Abstract
Graphics Processing Units (GPUs) are increasingly used for general-purpose applications because of their low price, energy efficiency and enormous computing power. Considering the importance of GPU applications, it is vital that the behaviour of GPU programs can be specied and proven correct formally. This paper presents our ideas how
to verify GPU programs written in OpenCL, a platform-independent low-level programming language. Our verication approach is modular, based on permission-based separation logic. We rst present the main ingredients of our logic, and then illustrate its use on several example kernels. We show in particular how the logic is used to prove data-race-
freedom and functional correctness of GPU applications.
to verify GPU programs written in OpenCL, a platform-independent low-level programming language. Our verication approach is modular, based on permission-based separation logic. We rst present the main ingredients of our logic, and then illustrate its use on several example kernels. We show in particular how the logic is used to prove data-race-
freedom and functional correctness of GPU applications.
Original language | English |
---|---|
Number of pages | 8 |
Publication status | Published - 2013 |
Event | 8th Workshop on Bytecode Semantics, Verification, Analysis and Transformation (BYTECODE 2013) - Rome, Italy Duration: 23 Mar 2013 → 23 Mar 2013 |
Workshop
Workshop | 8th Workshop on Bytecode Semantics, Verification, Analysis and Transformation (BYTECODE 2013) |
---|---|
Abbreviated title | BYTECODE 2013 |
Country/Territory | Italy |
City | Rome |
Period | 23/03/13 → 23/03/13 |