Halide: Decoupling Algorithms from Schedules for High-Performance Image Processing.

Writing high-performance code on modern machines requires not just locally optimizing inner loops, but globally reorganizing computations to exploit parallelism and locality--doing things such as tiling and blocking whole pipelines to fit in cache. This is especially true for image processing pipeli...

Descripción completa

Detalles Bibliográficos

Publicado en:	Communications of the ACM Vol. 61; no. 1; pp. 106 - 116
Autores principales:	Ragan-Kelley, Jonathan, Adams, Andrew, Sharlet, Dillon, Barnes, Connelly, Paris, Sylvain, Levoy, Marc, Amarasinghe, Saman, Durand, Frédo
Formato:	Artículo
Publicado:	Association for Computing Machinery Jan2018
Materias:	Mathematical decoupling Algorithms Image processing Computer scheduling High performance processors Computer vision Programming languages Computational photography Mathematics
Acceso en línea:	Ver este registro en EBSCOhost