tqchen commented on a change in pull request #8531:
URL: https://github.com/apache/tvm/pull/8531#discussion_r674819885
##########
File path: tests/python/unittest/test_tvmscript_roundtrip.py
##########
@@ -2961,15 +2961,15 @@ def test_abs():
@tvm.script.tir
-def printer(a: ty.handle) -> None:
+def constant_folding(a: ty.handle) -> None:
A = tir.match_buffer(a, (), "float32")
A[()] = tir.min(2.2, 5.2)
- A[()] = tir.max(tir.float32(2.2), tir.float32(5.2))
+ A[()] = tir.max(tir.float32(2.2), tir.float32(tir.float32(5.2)))
Review comment:
it is intended to test the fact that we actually fold conversions of
float32 into one
--
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]
