Classic loop unrolling allows to increase the performance of sequential loops by reducing the overheads of the non-computational parts of the loop. Unfortunately, when the loop con...
Roger Ferrer, Alejandro Duran, Xavier Martorell, E...
Efficient execution of well-parallelized applications is central to performance in the multicore era. Program analysis tools support the hardware and software sides of this effor...
Abstract. The combination of a language with ne-grain implicit parallelism and a data
ow evaluation scheme is suitable for high-level programming on massively parallel architectur...
This paper explains how efficient support for semiregular distributions can be incorporated in a uniform compilation framework for hybrid applications. The key focus of this work ...
Speculative parallelization can provide significant sources of additional thread-level parallelism, especially for irregular applications that are hard to parallelize by conventio...