As a guest user you are not logged in or recognized by your IP address. You have
access to the Front Matter, Abstracts, Author Index, Subject Index and the full
text of Open Access publications.
This paper outlines our experiences with porting a number of production simulation codes to the Xeon Phi co-processor. Large scale production simulation codes present a challenge for optimisation on any platform, and can be even more problematic for accelerator hardware as the codes contain language operations or functionality that are hard to get good performance from on novel hardware. We present the challenges we have experienced porting two large FORTRAN production codes: GS2 and CP2K. We discuss the strategies, which have proven useful or otherwise, for obtaining good performance on Xeon Phi. We also discuss the reasons why achieving good performance for large-scale codes is problematic.
This website uses cookies
We use cookies to provide you with the best possible experience. They also allow us to analyze user behavior in order to constantly improve the website for you. Info about the privacy policy of IOS Press.
This website uses cookies
We use cookies to provide you with the best possible experience. They also allow us to analyze user behavior in order to constantly improve the website for you. Info about the privacy policy of IOS Press.