diff --git a/llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp b/llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
--- a/llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
+++ b/llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
@@ -14305,10 +14305,8 @@
       if (FMul.getOpcode() == ISD::FMUL && FMul.hasOneUse()) {
         SDValue C = FMul.getOperand(0);
         SDValue D = FMul.getOperand(1);
-
-        DAG.MorphNodeTo(FMul.getNode(), PreferredFusedOpcode, FMul->getVTList(),
-                        {C, D, E});
-
+        SDValue CDE = DAG.getNode(PreferredFusedOpcode, SL, VT, C, D, E);
+        DAG.ReplaceAllUsesOfValueWith(FMul, CDE);
         return FMA;
       }
 
diff --git a/llvm/test/CodeGen/AMDGPU/dagcombine-fma-fmad.ll b/llvm/test/CodeGen/AMDGPU/dagcombine-fma-fmad.ll
--- a/llvm/test/CodeGen/AMDGPU/dagcombine-fma-fmad.ll
+++ b/llvm/test/CodeGen/AMDGPU/dagcombine-fma-fmad.ll
@@ -221,6 +221,22 @@
   ret float %t5
 }
 
+define amdgpu_ps float @fmac_sequence_innermost_fmul_sgpr(float inreg %a, float inreg %b, float inreg %c, float inreg %d, float inreg %e, float inreg %f, float %g) #0 {
+; GCN-LABEL: fmac_sequence_innermost_fmul_sgpr:
+; GCN:       ; %bb.0:
+; GCN-NEXT:    v_mac_f32_e64 v0, s2, s3
+; GCN-NEXT:    v_fmac_f32_e64 v0, s0, s1
+; GCN-NEXT:    v_fmac_f32_e64 v0, s4, s5
+; GCN-NEXT:    ; return to shader part epilog
+  %t0 = fmul fast float %a, %b
+  %t1 = fmul fast float %c, %d
+  %t2 = fadd fast float %t0, %t1
+  %t3 = fmul fast float %e, %f
+  %t4 = fadd fast float %t2, %t3
+  %t5 = fadd fast float %t4, %g
+  ret float %t5
+}
+
 ; Function Attrs: nofree nosync nounwind readnone speculatable willreturn
 declare float @llvm.maxnum.f32(float, float) #1