 Min: 5893.36 / Avg: 5893.41 / Max: 5893.5 Min: 5047.71 / Avg: 5052.73 / Max: 5060.46 Min: 5315.74 / Avg: 5329.84 / Max: 5357.41 Min: 7112.49 / Avg: 7115.39 / Max: 7118.95 Min: 4361.4 / Avg: 4362.31 / Max: 4363.77 Min: 16568 / Avg: 16656.2 / Max: 16832.1 1. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -lmpi_cxx -lmpi
OctaneBench OctaneBench is a test of the OctaneRender on the GPU and requires the use of NVIDIA CUDA. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Score, More Is Better OctaneBench 4.00c Total Score RTX 2070 SUPER RTX 2060 SUPER GTX 980 Ti RTX 2080 SUPER TITAN RTX RTX 2070 GTX 1070 Ti RTX 2080 RTX 2060 GTX 1060 GTX 1080 GTX 1080 Ti GTX 1660 Ti GTX 980 GTX 1660 GTX 1070 GTX 970 RTX 2080 Ti 70 140 210 280 350 220.76 205.23 142.20 233.56 322.76 206.88 141.35 222.88 164.52 91.44 147.98 212.04 132.28 109.70 118.49 132.86 95.60 309.04
LuxMark LuxMark is a multi-platform OpenGL benchmark using LuxRender. LuxMark supports targeting different OpenCL devices and has multiple scenes available for rendering. LuxMark is a fully open-source OpenCL program with real-world rendering examples. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Score, More Is Better LuxMark 3.1 OpenCL Device: GPU - Scene: Microphone RTX 2070 SUPER RTX 2060 SUPER GTX 980 Ti RTX 2080 SUPER TITAN RTX RTX 2070 GTX 1070 Ti RTX 2080 RTX 2060 GTX 1060 GTX 1080 GTX 1080 Ti GTX 1660 Ti GTX 980 GTX 1660 GTX 1070 GTX 970 RTX 2080 Ti 7K 14K 21K 28K 35K SE +/- 16.84, N = 3 SE +/- 43.34, N = 3 SE +/- 49.74, N = 3 SE +/- 108.17, N = 3 SE +/- 168.12, N = 3 SE +/- 26.44, N = 3 SE +/- 15.50, N = 3 SE +/- 11.68, N = 3 SE +/- 3.84, N = 3 SE +/- 1.53, N = 3 SE +/- 1.20, N = 3 SE +/- 19.33, N = 3 SE +/- 2.33, N = 3 SE +/- 18.25, N = 3 SE +/- 1.33, N = 3 SE +/- 4.91, N = 3 SE +/- 2.00, N = 3 SE +/- 21.50, N = 3 20499 18509 11096 20164 30756 18441 10259 19916 13754 7086 8716 13721 11003 8914 9794 9983 7985 28631 Result Confidence
OpenBenchmarking.org Score, More Is Better LuxMark 3.1 OpenCL Device: GPU - Scene: Microphone RTX 2070 SUPER RTX 2060 SUPER GTX 980 Ti RTX 2080 SUPER TITAN RTX RTX 2070 GTX 1070 Ti RTX 2080 RTX 2060 GTX 1060 GTX 1080 GTX 1080 Ti GTX 1660 Ti GTX 980 GTX 1660 GTX 1070 GTX 970 RTX 2080 Ti 5K 10K 15K 20K 25K Min: 20465 / Avg: 20498.67 / Max: 20516 Min: 18444 / Avg: 18508.67 / Max: 18591 Min: 11036 / Avg: 11096.33 / Max: 11195 Min: 19948 / Avg: 20164.33 / Max: 20273 Min: 30577 / Avg: 30756 / Max: 31092 Min: 18404 / Avg: 18440.67 / Max: 18492 Min: 10228 / Avg: 10259 / Max: 10275 Min: 19901 / Avg: 19916 / Max: 19939 Min: 13750 / Avg: 13754.33 / Max: 13762 Min: 7084 / Avg: 7086 / Max: 7089 Min: 8714 / Avg: 8715.67 / Max: 8718 Min: 13702 / Avg: 13721.33 / Max: 13760 Min: 11001 / Avg: 11003.33 / Max: 11008 Min: 8881 / Avg: 8914 / Max: 8944 Min: 9793 / Avg: 9794.33 / Max: 9797 Min: 9973 / Avg: 9982.67 / Max: 9989 Min: 7983 / Avg: 7985 / Max: 7989 Min: 28609 / Avg: 28631 / Max: 28674
Result
OpenBenchmarking.org Score, More Is Better LuxMark 3.1 OpenCL Device: GPU - Scene: Luxball HDR RTX 2070 SUPER RTX 2060 SUPER GTX 980 Ti RTX 2080 SUPER TITAN RTX RTX 2070 GTX 1070 Ti RTX 2080 RTX 2060 GTX 1060 GTX 1080 GTX 1080 Ti GTX 1660 Ti GTX 980 GTX 1660 GTX 1070 GTX 970 RTX 2080 Ti 10K 20K 30K 40K 50K SE +/- 98.93, N = 3 SE +/- 4.93, N = 3 SE +/- 39.15, N = 3 SE +/- 0.88, N = 3 SE +/- 20.92, N = 3 SE +/- 7.54, N = 3 SE +/- 36.50, N = 3 SE +/- 7.51, N = 3 SE +/- 0.67, N = 3 SE +/- 4.00, N = 3 SE +/- 17.98, N = 3 SE +/- 7.67, N = 3 SE +/- 19.86, N = 3 SE +/- 26.16, N = 3 SE +/- 35.04, N = 3 SE +/- 1.00, N = 3 SE +/- 6.23, N = 3 SE +/- 166.33, N = 3 29734 30093 16871 30179 46546 30097 16925 29164 21683 12245 13788 21689 16147 13246 15162 17290 11732 42974 Result Confidence
OpenBenchmarking.org Score, More Is Better LuxMark 3.1 OpenCL Device: GPU - Scene: Luxball HDR RTX 2070 SUPER RTX 2060 SUPER GTX 980 Ti RTX 2080 SUPER TITAN RTX RTX 2070 GTX 1070 Ti RTX 2080 RTX 2060 GTX 1060 GTX 1080 GTX 1080 Ti GTX 1660 Ti GTX 980 GTX 1660 GTX 1070 GTX 970 RTX 2080 Ti 8K 16K 24K 32K 40K Min: 29554 / Avg: 29734.33 / Max: 29895 Min: 30084 / Avg: 30093 / Max: 30101 Min: 16814 / Avg: 16871 / Max: 16946 Min: 30178 / Avg: 30179.33 / Max: 30181 Min: 46506 / Avg: 46545.67 / Max: 46577 Min: 30087 / Avg: 30097.33 / Max: 30112 Min: 16888 / Avg: 16925 / Max: 16998 Min: 29156 / Avg: 29164 / Max: 29179 Min: 21682 / Avg: 21682.67 / Max: 21684 Min: 12241 / Avg: 12245 / Max: 12253 Min: 13759 / Avg: 13788.33 / Max: 13821 Min: 21681 / Avg: 21688.67 / Max: 21704 Min: 16109 / Avg: 16147 / Max: 16176 Min: 13215 / Avg: 13246 / Max: 13298 Min: 15094 / Avg: 15162.33 / Max: 15210 Min: 17289 / Avg: 17290 / Max: 17292 Min: 11724 / Avg: 11731.67 / Max: 11744 Min: 42708 / Avg: 42974 / Max: 43280
Result
OpenBenchmarking.org Score, More Is Better LuxMark 3.1 OpenCL Device: GPU - Scene: Hotel RTX 2070 SUPER RTX 2060 SUPER GTX 980 Ti RTX 2080 SUPER TITAN RTX RTX 2070 GTX 1070 Ti RTX 2080 RTX 2060 GTX 1060 GTX 1080 GTX 1080 Ti GTX 1660 Ti GTX 980 GTX 1660 GTX 1070 GTX 970 RTX 2080 Ti 2K 4K 6K 8K 10K SE +/- 0.67, N = 3 SE +/- 8.00, N = 3 SE +/- 0.58, N = 3 SE +/- 1.73, N = 3 SE +/- 1.86, N = 3 SE +/- 3.51, N = 3 SE +/- 0.88, N = 3 SE +/- 0.67, N = 3 SE +/- 3.76, N = 3 SE +/- 0.67, N = 3 SE +/- 7.09, N = 3 SE +/- 2.73, N = 3 SE +/- 0.58, N = 3 SE +/- 1.20, N = 3 SE +/- 1.86, N = 3 SE +/- 4.37, N = 3 6565 6148 3885 6839 9836 6150 4170 6590 4833 2648 3807 5649 3805 3048 3733 3870 2730 9215 Result Confidence
OpenBenchmarking.org Score, More Is Better LuxMark 3.1 OpenCL Device: GPU - Scene: Hotel RTX 2070 SUPER RTX 2060 SUPER GTX 980 Ti RTX 2080 SUPER TITAN RTX RTX 2070 GTX 1070 Ti RTX 2080 RTX 2060 GTX 1060 GTX 1080 GTX 1080 Ti GTX 1660 Ti GTX 980 GTX 1660 GTX 1070 GTX 970 RTX 2080 Ti 2K 4K 6K 8K 10K Min: 6147 / Avg: 6148.33 / Max: 6149 Min: 3869 / Avg: 3885 / Max: 3893 Min: 6838 / Avg: 6839 / Max: 6840 Min: 9833 / Avg: 9836 / Max: 9839 Min: 6148 / Avg: 6150.33 / Max: 6154 Min: 4166 / Avg: 4170 / Max: 4177 Min: 6588 / Avg: 6589.67 / Max: 6591 Min: 4832 / Avg: 4832.67 / Max: 4834 Min: 2642 / Avg: 2648.33 / Max: 2655 Min: 3806 / Avg: 3806.67 / Max: 3808 Min: 5640 / Avg: 5649 / Max: 5663 Min: 3043 / Avg: 3048.33 / Max: 3052 Min: 3732 / Avg: 3733 / Max: 3734 Min: 3868 / Avg: 3869.67 / Max: 3872 Min: 2728 / Avg: 2730.33 / Max: 2734 Min: 9206 / Avg: 9214.67 / Max: 9220
FAHBench FAHBench is a Folding@Home benchmark on the GPU. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Ns Per Day, More Is Better FAHBench 2.3.2 RTX 2070 SUPER RTX 2060 SUPER GTX 980 Ti RTX 2080 SUPER TITAN RTX RTX 2070 GTX 1070 Ti RTX 2080 RTX 2060 GTX 1060 GTX 1080 GTX 1080 Ti GTX 1660 Ti GTX 980 GTX 1660 GTX 1070 GTX 970 RTX 2080 Ti 70 140 210 280 350 SE +/- 0.60, N = 3 SE +/- 0.34, N = 3 SE +/- 0.04, N = 3 SE +/- 0.78, N = 3 SE +/- 0.71, N = 3 SE +/- 0.64, N = 3 SE +/- 0.05, N = 3 SE +/- 0.99, N = 3 SE +/- 0.61, N = 3 SE +/- 0.17, N = 3 SE +/- 0.53, N = 3 SE +/- 0.43, N = 3 SE +/- 0.15, N = 3 SE +/- 0.08, N = 3 SE +/- 0.27, N = 3 SE +/- 0.43, N = 3 SE +/- 0.03, N = 3 SE +/- 0.90, N = 3 229.12 205.20 116.02 256.83 301.93 204.71 138.21 242.75 183.41 102.61 155.22 198.25 139.81 102.86 126.64 140.29 91.53 301.89 Result Confidence
OpenBenchmarking.org Ns Per Day, More Is Better FAHBench 2.3.2 RTX 2070 SUPER RTX 2060 SUPER GTX 980 Ti RTX 2080 SUPER TITAN RTX RTX 2070 GTX 1070 Ti RTX 2080 RTX 2060 GTX 1060 GTX 1080 GTX 1080 Ti GTX 1660 Ti GTX 980 GTX 1660 GTX 1070 GTX 970 RTX 2080 Ti 50 100 150 200 250 Min: 228.15 / Avg: 229.12 / Max: 230.21 Min: 204.54 / Avg: 205.2 / Max: 205.66 Min: 115.97 / Avg: 116.02 / Max: 116.09 Min: 256 / Avg: 256.83 / Max: 258.38 Min: 300.74 / Avg: 301.93 / Max: 303.21 Min: 203.78 / Avg: 204.71 / Max: 205.93 Min: 138.13 / Avg: 138.21 / Max: 138.28 Min: 241.66 / Avg: 242.75 / Max: 244.73 Min: 182.65 / Avg: 183.41 / Max: 184.63 Min: 102.39 / Avg: 102.61 / Max: 102.95 Min: 154.52 / Avg: 155.22 / Max: 156.25 Min: 197.72 / Avg: 198.25 / Max: 199.09 Min: 139.61 / Avg: 139.81 / Max: 140.1 Min: 102.74 / Avg: 102.86 / Max: 103.02 Min: 126.29 / Avg: 126.64 / Max: 127.17 Min: 139.79 / Avg: 140.29 / Max: 141.15 Min: 91.49 / Avg: 91.53 / Max: 91.59 Min: 300.8 / Avg: 301.89 / Max: 303.68
PlaidML This test profile uses PlaidML deep learning framework developed by Intel for offering up various benchmarks. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org FPS, More Is Better PlaidML FP16: Yes - Mode: Inference - Network: NASNer Large - Device: OpenCL RTX 2070 SUPER RTX 2060 SUPER GTX 980 Ti RTX 2080 SUPER TITAN RTX RTX 2070 GTX 1070 Ti RTX 2080 RTX 2060 GTX 1060 GTX 1080 GTX 1080 Ti GTX 1660 Ti GTX 980 GTX 1660 GTX 1070 GTX 970 RTX 2080 Ti 20 40 60 80 100 SE +/- 0.05, N = 3 SE +/- 0.14, N = 3 SE +/- 0.10, N = 3 SE +/- 0.08, N = 3 SE +/- 0.25, N = 3 SE +/- 0.13, N = 3 SE +/- 0.02, N = 3 SE +/- 0.15, N = 3 SE +/- 0.08, N = 3 SE +/- 0.03, N = 3 SE +/- 0.08, N = 3 SE +/- 0.11, N = 3 SE +/- 0.03, N = 3 SE +/- 0.15, N = 3 SE +/- 0.03, N = 3 SE +/- 0.05, N = 3 SE +/- 0.03, N = 3 SE +/- 0.21, N = 3 55.24 48.96 30.64 64.80 87.17 49.94 35.41 58.47 41.11 23.16 40.38 56.64 34.12 24.24 28.99 33.07 21.42 84.97 Result Confidence
OpenBenchmarking.org FPS, More Is Better PlaidML FP16: Yes - Mode: Inference - Network: NASNer Large - Device: OpenCL RTX 2070 SUPER RTX 2060 SUPER GTX 980 Ti RTX 2080 SUPER TITAN RTX RTX 2070 GTX 1070 Ti RTX 2080 RTX 2060 GTX 1060 GTX 1080 GTX 1080 Ti GTX 1660 Ti GTX 980 GTX 1660 GTX 1070 GTX 970 RTX 2080 Ti 20 40 60 80 100 Min: 55.17 / Avg: 55.24 / Max: 55.33 Min: 48.73 / Avg: 48.96 / Max: 49.22 Min: 30.54 / Avg: 30.64 / Max: 30.84 Min: 64.64 / Avg: 64.8 / Max: 64.88 Min: 86.77 / Avg: 87.17 / Max: 87.63 Min: 49.78 / Avg: 49.94 / Max: 50.19 Min: 35.38 / Avg: 35.41 / Max: 35.46 Min: 58.27 / Avg: 58.47 / Max: 58.77 Min: 41.01 / Avg: 41.11 / Max: 41.26 Min: 23.12 / Avg: 23.16 / Max: 23.23 Min: 40.24 / Avg: 40.38 / Max: 40.52 Min: 56.5 / Avg: 56.64 / Max: 56.87 Min: 34.07 / Avg: 34.12 / Max: 34.18 Min: 24.05 / Avg: 24.24 / Max: 24.53 Min: 28.95 / Avg: 28.99 / Max: 29.05 Min: 32.99 / Avg: 33.07 / Max: 33.17 Min: 21.38 / Avg: 21.42 / Max: 21.48 Min: 84.64 / Avg: 84.97 / Max: 85.36
Result
OpenBenchmarking.org FPS, More Is Better PlaidML FP16: Yes - Mode: Inference - Network: VGG19 - Device: OpenCL RTX 2070 SUPER RTX 2060 SUPER GTX 980 Ti RTX 2080 SUPER TITAN RTX RTX 2070 GTX 1070 Ti RTX 2080 RTX 2060 GTX 1060 GTX 1080 GTX 1080 Ti GTX 1660 Ti GTX 980 GTX 1660 GTX 1070 GTX 970 RTX 2080 Ti 40 80 120 160 200 SE +/- 0.16, N = 3 SE +/- 0.23, N = 3 SE +/- 0.77, N = 3 SE +/- 0.21, N = 3 SE +/- 0.48, N = 3 SE +/- 0.35, N = 3 SE +/- 0.03, N = 3 SE +/- 0.44, N = 3 SE +/- 0.19, N = 3 SE +/- 0.12, N = 3 SE +/- 0.28, N = 3 SE +/- 0.44, N = 3 SE +/- 0.12, N = 3 SE +/- 0.62, N = 4 SE +/- 0.08, N = 3 SE +/- 0.19, N = 3 SE +/- 0.18, N = 3 SE +/- 0.36, N = 3 97.82 80.82 56.13 115.44 162.05 83.56 73.12 105.54 71.07 44.37 83.83 115.03 58.03 43.63 52.52 63.56 39.34 154.20 Result Confidence
OpenBenchmarking.org FPS, More Is Better PlaidML FP16: Yes - Mode: Inference - Network: VGG19 - Device: OpenCL RTX 2070 SUPER RTX 2060 SUPER GTX 980 Ti RTX 2080 SUPER TITAN RTX RTX 2070 GTX 1070 Ti RTX 2080 RTX 2060 GTX 1060 GTX 1080 GTX 1080 Ti GTX 1660 Ti GTX 980 GTX 1660 GTX 1070 GTX 970 RTX 2080 Ti 30 60 90 120 150 Min: 97.51 / Avg: 97.82 / Max: 98.02 Min: 80.49 / Avg: 80.82 / Max: 81.26 Min: 55.19 / Avg: 56.13 / Max: 57.65 Min: 115.07 / Avg: 115.44 / Max: 115.8 Min: 161.31 / Avg: 162.05 / Max: 162.94 Min: 82.97 / Avg: 83.56 / Max: 84.19 Min: 73.08 / Avg: 73.12 / Max: 73.18 Min: 104.87 / Avg: 105.54 / Max: 106.37 Min: 70.82 / Avg: 71.07 / Max: 71.44 Min: 44.21 / Avg: 44.37 / Max: 44.6 Min: 83.37 / Avg: 83.83 / Max: 84.34 Min: 114.45 / Avg: 115.03 / Max: 115.89 Min: 57.88 / Avg: 58.03 / Max: 58.26 Min: 42.84 / Avg: 43.63 / Max: 45.49 Min: 52.4 / Avg: 52.52 / Max: 52.67 Min: 63.33 / Avg: 63.56 / Max: 63.94 Min: 39.15 / Avg: 39.34 / Max: 39.7 Min: 153.63 / Avg: 154.2 / Max: 154.86
Result
