Parallel programming with inductive synthesis
University of California, Berkeley
3rd USENIX conference on Hot topic in parallelism (HotPar’11), 2011
We show that program synthesis can generate GPU algorithms as well as their optimized implementations. Using the scan kernel as a case study, we describe our evolving synthesis techniques. Relying on our synthesizer, we can parallelize a serial problem by transforming it into a scan operation, synthesize a SIMD scan algorithm, and optimize it to reduce memory conflicts.
December 19, 2011 by hgpu
