vinx13 commented on code in PR #13243:
URL: https://github.com/apache/tvm/pull/13243#discussion_r1009905506
##########
src/meta_schedule/schedule_rule/multi_level_tiling_tensor_core.cc:
##########
@@ -556,6 +556,11 @@ ScheduleRule ScheduleRule::MultiLevelTilingTensorCore(
Optional<Integer> max_innermost_factor, Optional<Array<Integer>>
vector_load_lens,
Optional<Map<String, ObjectRef>> reuse_read, Optional<Map<String,
ObjectRef>> reuse_write,
bool use_software_pipeline) {
+ if (tile_binds.defined()) {
+ for (const String& tile_bind : tile_binds.value()) {
+ CHECK_NE(tile_bind, "threadIdx.x") << "Cannot bind to threadIdx.x when
using tensor core.";
+ }
+ }
Review Comment:
Yes this check covered the broken case that incorrectly using `threadIdx.x`.
As a follow up, I'm thinking also adding some e2e search space generation test
for the default config for each target.
--
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]
