NVIDIA Pascal Fresh Summer 2018 OpenCL Benchmarks NVIDIA OpenCL compute benchmarks on Ubuntu Linux for a future article by Michael Larabel. GeForce GTX 1050: Processor: Intel Core i7-8086K @ 5.00GHz (6 Cores / 12 Threads), Motherboard: ASUS PRIME Z370-A (0809 BIOS), Chipset: Intel Device 3ec2, Memory: 16384MB, Disk: 525GB SABRENT + 118GB INTEL SSDPEK1W120GA, Graphics: Zotac NVIDIA GeForce GTX 1050 2048MB (1354/3504MHz), Audio: Realtek ALC1220, Monitor: DELL P2415Q, Network: Intel Connection OS: Ubuntu 18.04, Kernel: 4.17.8-041708-generic (x86_64), Desktop: GNOME Shell 3.28.2, Display Server: X Server 1.19.6, Display Driver: NVIDIA 396.45, OpenGL: 4.6.0, OpenCL: OpenCL 1.2 CUDA 9.2.177, Compiler: GCC 7.3.0, File-System: ext4, Screen Resolution: 3840x2160 GeForce GTX 1050 Ti: Processor: Intel Core i7-8086K @ 5.00GHz (6 Cores / 12 Threads), Motherboard: ASUS PRIME Z370-A (0809 BIOS), Chipset: Intel Device 3ec2, Memory: 16384MB, Disk: 525GB SABRENT + 118GB INTEL SSDPEK1W120GA, Graphics: eVGA NVIDIA GeForce GTX 1050 Ti 4096MB (1354/3504MHz), Audio: Realtek ALC1220, Monitor: DELL P2415Q, Network: Intel Connection OS: Ubuntu 18.04, Kernel: 4.17.8-041708-generic (x86_64), Desktop: GNOME Shell 3.28.2, Display Server: X Server 1.19.6, Display Driver: NVIDIA 396.45, OpenGL: 4.6.0, OpenCL: OpenCL 1.2 CUDA 9.2.177, Compiler: GCC 7.3.0, File-System: ext4, Screen Resolution: 3840x2160 GeForce GTX 1060: Processor: Intel Core i7-8086K @ 5.00GHz (6 Cores / 12 Threads), Motherboard: ASUS PRIME Z370-A (0809 BIOS), Chipset: Intel Device 3ec2, Memory: 16384MB, Disk: 525GB SABRENT + 118GB INTEL SSDPEK1W120GA, Graphics: NVIDIA GeForce GTX 1060 6GB 6144MB (1506/4006MHz), Audio: Realtek ALC1220, Monitor: DELL P2415Q, Network: Intel Connection OS: Ubuntu 18.04, Kernel: 4.17.8-041708-generic (x86_64), Desktop: GNOME Shell 3.28.2, Display Server: X Server 1.19.6, Display Driver: NVIDIA 396.45, OpenGL: 4.6.0, OpenCL: OpenCL 1.2 CUDA 9.2.177, Compiler: GCC 7.3.0, File-System: ext4, Screen Resolution: 3840x2160 GeForce GTX 1070: Processor: Intel Core i7-8086K @ 5.00GHz (6 Cores / 12 Threads), Motherboard: ASUS PRIME Z370-A (0809 BIOS), Chipset: Intel Device 3ec2, Memory: 16384MB, Disk: 525GB SABRENT + 118GB INTEL SSDPEK1W120GA, Graphics: NVIDIA GeForce GTX 1070 8192MB (1506/4006MHz), Audio: Realtek ALC1220, Monitor: DELL P2415Q, Network: Intel Connection OS: Ubuntu 18.04, Kernel: 4.17.8-041708-generic (x86_64), Desktop: GNOME Shell 3.28.2, Display Server: X Server 1.19.6, Display Driver: NVIDIA 396.45, OpenGL: 4.6.0, OpenCL: OpenCL 1.2 CUDA 9.2.177, Compiler: GCC 7.3.0, File-System: ext4, Screen Resolution: 3840x2160 GeForce GTX 1070 Ti: Processor: Intel Core i7-8086K @ 5.00GHz (6 Cores / 12 Threads), Motherboard: ASUS PRIME Z370-A (0809 BIOS), Chipset: Intel Device 3ec2, Memory: 16384MB, Disk: 525GB SABRENT + 118GB INTEL SSDPEK1W120GA, Graphics: Zotac NVIDIA GeForce GTX 1070 Ti 8192MB (1607/4006MHz), Audio: Realtek ALC1220, Monitor: DELL P2415Q, Network: Intel Connection OS: Ubuntu 18.04, Kernel: 4.17.8-041708-generic (x86_64), Desktop: GNOME Shell 3.28.2, Display Server: X Server 1.19.6, Display Driver: NVIDIA 396.45, OpenGL: 4.6.0, OpenCL: OpenCL 1.2 CUDA 