Warp Scheduling for Fine-Grained Synchronization
Authors:
- Ahmed ElTantawyAEAhmed ElTantawy
- Tor M. AamodtTATor M. Aamodt
- 1 February 2018
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 375-388
Abstract
Fine-grained synchronization is employed in many parallel algorithms and is often implemented using busy-wait synchronization (e.g., spin locks). However, busy-wait synchronization incurs significant overheads and existing CPU solutions do not readily translate to single-instruction, multiple-thread (SIMT) graphics processor unit (GPU) architectures. In this paper, we propose Back-Off Warp Spinning (BOWS), a hardware warp scheduling policy that extends existing warp scheduling policies to temporarily deprioritize warps executing busy wait code. In addition, we propose Dynamic Detection of Spinning (DDOS), a novel hardware mechanism for accurately and efficiently detecting busy-wait synchronization on GPUs. On a set of GPU kernels employing busy-wait synchronization, DDOS identifies all busy-wait loops incurring no false detections. BOWS improves performance by 1.5× and reduces energy consumption by 1.6× versus Criticality-Aware Warp Acceleration (CAWA) [14].Keywords
This publication has 27 references indexed in Scilit:
- MemcachedGPU2015
- CAWA2015
- Fine-Grained Synchronizations and Dataflow Programming on GPUs2015
- Criticality stacksACM SIGARCH Computer Architecture News, 2013
- A GPU implementation of inclusion-based points-to analysis2012
- Improving GPU performance via large warps and two-level warp scheduling2011
- Hardware transactional memory for GPU architectures2011
- An Efficient CUDA Implementation of the Tree-Based Barnes Hut n-Body Algorithm2011
- Synchronization state buffer2007
- The performance of spin lock alternatives for shared-memory multiprocessorsIEEE Transactions on Parallel and Distributed Systems, 1990