Add codegen support for NEON vst2lane intrinsics with 128-bit vectors.

llvm-svn: 83596

llvm/lib/Target/ARM/ARMISelDAGToDAG.cpp

@@ -1911,18 +1911,56 @@ SDNode *ARMDAGToDAGISel::Select(SDValue Op) {
       SDValue MemAddr, MemUpdate, MemOpc;
       if (!SelectAddrMode6(Op, N->getOperand(2), MemAddr, MemUpdate, MemOpc))
         return NULL;
-      switch (N->getOperand(3).getValueType().getSimpleVT().SimpleTy) {
+      VT = N->getOperand(3).getValueType();
+      if (VT.is64BitVector()) {
+        switch (VT.getSimpleVT().SimpleTy) {
+        default: llvm_unreachable("unhandled vst2lane type");
+        case MVT::v8i8:  Opc = ARM::VST2LNd8; break;
+        case MVT::v4i16: Opc = ARM::VST2LNd16; break;
+        case MVT::v2f32:
+        case MVT::v2i32: Opc = ARM::VST2LNd32; break;
+        }
+        SDValue Chain = N->getOperand(0);
+        const SDValue Ops[] = { MemAddr, MemUpdate, MemOpc,
+                                N->getOperand(3), N->getOperand(4),
+                                N->getOperand(5), Chain };
+        return CurDAG->getMachineNode(Opc, dl, MVT::Other, Ops, 7);
+      }
+      // Quad registers are handled by extracting subregs and then doing
+      // the store.
+      EVT RegVT;
+      unsigned Opc2 = 0;
+      switch (VT.getSimpleVT().SimpleTy) {
       default: llvm_unreachable("unhandled vst2lane type");
-      case MVT::v8i8:  Opc = ARM::VST2LNd8; break;
+      case MVT::v8i16:
-      case MVT::v4i16: Opc = ARM::VST2LNd16; break;
+        Opc = ARM::VST2LNq16a;
-      case MVT::v2f32:
+        Opc2 = ARM::VST2LNq16b;
-      case MVT::v2i32: Opc = ARM::VST2LNd32; break;
+        RegVT = MVT::v4i16;
+        break;
+      case MVT::v4f32:
+        Opc = ARM::VST2LNq32a;
+        Opc2 = ARM::VST2LNq32b;
+        RegVT = MVT::v2f32;
+        break;
+      case MVT::v4i32:
+        Opc = ARM::VST2LNq32a;
+        Opc2 = ARM::VST2LNq32b;
+        RegVT = MVT::v2i32;
+        break;
       }
       SDValue Chain = N->getOperand(0);
-      const SDValue Ops[] = { MemAddr, MemUpdate, MemOpc,
+      unsigned Lane = cast<ConstantSDNode>(N->getOperand(5))->getZExtValue();
-                              N->getOperand(3), N->getOperand(4),
+      unsigned NumElts = RegVT.getVectorNumElements();
-                              N->getOperand(5), Chain };
+      int SubregIdx = (Lane < NumElts) ? ARM::DSUBREG_0 : ARM::DSUBREG_1;
-      return CurDAG->getMachineNode(Opc, dl, MVT::Other, Ops, 7);
+
+      SDValue D0 = CurDAG->getTargetExtractSubreg(SubregIdx, dl, RegVT,
+                                                  N->getOperand(3));
+      SDValue D1 = CurDAG->getTargetExtractSubreg(SubregIdx, dl, RegVT,
+                                                  N->getOperand(4));
+      const SDValue Ops[] = { MemAddr, MemUpdate, MemOpc, D0, D1,
+                              getI32Imm(Lane % NumElts), Chain };
+      return CurDAG->getMachineNode((Lane < NumElts) ? Opc : Opc2,
+                                    dl, MVT::Other, Ops, 7);
     }
 
     case Intrinsic::arm_neon_vst3lane: {

llvm/lib/Target/ARM/ARMInstrNEON.td

@@ -449,16 +449,24 @@ def  VST4q32b : VST4WB<0b1000, "vst4.32">;
 //   FIXME: Not yet implemented.
 
