NVIDIA vs. Radeon OpenCL compute testing on ubuntu Linux. Tests by Michael Larabel for a future article.
Compare your own system(s) to this result file with the
Phoronix Test Suite by running the command:
phoronix-test-suite benchmark 1707132-TR-1707100PT16 OpenCL ROCm 1.6 Radeon Compute vs. NVIDIA Linux - Phoronix Test Suite OpenCL ROCm 1.6 Radeon Compute vs. NVIDIA Linux NVIDIA vs. Radeon OpenCL compute testing on ubuntu Linux. Tests by Michael Larabel for a future article.
HTML result view exported from: https://openbenchmarking.org/result/1707132-TR-1707100PT16&sor&grt .
OpenCL ROCm 1.6 Radeon Compute vs. NVIDIA Linux Processor Motherboard Chipset Memory Disk Graphics Audio Network OS Kernel Desktop Display Server Display Driver OpenGL OpenCL Compiler File-System Screen Resolution Vulkan Radeon RX 460 Radeon RX 480 Radeon RX 560 Radeon RX 580 Radeon R9 Fury GeForce GTX 780 Ti GeForce GTX 960 GeForce GTX 970 GeForce GTX 980 GeForce GTX 980 Ti GeForce GTX 1050 GeForce GTX 1060 GeForce GTX 1070 GeForce GTX 1080 GeForce GTX 1080 Ti Gigabyte NVIDIA GeForce GTX 1050 Intel Core i7-7740K @ 4.50GHz (8 Cores) ASUS PRIME X299-A Intel Device 591f 16384MB Samsung SSD 950 PRO 256GB AMD POLARIS11 1920MB Realtek Generic Intel Connection Ubuntu 16.04 4.9.0-kfd-compute-rocm-rel-1.6-77 (x86_64) Unity 7.4.0 X Server 1.18.4 amdgpu 1.1.2 4.1 Mesa 12.0.6 Gallium 0.4 OpenCL 2.0 AMD-APP (2442.0) GCC 5.4.0 20160609 ext4 3840x2160 AMD POLARIS10 8064MB AMD POLARIS11 3968MB MSI AMD POLARIS10 8064MB modesetting 1.18.4 Sapphire AMD Radeon R9 FURY / NANO 3968MB NVIDIA GeForce GTX 780 Ti 3072MB (875/3500MHz) NVIDIA 384.47 4.5.0 OpenCL 1.2 CUDA 9.0.101 eVGA NVIDIA GeForce GTX 960 2048MB (1277/3505MHz) eVGA NVIDIA GeForce GTX 970 4096MB (1163/3505MHz) NVIDIA GeForce GTX 980 4096MB (1126/3505MHz) NVIDIA GeForce GTX 980 Ti 6144MB (999/3505MHz) Zotac NVIDIA GeForce GTX 1050 2048MB (1354/3504MHz) NVIDIA GeForce GTX 1060 6GB 6144MB (1506/4006MHz) NVIDIA GeForce GTX 1070 8192MB (1506/4006MHz) NVIDIA GeForce GTX 1080 8192MB (1607/5005MHz) NVIDIA GeForce GTX 1080 Ti 11264MB (1480/5508MHz) AMD Phenom II X3 720 @ 2.80GHz (3 Cores) ASUS M4A89GTD-PRO/USB3 AMD RS880 8192MB 120GB OCZ AGILITY3 + 3001GB Seagate ST3000DM001-1ER1 + 2000GB Seagate ST2000DM001-9YN1 + 1500GB SAMSUNG HD154UI + 300GB Western Digital WD3000HLFS-0 + 4001GB Seagate ST4000DM005-2DP1 Gigabyte NVIDIA GeForce GTX 1050 2048MB (120/405MHz) Realtek ALC892 Realtek RTL8111/8168/8411 + Qualcomm Atheros AR93xx Wireless 4.4.0-83-generic (x86_64) KDE Frameworks 5 NVIDIA 375.66 1.0.24 1680x1050 OpenBenchmarking.org Compiler Details - --build=x86_64-linux-gnu --disable-browser-plugin --disable-vtable-verify --disable-werror --enable-checking=release --enable-clocale=gnu --enable-gnu-unique-object --enable-gtk-cairo --enable-java-awt=gtk --enable-java-home --enable-languages=c,ada,c++,java,go,d,fortran,objc,obj-c++ --enable-libmpx --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-arch-directory=amd64 --with-default-libstdcxx-abi=new --with-multilib-list=m32,m64,mx32 --with-tune=generic -v Processor Details - Radeon RX 460: Scaling Governor: intel_pstate performance - Radeon RX 480: Scaling Governor: intel_pstate performance - Radeon RX 560: Scaling Governor: intel_pstate performance - Radeon RX 580: Scaling Governor: intel_pstate performance - Radeon R9 Fury: Scaling Governor: intel_pstate performance - GeForce GTX 780 Ti: Scaling Governor: intel_pstate performance - GeForce GTX 960: Scaling Governor: intel_pstate performance - GeForce GTX 970: Scaling Governor: intel_pstate performance - GeForce GTX 980: Scaling Governor: intel_pstate performance - GeForce GTX 980 Ti: Scaling Governor: intel_pstate performance - GeForce GTX 1050: Scaling Governor: intel_pstate performance - GeForce GTX 1060: Scaling Governor: intel_pstate performance - GeForce GTX 1070: Scaling Governor: intel_pstate performance - GeForce GTX 1080: Scaling Governor: intel_pstate performance - GeForce GTX 1080 Ti: Scaling Governor: intel_pstate performance - Gigabyte NVIDIA GeForce GTX 1050: Scaling Governor: acpi-cpufreq ondemand Graphics Details - Radeon RX 460, Radeon RX 480, Radeon RX 560, Radeon R9 Fury: GLAMOR OpenCL Details - GeForce GTX 780 Ti: GPU Compute Cores: 2880 - GeForce GTX 960: GPU Compute Cores: 1024 - GeForce GTX 970: GPU Compute Cores: 1664 - GeForce GTX 980: GPU Compute Cores: 2048 - GeForce GTX 980 Ti: GPU Compute Cores: 2816 - GeForce GTX 1050: GPU Compute Cores: 640 - GeForce GTX 1060: GPU Compute Cores: 1280 - GeForce GTX 1070: GPU Compute Cores: 1920 - GeForce GTX 1080: GPU Compute Cores: 2560 - GeForce GTX 1080 Ti: GPU Compute Cores: 3584 - Gigabyte NVIDIA GeForce GTX 1050: GPU Compute Cores: 640 System Details - GeForce GTX 780 Ti: GPU Compute Cores: 2880. - GeForce GTX 960: GPU Compute Cores: 1024. - GeForce GTX 970: GPU Compute Cores: 1664. - GeForce GTX 980: GPU Compute Cores: 2048. - GeForce GTX 980 Ti: GPU Compute Cores: 2816. - GeForce GTX 1050: GPU Compute Cores: 640. - GeForce GTX 1060: GPU Compute Cores: 1280. - GeForce GTX 1070: GPU Compute Cores: 1920. - GeForce GTX 1080: GPU Compute Cores: 2560. - GeForce GTX 1080 Ti: GPU Compute Cores: 3584. - Gigabyte NVIDIA GeForce GTX 1050: GPU Compute Cores: 640.
