Right now we do opcode wise matching to identify uniform/non-divergent
AMDGPU intrinsics. It is duplicated at 2 places once at IR level uniformity analysis
and at MIR level. Moving them to single tablegen table for consistency and adding
and API rapper to access them.
Details
Details
- Reviewers
arsenm sameerds - Group Reviewers
Restricted Project - Commits
- rG422d379de287: [AMDGPU] Use tablegen to list uniform intrinsics
Diff Detail
Diff Detail
Time | Test | |
---|---|---|
50 ms | x64 debian > MLIR.Dialect/Bufferization/Transforms::one-shot-module-bufferize-force-copy-before-write.mlir Script:
--
: 'RUN: at line 1'; /var/lib/buildkite-agent/builds/llvm-project/build/bin/mlir-opt /var/lib/buildkite-agent/builds/llvm-project/mlir/test/Dialect/Bufferization/Transforms/one-shot-module-bufferize-force-copy-before-write.mlir -one-shot-bufferize="bufferize-function-boundaries=1 no-analysis-func-filter=contains_to_memref_op" -drop-equivalent-buffer-results --split-input-file | /var/lib/buildkite-agent/builds/llvm-project/build/bin/FileCheck /var/lib/buildkite-agent/builds/llvm-project/mlir/test/Dialect/Bufferization/Transforms/one-shot-module-bufferize-force-copy-before-write.mlir
|