Some Experiments on Tiling Loop Programs for SharedMemory Multicore Architectures

Dagstuhl Seminar Proceedings 07351

计算机科学;物理学

Armin Gro¨ßlinger

PID  :  81799

学科分类：计算机科学（综合）

来源: CEUR

【 摘 要 】

The modelbased transformation of loop programs is a wayof detecting finegrained parallelism in sequential programs. One of the challenges is to agglomerate the parallelism to a coarser grain, in order to map the operations of the program to the available cores in a multicore architecture. We consider sharedmemory multicores as target architec ture for spacetime mapped loop programs and make some observations concerning code generation, load balancing and cache effects.