shingjan commented on a change in pull request #10793:
URL: https://github.com/apache/tvm/pull/10793#discussion_r835676061
##########
File path: tests/python/unittest/test_meta_schedule_tune_relay.py
##########
@@ -323,6 +326,227 @@ def get_output(data, lib):
assert np.allclose(actual_output, expected_output, rtol=1e-4,
atol=2e-4)
+@register
+def int32x16(imm, span):
+ return imm.astype("int32x16", span)
+
+
[email protected]_func
Review comment:
maybe we could move all the tensorization intrinsics in the same place.
Right now for wmma/mma cuda it is `meta_schedule.testing.tir_tensor_intrin` but
I believe it is not upstreamed yet.
--
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]
