National laboratory for parallel and distributed processing, Changsha, China

---

Abstract—As a solution to growing global wire delay, nonuniform cache architecture (NUCA) has already been a trend in large cache designs. The access time of NUCA is determined by the distance between the cache bank containing the required data and the processor. Thus, one of the important NUCA researches focuses on how to place data to be used into cache banks close to the processor. This paper proposes software prepromotion technique, which prepromote data using prepromotion instructions as similar as software prefetching does. Besides the basic software prepromotion, this paper also proposes smart multihop software prepromotion (SMSP), very long software prepromotion (VLSP) and their combination technique. SMSP intelligently chooses cache banks which the prepromoted data most ideally suit to being moved into. And VLSP prepromote multiple data using one instruction. Finally, we evaluate our approaches by testing 7 kernel benchmarks on a full-system simulator. The basic software prepromotion gets an average improvement of 2.6893% in IPC. The SMSP improves IPC by 7.0928% averagely. And the VLSP gets an IPC improvement of 7.2194% averagely. Lastly, after combining the SMSP and VLSP, the average improvement in IPC achieves 11.8650%.

Index Terms—NUCA, software prepromotion, smart multihop software prepromotion, very long software prepromotion, prefetching.

[PDF]

Cite: Junjie Wu, Xiaohui Pan, Xuejun Yang, "Software Prepromotion for Non-Uniform Cache Architecture," Journal of Software vol. 5, no. 1, pp. 11-19, 2010.