Mattan Erez (University of Texas at Austin)
A significant portion of the energy dissipated in modern integrated circuits is consumed by the overhead associated with timing guardbands that ensure reliable execution. Timing speculation, where the pipeline operates at an unsafe voltage with any rare errors detected and resolved by the architecture, has been demonstrated to significantly improve the energy-efficiency of scalar processor designs. Unfortunately, applying the same timing-speculative approach to wide-SIMD architectures, such as those used in highly-efficient GPUs, may not provide similar gains.
I will present our work on a decoupled SIMD pipeline that more effectively utilizes timing speculation and recovery, when compared with a standard SIMD design that uses only conventional timing speculation. The proposed lane decoupling enables each SIMD lane to tolerate timing errors independent of other adjacent lanes, resulting in higher throughput and improved scalability. To evaluate our design, we develop a new set of models describing a parametrized general error probability function that is based on measurements of a fabricated chip and the expected efficiency benefits of timing speculation in a SIMD context. I will also discuss under what scenarios the efficiency improvements can be obtained through speculation.