Abstract

This paper introduces the concept of dynamic instruction reuse. Empirical observations suggest that many instructions, and groups of instructions, having the same inputs, are executed dynamically. Such instructions do not have to be executed repeatedly --- their results can be obtained from a buffer where they were saved previously. This paper presents three hardware schemes for exploiting the phenomenon of dynamic instruction reuse, and evaluates their effectiveness using execution-driven simulation. We find that in some cases over 50% of the instructions can be reused. The speedups so obtained, though less striking than the percentage of instructions reused, are still quite significant. 1 Introduction There are three parameters that influence the execution time of a program. Microarchitecture has concentrated on two of them: (i) the number of instructions executed per clock cycle, i.e., the IPC, and (ii) the clock cycle time. The third parameter: (iii) the total number of instructi...

Citations