2010
DOI: 10.1007/978-3-642-15291-7_31
|View full text |Cite
|
Sign up to set email alerts
|

A Study of a Software Cache Implementation of the OpenMP Memory Model for Multicore and Manycore Architectures

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1

Citation Types

0
4
0

Year Published

2010
2010
2017
2017

Publication Types

Select...
3
2
1

Relationship

1
5

Authors

Journals

citations
Cited by 10 publications
(4 citation statements)
references
References 15 publications
0
4
0
Order By: Relevance
“…The software cache under the XL compiler is not configurable with respect to the number of dirty bytes that can be monitored in the line. This allows the implementation of novel memory models and frameworks as shown in [4]. The other difference is that the partition manager under the XL uses static GCC like overlays.…”
Section: Related Workmentioning
confidence: 99%
See 2 more Smart Citations
“…The software cache under the XL compiler is not configurable with respect to the number of dirty bytes that can be monitored in the line. This allows the implementation of novel memory models and frameworks as shown in [4]. The other difference is that the partition manager under the XL uses static GCC like overlays.…”
Section: Related Workmentioning
confidence: 99%
“…does not have caches (at least not across the SPU local storages) or any other way to maintain coherence. This presents a peculiar problem for the pseudo shared memory which Open OPELL presents 4 . This heterogeneity hindrance is resolved by the software cache.…”
Section: Software Cachementioning
confidence: 99%
See 1 more Smart Citation
“…The concept is illustrated for two execution nodes and their kernels [230]. SW-controlled [22,47], to enable demand-driven rollbacks. Thus, the proposed methodology is hybrid (HW-SW) in nature, since the detection occurs in HW and the mitigation is initiated by SW. A timing penalty is paid only when errors do occur and can be reclaimed if appropriate utilities are available on the target platform (e.g.…”
Section: Definition 54 a Computation Kernel (Ck) Is A Kernel That Performs A Computation Directly On Its Input Datamentioning
confidence: 99%