Extending Abstract GPU APIs to Shared Memory

摘要

Parallel programming is used extensively for general-purpose computations. However, performance of parallel APIs varies for a given problem and a given architecture. This gives rise to the need for having an abstract way to express the parallel problems. This poster presents a new approach through which programmers can access these APIs without having to focus on the technical or platform-specific details. Our earlier approach of Abstract Application Programming Interface (API) targeted for Graphical Processing Unit (GPU) programming is extended to shared memory using OpenMP.