Abstract
For general purpose high-performance computing, recently GPGPUs have emerged as powerful vehicles. Programming GPGPUs is complex when compared to programming general purpose CPUs and parallel programming models such as OpenMP. Goal of our translation is to improve programmability and make existing OpenMP applications to be able to execute on GPGPUs. OpenMP has established itself as an important method and language extension for programming shared-memory parallel computers. Our translator works well on regular applications, leading to performance improvements of up to 50X over the unoptimized translation.
Full Text 
Sign-in/Register to access full text options
Sign-in/Register to access full text options 
Published version (
Free)
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
