Code transformations and SIMD impact on embedded software energy/power consumption
Authors:
- 1 December 2009
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 27-32
Abstract
The increasing demand for portable computing has elevated power consumption to be one of the most critical embedded systems design parameters. In this paper, we present a qualitative study wherein we examine the impact of code transformations on the energy and power consumption. Three main categories of code transformations are investigated, namely data, loop and procedural oriented transformations. Moreover, we evaluate the influence of employing single instruction multiple data (SIMD) on energy and power dissipation via the utilization of compiler intrinsic C-functions. Results show that a trade-off between power and performance can be achieved by employing the intrinsic C-functions in conjunction with some transformations such as loop unrolling and procedure integration.Keywords
This publication has 9 references indexed in Scilit:
- Performance and power consumption trade-offs for a VLIW DSP2009
- Impact of source code optimizations on power consumption of embedded systems2008
- Code transformations for low power caching in embedded multimedia processors2002
- THE IMPACT OF SOURCE CODE TRANSFORMATIONS ON SOFTWARE POWER AND ENERGY CONSUMPTIONJournal of Circuits, Systems and Computers, 2002
- Code transformations for data transfer and storage exploration preprocessing in multimedia processorsIEEE Design & Test of Computers, 2001
- The SimpleScalar tool set, version 2.0ACM SIGARCH Computer Architecture News, 1997
- Power analysis and minimization techniques for embedded DSP softwareIEEE Transactions on Very Large Scale Integration (VLSI) Systems, 1997
- Improving data locality with loop transformationsACM Transactions on Programming Languages and Systems, 1996
- Compiler transformations for high-performance computingACM Computing Surveys, 1994