OpenCL ROCm 1.6 Radeon Compute vs. NVIDIA Linux cl-mem: Read cl-mem: Write cl-mem: Copy clpeak: Global Memory Bandwidth clpeak: Single-Precision Float clpeak: Double-Precision Double clpeak: Integer Compute INT clpeak: Transfer Bandwidth enqueueWriteBuffer clpeak: Transfer Bandwidth enqueueReadBuffer clpeak: Kernel Latency comd-cl: Average Atom Update Rate darktable: Boat - OpenCL darktable: Masskrug - OpenCL darktable: Server Room - OpenCL darktable: Boat - OpenCL darktable: Masskrug - OpenCL darktable: Server Room - OpenCL ethminer: GPU OpenCL fahbench: Phoronix Test Suite v7.2.1 lulesh-cl: Phoronix Test Suite v7.2.1 luxmark: GPU - Luxball HDR luxmark: GPU - Hotel mixbench: Single Precision mixbench: Double Precision mixbench: Integer rodinia: OpenCL Particle Filter shoc: OpenCL - Bus Speed Download shoc: OpenCL - Bus Speed Readback shoc: OpenCL - Texture Read Bandwidth shoc: OpenCL - FFT SP shoc: OpenCL - MD5 Hash viennacl: OpenCL LU Factorization xsbench-cl: Phoronix Test Suite v7.2.1 Radeon RX 460 Radeon RX 480 Radeon RX 560 Radeon RX 580 Radeon R9 Fury GeForce GTX 780 Ti GeForce GTX 960 GeForce GTX 970 GeForce GTX 980 GeForce GTX 980 Ti GeForce GTX 1050 GeForce GTX 1060 GeForce GTX 1070 GeForce GTX 1080 GeForce GTX 1080 Ti Gigabyte NVIDIA GeForce GTX 1050 91.50 78.57 77.87 89.25 2135.23 135.17 414.21 30.03 12.24 42.49 4.85 7.98 0.29 0.28 7176920 840.73 3872 430 1851.75 134.11 422.38 5.71 5.20 83.67 173.12 7.33 36982576 151.13 146.30 173.13 203.08 5755.59 364.11 1161.64 30.13 12.25 39.87 4.84 4.25 0.17 0.17 12543590 878.41 9731 1063 5442.89 362.18 1139.87 11.47 10.42 176.79 460.84 12.36 74635621 89.47 74.50 77.20 88.69 2599.84 164.57 525.62 30.04 12.25 41.06 4.84 6.96 0.29 0.31 7203134 852.97 4481 507 2303.86 149.51 487.82 5.72 5.24 105.19 208.75 9.54 38606004 156.93 158.07 172.20 201.45 6195.09 391.92 1252.48 30.47 12.26 39.54 4.85 4.22 0.17 0.16 12811559 866.99 10160 1206 5854.94 389.88 1226.84 6.62 11.49 10.21 190.13 496.76 13.01 74435707 121.03 300.30 198.43 388.73 7064.24 447.25 1429.19 30.52 12.25 41.62 4.85 3.50 0.13 0.15 16587889 845.27 12894 1369 6501.19 440.79 1385.89 11.38 10.61 239.03 550.95 20.60 85206540 271.70 250.80 237.00 252.46 3661.68 246.92 958.80 12.36 11.24 5.67 4.84 15.11 0.22 0.21 15689318 72.76 9516 1200 4260.60 245.04 967.53 15.30 13.00 13.20 286.87 429.63 4.68 56.89 81.13 2498.99 92.88 781.83 12.44 11.32 3.94 4.84 19.13 0.20 0.20 10341580 58.59 6114 1125 2726.15 92.73 835.02 18.47 13.00 13.19 279.37 207.09 4.49 47.42 143.67 129.20 125.30 143.41 3725.85 137.42 1134.30 12.47 11.33 4.08 4.84 15.46 0.17 0.17 17974339 86.07 10731 1756 4121.47 137.54 1220.95 13.11 13.00 13.20 288.61 384.81 6.54 52.87 164.50 151.80 142.50 164.05 4286.78 159.90 1293.68 12.46 11.25 4.12 4.84 15.02 0.16 0.17 19740899 97.56 11955 1863 4692.97 159.89 1404.21 11.87 13.00 13.20 333.05 447.24 7.56 54.76 266.07 238.07 216.40 262.13 5303.61 197.36 1605.34 12.46 11.37 4.32 4.85 4.05 0.17 0.17 18018030 109.12 14961 2034 5816.30 197.04 1717.69 10.14 13.00 13.20 350.63 694.57 9.29 56.98 94.90 85.70 86.70 92.42 1941.07 66.72 562.46 12.53 11.32 3.68 4.84 17.76 0.17 0.18 11398894 49.72 6576 1023 2037.30 66.66 615.44 26.09 13.00 13.20 276.45 253.32 3.23 42.12 153.40 139.37 138.97 146.64 4264.43 151.32 1227.52 12.61 11.32 3.60 4.85 4.51 0.14 0.14 18653001 97.88 11627 1782 4403.62 152.40 1370.35 12.15 12.99 13.20 381.92 404.59 7.36 54.25 205.37 191.20 186.57 196.24 6332.82 225.42 1657.74 12.60 11.36 3.60 4.84 3.71 0.13 0.14 25311459 132.83 16184 2506 6374.80 222.10 2027.70 8.27 13.00 13.20 456.70 553.04 10.69 58.69 228.73 214.97 208.83 222.43 8398.22 298.47 2372.63 12.63 11.32 3.59 4.84 3.55 0.13 0.13 20721026 146.29 12923 2643 8489.90 293.93 2656.67 6.56 13.00 13.20 528.02 652.64 14.36 61.06 337.90 334.80 316.60 329.40 11828.88 417.87 3276.83 12.62 11.36 3.60 4.84 3.03 0.13 0.13 31569419 186.33 19842 3739 5.03 13.00 13.20 600.45 980.92 19.99 63.36 37.49 47.03 28.19 6457 1127 OpenBenchmarking.org
cl-mem Benchmark: Read OpenBenchmarking.org GB/s, More Is Better cl-mem 2017-01-13 Benchmark: Read GeForce GTX 1080 Ti GeForce GTX 780 Ti GeForce GTX 980 Ti GeForce GTX 1080 GeForce GTX 1070 GeForce GTX 980 Radeon RX 580 GeForce GTX 1060 Radeon RX 480 GeForce GTX 970 Radeon R9 Fury GeForce GTX 1050 Radeon RX 460 Radeon RX 560 70 140 210 280 350 SE +/- 0.40, N = 3 SE +/- 0.06, N = 3 SE +/- 0.03, N = 3 SE +/- 0.13, N = 3 SE +/- 0.07, N = 3 SE +/- 0.06, N = 3 SE +/- 1.17, N = 3 SE +/- 0.00, N = 3 SE +/- 0.18, N = 3 SE +/- 0.03, N = 3 SE +/- 0.03, N = 3 SE +/- 0.00, N = 3 SE +/- 0.06, N = 3 SE +/- 0.18, N = 3 337.90 271.70 266.07 228.73 205.37 164.50 156.93 153.40 151.13 143.67 121.03 94.90 91.50 89.47 1. (CC) gcc options: -O2 -flto -lOpenCL
cl-mem Benchmark: Read OpenBenchmarking.org GB/s Per Watt, More Is Better cl-mem 2017-01-13 Benchmark: Read GeForce GTX 1080 Ti GeForce GTX 1080 GeForce GTX 1070 GeForce GTX 980 Ti GeForce GTX 1060 GeForce GTX 980 Radeon RX 580 GeForce GTX 1050 GeForce GTX 970 GeForce GTX 780 Ti Radeon RX 480 Radeon RX 560 Radeon RX 460 Radeon R9 Fury 0.4095 0.819 1.2285 1.638 2.0475 1.82 1.76 1.57 1.53 1.33 1.12 1.08 1.05 1.05 1.04 1.00 0.95 0.92 0.73
