Michael Wolfe

Michael Wolfe has over 40 years of experience designing and implementing languages and compilers for high performance and parallel computers in industry and academia, most recently including PGI OpenACC for multicore and heterogeneous targets. He has written one textbook, "High Performance Compilers for Parallel Computing," and several technical papers, and occasionally writes articles for the online newsletter HPCwire.
Avatar photo

Posts by Michael Wolfe

PCAST helps to quickly isolate divergence between CPU and GPU results so you can isolate bugs or verify your results are OK even if they aren’t identical.
Simulation / Modeling / Design

Detecting Divergence Using PCAST to Compare GPU to CPU Results

Parallel Compiler Assisted Software Testing (PCAST) is a feature available in the NVIDIA HPC Fortran, C++, and C compilers. PCAST has two use cases. The first... 14 MIN READ