Abstract
In this paper, we propose an effective data pipelining technique, SPDP (scratch-pad data pipelining), for dynamic scratch-pad memory (SPM) management with DMA (Direct Memory Access). In SPDP, we group multiple iterations of a loop into a block for SPM allocation, and implement a data pipeline by overlapping the execution of CPU instructions and DMA operations. We have implemented our SPDP technique into the IMPACT compiler, and conduct experiments using a set of benchmarks from DSPstone, Mibench and Mediabench on the cycle-accurate VLIW simulator of Trimaran. The experimental results show that our technique achieves significant performance improvement compared with the previous work.
Original language | English |
---|---|
Title of host publication | Proceedings - 12th IEEE International Conference on Computational Science and Engineering, CSE 2009 - 7th IEEE/IFIP International Conference on Embedded and Ubiquitous Computing, EUC 2009 |
Pages | 358-365 |
Number of pages | 8 |
Volume | 2 |
DOIs | |
Publication status | Published - 3 Dec 2009 |
Event | 7th IEEE/IFIP International Conference on Embedded and Ubiquitous Computing, EUC 2009 - Vancouver, BC, Canada Duration: 29 Aug 2009 → 31 Aug 2009 |
Conference
Conference | 7th IEEE/IFIP International Conference on Embedded and Ubiquitous Computing, EUC 2009 |
---|---|
Country/Territory | Canada |
City | Vancouver, BC |
Period | 29/08/09 → 31/08/09 |
ASJC Scopus subject areas
- Computational Theory and Mathematics
- Computer Science Applications
- Software