OpenBenchmarking.org FPS, More Is Better PlaidML FP16: Yes - Mode: Inference - Network: DenseNet 201 - Device: OpenCL RTX 2070 SUPER RTX 2060 SUPER GTX 980 Ti RTX 2080 SUPER TITAN RTX RTX 2070 GTX 1070 Ti RTX 2080 RTX 2060 GTX 1060 GTX 1080 GTX 1080 Ti GTX 1660 Ti GTX 980 GTX 1660 GTX 1070 GTX 970 RTX 2080 Ti 60 120 180 240 300 SE +/- 0.14, N = 3 SE +/- 0.03, N = 3 SE +/- 0.18, N = 3 SE +/- 0.07, N = 3 SE +/- 0.18, N = 3 SE +/- 0.22, N = 3 SE +/- 0.01, N = 3 SE +/- 0.17, N = 3 SE +/- 0.05, N = 3 SE +/- 0.15, N = 3 SE +/- 0.01, N = 3 SE +/- 0.03, N = 3 SE +/- 0.03, N = 3 SE +/- 0.12, N = 3 SE +/- 0.10, N = 3 SE +/- 0.05, N = 3 SE +/- 0.01, N = 3 SE +/- 0.10, N = 3 190.01 179.51 111.46 200.38 263.13 176.49 130.15 189.28 154.19 91.07 143.53 191.31 114.58 92.92 102.83 127.02 79.71 254.45 Result Confidence
OpenBenchmarking.org FPS, More Is Better PlaidML FP16: Yes - Mode: Inference - Network: DenseNet 201 - Device: OpenCL RTX 2070 SUPER RTX 2060 SUPER GTX 980 Ti RTX 2080 SUPER TITAN RTX RTX 2070 GTX 1070 Ti RTX 2080 RTX 2060 GTX 1060 GTX 1080 GTX 1080 Ti GTX 1660 Ti GTX 980 GTX 1660 GTX 1070 GTX 970 RTX 2080 Ti 50 100 150 200 250 Min: 189.74 / Avg: 190.01 / Max: 190.2 Min: 179.46 / Avg: 179.51 / Max: 179.56 Min: 111.2 / Avg: 111.46 / Max: 111.81 Min: 200.26 / Avg: 200.38 / Max: 200.51 Min: 262.77 / Avg: 263.13 / Max: 263.32 Min: 176.16 / Avg: 176.49 / Max: 176.91 Min: 130.13 / Avg: 130.15 / Max: 130.17 Min: 189.08 / Avg: 189.28 / Max: 189.62 Min: 154.1 / Avg: 154.19 / Max: 154.26 Min: 90.78 / Avg: 91.07 / Max: 91.23 Min: 143.51 / Avg: 143.53 / Max: 143.55 Min: 191.25 / Avg: 191.31 / Max: 191.34 Min: 114.52 / Avg: 114.58 / Max: 114.63 Min: 92.68 / Avg: 92.92 / Max: 93.05 Min: 102.69 / Avg: 102.83 / Max: 103.01 Min: 126.92 / Avg: 127.02 / Max: 127.07 Min: 79.69 / Avg: 79.71 / Max: 79.72 Min: 254.29 / Avg: 254.45 / Max: 254.63
Rodinia Rodinia is a suite focused upon accelerating compute-intensive applications with accelerators. CUDA, OpenMP, and OpenCL parallel models are supported by the included applications. This profile utilizes the OpenCL and OpenMP test binaries at the moment. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Seconds, Fewer Is Better Rodinia 2.4 Test: OpenCL Myocyte RTX 2070 SUPER RTX 2060 SUPER GTX 980 Ti RTX 2080 SUPER TITAN RTX RTX 2070 GTX 1070 Ti RTX 2080 RTX 2060 GTX 1060 GTX 1080 GTX 1080 Ti GTX 1660 Ti GTX 980 GTX 1660 GTX 1070 GTX 970 RTX 2080 Ti 12 24 36 48 60 SE +/- 0.15, N = 3 SE +/- 0.04, N = 3 SE +/- 0.18, N = 3 SE +/- 0.04, N = 3 SE +/- 0.04, N = 3 SE +/- 0.03, N = 3 SE +/- 0.14, N = 3 SE +/- 0.04, N = 3 SE +/- 0.05, N = 3 SE +/- 0.10, N = 3 SE +/- 0.04, N = 3 SE +/- 0.03, N = 3 SE +/- 0.05, N = 3 SE +/- 0.05, N = 3 SE +/- 0.08, N = 3 SE +/- 0.08, N = 3 SE +/- 0.06, N = 3 SE +/- 0.07, N = 3 30.76 30.42 52.13 30.63 31.69 31.64 38.70 31.65 31.11 34.69 34.87 35.91 30.67 47.38 30.97 35.10 45.48 31.05 1. (CXX) g++ options: -O2 -lOpenCL Result Confidence
OpenBenchmarking.org Seconds, Fewer Is Better Rodinia 2.4 Test: OpenCL Myocyte RTX 2070 SUPER RTX 2060 SUPER GTX 980 Ti RTX 2080 SUPER TITAN RTX RTX 2070 GTX 1070 Ti RTX 2080 RTX 2060 GTX 1060 GTX 1080 GTX 1080 Ti GTX 1660 Ti GTX 980 GTX 1660 GTX 1070 GTX 970 RTX 2080 Ti 10 20 30 40 50 Min: 30.56 / Avg: 30.76 / Max: 31.04 Min: 30.35 / Avg: 30.42 / Max: 30.47 Min: 51.87 / Avg: 52.13 / Max: 52.48 Min: 30.55 / Avg: 30.63 / Max: 30.67 Min: 31.62 / Avg: 31.69 / Max: 31.76 Min: 31.58 / Avg: 31.64 / Max: 31.7 Min: 38.49 / Avg: 38.7 / Max: 38.98 Min: 31.59 / Avg: 31.65 / Max: 31.72 Min: 31.01 / Avg: 31.11 / Max: 31.18 Min: 34.6 / Avg: 34.69 / Max: 34.89 Min: 34.79 / Avg: 34.87 / Max: 34.92 Min: 35.85 / Avg: 35.91 / Max: 35.95 Min: 30.62 / Avg: 30.67 / Max: 30.77 Min: 47.29 / Avg: 47.38 / Max: 47.44 Min: 30.86 / Avg: 30.97 / Max: 31.13 Min: 35 / Avg: 35.1 / Max: 35.25 Min: 45.37 / Avg: 45.48 / Max: 45.58 Min: 30.93 / Avg: 31.05 / Max: 31.18 1. (CXX) g++ options: -O2 -lOpenCL
PlaidML This test profile uses PlaidML deep learning framework developed by Intel for offering up various benchmarks. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org FPS, More Is Better PlaidML FP16: Yes - Mode: Inference - Network: VGG16 - Device: OpenCL RTX 2070 SUPER RTX 2060 SUPER GTX 980 Ti RTX 2080 SUPER TITAN RTX RTX 2070 GTX 1070 Ti RTX 2080 RTX 2060 GTX 1060 GTX 1080 GTX 1080 Ti GTX 1660 Ti GTX 980 GTX 1660 GTX 1070 GTX 970 RTX 2080 Ti 40 80 120 160 200 SE +/- 0.28, N = 3 SE +/- 0.35, N = 3 SE +/- 1.12, N = 3 SE +/- 0.29, N = 3 SE +/- 0.57, N = 3 SE +/- 0.39, N = 3 SE +/- 0.08, N = 3 SE +/- 0.57, N = 3 SE +/- 0.23, N = 3 SE +/- 0.18, N = 3 SE +/- 0.40, N = 3 SE +/- 0.62, N = 3 SE +/- 0.14, N = 3 SE +/- 0.83, N = 4 SE +/- 0.17, N = 3 SE +/- 0.30, N = 3 SE +/- 0.21, N = 3 SE +/- 0.51, N = 3 123.20 102.58 71.26 145.65 204.67 105.60 92.03 133.20 89.55 56.07 106.09 145.42 73.18 55.70 66.24 80.27 49.76 194.83 Result Confidence
OpenBenchmarking.org FPS, More Is Better PlaidML FP16: Yes - Mode: Inference - Network: VGG16 - Device: OpenCL RTX 2070 SUPER RTX 2060 SUPER GTX 980 Ti RTX 2080 SUPER TITAN RTX RTX 2070 GTX 1070 Ti RTX 2080 RTX 2060 GTX 1060 GTX 1080 GTX 1080 Ti GTX 1660 Ti GTX 980 GTX 1660 GTX 1070 GTX 970 RTX 2080 Ti 40 80 120 160 200 Min: 122.7 / Avg: 123.2 / Max: 123.67 Min: 102.1 / Avg: 102.58 / Max: 103.26 Min: 69.37 / Avg: 71.26 / Max: 73.24 Min: 145.22 / Avg: 145.65 / Max: 146.21 Min: 203.85 / Avg: 204.67 / Max: 205.76 Min: 105.06 / Avg: 105.6 / Max: 106.36 Min: 91.93 / Avg: 92.03 / Max: 92.19 Min: 132.33 / Avg: 133.2 / Max: 134.28 Min: 89.19 / Avg: 89.55 / Max: 89.98 Min: 55.8 / Avg: 56.07 / Max: 56.41 Min: 105.5 / Avg: 106.09 / Max: 106.86 Min: 144.46 / Avg: 145.42 / Max: 146.59 Min: 72.93 / Avg: 73.18 / Max: 73.43 Min: 54.49 / Avg: 55.7 / Max: 58.05 Min: 66.03 / Avg: 66.24 / Max: 66.58 Min: 79.81 / Avg: 80.27 / Max: 80.83 Min: 49.35 / Avg: 49.76 / Max: 50 Min: 194.12 / Avg: 194.83 / Max: 195.83
clpeak Clpeak is designed to test the peak capabilities of OpenCL devices. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org GFLOPS, More Is Better clpeak OpenCL Test: Double-Precision Double RTX 2070 SUPER RTX 2060 SUPER GTX 980 Ti RTX 2080 SUPER TITAN RTX RTX 2070 GTX 1070 Ti RTX 2080 RTX 2060 GTX 1060 GTX 1080 GTX 1080 Ti GTX 1660 Ti GTX 980 GTX 1660 GTX 1070 GTX 970 RTX 2080 Ti 120 240 360 480 600 SE +/- 0.77, N = 3 SE +/- 0.71, N = 3 SE +/- 0.35, N = 3 SE +/- 0.03, N = 3 SE +/- 1.16, N = 3 SE +/- 0.81, N = 3 SE +/- 0.02, N = 3 SE +/- 0.92, N = 3 SE +/- 0.01, N = 3 SE +/- 0.14, N = 3 SE +/- 0.76, N = 3 SE +/- 1.14, N = 3 SE +/- 0.01, N = 3 SE +/- 0.07, N = 3 SE +/- 0.00, N = 3 SE +/- 0.71, N = 3 SE +/- 0.03, N = 3 SE +/- 1.46, N = 3 310.27 263.11 196.60 378.98 547.97 268.32 242.63 345.81 231.44 149.58 297.94 414.96 185.12 159.68 168.44 223.91 137.47 521.90 1. (CXX) g++ options: -O3 -rdynamic -lOpenCL Result Confidence
OpenBenchmarking.org GFLOPS, More Is Better clpeak OpenCL Test: Double-Precision Double RTX 2070 SUPER RTX 2060 SUPER GTX 980 Ti RTX 2080 SUPER TITAN RTX RTX 2070 GTX 1070 Ti RTX 2080 RTX 2060 GTX 1060 GTX 1080 GTX 1080 Ti GTX 1660 Ti GTX 980 GTX 1660 GTX 1070 GTX 970 RTX 2080 Ti 100 200 300 400 500 Min: 308.73 / Avg: 310.27 / Max: 311.06 Min: 262.4 / Avg: 263.11 / Max: 264.52 Min: 196.17 / Avg: 196.6 / Max: 197.3 Min: 378.93 / Avg: 378.98 / Max: 379.02 Min: 546.71 / Avg: 547.97 / Max: 550.28 Min: 266.7 / Avg: 268.32 / Max: 269.18 Min: 242.6 / Avg: 242.63 / Max: 242.65 Min: 343.96 / Avg: 345.81 / Max: 346.75 Min: 231.43 / Avg: 231.44 / Max: 231.45 Min: 149.42 / Avg: 149.58 / Max: 149.86 Min: 296.99 / Avg: 297.94 / Max: 299.44 Min: 413.44 / Avg: 414.96 / Max: 417.19 Min: 185.1 / Avg: 185.12 / Max: 185.13 Min: 159.57 / Avg: 159.68 / Max: 159.81 Min: 168.44 / Avg: 168.44 / Max: 168.44 Min: 222.79 / Avg: 223.91 / Max: 225.23 Min: 137.43 / Avg: 137.47 / Max: 137.52 Min: 520.32 / Avg: 521.9 / Max: 524.82 1. (CXX) g++ options: -O3 -rdynamic -lOpenCL
PlaidML This test profile uses PlaidML deep learning framework developed by Intel for offering up various benchmarks. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org FPS, More Is Better PlaidML FP16: No - Mode: Inference - Network: VGG19 - Device: OpenCL RTX 2070 SUPER RTX 2060 SUPER GTX 980 Ti RTX 2080 SUPER TITAN RTX RTX 2070 GTX 1070 Ti RTX 2080 RTX 2060 GTX 1060 GTX 1080 GTX 1080 Ti GTX 1660 Ti GTX 980 GTX 1660 GTX 1070 GTX 970 RTX 2080 Ti 40 80 120 160 200 SE +/- 0.23, N = 3 SE +/- 0.19, N = 3 SE +/- 0.65, N = 3 SE +/- 0.22, N = 3 SE +/- 0.54, N = 3 SE +/- 0.25, N = 3 SE +/- 0.06, N = 3 SE +/- 0.42, N = 3 SE +/- 0.17, N = 3 SE +/- 0.08, N = 3 SE +/- 0.16, N = 3 SE +/- 0.35, N = 3 SE +/- 0.12, N = 3 SE +/- 0.47, N = 3 SE +/- 0.17, N = 3 SE +/- 0.11, N = 3 SE +/- 0.01, N = 3 SE +/- 0.41, N = 3 122.32 101.17 68.47 143.02 196.44 103.89 90.34 129.58 88.04 54.78 101.00 138.68 73.35 53.49 67.24 76.89 47.70 186.19 Result Confidence
OpenBenchmarking.org FPS, More Is Better PlaidML FP16: No - Mode: Inference - Network: VGG19 - Device: OpenCL RTX 2070 SUPER RTX 2060 SUPER GTX 980 Ti RTX 2080 SUPER TITAN RTX RTX 2070 GTX 1070 Ti RTX 2080 RTX 2060 GTX 1060 GTX 1080 GTX 1080 Ti GTX 1660 Ti GTX 980 GTX 1660 GTX 1070 GTX 970 RTX 2080 Ti 40 80 120 160 200 Min: 121.92 / Avg: 122.32 / Max: 122.72 Min: 100.84 / Avg: 101.17 / Max: 101.51 Min: 67.58 / Avg: 68.47 / Max: 69.74 Min: 142.65 / Avg: 143.02 / Max: 143.42 Min: 195.58 / Avg: 196.44 / Max: 197.44 Min: 103.47 / Avg: 103.89 / Max: 104.34 Min: 90.27 / Avg: 90.34 / Max: 90.45 Min: 128.93 / Avg: 129.58 / Max: 130.36 Min: 87.77 / Avg: 88.04 / Max: 88.35 Min: 54.68 / Avg: 54.78 / Max: 54.94 Min: 100.78 / Avg: 101 / Max: 101.31 Min: 138.17 / Avg: 138.68 / Max: 139.34 Min: 73.18 / Avg: 73.35 / Max: 73.59 Min: 52.98 / Avg: 53.49 / Max: 54.44 Min: 66.99 / Avg: 67.24 / Max: 67.55 Min: 76.7 / Avg: 76.89 / Max: 77.08 Min: 47.69 / Avg: 47.7 / Max: 47.73 Min: 185.53 / Avg: 186.19 / Max: 186.93
Result
OpenBenchmarking.org FPS, More Is Better PlaidML FP16: Yes - Mode: Inference - Network: Inception V3 - Device: OpenCL RTX 2070 SUPER RTX 2060 SUPER GTX 980 Ti RTX 2080 SUPER TITAN RTX RTX 2070 GTX 1070 Ti RTX 2080 RTX 2060 GTX 1060 GTX 1080 GTX 1080 Ti GTX 1660 Ti GTX 980 GTX 1660 GTX 1070 GTX 970 RTX 2080 Ti 80 160 240 320 400 SE +/- 0.10, N = 3 SE +/- 0.44, N = 3 SE +/- 0.26, N = 3 SE +/- 0.23, N = 3 SE +/- 0.48, N = 3 SE +/- 0.43, N = 3 SE +/- 0.06, N = 3 SE +/- 0.59, N = 3 SE +/- 0.37, N = 3 SE +/- 0.20, N = 3 SE +/- 0.30, N = 3 SE +/- 0.21, N = 3 SE +/- 0.05, N = 3 SE +/- 0.27, N = 3 SE +/- 0.27, N = 3 SE +/- 0.18, N = 3 SE +/- 0.01, N = 3 SE +/- 0.44, N = 3 239.61 219.76 116.31 301.11 373.71 220.99 147.04 268.33 193.75 97.83 173.79 228.68 161.33 101.92 137.66 141.55 88.16 363.16 Result Confidence
OpenBenchmarking.org FPS, More Is Better PlaidML FP16: Yes - Mode: Inference - Network: Inception V3 - Device: OpenCL RTX 2070 SUPER RTX 2060 SUPER GTX 980 Ti RTX 2080 SUPER TITAN RTX RTX 2070 GTX 1070 Ti RTX 2080 RTX 2060 GTX 1060 GTX 1080 GTX 1080 Ti GTX 1660 Ti GTX 980 GTX 1660 GTX 1070 GTX 970 RTX 2080 Ti 70 140 210 280 350 Min: 239.45 / Avg: 239.61 / Max: 239.78 Min: 218.98 / Avg: 219.76 / Max: 220.51 Min: 115.91 / Avg: 116.31 / Max: 116.79 Min: 300.74 / Avg: 301.11 / Max: 301.52 Min: 372.76 / Avg: 373.71 / Max: 374.29 Min: 220.47 / Avg: 220.99 / Max: 221.85 Min: 146.97 / Avg: 147.04 / Max: 147.16 Min: 267.37 / Avg: 268.33 / Max: 269.4 Min: 193.27 / Avg: 193.75 / Max: 194.47 Min: 97.49 / Avg: 97.83 / Max: 98.17 Min: 173.4 / Avg: 173.79 / Max: 174.38 Min: 228.33 / Avg: 228.68 / Max: 229.07 Min: 161.27 / Avg: 161.33 / Max: 161.43 Min: 101.39 / Avg: 101.92 / Max: 102.29 Min: 137.22 / Avg: 137.66 / Max: 138.15 Min: 141.28 / Avg: 141.55 / Max: 141.89 Min: 88.15 / Avg: 88.16 / Max: 88.17 Min: 362.35 / Avg: 363.16 / Max: 363.85
LeelaChessZero LeelaChessZero (lc0 / lczero) is a chess engine automated vian neural networks. This test profile can be used for OpenCL, CUDA + cuDNN, and BLAS (CPU-based) benchmarking. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Nodes Per Second, More Is Better LeelaChessZero 0.22.0 Backend: OpenCL RTX 2070 SUPER RTX 2060 SUPER GTX 980 Ti RTX 2080 SUPER TITAN RTX RTX 2070 GTX 1070 Ti RTX 2080 RTX 2060 GTX 1060 GTX 1080 GTX 1080 Ti GTX 1660 Ti GTX 980 GTX 1660 GTX 1070 GTX 970 RTX 2080 Ti 700 1400 2100 2800 3500 SE +/- 17.64, N = 7 SE +/- 18.12, N = 15 SE +/- 5.67, N = 15 SE +/- 29.82, N = 3 SE +/- 28.21, N = 3 SE +/- 16.93, N = 15 SE +/- 8.69, N = 6 SE +/- 21.60, N = 3 SE +/- 1.84, N = 3 SE +/- 3.68, N = 4 SE +/- 14.70, N = 3 SE +/- 32.29, N = 3 SE +/- 5.83, N = 15 SE +/- 2.79, N = 3 SE +/- 4.05, N = 15 SE +/- 12.32, N = 15 SE +/- 1.93, N = 15 SE +/- 8.77, N = 3 1604.21 998.17 466.84 2105.26 3126.48 999.75 753.69 1879.99 704.69 262.41 1146.75 1886.30 420.04 280.99 335.86 642.12 207.84 3032.10 1. (CXX) g++ options: -lpthread Result Confidence
