Optimal Code Size Reduction for Software-Pipelined and Unfolded Loops

Software pipelining and unfolding are commonly used techniques to increase parallelism for DSP applications. However, these techniques expand the code size of the application significantly. For most DSP systems with limited memory resources, code size becomes one of the most critical concerns for the highperformance applications. In this paper, we present the code size reduction theory based on retiming and unfolding concepts. We propose a code size reduction framework to achieve the optimal code size of software-pipelined and unfolded loops by using conditional registers. The experimental results on several wellknow benchmarks show the effectiveness of our code size reduction technique in controlling the code size of optimized loops. Categories and Subject Descriptors C.3 [Computer Systems Organization]: Special-Purpose and Application-Based Systems—Real-Time and Embedded Systems;

• Type: Conference
• Year: 2002
• Where: ISSS
• Authors: Bin Xiao, Zili Shao, Chantana Chantrapornchai, Edwin Hsing-Mean Sha, Qingfeng Zhuge
• Keywords: Code Size, Code Size Reduction, Hardware, ISSS 2002, Optimal Code Size