[llvm] [AArch64] Legalize fp128 scalars as libcalls for G_FCMP (PR #98452)

David Green via llvm-commits llvm-commits at lists.llvm.org
Tue Jul 16 04:27:33 PDT 2024


================
@@ -560,7 +560,7 @@ AArch64LegalizerInfo::AArch64LegalizerInfo(const AArch64Subtarget &ST)
       })
       .widenScalarOrEltToNextPow2(1)
       .clampScalar(0, s32, s32)
-      .clampScalarOrElt(1, MinFPScalar, s64)
+      .clampScalarOrElt(1, MinFPScalar, s128)
----------------
davemgreen wrote:

Is this needed? If so could it use minScalarOrElt?

Is it worth scalarizing vectors in this same patch?

https://github.com/llvm/llvm-project/pull/98452


More information about the llvm-commits mailing list