OpenCL CUDA NVIDIA GPGPU Linux Tests All Maxwell and various Kepler graphics cards tested on the NVIDIA Linux driver. Benchmarks by Michael Larabel for a future article on Phoronix.com just delivering various GPGPU benchmarks for reference purposes. GeForce GTX 680: Processor: Intel Core i5-6600K @ 3.50GHz (4 Cores), Motherboard: MSI Z170A GAMING PRO (MS-7984) v1.0, Chipset: Intel Device 191f, Memory: 16384MB, Disk: 256GB TS256GSSD370S, Graphics: NVIDIA GeForce GTX 680 2048MB (1006/3004MHz), Audio: Intel Device a170, Network: Intel Device 15b8 OS: Ubuntu 14.04, Kernel: 3.19.0-33-generic (x86_64), Desktop: Unity 7.2.5, Display Server: X Server 1.17.1, Display Driver: NVIDIA 352.39, OpenGL: 4.3.0, Compiler: GCC 4.8.4 + Clang 3.4-1ubuntu3 + CUDA 7.5, File-System: ext4, Screen Resolution: 3840x2160 GeForce GTX 750: Processor: Intel Core i5-6600K @ 3.50GHz (4 Cores), Motherboard: MSI Z170A GAMING PRO (MS-7984) v1.0, Chipset: Intel Device 191f, Memory: 16384MB, Disk: 256GB TS256GSSD370S, Graphics: eVGA NVIDIA GeForce GTX 750 1024MB (1019/2505MHz), Audio: Intel Device a170, Network: Intel Device 15b8 OS: Ubuntu 14.04, Kernel: 3.19.0-33-generic (x86_64), Desktop: Unity 7.2.5, Display Server: X Server 1.17.1, Display Driver: NVIDIA 352.39, OpenGL: 4.3.0, Compiler: GCC 4.8.4 + Clang 3.4-1ubuntu3 + CUDA 7.5, File-System: ext4, Screen Resolution: 3840x2160 GeForce GTX 760: Processor: Intel Core i5-6600K @ 3.50GHz (4 Cores), Motherboard: MSI Z170A GAMING PRO (MS-7984) v1.0, Chipset: Intel Device 191f, Memory: 16384MB, Disk: 256GB TS256GSSD370S, Graphics: NVIDIA GeForce GTX 760 2048MB (980/3004MHz), Audio: Intel Device a170, Network: Intel Device 15b8 OS: Ubuntu 14.04, Kernel: 3.19.0-33-generic (x86_64), Desktop: Unity 7.2.5, Display Server: X Server 1.17.1, Display Driver: NVIDIA 352.39, OpenGL: 4.3.0, Compiler: GCC 4.8.4 + Clang 3.4-1ubuntu3 + CUDA 7.5, File-System: ext4, Screen Resolution: 3840x2160 GeForce GTX 780 Ti: Processor: Intel Core i5-6600K @ 3.50GHz (4 Cores), Motherboard: MSI Z170A GAMING PRO (MS-7984) v1.0, Chipset: Intel Device 191f, Memory: 16384MB, Disk: 256GB TS256GSSD370S, Graphics: NVIDIA GeForce GTX 780 Ti 3072MB (875/3500MHz), Audio: Intel Device a170, Network: Intel Device 15b8 OS: Ubuntu 14.04, Kernel: 3.19.0-33-generic (x86_64), Desktop: Unity 7.2.5, Display Server: X Server 1.17.1, Display Driver: NVIDIA 352.39, OpenGL: 4.3.0, Compiler: GCC 4.8.4 + Clang 3.4-1ubuntu3 + CUDA 7.5, File-System: ext4, Screen Resolution: 3840x2160 GeForce GTX 950: Processor: Intel Core i5-6600K @ 3.50GHz (4 Cores), Motherboard: MSI Z170A GAMING PRO (MS-7984) v1.0, Chipset: Intel Device 191f, Memory: 16384MB, Disk: 256GB TS256GSSD370S, Graphics: eVGA NVIDIA GeForce GTX 950 2048MB (135/405MHz), Audio: Intel Device a170, Network: Intel Device 15b8 OS: Ubuntu 14.04, Kernel: 3.19.0-33-generic (x86_64), Desktop: Unity 7.2.5, Display Server: X Server 1.17.1, Display Driver: NVIDIA 352.39, OpenGL: 4.3.0, Compiler: GCC 4.8.4 + Clang 3.4-1ubuntu3 + CUDA 7.5, File-System: ext4, Screen Resolution: 3840x2160 GeForce GTX 960: Processor: Intel Core i5-6600K @ 3.50GHz (4 Cores), Motherboard: MSI Z170A GAMING PRO (MS-7984) v1.0, Chipset: Intel Device 191f, Memory: 16384MB, Disk: 256GB TS256GSSD370S, Graphics: eVGA NVIDIA GeForce GTX 960 2048MB (1277/3505MHz), Audio: Intel Device a170, Network: Intel Device 15b8 OS: Ubuntu 14.04, Kernel: 3.19.0-33-generic (x86_64), Desktop: Unity 7.2.5, Display Server: X Server 1.17.1, Display Driver: NVIDIA 352.39, OpenGL: 4.3.0, Compiler: GCC 4.8.4 + Clang 3.4-1ubuntu3 + CUDA 7.5, File-System: ext4, Screen Resolution: 3840x2160 GeForce GTX 970: Processor: Intel Core i5-6600K @ 3.50GHz (4 Cores), Motherboard: MSI Z170A GAMING PRO (MS-7984) v1.0, Chipset: Intel Device 191f, Memory: 16384MB, Disk: 256GB TS256GSSD370S, Graphics: eVGA NVIDIA GeForce GTX 970 4096MB (1163/3505MHz), Audio: Intel Device a170, Network: Intel Device 15b8 OS: Ubuntu 14.04, Kernel: 3.19.0-33-generic (x86_64), Desktop: Unity 7.2.5, Display Server: X Server 1.17.1, Display Driver: NVIDIA 352.39, OpenGL: 4.3.0, Compiler: GCC 4.8.4 + Clang 3.4-1ubuntu3 + CUDA 7.5, File-System: ext4, Screen Resolution: 3840x2160 GeForce GTX 980: Processor: Intel Core i5-6600K @ 3.50GHz (4 Cores), Motherboard: MSI Z170A GAMING PRO (MS-7984) v1.0, Chipset: Intel Device 191f, Memory: 16384MB, Disk: 256GB TS256GSSD370S, Graphics: NVIDIA GeForce GTX 980 4096MB (1126/3505MHz), Audio: Intel Device a170, Network: Intel Device 15b8 OS: Ubuntu 14.04, Kernel: 3.19.0-33-generic (x86_64), Desktop: Unity 7.2.5, Display Server: X Server 1.17.1, Display Driver: NVIDIA 352.39, OpenGL: 4.3.0, Compiler: GCC 4.8.4 + Clang 3.4-1ubuntu3 + CUDA 7.5, File-System: ext4, Screen Resolution: 3840x2160 GeForce GTX 980 Ti: Processor: Intel Core i5-6600K @ 3.50GHz (4 Cores), Motherboard: MSI Z170A GAMING PRO (MS-7984) v1.0, Chipset: Intel Device 191f, Memory: 16384MB, Disk: 256GB TS256GSSD370S, Graphics: NVIDIA GeForce GTX 980 Ti 6144MB (999/3505MHz), Audio: Intel Device a170, Network: Intel Device 15b8 OS: Ubuntu 14.04, Kernel: 3.19.0-33-generic (x86_64), Desktop: Unity 7.2.5, Display Server: X Server 1.17.1, Display Driver: NVIDIA 352.39, OpenGL: 4.3.0, Compiler: GCC 4.8.4 + Clang 3.4-1ubuntu3 + CUDA 7.5, File-System: ext4, Screen Resolution: 3840x2160 GeForce GTX TITAN X: Processor: Intel Core i5-6600K @ 3.50GHz (4 Cores), Motherboard: MSI Z170A GAMING PRO (MS-7984) v1.0, Chipset: Intel Device 191f, Memory: 16384MB, Disk: 256GB TS256GSSD370S, Graphics: NVIDIA GeForce GTX TITAN X 12288MB (1001/3505MHz), Audio: Intel Device a170, Network: Intel Device 15b8 OS: Ubuntu 14.04, Kernel: 3.19.0-33-generic (x86_64), Desktop: Unity 7.2.5, Display Server: X Server 1.17.1, Display Driver: NVIDIA 352.39, OpenGL: 4.3.0, Compiler: GCC 4.8.4 + Clang 3.4-1ubuntu3 + CUDA 7.5, File-System: ext4, Screen Resolution: 3840x2160 eVGA NVIDIA GeForce GTX 1060: Processor: 2 x Intel Xeon E5-2670 0 @ 3.30GHz (32 Cores), Motherboard: HP 158A, Chipset: Intel Xeon E5/Core, Memory: 16384MB, Disk: 500GB Samsung SSD 850 + 4001GB Seagate ST4000DM005-2DP1 + 500GB Seagate ST500DM002-1BD14, Graphics: eVGA NVIDIA GeForce GTX 1060 6GB, Audio: Realtek ALC262, Network: Intel 82579LM Gigabit Connection + Broadcom Limited BCM4360 802.11ac Wireless OS: ManjaroLinux 17.0.5, Kernel: 4.9.53-1-MANJARO (x86_64), Desktop: KDE Frameworks 5, Compiler: GCC 7.2.0 + Clang 5.0.0 + CUDA 8.0, File-System: ext4, Screen Resolution: 800x600 SHOC Scalable HeterOgeneous Computing 2015-11-10 Target: CUDA - Benchmark: FFT SP GFLOPS > Higher Is Better GeForce GTX 750 ..... 113.64 |================= GeForce GTX 950 ..... 172.28 |========================== GeForce GTX 960 ..... 212.43 |================================ GeForce GTX 970 ..... 263.14 |======================================== GeForce GTX 980 ..... 