Title :
Designing and optimizing compute kernels on NVIDIA GPUs
Author :
Jamsek, Damir A.
Author_Institution :
IBM Res., Austin, TX
Abstract :
The availability of high performance compute capability in NVIDIA GPUs has expanded their use in CAD environments. We will describe the basic compute models including host/device programming models, device multi-thread programming models, as well optimization and performance tuning techniques.
Keywords :
CAD; computer graphic equipment; operating system kernels; optimisation; CAD algorithms; NVIDIA GPU; device multithread programming models; host/device programming models; kernel computation; optimization; performance tuning techniques; Acceleration; Algorithm design and analysis; Availability; Computational modeling; Design automation; Design optimization; Graphics processing unit; High performance computing; Kernel; Programming;
Conference_Titel :
Design Automation Conference, 2009. ASP-DAC 2009. Asia and South Pacific
Conference_Location :
Yokohama
Print_ISBN :
978-1-4244-2748-2
Electronic_ISBN :
978-1-4244-2749-9
DOI :
10.1109/ASPDAC.2009.4796484
