-
Notifications
You must be signed in to change notification settings - Fork 14.9k
[MLIR][ROCDL] Add math.clampf -> rocdl.fmed3 conversion #163520
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
[MLIR][ROCDL] Add math.clampf -> rocdl.fmed3 conversion #163520
Conversation
Signed-off-by: Keshav Vinayak Jha <keshavvinayakjha@gmail.com>
Signed-off-by: Keshav Vinayak Jha <keshavvinayakjha@gmail.com>
Signed-off-by: Keshav Vinayak Jha <keshavvinayakjha@gmail.com>
1. Added lit test for 1D and 2D vectors 2. Added unrolling support for ND inputs Signed-off-by: Keshav Vinayak Jha <keshavvinayakjha@gmail.com>
Signed-off-by: Keshav Vinayak Jha <keshavvinayakjha@gmail.com>
Signed-off-by: Keshav Vinayak Jha <keshavvinayakjha@gmail.com>
Signed-off-by: Keshav Vinayak Jha <keshavvinayakjha@gmail.com>
Signed-off-by: Keshav Vinayak Jha <keshavvinayakjha@gmail.com>
Signed-off-by: Keshav Vinayak Jha <keshavvinayakjha@gmail.com>
Signed-off-by: Keshav Vinayak Jha <keshavvinayakjha@gmail.com>
Removed the pass from the conditional block. That was probably the reason behind a lot of LLVM builedbot failures. |
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.
Thank you for trying to reland this. The reason the previous commit failed on shared build bots has not been addressed. The relevant error was:
ld.lld: error: undefined symbol: mlir::amdgpu::Chipset::parse(llvm::StringRef)
>>> referenced by MathToROCDL.cpp
>>> tools/mlir/lib/Conversion/MathToROCDL/CMakeFiles/obj.MLIRMathToROCDL.dir/MathToROCDL.cpp.o:(ConvertMathToROCDLPass::runOnOperation())
clang: error: linker command failed with exit code 1 (use -v to see invocation)
So you need to add the library implementing mlir::amdgpu::Chipset::parse(llvm::StringRef)
to the LINK libs of MathToROCDL in the CMAKE, otherwise this will fail again in the build bot.
…d MLIRAMDGPUUtils to LINK_LIBS Signed-off-by: Keshav Vinayak Jha <keshavvinayakjha@gmail.com>
…hToROCDLConversionPatterns call Signed-off-by: Keshav Vinayak Jha <keshavvinayakjha@gmail.com>
Signed-off-by: Keshav Vinayak Jha <keshavvinayakjha@gmail.com>
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, thanks!
@fabianmcg Please merge this since I don't have commit access yet. |
LLVM Buildbot has detected a new failure on builder Full details are available at: https://lab.llvm.org/buildbot/#/builders/169/builds/16096 Here is the relevant piece of the build log for the reference
|
Added Pattern for lowering
Math::ClampFOp
toROCDL::FMED3
.Also added
chipet
option toMathToRocdl
pass to check for arch support ISA instructionsSolves #15072
Reapplies #160100
Un-reverts the merged #163259, and fixes the error.