Revert "[DAGCombiner] Add support for scalarising extracts of a vector setcc (#116031)" (#117556)

david-arm · web-flow · commit 9b76e7fc6030 · 2024-11-25T13:49:21.000Z
This reverts commit 22ec44f.
diff --git a/llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp b/llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
@@ -22746,21 +22746,16 @@ SDValue DAGCombiner::scalarizeExtractedVectorLoad(SDNode *EVE, EVT InVecVT,
 
 /// Transform a vector binary operation into a scalar binary operation by moving
 /// the math/logic after an extract element of a vector.
-static SDValue scalarizeExtractedBinOp(SDNode *ExtElt, SelectionDAG &DAG,
-                                       const SDLoc &DL) {
+static SDValue scalarizeExtractedBinop(SDNode *ExtElt, SelectionDAG &DAG,
+                                       const SDLoc &DL, bool LegalOperations) {
   const TargetLowering &TLI = DAG.getTargetLoweringInfo();
   SDValue Vec = ExtElt->getOperand(0);
   SDValue Index = ExtElt->getOperand(1);
   auto *IndexC = dyn_cast<ConstantSDNode>(Index);
-  unsigned Opc = Vec.getOpcode();
-  if (!IndexC || (!TLI.isBinOp(Opc) && Opc != ISD::SETCC) || !Vec.hasOneUse() ||
+  if (!IndexC || !TLI.isBinOp(Vec.getOpcode()) || !Vec.hasOneUse() ||
       Vec->getNumValues() != 1)
     return SDValue();
 
-  EVT ResVT = ExtElt->getValueType(0);
-  if (Opc == ISD::SETCC && ResVT != Vec.getValueType().getVectorElementType())
-    return SDValue();
-
   // Targets may want to avoid this to prevent an expensive register transfer.
   if (!TLI.shouldScalarizeBinop(Vec))
     return SDValue();
@@ -22771,23 +22766,19 @@ static SDValue scalarizeExtractedBinOp(SDNode *ExtElt, SelectionDAG &DAG,
   SDValue Op0 = Vec.getOperand(0);
   SDValue Op1 = Vec.getOperand(1);
   APInt SplatVal;
-  if (!isAnyConstantBuildVector(Op0, true) &&
-      !ISD::isConstantSplatVector(Op0.getNode(), SplatVal) &&
-      !isAnyConstantBuildVector(Op1, true) &&
-      !ISD::isConstantSplatVector(Op1.getNode(), SplatVal))
-    return SDValue();
-
-  // extractelt (op X, C), IndexC --> op (extractelt X, IndexC), C'
-  // extractelt (op C, X), IndexC --> op C', (extractelt X, IndexC)
-  EVT OpVT = Op0->getValueType(0).getVectorElementType();
-  Op0 = DAG.getNode(ISD::EXTRACT_VECTOR_ELT, DL, OpVT, Op0, Index);
-  Op1 = DAG.getNode(ISD::EXTRACT_VECTOR_ELT, DL, OpVT, Op1, Index);
+  if (isAnyConstantBuildVector(Op0, true) ||
+      ISD::isConstantSplatVector(Op0.getNode(), SplatVal) ||
+      isAnyConstantBuildVector(Op1, true) ||
+      ISD::isConstantSplatVector(Op1.getNode(), SplatVal)) {
+    // extractelt (binop X, C), IndexC --> binop (extractelt X, IndexC), C'
+    // extractelt (binop C, X), IndexC --> binop C', (extractelt X, IndexC)
+    EVT VT = ExtElt->getValueType(0);
+    SDValue Ext0 = DAG.getNode(ISD::EXTRACT_VECTOR_ELT, DL, VT, Op0, Index);
+    SDValue Ext1 = DAG.getNode(ISD::EXTRACT_VECTOR_ELT, DL, VT, Op1, Index);
+    return DAG.getNode(Vec.getOpcode(), DL, VT, Ext0, Ext1);
+  }
 
-  if (Opc == ISD::SETCC)
-    return DAG.getSetCC(DL, ResVT, Op0, Op1,
-                        cast<CondCodeSDNode>(Vec->getOperand(2))->get());
-  else
-    return DAG.getNode(Opc, DL, ResVT, Op0, Op1);
+  return SDValue();
 }
 
 // Given a ISD::EXTRACT_VECTOR_ELT, which is a glorified bit sequence extract,
@@ -23020,7 +23011,7 @@ SDValue DAGCombiner::visitEXTRACT_VECTOR_ELT(SDNode *N) {
     }
   }
 
