[CodeGen][CUDA] Fix bugs #5209
Merged
[CodeGen][CUDA] Fix bugs #5209
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
- Support vectorized casts - It is incorrect to extract elements from int8x4 with 0x000000ff & (x >> i * 8) as this value is of type int in C/C++. If this expression is used for sign extensions, the sign bit will be wrong. Simply use C style casts instead and sign bits will just work. Signed-off-by: Wei Pan <weip@nvidia.com>
|
@vinx13 would be great if you can help to take a look |
vinx13
reviewed
Apr 2, 2020
| return CodeGenC::VisitExpr_(op, os); | ||
|
|
||
| // We could emit make_float4 like calls, but the emitted code looks | ||
| // too compact to read. Emit this as vectorized unary ops. |
There was a problem hiding this comment.
is there any difference in performance?
There was a problem hiding this comment.
No, typical optimizations like mem2reg will promote temporary into registers and make them equivalent.
vinx13
approved these changes
Apr 3, 2020
trevor-m
pushed a commit
to trevor-m/tvm
that referenced
this pull request
Apr 16, 2020
- Support vectorized casts - It is incorrect to extract elements from int8x4 with 0x000000ff & (x >> i * 8) as this value is of type int in C/C++. If this expression is used for sign extensions, the sign bit will be wrong. Simply use C style casts instead and sign bits will just work. Signed-off-by: Wei Pan <weip@nvidia.com>
zhiics
pushed a commit
to neo-ai/tvm
that referenced
this pull request
Apr 17, 2020
- Support vectorized casts - It is incorrect to extract elements from int8x4 with 0x000000ff & (x >> i * 8) as this value is of type int in C/C++. If this expression is used for sign extensions, the sign bit will be wrong. Simply use C style casts instead and sign bits will just work. Signed-off-by: Wei Pan <weip@nvidia.com>
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.
Support vectorized casts
It is incorrect to extract elements from int8x4 with
0x000000ff & (x >> i * 8)
as this value is of type int in C/C++. If this expression
is used for sign extensions, the sign bit will be wrong.
Simply use C style casts instead and sign bits will just work.
Signed-off-by: Wei Pan weip@nvidia.com
Thanks for contributing to TVM! Please refer to guideline https://tvm.apache.org/docs/contribute/ for useful information and tips. After the pull request is submitted, please request code reviews from Reviewers by @ them in the pull request thread.