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

Fix int8x4 broadcast value codegen in cuda #1959

Merged
merged 4 commits into from
Oct 24, 2018
Merged

Fix int8x4 broadcast value codegen in cuda #1959

merged 4 commits into from
Oct 24, 2018

Conversation

vinx13
Copy link
Member

@vinx13 vinx13 commented Oct 23, 2018

There are no make_int or make_int8x4 in cuda, so we need to generate packed value in codegen. This PR fixed codegen of x4(int8)imm_value in cuda.

@vinx13
Copy link
Member Author

vinx13 commented Oct 23, 2018

@tqchen Please review.

@vinx13 vinx13 force-pushed the feature/make_int8x4 branch 2 times, most recently from 6c76bb1 to 43da12b Compare October 23, 2018 05:52
@tqchen
Copy link
Member

tqchen commented Oct 23, 2018

@nishi-t can you help review this?

nishi-t
nishi-t reviewed Oct 23, 2018
View reviewed changes
Copy link
Contributor

@nishi-t nishi-t left a comment

Choose a reason for hiding this comment

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

Could you add the test for this change?

nishi-t
nishi-t approved these changes Oct 24, 2018
View reviewed changes
Copy link
Contributor

@nishi-t nishi-t left a comment

Choose a reason for hiding this comment

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

Thanks. Looks good to me.

@tqchen tqchen merged commit 155e955 into apache:master Oct 24, 2018
@tqchen
Copy link
Member

tqchen commented Oct 24, 2018

Thanks @nishi-t for reviewing, Thanks @vinx13 for contribution! This is merged

FrozenGene pushed a commit to FrozenGene/tvm that referenced this pull request Dec 27, 2018
@vinx13 @tqchen
Fix int8x4 broadcast value codegen in cuda (apache#1959)
f4dfcab
wweic pushed a commit to neo-ai/tvm that referenced this pull request Feb 20, 2019
@vinx13
Fix int8x4 broadcast value codegen in cuda (apache#1959)
bb6a321
wweic pushed a commit to neo-ai/tvm that referenced this pull request Feb 20, 2019
@vinx13
Fix int8x4 broadcast value codegen in cuda (apache#1959)
625627c
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@nishi-t nishi-t nishi-t approved these changes

Assignees
No one assigned
Labels
status: accepted
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
3 participants
@vinx13 @tqchen @nishi-t