cl-mem Benchmark: Write OpenBenchmarking.org GB/s, More Is Better cl-mem 2017-01-13 Benchmark: Write GeForce GTX 1080 Ti Radeon R9 Fury GeForce GTX 780 Ti GeForce GTX 980 Ti GeForce GTX 1080 GeForce GTX 1070 Radeon RX 580 GeForce GTX 980 Radeon RX 480 GeForce GTX 1060 GeForce GTX 970 GeForce GTX 1050 Radeon RX 460 Radeon RX 560 70 140 210 280 350 SE +/- 0.23, N = 3 SE +/- 1.90, N = 3 SE +/- 1.00, N = 3 SE +/- 0.03, N = 3 SE +/- 0.03, N = 3 SE +/- 0.10, N = 3 SE +/- 0.12, N = 3 SE +/- 0.00, N = 3 SE +/- 9.95, N = 3 SE +/- 0.03, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.09, N = 3 SE +/- 0.06, N = 3 334.80 300.30 250.80 238.07 214.97 191.20 158.07 151.80 146.30 139.37 129.20 85.70 78.57 74.50 1. (CC) gcc options: -O2 -flto -lOpenCL
cl-mem Benchmark: Copy OpenBenchmarking.org GB/s, More Is Better cl-mem 2017-01-13 Benchmark: Copy GeForce GTX 1080 Ti GeForce GTX 780 Ti GeForce GTX 980 Ti GeForce GTX 1080 Radeon R9 Fury GeForce GTX 1070 Radeon RX 480 Radeon RX 580 GeForce GTX 980 GeForce GTX 1060 GeForce GTX 970 GeForce GTX 1050 Radeon RX 460 Radeon RX 560 70 140 210 280 350 SE +/- 0.12, N = 3 SE +/- 0.26, N = 3 SE +/- 0.00, N = 3 SE +/- 0.09, N = 3 SE +/- 0.64, N = 3 SE +/- 0.07, N = 3 SE +/- 1.19, N = 3 SE +/- 0.15, N = 3 SE +/- 0.00, N = 3 SE +/- 0.03, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.15, N = 3 SE +/- 0.06, N = 3 316.60 237.00 216.40 208.83 198.43 186.57 173.13 172.20 142.50 138.97 125.30 86.70 77.87 77.20 1. (CC) gcc options: -O2 -flto -lOpenCL
clpeak OpenCL Test: Global Memory Bandwidth OpenBenchmarking.org GBPS, More Is Better clpeak OpenCL Test: Global Memory Bandwidth Radeon R9 Fury GeForce GTX 1080 Ti GeForce GTX 980 Ti GeForce GTX 780 Ti GeForce GTX 1080 Radeon RX 480 Radeon RX 580 GeForce GTX 1070 GeForce GTX 980 GeForce GTX 1060 GeForce GTX 970 GeForce GTX 1050 Radeon RX 460 Radeon RX 560 GeForce GTX 960 80 160 240 320 400 SE +/- 0.35, N = 3 SE +/- 0.66, N = 3 SE +/- 0.49, N = 3 SE +/- 10.56, N = 3 SE +/- 0.59, N = 3 SE +/- 0.35, N = 3 SE +/- 0.50, N = 3 SE +/- 0.02, N = 3 SE +/- 0.08, N = 3 SE +/- 0.07, N = 3 SE +/- 0.03, N = 3 SE +/- 0.19, N = 3 SE +/- 0.28, N = 3 SE +/- 0.23, N = 3 SE +/- 0.01, N = 3 388.73 329.40 262.13 252.46 222.43 203.08 201.45 196.24 164.05 146.64 143.41 92.42 89.25 88.69 81.13
clpeak OpenCL Test: Single-Precision Float OpenBenchmarking.org GFLOPS, More Is Better clpeak OpenCL Test: Single-Precision Float GeForce GTX 1080 Ti GeForce GTX 1080 Radeon R9 Fury GeForce GTX 1070 Radeon RX 580 Radeon RX 480 GeForce GTX 980 Ti GeForce GTX 980 GeForce GTX 1060 GeForce GTX 970 GeForce GTX 780 Ti Radeon RX 560 GeForce GTX 960 Radeon RX 460 GeForce GTX 1050 3K 6K 9K 12K 15K SE +/- 0.75, N = 3 SE +/- 0.88, N = 3 SE +/- 0.48, N = 3 SE +/- 10.06, N = 3 SE +/- 0.05, N = 3 SE +/- 0.06, N = 3 SE +/- 0.85, N = 3 SE +/- 1.23, N = 3 SE +/- 0.45, N = 3 SE +/- 0.28, N = 3 SE +/- 186.06, N = 3 SE +/- 0.19, N = 3 SE +/- 8.65, N = 3 SE +/- 0.18, N = 3 SE +/- 0.06, N = 3 11828.88 8398.22 7064.24 6332.82 6195.09 5755.59 5303.61 4286.78 4264.43 3725.85 3661.68 2599.84 2498.99 2135.23 1941.07
clpeak OpenCL Test: Double-Precision Double OpenBenchmarking.org GFLOPS, More Is Better clpeak OpenCL Test: Double-Precision Double Radeon R9 Fury GeForce GTX 1080 Ti Radeon RX 580 Radeon RX 480 GeForce GTX 1080 GeForce GTX 780 Ti GeForce GTX 1070 GeForce GTX 980 Ti Radeon RX 560 GeForce GTX 980 GeForce GTX 1060 GeForce GTX 970 Radeon RX 460 GeForce GTX 960 GeForce GTX 1050 100 200 300 400 500 SE +/- 0.00, N = 3 SE +/- 1.16, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.62, N = 3 SE +/- 0.03, N = 3 SE +/- 0.83, N = 3 SE +/- 0.13, N = 3 SE +/- 0.01, N = 3 SE +/- 0.04, N = 3 SE +/- 0.41, N = 3 SE +/- 0.03, N = 3 SE +/- 0.00, N = 3 SE +/- 0.25, N = 3 SE +/- 0.05, N = 3 447.25 417.87 391.92 364.11 298.47 246.92 225.42 197.36 164.57 159.90 151.32 137.42 135.17 92.88 66.72
clpeak OpenCL Test: Integer Compute INT OpenBenchmarking.org GIOPS, More Is Better clpeak OpenCL Test: Integer Compute INT GeForce GTX 1080 Ti GeForce GTX 1080 GeForce GTX 1070 GeForce GTX 980 Ti Radeon R9 Fury GeForce GTX 980 Radeon RX 580 GeForce GTX 1060 Radeon RX 480 GeForce GTX 970 GeForce GTX 780 Ti GeForce GTX 960 GeForce GTX 1050 Radeon RX 560 Radeon RX 460 700 1400 2100 2800 3500 SE +/- 46.39, N = 3 SE +/- 24.29, N = 3 SE +/- 14.62, N = 3 SE +/- 20.06, N = 3 SE +/- 0.01, N = 3 SE +/- 2.51, N = 3 SE +/- 0.00, N = 3 SE +/- 43.18, N = 3 SE +/- 0.25, N = 3 SE +/- 11.84, N = 3 SE +/- 20.83, N = 3 SE +/- 3.20, N = 3 SE +/- 24.37, N = 3 SE +/- 0.11, N = 3 SE +/- 0.15, N = 3 3276.83 2372.63 1657.74 1605.34 1429.19 1293.68 1252.48 1227.52 1161.64 1134.30 958.80 781.83 562.46 525.62 414.21
clpeak OpenCL Test: Integer Compute INT OpenBenchmarking.org GIOPS Per Watt, More Is Better clpeak OpenCL Test: Integer Compute INT Radeon RX 580 Radeon R9 Fury Radeon RX 480 GeForce GTX 980 GeForce GTX 960 Radeon RX 560 Radeon RX 460 3 6 9 12 15 9.62 8.60 8.59 7.08 5.35 5.33 4.79
clpeak System Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better clpeak System Power Consumption Monitor GeForce GTX 970 Radeon RX 460 GeForce GTX 1050 GeForce GTX 1080 Radeon RX 560 Radeon RX 580 Radeon RX 480 GeForce GTX 960 GeForce GTX 780 Ti Radeon R9 Fury GeForce GTX 1060 GeForce GTX 1070 GeForce GTX 1080 Ti GeForce GTX 980 GeForce GTX 980 Ti 60 120 180 240 300 Min: 55.3 / Avg: 75.15 / Max: 95 Min: 54.4 / Avg: 86.44 / Max: 101.3 Min: 46.5 / Avg: 87.6 / Max: 128.7 Min: 50.3 / Avg: 93.75 / Max: 137.2 Min: 81.7 / Avg: 98.6 / Max: 111.7 Min: 63.7 / Avg: 130.17 / Max: 215.5 Min: 68.8 / Avg: 135.3 / Max: 197.4 Min: 53.6 / Avg: 146.17 / Max: 204 Min: 59.5 / Avg: 148.7 / Max: 237.9 Min: 79.4 / Avg: 166.19 / Max: 294.3 Min: 50.2 / Avg: 117.05 / Max: 183.9 Min: 56.6 / Avg: 158.7 / Max: 260.8 Min: 56.7 / Avg: 182.83 / Max: 246 Min: 60.3 / Avg: 195.05 / Max: 329.8
