Back to Search
Start Over
CRAT: Enabling Coordinated Register Allocation and Thread-Level Parallelism Optimization for GPUs.
- Source :
- IEEE Transactions on Computers; Jun2018, Vol. 67 Issue 6, p890-897, 8p
- Publication Year :
- 2018
-
Abstract
- The key to the high performance on GPUs lies in the massive threading to enable thread switching and hide long latencies. GPUs are equipped with a large register file to enable fast context switch. However, thread throttling techniques that are designed to mitigate cache contention, lead to under-utilization of registers. Register allocation is a significant factor for performance as it not just determines the single-thread performance, but indirectly affects the TLP. In this paper, we propose Coordinated Register Allocation and Thread-level parallelism (CRAT ) to explore the optimization space of register allocation and TLP management on GPUs. CRAT employs both compile-time(CRAT-static) and run-time techniques(CRAT-dyn) to exhaust the design space. CRAT-static works statically to explore TLP and register allocation trade-off and CRAT-dyn exploits dynamic register allocation for further improvement. Experiments indicate that CRAT-static achieves an average 1.25X speedup over existing TLP management technique. On four register-limited applications, CRAT-dyn further improves the performance speedup of CRAT-static from 1.51X to 1.70X. [ABSTRACT FROM PUBLISHER]
Details
- Language :
- English
- ISSN :
- 00189340
- Volume :
- 67
- Issue :
- 6
- Database :
- Complementary Index
- Journal :
- IEEE Transactions on Computers
- Publication Type :
- Academic Journal
- Accession number :
- 129614861
- Full Text :
- https://doi.org/10.1109/TC.2017.2776272