Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[TOPI][X86] Pool operator parallel support. #4090

Merged
merged 1 commit into from
Oct 9, 2019
Merged

[TOPI][X86] Pool operator parallel support. #4090

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
7 changes: 7 additions & 0 deletions topi/python/topi/x86/pooling.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -98,6 +98,13 @@ def traverse(OP):
traverse(tensor.op)
# schedule pool
elif OP.tag.startswith('pool'):
# Average pool accumulation and division happens in different for loops (#3607).
# To ensure good parallel support, apply multi-threading on the second loop.
if OP != outs[0].op:
output = outs[0]
output_fused = s[output].fuse(output.op.axis[0], output.op.axis[1])
s[output].parallel(output_fused)

PaddedInput = OP.input_tensors[0]
Pool = OP.output(0)
_schedule(PaddedInput, Pool)
Expand Down