GRAPE: Minimizing energy for GPU applications with performance requirements

Many applications have performance requirements (e.g., real-time deadlines or quality-of-service goals) and we can save tremendous energy by tailoring resource usage so the application just meets its performance using the minimal resources. This problem is a classic constrained optimization: the performance goal is the constraint and energy consumption is the objective to be optimized. While several existing hardware approaches solve unconstrained optimizations (i.e., maximizing performance or minimizing energy), we are not aware of a hardware approach that minimizes GPU energy under an externally defined performance constraint. Therefore, we propose GRAPE, a hardware control system for GPUs that coordinates core usage, wavefront/warp action, core speed, and memory speed to deliver user-specified performance while minimizing energy. We implement GRAPE in VHDL (to demonstrate feasibility) and as an extension to GPGPU-Sim (for performance and power measurement). We find that GRAPE can be implemented with very low hardware overhead; however, compared to the no-overhead approach of race-to-idle, GRAPE reduces energy by 9-26% (depending on the performance goal), while meeting performance goals with an average error of 0.75%.