clpeak OpenCL Test: Transfer Bandwidth enqueueWriteBuffer OpenBenchmarking.org GBPS, More Is Better clpeak OpenCL Test: Transfer Bandwidth enqueueWriteBuffer Radeon R9 Fury Radeon RX 580 Radeon RX 480 Radeon RX 560 Radeon RX 460 GeForce GTX 1080 GeForce GTX 1080 Ti GeForce GTX 1060 GeForce GTX 1070 GeForce GTX 1050 GeForce GTX 970 GeForce GTX 980 Ti GeForce GTX 980 GeForce GTX 960 GeForce GTX 780 Ti 7 14 21 28 35 SE +/- 0.33, N = 3 SE +/- 0.33, N = 3 SE +/- 0.04, N = 3 SE +/- 0.00, N = 3 SE +/- 0.04, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.03, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.05, N = 3 30.52 30.47 30.13 30.04 30.03 12.63 12.62 12.61 12.60 12.53 12.47 12.46 12.46 12.44 12.36
clpeak OpenCL Test: Transfer Bandwidth enqueueReadBuffer OpenBenchmarking.org GBPS, More Is Better clpeak OpenCL Test: Transfer Bandwidth enqueueReadBuffer Radeon RX 580 Radeon R9 Fury Radeon RX 560 Radeon RX 480 Radeon RX 460 GeForce GTX 980 Ti GeForce GTX 1080 Ti GeForce GTX 1070 GeForce GTX 970 GeForce GTX 1080 GeForce GTX 1060 GeForce GTX 1050 GeForce GTX 960 GeForce GTX 980 GeForce GTX 780 Ti 3 6 9 12 15 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 SE +/- 0.03, N = 3 SE +/- 0.01, N = 3 SE +/- 0.03, N = 3 SE +/- 0.01, N = 3 SE +/- 0.03, N = 3 SE +/- 0.02, N = 3 12.26 12.25 12.25 12.25 12.24 11.37 11.36 11.36 11.33 11.32 11.32 11.32 11.32 11.25 11.24
clpeak OpenCL Test: Kernel Latency OpenBenchmarking.org us, Fewer Is Better clpeak OpenCL Test: Kernel Latency GeForce GTX 1080 GeForce GTX 1060 GeForce GTX 1070 GeForce GTX 1080 Ti GeForce GTX 1050 GeForce GTX 960 GeForce GTX 970 GeForce GTX 980 GeForce GTX 980 Ti GeForce GTX 780 Ti Radeon RX 580 Radeon RX 480 Radeon RX 560 Radeon R9 Fury Radeon RX 460 10 20 30 40 50 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.03, N = 3 SE +/- 0.05, N = 3 SE +/- 0.04, N = 3 SE +/- 0.05, N = 3 SE +/- 0.04, N = 3 SE +/- 0.10, N = 3 SE +/- 0.03, N = 3 SE +/- 0.42, N = 3 SE +/- 0.77, N = 3 SE +/- 0.63, N = 3 SE +/- 0.40, N = 3 SE +/- 2.83, N = 3 3.59 3.60 3.60 3.60 3.68 3.94 4.08 4.12 4.32 5.67 39.54 39.87 41.06 41.62 42.49
CoMD OpenCL Average Atom Update Rate OpenBenchmarking.org us/atom/task, More Is Better CoMD OpenCL 2017-07-06 Average Atom Update Rate GeForce GTX 1060 GeForce GTX 980 Ti Radeon R9 Fury Radeon RX 580 Radeon RX 460 GeForce GTX 1080 Ti GeForce GTX 1080 GeForce GTX 1070 GeForce GTX 1050 GeForce GTX 980 GeForce GTX 970 GeForce GTX 960 GeForce GTX 780 Ti Radeon RX 560 Radeon RX 480 1.0913 2.1826 3.2739 4.3652 5.4565 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 +/- 0.00, 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 +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 4.85 4.85 4.85 4.85 4.85 4.84 4.84 4.84 4.84 4.84 4.84 4.84 4.84 4.84 4.84 1. (CC) gcc options: -std=c99 -O5 -lm -lOpenCL
Darktable Test: Boat - Acceleration: OpenCL OpenBenchmarking.org Seconds, Fewer Is Better Darktable 2.0.3 Test: Boat - Acceleration: OpenCL GeForce GTX 1080 Ti Radeon R9 Fury GeForce GTX 1080 GeForce GTX 1070 GeForce GTX 980 Ti Radeon RX 580 Radeon RX 480 GeForce GTX 1060 Radeon RX 560 Radeon RX 460 GeForce GTX 980 GeForce GTX 780 Ti GeForce GTX 970 GeForce GTX 1050 GeForce GTX 960 5 10 15 20 25 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 +/- 0.04, N = 3 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 SE +/- 0.08, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 3.03 3.50 3.55 3.71 4.05 4.22 4.25 4.51 6.96 7.98 15.02 15.11 15.46 17.76 19.13
Darktable Test: Masskrug - Acceleration: OpenCL OpenBenchmarking.org Seconds, Fewer Is Better Darktable 2.0.3 Test: Masskrug - Acceleration: OpenCL Radeon R9 Fury GeForce GTX 1070 GeForce GTX 1080 GeForce GTX 1080 Ti GeForce GTX 1060 GeForce GTX 980 Radeon RX 480 Radeon RX 580 GeForce GTX 970 GeForce GTX 980 Ti GeForce GTX 1050 GeForce GTX 960 GeForce GTX 780 Ti Radeon RX 460 Radeon RX 560 0.0653 0.1306 0.1959 0.2612 0.3265 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 +/- 0.01, 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 = 3 0.13 0.13 0.13 0.13 0.14 0.16 0.17 0.17 0.17 0.17 0.17 0.20 0.22 0.29 0.29
Darktable Test: Server Room - Acceleration: OpenCL OpenBenchmarking.org Seconds, Fewer Is Better Darktable 2.0.3 Test: Server Room - Acceleration: OpenCL GeForce GTX 1080 GeForce GTX 1080 Ti GeForce GTX 1060 GeForce GTX 1070 Radeon R9 Fury Radeon RX 580 Radeon RX 480 GeForce GTX 970 GeForce GTX 980 GeForce GTX 980 Ti GeForce GTX 1050 GeForce GTX 960 GeForce GTX 780 Ti Radeon RX 460 Radeon RX 560 0.0698 0.1396 0.2094 0.2792 0.349 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 +/- 0.00, 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 +/- 0.00, N = 3 SE +/- 0.00, N = 3 0.13 0.13 0.14 0.14 0.15 0.16 0.17 0.17 0.17 0.17 0.18 0.20 0.21 0.28 0.31
Darktable Test: Boat - Acceleration: OpenCL OpenBenchmarking.org Seconds, Fewer Is Better Darktable 2.2.5 Test: Boat - Acceleration: OpenCL Gigabyte NVIDIA GeForce GTX 1050 9 18 27 36 45 SE +/- 1.05, N = 6 37.49
Darktable Test: Masskrug - Acceleration: OpenCL OpenBenchmarking.org Seconds, Fewer Is Better Darktable 2.2.5 Test: Masskrug - Acceleration: OpenCL Gigabyte NVIDIA GeForce GTX 1050 11 22 33 44 55 SE +/- 1.47, N = 6 47.03
Darktable Test: Server Room - Acceleration: OpenCL OpenBenchmarking.org Seconds, Fewer Is Better Darktable 2.2.5 Test: Server Room - Acceleration: OpenCL Gigabyte NVIDIA GeForce GTX 1050 7 14 21 28 35 SE +/- 0.64, N = 6 28.19