9.2.177, Compiler: GCC 7.3.0, File-System: ext4, Screen Resolution: 3840x2160 GeForce GTX 1080 Ti: Processor: Intel Core i7-8086K @ 5.00GHz (6 Cores / 12 Threads), Motherboard: ASUS PRIME Z370-A (0809 BIOS), Chipset: Intel Device 3ec2, Memory: 16384MB, Disk: 525GB SABRENT + 118GB INTEL SSDPEK1W120GA, Graphics: NVIDIA GeForce GTX 1080 Ti 11264MB (1480/5508MHz), Audio: Realtek ALC1220, Monitor: DELL P2415Q, Network: Intel Connection OS: Ubuntu 18.04, Kernel: 4.17.8-041708-generic (x86_64), Desktop: GNOME Shell 3.28.2, Display Server: X Server 1.19.6, Display Driver: NVIDIA 396.45, OpenGL: 4.6.0, OpenCL: OpenCL 1.2 CUDA 9.2.177, Compiler: GCC 7.3.0, File-System: ext4, Screen Resolution: 3840x2160 SHOC Scalable HeterOgeneous Computing 2015-11-10 Target: OpenCL - Benchmark: FFT SP GFLOPS > Higher Is Better GeForce GTX 1050 .... 248.78 |============ GeForce GTX 1050 Ti . 223.70 |=========== GeForce GTX 1060 .... 350.64 |================= GeForce GTX 1070 .... 516.41 |========================== GeForce GTX 1070 Ti . 557.46 |============================ GeForce GTX 1080 Ti . 988.42 |================================================= SHOC Scalable HeterOgeneous Computing 2015-11-10 Target: OpenCL - Benchmark: MD5 Hash GHash/s > Higher Is Better GeForce GTX 1050 .... 3.24 |======== GeForce GTX 1050 Ti . 4.12 |========== GeForce GTX 1060 .... 7.38 |================== GeForce GTX 1070 .... 10.74 |=========================== GeForce GTX 1070 Ti . 13.83 |================================== GeForce GTX 1080 Ti . 20.20 |================================================== SHOC Scalable HeterOgeneous Computing 2015-11-10 Target: OpenCL - Benchmark: Texture Read Bandwidth GB/s > Higher Is Better GeForce GTX 1050 .... 308.56 |========================= GeForce GTX 1050 Ti . 336.67 |=========================== GeForce GTX 1060 .... 417.80 |================================== GeForce GTX 1070 .... 458.99 |===================================== GeForce GTX 1070 Ti . 510.18 |========================================= GeForce GTX 1080 Ti . 606.73 |================================================= ViennaCL 1.4.2 OpenCL LU Factorization GFLOPS > Higher Is Better GeForce GTX 1050 .... 45.05 |================================= GeForce GTX 1050 Ti . 49.55 |==================================== GeForce GTX 1060 .... 59.01 |=========================================== GeForce GTX 1070 .... 64.27 |============================================== GeForce GTX 1070 Ti . 66.49 |================================================ GeForce GTX 1080 Ti . 69.22 |================================================== cl-mem 2017-01-13 Benchmark: Copy GB/s > Higher Is Better GeForce GTX 1050 .... 88.70 |============== GeForce GTX 1050 Ti . 88.17 |============== GeForce GTX 1060 .... 140.57 |====================== GeForce GTX 1070 .... 188.23 |============================= GeForce GTX 1070 Ti . 188.20 |============================= GeForce GTX 1080 Ti . 319.20 |================================================= cl-mem 2017-01-13 Benchmark: Read GB/s > Higher Is Better GeForce GTX 1050 .... 96.00 |============== GeForce GTX 1050 Ti . 95.17 |============== GeForce GTX 1060 .... 