Abstract
A study of the implementation patterns among massively threaded applications for many-core GPUs reveals that each of the seven most commonly used algorithm and data optimization techniques can enhance the performance of applicable kernels by 2 to 10× in current processors while also improving future scalability.
Original language | English (US) |
---|---|
Pages | 26-32 |
Number of pages | 7 |
Volume | 45 |
No | 8 |
Specialist publication | Computer |
DOIs | |
State | Published - 2012 |
Keywords
- Parboil benchmarks
- accelerators
- massively threaded systems
- optimization patterns
- scalability
ASJC Scopus subject areas
- Computer Science(all)