An ASIC Implementation and Evaluation of a Profiled Low-Energy Instruction Set Architecture Extension

TL;DR

This paper introduces an ASIC implementation of a profiled instruction set extension that reduces power consumption by shortening common instructions, decreasing cache accesses, and lowering instruction fetch cycles.

Contribution

It presents a novel instruction set extension based on profiling, implemented in ASIC, demonstrating significant power savings over traditional architectures.

Findings

Reduced power consumption in ASIC implementation

Fewer instruction cache accesses

Lower instruction fetch cycles

Abstract

This paper presents an extension to an existing instruction set architecture, which gains considerable reduction in power consumption. The reduction in power consumption is achieved through coding of the most commonly executed instructions in a short format done by the compiler based on a profile of previous executions. This leads to fewer accesses to the instruction cache and that more instructions can fit in the cache. As a secondary effect, this turned out to be very beneficial in terms of power. Another major advantage, which is the main concern of this paper is the reduction in the number of instruction fetch cycles which will also contribute significantly towards reduction in power consumption. The work involves implementing the new processor architecture in ASIC and estimation of power-consumption compared to the normal architecture.