Power Saving Evaluation with Automatic Offloading

TL;DR

This paper evaluates power savings achieved through automatic offloading to heterogeneous hardware like GPU and FPGA, demonstrating improved energy efficiency over CPU-only processing.

Contribution

It verifies low-power operation via environment-adaptive software that automatically offloads tasks to hardware accelerators, building on prior performance improvements.

Findings

Significant reduction in power consumption with automatic offloading

Effective energy efficiency improvements over CPU-only execution

Validation of environment-adaptive software for power management

Abstract

Heterogeneous hardware other than small-core CPU such as GPU, FPGA, or many-core CPU is increasingly being used. However, heterogeneous hardware usage presents high technical skill barriers such as familiarity with CUDA. To overcome this challenge, I previously proposed environment-adaptive software that enables automatic conversion, automatic configuration, and high-performance and low-power operation of once-written code, in accordance with the hardware to be placed. I also previously verified performance improvement of automatic GPU and FPGA offloading. In this paper, I verify low-power operation with environment adaptation by evaluating power utilization after automatic offloading. I compare Watt*seconds of existing applications after automatic offloading with the case of CPU-only processing.