2011 IEEE International Symposium on Parallel and Distributed Processing Workshops and PHD Forum 2011
DOI: 10.1109/ipdps.2011.137
|View full text |Cite
|
Sign up to set email alerts
|

Abstract: Application-specific hardware and reconfigurable processors can dramatically speed up compute-intensive kernels of applications, offloading the burden of main processor. To minimize the communication overhead in such a coprocessor approach, the two processors can share an on-chip memory, which may be considered by each processor as a scratchpad memory. However, this setup poses a significant challenge to the main processor, which now must manage data on the scratchpad explicitly, often resulting in superfluous… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1
1

Citation Types

0
5
0

Year Published

2011
2011
2013
2013

Publication Types

Select...
4
1

Relationship

2
3

Authors

Journals

citations
Cited by 5 publications
(5 citation statements)
references
References 21 publications
0
5
0
Order By: Relevance
“…However, the previous works that come closest to us are [23] and [12]. In [23], promising results have been obtained by using an SPM as a shared memory between the main processor and the coprocessor.…”
Section: Related Workmentioning
confidence: 99%
See 3 more Smart Citations
“…However, the previous works that come closest to us are [23] and [12]. In [23], promising results have been obtained by using an SPM as a shared memory between the main processor and the coprocessor.…”
Section: Related Workmentioning
confidence: 99%
“…However, this scheme requires the main processor to explicitly manage the data on the SPM leading to huge data copy overhead. A tagbased CRM proposed in [12] can eliminate unnecessary data copy. However, the range recognizers are restricted to specific banks.…”
Section: Related Workmentioning
confidence: 99%
See 2 more Smart Citations
“…As a solution to this, we have adopted a configurable range memory architecture (CRM) [8] as shown in Figure 5. When the host processor read or write data from/to the main memory, if the address is within a pre-specified range, then the access is done through the CRM instead of the data cache.…”
Section: VImentioning
confidence: 99%