289.63 |============================================ GeForce GTX 980 Ti .. 311.46 |=============================================== GeForce GTX TITAN X . 324.09 |================================================= SHOC Scalable HeterOgeneous Computing 2015-11-10 Target: CUDA - Benchmark: MD5 Hash GHash/s > Higher Is Better GeForce GTX 750 ..... 1.08 |======= GeForce GTX 950 ..... 2.36 |================ GeForce GTX 960 ..... 3.38 |======================= GeForce GTX 970 ..... 4.79 |================================= GeForce GTX 980 ..... 5.70 |======================================= GeForce GTX 980 Ti .. 6.81 |=============================================== GeForce GTX TITAN X . 7.42 |=================================================== SHOC Scalable HeterOgeneous Computing 2015-11-10 Target: OpenCL - Benchmark: FFT SP GFLOPS > Higher Is Better GeForce GTX 680 ..... 74.97 |===================== GeForce GTX 750 ..... 54.69 |=============== GeForce GTX 760 ..... 78.44 |====================== GeForce GTX 780 Ti .. 126.71 |==================================== GeForce GTX 950 ..... 63.22 |================== GeForce GTX 960 ..... 62.78 |================== GeForce GTX 970 ..... 117.23 |================================= GeForce GTX 980 ..... 140.12 |======================================= GeForce GTX 980 Ti .. 170.36 |================================================ GeForce GTX TITAN X . 173.89 |================================================= SHOC Scalable HeterOgeneous Computing 2015-11-10 Target: OpenCL - Benchmark: MD5 Hash GHash/s > Higher Is Better GeForce GTX 680 ..... 1.91 |============= GeForce GTX 750 ..... 1.07 |======= GeForce GTX 760 ..... 1.40 |========== GeForce GTX 780 Ti .. 3.78 |========================== GeForce GTX 950 ..... 2.34 |================ GeForce GTX 960 ..... 3.36 |======================= GeForce GTX 970 ..... 4.77 |================================= GeForce GTX 980 ..... 5.68 |======================================= GeForce GTX 980 Ti .. 6.79 |=============================================== GeForce GTX TITAN X . 7.41 |=================================================== SHOC Scalable HeterOgeneous Computing 2015-11-10 Target: CUDA - Benchmark: Texture Read Bandwidth GB/s > Higher Is Better GeForce GTX 750 ..... 158.42 |====================== GeForce GTX 950 ..... 326.23 |============================================= GeForce GTX 960 ..... 351.31 |================================================ GeForce GTX 970 ..... 325.16 |============================================= GeForce GTX 980 ..... 336.48 |============================================== GeForce GTX 980 Ti .. 348.92 |================================================ GeForce GTX TITAN X . 356.52 |================================================= SHOC Scalable HeterOgeneous Computing 2015-11-10 Target: OpenCL - Benchmark: Texture Read Bandwidth GB/s > Higher Is Better GeForce GTX 680 ..... 242.16 |================================== GeForce GTX 750 ..... 121.14 |================= GeForce GTX 760 ..... 170.26 |======================== GeForce GTX 780 Ti .. 286.62 |======================================== GeForce GTX 950 ..... 239.19 |================================= GeForce GTX 960 ..... 269.98 |===================================== GeForce GTX 970 ..... 283.36 |======================================= GeForce GTX 980 ..... 