[Mlir-commits] [mlir] [mlir][vector] Linearization: push 'bit width' logic out of patterns (PR #136581)

Ivan Butygin llvmlistbot at llvm.org
Wed Apr 30 14:33:52 PDT 2025


Hardcode84 wrote:

The motivation to use dialect conversion instead of just greedy rewriter was so we can reuse existing generic scf/cf/func conversions to convert vector types through control flow ops.

https://github.com/llvm/llvm-project/pull/136581


More information about the Mlir-commits mailing list