Ethereum Ethminer Device: GPU OpenCL OpenBenchmarking.org H/s, More Is Better Ethereum Ethminer 1.2.9 Device: GPU OpenCL GeForce GTX 1080 Ti GeForce GTX 1070 GeForce GTX 1080 GeForce GTX 980 GeForce GTX 1060 GeForce GTX 980 Ti GeForce GTX 970 Radeon R9 Fury GeForce GTX 780 Ti Radeon RX 580 Radeon RX 480 GeForce GTX 1050 GeForce GTX 960 Radeon RX 560 Radeon RX 460 7M 14M 21M 28M 35M SE +/- 64820.10, N = 3 SE +/- 48804.13, N = 3 SE +/- 45147.00, N = 3 SE +/- 103401.33, N = 3 SE +/- 94663.00, N = 3 SE +/- 4369.33, N = 3 SE +/- 37158.58, N = 3 SE +/- 43860.23, N = 3 SE +/- 27284.72, N = 3 SE +/- 430364.89, N = 3 SE +/- 28649.78, N = 3 SE +/- 21845.33, N = 3 SE +/- 21845.33, N = 3 SE +/- 46807.89, N = 3 SE +/- 7706.19, N = 3 31569419 25311459 20721026 19740899 18653001 18018030 17974339 16587889 15689318 12811559 12543590 11398894 10341580 7203134 7176920 MIN: 29989273 / MAX: 31745638 MIN: 24064819 / MAX: 25454182 MIN: 19660800 / MAX: 20840448 MIN: 17694720 / MAX: 19922944 MIN: 16672358 / MAX: 18821939 MIN: 17301504 / MAX: 18271436 MIN: 17091788 / MAX: 18087936 MIN: 2097152 / MAX: 19424870 MIN: 14129561 / MAX: 15938355 MIN: 1546649 / MAX: 15964569 MIN: 1572864 / MAX: 14680064 MIN: 10826547 / MAX: 11481907 MIN: 9804185 / MAX: 10407116 MIN: 760217 / MAX: 8545894 MIN: 760217 / MAX: 8493465
Ethereum Ethminer Device: GPU OpenCL OpenBenchmarking.org H/s Per Watt, More Is Better Ethereum Ethminer 1.2.9 Device: GPU OpenCL GeForce GTX 1070 GeForce GTX 1080 Ti GeForce GTX 1060 GeForce GTX 1080 GeForce GTX 1050 GeForce GTX 980 GeForce GTX 970 Radeon R9 Fury GeForce GTX 980 Ti Radeon RX 480 Radeon RX 580 GeForce GTX 960 Radeon RX 560 Radeon RX 460 GeForce GTX 780 Ti 30K 60K 90K 120K 150K 135952.92 126492.71 124485.61 115090.84 102539.74 96016.05 94763.88 80363.35 76784.79 72609.92 72012.98 70561.75 69113.46 67367.83 60749.50
Ethereum Ethminer System Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better Ethereum Ethminer 1.2.9 System Power Consumption Monitor Radeon RX 560 Radeon RX 460 GeForce GTX 1050 GeForce GTX 960 GeForce GTX 1060 Radeon RX 480 Radeon RX 580 GeForce GTX 1080 GeForce GTX 1070 GeForce GTX 970 GeForce GTX 980 Radeon R9 Fury GeForce GTX 980 Ti GeForce GTX 1080 Ti GeForce GTX 780 Ti 50 100 150 200 250 Min: 51.4 / Avg: 104.22 / Max: 112.7 Min: 85.7 / Avg: 106.53 / Max: 112.1 Min: 68.7 / Avg: 111.17 / Max: 114.5 Min: 85.6 / Avg: 146.56 / Max: 150 Min: 77.6 / Avg: 149.84 / Max: 157.9 Min: 68.2 / Avg: 172.75 / Max: 197.9 Min: 61.4 / Avg: 177.91 / Max: 205.3 Min: 98.1 / Avg: 180.04 / Max: 188 Min: 90.4 / Avg: 186.18 / Max: 198.1 Min: 97.2 / Avg: 189.68 / Max: 199.4 Min: 116.2 / Avg: 205.6 / Max: 219.2 Min: 100.1 / Avg: 206.41 / Max: 233.5 Min: 132.5 / Avg: 234.66 / Max: 245.4 Min: 129.5 / Avg: 249.58 / Max: 268.7 Min: 58.9 / Avg: 258.26 / Max: 287.9
FAHBench Phoronix Test Suite v7.2.1 OpenBenchmarking.org Ns Per Day, More Is Better FAHBench 2.3.2 Phoronix Test Suite v7.2.1 GeForce GTX 1080 Ti GeForce GTX 1080 GeForce GTX 1070 GeForce GTX 980 Ti GeForce GTX 1060 GeForce GTX 980 GeForce GTX 970 GeForce GTX 780 Ti GeForce GTX 960 GeForce GTX 1050 40 80 120 160 200 SE +/- 0.03, N = 3 SE +/- 0.04, N = 3 SE +/- 0.01, N = 3 SE +/- 0.07, N = 3 SE +/- 0.05, N = 3 SE +/- 0.02, N = 3 SE +/- 0.00, N = 3 SE +/- 0.06, N = 3 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 186.33 146.29 132.83 109.12 97.88 97.56 86.07 72.76 58.59 49.72
FAHBench Phoronix Test Suite v7.2.1 OpenBenchmarking.org Ns Per Day Per Watt, More Is Better FAHBench 2.3.2 Phoronix Test Suite v7.2.1 GeForce GTX 1080 Ti GeForce GTX 1080 GeForce GTX 1070 GeForce GTX 1060 GeForce GTX 980 GeForce GTX 980 Ti GeForce GTX 970 GeForce GTX 1050 GeForce GTX 960 GeForce GTX 780 Ti 0.2295 0.459 0.6885 0.918 1.1475 1.02 1.01 0.96 0.85 0.67 0.63 0.62 0.54 0.50 0.36
FAHBench System Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better FAHBench 2.3.2 System Power Consumption Monitor GeForce GTX 1050 GeForce GTX 1060 GeForce GTX 1070 GeForce GTX 780 Ti Radeon RX 580 GeForce GTX 960 GeForce GTX 970 GeForce GTX 980 GeForce GTX 1080 GeForce GTX 980 Ti GeForce GTX 1080 Ti 50 100 150 200 250 Min: 55.3 / Avg: 92.89 / Max: 108.2 Min: 47.9 / Avg: 114.63 / Max: 153.4 Min: 70.8 / Avg: 138.5 / Max: 191.8 Min: 63.3 / Avg: 204.01 / Max: 297.5 Min: 72.8 / Avg: 118.26 / Max: 155.6 Min: 76.4 / Avg: 139.24 / Max: 188.5 Min: 56.6 / Avg: 145.25 / Max: 208.4 Min: 71.4 / Avg: 145.55 / Max: 207.6 Min: 61.3 / Avg: 172.14 / Max: 240.9 Min: 76.9 / Avg: 183.12 / Max: 261.1
Lulesh OpenCL Phoronix Test Suite v7.2.1 OpenBenchmarking.org z/s, More Is Better Lulesh OpenCL 2017-07-06 Phoronix Test Suite v7.2.1 Radeon RX 480 Radeon RX 580 Radeon RX 560 Radeon R9 Fury Radeon RX 460 200 400 600 800 1000 SE +/- 5.33, N = 3 SE +/- 2.24, N = 3 SE +/- 2.33, N = 3 SE +/- 3.37, N = 3 SE +/- 0.68, N = 3 878.41 866.99 852.97 845.27 840.73 1. (CXX) g++ options: -std=c++11 -lOpenCL -O3 -lm
LuxMark OpenCL Device: GPU - Scene: Luxball HDR OpenBenchmarking.org Score, More Is Better LuxMark 3.0 OpenCL Device: GPU - Scene: Luxball HDR GeForce GTX 1080 Ti GeForce GTX 1070 GeForce GTX 980 Ti GeForce GTX 1080 Radeon R9 Fury GeForce GTX 980 GeForce GTX 1060 GeForce GTX 970 Radeon RX 580 Radeon RX 480 GeForce GTX 780 Ti GeForce GTX 1050 Gigabyte NVIDIA GeForce GTX 1050 GeForce GTX 960 Radeon RX 560 Radeon RX 460 4K 8K 12K 16K 20K SE +/- 15.38, N = 3 SE +/- 1.00, N = 3 SE +/- 47.84, N = 3 SE +/- 17.53, N = 3 SE +/- 21.50, N = 3 SE +/- 27.67, N = 3 SE +/- 25.50, N = 3 SE +/- 2.52, N = 3 SE +/- 32.71, N = 3 SE +/- 26.17, N = 3 SE +/- 20.55, N = 3 SE +/- 15.24, N = 3 SE +/- 4.58, N = 3 SE +/- 29.72, N = 3 SE +/- 7.54, N = 3 SE +/- 10.00, N = 3 19842 16184 14961 12923 12894 11955 11627 10731 10160 9731 9516 6576 6457 6114 4481 3872
