Idioma:

PPOpenCL: a performance-portable OpenCL compiler with host and kernel thread code fusion

Liu, Ying ; Huang, Lei ; Wu, Mingchuan ; Cui, Huimin ; Lv, Fang ; Feng, Xiaobing ; Xue, Jingling

Proceedings of the 28th International Conference on Compiler Construction, 2019, p.2-16

Texto completo disponible

Citas Citado por

Título:
PPOpenCL: a performance-portable OpenCL compiler with host and kernel thread code fusion
Autor: Liu, Ying ; Huang, Lei ; Wu, Mingchuan ; Cui, Huimin ; Lv, Fang ; Feng, Xiaobing ; Xue, Jingling
Materias: Software and its engineering -- Software notations and tools -- Compilers -- Source code generation
Es parte de: Proceedings of the 28th International Conference on Compiler Construction, 2019, p.2-16
Descripción: OpenCL offers code portability but no performance portability. Given an OpenCL program X specifically written for one platform P, existing OpenCL compilers, which usually optimize its host and kernel codes individually, often yield poor performance for another platform Q. Instead of obtaining a performance-improved version of X for Q via manual tuning, we aim to achieve this automatically by a source-to-source OpenCL compiler framework, PPOpenCL. By fusing X's host and kernel thread codes (with the operations in different work-items in the same work-group represented explicitly), we are able to apply data flow analyses, and subsequently, performance-enhancing optimizations on a fused control flow graph specifically for platform Q. Validation against OpenCL benchmarks shows that PPOpenCL (implemented in Clang 3.9.1) can achieve significantly improved portable performance on seven platforms considered.
Editor: New York, NY, USA: ACM
Idioma: Inglés

Volver a la lista de resultados

Resultado 1 Siguiente Ir a la siguiente página