-
Notifications
You must be signed in to change notification settings - Fork 3.5k
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.
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
[Test] Fix AutoScheduler test to cover Conv2D Winograd #8539
Merged
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
modify format_lower
update from tvm
add set_output_zero_copy
sunjiweiswift
requested review from
areusch,
comaniac,
jroesch,
junrushao,
merrymercy,
tqchen and
yzhliu
as code owners
July 23, 2021 09:11
comaniac
approved these changes
Jul 23, 2021
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
LGTM. cc @jcf94
comaniac
changed the title
[UnitTests]Winograd ut outc <= 64
[Test] Fix AutoScheduler test to cover Conv2D Winograd
Jul 23, 2021
jcf94
approved these changes
Jul 24, 2021
ylc
pushed a commit
to ylc/tvm
that referenced
this pull request
Sep 29, 2021
* optimize resize vertor * tmp * DoMultiLevelTiling * modify size_t to int * modify * modify level fill * Update utils.cc modify format_lower * format lower count * delete blank lines * delete blank lines * re-commit message * Update graph_executor.h add set_output_zero_copy * add setoutputzero * add set output zero * Update graph_executor.cc * Update graph_executor.h * delete const_cast * add common function chechDltensor * Update graph_executor.h * Update graph_executor.cc * add output_ sort * Update graph_executor.cc * add a.nodeid == b.nodeid * add unit test for set output zero * add include <algorithm> * modify Setoutput zero copy * modify by clang-format * add unit test for set output zero * rrealy ut go back * rrealy ut go back * modify input->output * delete sort output input * modify build_module_test.cc * midify winograd UT * re-pr * empty commit * empty commit * empty commit * empty commit * empty commit * empty commit * empty commit * empty commit * empty commit * empty commit * empty commit * empty commit
ylc
pushed a commit
to ylc/tvm
that referenced
this pull request
Jan 13, 2022
* optimize resize vertor * tmp * DoMultiLevelTiling * modify size_t to int * modify * modify level fill * Update utils.cc modify format_lower * format lower count * delete blank lines * delete blank lines * re-commit message * Update graph_executor.h add set_output_zero_copy * add setoutputzero * add set output zero * Update graph_executor.cc * Update graph_executor.h * delete const_cast * add common function chechDltensor * Update graph_executor.h * Update graph_executor.cc * add output_ sort * Update graph_executor.cc * add a.nodeid == b.nodeid * add unit test for set output zero * add include <algorithm> * modify Setoutput zero copy * modify by clang-format * add unit test for set output zero * rrealy ut go back * rrealy ut go back * modify input->output * delete sort output input * modify build_module_test.cc * midify winograd UT * re-pr * empty commit * empty commit * empty commit * empty commit * empty commit * empty commit * empty commit * empty commit * empty commit * empty commit * empty commit * empty commit
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
tvm/python/tvm/relay/op/strategy/x86.py
147-159
judge_winograd_auto_scheduler = False
if len(kernel.shape) == 4:
kernel_h, kernel_w, _, co = get_const_tuple(kernel.shape)
judge_winograd_auto_scheduler = (
"float" in data.dtype
and "float" in kernel.dtype
and kernel_h == 3
and kernel_w == 3
and stride_h == 1
and stride_w == 1
and dilation_h == 1
and dilation_w == 1
and 64 < co < 512
# The last condition of co is based on our profiling of resnet workloads
# on skylake avx512 machines. We found winograd is faster than direct
# only when co is within this range
)
"co" need large than 64
outc defaults is 32
can not enter winograd