Proceedings 16th International Parallel and Distributed Processing Symposium 2002
DOI: 10.1109/ipdps.2002.1016517
|View full text |Cite
|
Sign up to set email alerts
|

Eclipse: heterogeneous multiprocessor architecture for flexible media processing

Abstract: Eclipse is a heterogeneous multiprocessor architecture for high-performance media processing, including highdefinition MPEG encoding/decoding. The scalable architecture framework concurrently executes media processing kernels in function-specific multi-tasking coprocessors and a media processor, communicating via on-chip memory. Eclipse instances combine application configuration flexibility with the efficiency of function-specific hardware.

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
2
1

Citation Types

0
13
0

Year Published

2004
2004
2009
2009

Publication Types

Select...
7
1

Relationship

0
8

Authors

Journals

citations
Cited by 16 publications
(13 citation statements)
references
References 23 publications
0
13
0
Order By: Relevance
“…Table 3 gives an overview of four SoC subsystem architecture templates: the MOVE project at Delft University of Technology [26], Philips Research Prophid/CPA [136], Intel MXP [72], and Philips Research Eclipse [121]. …”
Section: Soc Subsystem Architecture Templatesmentioning
confidence: 99%
“…Table 3 gives an overview of four SoC subsystem architecture templates: the MOVE project at Delft University of Technology [26], Philips Research Prophid/CPA [136], Intel MXP [72], and Philips Research Eclipse [121]. …”
Section: Soc Subsystem Architecture Templatesmentioning
confidence: 99%
“…Tensilica [27] enables rapid design of highly efficient processor cores by extending the processor hardware and software to fit each system's application requirements based on a lean core implementation. The Eclipse [24] provides an architecture template at subsystem level. It supports the reuse of design effort for providing a set of parameterized rules for subsystem composition.…”
Section: Related Workmentioning
confidence: 99%
“…Moreover, it is also important to extract several levels of parallelism to maximally utilize all available processor cores in the multi-core platforms. For this purpose, several architectures for task-or thread-level parallelism have been introduced in the multi-core platforms [5][6][7]. Using finegrain tasks or threads provides more flexible but requires more communication for control and data.…”
Section: Introductionmentioning
confidence: 99%