LuxMark OpenCL Device: GPU - Scene: Luxball HDR OpenBenchmarking.org Score Per Watt, More Is Better LuxMark 3.0 OpenCL Device: GPU - Scene: Luxball HDR GeForce GTX 1070 GeForce GTX 1060 GeForce GTX 1080 Ti GeForce GTX 1080 GeForce GTX 1050 GeForce GTX 980 Ti GeForce GTX 980 GeForce GTX 970 Radeon R9 Fury Radeon RX 580 Radeon RX 480 GeForce GTX 960 Radeon RX 560 Radeon RX 460 GeForce GTX 780 Ti 20 40 60 80 100 89.05 78.53 78.40 72.32 60.76 60.65 59.86 57.14 54.91 51.48 51.41 43.35 43.14 36.39 32.63
LuxMark System Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better LuxMark 3.0 System Power Consumption Monitor Radeon RX 560 Radeon RX 460 GeForce GTX 1050 GeForce GTX 960 GeForce GTX 1060 GeForce GTX 1080 GeForce GTX 1070 GeForce GTX 970 Radeon RX 480 Radeon RX 580 GeForce GTX 980 Radeon R9 Fury GeForce GTX 980 Ti GeForce GTX 1080 Ti GeForce GTX 780 Ti 60 120 180 240 300 Min: 52.2 / Avg: 103.88 / Max: 108 Min: 86.7 / Avg: 106.41 / Max: 107.6 Min: 107.7 / Avg: 108.23 / Max: 109.2 Min: 53 / Avg: 141.04 / Max: 144.1 Min: 107 / Avg: 148.06 / Max: 150.1 Min: 49.6 / Avg: 178.68 / Max: 182.4 Min: 49.6 / Avg: 181.74 / Max: 188.2 Min: 184.3 / Avg: 187.81 / Max: 188.8 Min: 69.1 / Avg: 189.27 / Max: 195.2 Min: 74.8 / Avg: 197.35 / Max: 204.2 Min: 56 / Avg: 199.7 / Max: 209 Min: 62 / Avg: 234.81 / Max: 246.5 Min: 156.1 / Avg: 246.7 / Max: 251.3 Min: 72.7 / Avg: 253.08 / Max: 259.9 Min: 59.2 / Avg: 291.66 / Max: 308.3
LuxMark System Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better LuxMark 3.0 System Power Consumption Monitor Radeon RX 560 Radeon RX 460 GeForce GTX 1060 GeForce GTX 1080 Radeon RX 480 Radeon R9 Fury 20 40 60 80 100 Min: 52.3 / Avg: 77.41 / Max: 92.2 Min: 54.7 / Avg: 81.4 / Max: 97.2 Min: 49.1 / Avg: 86.49 / Max: 100.7 Min: 51 / Avg: 97.96 / Max: 104.7 Min: 69.1 / Avg: 103.14 / Max: 116.8 Min: 64 / Avg: 116.66 / Max: 120
LuxMark OpenCL Device: GPU - Scene: Hotel OpenBenchmarking.org Score, More Is Better LuxMark 3.0 OpenCL Device: GPU - Scene: Hotel GeForce GTX 1080 Ti GeForce GTX 1080 GeForce GTX 1070 GeForce GTX 980 Ti GeForce GTX 980 GeForce GTX 1060 GeForce GTX 970 Radeon R9 Fury Radeon RX 580 GeForce GTX 780 Ti Gigabyte NVIDIA GeForce GTX 1050 GeForce GTX 960 Radeon RX 480 GeForce GTX 1050 Radeon RX 560 Radeon RX 460 800 1600 2400 3200 4000 SE +/- 7.17, N = 3 SE +/- 11.17, N = 3 SE +/- 15.56, N = 3 SE +/- 3.67, N = 3 SE +/- 1.86, N = 3 SE +/- 2.08, N = 3 SE +/- 2.52, N = 3 SE +/- 4.04, N = 3 SE +/- 6.03, N = 3 SE +/- 5.13, N = 3 SE +/- 5.84, N = 3 SE +/- 4.51, N = 3 SE +/- 1.33, N = 3 SE +/- 3.00, N = 3 SE +/- 0.58, N = 3 3739 2643 2506 2034 1863 1782 1756 1369 1206 1200 1127 1125 1063 1023 507 430
LuxMark OpenCL Device: GPU - Scene: Hotel OpenBenchmarking.org Score Per Watt, More Is Better LuxMark 3.0 OpenCL Device: GPU - Scene: Hotel GeForce GTX 1080 Ti GeForce GTX 1080 GeForce GTX 1070 GeForce GTX 1060 GeForce GTX 1050 GeForce GTX 970 GeForce GTX 980 GeForce GTX 980 Ti GeForce GTX 960 Radeon RX 580 Radeon R9 Fury Radeon RX 480 Radeon RX 560 GeForce GTX 780 Ti Radeon RX 460 4 8 12 16 20 13.96 13.70 13.70 12.40 9.61 9.24 9.22 8.73 7.56 6.83 6.34 6.29 5.15 4.38 4.28
LuxMark System Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better LuxMark 3.0 System Power Consumption Monitor Radeon RX 560 Radeon RX 460 GeForce GTX 1050 GeForce GTX 1060 GeForce GTX 960 Radeon RX 480 Radeon RX 580 GeForce GTX 1070 GeForce GTX 970 GeForce GTX 1080 GeForce GTX 980 Radeon R9 Fury GeForce GTX 980 Ti GeForce GTX 1080 Ti GeForce GTX 780 Ti 50 100 150 200 250 Min: 80.1 / Avg: 98.46 / Max: 103.2 Min: 53.5 / Avg: 100.49 / Max: 105 Min: 70.3 / Avg: 106.45 / Max: 108.5 Min: 53.3 / Avg: 143.77 / Max: 149.4 Min: 53.1 / Avg: 148.91 / Max: 153.1 Min: 68.8 / Avg: 169.01 / Max: 182.7 Min: 62.7 / Avg: 176.61 / Max: 197.2 Min: 52.1 / Avg: 182.92 / Max: 188.9 Min: 56 / Avg: 190.14 / Max: 193.4 Min: 49.6 / Avg: 192.91 / Max: 200 Min: 101.1 / Avg: 201.97 / Max: 211.7 Min: 63.6 / Avg: 215.97 / Max: 239.5 Min: 61.4 / Avg: 233.07 / Max: 251.9 Min: 134.6 / Avg: 267.82 / Max: 279.4 Min: 61.1 / Avg: 274.22 / Max: 293
Mixbench Benchmark: Single Precision OpenBenchmarking.org GFLOPS, More Is Better Mixbench 2016-06-06 Benchmark: Single Precision GeForce GTX 1080 Radeon R9 Fury GeForce GTX 1070 Radeon RX 580 GeForce GTX 980 Ti Radeon RX 480 GeForce GTX 980 GeForce GTX 1060 GeForce GTX 780 Ti GeForce GTX 970 GeForce GTX 960 Radeon RX 560 GeForce GTX 1050 Radeon RX 460 2K 4K 6K 8K 10K SE +/- 4.95, N = 3 SE +/- 1.93, N = 3 SE +/- 41.33, N = 3 SE +/- 0.69, N = 3 SE +/- 9.24, N = 3 SE +/- 2.47, N = 3 SE +/- 4.21, N = 3 SE +/- 0.40, N = 3 SE +/- 1.52, N = 3 SE +/- 1.69, N = 3 SE +/- 39.77, N = 3 SE +/- 163.68, N = 3 SE +/- 0.48, N = 3 SE +/- 88.43, N = 3 8489.90 6501.19 6374.80 5854.94 5816.30 5442.89 4692.97 4403.62 4260.60 4121.47 2726.15 2303.86 2037.30 1851.75 1. (CXX) g++ options: -lm -lstdc++ -lOpenCL -lrt -O2
Mixbench Benchmark: Double Precision OpenBenchmarking.org GFLOPS, More Is Better Mixbench 2016-06-06 Benchmark: Double Precision Radeon R9 Fury Radeon RX 580 Radeon RX 480 GeForce GTX 1080 GeForce GTX 780 Ti GeForce GTX 1070 GeForce GTX 980 Ti GeForce GTX 980 GeForce GTX 1060 Radeon RX 560 GeForce GTX 970 Radeon RX 460 GeForce GTX 960 GeForce GTX 1050 100 200 300 400 500 SE +/- 0.01, N = 3 SE +/- 0.03, N = 3 SE +/- 0.03, N = 3 SE +/- 1.59, N = 3 SE +/- 0.01, N = 3 SE +/- 0.27, N = 3 SE +/- 0.08, N = 3 SE +/- 0.02, N = 3 SE +/- 0.12, N = 3 SE +/- 14.51, N = 3 SE +/- 0.02, N = 3 SE +/- 0.30, N = 3 SE +/- 0.22, N = 3 SE +/- 0.06, N = 3 440.79 389.88 362.18 293.93 245.04 222.10 197.04 159.89 152.40 149.51 137.54 134.11 92.73 66.66 1. (CXX) g++ options: -lm -lstdc++ -lOpenCL -lrt -O2
