In this paper, we design an on-chip memory processor with arithmetic accelerators, which are expected to improve power consumption. In addition, we evaluate the power performance of the processor. We propose implementing vector-type arithmetic accelerators and SIMD-type arithmetic accelerators in the on-chip memory processor. The evaluation results obtained using our simulator indicate that the performance of the 4 FMAs SIMD-type accelerators is similar to that of the 4 FMAs vector-type accelerators on DAXPY, Livermore kernel 1 and 3. However, the performance of the 4 FMAs vector-type accelerator exceeds that of the 4 FMAs SIMD-type accelerator with respect to matrix multiplication and QCD because of difference in element size of the registers. On Livermore kernel 7, the power performance of the 4 FMAs SIMD-type accelerators exceeds that of the 4 FMAs vectortype because of register reuse. However, the 16 FMAs vectortype accelerators have an advantage in almost all simulations, excluding main memory bandwidth intensive benchmarks.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.