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

Jump to bottom

Implement Fold and Unfold #3167

Open
wants to merge 74 commits into
base: develop
Choose a base branch
from
Open

Implement Fold and Unfold #3167

wants to merge 74 commits into from
+4,355 −4

Conversation

DuongQLee
Copy link
Collaborator

@DuongQLee DuongQLee commented Jul 29, 2024 •
edited
Loading

  • Added Fold and Unfold op.
  • Full benchmark result compared to ROCm Here
  • Average performance:

Op Dtype Direction Time
Unfold fp32 fwd 16.43641979
fp32 bwd 1.458798342
fp16 fwd 15.83955361
fp16 bwd 1.459763543
bfp16 fwd 15.90593279
bfp16 bwd 1.455323877
Fold fp32 fwd 1.463731927
fp32 bwd 28.09828887
fp16 fwd 1.479315364
fp16 bwd 28.08557933
bfp16 fwd 1.47158127
bfp16 bwd 26.84660993

DuongQLee added 28 commits July 2, 2024 11:02
@DuongQLee
UnfoldFwd4d driver, test and api
113620a
@DuongQLee
githook format
6902fdf
@DuongQLee
githook format
0f15ed5
@DuongQLee
unfold backward driver and gtest
9b49b9d
@DuongQLee
githook format
83fba56
@DuongQLee
Add foldfwd, foldbwd, problem_description verification, gtest and driver
101794f
@DuongQLee
githook format
9286ce7
@DuongQLee
update doc and miopen.h description
e59ce36
@DuongQLee
Update driver help text
c114934
@DuongQLee
Change IN_OUT_TYPE to FLOAT
bd5db59
@DuongQLee
add __restrict__ to tensor pointer
4bb5855
@DuongQLee
replace include "" with <>
918a267
@DuongQLee
change all int -> int32_t, remove duplicate lines in solver
4f51b6e
@DuongQLee
githook format
e726fc1
@DuongQLee
remove useless if else in problem description
8ee2861
@DuongQLee
add more tensor_layout_t constructor and update kernel to use get_ten…
f3dea16 
…sor_view_idx
@DuongQLee
githook format
4a83296
@DuongQLee
remove {}
299117b
@DuongQLee
update code as comments
e76095e
@DuongQLee
githook format
526f772
@DuongQLee
cpu_fold -> cpu_unfold
2a3d2b0
@DuongQLee
update code as comments
27e26c3
@DuongQLee
githook format
366e350
@DuongQLee
Merge branch 'develop' into mv_510_fold
8f14828
@DuongQLee
githook format
2b3bd1f
@DuongQLee
Update gtest code
5c506b4
@DuongQLee
Merge remote-tracking branch 'origin' into mv_510_fold
4e97559
@DuongQLee
githook format
e2631d8
@hieule88 hieule88 requested a review from CAHEK7 October 18, 2024 04:10
@hieule88 hieule88 assigned hieule88 and unassigned DuongQLee Oct 18, 2024
@hieule88
Copy link
Collaborator

@iq136boy Would you send us the build log of this PR?

iq136boy
iq136boy requested changes Oct 22, 2024
View reviewed changes
Copy link
Contributor

@iq136boy iq136boy left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Please fix the following errors:
error_log_3167.txt

iq136boy
iq136boy reviewed Nov 6, 2024
View reviewed changes
Copy link
Contributor

@iq136boy iq136boy left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Error log:
error_log (2).txt

iq136boy
iq136boy reviewed Nov 19, 2024
View reviewed changes
Copy link
Contributor

@iq136boy iq136boy left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Error log:
3167_log.txt

@hieule88
Copy link
Collaborator

Error log: 3167_log.txt

I fixed this error. Please send me the newest error log of this PR.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@hieule88 hieule88 hieule88 left review comments

@iq136boy iq136boy iq136boy requested changes

@JehandadKhan JehandadKhan Awaiting requested review from JehandadKhan

@junliume junliume Awaiting requested review from junliume

@DrizztDoUrden DrizztDoUrden Awaiting requested review from DrizztDoUrden

@BrianHarrisonAMD BrianHarrisonAMD Awaiting requested review from BrianHarrisonAMD BrianHarrisonAMD is a code owner

@CAHEK7 CAHEK7 Awaiting requested review from CAHEK7

@BradPepersAMD BradPepersAMD Awaiting requested review from BradPepersAMD BradPepersAMD is a code owner

Requested changes must be addressed to merge this pull request.

Assignees

@hieule88 hieule88

Labels
enhancement external_collaborator TESTING_CI_PASSED
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
5 participants
@DuongQLee @iq136boy @long10024070 @hieule88 @CAHEK7