OpenBenchmarking.org Nodes Per Second, More Is Better LeelaChessZero 0.22.0 Backend: OpenCL RTX 2070 SUPER RTX 2060 SUPER GTX 980 Ti RTX 2080 SUPER TITAN RTX RTX 2070 GTX 1070 Ti RTX 2080 RTX 2060 GTX 1060 GTX 1080 GTX 1080 Ti GTX 1660 Ti GTX 980 GTX 1660 GTX 1070 GTX 970 RTX 2080 Ti 500 1000 1500 2000 2500 Min: 1547.69 / Avg: 1604.21 / Max: 1678.53 Min: 902.21 / Avg: 998.17 / Max: 1118.93 Min: 421.15 / Avg: 466.84 / Max: 492.4 Min: 2066.54 / Avg: 2105.26 / Max: 2163.91 Min: 3071.21 / Avg: 3126.48 / Max: 3163.96 Min: 882.9 / Avg: 999.75 / Max: 1123.7 Min: 712.7 / Avg: 753.69 / Max: 772.31 Min: 1837.67 / Avg: 1879.99 / Max: 1908.71 Min: 701.95 / Avg: 704.69 / Max: 708.17 Min: 253.74 / Avg: 262.41 / Max: 271.07 Min: 1121.3 / Avg: 1146.75 / Max: 1172.23 Min: 1835.53 / Avg: 1886.3 / Max: 1946.25 Min: 375.01 / Avg: 420.04 / Max: 449.23 Min: 275.81 / Avg: 280.99 / Max: 285.36 Min: 308.55 / Avg: 335.86 / Max: 357.56 Min: 543.08 / Avg: 642.12 / Max: 714.76 Min: 196.93 / Avg: 207.84 / Max: 221.87 Min: 3020.49 / Avg: 3032.1 / Max: 3049.3 1. (CXX) g++ options: -lpthread
PlaidML This test profile uses PlaidML deep learning framework developed by Intel for offering up various benchmarks. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org FPS, More Is Better PlaidML FP16: No - Mode: Inference - Network: VGG16 - Device: OpenCL RTX 2070 SUPER RTX 2060 SUPER GTX 980 Ti RTX 2080 SUPER TITAN RTX RTX 2070 GTX 1070 Ti RTX 2080 RTX 2060 GTX 1060 GTX 1080 GTX 1080 Ti GTX 1660 Ti GTX 980 GTX 1660 GTX 1070 GTX 970 RTX 2080 Ti 50 100 150 200 250 SE +/- 0.29, N = 3 SE +/- 0.34, N = 3 SE +/- 1.36, N = 3 SE +/- 0.28, N = 3 SE +/- 0.40, N = 3 SE +/- 0.43, N = 3 SE +/- 0.06, N = 3 SE +/- 0.73, N = 3 SE +/- 0.32, N = 3 SE +/- 0.12, N = 3 SE +/- 0.38, N = 3 SE +/- 0.62, N = 3 SE +/- 0.24, N = 3 SE +/- 0.79, N = 3 SE +/- 0.21, N = 3 SE +/- 0.17, N = 3 SE +/- 0.05, N = 3 SE +/- 0.50, N = 3 154.64 128.22 87.39 180.45 247.83 131.54 114.03 164.05 110.93 69.31 128.05 175.37 92.45 68.95 84.83 97.32 60.32 234.65 Result Confidence
OpenBenchmarking.org FPS, More Is Better PlaidML FP16: No - Mode: Inference - Network: VGG16 - Device: OpenCL RTX 2070 SUPER RTX 2060 SUPER GTX 980 Ti RTX 2080 SUPER TITAN RTX RTX 2070 GTX 1070 Ti RTX 2080 RTX 2060 GTX 1060 GTX 1080 GTX 1080 Ti GTX 1660 Ti GTX 980 GTX 1660 GTX 1070 GTX 970 RTX 2080 Ti 40 80 120 160 200 Min: 154.27 / Avg: 154.64 / Max: 155.2 Min: 127.68 / Avg: 128.22 / Max: 128.86 Min: 85.16 / Avg: 87.39 / Max: 89.84 Min: 180.02 / Avg: 180.45 / Max: 180.98 Min: 247.23 / Avg: 247.83 / Max: 248.59 Min: 130.9 / Avg: 131.54 / Max: 132.37 Min: 113.94 / Avg: 114.03 / Max: 114.15 Min: 162.9 / Avg: 164.05 / Max: 165.4 Min: 110.47 / Avg: 110.93 / Max: 111.54 Min: 69.14 / Avg: 69.31 / Max: 69.55 Min: 127.45 / Avg: 128.05 / Max: 128.75 Min: 174.34 / Avg: 175.37 / Max: 176.48 Min: 92.08 / Avg: 92.45 / Max: 92.91 Min: 67.57 / Avg: 68.95 / Max: 70.31 Min: 84.49 / Avg: 84.83 / Max: 85.21 Min: 97.01 / Avg: 97.32 / Max: 97.59 Min: 60.26 / Avg: 60.32 / Max: 60.42 Min: 233.84 / Avg: 234.65 / Max: 235.55
Result
OpenBenchmarking.org FPS, More Is Better PlaidML FP16: No - Mode: Inference - Network: Inception V3 - Device: OpenCL RTX 2070 SUPER RTX 2060 SUPER GTX 980 Ti RTX 2080 SUPER TITAN RTX RTX 2070 GTX 1070 Ti RTX 2080 RTX 2060 GTX 1060 GTX 1080 GTX 1080 Ti GTX 1660 Ti GTX 980 GTX 1660 GTX 1070 GTX 970 RTX 2080 Ti 80 160 240 320 400 SE +/- 0.07, N = 3 SE +/- 0.25, N = 3 SE +/- 0.07, N = 3 SE +/- 0.10, N = 3 SE +/- 0.42, N = 3 SE +/- 0.29, N = 3 SE +/- 0.06, N = 3 SE +/- 0.57, N = 3 SE +/- 0.23, N = 3 SE +/- 0.10, N = 3 SE +/- 0.38, N = 3 SE +/- 0.14, N = 3 SE +/- 0.23, N = 3 SE +/- 0.17, N = 3 SE +/- 0.12, N = 3 SE +/- 0.09, N = 3 SE +/- 0.16, N = 3 SE +/- 0.38, N = 3 215.85 199.43 135.14 259.26 347.93 198.03 153.34 238.73 167.87 104.44 184.80 257.55 140.05 105.64 116.90 147.17 94.72 343.49 Result Confidence
OpenBenchmarking.org FPS, More Is Better PlaidML FP16: No - Mode: Inference - Network: Inception V3 - Device: OpenCL RTX 2070 SUPER RTX 2060 SUPER GTX 980 Ti RTX 2080 SUPER TITAN RTX RTX 2070 GTX 1070 Ti RTX 2080 RTX 2060 GTX 1060 GTX 1080 GTX 1080 Ti GTX 1660 Ti GTX 980 GTX 1660 GTX 1070 GTX 970 RTX 2080 Ti 60 120 180 240 300 Min: 215.74 / Avg: 215.85 / Max: 215.97 Min: 199.07 / Avg: 199.43 / Max: 199.9 Min: 135.01 / Avg: 135.14 / Max: 135.24 Min: 259.14 / Avg: 259.26 / Max: 259.45 Min: 347.16 / Avg: 347.93 / Max: 348.59 Min: 197.44 / Avg: 198.03 / Max: 198.36 Min: 153.24 / Avg: 153.34 / Max: 153.46 Min: 237.79 / Avg: 238.73 / Max: 239.76 Min: 167.48 / Avg: 167.87 / Max: 168.27 Min: 104.32 / Avg: 104.44 / Max: 104.65 Min: 184.26 / Avg: 184.8 / Max: 185.52 Min: 257.39 / Avg: 257.55 / Max: 257.83 Min: 139.71 / Avg: 140.05 / Max: 140.49 Min: 105.45 / Avg: 105.64 / Max: 105.99 Min: 116.72 / Avg: 116.9 / Max: 117.12 Min: 147.06 / Avg: 147.17 / Max: 147.36 Min: 94.51 / Avg: 94.72 / Max: 95.03 Min: 343.05 / Avg: 343.49 / Max: 344.25
Result
OpenBenchmarking.org FPS, More Is Better PlaidML FP16: Yes - Mode: Inference - Network: ResNet 50 - Device: OpenCL RTX 2070 SUPER RTX 2060 SUPER GTX 980 Ti RTX 2080 SUPER TITAN RTX RTX 2070 GTX 1070 Ti RTX 2080 RTX 2060 GTX 1060 GTX 1080 GTX 1080 Ti GTX 1660 Ti GTX 980 GTX 1660 GTX 1070 GTX 970 RTX 2080 Ti 90 180 270 360 450 SE +/- 0.71, N = 3 SE +/- 0.48, N = 3 SE +/- 0.06, N = 3 SE +/- 0.12, N = 3 SE +/- 0.70, N = 3 SE +/- 0.53, N = 3 SE +/- 0.08, N = 3 SE +/- 0.60, N = 3 SE +/- 0.16, N = 3 SE +/- 0.16, N = 3 SE +/- 0.11, N = 3 SE +/- 0.42, N = 3 SE +/- 0.06, N = 3 SE +/- 0.26, N = 3 SE +/- 0.31, N = 3 SE +/- 0.28, N = 3 SE +/- 0.00, N = 3 SE +/- 1.04, N = 3 283.98 250.98 162.63 327.80 433.81 251.07 205.85 305.76 220.44 130.64 240.62 333.54 172.68 142.14 156.50 196.01 116.05 424.07 Result Confidence
OpenBenchmarking.org FPS, More Is Better PlaidML FP16: Yes - Mode: Inference - Network: ResNet 50 - Device: OpenCL RTX 2070 SUPER RTX 2060 SUPER GTX 980 Ti RTX 2080 SUPER TITAN RTX RTX 2070 GTX 1070 Ti RTX 2080 RTX 2060 GTX 1060 GTX 1080 GTX 1080 Ti GTX 1660 Ti GTX 980 GTX 1660 GTX 1070 GTX 970 RTX 2080 Ti 80 160 240 320 400 Min: 282.89 / Avg: 283.98 / Max: 285.31 Min: 250.26 / Avg: 250.98 / Max: 251.89 Min: 162.56 / Avg: 162.63 / Max: 162.74 Min: 327.59 / Avg: 327.8 / Max: 327.99 Min: 432.58 / Avg: 433.81 / Max: 435 Min: 250.02 / Avg: 251.07 / Max: 251.75 Min: 205.75 / Avg: 205.85 / Max: 206 Min: 305.05 / Avg: 305.76 / Max: 306.96 Min: 220.26 / Avg: 220.44 / Max: 220.76 Min: 130.32 / Avg: 130.64 / Max: 130.86 Min: 240.5 / Avg: 240.62 / Max: 240.84 Min: 332.77 / Avg: 333.54 / Max: 334.21 Min: 172.61 / Avg: 172.68 / Max: 172.81 Min: 141.87 / Avg: 142.14 / Max: 142.66 Min: 156.03 / Avg: 156.5 / Max: 157.08 Min: 195.53 / Avg: 196.01 / Max: 196.51 Min: 116.05 / Avg: 116.05 / Max: 116.05 Min: 422.83 / Avg: 424.07 / Max: 426.14
NAMD CUDA NAMD is a parallel molecular dynamics code designed for high-performance simulation of large biomolecular systems. NAMD was developed by the Theoretical and Computational Biophysics Group in the Beckman Institute for Advanced Science and Technology at the University of Illinois at Urbana-Champaign. This version of the NAMD test profile uses CUDA GPU acceleration. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org days/ns, Fewer Is Better NAMD CUDA 2.13 ATPase Simulation - 327,506 Atoms RTX 2070 SUPER RTX 2060 SUPER GTX 980 Ti RTX 2080 SUPER TITAN RTX RTX 2070 GTX 1070 Ti RTX 2080 RTX 2060 GTX 1060 GTX 1080 GTX 1080 Ti GTX 1660 Ti GTX 980 GTX 1660 GTX 1070 GTX 970 RTX 2080 Ti 0.0818 0.1636 0.2454 0.3272 0.409 SE +/- 0.00245, N = 3 SE +/- 0.00245, N = 3 SE +/- 0.00105, N = 3 SE +/- 0.00233, N = 3 SE +/- 0.00297, N = 3 SE +/- 0.00250, N = 3 SE +/- 0.00075, N = 6 SE +/- 0.00199, N = 3 SE +/- 0.00147, N = 4 SE +/- 0.00303, N = 3 SE +/- 0.00088, N = 5 SE +/- 0.00044, N = 3 SE +/- 0.00192, N = 3 SE +/- 0.00159, N = 3 SE +/- 0.00287, N = 3 SE +/- 0.00195, N = 3 SE +/- 0.00026, N = 4 SE +/- 0.00238, N = 3 0.19501 0.19336 0.28675 0.19385 0.18867 0.19440 0.22269 0.19307 0.20250 0.31789 0.20978 0.19669 0.23185 0.33110 0.25031 0.23957 0.36368 0.18909 Result Confidence
OpenBenchmarking.org days/ns, Fewer Is Better NAMD CUDA 2.13 ATPase Simulation - 327,506 Atoms RTX 2070 SUPER RTX 2060 SUPER GTX 980 Ti RTX 2080 SUPER TITAN RTX RTX 2070 GTX 1070 Ti RTX 2080 RTX 2060 GTX 1060 GTX 1080 GTX 1080 Ti GTX 1660 Ti GTX 980 GTX 1660 GTX 1070 GTX 970 RTX 2080 Ti 1 2 3 4 5 Min: 0.19 / Avg: 0.2 / Max: 0.2 Min: 0.19 / Avg: 0.19 / Max: 0.2 Min: 0.29 / Avg: 0.29 / Max: 0.29 Min: 0.19 / Avg: 0.19 / Max: 0.2 Min: 0.19 / Avg: 0.19 / Max: 0.19 Min: 0.19 / Avg: 0.19 / Max: 0.2 Min: 0.22 / Avg: 0.22 / Max: 0.23 Min: 0.19 / Avg: 0.19 / Max: 0.2 Min: 0.2 / Avg: 0.2 / Max: 0.21 Min: 0.31 / Avg: 0.32 / Max: 0.32 Min: 0.21 / Avg: 0.21 / Max: 0.21 Min: 0.2 / Avg: 0.2 / Max: 0.2 Min: 0.23 / Avg: 0.23 / Max: 0.23 Min: 0.33 / Avg: 0.33 / Max: 0.33 Min: 0.24 / Avg: 0.25 / Max: 0.25 Min: 0.24 / Avg: 0.24 / Max: 0.24 Min: 0.36 / Avg: 0.36 / Max: 0.36 Min: 0.19 / Avg: 0.19 / Max: 0.19
PlaidML This test profile uses PlaidML deep learning framework developed by Intel for offering up various benchmarks. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org FPS, More Is Better PlaidML FP16: No - Mode: Inference - Network: ResNet 50 - Device: OpenCL RTX 2070 SUPER RTX 2060 SUPER GTX 980 Ti RTX 2080 SUPER TITAN RTX RTX 2070 GTX 1070 Ti RTX 2080 RTX 2060 GTX 1060 GTX 1080 GTX 1080 Ti GTX 1660 Ti GTX 980 GTX 1660 GTX 1070 GTX 970 RTX 2080 Ti 140 280 420 560 700 SE +/- 0.19, N = 3 SE +/- 0.53, N = 3 SE +/- 0.58, N = 3 SE +/- 0.61, N = 3 SE +/- 0.75, N = 3 SE +/- 0.27, N = 3 SE +/- 0.09, N = 3 SE +/- 0.25, N = 3 SE +/- 0.39, N = 3 SE +/- 0.07, N = 3 SE +/- 0.32, N = 3 SE +/- 0.72, N = 3 SE +/- 0.47, N = 3 SE +/- 0.02, N = 3 SE +/- 0.16, N = 3 SE +/- 0.15, N = 3 SE +/- 0.06, N = 3 SE +/- 0.63, N = 3 421.58 374.71 247.47 468.70 648.36 376.73 294.36 441.24 319.25 196.00 337.47 496.24 259.43 203.91 228.14 276.89 181.87 634.09 Result Confidence
OpenBenchmarking.org FPS, More Is Better PlaidML FP16: No - Mode: Inference - Network: ResNet 50 - Device: OpenCL RTX 2070 SUPER RTX 2060 SUPER GTX 980 Ti RTX 2080 SUPER TITAN RTX RTX 2070 GTX 1070 Ti RTX 2080 RTX 2060 GTX 1060 GTX 1080 GTX 1080 Ti GTX 1660 Ti GTX 980 GTX 1660 GTX 1070 GTX 970 RTX 2080 Ti 110 220 330 440 550 Min: 421.32 / Avg: 421.58 / Max: 421.95 Min: 374.14 / Avg: 374.71 / Max: 375.76 Min: 246.32 / Avg: 247.47 / Max: 248.16 Min: 467.54 / Avg: 468.7 / Max: 469.59 Min: 646.86 / Avg: 648.36 / Max: 649.2 Min: 376.25 / Avg: 376.73 / Max: 377.19 Min: 294.22 / Avg: 294.36 / Max: 294.52 Min: 440.77 / Avg: 441.24 / Max: 441.62 Min: 318.64 / Avg: 319.25 / Max: 319.97 Min: 195.86 / Avg: 196 / Max: 196.07 Min: 337.14 / Avg: 337.47 / Max: 338.12 Min: 494.81 / Avg: 496.24 / Max: 497.01 Min: 258.64 / Avg: 259.43 / Max: 260.28 Min: 203.88 / Avg: 203.91 / Max: 203.94 Min: 227.89 / Avg: 228.14 / Max: 228.44 Min: 276.68 / Avg: 276.89 / Max: 277.18 Min: 181.81 / Avg: 181.87 / Max: 181.99 Min: 632.87 / Avg: 634.09 / Max: 634.95
Result
OpenBenchmarking.org FPS, More Is Better PlaidML FP16: No - Mode: Inference - Network: IMDB LSTM - Device: OpenCL RTX 2070 SUPER RTX 2060 SUPER GTX 980 Ti RTX 2080 SUPER TITAN RTX RTX 2070 GTX 1070 Ti RTX 2080 RTX 2060 GTX 1060 GTX 1080 GTX 1080 Ti GTX 1660 Ti GTX 980 GTX 1660 GTX 1070 GTX 970 RTX 2080 Ti 200 400 600 800 1000 SE +/- 0.67, N = 3 SE +/- 0.31, N = 3 SE +/- 0.56, N = 3 SE +/- 1.47, N = 3 SE +/- 2.25, N = 3 SE +/- 0.21, N = 3 SE +/- 0.49, N = 3 SE +/- 1.63, N = 3 SE +/- 0.37, N = 3 SE +/- 0.17, N = 3 SE +/- 0.31, N = 3 SE +/- 0.74, N = 3 SE +/- 0.15, N = 3 SE +/- 0.50, N = 3 SE +/- 0.01, N = 3 SE +/- 0.13, N = 3 SE +/- 0.03, N = 3 SE +/- 1.01, N = 3 499.69 440.79 270.00 589.86 790.77 446.23 333.03 548.83 389.40 224.89 399.00 523.98 315.83 231.66 287.68 315.37 204.32 758.21 Result Confidence
