ST2 GPU: An Energy-Efficient GPU Design with Spatio-Temporal Shared-Thread Speculative Adders

Modern GPUs employ thousands of cores, yielding higher performance but also higher power consumption. To meet performance targets while staying within a reasonable power budget, designers have to make these execution cores increasingly more power efficient. One way to increase their power efficiency is to employ power-efficient adders. In this paper, we observe that consecutive arithmetic computations from the same code location are highly correlated and propose ST
²
GPU, a GPU architecture that uses history-based speculative adders that produce guaranteed correct results while saving 70% of the nominal adder power. We estimate that ST
²
GPU saves 21% of the GPU chip energy with practically no performance and area overheads.