Program optimization space pruning for a multithreaded gpu
Shane Ryoo, Christopher I. Rodrigues, Sam S. Stone et al. · IEEE/ACM International Symposium on Code Generation and Optimization (CGO) · 2008
Program optimization for highly-parallel systems has historically been considered an art, with experts doing much of the performance tuning by hand. With the introduction of inexpensive, single-chip, massively parallel platforms, more developers will be creating highly-parallel applications for these platforms, who lack the substantial experience and knowledge needed to maximize their performance. This creates a need for more structured optimization methods with means to estimate their performance effects. Furthermore these methods need to be understandable by most programmers. This paper shows the complexity involved in optimizing applications for one such system and one relatively simple methodology for reducing the workload involved in the optimization process.
Cited by 285 works. doi:10.1145/1356058.1356084
Authors
- Shane Ryoo
- Christopher I. Rodrigues
- Sam S. Stone
- Sara S. Baghsorkhi
- Sain-Zee Ueng
- John A. Stratton
- Wen‐mei Hwu
References
- The cache performance and optimizations of blocked algorithms
- Accelerating molecular modeling applications with graphics processors
- Optimization principles and application performance evaluation of a multithreaded GPU using CUDA
- Maximizing multiprocessor performance with the SUIF compiler
- Accelerator
- Supercompilers for parallel and vector computers
- Optimizing Compilers for Modern Architectures: A Dependence-based Approach
- Understanding the efficiency of GPU algorithms for matrix-matrix multiplication
- Memory---A memory model for scientific algorithms on graphics processors
- NVIDIA cuda software and gpu parallel computing architecture