Compiling a high-level language for GPUs
Authors:
Open Access
- 11 June 2012
- journal article
- conference paper
- Published by Association for Computing Machinery (ACM) in ACM SIGPLAN Notices
- Vol. 47 (6) , 1-12
Abstract
Languages such as OpenCL and CUDA offer a standard interface for general-purpose programming of GPUs. However, with these languages, programmers must explicitly manage numerous low-level details involving communication and synchronization. This burden makes programming GPUs difficult and error-prone, rendering these powerful devices inaccessible to most programmers. We desire a higher-level programming model that makes GPUs more accessible while also effectively exploiting their computational power. This paper presents features of Lime, a new Java-compatible language targeting heterogeneous systems, that allow an optimizing compiler to generate high quality GPU code. The key insight is that the language type system enforces isolation and immutability invariants that allow the compiler to optimize for a GPU without heroic compiler analysis. Our compiler attains GPU speedups between 75% and 140% of the performance of native OpenCL code.Keywords
This publication has 17 references indexed in Scilit:
- Lime2010
- A GPGPU compiler for memory optimization and parallelism management2010
- OpenMP to GPGPU2009
- SoC-C2008
- Optimization principles and application performance evaluation of a multithreaded GPU using CUDA2008
- Accelerator2006
- Exploiting coarse-grained task, data, and pipeline parallelism in stream programs2006
- Brook for GPUs2004
- Cg2003
- Analysis and development of Java Grande benchmarks1999