Integrating CUDA BLAS with IMSL Fortran for Improved Performance with GPU Hardware
SESSION: Heterogeneous Computing I
EVENT TYPE: Exhibitor Forum
TIME: 11:30AM - 12:00PM
ABSTRACT: As GPU hardware becomes less expensive, it becomes more prevalent in both research and commercial institutions. Software that takes advantage of this specialized hardware is growing in demand. In many cases, it is infeasible or impossible to rewrite an existing program to run entirely on the GPU, so the goal is often to offload as much work as possible. This architecture leads to the performance threat of copying data back and forth, negating any performance gains.
As the IMSL Library team at Rogue Wave Software considers how best to tackle the GPU realm with a general mathematical library, the IMSL Fortran Library takes an initial step where the CUDA BLAS library is utilized to offload CPU work to GPU hardware. This presentation will discuss the approach and architecture of the solution. Benchmark results will show where success has been found. Some limitations encountered and future plans will also be covered.