Proceedings of the International Conference on Compilers, Architecture, and Synthesis for Embedded Systems - CASES '01 2001
DOI: 10.1145/502217.502252
|View full text |Cite
|
Sign up to set email alerts
|

Algorithms for energy optimization using processor instructions

Abstract: In this paper, we consider processors which provide an idle instruction to the user for powering down processor units which are not required during portions of program execution. We describe algorithms which can be implemented in an energy-aware compiler to make efficient use of such an instruction. These algorithms are based on program static analysis and a combinatorial optimization formulation of the problem. We assume as input an assembly language program of the processor in question. The problem is to ins… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1

Citation Types

0
2
0

Year Published

2006
2006
2014
2014

Publication Types

Select...
3
2
1

Relationship

0
6

Authors

Journals

citations
Cited by 9 publications
(3 citation statements)
references
References 5 publications
(3 reference statements)
0
2
0
Order By: Relevance
“…Seth et al [22] explored the possibility of using the compiler to insert idle instructions automatically, increasing the execution time up to a set limit. Using the SIMD pipeline has been shown to decrease energy consumption [23] by roughly 25%.…”
Section: Optimisations Targeting Energymentioning
confidence: 99%
“…Seth et al [22] explored the possibility of using the compiler to insert idle instructions automatically, increasing the execution time up to a set limit. Using the SIMD pipeline has been shown to decrease energy consumption [23] by roughly 25%.…”
Section: Optimisations Targeting Energymentioning
confidence: 99%
“…Other software optimizations targeting energy have considered automatically inserting idle instructions [20], instruction scheduling [18], use of SIMD [11] and exploiting differences in functional units [6].…”
Section: Related Workmentioning
confidence: 99%
“…Hardware consumes a significant amount of energy due to the software it runs, and thus the same hardware configuration running different software implementations of the same functionality will have different energy consumption figures (Lafond, 2009). There is a considerable amount of work on optimizing the energy consumption of software by studying processor instructions (Seth, Keskar, & Venugopal, 2001), a family of processors (Russel & Jacome, 1998), or the memory management (Fan, Ellis, & Lebeck, 2001). It is also very useful to evaluate such figures for identifying the best high level software configuration.…”
Section: Related Workmentioning
confidence: 99%