Compiler Design: Difference between revisions

From dankwiki
Line 35: Line 35:
* Primary references: Allen/Kennedy ch. 9, Muchnick ch. 20. See also [[Architecture#Caches|Caches]] on the [[Architecture]] page.
* Primary references: Allen/Kennedy ch. 9, Muchnick ch. 20. See also [[Architecture#Caches|Caches]] on the [[Architecture]] page.
* The benefits of spatial locality can now be taken advantage of at the more natural word level.
* The benefits of spatial locality can now be taken advantage of at the more natural word level.
* Loop interchange -- are we striding through nested loops optimally? If not, we can interchange levels, provided all dependencies are preserved. Especially powerful when combined with hardware- or software-based prefetching and further augmented with non-blocking caches.
* Loop interchange -- are we striding through nested loops optimally? If not, we can interchange levels, provided all dependencies are preserved. Especially powerful when combined with hardware- or software-based prefetching and further augmented with non-blocking caches. Optimal interpositioning is NP-hard in general but excellent heuristics exist. See Allen/Kennedy p. 472-474.
** This can be valuable enough that we perform small transformations to accommodate it: loop alignment, loop peeling, etc
** This can be valuable enough that we perform small transformations to accommodate it: loop alignment, loop peeling, etc