LOOP OPTIMIZATION WITH TRADEOFF BETWEEN CYCLE COUNT AND CODE SIZE FOR DSP APPLICATIONS (ThuAmPO2)

Author(s) : Bogong Su (Dept. of Computer Science, The William Paterson University of New Jersey, US) Jian Wang (Wireless Speech and Data Processing, Nortel Networks, Canada) Rafi Rabipour (Wireless Speech and Data Processing, Nortel Networks, Canada) Erh-Wen Hu (Dept. of Computer Science, The William Paterson University of New Jersey, US) Joseph Manzano (Dept. of Computer Science, The William Paterson University of New Jersey, US)

Abstract : Software pipelining is an effective technique to reduce cycle count by exploiting instruction level parallelism in loops. It has been implemented in most VLIW DSP compilers. However, software pipelining expands the code size due to the introduction of prelude and postlude. To address this problem, many VLIW DSP compilers include certain code size reduction features. During compilation, a user is given limited options of exercising these code reduction features. As a result, the tradeoff options between cycle count and code size are also limited. Yet today¡¯s software development often requires an optimum balance between code size and cycle count, which in turn requires a much wider tradeoff space. This paper presents a new heuristic code-size-constraint loop optimization approach to extend the tradeoff space. Preliminary experimental results indicate that the new approach can significantly widen the tradeoff space, thus providing DSP users with more flexibility to meet their various design criteria.

Menu