Mixbench Benchmark: Integer OpenBenchmarking.org GIOPS, More Is Better Mixbench 2016-06-06 Benchmark: Integer GeForce GTX 1080 GeForce GTX 1070 GeForce GTX 980 Ti GeForce GTX 980 Radeon R9 Fury GeForce GTX 1060 Radeon RX 580 GeForce GTX 970 Radeon RX 480 GeForce GTX 780 Ti GeForce GTX 960 GeForce GTX 1050 Radeon RX 560 Radeon RX 460 600 1200 1800 2400 3000 SE +/- 4.48, N = 3 SE +/- 0.40, N = 3 SE +/- 1.79, N = 3 SE +/- 1.49, N = 3 SE +/- 0.02, N = 3 SE +/- 0.73, N = 3 SE +/- 0.12, N = 3 SE +/- 0.33, N = 3 SE +/- 0.02, N = 3 SE +/- 0.33, N = 3 SE +/- 1.74, N = 3 SE +/- 0.38, N = 3 SE +/- 11.00, N = 3 SE +/- 0.01, N = 3 2656.67 2027.70 1717.69 1404.21 1385.89 1370.35 1226.84 1220.95 1139.87 967.53 835.02 615.44 487.82 422.38 1. (CXX) g++ options: -lm -lstdc++ -lOpenCL -lrt -O2
Mixbench System Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better Mixbench 2016-06-06 System Power Consumption Monitor GeForce GTX 1080 GeForce GTX 1070 GeForce GTX 960 GeForce GTX 970 GeForce GTX 980 GeForce GTX 980 Ti Radeon RX 460 Radeon R9 Fury Radeon RX 560 Radeon RX 480 Radeon RX 580 GeForce GTX 1060 GeForce GTX 1050 GeForce GTX 780 Ti 40 80 120 160 200 Min: 54 / Avg: 79.72 / Max: 101.1 Min: 63.5 / Avg: 84.5 / Max: 122.7 Min: 82.1 / Avg: 84.7 / Max: 92 Min: 67.8 / Avg: 95.82 / Max: 106.7 Min: 104.3 / Avg: 113.58 / Max: 133
Rodinia Test: OpenCL Particle Filter OpenBenchmarking.org Seconds, Fewer Is Better Rodinia 2.4 Test: OpenCL Particle Filter GeForce GTX 1080 Ti GeForce GTX 1080 Radeon RX 580 GeForce GTX 1070 GeForce GTX 980 Ti GeForce GTX 980 GeForce GTX 1060 GeForce GTX 970 GeForce GTX 780 Ti GeForce GTX 960 GeForce GTX 1050 6 12 18 24 30 SE +/- 0.03, N = 3 SE +/- 0.01, N = 3 SE +/- 0.15, N = 3 SE +/- 0.02, N = 3 SE +/- 0.09, N = 3 SE +/- 0.02, N = 3 SE +/- 0.08, N = 3 SE +/- 0.02, N = 3 SE +/- 0.05, N = 3 SE +/- 0.04, N = 3 SE +/- 0.03, N = 3 5.03 6.56 6.62 8.27 10.14 11.87 12.15 13.11 15.30 18.47 26.09 1. (CXX) g++ options: -O2 -lOpenCL
SHOC Scalable HeterOgeneous Computing Target: OpenCL - Benchmark: Bus Speed Download OpenBenchmarking.org GB/s, More Is Better SHOC Scalable HeterOgeneous Computing 2015-11-10 Target: OpenCL - Benchmark: Bus Speed Download GeForce GTX 1080 Ti GeForce GTX 1080 GeForce GTX 1070 GeForce GTX 1050 GeForce GTX 980 Ti GeForce GTX 980 GeForce GTX 970 GeForce GTX 960 GeForce GTX 780 Ti GeForce GTX 1060 Radeon RX 580 Radeon RX 480 Radeon R9 Fury Radeon RX 560 Radeon RX 460 3 6 9 12 15 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 +/- 0.00, 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 +/- 0.06, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 13.00 13.00 13.00 13.00 13.00 13.00 13.00 13.00 13.00 12.99 11.49 11.47 11.38 5.72 5.71 1. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -lmpi_cxx -lmpi
SHOC Scalable HeterOgeneous Computing Target: OpenCL - Benchmark: Bus Speed Readback OpenBenchmarking.org GB/s, More Is Better SHOC Scalable HeterOgeneous Computing 2015-11-10 Target: OpenCL - Benchmark: Bus Speed Readback GeForce GTX 1080 Ti GeForce GTX 1080 GeForce GTX 1070 GeForce GTX 1060 GeForce GTX 1050 GeForce GTX 980 Ti GeForce GTX 980 GeForce GTX 970 GeForce GTX 780 Ti GeForce GTX 960 Radeon R9 Fury Radeon RX 480 Radeon RX 580 Radeon RX 560 Radeon RX 460 3 6 9 12 15 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 +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.06, N = 3 SE +/- 0.00, N = 3 SE +/- 0.18, N = 3 SE +/- 0.03, N = 3 SE +/- 0.01, N = 3 13.20 13.20 13.20 13.20 13.20 13.20 13.20 13.20 13.20 13.19 10.61 10.42 10.21 5.24 5.20 1. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -lmpi_cxx -lmpi
SHOC Scalable HeterOgeneous Computing Target: OpenCL - Benchmark: Texture Read Bandwidth OpenBenchmarking.org GB/s, More Is Better SHOC Scalable HeterOgeneous Computing 2015-11-10 Target: OpenCL - Benchmark: Texture Read Bandwidth GeForce GTX 1080 Ti GeForce GTX 1080 GeForce GTX 1070 GeForce GTX 1060 GeForce GTX 980 Ti GeForce GTX 980 GeForce GTX 970 GeForce GTX 780 Ti GeForce GTX 960 GeForce GTX 1050 Radeon R9 Fury Radeon RX 580 Radeon RX 480 Radeon RX 560 Radeon RX 460 130 260 390 520 650 SE +/- 0.51, N = 3 SE +/- 0.26, N = 3 SE +/- 0.30, N = 3 SE +/- 1.28, N = 3 SE +/- 0.26, N = 3 SE +/- 1.39, N = 3 SE +/- 0.52, N = 3 SE +/- 0.04, N = 3 SE +/- 0.53, N = 3 SE +/- 1.02, N = 3 SE +/- 0.34, N = 3 SE +/- 0.90, N = 3 SE +/- 3.90, N = 3 SE +/- 1.64, N = 3 SE +/- 0.37, N = 3 600.45 528.02 456.70 381.92 350.63 333.05 288.61 286.87 279.37 276.45 239.03 190.13 176.79 105.19 83.67 1. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -lmpi_cxx -lmpi
SHOC Scalable HeterOgeneous Computing Target: OpenCL - Benchmark: Texture Read Bandwidth OpenBenchmarking.org GB/s Per Watt, More Is Better SHOC Scalable HeterOgeneous Computing 2015-11-10 Target: OpenCL - Benchmark: Texture Read Bandwidth GeForce GTX 1080 GeForce GTX 1060 GeForce GTX 1080 Ti GeForce GTX 1050 GeForce GTX 1070 GeForce GTX 960 GeForce GTX 980 GeForce GTX 970 GeForce GTX 980 Ti Radeon R9 Fury Radeon RX 580 Radeon RX 480 Radeon RX 560 GeForce GTX 780 Ti Radeon RX 460 0.819 1.638 2.457 3.276 4.095 3.64 3.16 3.15 3.12 2.95 2.47 2.25 1.84 1.82 1.51 1.45 1.33 1.21 1.12 0.96
