Reducing memory latency via non-blocking and prefetching caches

Tien-Fu Chen*, Jean Loup Baer

*Corresponding author for this work

研究成果: Conference contribution同行評審

82 引文 斯高帕斯(Scopus)

摘要

Non-blocking caches and prefetching caches are two techniques for hiding memory latency by exploiting the overlap of processor computations with data accesses. A non-blocking cache allows execution to proceed concurrently with cache misses as long as dependency constraints are observed, thus exploiting post-miss operations. A prefetching cache generates prefetch requests to bring data in the cache before it is actually needed thus allowing overlap with premiss computations. In this paper, we evaluate the effectiveness of these two hardware-based schemes. We propose a hybrid design based on the combination of these approaches. We also consider compiler-based optimizations to enhance the effectiveness of non-blocking caches. Results from instruction level simulations on the SPEC benchmarks show that the hardware prefetching caches generally outperform non-blocking caches. Also, the relative effectiveness of non-blocking caches is more adversely affected by an increase in memory latency than that of prefetching caches. However, the performance of non-blocking caches can be improved substantially by compiler optimizations such as instruction scheduling and register renaming. The hybrid design can be very effective in reducing the memory latency penalty for many applications.

原文English
主出版物標題International Conference on Architectural Support for Programming Languages and Operating Systems - ASPLOS
發行者Publ by ACM
頁面51-61
頁數11
版本9
ISBN(列印)0897915356, 9780897915359
DOIs
出版狀態Published - 1 一月 1992
事件Proceedings of the Fifth International Conference on Architectural Support Programming Languages and Operating Systems - ASPLOS-V - Boston, MA, USA
持續時間: 12 十月 199215 十月 1992

出版系列

名字International Conference on Architectural Support for Programming Languages and Operating Systems - ASPLOS
號碼9
27

Conference

ConferenceProceedings of the Fifth International Conference on Architectural Support Programming Languages and Operating Systems - ASPLOS-V
城市Boston, MA, USA
期間12/10/9215/10/92

指紋 深入研究「Reducing memory latency via non-blocking and prefetching caches」主題。共同形成了獨特的指紋。

引用此