A survey of techniques for warp scheduling in GPUs
Authors:
- 1 December 2015
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 600-606
Abstract
The heterogeneous nature of Graphics processor unit (GPU) - CPU makes it a candidate for coming exascale systems. The cores of GPGPU-which is a cost-effective computing platform-are characterized by long periods of inactive times, which results in the underutilization of the hardware resources. This is due to several factors like the limitation of on-chip memory and register files, the inefficient scheduling mechanisms, and communication bottlenecks GPU - CPU communication. In order to counteract the underutilization of recourses, certain techniques have been proposed. In this research, many architectural and system-level techniques aiming to manage and fully leverage GPU resources are surveyed, compared and evaluated. Also, the significance and challenges of warp scheduler in GPUs are thoroughly discussed. The main purpose of this paper is to provide researchers an insight into warp scheduler techniques for GPUs, as well as motivate them to present more efficient methods for enhance performance via improve thread scheduler in future GPUs.Keywords
This publication has 27 references indexed in Scilit:
- Studying Inter-Warp Divergence Aware Execution on GPUsIEEE Computer Architecture Letters, 2015
- CAWA2015
- Warped-compression2015
- PRO: Progress Aware GPU Warp Scheduling Algorithm2015
- Priority-based cache allocation in throughput processors2015
- CAWS2014
- Guided Region-Based GPU Scheduling: Utilizing Multi-thread Parallelism to Hide Memory Latency2013
- Recent Advances on GPU Computing in Operations Research2013
- Cache-Conscious Wavefront Scheduling2012
- Automated Architecture-Aware Mapping of Streaming Applications Onto GPUs2011