OpenBenchmarking.org FPS, More Is Better PlaidML FP16: No - Mode: Inference - Network: IMDB LSTM - Device: OpenCL RTX 2070 SUPER RTX 2060 SUPER GTX 980 Ti RTX 2080 SUPER TITAN RTX RTX 2070 GTX 1070 Ti RTX 2080 RTX 2060 GTX 1060 GTX 1080 GTX 1080 Ti GTX 1660 Ti GTX 980 GTX 1660 GTX 1070 GTX 970 RTX 2080 Ti 140 280 420 560 700 Min: 498.72 / Avg: 499.69 / Max: 500.98 Min: 440.29 / Avg: 440.79 / Max: 441.37 Min: 269.37 / Avg: 270 / Max: 271.13 Min: 587.12 / Avg: 589.86 / Max: 592.17 Min: 786.44 / Avg: 790.77 / Max: 793.98 Min: 445.83 / Avg: 446.23 / Max: 446.55 Min: 332.49 / Avg: 333.03 / Max: 334 Min: 545.63 / Avg: 548.83 / Max: 550.96 Min: 389.01 / Avg: 389.4 / Max: 390.13 Min: 224.54 / Avg: 224.89 / Max: 225.07 Min: 398.38 / Avg: 399 / Max: 399.37 Min: 522.59 / Avg: 523.98 / Max: 525.11 Min: 315.54 / Avg: 315.83 / Max: 316.06 Min: 230.69 / Avg: 231.66 / Max: 232.35 Min: 287.66 / Avg: 287.68 / Max: 287.71 Min: 315.2 / Avg: 315.37 / Max: 315.63 Min: 204.27 / Avg: 204.32 / Max: 204.36 Min: 756.33 / Avg: 758.21 / Max: 759.78
Rodinia Rodinia is a suite focused upon accelerating compute-intensive applications with accelerators. CUDA, OpenMP, and OpenCL parallel models are supported by the included applications. This profile utilizes the OpenCL and OpenMP test binaries at the moment. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Seconds, Fewer Is Better Rodinia 2.4 Test: OpenCL Particle Filter RTX 2070 SUPER RTX 2060 SUPER GTX 980 Ti RTX 2080 SUPER TITAN RTX RTX 2070 GTX 1070 Ti RTX 2080 RTX 2060 GTX 1060 GTX 1080 GTX 1080 Ti GTX 1660 Ti GTX 980 GTX 1660 GTX 1070 GTX 970 RTX 2080 Ti 3 6 9 12 15 SE +/- 0.07, N = 3 SE +/- 0.00, N = 3 SE +/- 0.04, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.07, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 SE +/- 0.07, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 6.82 7.87 9.95 5.74 4.24 7.75 7.88 6.22 8.90 11.93 6.49 4.96 10.82 11.69 11.87 8.26 12.99 4.39 1. (CXX) g++ options: -O2 -lOpenCL Result Confidence
OpenBenchmarking.org Seconds, Fewer Is Better Rodinia 2.4 Test: OpenCL Particle Filter RTX 2070 SUPER RTX 2060 SUPER GTX 980 Ti RTX 2080 SUPER TITAN RTX RTX 2070 GTX 1070 Ti RTX 2080 RTX 2060 GTX 1060 GTX 1080 GTX 1080 Ti GTX 1660 Ti GTX 980 GTX 1660 GTX 1070 GTX 970 RTX 2080 Ti 4 8 12 16 20 Min: 6.74 / Avg: 6.82 / Max: 6.96 Min: 7.87 / Avg: 7.87 / Max: 7.88 Min: 9.89 / Avg: 9.95 / Max: 10.01 Min: 5.72 / Avg: 5.74 / Max: 5.75 Min: 4.23 / Avg: 4.24 / Max: 4.26 Min: 7.74 / Avg: 7.75 / Max: 7.76 Min: 7.78 / Avg: 7.88 / Max: 8.01 Min: 6.2 / Avg: 6.22 / Max: 6.24 Min: 8.88 / Avg: 8.9 / Max: 8.93 Min: 11.91 / Avg: 11.93 / Max: 11.98 Min: 6.48 / Avg: 6.49 / Max: 6.51 Min: 4.94 / Avg: 4.96 / Max: 5.01 Min: 10.8 / Avg: 10.82 / Max: 10.85 Min: 11.6 / Avg: 11.69 / Max: 11.83 Min: 11.86 / Avg: 11.87 / Max: 11.89 Min: 8.25 / Avg: 8.26 / Max: 8.27 Min: 12.96 / Avg: 12.99 / Max: 13.02 Min: 4.37 / Avg: 4.39 / Max: 4.42 1. (CXX) g++ options: -O2 -lOpenCL
cl-mem A basic OpenCL memory benchmark. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org GB/s, More Is Better cl-mem 2017-01-13 Benchmark: Read RTX 2070 SUPER RTX 2060 SUPER GTX 980 Ti RTX 2080 SUPER TITAN RTX RTX 2070 GTX 1070 Ti RTX 2080 RTX 2060 GTX 1060 GTX 1080 GTX 1080 Ti GTX 1660 Ti GTX 980 GTX 1660 GTX 1070 GTX 970 RTX 2080 Ti 120 240 360 480 600 SE +/- 0.22, N = 3 SE +/- 0.22, N = 3 SE +/- 0.12, N = 3 SE +/- 0.27, N = 3 SE +/- 0.40, N = 3 SE +/- 0.25, N = 3 SE +/- 0.07, N = 3 SE +/- 0.25, N = 3 SE +/- 0.20, N = 3 SE +/- 0.00, N = 3 SE +/- 0.12, N = 3 SE +/- 0.20, N = 3 SE +/- 0.07, N = 3 SE +/- 0.10, N = 3 SE +/- 0.00, N = 3 SE +/- 0.03, N = 3 SE +/- 1.50, N = 8 SE +/- 0.38, N = 3 395.67 395.67 265.33 436.27 566.70 395.70 205.27 395.70 296.20 153.50 228.80 337.53 250.23 164.50 162.90 205.27 142.10 544.33 1. (CC) gcc options: -O2 -flto -lOpenCL Result Confidence
OpenBenchmarking.org GB/s, More Is Better cl-mem 2017-01-13 Benchmark: Read RTX 2070 SUPER RTX 2060 SUPER GTX 980 Ti RTX 2080 SUPER TITAN RTX RTX 2070 GTX 1070 Ti RTX 2080 RTX 2060 GTX 1060 GTX 1080 GTX 1080 Ti GTX 1660 Ti GTX 980 GTX 1660 GTX 1070 GTX 970 RTX 2080 Ti 100 200 300 400 500 Min: 395.4 / Avg: 395.67 / Max: 396.1 Min: 395.4 / Avg: 395.67 / Max: 396.1 Min: 265.1 / Avg: 265.33 / Max: 265.5 Min: 436 / Avg: 436.27 / Max: 436.8 Min: 566 / Avg: 566.7 / Max: 567.4 Min: 395.4 / Avg: 395.7 / Max: 396.2 Min: 205.2 / Avg: 205.27 / Max: 205.4 Min: 395.4 / Avg: 395.7 / Max: 396.2 Min: 296 / Avg: 296.2 / Max: 296.6 Min: 153.5 / Avg: 153.5 / Max: 153.5 Min: 228.6 / Avg: 228.8 / Max: 229 Min: 337.2 / Avg: 337.53 / Max: 337.9 Min: 250.1 / Avg: 250.23 / Max: 250.3 Min: 164.3 / Avg: 164.5 / Max: 164.6 Min: 162.9 / Avg: 162.9 / Max: 162.9 Min: 205.2 / Avg: 205.27 / Max: 205.3 Min: 131.6 / Avg: 142.1 / Max: 143.7 Min: 543.7 / Avg: 544.33 / Max: 545 1. (CC) gcc options: -O2 -flto -lOpenCL
JuliaGPU JuliaGPU is an OpenCL benchmark with this version containing various PTS-specific enhancements. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Samples/sec, More Is Better JuliaGPU 1.2pts1 OpenCL Device: GPU RTX 2070 SUPER RTX 2060 SUPER GTX 980 Ti RTX 2080 SUPER TITAN RTX RTX 2070 GTX 1070 Ti RTX 2080 RTX 2060 GTX 1060 GTX 1080 GTX 1080 Ti GTX 1660 Ti GTX 980 GTX 1660 GTX 1070 GTX 970 RTX 2080 Ti 60M 120M 180M 240M 300M SE +/- 389272.10, N = 3 SE +/- 369711.60, N = 3 SE +/- 78142.08, N = 3 SE +/- 1165562.77, N = 3 SE +/- 489061.14, N = 3 SE +/- 633693.84, N = 3 SE +/- 97519.45, N = 3 SE +/- 169596.23, N = 3 SE +/- 121354.48, N = 3 SE +/- 137674.47, N = 3 SE +/- 341457.11, N = 3 SE +/- 540298.84, N = 3 SE +/- 495295.96, N = 3 SE +/- 52667.10, N = 3 SE +/- 197521.26, N = 3 SE +/- 76295.47, N = 3 SE +/- 383961.59, N = 3 SE +/- 78810.54, N = 3 275868151.17 264172441.47 195653728.47 286818331.27 303198573.97 267086274.53 220447755.87 280162469.67 251925176.90 182188318.67 237914974.40 262248899.33 239300837.60 181882709.77 230919642.13 216942144.93 169258044.90 299834728.80 1. (CC) gcc options: -O3 -march=native -ftree-vectorize -funroll-loops -lglut -lOpenCL -lGL -lm Result Confidence
OpenBenchmarking.org Samples/sec, More Is Better JuliaGPU 1.2pts1 OpenCL Device: GPU RTX 2070 SUPER RTX 2060 SUPER GTX 980 Ti RTX 2080 SUPER TITAN RTX RTX 2070 GTX 1070 Ti RTX 2080 RTX 2060 GTX 1060 GTX 1080 GTX 1080 Ti GTX 1660 Ti GTX 980 GTX 1660 GTX 1070 GTX 970 RTX 2080 Ti 50M 100M 150M 200M 250M Min: 275409849.2 / Avg: 275868151.17 / Max: 276642341.4 Min: 263796744.9 / Avg: 264172441.47 / Max: 264911832.2 Min: 195536537.9 / Avg: 195653728.47 / Max: 195801868.9 Min: 285621108.4 / Avg: 286818331.27 / Max: 289149167.5 Min: 302303081.3 / Avg: 303198573.97 / Max: 303987072.5 Min: 266002172.4 / Avg: 267086274.53 / Max: 268196872.5 Min: 220327896.8 / Avg: 220447755.87 / Max: 220640935.1 Min: 279907652.6 / Avg: 280162469.67 / Max: 280483759.2 Min: 251682900.3 / Avg: 251925176.9 / Max: 252058855.7 Min: 181934715.1 / Avg: 182188318.67 / Max: 182408000.5 Min: 237311155 / Avg: 237914974.4 / Max: 238493163.8 Min: 261590858.5 / Avg: 262248899.33 / Max: 263320217 Min: 238659645.2 / Avg: 239300837.6 / Max: 240275351.6 Min: 181805709 / Avg: 181882709.77 / Max: 181983456.7 Min: 230528006.9 / Avg: 230919642.13 / Max: 231160296.4 Min: 216792281.1 / Avg: 216942144.93 / Max: 217041948.9 Min: 168529375.9 / Avg: 169258044.9 / Max: 169832285.6 Min: 299683160.1 / Avg: 299834728.8 / Max: 299947976.5 1. (CC) gcc options: -O3 -march=native -ftree-vectorize -funroll-loops -lglut -lOpenCL -lGL -lm
PlaidML This test profile uses PlaidML deep learning framework developed by Intel for offering up various benchmarks. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org FPS, More Is Better PlaidML FP16: Yes - Mode: Inference - Network: Mobilenet - Device: OpenCL RTX 2070 SUPER RTX 2060 SUPER GTX 980 Ti RTX 2080 SUPER TITAN RTX RTX 2070 GTX 1070 Ti RTX 2080 RTX 2060 GTX 1060 GTX 1080 GTX 1080 Ti GTX 1660 Ti GTX 980 GTX 1660 GTX 1070 GTX 970 RTX 2080 Ti 600 1200 1800 2400 3000 SE +/- 4.73, N = 3 SE +/- 10.89, N = 3 SE +/- 1.24, N = 3 SE +/- 6.75, N = 3 SE +/- 4.02, N = 3 SE +/- 5.21, N = 3 SE +/- 0.80, N = 3 SE +/- 4.68, N = 3 SE +/- 3.62, N = 3 SE +/- 2.37, N = 3 SE +/- 4.27, N = 3 SE +/- 7.35, N = 3 SE +/- 2.77, N = 3 SE +/- 2.37, N = 3 SE +/- 1.34, N = 3 SE +/- 4.57, N = 3 SE +/- 1.43, N = 3 SE +/- 13.82, N = 3 2264.97 1983.82 1202.77 2437.48 2842.38 1969.50 1371.21 2292.38 1694.07 908.43 1544.50 2162.58 1394.05 973.39 1160.52 1288.94 841.48 2750.57 Result Confidence
OpenBenchmarking.org FPS, More Is Better PlaidML FP16: Yes - Mode: Inference - Network: Mobilenet - Device: OpenCL RTX 2070 SUPER RTX 2060 SUPER GTX 980 Ti RTX 2080 SUPER TITAN RTX RTX 2070 GTX 1070 Ti RTX 2080 RTX 2060 GTX 1060 GTX 1080 GTX 1080 Ti GTX 1660 Ti GTX 980 GTX 1660 GTX 1070 GTX 970 RTX 2080 Ti 500 1000 1500 2000 2500 Min: 2257.89 / Avg: 2264.97 / Max: 2273.95 Min: 1962.07 / Avg: 1983.82 / Max: 1995.82 Min: 1201.03 / Avg: 1202.77 / Max: 1205.17 Min: 2424.79 / Avg: 2437.48 / Max: 2447.82 Min: 2836.78 / Avg: 2842.38 / Max: 2850.17 Min: 1960.87 / Avg: 1969.5 / Max: 1978.86 Min: 1369.86 / Avg: 1371.21 / Max: 1372.62 Min: 2284.48 / Avg: 2292.38 / Max: 2300.69 Min: 1687.76 / Avg: 1694.07 / Max: 1700.31 Min: 903.72 / Avg: 908.43 / Max: 911.3 Min: 1536.07 / Avg: 1544.5 / Max: 1549.93 Min: 2147.89 / Avg: 2162.58 / Max: 2170.35 Min: 1388.53 / Avg: 1394.05 / Max: 1397.22 Min: 968.67 / Avg: 973.39 / Max: 976.16 Min: 1159.04 / Avg: 1160.52 / Max: 1163.2 Min: 1279.87 / Avg: 1288.94 / Max: 1294.37 Min: 838.63 / Avg: 841.48 / Max: 843.09 Min: 2728.29 / Avg: 2750.57 / Max: 2775.87
cl-mem A basic OpenCL memory benchmark. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org GB/s, More Is Better cl-mem 2017-01-13 Benchmark: Copy RTX 2070 SUPER RTX 2060 SUPER GTX 980 Ti RTX 2080 SUPER TITAN RTX RTX 2070 GTX 1070 Ti RTX 2080 RTX 2060 GTX 1060 GTX 1080 GTX 1080 Ti GTX 1660 Ti GTX 980 GTX 1660 GTX 1070 GTX 970 RTX 2080 Ti 70 140 210 280 350 SE +/- 0.17, N = 3 SE +/- 0.31, N = 3 SE +/- 0.17, N = 3 SE +/- 0.13, N = 3 SE +/- 0.67, N = 3 SE +/- 0.24, N = 3 SE +/- 0.00, N = 3 SE +/- 0.15, N = 3 SE +/- 0.12, N = 3 SE +/- 0.06, N = 3 SE +/- 0.03, N = 3 SE +/- 0.25, N = 3 SE +/- 0.15, N = 3 SE +/- 0.00, N = 3 SE +/- 0.03, N = 3 SE +/- 0.06, N = 3 SE +/- 0.03, N = 3 SE +/- 0.40, N = 3 291.87 287.80 216.83 301.23 322.20 284.43 182.70 289.20 237.77 137.20 205.93 283.20 208.50 143.40 145.37 182.00 124.77 324.40 1. (CC) gcc options: -O2 -flto -lOpenCL Result Confidence
OpenBenchmarking.org GB/s, More Is Better cl-mem 2017-01-13 Benchmark: Copy RTX 2070 SUPER RTX 2060 SUPER GTX 980 Ti RTX 2080 SUPER TITAN RTX RTX 2070 GTX 1070 Ti RTX 2080 RTX 2060 GTX 1060 GTX 1080 GTX 1080 Ti GTX 1660 Ti GTX 980 GTX 1660 GTX 1070 GTX 970 RTX 2080 Ti 60 120 180 240 300 Min: 291.7 / Avg: 291.87 / Max: 292.2 Min: 287.4 / Avg: 287.8 / Max: 288.4 Min: 216.5 / Avg: 216.83 / Max: 217 Min: 301.1 / Avg: 301.23 / Max: 301.5 Min: 320.9 / Avg: 322.2 / Max: 323.1 Min: 284.1 / Avg: 284.43 / Max: 284.9 Min: 182.7 / Avg: 182.7 / Max: 182.7 Min: 289 / Avg: 289.2 / Max: 289.5 Min: 237.6 / Avg: 237.77 / Max: 238 Min: 137.1 / Avg: 137.2 / Max: 137.3 Min: 205.9 / Avg: 205.93 / Max: 206 Min: 282.9 / Avg: 283.2 / Max: 283.7 Min: 208.3 / Avg: 208.5 / Max: 208.8 Min: 143.4 / Avg: 143.4 / Max: 143.4 Min: 145.3 / Avg: 145.37 / Max: 145.4 Min: 181.9 / Avg: 182 / Max: 182.1 Min: 124.7 / Avg: 124.77 / Max: 124.8 Min: 323.7 / Avg: 324.4 / Max: 325.1 1. (CC) gcc options: -O2 -flto -lOpenCL
Result
OpenBenchmarking.org GB/s, More Is Better cl-mem 2017-01-13 Benchmark: Write RTX 2070 SUPER RTX 2060 SUPER GTX 980 Ti RTX 2080 SUPER TITAN RTX RTX 2070 GTX 1070 Ti RTX 2080 RTX 2060 GTX 1060 GTX 1080 GTX 1080 Ti GTX 1660 Ti GTX 980 GTX 1660 GTX 1070 GTX 970 RTX 2080 Ti 110 220 330 440 550 SE +/- 0.43, N = 3 SE +/- 0.82, N = 3 SE +/- 0.06, N = 3 SE +/- 0.54, N = 3 SE +/- 1.39, N = 3 SE +/- 1.00, N = 3 SE +/- 0.03, N = 3 SE +/- 0.15, N = 3 SE +/- 0.40, N = 3 SE +/- 0.03, N = 3 SE +/- 0.03, N = 3 SE +/- 0.28, N = 3 SE +/- 0.12, N = 3 SE +/- 0.00, N = 3 SE +/- 0.03, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.35, N = 3 319.57 333.20 241.50 345.77 495.37 322.67 190.03 331.50 241.20 144.57 214.67 340.27 208.67 151.50 148.87 190.90 132.60 441.23 1. (CC) gcc options: -O2 -flto -lOpenCL Result Confidence
