[X86] Stop custom-widening v2f32 = fpext v2bf16 (llvm#80106)

llvm/lib/Target/X86/X86ISelLowering.cpp

@@ -32852,6 +32852,8 @@ void X86TargetLowering::ReplaceNodeResults(SDNode *N,
       return;
     bool IsStrict = N->isStrictFPOpcode();
     SDValue Src = N->getOperand(IsStrict ? 1 : 0);
+    if (Src.getValueType().getVectorElementType() != MVT::f16)
+      return;
     SDValue Ext = IsStrict ? DAG.getConstantFP(0.0, dl, MVT::v2f16)
                            : DAG.getUNDEF(MVT::v2f16);
     SDValue V = DAG.getNode(ISD::CONCAT_VECTORS, dl, MVT::v4f16, Src, Ext);

llvm/test/CodeGen/X86/concat-fpext-v2bf16.ll

@@ -0,0 +1,40 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: llc < %s -mtriple=x86_64-- -mattr=avx512bf16,avx512fp16      | FileCheck %s
+
+define void @test(<2 x ptr> %ptr) {
+; CHECK-LABEL: test:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    xorl %eax, %eax
+; CHECK-NEXT:    testb %al, %al
+; CHECK-NEXT:    je .LBB0_1
+; CHECK-NEXT:  # %bb.2: # %loop.127.preheader
+; CHECK-NEXT:    retq
+; CHECK-NEXT:  .LBB0_1: # %ifmerge.89
+; CHECK-NEXT:    movzwl (%rax), %eax
+; CHECK-NEXT:    shll $16, %eax
+; CHECK-NEXT:    vmovd %eax, %xmm0
+; CHECK-NEXT:    vmulss %xmm0, %xmm0, %xmm0
+; CHECK-NEXT:    vbroadcastss %xmm0, %xmm0
+; CHECK-NEXT:    vmovlps %xmm0, (%rax)
+entry:
+  br label %then.13
+
+then.13:                                          ; preds = %entry
+  %0 = fpext bfloat poison to float
+  br i1 poison, label %loop.127.preheader, label %ifmerge.89
+
+ifmerge.89:                                       ; preds = %then.13
+  %.splatinsert144 = insertelement <2 x float> poison, float %0, i64 0
+  %.splat145 = shufflevector <2 x float> %.splatinsert144, <2 x float> poison, <2 x i32> zeroinitializer
+  %1 = tail call <2 x bfloat> @llvm.masked.gather.v2bf16.v2p0(<2 x ptr> undef, i32 2, <2 x i1> <i1 true, i1 true>, <2 x bfloat> poison)
+  %2 = fpext <2 x bfloat> %1 to <2 x float>
+  %3 = fmul fast <2 x float> %.splat145, %2
+  %4 = fadd fast <2 x float> zeroinitializer, %3
+  store <2 x float> %4, ptr poison, align 4
+  unreachable
+
+loop.127.preheader:                               ; preds = %then.13
+  ret void
+}
+
+declare <2 x bfloat> @llvm.masked.gather.v2bf16.v2p0(<2 x ptr>, i32 immarg, <2 x i1>, <2 x bfloat>)