[PowerPC] recognize vmnsub in older ppc versions (#155465)

fixes #129432

Recognize expansion sequence of negate where it isn't legal in order to select multiply-subtract.

Author: folkertdev

llvm/lib/Target/PowerPC/PPCInstrAltivec.td

@@ -30,6 +30,11 @@
 // Altivec transformation functions and pattern fragments.
 //
 
+// fneg is not legal, and desugared as an xor.
+def desugared_fneg : PatFrag<(ops node:$x), (v4f32 (bitconvert (xor (bitconvert $x), 
+                             (int_ppc_altivec_vslw (bitconvert (v16i8 immAllOnesV)), 
+                             (bitconvert (v16i8 immAllOnesV))))))>; 
+
 def vpkuhum_shuffle : PatFrag<(ops node:$lhs, node:$rhs),
                               (vector_shuffle node:$lhs, node:$rhs), [{
   return PPC::isVPKUHUMShuffleMask(cast<ShuffleVectorSDNode>(N), 0, *CurDAG);
@@ -467,11 +472,12 @@ def VMADDFP : VAForm_1<46, (outs vrrc:$RT), (ins vrrc:$RA, vrrc:$RC, vrrc:$RB),
                        [(set v4f32:$RT,
                         (fma v4f32:$RA, v4f32:$RC, v4f32:$RB))]>;
 
-// FIXME: The fma+fneg pattern won't match because fneg is not legal.
+// fneg is not legal, hence we have to match on the desugared version. 
 def VNMSUBFP: VAForm_1<47, (outs vrrc:$RT), (ins vrrc:$RA, vrrc:$RC, vrrc:$RB),
                        "vnmsubfp $RT, $RA, $RC, $RB", IIC_VecFP,
-                       [(set v4f32:$RT, (fneg (fma v4f32:$RA, v4f32:$RC,
-                                                  (fneg v4f32:$RB))))]>;
+                       [(set v4f32:$RT, (desugared_fneg (fma v4f32:$RA, v4f32:$RC,
+                                                  (desugared_fneg v4f32:$RB))))]>;
+
 let hasSideEffects = 1 in {
   def VMHADDSHS  : VA1a_Int_Ty<32, "vmhaddshs", int_ppc_altivec_vmhaddshs, v8i16>;
   def VMHRADDSHS : VA1a_Int_Ty<33, "vmhraddshs", int_ppc_altivec_vmhraddshs,
@@ -892,6 +898,13 @@ def : Pat<(mul v8i16:$vA, v8i16:$vB), (VMLADDUHM $vA, $vB, (v8i16(V_SET0H)))>;
 // Add
 def : Pat<(add (mul v8i16:$vA, v8i16:$vB), v8i16:$vC), (VMLADDUHM $vA, $vB, $vC)>;
 
+
+// Fused negated multiply-subtract
+def : Pat<(v4f32 (desugared_fneg
+                    (int_ppc_altivec_vmaddfp v4f32:$RA, v4f32:$RC,
+                         (desugared_fneg v4f32:$RB)))),
+          (VNMSUBFP $RA, $RC, $RB)>;
+
 // Saturating adds/subtracts.
 def : Pat<(v16i8 (saddsat v16i8:$vA, v16i8:$vB)), (v16i8 (VADDSBS $vA, $vB))>;
 def : Pat<(v16i8 (uaddsat v16i8:$vA, v16i8:$vB)), (v16i8 (VADDUBS $vA, $vB))>;

llvm/test/CodeGen/PowerPC/vec-nmsub.ll

@@ -0,0 +1,36 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 5
+; RUN: llc -verify-machineinstrs < %s -mcpu=pwr5 -mtriple=ppc32-- -mattr=+altivec | FileCheck %s
+
+define dso_local <4 x float> @intrinsic(<4 x float> noundef %a, <4 x float> noundef %b, <4 x float> noundef %c) local_unnamed_addr {
+; CHECK-LABEL: intrinsic:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vnmsubfp 2, 2, 3, 4
+; CHECK-NEXT:    blr
+entry:
+  %0 = tail call <4 x float> @llvm.ppc.altivec.vnmsubfp(<4 x float> %a, <4 x float> %b, <4 x float> %c)
+  ret <4 x float> %0
+}
+
+define <4 x float> @manual_llvm_fma(<4 x float> %a, <4 x float> %b, <4 x float> %c) unnamed_addr {
+; CHECK-LABEL: manual_llvm_fma:
+; CHECK:       # %bb.0: # %start
+; CHECK-NEXT:    vnmsubfp 2, 2, 3, 4
+; CHECK-NEXT:    blr
+start:
+  %0 = fneg <4 x float> %c
+  %1 = tail call <4 x float> @llvm.fma.v4f32(<4 x float> %a, <4 x float> %b, <4 x float> %0)
+  %2 = fneg <4 x float> %1
+  ret <4 x float> %2
+}
+
+define dso_local <4 x float> @manual_vmaddfp(<4 x float> noundef %a, <4 x float> noundef %b, <4 x float> noundef %c) local_unnamed_addr {
+; CHECK-LABEL: manual_vmaddfp:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    vnmsubfp 2, 2, 3, 4
+; CHECK-NEXT:    blr
+entry:
+  %fneg.i3 = fneg <4 x float> %c
+  %0 = tail call <4 x float> @llvm.ppc.altivec.vmaddfp(<4 x float> %a, <4 x float> %b, <4 x float> %fneg.i3)
+  %fneg.i = fneg <4 x float> %0
+  ret <4 x float> %fneg.i
+}