Title
A Gpgpu Compiler For Memory Optimization And Parallelism Management
Keywords
Compiler; GPGPU
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. Copyright © 2010 ACM.
Publication Date
6-1-2010
Publication Title
ACM SIGPLAN Notices
Volume
45
Issue
6
Number of Pages
86-97
Document Type
Article; Proceedings Paper
Personal Identifier
scopus
DOI Link
https://doi.org/10.1145/1809028.1806606
Copyright Status
Unknown
Socpus ID
77957600490 (Scopus)
Source API URL
https://api.elsevier.com/content/abstract/scopus_id/77957600490
STARS Citation
Yang, Yi; Xiang, Ping; Kong, Jingfei; and Zhou, Huiyang, "A Gpgpu Compiler For Memory Optimization And Parallelism Management" (2010). Scopus Export 2010-2014. 1103.
https://stars.library.ucf.edu/scopus2010/1103