154.47 |====================== GeForce GTX 1070 .... 206.30 |============================== GeForce GTX 1070 Ti . 206.50 |============================== GeForce GTX 1080 Ti . 339.23 |================================================= cl-mem 2017-01-13 Benchmark: Write GB/s > Higher Is Better GeForce GTX 1050 .... 90.20 |============= GeForce GTX 1050 Ti . 89.10 |============= GeForce GTX 1060 .... 145.60 |===================== GeForce GTX 1070 .... 197.63 |============================ GeForce GTX 1070 Ti . 196.53 |============================ GeForce GTX 1080 Ti . 344.10 |================================================= IndigoBench 4.0.64 Scene: Bedroom M samples/s > Higher Is Better GeForce GTX 1050 .... 1.42 |============== GeForce GTX 1050 Ti . 1.65 |================ GeForce GTX 1060 .... 2.65 |========================= GeForce GTX 1070 .... 3.77 |==================================== GeForce GTX 1070 Ti . 4.15 |======================================== GeForce GTX 1080 Ti . 5.32 |=================================================== IndigoBench 4.0.64 Scene: Supercar M samples/s > Higher Is Better GeForce GTX 1050 .... 4.64 |============= GeForce GTX 1050 Ti . 5.48 |================ GeForce GTX 1060 .... 8.74 |========================= GeForce GTX 1070 .... 12.41 |=================================== GeForce GTX 1070 Ti . 13.87 |======================================== GeForce GTX 1080 Ti . 17.55 |================================================== JuliaGPU 1.2pts1 OpenCL Device: GPU Samples/sec > Higher Is Better GeForce GTX 1050 .... 68020911.20 |============== GeForce GTX 1050 Ti . 82228551.07 |================= GeForce GTX 1060 .... 123277207.17 |========================= GeForce GTX 1070 .... 155907964.80 |================================ GeForce GTX 1070 Ti . 177590252.53 |==================================== GeForce GTX 1080 Ti . 209807323.37 |=========================================== MandelGPU 1.3pts1 OpenCL Device: GPU Samples/sec > Higher Is Better GeForce GTX 1050 .... 48526868.77 |======== GeForce GTX 1050 Ti . 61788066.47 |========== GeForce GTX 1060 .... 106989159.30 |================= GeForce GTX 1070 .... 153001211.87 |========================= GeForce GTX 1070 Ti . 189306428.90 |=============================== GeForce GTX 1080 Ti . 264945183.70 |=========================================== LuxMark 3.1 OpenCL Device: GPU - Scene: Hotel Score > Higher Is Better GeForce GTX 1050 .... 1385 |============ GeForce GTX 1050 Ti . 1634 |=============== GeForce GTX 1060 .... 2630 |======================== GeForce GTX 1070 .... 3846 |================================== GeForce GTX 1070 Ti . 4461 |======================================== GeForce GTX 1080 Ti . 5707 |=================================================== LuxMark 3.1 OpenCL Device: GPU - Scene: Microphone Score > Higher Is Better GeForce GTX 1050 .... 4122 |=============== GeForce GTX 1050 Ti . 4703 |================= GeForce GTX 1060 .... 6965 |========================= GeForce GTX 1070 .... 9982 |==================================== GeForce GTX 1070 Ti . 10620 |======================================= GeForce GTX 1080 Ti . 13781 |==================================================