-  if (SDValue BO = scalarizeExtractedBinOp(N, DAG, DL))
+  if (SDValue BO = scalarizeExtractedBinop(N, DAG, DL, LegalOperations))
     return BO;
 
   if (VecVT.isScalableVector())
diff --git a/llvm/lib/Target/AArch64/AArch64ISelLowering.h b/llvm/lib/Target/AArch64/AArch64ISelLowering.h
@@ -1348,10 +1348,6 @@ class AArch64TargetLowering : public TargetLowering {
   unsigned getMinimumJumpTableEntries() const override;
 
   bool softPromoteHalfType() const override { return true; }
-
-  bool shouldScalarizeBinop(SDValue VecOp) const override {
-    return VecOp.getOpcode() == ISD::SETCC;
-  }
 };
 
 namespace AArch64 {
diff --git a/llvm/lib/Target/RISCV/RISCVISelLowering.cpp b/llvm/lib/Target/RISCV/RISCVISelLowering.cpp
@@ -2093,7 +2093,7 @@ bool RISCVTargetLowering::shouldScalarizeBinop(SDValue VecOp) const {
 
   // Assume target opcodes can't be scalarized.
   // TODO - do we have any exceptions?
-  if (Opc >= ISD::BUILTIN_OP_END || !isBinOp(Opc))
+  if (Opc >= ISD::BUILTIN_OP_END)
     return false;
 
   // If the vector op is not supported, try to convert to scalar.
diff --git a/llvm/lib/Target/WebAssembly/WebAssemblyISelLowering.cpp b/llvm/lib/Target/WebAssembly/WebAssemblyISelLowering.cpp
@@ -429,7 +429,7 @@ bool WebAssemblyTargetLowering::shouldScalarizeBinop(SDValue VecOp) const {
 
   // Assume target opcodes can't be scalarized.
   // TODO - do we have any exceptions?
-  if (Opc >= ISD::BUILTIN_OP_END || !isBinOp(Opc))
+  if (Opc >= ISD::BUILTIN_OP_END)
     return false;
 
   // If the vector op is not supported, try to convert to scalar.
diff --git a/llvm/lib/Target/X86/X86ISelLowering.cpp b/llvm/lib/Target/X86/X86ISelLowering.cpp
@@ -3300,7 +3300,7 @@ bool X86TargetLowering::shouldScalarizeBinop(SDValue VecOp) const {
 
   // Assume target opcodes can't be scalarized.
   // TODO - do we have any exceptions?
-  if (Opc >= ISD::BUILTIN_OP_END || !isBinOp(Opc))
+  if (Opc >= ISD::BUILTIN_OP_END)
     return false;
 
   // If the vector op is not supported, try to convert to scalar.
diff --git a/llvm/test/CodeGen/AArch64/dag-combine-concat-vectors.ll b/llvm/test/CodeGen/AArch64/dag-combine-concat-vectors.ll
@@ -5,7 +5,7 @@
 
 declare void @llvm.masked.scatter.nxv16i8.nxv16p0(<vscale x 16 x i8>, <vscale x 16 x ptr>, i32 immarg, <vscale x 16 x i1>)
 
