GPUoutput
Testing the difference between VGA and DVI video output on CUDA performance


GPUoutputCUDA: 

	Processor: 2 x Intel Xeon E5-2660 v3 @ 3.30GHz (40 Cores), Motherboard: Supermicro X10DRG-OT+-CPU v1.00, Chipset: Intel Xeon E7 v3/Xeon, Memory: 8 x 16384 MB 2133MHz, Disk: 240GB INTEL SSDSC2BB24, Graphics: TITAN X (Pascal) 12288MB (1417/5005MHz), Audio: NVIDIA Device 10ef, Network: Intel 10-Gigabit X540-AT2

	OS: CentOS Linux 7, Kernel: 3.10.0-514.6.2.el7.x86_64 (x86_64), Desktop: GNOME Shell 3.14.4, Display Driver: NVIDIA 375.26, OpenGL: 4.4.0, Vulkan: 1.0.24, Compiler: GCC 4.8.5 20150623 + CUDA 8.0, File-System: xfs, Screen Resolution: 1920x1080


ASKAP tConvolveCuda 2015-11-10
Processing: Gridding
Million Grid Points Per Second > Higher Is Better
GPUoutputCUDA . 10946.07 |=====================================================


ASKAP tConvolveCuda 2015-11-10
Processing: Degridding
Million Grid Points Per Second > Higher Is Better
GPUoutputCUDA . 21619.07 |=====================================================


CUDA Mini-Nbody 2015-11-10
Test: Original
Seconds < Lower Is Better
GPUoutputCUDA . 24.65 |========================================================


CUDA Mini-Nbody 2015-11-10
Test: Cache Blocking
Seconds < Lower Is Better
GPUoutputCUDA . 14.60 |========================================================


CUDA Mini-Nbody 2015-11-10
Test: Loop Unrolling
Seconds < Lower Is Better
GPUoutputCUDA . 15.52 |========================================================


CUDA Mini-Nbody 2015-11-10
Test: SOA Data Layout
Seconds < Lower Is Better
GPUoutputCUDA . 27.21 |========================================================


CUDA Mini-Nbody 2015-11-10
Test: Flush Denormals To Zero
Seconds < Lower Is Better
GPUoutputCUDA . 27.17 |========================================================