Sat 13 Jun 2015 11:20 - 11:50 at C122 - Paper Session 2 Chair(s): Mary Sheeran

In this paper, we present a compiler that compiles a rich subset of APL into programs that can be executed on GPGPUs. The compiler is based on the APLTAIL compiler, which compiles APL programs into a typed array intermediate language, called TAIL. The central part of the compiler compiles TAIL programs into Haskell programs that make use of the Accelerate library, an array language embedded in Haskell for high-performance computation on GPGPUs. We demonstrate the feasibility of the approach by presenting some encouraging results for a number of smaller benchmarks. We also outline some problems that we need to overcome in order for the approach to result in competitive code for larger benchmarks.

Sat 13 Jun

Displayed time zone: Tijuana, Baja California change