OpenBenchmarking.org GB/s, More Is Better cl-mem 2017-01-13 Benchmark: Write RTX 2070 SUPER RTX 2060 SUPER GTX 980 Ti RTX 2080 SUPER TITAN RTX RTX 2070 GTX 1070 Ti RTX 2080 RTX 2060 GTX 1060 GTX 1080 GTX 1080 Ti GTX 1660 Ti GTX 980 GTX 1660 GTX 1070 GTX 970 RTX 2080 Ti 90 180 270 360 450 Min: 319 / Avg: 319.57 / Max: 320.4 Min: 332.1 / Avg: 333.2 / Max: 334.8 Min: 241.4 / Avg: 241.5 / Max: 241.6 Min: 345 / Avg: 345.77 / Max: 346.8 Min: 492.9 / Avg: 495.37 / Max: 497.7 Min: 320.8 / Avg: 322.67 / Max: 324.2 Min: 190 / Avg: 190.03 / Max: 190.1 Min: 331.2 / Avg: 331.5 / Max: 331.7 Min: 240.4 / Avg: 241.2 / Max: 241.6 Min: 144.5 / Avg: 144.57 / Max: 144.6 Min: 214.6 / Avg: 214.67 / Max: 214.7 Min: 339.7 / Avg: 340.27 / Max: 340.6 Min: 208.5 / Avg: 208.67 / Max: 208.9 Min: 151.5 / Avg: 151.5 / Max: 151.5 Min: 148.8 / Avg: 148.87 / Max: 148.9 Min: 190.9 / Avg: 190.9 / Max: 190.9 Min: 132.6 / Avg: 132.6 / Max: 132.6 Min: 440.6 / Avg: 441.23 / Max: 441.8 1. (CC) gcc options: -O2 -flto -lOpenCL
PlaidML This test profile uses PlaidML deep learning framework developed by Intel for offering up various benchmarks. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org FPS, More Is Better PlaidML FP16: No - Mode: Inference - Network: Mobilenet - Device: OpenCL RTX 2070 SUPER RTX 2060 SUPER GTX 980 Ti RTX 2080 SUPER TITAN RTX RTX 2070 GTX 1070 Ti RTX 2080 RTX 2060 GTX 1060 GTX 1080 GTX 1080 Ti GTX 1660 Ti GTX 980 GTX 1660 GTX 1070 GTX 970 RTX 2080 Ti 500 1000 1500 2000 2500 SE +/- 1.25, N = 3 SE +/- 1.59, N = 3 SE +/- 0.07, N = 3 SE +/- 2.80, N = 3 SE +/- 13.68, N = 3 SE +/- 1.46, N = 3 SE +/- 0.73, N = 3 SE +/- 4.17, N = 3 SE +/- 2.11, N = 3 SE +/- 0.63, N = 3 SE +/- 1.27, N = 3 SE +/- 5.20, N = 3 SE +/- 0.86, N = 3 SE +/- 0.24, N = 3 SE +/- 1.38, N = 3 SE +/- 1.57, N = 3 SE +/- 0.75, N = 3 SE +/- 6.28, N = 3 1649.17 1531.01 990.12 1762.00 2466.66 1516.96 1009.26 1663.87 1232.47 726.30 1123.85 1672.73 1002.00 759.43 814.65 987.69 671.49 2335.46 Result Confidence
OpenBenchmarking.org FPS, More Is Better PlaidML FP16: No - Mode: Inference - Network: Mobilenet - Device: OpenCL RTX 2070 SUPER RTX 2060 SUPER GTX 980 Ti RTX 2080 SUPER TITAN RTX RTX 2070 GTX 1070 Ti RTX 2080 RTX 2060 GTX 1060 GTX 1080 GTX 1080 Ti GTX 1660 Ti GTX 980 GTX 1660 GTX 1070 GTX 970 RTX 2080 Ti 400 800 1200 1600 2000 Min: 1646.69 / Avg: 1649.17 / Max: 1650.64 Min: 1529.18 / Avg: 1531.01 / Max: 1534.17 Min: 990.01 / Avg: 990.12 / Max: 990.24 Min: 1757.01 / Avg: 1762 / Max: 1766.68 Min: 2439.39 / Avg: 2466.66 / Max: 2482.28 Min: 1514.94 / Avg: 1516.96 / Max: 1519.79 Min: 1008.28 / Avg: 1009.26 / Max: 1010.69 Min: 1655.67 / Avg: 1663.87 / Max: 1669.26 Min: 1230.15 / Avg: 1232.47 / Max: 1236.68 Min: 725.1 / Avg: 726.3 / Max: 727.2 Min: 1121.42 / Avg: 1123.85 / Max: 1125.72 Min: 1662.99 / Avg: 1672.73 / Max: 1680.78 Min: 1000.55 / Avg: 1002 / Max: 1003.54 Min: 759.11 / Avg: 759.43 / Max: 759.9 Min: 812.09 / Avg: 814.65 / Max: 816.83 Min: 984.63 / Avg: 987.69 / Max: 989.85 Min: 670.13 / Avg: 671.49 / Max: 672.71 Min: 2328.06 / Avg: 2335.46 / Max: 2347.95
Darktable Darktable is an open-source photography / workflow application this will use any system-installed Darktable program or on Windows will automatically download the pre-built binary from the project. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Seconds, Fewer Is Better Darktable 2.6.0 Test: Masskrug - Acceleration: OpenCL RTX 2070 SUPER RTX 2060 SUPER GTX 980 Ti RTX 2080 SUPER TITAN RTX RTX 2070 GTX 1070 Ti RTX 2080 RTX 2060 GTX 1060 GTX 1080 GTX 1080 Ti GTX 1660 Ti GTX 980 GTX 1660 GTX 1070 GTX 970 RTX 2080 Ti 1.3005 2.601 3.9015 5.202 6.5025 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.03, N = 3 SE +/- 0.01, N = 3 3.71 3.68 4.12 3.69 3.66 3.67 3.97 3.71 3.73 4.07 3.94 3.92 4.02 5.74 4.01 3.92 5.78 3.66 Result Confidence
OpenBenchmarking.org Seconds, Fewer Is Better Darktable 2.6.0 Test: Masskrug - Acceleration: OpenCL RTX 2070 SUPER RTX 2060 SUPER GTX 980 Ti RTX 2080 SUPER TITAN RTX RTX 2070 GTX 1070 Ti RTX 2080 RTX 2060 GTX 1060 GTX 1080 GTX 1080 Ti GTX 1660 Ti GTX 980 GTX 1660 GTX 1070 GTX 970 RTX 2080 Ti 2 4 6 8 10 Min: 3.69 / Avg: 3.71 / Max: 3.74 Min: 3.67 / Avg: 3.68 / Max: 3.71 Min: 4.11 / Avg: 4.12 / Max: 4.13 Min: 3.67 / Avg: 3.69 / Max: 3.7 Min: 3.63 / Avg: 3.66 / Max: 3.68 Min: 3.66 / Avg: 3.67 / Max: 3.7 Min: 3.96 / Avg: 3.97 / Max: 3.98 Min: 3.69 / Avg: 3.71 / Max: 3.73 Min: 3.72 / Avg: 3.73 / Max: 3.73 Min: 4.05 / Avg: 4.07 / Max: 4.1 Min: 3.92 / Avg: 3.94 / Max: 3.97 Min: 3.9 / Avg: 3.92 / Max: 3.94 Min: 4.02 / Avg: 4.02 / Max: 4.02 Min: 5.72 / Avg: 5.74 / Max: 5.79 Min: 4 / Avg: 4.01 / Max: 4.03 Min: 3.91 / Avg: 3.92 / Max: 3.94 Min: 5.75 / Avg: 5.78 / Max: 5.84 Min: 3.64 / Avg: 3.66 / Max: 3.68
clpeak Clpeak is designed to test the peak capabilities of OpenCL devices. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org GIOPS, More Is Better clpeak OpenCL Test: Integer Compute INT RTX 2070 SUPER RTX 2060 SUPER GTX 980 Ti RTX 2080 SUPER TITAN RTX RTX 2070 GTX 1070 Ti RTX 2080 RTX 2060 GTX 1060 GTX 1080 GTX 1080 Ti GTX 1660 Ti GTX 980 GTX 1660 GTX 1070 GTX 970 RTX 2080 Ti 3K 6K 9K 12K 15K SE +/- 81.60, N = 15 SE +/- 76.65, N = 15 SE +/- 23.09, N = 3 SE +/- 83.79, N = 15 SE +/- 156.59, N = 15 SE +/- 84.78, N = 15 SE +/- 0.72, N = 3 SE +/- 4.11, N = 3 SE +/- 63.11, N = 3 SE +/- 13.36, N = 15 SE +/- 26.46, N = 3 SE +/- 29.87, N = 15 SE +/- 64.34, N = 15 SE +/- 0.38, N = 3 SE +/- 32.97, N = 3 SE +/- 24.36, N = 3 SE +/- 19.67, N = 3 SE +/- 57.62, N = 3 8570.60 7023.07 1610.28 10404.71 13841.25 7161.48 2076.93 9660.92 5269.01 1267.89 2430.74 3301.89 4775.45 1312.06 4657.79 1685.05 1140.29 13609.33 1. (CXX) g++ options: -O3 -rdynamic -lOpenCL Result Confidence
OpenBenchmarking.org GIOPS, More Is Better clpeak OpenCL Test: Integer Compute INT RTX 2070 SUPER RTX 2060 SUPER GTX 980 Ti RTX 2080 SUPER TITAN RTX RTX 2070 GTX 1070 Ti RTX 2080 RTX 2060 GTX 1060 GTX 1080 GTX 1080 Ti GTX 1660 Ti GTX 980 GTX 1660 GTX 1070 GTX 970 RTX 2080 Ti 2K 4K 6K 8K 10K Min: 8189.47 / Avg: 8570.6 / Max: 9038.07 Min: 6574.27 / Avg: 7023.07 / Max: 7441.44 Min: 1564.12 / Avg: 1610.28 / Max: 1634.55 Min: 10047.59 / Avg: 10404.71 / Max: 10847.47 Min: 13064.83 / Avg: 13841.25 / Max: 14710.79 Min: 6785.41 / Avg: 7161.48 / Max: 7580.47 Min: 2075.79 / Avg: 2076.93 / Max: 2078.25 Min: 9656.5 / Avg: 9660.92 / Max: 9669.13 Min: 5201.92 / Avg: 5269.01 / Max: 5395.15 Min: 1126.34 / Avg: 1267.89 / Max: 1290.72 Min: 2378.04 / Avg: 2430.74 / Max: 2461.23 Min: 3000.66 / Avg: 3301.89 / Max: 3375.19 Min: 4496.99 / Avg: 4775.45 / Max: 5173.28 Min: 1311.49 / Avg: 1312.06 / Max: 1312.77 Min: 4594.53 / Avg: 4657.79 / Max: 4705.52 Min: 1639.44 / Avg: 1685.05 / Max: 1722.69 Min: 1102.57 / Avg: 1140.29 / Max: 1168.83 Min: 13496.99 / Avg: 13609.33 / Max: 13687.78 1. (CXX) g++ options: -O3 -rdynamic -lOpenCL
Darktable Darktable is an open-source photography / workflow application this will use any system-installed Darktable program or on Windows will automatically download the pre-built binary from the project. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Seconds, Fewer Is Better Darktable 2.6.0 Test: Boat - Acceleration: OpenCL RTX 2070 SUPER RTX 2060 SUPER GTX 980 Ti RTX 2080 SUPER TITAN RTX RTX 2070 GTX 1070 Ti RTX 2080 RTX 2060 GTX 1060 GTX 1080 GTX 1080 Ti GTX 1660 Ti GTX 980 GTX 1660 GTX 1070 GTX 970 RTX 2080 Ti 0.9945 1.989 2.9835 3.978 4.9725 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 SE +/- 0.02, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 1.93 1.95 3.27 1.82 1.64 1.93 2.93 1.90 2.22 3.65 2.72 2.29 2.92 3.92 3.35 2.89 4.42 1.64 Result Confidence
OpenBenchmarking.org Seconds, Fewer Is Better Darktable 2.6.0 Test: Boat - Acceleration: OpenCL RTX 2070 SUPER RTX 2060 SUPER GTX 980 Ti RTX 2080 SUPER TITAN RTX RTX 2070 GTX 1070 Ti RTX 2080 RTX 2060 GTX 1060 GTX 1080 GTX 1080 Ti GTX 1660 Ti GTX 980 GTX 1660 GTX 1070 GTX 970 RTX 2080 Ti 2 4 6 8 10 Min: 1.93 / Avg: 1.93 / Max: 1.94 Min: 1.94 / Avg: 1.95 / Max: 1.95 Min: 3.26 / Avg: 3.27 / Max: 3.28 Min: 1.81 / Avg: 1.82 / Max: 1.82 Min: 1.61 / Avg: 1.64 / Max: 1.67 Min: 1.93 / Avg: 1.93 / Max: 1.94 Min: 2.93 / Avg: 2.93 / Max: 2.93 Min: 1.9 / Avg: 1.9 / Max: 1.9 Min: 2.21 / Avg: 2.22 / Max: 2.23 Min: 3.64 / Avg: 3.65 / Max: 3.66 Min: 2.72 / Avg: 2.72 / Max: 2.73 Min: 2.28 / Avg: 2.29 / Max: 2.3 Min: 2.91 / Avg: 2.92 / Max: 2.92 Min: 3.92 / Avg: 3.92 / Max: 3.93 Min: 3.34 / Avg: 3.35 / Max: 3.37 Min: 2.88 / Avg: 2.89 / Max: 2.9 Min: 4.41 / Avg: 4.42 / Max: 4.43 Min: 1.64 / Avg: 1.64 / Max: 1.64
clpeak Clpeak is designed to test the peak capabilities of OpenCL devices. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org GFLOPS, More Is Better clpeak OpenCL Test: Single-Precision Float RTX 2070 SUPER RTX 2060 SUPER GTX 980 Ti RTX 2080 SUPER TITAN RTX RTX 2070 GTX 1070 Ti RTX 2080 RTX 2060 GTX 1060 GTX 1080 GTX 1080 Ti GTX 1660 Ti GTX 980 GTX 1660 GTX 1070 GTX 970 RTX 2080 Ti 3K 6K 9K 12K 15K SE +/- 76.18, N = 15 SE +/- 84.87, N = 15 SE +/- 44.36, N = 15 SE +/- 124.22, N = 3 SE +/- 228.75, N = 15 SE +/- 81.15, N = 15 SE +/- 7.63, N = 3 SE +/- 7.41, N = 3 SE +/- 77.72, N = 3 SE +/- 1.88, N = 3 SE +/- 3.14, N = 3 SE +/- 5.50, N = 3 SE +/- 61.47, N = 15 SE +/- 46.38, N = 8 SE +/- 7.83, N = 3 SE +/- 3.03, N = 3 SE +/- 40.24, N = 15 SE +/- 207.30, N = 3 8502.71 7089.50 5538.75 10335.50 14203.87 7198.64 6770.97 8883.90 5329.07 4199.71 8314.29 11720.57 4793.66 4476.69 4610.01 6269.49 3888.16 13532.74 1. (CXX) g++ options: -O3 -rdynamic -lOpenCL Result Confidence
OpenBenchmarking.org GFLOPS, More Is Better clpeak OpenCL Test: Single-Precision Float RTX 2070 SUPER RTX 2060 SUPER GTX 980 Ti RTX 2080 SUPER TITAN RTX RTX 2070 GTX 1070 Ti RTX 2080 RTX 2060 GTX 1060 GTX 1080 GTX 1080 Ti GTX 1660 Ti GTX 980 GTX 1660 GTX 1070 GTX 970 RTX 2080 Ti 2K 4K 6K 8K 10K Min: 8142.21 / Avg: 8502.71 / Max: 9026.44 Min: 6660.52 / Avg: 7089.5 / Max: 7602.81 Min: 5101.9 / Avg: 5538.75 / Max: 5611.95 Min: 10140.95 / Avg: 10335.5 / Max: 10566.59 Min: 13053.45 / Avg: 14203.87 / Max: 15437.95 Min: 6674.06 / Avg: 7198.64 / Max: 7696.67 Min: 6760.98 / Avg: 6770.97 / Max: 6785.95 Min: 8869.2 / Avg: 8883.9 / Max: 8892.92 Min: 5220.89 / Avg: 5329.07 / Max: 5479.82 Min: 4196.49 / Avg: 4199.71 / Max: 4202.99 Min: 8308.48 / Avg: 8314.29 / Max: 8319.28 Min: 11712.35 / Avg: 11720.57 / Max: 11731.01 Min: 4537.68 / Avg: 4793.66 / Max: 5133.4 Min: 4152.15 / Avg: 4476.69 / Max: 4525.78 Min: 4597.89 / Avg: 4610.01 / Max: 4624.67 Min: 6265.3 / Avg: 6269.49 / Max: 6275.37 Min: 3498.29 / Avg: 3888.16 / Max: 3948.46 Min: 13125.63 / Avg: 13532.74 / Max: 13804.22 1. (CXX) g++ options: -O3 -rdynamic -lOpenCL
Darktable Darktable is an open-source photography / workflow application this will use any system-installed Darktable program or on Windows will automatically download the pre-built binary from the project. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Seconds, Fewer Is Better Darktable 2.6.0 Test: Server Room - Acceleration: OpenCL RTX 2070 SUPER RTX 2060 SUPER GTX 980 Ti RTX 2080 SUPER TITAN RTX RTX 2070 GTX 1070 Ti RTX 2080 RTX 2060 GTX 1060 GTX 1080 GTX 1080 Ti GTX 1660 Ti GTX 980 GTX 1660 GTX 1070 GTX 970 RTX 2080 Ti 0.711 1.422 2.133 2.844 3.555 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 8 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 4 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 0.80 0.75 1.51 0.79 0.74 0.75 1.17 0.80 0.83 1.28 1.09 1.05 1.15 3.10 1.18 1.11 3.16 0.75 Result Confidence
OpenBenchmarking.org Seconds, Fewer Is Better Darktable 2.6.0 Test: Server Room - Acceleration: OpenCL RTX 2070 SUPER RTX 2060 SUPER GTX 980 Ti RTX 2080 SUPER TITAN RTX RTX 2070 GTX 1070 Ti RTX 2080 RTX 2060 GTX 1060 GTX 1080 GTX 1080 Ti GTX 1660 Ti GTX 980 GTX 1660 GTX 1070 GTX 970 RTX 2080 Ti 2 4 6 8 10 Min: 0.8 / Avg: 0.8 / Max: 0.81 Min: 0.75 / Avg: 0.75 / Max: 0.76 Min: 1.5 / Avg: 1.51 / Max: 1.51 Min: 0.78 / Avg: 0.79 / Max: 0.8 Min: 0.74 / Avg: 0.74 / Max: 0.75 Min: 0.75 / Avg: 0.75 / Max: 0.75 Min: 1.16 / Avg: 1.17 / Max: 1.18 Min: 0.8 / Avg: 0.8 / Max: 0.81 Min: 0.83 / Avg: 0.83 / Max: 0.83 Min: 1.27 / Avg: 1.28 / Max: 1.3 Min: 1.08 / Avg: 1.09 / Max: 1.1 Min: 1.03 / Avg: 1.05 / Max: 1.09 Min: 1.15 / Avg: 1.15 / Max: 1.16 Min: 3.09 / Avg: 3.1 / Max: 3.11 Min: 1.18 / Avg: 1.18 / Max: 1.18 Min: 1.1 / Avg: 1.11 / Max: 1.12 Min: 3.14 / Avg: 3.16 / Max: 3.18 Min: 0.74 / Avg: 0.75 / Max: 0.75