332.60 |============================================== GeForce GTX 980 Ti .. 345.55 |================================================ GeForce GTX TITAN X . 354.09 |================================================= ASKAP tConvolveCuda 2015-11-10 Processing: Gridding Million Grid Points Per Second > Higher Is Better GeForce GTX 950 ..... 3399.14 |=================== GeForce GTX 960 ..... 3144.85 |================== GeForce GTX 970 ..... 5325.12 |============================== GeForce GTX 980 ..... 6051.27 |================================== GeForce GTX 980 Ti .. 8320.50 |=============================================== GeForce GTX TITAN X . 8458.77 |================================================ ASKAP tConvolveCuda 2015-11-10 Processing: Degridding Million Grid Points Per Second > Higher Is Better GeForce GTX 950 ..... 5706.07 |=============== GeForce GTX 960 ..... 5290.32 |============== GeForce GTX 970 ..... 9509.14 |========================== GeForce GTX 980 ..... 11094.00 |============================== GeForce GTX 980 Ti .. 17380.60 |=============================================== GeForce GTX TITAN X . 17380.60 |=============================================== CUDA Mini-Nbody 2015-11-10 Test: Original Seconds < Lower Is Better GeForce GTX 750 ..... 180.66 |================================================= GeForce GTX 780 Ti .. 61.03 |================= GeForce GTX 950 ..... 105.30 |============================= GeForce GTX 960 ..... 82.01 |====================== GeForce GTX 970 ..... 54.32 |=============== GeForce GTX 980 ..... 45.38 |============ GeForce GTX 980 Ti .. 34.58 |========= GeForce GTX TITAN X . 32.37 |========= CUDA Mini-Nbody 2015-11-10 Test: Cache Blocking Seconds < Lower Is Better GeForce GTX 750 ..... 98.19 |================================================== GeForce GTX 780 Ti .. 29.99 |=============== GeForce GTX 950 ..... 49.89 |========================= GeForce GTX 960 ..... 37.08 |=================== GeForce GTX 970 ..... 28.53 |=============== GeForce GTX 980 ..... 25.13 |============= GeForce GTX 980 Ti .. 19.77 |========== GeForce GTX TITAN X . 18.65 |========= CUDA Mini-Nbody 2015-11-10 Test: Loop Unrolling Seconds < Lower Is Better GeForce GTX 750 ..... 89.34 |================================================== GeForce GTX 780 Ti .. 27.05 |=============== GeForce GTX 950 ..... 47.54 |=========================== GeForce GTX 960 ..... 35.35 |==================== GeForce GTX 970 ..... 26.42 |=============== GeForce GTX 980 ..... 23.88 |============= GeForce GTX 980 Ti .. 18.46 |========== GeForce GTX TITAN X . 17.59 |========== CUDA Mini-Nbody 2015-11-10 Test: SOA Data Layout Seconds < Lower Is Better GeForce GTX 750 ..... 199.95 |================================================= GeForce GTX 780 Ti .. 54.39 |============= GeForce GTX 950 ..... 108.50 |=========================== GeForce GTX 960 ..... 79.97 |==================== GeForce GTX 970 ..... 55.87 |============== GeForce GTX 980 ..... 50.15 |============ GeForce GTX 980 Ti .. 40.94 |========== GeForce GTX TITAN X . 37.43 |========= CUDA Mini-Nbody 2015-11-10 Test: Flush Denormals To Zero Seconds < Lower Is Better GeForce GTX 750 ..... 199.83 |================================================= GeForce GTX 780 Ti .. 53.26 |============= GeForce GTX 950 ..... 108.48 |=========================== GeForce GTX 960 ..... 79.84 |==================== GeForce GTX 970 ..... 55.80 |============== GeForce GTX 980 ..... 