wrongtest-intellif opened a new pull request, #14021:
URL: https://github.com/apache/tvm/pull/14021
The change want to enforce the power and flexiblity of
`CompactBufferAllocation` pass on below aspects:
- Free of pass order
- It could work on both s-tir (with opaque blocks) and lowered tir. For
example, now one could be able to invoke `LoopPartition` and then make
partitioned tile aware buffer compactions.
- We test existing cases to ensure that
`(LowerOpaqueBlock . CompactBufferAllocation) (mod) ==
(CompactBufferAllocation . LowerOpaqueBlock) (mod)`
- Allow "non-strict" compaction
- Add an option "is_strict" defaults to `True`, to denote that during
compaction we should respect the original buffer shape bound. Thus the
compacted buffer region never exceed the original.
- If set to `False`, the "compacted" shape is totally determined to cover
buffer region accesses. Thus it may become larger than the original shape. This
change the original semantic for out-of-bound accesses but may be helpful in
certain usages.
- If people make optimizations to the loop domain (eg, align the loop dim
or remove the extra predicate), the accessed buffer region may grow, the pass
could now provide a fallback implementation if they do not want bother more to
adapt the buffer region as with their change.
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