ViennaCL ViennaCL is an open-source linear algebra library written in C++ and with support for OpenCL and OpenMP. This test profile uses ViennaCL OpenCL support and runs the included computational benchmark. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org GFLOPS, More Is Better ViennaCL 1.4.2 OpenCL LU Factorization RTX 2070 SUPER RTX 2060 SUPER GTX 980 Ti RTX 2080 SUPER TITAN RTX RTX 2070 GTX 1070 Ti RTX 2080 RTX 2060 GTX 1060 GTX 1080 GTX 1080 Ti GTX 1660 Ti GTX 980 GTX 1660 GTX 1070 GTX 970 RTX 2080 Ti 16 32 48 64 80 SE +/- 0.05, N = 3 SE +/- 0.06, N = 3 SE +/- 0.02, N = 3 SE +/- 0.26, N = 3 SE +/- 0.60, N = 3 SE +/- 0.03, N = 3 SE +/- 0.01, N = 3 SE +/- 0.07, N = 3 SE +/- 0.21, N = 3 SE +/- 0.05, N = 3 SE +/- 0.20, N = 3 SE +/- 0.31, N = 3 SE +/- 0.05, N = 3 SE +/- 0.04, N = 3 SE +/- 0.02, N = 3 SE +/- 0.03, N = 3 SE +/- 0.11, N = 3 SE +/- 0.72, N = 3 70.45 69.17 62.01 71.47 72.96 69.41 64.68 70.96 67.92 58.67 66.67 69.09 66.06 59.21 65.10 63.86 56.95 72.71 1. (CXX) g++ options: -rdynamic -lOpenCL Result Confidence
OpenBenchmarking.org GFLOPS, More Is Better ViennaCL 1.4.2 OpenCL LU Factorization RTX 2070 SUPER RTX 2060 SUPER GTX 980 Ti RTX 2080 SUPER TITAN RTX RTX 2070 GTX 1070 Ti RTX 2080 RTX 2060 GTX 1060 GTX 1080 GTX 1080 Ti GTX 1660 Ti GTX 980 GTX 1660 GTX 1070 GTX 970 RTX 2080 Ti 14 28 42 56 70 Min: 70.37 / Avg: 70.45 / Max: 70.53 Min: 69.1 / Avg: 69.17 / Max: 69.28 Min: 61.99 / Avg: 62.01 / Max: 62.05 Min: 70.96 / Avg: 71.47 / Max: 71.76 Min: 71.76 / Avg: 72.96 / Max: 73.65 Min: 69.35 / Avg: 69.41 / Max: 69.46 Min: 64.66 / Avg: 64.68 / Max: 64.71 Min: 70.86 / Avg: 70.96 / Max: 71.1 Min: 67.52 / Avg: 67.92 / Max: 68.21 Min: 58.58 / Avg: 58.67 / Max: 58.73 Min: 66.27 / Avg: 66.67 / Max: 66.89 Min: 68.47 / Avg: 69.09 / Max: 69.41 Min: 65.98 / Avg: 66.06 / Max: 66.16 Min: 59.14 / Avg: 59.21 / Max: 59.27 Min: 65.06 / Avg: 65.1 / Max: 65.14 Min: 63.8 / Avg: 63.86 / Max: 63.9 Min: 56.74 / Avg: 56.95 / Max: 57.11 Min: 71.26 / Avg: 72.71 / Max: 73.53 1. (CXX) g++ options: -rdynamic -lOpenCL
SHOC Scalable HeterOgeneous Computing The CUDA and OpenCL version of Vetter's Scalable HeterOgeneous Computing benchmark suite. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org GFLOPS, More Is Better SHOC Scalable HeterOgeneous Computing 2015-11-10 Target: OpenCL - Benchmark: FFT SP RTX 2070 SUPER RTX 2060 SUPER GTX 980 Ti RTX 2080 SUPER TITAN RTX RTX 2070 GTX 1070 Ti RTX 2080 RTX 2060 GTX 1060 GTX 1080 GTX 1080 Ti GTX 1660 Ti GTX 980 GTX 1660 GTX 1070 GTX 970 RTX 2080 Ti 300 600 900 1200 1500 SE +/- 0.27, N = 3 SE +/- 3.09, N = 3 SE +/- 3.01, N = 3 SE +/- 0.78, N = 3 SE +/- 1.38, N = 3 SE +/- 2.90, N = 3 SE +/- 0.19, N = 3 SE +/- 0.39, N = 3 SE +/- 0.56, N = 3 SE +/- 3.50, N = 7 SE +/- 3.58, N = 3 SE +/- 1.06, N = 3 SE +/- 1.57, N = 3 SE +/- 1.09, N = 3 SE +/- 0.27, N = 3 SE +/- 6.42, N = 4 SE +/- 0.48, N = 3 SE +/- 2.79, N = 3 1088.17 971.24 725.98 1203.57 1578.29 976.78 525.89 1100.00 818.44 326.68 614.69 982.23 665.66 458.35 452.89 478.54 411.29 1485.73 1. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -lmpi_cxx -lmpi Result Confidence
OpenBenchmarking.org GFLOPS, More Is Better SHOC Scalable HeterOgeneous Computing 2015-11-10 Target: OpenCL - Benchmark: FFT SP RTX 2070 SUPER RTX 2060 SUPER GTX 980 Ti RTX 2080 SUPER TITAN RTX RTX 2070 GTX 1070 Ti RTX 2080 RTX 2060 GTX 1060 GTX 1080 GTX 1080 Ti GTX 1660 Ti GTX 980 GTX 1660 GTX 1070 GTX 970 RTX 2080 Ti 300 600 900 1200 1500 Min: 1087.63 / Avg: 1088.17 / Max: 1088.49 Min: 968.1 / Avg: 971.24 / Max: 977.42 Min: 719.96 / Avg: 725.98 / Max: 729.08 Min: 1202.34 / Avg: 1203.57 / Max: 1205.01 Min: 1576.6 / Avg: 1578.29 / Max: 1581.03 Min: 973.65 / Avg: 976.78 / Max: 982.57 Min: 525.56 / Avg: 525.89 / Max: 526.22 Min: 1099.29 / Avg: 1100 / Max: 1100.65 Min: 817.33 / Avg: 818.44 / Max: 819.12 Min: 306.72 / Avg: 326.68 / Max: 334.81 Min: 607.91 / Avg: 614.69 / Max: 620.06 Min: 980.36 / Avg: 982.23 / Max: 984.05 Min: 662.55 / Avg: 665.66 / Max: 667.51 Min: 457.19 / Avg: 458.35 / Max: 460.54 Min: 452.56 / Avg: 452.89 / Max: 453.44 Min: 459.83 / Avg: 478.54 / Max: 488.17 Min: 410.33 / Avg: 411.29 / Max: 411.91 Min: 1480.57 / Avg: 1485.73 / Max: 1490.16 1. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -lmpi_cxx -lmpi
clpeak Clpeak is designed to test the peak capabilities of OpenCL devices. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org GBPS, More Is Better clpeak OpenCL Test: Global Memory Bandwidth RTX 2070 SUPER RTX 2060 SUPER GTX 980 Ti RTX 2080 SUPER TITAN RTX RTX 2070 GTX 1070 Ti RTX 2080 RTX 2060 GTX 1060 GTX 1080 GTX 1080 Ti GTX 1660 Ti GTX 980 GTX 1660 GTX 1070 GTX 970 RTX 2080 Ti 110 220 330 440 550 SE +/- 0.33, N = 3 SE +/- 0.11, N = 3 SE +/- 0.52, N = 3 SE +/- 0.08, N = 3 SE +/- 0.66, N = 3 SE +/- 0.07, N = 3 SE +/- 0.00, N = 3 SE +/- 0.22, N = 3 SE +/- 0.24, N = 3 SE +/- 0.06, N = 3 SE +/- 0.09, N = 3 SE +/- 0.71, N = 3 SE +/- 0.17, N = 3 SE +/- 0.03, N = 3 SE +/- 0.00, N = 3 SE +/- 0.18, N = 3 SE +/- 0.06, N = 3 SE +/- 0.44, N = 3 369.11 367.92 263.22 405.00 528.89 368.96 197.26 368.47 275.86 146.62 222.09 328.90 234.67 164.25 157.60 196.47 143.48 506.33 1. (CXX) g++ options: -O3 -rdynamic -lOpenCL Result Confidence
OpenBenchmarking.org GBPS, More Is Better clpeak OpenCL Test: Global Memory Bandwidth RTX 2070 SUPER RTX 2060 SUPER GTX 980 Ti RTX 2080 SUPER TITAN RTX RTX 2070 GTX 1070 Ti RTX 2080 RTX 2060 GTX 1060 GTX 1080 GTX 1080 Ti GTX 1660 Ti GTX 980 GTX 1660 GTX 1070 GTX 970 RTX 2080 Ti 90 180 270 360 450 Min: 368.45 / Avg: 369.11 / Max: 369.46 Min: 367.71 / Avg: 367.92 / Max: 368.07 Min: 262.17 / Avg: 263.22 / Max: 263.74 Min: 404.89 / Avg: 405 / Max: 405.16 Min: 527.56 / Avg: 528.89 / Max: 529.56 Min: 368.88 / Avg: 368.96 / Max: 369.1 Min: 197.25 / Avg: 197.26 / Max: 197.26 Min: 368.14 / Avg: 368.47 / Max: 368.89 Min: 275.39 / Avg: 275.86 / Max: 276.14 Min: 146.5 / Avg: 146.62 / Max: 146.69 Min: 221.97 / Avg: 222.09 / Max: 222.26 Min: 327.62 / Avg: 328.9 / Max: 330.06 Min: 234.41 / Avg: 234.67 / Max: 234.99 Min: 164.2 / Avg: 164.25 / Max: 164.28 Min: 157.6 / Avg: 157.6 / Max: 157.61 Min: 196.28 / Avg: 196.47 / Max: 196.83 Min: 143.36 / Avg: 143.48 / Max: 143.56 Min: 505.86 / Avg: 506.33 / Max: 507.2 1. (CXX) g++ options: -O3 -rdynamic -lOpenCL
SHOC Scalable HeterOgeneous Computing The CUDA and OpenCL version of Vetter's Scalable HeterOgeneous Computing benchmark suite. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org GHash/s, More Is Better SHOC Scalable HeterOgeneous Computing 2015-11-10 Target: OpenCL - Benchmark: MD5 Hash RTX 2070 SUPER RTX 2060 SUPER GTX 980 Ti RTX 2080 SUPER TITAN RTX RTX 2070 GTX 1070 Ti RTX 2080 RTX 2060 GTX 1060 GTX 1080 GTX 1080 Ti GTX 1660 Ti GTX 980 GTX 1660 GTX 1070 GTX 970 RTX 2080 Ti 8 16 24 32 40 SE +/- 0.05, N = 3 SE +/- 0.02, N = 3 SE +/- 0.00, N = 3 SE +/- 0.02, N = 3 SE +/- 0.06, N = 3 SE +/- 0.03, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 SE +/- 0.03, N = 3 SE +/- 0.00, N = 3 SE +/- 0.02, N = 3 SE +/- 0.04, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.02, N = 3 SE +/- 0.00, N = 3 SE +/- 0.12, N = 3 21.78 18.22 9.22 26.56 36.39 18.77 11.70 24.07 16.04 7.26 14.25 19.72 12.98 7.49 11.87 10.61 6.50 34.91 1. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -lmpi_cxx -lmpi Result Confidence
OpenBenchmarking.org GHash/s, More Is Better SHOC Scalable HeterOgeneous Computing 2015-11-10 Target: OpenCL - Benchmark: MD5 Hash RTX 2070 SUPER RTX 2060 SUPER GTX 980 Ti RTX 2080 SUPER TITAN RTX RTX 2070 GTX 1070 Ti RTX 2080 RTX 2060 GTX 1060 GTX 1080 GTX 1080 Ti GTX 1660 Ti GTX 980 GTX 1660 GTX 1070 GTX 970 RTX 2080 Ti 8 16 24 32 40 Min: 21.72 / Avg: 21.78 / Max: 21.89 Min: 18.18 / Avg: 18.22 / Max: 18.24 Min: 9.22 / Avg: 9.22 / Max: 9.23 Min: 26.52 / Avg: 26.56 / Max: 26.57 Min: 36.32 / Avg: 36.39 / Max: 36.51 Min: 18.71 / Avg: 18.77 / Max: 18.81 Min: 11.69 / Avg: 11.7 / Max: 11.7 Min: 24.05 / Avg: 24.07 / Max: 24.09 Min: 16 / Avg: 16.04 / Max: 16.09 Min: 7.26 / Avg: 7.26 / Max: 7.27 Min: 14.22 / Avg: 14.25 / Max: 14.3 Min: 19.66 / Avg: 19.72 / Max: 19.8 Min: 12.97 / Avg: 12.98 / Max: 12.98 Min: 7.49 / Avg: 7.49 / Max: 7.5 Min: 11.87 / Avg: 11.87 / Max: 11.88 Min: 10.59 / Avg: 10.61 / Max: 10.65 Min: 6.5 / Avg: 6.5 / Max: 6.5 Min: 34.68 / Avg: 34.91 / Max: 35.05 1. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -lmpi_cxx -lmpi
System Power Consumption Monitor OpenBenchmarking.org Watts System Power Consumption Monitor Phoronix Test Suite System Monitoring RTX 2070 SUPER RTX 2060 SUPER GTX 980 Ti RTX 2080 SUPER TITAN RTX RTX 2070 GTX 1070 Ti RTX 2080 RTX 2060 GTX 1060 GTX 1080 GTX 1080 Ti GTX 1660 Ti GTX 980 GTX 1660 GTX 1070 GTX 970 RTX 2080 Ti 70 140 210 280 350 Min: 45.5 / Avg: 134.05 / Max: 323.3 Min: 45.4 / Avg: 158.95 / Max: 312 Min: 53.6 / Avg: 199.07 / Max: 370.3 Min: 46 / Avg: 173.42 / Max: 330.5 Min: 50.6 / Avg: 227.86 / Max: 371.4 Min: 46 / Avg: 164.53 / Max: 321.3 Min: 48.6 / Avg: 131.89 / Max: 259.9 Min: 47.5 / Avg: 181.54 / Max: 342.9 Min: 46.1 / Avg: 153.75 / Max: 303.8 Min: 44.3 / Avg: 128.45 / Max: 269.5 Min: 44.9 / Avg: 162.99 / Max: 328.3 Min: 49.6 / Avg: 207.86 / Max: 380 Min: 45.4 / Avg: 127.55 / Max: 273.9 Min: 49.8 / Avg: 167.77 / Max: 329.4 Min: 43.1 / Avg: 115.15 / Max: 262.4 Min: 43.8 / Avg: 150.54 / Max: 286.9 Min: 48.8 / Avg: 157.71 / Max: 306.3 Min: 49.7 / Avg: 227.4 / Max: 374
GPU Temperature Monitor OpenBenchmarking.org Celsius GPU Temperature Monitor Phoronix Test Suite System Monitoring RTX 2070 SUPER RTX 2060 SUPER GTX 980 Ti RTX 2080 SUPER TITAN RTX RTX 2070 GTX 1070 Ti RTX 2080 RTX 2060 GTX 1060 GTX 1080 GTX 1080 Ti GTX 1660 Ti GTX 980 GTX 1660 GTX 1070 GTX 970 RTX 2080 Ti 16 32 48 64 80 Min: 27 / Avg: 43.67 / Max: 69 Min: 29 / Avg: 54.33 / Max: 75 Min: 36 / Avg: 71.62 / Max: 85 Min: 34 / Avg: 53.35 / Max: 70 Min: 37 / Avg: 62.01 / Max: 80 Min: 28 / Avg: 58.64 / Max: 77 Min: 39 / Avg: 48.41 / Max: 61 Min: 30 / Avg: 66.02 / Max: 83 Min: 32 / Avg: 57.94 / Max: 72 Min: 30 / Avg: 58.15 / Max: 74 Min: 30 / Avg: 63.66 / Max: 77 Min: 34 / Avg: 67.92 / Max: 84 Min: 30 / Avg: 50.73 / Max: 65 Min: 29 / Avg: 68.53 / Max: 81 Min: 28 / Avg: 56.71 / Max: 77 Min: 28 / Avg: 61.94 / Max: 76 Min: 28 / Avg: 52.34 / Max: 68 Min: 31 / Avg: 60.94 / Max: 77
OctaneBench OpenBenchmarking.org Watts, Fewer Is Better OctaneBench 4.00c System Power Consumption Monitor RTX 2070 SUPER RTX 2060 SUPER GTX 980 Ti RTX 2080 SUPER TITAN RTX RTX 2070 GTX 1070 Ti RTX 2080 RTX 2060 GTX 1060 GTX 1080 GTX 1080 Ti GTX 1660 Ti GTX 980 GTX 1660 GTX 1070 GTX 970 RTX 2080 Ti 60 120 180 240 300 Min: 49 / Avg: 211.57 / Max: 245.6 Min: 46.5 / Avg: 210.53 / Max: 232.6 Min: 128.3 / Avg: 220.62 / Max: 240 Min: 47.8 / Avg: 225.1 / Max: 261.8 Min: 55.3 / Avg: 326.69 / Max: 357.7 Min: 47.1 / Avg: 215.17 / Max: 242.1 Min: 52.2 / Avg: 132.45 / Max: 182.7 Min: 50 / Avg: 239.21 / Max: 278.1 Min: 49.8 / Avg: 188.5 / Max: 218.2 Min: 44.9 / Avg: 120.33 / Max: 135.2 Min: 48.3 / Avg: 167.77 / Max: 228.3 Min: 130.6 / Avg: 236.94 / Max: 265 Min: 47.1 / Avg: 145.79 / Max: 161.1 Min: 53.6 / Avg: 178.66 / Max: 203.2 Min: 46.3 / Avg: 127.11 / Max: 144.7 Min: 86 / Avg: 157.88 / Max: 173.8 Min: 50.8 / Avg: 160.22 / Max: 180 Min: 51.7 / Avg: 322.94 / Max: 355.5
OpenBenchmarking.org Score Per Watt, More Is Better OctaneBench 4.00c Total Score RTX 2070 SUPER RTX 2060 SUPER GTX 980 Ti RTX 2080 SUPER TITAN RTX RTX 2070 GTX 1070 Ti RTX 2080 RTX 2060 GTX 1060 GTX 1080 GTX 1080 Ti GTX 1660 Ti GTX 980 GTX 1660 GTX 1070 GTX 970 RTX 2080 Ti 0.2408 0.4816 0.7224 0.9632 1.204 1.04 0.97 0.64 1.04 0.99 0.96 1.07 0.93 0.87 0.76 0.88 0.89 0.91 0.61 0.93 0.84 0.60 0.96
