[AMDGPU] fixes mistake in #82018

[nickleus27]

fixes #81766 #82018

[llvmbot]

@llvm/pr-subscribers-backend-amdgpu

Author: Nick Anderson (nickleus27)

Changes

fixes #81766 #82018

---

Full diff: https://github.com/llvm/llvm-project/pull/82223.diff

1 Files Affected:

• (modified) llvm/lib/Target/AMDGPU/SIISelLowering.cpp (+1-1)

diff --git a/llvm/lib/Target/AMDGPU/SIISelLowering.cpp b/llvm/lib/Target/AMDGPU/SIISelLowering.cpp
index 5e1d7508503741..257dff6ef6839d 100644
--- a/llvm/lib/Target/AMDGPU/SIISelLowering.cpp
+++ b/llvm/lib/Target/AMDGPU/SIISelLowering.cpp
@@ -6306,7 +6306,7 @@ SDValue SITargetLowering::lowerFMINNUM_FMAXNUM(SDValue Op,
     return expandFMINNUM_FMAXNUM(Op.getNode(), DAG);
 
   if (VT == MVT::v4f16 || VT == MVT::v8f16 || VT == MVT::v16f16 ||
-      VT == MVT::v32f16)
+      VT == MVT::v16bf16)
     return splitBinaryVectorOp(Op, DAG);
   return Op;
 }

[nickleus27]

If everyone approves could someone go ahead and commit for me. I do not have write access. Thank you.