Add new pass for math to rocdl. #93
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
searlmc1
pushed a commit
that referenced
this pull request
May 24, 2024
llvm#93290) …280)" This reverts commit 6977bfb.
jsjodin
requested review from
agozillon,
skatrak,
raghavendhra and
bhandarkar-pranav
agozillon
approved these changes
Jun 11, 2024
| @@ -3559,6 +3560,14 @@ class FIRToLLVMLowering | |||
| // as passes here. | |||
| mlir::OpPassManager mathConvertionPM("builtin.module"); | |||
|
|
|||
| bool isAMDGCN = fir::getTargetTriple(mod).isAMDGCN(); | |||
| // If compiling for AMD target some math operations must be lowered to ocml | |||
There was a problem hiding this comment.
Nit: would it be possible to get the full name for ocml in the comments? Maybe a weird request, just unfamiliar with the library so would be handy to have in the comment! if not that's not a big deal.
There was a problem hiding this comment.
I think ocml stands for OpenCL Math Library, so I'm not sure that will help or confuse more. I should perhaps use "AMD GPU math library" or something like that.
| @@ -3567,6 +3576,7 @@ class FIRToLLVMLowering | |||
| mathConvertionPM.addPass( | |||
| mlir::createConvertMathToFuncs(mathToFuncsOptions)); | |||
| mathConvertionPM.addPass(mlir::createConvertComplexToStandardPass()); | |||
|
|
|||
jsjodin
changed the title
skatrak
approved these changes
Jun 12, 2024
| // library calls, the rest can be converted to LLVM intrinsics, which is | ||
| // handled in the mathToLLVM conversion. The lowering to libm calls is not | ||
| // needed since all math operations are handled this way. | ||
| if (isAMDGCN) { |
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Outdated suggestions cannot be applied.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.
There are math operations that are not yet being converted, but it works for most operations. The changes to the flang codegen enables the pass for AMDGCN and disables the MathToLLVM and MathToLibm passes.