A GPGPU compiler for memory optimization and parallelism management
Authors:
Open Access
- 5 June 2010
- journal article
- Published by Association for Computing Machinery (ACM) in ACM SIGPLAN Notices
- Vol. 45 (6) , 86-97
Abstract
This paper presents a novel optimizing compiler for general purpose computation on graphics processing units (GPGPU). It addresses two major challenges of developing high performance GPGPU programs: effective utilization of GPU memory hierarchy and judicious management of parallelism. The input to our compiler is a naïve GPU kernel function, which is functionally correct but without any consideration for performance optimization. The compiler analyzes the code, identifies its memory access patterns, and generates both the optimized kernel and the kernel invocation parameters. Our optimization process includes vectorization and memory coalescing for memory bandwidth enhancement, tiling and unrolling for data reuse and parallelism management, and thread block remapping or address-offset insertion for partition-camping elimination. The experiments on a set of scientific and media processing algorithms show that our optimized code achieves very high performance, either superior or very close to the highly fine-tuned library, NVIDIA CUBLAS 2.2, and up to 128 times speedups over the naive versions. Another distinguishing feature of our compiler is the understandability of the optimized code, which is useful for performance analysis and algorithm refinement.Keywords
This publication has 13 references indexed in Scilit:
- An adaptive performance modeling tool for GPU architectures2010
- A cross-input adaptive framework for GPU program optimizations2009
- OpenMP to GPGPU2009
- A compiler framework for optimization of affine loop nests for gpgpus2008
- Program optimization space pruning for a multithreaded gpu2008
- Optimization principles and application performance evaluation of a multithreaded GPU using CUDA2008
- Automatic data movement and computation mapping for multi-level parallel architectures with explicitly managed memories2008
- CUDA-Lite: Reducing GPU Programming Complexity2008
- Iterative Optimization in the Polyhedral Model: Part I, One-Dimensional Time2007
- An algorithm for the machine calculation of complex Fourier seriesMathematics of Computation, 1965