Abstract | ||
---|---|---|
Domain Wall Memory (DWM) is a promising emerging memory technology but suffers from the expensive shifts needed to align memory locations with access ports. Previous work on DWM concentrates on data, while, to the best of our knowledge, techniques to specifically target instruction streams have not yet been studied. In this paper, we propose Shift-Reducing Instruction Memory Placement (SHRIMP), the first instruction placement strategy suited for DWM which is accompanied with a supporting instruction fetch and memory architecture. The proposed approach reduces the number of shifts by 40% in the best case with a small memory overhead. In addition, SHRIMP achieves a best case of 23% reduction in total cycle counts. |
Year | DOI | Venue |
---|---|---|
2019 | 10.1109/ISLPED.2019.8824954 | 2019 IEEE/ACM International Symposium on Low Power Electronics and Design (ISLPED) |
Keywords | Field | DocType |
instruction placement strategy,memory architecture,memory overhead,SHRIMP,DWM concentrates,instruction streams,instruction fetch,instruction delivery,domain wall memory,memory technology,memory locations,shift-reducing instruction memory placement,access ports | Computer architecture,Computer science,Cycle count,Real-time computing,Fetch,Memory architecture,Shrimp | Conference |
ISBN | Citations | PageRank |
978-1-7281-2955-6 | 0 | 0.34 |
References | Authors | |
5 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Joonas Multanen | 1 | 4 | 2.13 |
Pekka Jääskeläinen | 2 | 140 | 31.26 |
Asif Ali Khan | 3 | 7 | 2.22 |
Fazal Hameed | 4 | 54 | 7.25 |
Jerónimo Castrillón | 5 | 0 | 0.34 |