49.53 |============ GeForce GTX 980 Ti .. 40.85 |========== GeForce GTX TITAN X . 37.37 |========= JuliaGPU 1.2pts1 OpenCL Device: GPU Samples/sec > Higher Is Better GeForce GTX 680 ..... 48074789.03 |=============== GeForce GTX 750 ..... 36136874.00 |=========== GeForce GTX 760 ..... 38310650.50 |============ GeForce GTX 780 Ti .. 78839770.13 |========================= GeForce GTX 950 ..... 64913682.63 |===================== GeForce GTX 960 ..... 80042041.73 |========================= GeForce GTX 970 ..... 104144917.23 |================================= GeForce GTX 980 ..... 113830604.27 |==================================== GeForce GTX 980 Ti .. 127978049.53 |======================================== GeForce GTX TITAN X . 136037921.43 |=========================================== MandelbulbGPU 1.0pts1 OpenCL Device: GPU Samples/sec > Higher Is Better GeForce GTX 680 ..... 31636512.97 |================== GeForce GTX 750 ..... 20060275.53 |============ GeForce GTX 760 ..... 25392138.50 |=============== GeForce GTX 780 Ti .. 47400001.90 |============================ GeForce GTX 950 ..... 37156070.87 |====================== GeForce GTX 960 ..... 44953399.47 |========================== GeForce GTX 970 ..... 58811317.17 |================================== GeForce GTX 980 ..... 63616558.77 |===================================== GeForce GTX 980 Ti .. 71656708.83 |========================================== GeForce GTX TITAN X . 75614774.13 |============================================ LuxMark 3.0 OpenCL Device: GPU - Scene: Hotel Score > Higher Is Better GeForce GTX 680 ..... 577 |=============== GeForce GTX 760 ..... 463 |============ GeForce GTX 780 Ti .. 992 |=========================== GeForce GTX 950 ..... 769 |===================== GeForce GTX 960 ..... 897 |======================== GeForce GTX 970 ..... 1346 |==================================== GeForce GTX 980 ..... 1492 |======================================== GeForce GTX 980 Ti .. 1855 |================================================== GeForce GTX TITAN X . 1906 |=================================================== LuxMark 3.0 OpenCL Device: GPU - Scene: Microphone Score > Higher Is Better GeForce GTX 680 ..... 2127 |================= GeForce GTX 760 ..... 1941 |================ GeForce GTX 780 Ti .. 4302 |================================== GeForce GTX 950 ..... 2423 |=================== GeForce GTX 960 ..... 2460 |==================== GeForce GTX 970 ..... 4458 |==================================== GeForce GTX 980 ..... 4776 |====================================== GeForce GTX 980 Ti .. 6268 |================================================== GeForce GTX TITAN X . 6360 |=================================================== LuxMark 3.0 OpenCL Device: GPU - Scene: Luxball HDR Score > Higher Is Better GeForce GTX 680 ..... 4554 |================ GeForce GTX 750 ..... 3491 |============ GeForce GTX 760 ..... 4253 |=============== GeForce GTX 780 Ti .. 9639 |================================== GeForce GTX 950 ..... 5313 |=================== GeForce GTX 960 ..... 5474 |=================== GeForce GTX 970 ..... 9737 |=================================== GeForce GTX 980 ..... 10713 |====================================== GeForce GTX 980 Ti .. 13802 |================================================= GeForce GTX TITAN X . 14081 |==================================================