LeiWang1999 commented on code in PR #16560:
URL: https://github.com/apache/tvm/pull/16560#discussion_r1488852238
##########
src/tir/schedule/primitive/blockize_tensorize.cc:
##########
@@ -738,6 +739,28 @@ StmtSRef Blockize(ScheduleState self, const
Array<StmtSRef>& blocks, bool preser
return result;
}
+class TensorIntrinSimplifier : public arith::IRMutatorWithAnalyzer {
+ public:
+ static PrimFunc Apply(PrimFunc func, arith::Analyzer* analyzer) {
Review Comment:
as u mentioned in
https://github.com/apache/tvm/pull/13299#issuecomment-1942085566 , perhaps its
better to simplify in prim_func level, I chose to implement a stmt simplifier
because it may be more useful. The rationale is that stmt is more fine-grained.
Moreover, in the context of tensor desc in tensorize schedule, prim_func
typically encompasses a single block without dynamic symbolic. I think for this
issue a stmt simplifier is enough.
But we can implement a prim_func one as well, should we keep both stmt and
primfunc simplifier or just maintain only one of them?
--
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]