LeelaChessZero OpenBenchmarking.org Watts, Fewer Is Better LeelaChessZero 0.22.0 System Power Consumption Monitor RTX 2070 SUPER RTX 2060 SUPER GTX 980 Ti RTX 2080 SUPER TITAN RTX RTX 2070 GTX 1070 Ti RTX 2080 RTX 2060 GTX 1060 GTX 1080 GTX 1080 Ti GTX 1660 Ti GTX 980 GTX 1660 GTX 1070 GTX 970 70 140 210 280 350 Min: 47.2 / Avg: 178.69 / Max: 276 Min: 45.5 / Avg: 151.83 / Max: 241.9 Min: 59.1 / Avg: 216.14 / Max: 319.4 Min: 47.5 / Avg: 170.9 / Max: 315 Min: 53.3 / Avg: 197.7 / Max: 371.4 Min: 48.6 / Avg: 172.95 / Max: 253.7 Min: 52 / Avg: 128.59 / Max: 197.7 Min: 52.8 / Avg: 175.13 / Max: 286.6 Min: 49.1 / Avg: 147.07 / Max: 231.4 Min: 47.2 / Avg: 138.37 / Max: 187.2 Min: 48.8 / Avg: 161.47 / Max: 252.9 Min: 106.6 / Avg: 215.46 / Max: 320.5 Min: 47.9 / Avg: 134.26 / Max: 195.9 Min: 51.8 / Avg: 153.94 / Max: 247.5 Min: 46.5 / Avg: 118.46 / Max: 180.4 Min: 71.9 / Avg: 152.4 / Max: 214.7 Min: 82.3 / Avg: 164.63 / Max: 252.9
OpenBenchmarking.org Nodes Per Second Per Watt, More Is Better LeelaChessZero 0.22.0 Backend: OpenCL RTX 2070 SUPER RTX 2060 SUPER GTX 980 Ti RTX 2080 SUPER TITAN RTX RTX 2070 GTX 1070 Ti RTX 2080 RTX 2060 GTX 1060 GTX 1080 GTX 1080 Ti GTX 1660 Ti GTX 980 GTX 1660 GTX 1070 GTX 970 RTX 2080 Ti 4 8 12 16 20 8.98 6.57 2.16 12.32 15.81 5.78 5.86 10.73 4.79 1.90 7.10 8.75 3.13 1.83 2.84 4.21 1.26 14.00
PlaidML OpenBenchmarking.org Watts, Fewer Is Better PlaidML System Power Consumption Monitor RTX 2070 SUPER RTX 2060 SUPER GTX 980 Ti RTX 2080 SUPER TITAN RTX RTX 2070 GTX 1070 Ti RTX 2080 RTX 2060 GTX 1060 GTX 1080 GTX 1080 Ti GTX 1660 Ti GTX 980 GTX 1660 GTX 1070 GTX 970 RTX 2080 Ti 60 120 180 240 300 Min: 47.5 / Avg: 199.98 / Max: 276.8 Min: 55 / Avg: 193.52 / Max: 240.6 Min: 119.7 / Avg: 273.57 / Max: 330.8 Min: 49.5 / Avg: 224.18 / Max: 302.6 Min: 53.2 / Avg: 260.22 / Max: 361.7 Min: 49.7 / Avg: 197.21 / Max: 252.5 Min: 52.4 / Avg: 180.41 / Max: 207.7 Min: 49.9 / Avg: 230.45 / Max: 288.2 Min: 50.1 / Avg: 192.21 / Max: 230.7 Min: 45.1 / Avg: 170.04 / Max: 188.8 Min: 89.9 / Avg: 209.47 / Max: 253.5 Min: 55.7 / Avg: 245.95 / Max: 321.1 Min: 48.3 / Avg: 167.7 / Max: 196.3 Min: 55.7 / Avg: 208.34 / Max: 246.7 Min: 46 / Avg: 160.67 / Max: 185.8 Min: 84.2 / Avg: 180.68 / Max: 209.8 Min: 75.4 / Avg: 201.26 / Max: 220.7 Min: 52.9 / Avg: 251.39 / Max: 354
OpenBenchmarking.org FPS Per Watt, More Is Better PlaidML FP16: No - Mode: Inference - Network: VGG19 - Device: OpenCL RTX 2070 SUPER RTX 2060 SUPER GTX 980 Ti RTX 2080 SUPER TITAN RTX RTX 2070 GTX 1070 Ti RTX 2080 RTX 2060 GTX 1060 GTX 1080 GTX 1080 Ti GTX 1660 Ti GTX 980 GTX 1660 GTX 1070 GTX 970 RTX 2080 Ti 0.1688 0.3376 0.5064 0.6752 0.844 0.61 0.52 0.25 0.64 0.75 0.53 0.50 0.56 0.46 0.32 0.48 0.56 0.44 0.26 0.42 0.43 0.24 0.74
OpenBenchmarking.org Watts, Fewer Is Better PlaidML System Power Consumption Monitor RTX 2070 SUPER RTX 2060 SUPER GTX 980 Ti RTX 2080 SUPER TITAN RTX RTX 2070 GTX 1070 Ti RTX 2080 RTX 2060 GTX 1060 GTX 1080 GTX 1080 Ti GTX 1660 Ti GTX 980 GTX 1660 GTX 1070 GTX 970 RTX 2080 Ti 60 120 180 240 300 Min: 47.2 / Avg: 191.71 / Max: 276.3 Min: 53.3 / Avg: 181.51 / Max: 239.5 Min: 56.5 / Avg: 270.73 / Max: 328.7 Min: 47.7 / Avg: 218.91 / Max: 299.1 Min: 52.4 / Avg: 239.94 / Max: 363 Min: 48.4 / Avg: 193.79 / Max: 250.6 Min: 52.3 / Avg: 169.99 / Max: 205.7 Min: 48.9 / Avg: 201.23 / Max: 285.7 Min: 48.4 / Avg: 179.22 / Max: 228.5 Min: 69.4 / Avg: 166.46 / Max: 190 Min: 46.2 / Avg: 209.24 / Max: 254.3 Min: 51.8 / Avg: 234.29 / Max: 318.4 Min: 46.4 / Avg: 163.81 / Max: 195.7 Min: 90.4 / Avg: 213.83 / Max: 251.4 Min: 45.6 / Avg: 146.27 / Max: 182 Min: 50 / Avg: 172.78 / Max: 208.8 Min: 94.5 / Avg: 195.88 / Max: 219.3 Min: 52.7 / Avg: 239.16 / Max: 354.3
OpenBenchmarking.org FPS Per Watt, More Is Better PlaidML FP16: No - Mode: Inference - Network: VGG16 - Device: OpenCL RTX 2070 SUPER RTX 2060 SUPER GTX 980 Ti RTX 2080 SUPER TITAN RTX RTX 2070 GTX 1070 Ti RTX 2080 RTX 2060 GTX 1060 GTX 1080 GTX 1080 Ti GTX 1660 Ti GTX 980 GTX 1660 GTX 1070 GTX 970 RTX 2080 Ti 0.2318 0.4636 0.6954 0.9272 1.159 0.81 0.71 0.32 0.82 1.03 0.68 0.67 0.82 0.62 0.42 0.61 0.75 0.56 0.32 0.58 0.56 0.31 0.98
OpenBenchmarking.org Watts, Fewer Is Better PlaidML System Power Consumption Monitor RTX 2070 SUPER RTX 2060 SUPER GTX 980 Ti RTX 2080 SUPER GTX 1070 Ti RTX 2080 RTX 2060 GTX 1060 GTX 1080 GTX 1660 Ti GTX 980 GTX 1660 GTX 1070 GTX 970 RTX 2080 Ti 50 100 150 200 250 Min: 49.2 / Avg: 136.18 / Max: 192.6 Min: 54.9 / Avg: 136.39 / Max: 187.2 Min: 57.1 / Avg: 192.1 / Max: 249.1 Min: 51.8 / Avg: 130.6 / Max: 207.8 Min: 52.4 / Avg: 128.8 / Max: 152 Min: 56.5 / Avg: 138.96 / Max: 215.1 Min: 49.2 / Avg: 125.65 / Max: 186.5 Min: 46.3 / Avg: 122.88 / Max: 159.6 Min: 48.5 / Avg: 142.23 / Max: 208.8 Min: 46.6 / Avg: 100.43 / Max: 150.5 Min: 100 / Avg: 162.49 / Max: 218.7 Min: 46.3 / Avg: 96.5 / Max: 135.8 Min: 50.4 / Avg: 132.86 / Max: 187.3 Min: 94.4 / Avg: 160.18 / Max: 203.4 Min: 52.6 / Avg: 166.27 / Max: 275.3
OpenBenchmarking.org FPS Per Watt, More Is Better PlaidML FP16: No - Mode: Inference - Network: IMDB LSTM - Device: OpenCL RTX 2070 SUPER RTX 2060 SUPER GTX 980 Ti RTX 2080 SUPER TITAN RTX RTX 2070 GTX 1070 Ti RTX 2080 RTX 2060 GTX 1060 GTX 1080 GTX 1080 Ti GTX 1660 Ti GTX 980 GTX 1660 GTX 1070 GTX 970 RTX 2080 Ti 1.1453 2.2906 3.4359 4.5812 5.7265 3.67 3.23 1.41 4.52 5.09 3.68 2.59 3.95 3.10 1.83 2.81 3.00 3.14 1.43 2.98 2.37 1.28 4.56
OpenBenchmarking.org Watts, Fewer Is Better PlaidML System Power Consumption Monitor RTX 2070 SUPER RTX 2060 SUPER GTX 980 Ti RTX 2080 SUPER TITAN RTX RTX 2070 GTX 1070 Ti RTX 2080 RTX 2060 GTX 1060 GTX 1080 GTX 1080 Ti GTX 1660 Ti GTX 980 GTX 1660 GTX 1070 GTX 970 60 120 180 240 300 Min: 46.8 / Avg: 145.98 / Max: 249.6 Min: 55.4 / Avg: 144.71 / Max: 231.4 Min: 129.1 / Avg: 233.7 / Max: 292 Min: 49.4 / Avg: 162.94 / Max: 270.3 Min: 52.7 / Avg: 128.84 / Max: 167.9 Min: 47.5 / Avg: 122.1 / Max: 239.9 Min: 52.2 / Avg: 140.17 / Max: 177.3 Min: 52 / Avg: 137.63 / Max: 231.8 Min: 48.6 / Avg: 147.64 / Max: 221.8 Min: 45.9 / Avg: 132.6 / Max: 182.3 Min: 48.4 / Avg: 149.71 / Max: 246.6 Min: 56.4 / Avg: 186.43 / Max: 312.7 Min: 47.9 / Avg: 141.14 / Max: 182.8 Min: 53 / Avg: 176.69 / Max: 244.6 Min: 46.3 / Avg: 119.8 / Max: 159.7 Min: 89.6 / Avg: 153.55 / Max: 208.4 Min: 83.3 / Avg: 172.91 / Max: 233.2
OpenBenchmarking.org FPS Per Watt, More Is Better PlaidML FP16: No - Mode: Inference - Network: ResNet 50 - Device: OpenCL RTX 2070 SUPER RTX 2060 SUPER GTX 980 Ti RTX 2080 SUPER TITAN RTX RTX 2070 GTX 1070 Ti RTX 2080 RTX 2060 GTX 1060 GTX 1080 GTX 1080 Ti GTX 1660 Ti GTX 980 GTX 1660 GTX 1070 GTX 970 RTX 2080 Ti 1.1318 2.2636 3.3954 4.5272 5.659 2.89 2.59 1.06 3.18 5.03 3.09 2.10 3.21 2.16 1.48 2.25 2.66 1.84 1.15 1.90 1.80 1.05 3.70
OpenBenchmarking.org Watts, Fewer Is Better PlaidML System Power Consumption Monitor RTX 2070 SUPER RTX 2060 SUPER GTX 980 Ti RTX 2080 SUPER TITAN RTX RTX 2070 GTX 1070 Ti RTX 2080 RTX 2060 GTX 1060 GTX 1080 GTX 1080 Ti GTX 1660 Ti GTX 980 GTX 1660 GTX 1070 GTX 970 RTX 2080 Ti 60 120 180 240 300 Min: 49.5 / Avg: 161.34 / Max: 234.9 Min: 54.4 / Avg: 162.79 / Max: 223.8 Min: 126.5 / Avg: 220.09 / Max: 281.6 Min: 49.6 / Avg: 170.73 / Max: 255.1 Min: 56.2 / Avg: 178.56 / Max: 327.6 Min: 49.8 / Avg: 167.7 / Max: 230.4 Min: 51.1 / Avg: 141.76 / Max: 172.5 Min: 49.4 / Avg: 176.08 / Max: 254.9 Min: 47.6 / Avg: 150.66 / Max: 214.3 Min: 46.9 / Avg: 150.12 / Max: 180 Min: 84.7 / Avg: 196.13 / Max: 242.5 Min: 128 / Avg: 191.53 / Max: 304 Min: 46.3 / Avg: 136.65 / Max: 177.5 Min: 56.7 / Avg: 188.31 / Max: 242.7 Min: 46.3 / Avg: 123.06 / Max: 152.7 Min: 84.3 / Avg: 149.15 / Max: 206.1 Min: 81.4 / Avg: 182.54 / Max: 219.9 Min: 51.8 / Avg: 206.66 / Max: 321.6
OpenBenchmarking.org FPS Per Watt, More Is Better PlaidML FP16: No - Mode: Inference - Network: Inception V3 - Device: OpenCL RTX 2070 SUPER RTX 2060 SUPER GTX 980 Ti RTX 2080 SUPER TITAN RTX RTX 2070 GTX 1070 Ti RTX 2080 RTX 2060 GTX 1060 GTX 1080 GTX 1080 Ti GTX 1660 Ti GTX 980 GTX 1660 GTX 1070 GTX 970 RTX 2080 Ti 0.4388 0.8776 1.3164 1.7552 2.194 1.34 1.23 0.61 1.52 1.95 1.18 1.08 1.36 1.11 0.70 0.94 1.34 1.02 0.56 0.95 0.99 0.52 1.66
OpenBenchmarking.org FPS Per Watt, More Is Better PlaidML FP16: No - Mode: Inference - Network: Mobilenet - Device: OpenCL RTX 2070 SUPER RTX 2060 SUPER GTX 980 Ti RTX 2080 SUPER TITAN RTX RTX 2070 GTX 1070 Ti RTX 2080 RTX 2060 GTX 1060 GTX 1080 GTX 1080 Ti GTX 1660 Ti GTX 980 GTX 1660 GTX 1070 GTX 970 RTX 2080 Ti 6 12 18 24 30 19.70 12.98 6.64 16.60 23.23 14.84 11.30 14.16 11.67 7.59 9.35 10.22 11.20 5.53 9.56 9.65 5.20 22.63
OpenBenchmarking.org Watts, Fewer Is Better PlaidML System Power Consumption Monitor RTX 2070 SUPER RTX 2060 SUPER GTX 980 Ti RTX 2080 SUPER TITAN RTX RTX 2070 GTX 1070 Ti RTX 2080 RTX 2060 GTX 1060 GTX 1080 GTX 1080 Ti GTX 1660 Ti GTX 980 GTX 1660 GTX 1070 GTX 970 RTX 2080 Ti 60 120 180 240 300 Min: 47.2 / Avg: 198.27 / Max: 271.7 Min: 57.1 / Avg: 209.61 / Max: 237.5 Min: 71.2 / Avg: 244.52 / Max: 316.6 Min: 49.1 / Avg: 194.92 / Max: 278.5 Min: 52.8 / Avg: 227.24 / Max: 356.3 Min: 48.7 / Avg: 189.06 / Max: 250.5 Min: 51.9 / Avg: 158.16 / Max: 196.1 Min: 52.6 / Avg: 181.66 / Max: 277.7 Min: 48.9 / Avg: 179.62 / Max: 228 Min: 45.9 / Avg: 157.15 / Max: 187.3 Min: 91.2 / Avg: 194.23 / Max: 252.2 Min: 120.6 / Avg: 236.48 / Max: 318.6 Min: 48.2 / Avg: 154.23 / Max: 191.6 Min: 53.3 / Avg: 201.25 / Max: 246.9 Min: 45.5 / Avg: 136.67 / Max: 171.6 Min: 70.7 / Avg: 170.23 / Max: 208.9 Min: 89.6 / Avg: 193.7 / Max: 220.3 Min: 52.9 / Avg: 210.77 / Max: 350.6
OpenBenchmarking.org FPS Per Watt, More Is Better PlaidML FP16: Yes - Mode: Inference - Network: VGG19 - Device: OpenCL RTX 2070 SUPER RTX 2060 SUPER GTX 980 Ti RTX 2080 SUPER TITAN RTX RTX 2070 GTX 1070 Ti RTX 2080 RTX 2060 GTX 1060 GTX 1080 GTX 1080 Ti GTX 1660 Ti GTX 980 GTX 1660 GTX 1070 GTX 970 RTX 2080 Ti 0.1643 0.3286 0.4929 0.6572 0.8215 0.49 0.39 0.23 0.59 0.71 0.44 0.46 0.58 0.40 0.28 0.43 0.49 0.38 0.22 0.38 0.37 0.20 0.73
OpenBenchmarking.org Watts, Fewer Is Better PlaidML System Power Consumption Monitor RTX 2070 SUPER RTX 2060 SUPER GTX 980 Ti RTX 2080 SUPER TITAN RTX RTX 2070 GTX 1070 Ti RTX 2080 RTX 2060 GTX 1060 GTX 1080 GTX 1080 Ti GTX 1660 Ti GTX 980 GTX 1660 GTX 1070 GTX 970 RTX 2080 Ti 60 120 180 240 300 Min: 46.7 / Avg: 187.65 / Max: 267.6 Min: 54 / Avg: 187.95 / Max: 233.7 Min: 55.1 / Avg: 244.29 / Max: 316.2 Min: 49.4 / Avg: 181.31 / Max: 274.6 Min: 53.8 / Avg: 216.91 / Max: 353.5 Min: 48.1 / Avg: 174.02 / Max: 249.3 Min: 95.2 / Avg: 160.1 / Max: 191.4 Min: 54.1 / Avg: 173.35 / Max: 273.1 Min: 48.1 / Avg: 163.79 / Max: 226.4 Min: 45.8 / Avg: 152.31 / Max: 187.6 Min: 88.2 / Avg: 189.28 / Max: 251.8 Min: 118 / Avg: 235.58 / Max: 316.5 Min: 47.3 / Avg: 151.58 / Max: 191.5 Min: 69.1 / Avg: 196.2 / Max: 247.2 Min: 45.6 / Avg: 137.8 / Max: 169.2 Min: 47.7 / Avg: 162.2 / Max: 207.3 Min: 51.5 / Avg: 184.27 / Max: 233.4 Min: 52.7 / Avg: 188.04 / Max: 345.4
OpenBenchmarking.org FPS Per Watt, More Is Better PlaidML FP16: Yes - Mode: Inference - Network: VGG16 - Device: OpenCL RTX 2070 SUPER RTX 2060 SUPER GTX 980 Ti RTX 2080 SUPER TITAN RTX RTX 2070 GTX 1070 Ti RTX 2080 RTX 2060 GTX 1060 GTX 1080 GTX 1080 Ti GTX 1660 Ti GTX 980 GTX 1660 GTX 1070 GTX 970 RTX 2080 Ti 0.234 0.468 0.702 0.936 1.17 0.66 0.55 0.29 0.80 0.94 0.61 0.57 0.77 0.55 0.37 0.56 0.62 0.48 0.28 0.48 0.49 0.27 1.04
OpenBenchmarking.org Watts, Fewer Is Better PlaidML System Power Consumption Monitor RTX 2070 SUPER RTX 2060 SUPER GTX 980 Ti RTX 2080 SUPER TITAN RTX RTX 2070 GTX 1070 Ti RTX 2080 RTX 2060 GTX 1060 GTX 1080 GTX 1080 Ti GTX 1660 Ti GTX 980 GTX 1660 GTX 1070 GTX 970 RTX 2080 Ti 50 100 150 200 250 Min: 49.1 / Avg: 124.58 / Max: 203.3 Min: 55.8 / Avg: 142.16 / Max: 204.9 Min: 57 / Avg: 191.08 / Max: 247.4 Min: 48.8 / Avg: 141.86 / Max: 214.3 Min: 52.7 / Avg: 173.29 / Max: 277.5 Min: 51.5 / Avg: 138.71 / Max: 203.8 Min: 53.5 / Avg: 128.35 / Max: 157.6 Min: 51.5 / Avg: 146.49 / Max: 216.5 Min: 49 / Avg: 134.34 / Max: 190.3 Min: 45.7 / Avg: 125.77 / Max: 157.6 Min: 49.1 / Avg: 151.63 / Max: 200.9 Min: 109.8 / Avg: 203.83 / Max: 255.3 Min: 48.2 / Avg: 115.16 / Max: 152 Min: 53.5 / Avg: 157.67 / Max: 213.1 Min: 45.8 / Avg: 106.92 / Max: 138.1 Min: 48.3 / Avg: 135.38 / Max: 188.6 Min: 52.1 / Avg: 148.78 / Max: 190.2 Min: 52.4 / Avg: 173.16 / Max: 273
OpenBenchmarking.org FPS Per Watt, More Is Better PlaidML FP16: Yes - Mode: Inference - Network: DenseNet 201 - Device: OpenCL RTX 2070 SUPER RTX 2060 SUPER GTX 980 Ti RTX 2080 SUPER TITAN RTX RTX 2070 GTX 1070 Ti RTX 2080 RTX 2060 GTX 1060 GTX 1080 GTX 1080 Ti GTX 1660 Ti GTX 980 GTX 1660 GTX 1070 GTX 970 RTX 2080 Ti 0.3443 0.6886 1.0329 1.3772 1.7215 1.53 1.26 0.58 1.41 1.52 1.27 1.01 1.29 1.15 0.72 0.95 0.94 0.99 0.59 0.96 0.94 0.54 1.47
OpenBenchmarking.org Watts, Fewer Is Better PlaidML System Power Consumption Monitor RTX 2070 SUPER RTX 2060 SUPER GTX 980 Ti RTX 2080 SUPER TITAN RTX RTX 2070 GTX 1070 Ti RTX 2080 RTX 2060 GTX 1060 GTX 1080 GTX 1080 Ti GTX 1660 Ti GTX 980 GTX 1660 GTX 1070 GTX 970 RTX 2080 Ti 60 120 180 240 300 Min: 46.5 / Avg: 184.51 / Max: 249.7 Min: 54.2 / Avg: 192.58 / Max: 235.4 Min: 124.3 / Avg: 237.03 / Max: 284.6 Min: 46.7 / Avg: 204.84 / Max: 277 Min: 51.3 / Avg: 235.38 / Max: 341.7 Min: 48 / Avg: 190.9 / Max: 247 Min: 51.4 / Avg: 151.49 / Max: 175.5 Min: 49.7 / Avg: 201.32 / Max: 272.7 Min: 48.1 / Avg: 176.3 / Max: 224.1 Min: 75.4 / Avg: 157.49 / Max: 178.6 Min: 48.2 / Avg: 203.49 / Max: 246 Min: 107 / Avg: 238.78 / Max: 315.7 Min: 46.5 / Avg: 154.44 / Max: 184.5 Min: 99.4 / Avg: 199.9 / Max: 241.3 Min: 44.8 / Avg: 135.27 / Max: 159.9 Min: 83.7 / Avg: 182.29 / Max: 211.2 Min: 94.8 / Avg: 192.64 / Max: 216.8 Min: 50.4 / Avg: 231.53 / Max: 336
OpenBenchmarking.org FPS Per Watt, More Is Better PlaidML FP16: Yes - Mode: Inference - Network: NASNer Large - Device: OpenCL RTX 2070 SUPER RTX 2060 SUPER GTX 980 Ti RTX 2080 SUPER TITAN RTX RTX 2070 GTX 1070 Ti RTX 2080 RTX 2060 GTX 1060 GTX 1080 GTX 1080 Ti GTX 1660 Ti GTX 980 GTX 1660 GTX 1070 GTX 970 RTX 2080 Ti 0.0833 0.1666 0.2499 0.3332 0.4165 0.30 0.25 0.13 0.32 0.37 0.26 0.23 0.29 0.23 0.15 0.20 0.24 0.22 0.12 0.21 0.18 0.11 0.37
OpenBenchmarking.org Watts, Fewer Is Better PlaidML System Power Consumption Monitor RTX 2070 SUPER RTX 2060 SUPER GTX 980 Ti RTX 2080 SUPER TITAN RTX RTX 2070 GTX 1070 Ti RTX 2080 RTX 2060 GTX 1060 GTX 1080 GTX 1080 Ti GTX 1660 Ti GTX 980 GTX 1660 GTX 1070 GTX 970 RTX 2080 Ti 50 100 150 200 250 Min: 47.9 / Avg: 135.09 / Max: 211.7 Min: 54.4 / Avg: 144.26 / Max: 207.2 Min: 127.5 / Avg: 205.03 / Max: 260.5 Min: 48.5 / Avg: 147.96 / Max: 225.2 Min: 55.6 / Avg: 169.21 / Max: 293 Min: 49 / Avg: 148.17 / Max: 210.6 Min: 51.5 / Avg: 131.42 / Max: 162.8 Min: 50.7 / Avg: 139.72 / Max: 234.8 Min: 47.9 / Avg: 142.09 / Max: 199.4 Min: 68.7 / Avg: 129.36 / Max: 164 Min: 94.6 / Avg: 159.56 / Max: 227.4 Min: 55.7 / Avg: 189.84 / Max: 284.9 Min: 47.3 / Avg: 117.8 / Max: 162 Min: 52.8 / Avg: 183.08 / Max: 228.8 Min: 44.8 / Avg: 109.89 / Max: 143.5 Min: 77.9 / Avg: 157.58 / Max: 202.6 Min: 81.7 / Avg: 163.48 / Max: 201.2 Min: 51.5 / Avg: 167.74 / Max: 291.7
OpenBenchmarking.org FPS Per Watt, More Is Better PlaidML FP16: Yes - Mode: Inference - Network: ResNet 50 - Device: OpenCL RTX 2070 SUPER RTX 2060 SUPER GTX 980 Ti RTX 2080 SUPER TITAN RTX RTX 2070 GTX 1070 Ti RTX 2080 RTX 2060 GTX 1060 GTX 1080 GTX 1080 Ti GTX 1660 Ti GTX 980 GTX 1660 GTX 1070 GTX 970 RTX 2080 Ti 0.576 1.152 1.728 2.304 2.88 2.10 1.74 0.79 2.22 2.56 1.69 1.57 2.19 1.55 1.01 1.51 1.76 1.47 0.78 1.42 1.24 0.71 2.53
OpenBenchmarking.org Watts, Fewer Is Better PlaidML System Power Consumption Monitor RTX 2070 SUPER RTX 2060 SUPER GTX 980 Ti RTX 2080 SUPER TITAN RTX RTX 2070 GTX 1070 Ti RTX 2080 RTX 2060 GTX 1060 GTX 1080 GTX 1080 Ti GTX 1660 Ti GTX 980 GTX 1660 GTX 1070 GTX 970 RTX 2080 Ti 50 100 150 200 250 Min: 46.6 / Avg: 139.53 / Max: 205.1 Min: 53 / Avg: 147.84 / Max: 203.6 Min: 128.3 / Avg: 193.81 / Max: 239.9 Min: 48.4 / Avg: 151.02 / Max: 226.9 Min: 51.1 / Avg: 182.86 / Max: 282.6 Min: 47.6 / Avg: 141.04 / Max: 207.9 Min: 51 / Avg: 131.33 / Max: 154.1 Min: 49 / Avg: 153.24 / Max: 230.1 Min: 48.8 / Avg: 144.1 / Max: 197.4 Min: 55.5 / Avg: 124.66 / Max: 155.7 Min: 84.5 / Avg: 158.48 / Max: 204.6 Min: 125.6 / Avg: 201.87 / Max: 257 Min: 46.7 / Avg: 122.59 / Max: 164 Min: 99.3 / Avg: 168.06 / Max: 211.7 Min: 44.4 / Avg: 112.99 / Max: 143 Min: 70.5 / Avg: 148.83 / Max: 185.2 Min: 72.9 / Avg: 158.81 / Max: 190.7 Min: 50.7 / Avg: 178.03 / Max: 280
OpenBenchmarking.org FPS Per Watt, More Is Better PlaidML FP16: Yes - Mode: Inference - Network: Inception V3 - Device: OpenCL RTX 2070 SUPER RTX 2060 SUPER GTX 980 Ti RTX 2080 SUPER TITAN RTX RTX 2070 GTX 1070 Ti RTX 2080 RTX 2060 GTX 1060 GTX 1080 GTX 1080 Ti GTX 1660 Ti GTX 980 GTX 1660 GTX 1070 GTX 970 RTX 2080 Ti 0.459 0.918 1.377 1.836 2.295 1.72 1.49 0.60 1.99 2.04 1.57 1.12 1.75 1.34 0.78 1.10 1.13 1.32 0.61 1.22 0.95 0.56 2.04
OpenBenchmarking.org FPS Per Watt, More Is Better PlaidML FP16: Yes - Mode: Inference - Network: Mobilenet - Device: OpenCL RTX 2070 SUPER RTX 2060 SUPER GTX 980 Ti RTX 2080 SUPER TITAN RTX RTX 2070 GTX 1070 Ti RTX 2080 RTX 2060 GTX 1060 GTX 1080 GTX 1080 Ti GTX 1660 Ti GTX 980 GTX 1660 GTX 1070 GTX 970 RTX 2080 Ti 6 12 18 24 30 24.75 20.68 7.67 25.06 22.19 21.35 14.16 26.21 18.20 9.57 14.02 15.21 16.06 7.17 14.79 12.35 6.98 26.71
cl-mem OpenBenchmarking.org GB/s Per Watt, More Is Better cl-mem 2017-01-13 Benchmark: Write RTX 2070 SUPER RTX 2060 SUPER GTX 980 Ti RTX 2080 SUPER TITAN RTX RTX 2070 GTX 1070 Ti RTX 2080 RTX 2060 GTX 1060 GTX 1080 GTX 1080 Ti GTX 1660 Ti GTX 980 GTX 1660 GTX 1070 GTX 970 RTX 2080 Ti 0.8348 1.6696 2.5044 3.3392 4.174 2.60 2.61 1.48 2.85 3.13 3.71 1.76 2.74 2.24 1.44 1.64 2.02 2.33 1.03 1.61 1.54 1.07 3.46
OpenBenchmarking.org GB/s Per Watt, More Is Better cl-mem 2017-01-13 Benchmark: Read RTX 2070 SUPER RTX 2060 SUPER GTX 980 Ti RTX 2080 SUPER TITAN RTX RTX 2070 GTX 1070 Ti RTX 2080 RTX 2060 GTX 1060 GTX 1080 GTX 1080 Ti GTX 1660 Ti GTX 980 GTX 1660 GTX 1070 GTX 970 RTX 2080 Ti 0.8663 1.7326 2.5989 3.4652 4.3315 3.47 3.09 1.76 3.85 3.37 3.28 1.86 3.26 2.76 1.34 1.90 2.10 2.67 1.19 1.69 1.68 1.05 3.38
clpeak OpenBenchmarking.org Watts, Fewer Is Better clpeak System Power Consumption Monitor RTX 2070 SUPER RTX 2060 SUPER RTX 2080 SUPER TITAN RTX RTX 2070 GTX 1060 GTX 1080 Ti GTX 1660 Ti 70 140 210 280 350 Min: 47.5 / Avg: 141.91 / Max: 279.4 Min: 47.4 / Avg: 86.98 / Max: 242.5 Min: 47.9 / Avg: 144.19 / Max: 288.8 Min: 52.5 / Avg: 207.88 / Max: 366.7 Min: 47.8 / Avg: 135.68 / Max: 254.5 Min: 66.2 / Avg: 117.06 / Max: 191 Min: 52.4 / Avg: 199.89 / Max: 328.7 Min: 46.4 / Avg: 77.81 / Max: 158.1
OpenBenchmarking.org GIOPS Per Watt, More Is Better clpeak OpenCL Test: Integer Compute INT RTX 2070 SUPER RTX 2060 SUPER GTX 980 Ti RTX 2080 SUPER TITAN RTX RTX 2070 GTX 1070 Ti RTX 2080 RTX 2060 GTX 1060 GTX 1080 GTX 1080 Ti GTX 1660 Ti GTX 980 GTX 1660 GTX 1070 GTX 970 RTX 2080 Ti 30 60 90 120 150 60.39 80.74 9.00 72.16 66.58 52.78 25.59 123.07 63.25 10.83 26.82 16.52 61.38 8.44 79.94 23.89 9.19 54.76
OpenBenchmarking.org Watts, Fewer Is Better clpeak System Power Consumption Monitor RTX 2070 SUPER RTX 2060 SUPER GTX 980 Ti RTX 2080 SUPER TITAN RTX RTX 2070 GTX 1070 Ti RTX 2080 RTX 2060 GTX 1060 GTX 1080 GTX 1080 Ti GTX 1660 Ti GTX 980 GTX 1660 GTX 1070 GTX 970 RTX 2080 Ti 40 80 120 160 200 Min: 47 / Avg: 137.66 / Max: 150.3 Min: 47.1 / Avg: 142.14 / Max: 150.8 Min: 128.4 / Avg: 179.97 / Max: 191.4 Min: 47.6 / Avg: 151.43 / Max: 166.9 Min: 51.5 / Avg: 203.24 / Max: 225.1 Min: 46.9 / Avg: 137.5 / Max: 151.9 Min: 51 / Avg: 113.26 / Max: 124.1 Min: 49.8 / Avg: 153.89 / Max: 172.5 Min: 47.9 / Avg: 126.06 / Max: 143 Min: 44.7 / Avg: 102.22 / Max: 117.3 Min: 46.2 / Avg: 135.52 / Max: 152.6 Min: 51.6 / Avg: 166.5 / Max: 193 Min: 46.4 / Avg: 107.92 / Max: 119.4 Min: 51.6 / Avg: 146.12 / Max: 159.1 Min: 43.9 / Avg: 97.25 / Max: 106.6 Min: 46 / Avg: 117.77 / Max: 137.1 Min: 93.6 / Avg: 140.29 / Max: 146.2 Min: 50.3 / Avg: 197 / Max: 217.1
OpenBenchmarking.org GFLOPS Per Watt, More Is Better clpeak OpenCL Test: Double-Precision Double RTX 2070 SUPER RTX 2060 SUPER GTX 980 Ti RTX 2080 SUPER TITAN RTX RTX 2070 GTX 1070 Ti RTX 2080 RTX 2060 GTX 1060 GTX 1080 GTX 1080 Ti GTX 1660 Ti GTX 980 GTX 1660 GTX 1070 GTX 970 RTX 2080 Ti 0.6075 1.215 1.8225 2.43 3.0375 2.25 1.85 1.09 2.50 2.70 1.95 2.14 2.25 1.84 1.46 2.20 2.49 1.72 1.09 1.73 1.90 0.98 2.65
OpenBenchmarking.org Watts, Fewer Is Better clpeak System Power Consumption Monitor RTX 2070 SUPER RTX 2060 SUPER GTX 980 Ti TITAN RTX RTX 2070 GTX 1660 Ti GTX 980 GTX 970 60 120 180 240 300 Min: 47.5 / Avg: 69.91 / Max: 138.9 Min: 46.6 / Avg: 63.45 / Max: 103 Min: 54.9 / Avg: 131.87 / Max: 194.2 Min: 50.6 / Avg: 137.09 / Max: 308.7 Min: 48.2 / Avg: 96.86 / Max: 180.2 Min: 45.5 / Avg: 67.18 / Max: 127.1 Min: 52.5 / Avg: 122.69 / Max: 181.1 Min: 51.4 / Avg: 98.78 / Max: 148.8
OpenBenchmarking.org GFLOPS Per Watt, More Is Better clpeak OpenCL Test: Single-Precision Float RTX 2070 SUPER RTX 2060 SUPER GTX 980 Ti RTX 2080 SUPER TITAN RTX RTX 2070 GTX 1070 Ti RTX 2080 RTX 2060 GTX 1080 GTX 1660 Ti GTX 980 GTX 1070 GTX 970 RTX 2080 Ti 50 100 150 200 250 121.62 111.74 42.00 84.49 103.61 74.32 84.46 79.25 109.20 89.11 71.35 36.49 70.63 39.36 222.09
OpenBenchmarking.org GBPS Per Watt, More Is Better clpeak OpenCL Test: Global Memory Bandwidth RTX 2070 SUPER RTX 2060 SUPER GTX 980 Ti RTX 2080 SUPER TITAN RTX RTX 2070 GTX 1070 Ti RTX 2080 GTX 1060 GTX 1080 GTX 1080 Ti GTX 1660 Ti GTX 980 GTX 1660 GTX 1070 GTX 970 RTX 2080 Ti 3 6 9 12 15 5.41 4.88 2.02 4.86 6.18 3.33 1.92 5.09 1.84 2.26 2.73 2.24 1.65 3.16 2.63 1.52 9.15
JuliaGPU OpenBenchmarking.org Samples/sec Per Watt, More Is Better JuliaGPU 1.2pts1 OpenCL Device: GPU RTX 2070 SUPER RTX 2060 SUPER GTX 980 Ti RTX 2080 SUPER TITAN RTX RTX 2070 GTX 1070 Ti RTX 2080 RTX 2060 GTX 1060 GTX 1080 GTX 1080 Ti GTX 1660 Ti GTX 980 GTX 1660 GTX 1070 GTX 970 RTX 2080 Ti 600K 1200K 1800K 2400K 3000K 2632329.69 2670026.70 1099178.25 2379445.26 1923116.67 2271141.79 2260229.90 2691799.29 2469451.17 1658141.69 1906369.99 1682592.71 2880366.36 1325997.88 2790569.69 1809790.27 1275493.93 1910018.66
SHOC Scalable HeterOgeneous Computing OpenBenchmarking.org GHash/s Per Watt, More Is Better SHOC Scalable HeterOgeneous Computing 2015-11-10 Target: OpenCL - Benchmark: MD5 Hash RTX 2070 SUPER GTX 980 Ti RTX 2080 SUPER TITAN RTX RTX 2070 RTX 2080 RTX 2060 GTX 1060 GTX 1080 GTX 1660 Ti GTX 980 GTX 1660 GTX 970 0.0833 0.1666 0.2499 0.3332 0.4165 0.30 0.04 0.32 0.37 0.15 0.21 0.12 0.11 0.15 0.26 0.08 0.26 0.05
OpenBenchmarking.org GFLOPS Per Watt, More Is Better SHOC Scalable HeterOgeneous Computing 2015-11-10 Target: OpenCL - Benchmark: FFT SP RTX 2070 SUPER RTX 2060 SUPER GTX 980 Ti RTX 2070 GTX 1070 Ti RTX 2080 RTX 2060 GTX 1060 GTX 1080 GTX 1080 Ti GTX 1660 Ti GTX 980 GTX 1660 GTX 1070 GTX 970 RTX 2080 Ti 4 8 12 16 20 15.58 17.59 6.92 8.67 6.36 15.46 13.23 4.00 7.87 7.97 12.25 5.45 5.70 6.23 5.12 11.54
OpenBenchmarking.org Watts, Fewer Is Better SHOC Scalable HeterOgeneous Computing 2015-11-10 System Power Consumption Monitor RTX 2070 SUPER RTX 2060 SUPER GTX 980 Ti RTX 2080 SUPER TITAN RTX RTX 2070 GTX 1070 Ti RTX 2080 RTX 2060 GTX 1060 GTX 1080 GTX 1080 Ti GTX 1660 Ti GTX 980 GTX 1660 GTX 1070 GTX 970 RTX 2080 Ti 70 140 210 280 350 Min: 47.1 / Avg: 150.09 / Max: 265.5 Min: 46.8 / Avg: 148.63 / Max: 238 Min: 126.9 / Avg: 193.91 / Max: 298.6 Min: 47 / Avg: 164.08 / Max: 318.6 Min: 52 / Avg: 223.03 / Max: 367 Min: 47.9 / Avg: 149.29 / Max: 251.7 Min: 50.5 / Avg: 125.61 / Max: 179.8 Min: 48.7 / Avg: 171.33 / Max: 292.2 Min: 47 / Avg: 145.37 / Max: 229.5 Min: 74.8 / Avg: 119.53 / Max: 184.8 Min: 94 / Avg: 157.13 / Max: 259.6 Min: 49.6 / Avg: 199.67 / Max: 326.6 Min: 46.4 / Avg: 118.75 / Max: 170.7 Min: 97.6 / Avg: 160.93 / Max: 243.5 Min: 44.5 / Avg: 106.24 / Max: 161 Min: 78 / Avg: 141.46 / Max: 206.4 Min: 80.6 / Avg: 148.92 / Max: 222.7 Min: 51.3 / Avg: 217.17 / Max: 360
OpenBenchmarking.org GFLOPS Per Watt, More Is Better SHOC Scalable HeterOgeneous Computing 2015-11-10 Target: OpenCL - Benchmark: Max SP Flops RTX 2070 SUPER RTX 2060 SUPER GTX 980 Ti RTX 2080 SUPER TITAN RTX RTX 2070 GTX 1070 Ti RTX 2080 RTX 2060 GTX 1060 GTX 1080 GTX 1080 Ti GTX 1660 Ti GTX 980 GTX 1660 GTX 1070 GTX 970 RTX 2080 Ti 20 40 60 80 100