junrushao1994 commented on a change in pull request #10689:
URL: https://github.com/apache/tvm/pull/10689#discussion_r836005779
##########
File path: src/tir/schedule/primitive/sampling.cc
##########
@@ -299,22 +299,12 @@ std::vector<int64_t>
SamplePerfectTile(support::LinearCongruentialEngine::TRandS
return SamplePerfectTile(rand_state, extent, n_splits);
}
CHECK_GE(n_splits, 2) << "ValueError: Cannot tile a loop into " << n_splits
<< " splits";
- std::vector<int32_t> innermost_candidates;
- innermost_candidates.reserve(max_innermost_factor);
- for (int32_t i = 1; i <= max_innermost_factor; ++i) {
- if (extent % i == 0) {
- innermost_candidates.push_back(i);
+ while (true) {
+ std::vector<int64_t> result = SamplePerfectTile(rand_state, extent,
n_splits);
+ if (result.back() <= max_innermost_factor) {
+ return result;
Review comment:
Oh ooops! so this PR basically loops until the innermost factor
satisfies some certain constraint, with the assumption that there is always a
case where the factor could be 1 where `1 <= max_innermost_factor` always holds.
To make sure I understand this correctly, in your particular case, `extent =
1024`, `max_innermost_factor = 128`, and what is `n_splits`? And it causes
forever hang on this method? If so, probably @zxybazh or I could reproduce this
bug and get it fixed :-)
--
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]
