[Mlir-commits] [mlir] [mlir][AMDGPU] Support vector<2xf16> inputs to buffer atomic fadd (PR #108286)

Krzysztof Drewniak llvmlistbot at llvm.org
Wed Sep 11 15:38:36 PDT 2024


krzysz00 wrote:

Note: force-pushed to get rid of an unneeded and style-breaking loss of indentation (while incidentally cleaning up some trailing whitespace), am relying on a previous CI pass and local testing to merge

https://github.com/llvm/llvm-project/pull/108286


More information about the Mlir-commits mailing list