Future of GPGPU Micro-Architectural Parameters

Provided by: edaa
Topic: Hardware
Format: PDF
As Graphics Processing Units (GPUs) are becoming increasingly popular for General-Purpose Graphics Processing Unit workloads (GPGPU), the question arises how such processors will evolve architecturally in the near future. In this paper, the authors identify and discuss tradeoffs for three GPU architecture parameters: active thread count, compute-memory ratio, and cluster and warp sizing. For each parameter, they propose changes to improve GPU design, keeping in mind trends such as dark silicon and the increasing popularity of GPGPU architectures. A key-enabler is dynamism and workload-adaptiveness, enabling among others: dynamic register file sizing, latency aware scheduling, roofline-aware DVFS, runtime cluster fusion, and dynamic warp sizing.

Find By Topic