SHOC Scalable HeterOgeneous Computing System Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better SHOC Scalable HeterOgeneous Computing 2015-11-10 System Power Consumption Monitor Radeon RX 560 Radeon RX 460 GeForce GTX 1050 GeForce GTX 960 GeForce GTX 1060 Radeon RX 580 Radeon RX 480 GeForce GTX 1080 GeForce GTX 980 GeForce GTX 1070 GeForce GTX 970 Radeon R9 Fury GeForce GTX 1080 Ti GeForce GTX 980 Ti GeForce GTX 780 Ti 50 100 150 200 250 Min: 67.3 / Avg: 86.87 / Max: 100.5 Min: 65.8 / Avg: 87.53 / Max: 94.6 Min: 46.9 / Avg: 88.68 / Max: 105.3 Min: 54.1 / Avg: 113.15 / Max: 128.5 Min: 108 / Avg: 120.86 / Max: 129.2 Min: 79.6 / Avg: 131.39 / Max: 155.7 Min: 118.1 / Avg: 133.18 / Max: 166.9 Min: 127.5 / Avg: 145.13 / Max: 156.9 Min: 101.1 / Avg: 147.85 / Max: 174.4 Min: 150.6 / Avg: 154.6 / Max: 158.3 Min: 147 / Avg: 156.96 / Max: 163.8 Min: 106.4 / Avg: 157.83 / Max: 194.9 Min: 129.5 / Avg: 190.56 / Max: 220 Min: 149 / Avg: 192.16 / Max: 218.2 Min: 204 / Avg: 255.96 / Max: 279.4
SHOC Scalable HeterOgeneous Computing Target: OpenCL - Benchmark: FFT SP OpenBenchmarking.org GFLOPS, More Is Better SHOC Scalable HeterOgeneous Computing 2015-11-10 Target: OpenCL - Benchmark: FFT SP GeForce GTX 1080 Ti GeForce GTX 980 Ti GeForce GTX 1080 GeForce GTX 1070 Radeon R9 Fury Radeon RX 580 Radeon RX 480 GeForce GTX 980 GeForce GTX 780 Ti GeForce GTX 1060 GeForce GTX 970 GeForce GTX 1050 Radeon RX 560 GeForce GTX 960 Radeon RX 460 200 400 600 800 1000 SE +/- 4.98, N = 3 SE +/- 19.98, N = 3 SE +/- 2.36, N = 3 SE +/- 3.71, N = 3 SE +/- 0.01, N = 3 SE +/- 0.09, N = 3 SE +/- 0.28, N = 3 SE +/- 4.18, N = 3 SE +/- 21.17, N = 3 SE +/- 3.80, N = 3 SE +/- 2.36, N = 3 SE +/- 10.20, N = 3 SE +/- 0.04, N = 3 SE +/- 0.54, N = 3 SE +/- 0.02, N = 3 980.92 694.57 652.64 553.04 550.95 496.76 460.84 447.24 429.63 404.59 384.81 253.32 208.75 207.09 173.12 1. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -lmpi_cxx -lmpi
SHOC Scalable HeterOgeneous Computing Target: OpenCL - Benchmark: MD5 Hash OpenBenchmarking.org GHash/s, More Is Better SHOC Scalable HeterOgeneous Computing 2015-11-10 Target: OpenCL - Benchmark: MD5 Hash GeForce GTX 1080 Ti GeForce GTX 1080 GeForce GTX 1070 GeForce GTX 980 Ti GeForce GTX 980 GeForce GTX 1060 GeForce GTX 970 GeForce GTX 780 Ti GeForce GTX 960 GeForce GTX 1050 5 10 15 20 25 SE +/- 0.08, N = 3 SE +/- 0.05, 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 +/- 0.02, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 19.99 14.36 10.69 9.29 7.56 7.36 6.54 4.68 4.49 3.23 1. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -lmpi_cxx -lmpi
SHOC Scalable HeterOgeneous Computing System Power Consumption Monitor OpenBenchmarking.org Watts, Fewer Is Better SHOC Scalable HeterOgeneous Computing 2015-11-10 System Power Consumption Monitor GeForce GTX 1080 Ti GeForce GTX 780 Ti Radeon RX 560 Radeon RX 580 GeForce GTX 960 GeForce GTX 980 GeForce GTX 980 Ti GeForce GTX 1050 GeForce GTX 1060 GeForce GTX 1080 GeForce GTX 1070 Radeon RX 460 GeForce GTX 970 Radeon R9 Fury Radeon RX 480 30 60 90 120 150 Min: 51 / Avg: 56.9 / Max: 62.8 Min: 61.2 / Avg: 68.8 / Max: 76.4 Min: 53.5 / Avg: 72.85 / Max: 92.2 Min: 46.7 / Avg: 67.65 / Max: 88.6 Min: 48.4 / Avg: 71 / Max: 93.6 Min: 49.8 / Avg: 74.45 / Max: 99.1 Min: 65.8 / Avg: 75.45 / Max: 85.1 Min: 56.1 / Avg: 84 / Max: 111.9 Min: 89.6 / Avg: 98.9 / Max: 108.2 Min: 68.6 / Avg: 98.95 / Max: 129.3
System Power Consumption Monitor Phoronix Test Suite System Monitoring OpenBenchmarking.org Watts System Power Consumption Monitor Phoronix Test Suite System Monitoring Radeon RX 560 Radeon RX 460 GeForce GTX 1050 GeForce GTX 1060 GeForce GTX 960 Radeon RX 480 Radeon RX 580 GeForce GTX 1070 GeForce GTX 1080 GeForce GTX 970 GeForce GTX 980 Radeon R9 Fury GeForce GTX 1080 Ti GeForce GTX 980 Ti GeForce GTX 780 Ti 60 120 180 240 300 Min: 51 / Avg: 82.97 / Max: 121.4 Min: 53.2 / Avg: 84.6 / Max: 134 Min: 46.4 / Avg: 90.71 / Max: 132.3 Min: 47.8 / Avg: 109.18 / Max: 185.3 Min: 53 / Avg: 116.21 / Max: 204 Min: 66.1 / Avg: 129.75 / Max: 197.9 Min: 61.1 / Avg: 135.51 / Max: 221.1 Min: 49.6 / Avg: 139.11 / Max: 198.1 Min: 48.9 / Avg: 140.7 / Max: 256.5 Min: 55 / Avg: 141.74 / Max: 216.6 Min: 55.2 / Avg: 145.65 / Max: 246 Min: 61.5 / Avg: 150.69 / Max: 294.3 Min: 53.5 / Avg: 184.89 / Max: 279.4 Min: 60.3 / Avg: 185.09 / Max: 333.7 Min: 58.7 / Avg: 201.83 / Max: 337.7
ViennaCL OpenCL LU Factorization OpenBenchmarking.org GFLOPS, More Is Better ViennaCL 1.4.2 OpenCL LU Factorization GeForce GTX 1080 Ti GeForce GTX 1080 GeForce GTX 1070 GeForce GTX 980 Ti GeForce GTX 780 Ti GeForce GTX 980 GeForce GTX 1060 GeForce GTX 970 GeForce GTX 960 GeForce GTX 1050 Radeon R9 Fury Radeon RX 580 Radeon RX 480 Radeon RX 560 Radeon RX 460 14 28 42 56 70 SE +/- 0.01, N = 3 SE +/- 0.08, N = 3 SE +/- 0.02, N = 3 SE +/- 0.10, N = 3 SE +/- 0.18, N = 3 SE +/- 0.06, N = 3 SE +/- 0.04, N = 3 SE +/- 0.04, N = 3 SE +/- 0.05, N = 3 SE +/- 0.01, N = 3 SE +/- 0.03, N = 3 SE +/- 0.78, N = 3 SE +/- 0.37, N = 3 SE +/- 2.19, N = 3 SE +/- 0.27, N = 3 63.36 61.06 58.69 56.98 56.89 54.76 54.25 52.87 47.42 42.12 20.60 13.01 12.36 9.54 7.33 1. (CXX) g++ options: -rdynamic -lOpenCL
Xsbench OpenCL Phoronix Test Suite v7.2.1 OpenBenchmarking.org Lookups/s, More Is Better Xsbench OpenCL 2017-07-06 Phoronix Test Suite v7.2.1 Radeon R9 Fury Radeon RX 480 Radeon RX 580 Radeon RX 560 Radeon RX 460 20M 40M 60M 80M 100M SE +/- 81529.87, N = 3 SE +/- 51063.25, N = 3 SE +/- 133262.11, N = 3 SE +/- 22251.35, N = 3 SE +/- 84388.68, N = 3 85206540 74635621 74435707 38606004 36982576 1. (CC) gcc options: -std=gnu99 -fopenmp -O3 -lm -lOpenCL
Phoronix Test Suite v10.8.4