masahi commented on code in PR #12911:
URL: https://github.com/apache/tvm/pull/12911#discussion_r980783267
##########
python/tvm/topi/hexagon/injective.py:
##########
@@ -42,8 +42,9 @@ def schedule_injective(outs):
# Fuse axes and vectorize inner elements
for x in outs:
fused = s[x].fuse(*x.op.axis)
- _, inner = s[x].split(fused, factor=128 // np.dtype(x.dtype).itemsize)
+ outer, inner = s[x].split(fused, factor=128 //
np.dtype(x.dtype).itemsize)
s[x].vectorize(inner)
+ s[x].parallel(outer)
Review Comment:
cc @kparzysz-quic @nverke, we are enabling multithreading of elemwise ops
here. Multithreading on e2e models have been stable since
https://github.com/apache/tvm/pull/12807
--
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]
