Trellis: Portability Across Architectures with a High-level Framework

Download Now
Provided by: University of Vigo
Topic: Hardware
Format: PDF
The increasing computational needs of parallel applications inevitably require portability across parallel architectures, which now include heterogeneous processing resources, such as CPUs and GPUs, and multiple SIMD/SIMT widths. However, the lack of a common parallel programming paradigm that provides predictable, near-optimal performance on each resource leads to the use of low-level frameworks with architecture-specific optimizations, which in turn cause the code base to diverge and makes porting difficult. The authors' experiences with parallel applications and frameworks lead the user to the conclusion that achieving performance portability requires structured code, a common set of high-level directives and efficient mapping onto hardware.
Download Now

Find By Topic