Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
This replaces the use of
mapX_inline
andapplyX_inline
by the forEach / forEachContiguous / forEachParallel / forEachSerial laser iterators.This is particularly valuable for recurrent neural network like GRU because we can implement the equation in a straightforward manner with meaning ful variable name instead of magic
x
,y
,z
and we would have needed anapply11_inline
anyway (with the correct var/non-var parameters).TODO:
Even then RNN are a type of iterative stencil application that require special care and often used for polyhedral benchmarking so another approach using tiling is probably needed to properly speed those up. (see https://github.com/numforge/laser/blob/master/research/automatic_loop_nest_scheduling.md#polyhedral-approaches)
Not in scope: