[Mlir-commits] [mlir] [mlir][arith][transforms] Adds Truncf f32 to f4e2m1 (PR #144157)

Jakub Kuderski llvmlistbot at llvm.org
Thu Jun 19 12:48:16 PDT 2025


================
@@ -228,9 +243,8 @@ struct BFloat16ExtFOpConverter : public OpRewritePattern<arith::ExtFOp> {
     Type operandETy = getElementTypeOrSelf(operandTy);
     Type resultETy = getElementTypeOrSelf(resultTy);
 
-    if (!operandETy.isBF16() || !resultETy.isF32()) {
+    if (!operandETy.isBF16() || !resultETy.isF32())
----------------
kuhar wrote:

Let's drop unrelated formatting/coding style changes from this PR and land this separately. This should take no time to review and make this PR shorter.

https://github.com/llvm/llvm-project/pull/144157


More information about the Mlir-commits mailing list