A New Perspective for Efficient Virtual-Cache Coherence. By Stefanos Kaxiras and Alberto Ros.
Accepted to appear in the 40th International Symposium on Computer Architecture (ISCA), 2013.
This paper proposes simple and efficient Coherent shared virtual memory (cSVM) for heterogeneous architectures (CPU + GPU) based on the VIPS coherence technology developed in Uppsala. Coherent shared virtual memory (cSVM) is highly coveted for heterogeneous architectures as it will simplify programming across different cores and manycore accelerators. In this context, virtual L1 caches can be used to great advantage, e.g., saving energy consumption, by eliminating address translation for hits. Unfortunately, multicore virtual-cache coherence is complex and costly because it requires reverse translation for any coherence request directed towards a virtual L1. The reason is the ambiguity of the virtual address due to the possibility of synonyms. In this paper, we take a radically different approach than all prior work which is focused on reverse translation. This results in a new solution for virtual-cache coherence, significantly less complex and more efficient than prior proposals. Significant area, energy, and performance benefits (43.4%, 19.5%, and 5.4%, respectively) ensue as a result of simplifying the entire multicore memory organization, making this the cutting-edge approach for virtualizing the GPU cores.
Comments are closed.