[PATCH] D129537: [X86][DAGISel] Combine select vXi64 with AVX512 target

[LuoYuanke via Phabricator via llvm-commits]

LuoYuanke updated this revision to Diff 443828.
LuoYuanke added a comment.

Rebase.


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D129537/new/

https://reviews.llvm.org/D129537

Files:
  llvm/lib/Target/X86/X86ISelLowering.cpp
  llvm/test/CodeGen/X86/avx512-shuffles/shuffle-blend.ll


Index: llvm/test/CodeGen/X86/avx512-shuffles/shuffle-blend.ll
===================================================================
--- llvm/test/CodeGen/X86/avx512-shuffles/shuffle-blend.ll
+++ llvm/test/CodeGen/X86/avx512-shuffles/shuffle-blend.ll
@@ -5,10 +5,9 @@
 ; CHECK-LABEL: shuffle_v8i64:
 ; CHECK:       # %bb.0: # %entry
 ; CHECK-NEXT:    vpaddd %zmm1, %zmm0, %zmm2
-; CHECK-NEXT:    vpsubd %zmm1, %zmm0, %zmm0
-; CHECK-NEXT:    movb $-86, %al
+; CHECK-NEXT:    movw $510, %ax # imm = 0x1FE
 ; CHECK-NEXT:    kmovd %eax, %k1
-; CHECK-NEXT:    vmovdqa64 %zmm0, %zmm2 {%k1}
+; CHECK-NEXT:    vpsubd %zmm1, %zmm0, %zmm2 {%k1}
 ; CHECK-NEXT:    vmovdqa64 %zmm2, %zmm0
 ; CHECK-NEXT:    retq
 entry:
Index: llvm/lib/Target/X86/X86ISelLowering.cpp
===================================================================
--- llvm/lib/Target/X86/X86ISelLowering.cpp
+++ llvm/lib/Target/X86/X86ISelLowering.cpp
@@ -44325,6 +44325,59 @@
   return DAG.getBitcast(VT, Res);
 }
 
+static SDValue combineSelectVxi64(SDNode *N, SelectionDAG &DAG,
+                                  const X86Subtarget &Subtarget) {
+  SDLoc DL(N);
+  SDValue Cond = N->getOperand(0);
+  SDValue LHS = N->getOperand(1);
+  SDValue RHS = N->getOperand(2);
+  EVT VT = LHS.getValueType();
+  EVT CondVT = Cond.getValueType();
+  // Combine
+  // select vXi1 bitcast (int cond),
+  //         (<vXi64> bitcast <v2Xi32> a),
+  //         (<vXi64> bitcast <v2Xi32> b)
+  // to
+  // select <v2Xi1> cond, <v2Xi32> a, <v2Xi32> b
+  // to create opportunity for mask instructions with AVX512 instructions.
+  if (!Subtarget.hasAVX512())
+    return SDValue();
+
+  if (!CondVT.isVector() || CondVT.getVectorElementType() != MVT::i1)
+    return SDValue();
+  if (Cond.getOpcode() != ISD::BITCAST)
+    return SDValue();
+  if (!dyn_cast<ConstantSDNode>(Cond.getOperand(0)))
+    return SDValue();
+
+  if (VT.getVectorElementType() != MVT::i64)
+    return SDValue();
+
+  if (LHS.getOpcode() != ISD::BITCAST ||
+      LHS.getOperand(0).getValueType().getVectorElementType() != MVT::i32)
+    return SDValue();
+  if (RHS.getOpcode() != ISD::BITCAST ||
+      RHS.getOperand(0).getValueType().getVectorElementType() != MVT::i32)
+    return SDValue();
+
+  if (!Cond.hasOneUse() || !LHS.hasOneUse() || !RHS.hasOneUse())
+    return SDValue();
+
+  int NumElts = VT.getVectorNumElements();
+  EVT ExpandCondVT = EVT::getVectorVT(*DAG.getContext(), MVT::i1, NumElts * 2);
+  EVT ExpandVT = EVT::getVectorVT(*DAG.getContext(), MVT::i32, NumElts * 2);
+
+  ConstantSDNode *ConstCond = cast<ConstantSDNode>(Cond.getOperand(0));
+  uint64_t Mask = ConstCond->getZExtValue();
+  Mask = (Mask << 1) | Mask;
+  SDValue MaskVal = DAG.getConstant(
+      Mask, DL, EVT::getIntegerVT(*DAG.getContext(), NumElts * 2));
+  SDValue NewCond = DAG.getBitcast(ExpandCondVT, MaskVal);
+  return DAG.getBitcast(VT,
+                        DAG.getSelect(DL, ExpandVT, NewCond, LHS.getOperand(0),
+                                      RHS.getOperand(0)));
+}
+
 /// Do target-specific dag combines on SELECT and VSELECT nodes.
 static SDValue combineSelect(SDNode *N, SelectionDAG &DAG,
                              TargetLowering::DAGCombinerInfo &DCI,
@@ -44549,6 +44602,9 @@
       return DAG.getNode(Opcode, DL, N->getValueType(0), LHS, RHS);
   }
 
+  if (SDValue V = combineSelectVxi64(N, DAG, Subtarget))
+    return V;
+
   // Some mask scalar intrinsics rely on checking if only one bit is set
   // and implement it in C code like this:
   // A[0] = (U & 1) ? A[0] : W[0];


-------------- next part --------------
A non-text attachment was scrubbed...
Name: D129537.443828.patch
Type: text/x-patch
Size: 3528 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20220712/860c3051/attachment.bin>