Automating CUDA Synchronization via Program Transformation

Mingyuan Wu
Mingyuan Wu
Shin Hwei Tan
Shin Hwei Tan
Yuqun Zhang
Yuqun Zhang

ASE, pp. 748-759, 2019.

Cited by: 3|Bibtex|Views5|Links
EI

Abstract:

While CUDA has been the most popular parallel computing platform and programming model for generalpurpose GPU computing, CUDA synchronization undergoes significant challenges for GPU programmers due to its intricate parallel computing mechanism and coding practices. In this paper, we propose AuCS, the first general framework to automate s...More

Code:

Data:

Your rating :
0

 

Tags
Comments