Efficient Exploitation of Parallelism on Pentium III and Pentium 4 Processor-Based Systems
Aart J. C. Bik, Xinmin Tian · 2001
Systems based on the Pentium III and Pentium processors enable the exploitation of parallelism at a fineand medium-grained level. Dual- and quad-processor systems, for example, enable the exploitation of mediumgrained parallelism by using multithreaded code that takes advantage of multiple control and arithmetic logic units. Streaming Single-Instruction-Multiple-Data (SIMD) extensions, on the other hand, enable the exploitation of fine-grained SIMD parallelism by vectorizing loops that perform a single operation on multiple elements in a data set. This paper provides a high-level overview of the automatic parallelization and vectorization methods used by the Intel C++/Fortran compiler developed at the Microcomputer Software Labs.