-define fastcc i8 @allocno_reload_assign(ptr %p) {
+define fastcc i8 @allocno_reload_assign() {
 ; CHECK-LABEL: allocno_reload_assign:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    fmov d0, xzr
@@ -14,8 +14,8 @@ define fastcc i8 @allocno_reload_assign(ptr %p) {
 ; CHECK-NEXT:    cmpeq p0.d, p0/z, z0.d, #0
 ; CHECK-NEXT:    uzp1 p0.s, p0.s, p0.s
 ; CHECK-NEXT:    uzp1 p0.h, p0.h, p0.h
-; CHECK-NEXT:    uzp1 p8.b, p0.b, p0.b
-; CHECK-NEXT:    mov z0.b, p8/z, #1 // =0x1
+; CHECK-NEXT:    uzp1 p0.b, p0.b, p0.b
+; CHECK-NEXT:    mov z0.b, p0/z, #1 // =0x1
 ; CHECK-NEXT:    fmov w8, s0
 ; CHECK-NEXT:    mov z0.b, #0 // =0x0
 ; CHECK-NEXT:    uunpklo z1.h, z0.b
@@ -30,35 +30,34 @@ define fastcc i8 @allocno_reload_assign(ptr %p) {
 ; CHECK-NEXT:    punpklo p1.h, p0.b
 ; CHECK-NEXT:    punpkhi p0.h, p0.b
 ; CHECK-NEXT:    punpklo p2.h, p1.b
-; CHECK-NEXT:    punpkhi p4.h, p1.b
+; CHECK-NEXT:    punpkhi p3.h, p1.b
 ; CHECK-NEXT:    uunpklo z0.d, z2.s
 ; CHECK-NEXT:    uunpkhi z1.d, z2.s
-; CHECK-NEXT:    punpklo p6.h, p0.b
+; CHECK-NEXT:    punpklo p5.h, p0.b
 ; CHECK-NEXT:    uunpklo z2.d, z3.s
 ; CHECK-NEXT:    uunpkhi z3.d, z3.s
-; CHECK-NEXT:    punpkhi p0.h, p0.b
+; CHECK-NEXT:    punpkhi p7.h, p0.b
 ; CHECK-NEXT:    uunpklo z4.d, z5.s
 ; CHECK-NEXT:    uunpkhi z5.d, z5.s
 ; CHECK-NEXT:    uunpklo z6.d, z7.s
 ; CHECK-NEXT:    uunpkhi z7.d, z7.s
-; CHECK-NEXT:    punpklo p1.h, p2.b
-; CHECK-NEXT:    punpkhi p2.h, p2.b
-; CHECK-NEXT:    punpklo p3.h, p4.b
-; CHECK-NEXT:    punpkhi p4.h, p4.b
-; CHECK-NEXT:    punpklo p5.h, p6.b
-; CHECK-NEXT:    punpkhi p6.h, p6.b
-; CHECK-NEXT:    punpklo p7.h, p0.b
-; CHECK-NEXT:    punpkhi p0.h, p0.b
+; CHECK-NEXT:    punpklo p0.h, p2.b
+; CHECK-NEXT:    punpkhi p1.h, p2.b
+; CHECK-NEXT:    punpklo p2.h, p3.b
+; CHECK-NEXT:    punpkhi p3.h, p3.b
+; CHECK-NEXT:    punpklo p4.h, p5.b
+; CHECK-NEXT:    punpkhi p5.h, p5.b
+; CHECK-NEXT:    punpklo p6.h, p7.b
+; CHECK-NEXT:    punpkhi p7.h, p7.b
 ; CHECK-NEXT:  .LBB0_1: // =>This Inner Loop Header: Depth=1
-; CHECK-NEXT:    st1b { z0.d }, p1, [z16.d]
-; CHECK-NEXT:    st1b { z1.d }, p2, [z16.d]
-; CHECK-NEXT:    st1b { z2.d }, p3, [z16.d]
-; CHECK-NEXT:    st1b { z3.d }, p4, [z16.d]
-; CHECK-NEXT:    st1b { z4.d }, p5, [z16.d]
-; CHECK-NEXT:    st1b { z5.d }, p6, [z16.d]
-; CHECK-NEXT:    st1b { z6.d }, p7, [z16.d]
-; CHECK-NEXT:    st1b { z7.d }, p0, [z16.d]
-; CHECK-NEXT:    str p8, [x0]
+; CHECK-NEXT:    st1b { z0.d }, p0, [z16.d]
+; CHECK-NEXT:    st1b { z1.d }, p1, [z16.d]
+; CHECK-NEXT:    st1b { z2.d }, p2, [z16.d]
+; CHECK-NEXT:    st1b { z3.d }, p3, [z16.d]
+; CHECK-NEXT:    st1b { z4.d }, p4, [z16.d]
+; CHECK-NEXT:    st1b { z5.d }, p5, [z16.d]
+; CHECK-NEXT:    st1b { z6.d }, p6, [z16.d]
+; CHECK-NEXT:    st1b { z7.d }, p7, [z16.d]
 ; CHECK-NEXT:    b .LBB0_1
   br label %1
 
@@ -67,7 +66,6 @@ define fastcc i8 @allocno_reload_assign(ptr %p) {
   %constexpr1 = shufflevector <vscale x 16 x i1> %constexpr, <vscale x 16 x i1> poison, <vscale x 16 x i32> zeroinitializer
   %constexpr2 = xor <vscale x 16 x i1> %constexpr1, shufflevector (<vscale x 16 x i1> insertelement (<vscale x 16 x i1> poison, i1 true, i64 0), <vscale x 16 x i1> poison, <vscale x 16 x i32> zeroinitializer)
   call void @llvm.masked.scatter.nxv16i8.nxv16p0(<vscale x 16 x i8> zeroinitializer, <vscale x 16 x ptr> zeroinitializer, i32 0, <vscale x 16 x i1> %constexpr2)
-  store <vscale x 16 x i1> %constexpr, ptr %p, align 16
   br label %1
 }
 
diff --git a/llvm/test/CodeGen/AArch64/extract-vector-cmp.ll b/llvm/test/CodeGen/AArch64/extract-vector-cmp.ll
