Parallelism and the ARM instruction set architecture

Over the past few years, the ARM reduced-instruction-set computing (RISC) processor has evolved to offer a family of chips that range up to a full-blown multiprocessor. Embedded applications' demand for increasing levels of performance and the added efficiency of key new technologies has driven the ARM architecture's evolution. Throughout this evolutionary path, the ARM team has used a full range of techniques known to computer architecture for exploiting parallelism. The performance and efficiency methods that ARM uses include variable execution time, subword parallelism, digital signal processor-like operations, thread-level parallelism and exception handling, and multiprocessing. Leveraging parallelism on several levels, ARM's new chip designs could change how people access technology. With sales growing rapidly and more than 1.5 billion ARM processors already sold each year, software writers now have a huge range of markets in which their ARM code can be used.