[AMDGPU] Add use check in v_fma combine.

[tsymalla]

Summary

In D132837, an existing v_fma combine was extended to regard nested
fma instructions. Originally, the inner FMA was checked for being used
only once. In its current state, this check is missing, which causes
some regressions.

In this patch, this check was added.

llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp

if (isFusedOp(N0) && N0.hasOneUse()) {
       FMA = N0;
       E = N1;
     } else if (isFusedOp(N1) && N1.hasOneUse()) {
       FMA = N1;
       E = N0;
     }
 
     SDValue TmpFMA = FMA;
-    while (E && isFusedOp(TmpFMA)) {
+    while (E && isFusedOp(TmpFMA) && TmpFMA.hasOneUse()) {
       SDValue FMul = TmpFMA->getOperand(2);
       if (FMul.getOpcode() == ISD::FMUL && FMul.hasOneUse()) {
         SDValue C = FMul.getOperand(0);
         SDValue D = FMul.getOperand(1);
         SDValue CDE = DAG.getNode(PreferredFusedOpcode, SL, VT, C, D, E);
         DAG.ReplaceAllUsesOfValueWith(FMul, CDE);
         return FMA;
       }

llvm/test/CodeGen/AMDGPU/dagcombine-fma-fmad.ll

; GCN-NEXT:    ; return to shader part epilog
   %t4 = fadd fast float %t2, %t3
   %t5 = fadd fast float %t4, %g
   ret float %t5
 }
 
 define amdgpu_ps float @fmac_sequence_innermost_fmul_multiple_use(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_multiple_use:
 ; GCN:       ; %bb.0:
-; GCN-NEXT:    v_mac_f32_e64 v0, s2, s3
-; GCN-NEXT:    v_fmac_f32_e64 v0, s0, s1
-; GCN-NEXT:    v_fma_f32 v1, s5, s4, v0
-; GCN-NEXT:    v_fmac_f32_e32 v0, s5, v1
+; GCN-NEXT:    v_mul_f32_e64 v1, s2, s3
+; GCN-NEXT:    v_fmac_f32_e64 v1, s0, s1
+; GCN-NEXT:    v_fma_f32 v2, s5, s4, v1
+; GCN-NEXT:    v_fmac_f32_e32 v1, s5, v2
+; GCN-NEXT:    v_add_f32_e32 v0, v1, v0
 ; 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 = fmul fast float %f, %t4
   %t6 = fadd fast float %t5, %t2