[Mlir-commits] [mlir] [mlir][linalg] Add mixed precision folding pattern in vectorize_children_and_apply_patterns TD Op (PR #148684)
Tuomas Kärnä
llvmlistbot at llvm.org
Thu Jul 31 12:57:54 PDT 2025
tkarna wrote:
Thanks @shahidact! I confirm that with this PR I can vectorize mixed precision (f16, f16 -> f32) matmuls.
https://github.com/llvm/llvm-project/pull/148684
More information about the Mlir-commits
mailing list