 //   VST2LN   : Vector Store (single 2-element structure from one lane)
-class VST2LND<bits<4> op11_8, string OpcodeStr>
+class VST2LN<bits<4> op11_8, string OpcodeStr>
   : NLdSt<1,0b00,op11_8,0b0000, (outs),
           (ins addrmode6:$addr, DPR:$src1, DPR:$src2, nohash_imm:$lane),
           IIC_VST,
           !strconcat(OpcodeStr, "\t\\{$src1[$lane],$src2[$lane]\\}, $addr"),
           "", []>;
 
-def VST2LNd8  : VST2LND<0b0000, "vst2.8">;
+def VST2LNd8  : VST2LN<0b0000, "vst2.8">;
-def VST2LNd16 : VST2LND<0b0100, "vst2.16">;
+def VST2LNd16 : VST2LN<0b0100, "vst2.16">;
-def VST2LNd32 : VST2LND<0b1000, "vst2.32">;
+def VST2LNd32 : VST2LN<0b1000, "vst2.32">;
+
+// vst2 to double-spaced even registers.
+def VST2LNq16a: VST2LN<0b0100, "vst2.16">;
+def VST2LNq32a: VST2LN<0b1000, "vst2.32">;
+
+// vst2 to double-spaced odd registers.
+def VST2LNq16b: VST2LN<0b0100, "vst2.16">;
+def VST2LNq32b: VST2LN<0b1000, "vst2.32">;
 
 //   VST3LN   : Vector Store (single 3-element structure from one lane)
 class VST3LND<bits<4> op11_8, string OpcodeStr>

llvm/lib/Target/ARM/NEONPreAllocPass.cpp

@@ -188,6 +188,22 @@ static bool isNEONMultiRegOp(int Opcode, unsigned &FirstOpnd, unsigned &NumRegs,
     NumRegs = 4;
     return true;
 
+  case ARM::VST2LNq16a:
+  case ARM::VST2LNq32a:
+    FirstOpnd = 3;
+    NumRegs = 2;
+    Offset = 0;
+    Stride = 2;
+    return true;
+
+  case ARM::VST2LNq16b:
+  case ARM::VST2LNq32b:
+    FirstOpnd = 3;
+    NumRegs = 2;
+    Offset = 1;
+    Stride = 2;
+    return true;
+
   case ARM::VST3d8:
   case ARM::VST3d16:
   case ARM::VST3d32:

llvm/test/CodeGen/ARM/vstlane.ll

@@ -32,11 +32,39 @@ define void @vst2lanef(float* %A, <2 x float>* %B) nounwind {
 	ret void
 }
 
+define void @vst2laneQi16(i16* %A, <8 x i16>* %B) nounwind {
+;CHECK: vst2laneQi16:
+;CHECK: vst2.16
+	%tmp1 = load <8 x i16>* %B
+	call void @llvm.arm.neon.vst2lane.v8i16(i16* %A, <8 x i16> %tmp1, <8 x i16> %tmp1, i32 1)
+	ret void
+}
+
+define void @vst2laneQi32(i32* %A, <4 x i32>* %B) nounwind {
+;CHECK: vst2laneQi32:
+;CHECK: vst2.32
+	%tmp1 = load <4 x i32>* %B
+	call void @llvm.arm.neon.vst2lane.v4i32(i32* %A, <4 x i32> %tmp1, <4 x i32> %tmp1, i32 2)
+	ret void
+}
+
+define void @vst2laneQf(float* %A, <4 x float>* %B) nounwind {
+;CHECK: vst2laneQf:
+;CHECK: vst2.32
+	%tmp1 = load <4 x float>* %B
+	call void @llvm.arm.neon.vst2lane.v4f32(float* %A, <4 x float> %tmp1, <4 x float> %tmp1, i32 3)
+	ret void
+}
+
 declare void @llvm.arm.neon.vst2lane.v8i8(i8*, <8 x i8>, <8 x i8>, i32) nounwind
 declare void @llvm.arm.neon.vst2lane.v4i16(i8*, <4 x i16>, <4 x i16>, i32) nounwind
 declare void @llvm.arm.neon.vst2lane.v2i32(i8*, <2 x i32>, <2 x i32>, i32) nounwind
 declare void @llvm.arm.neon.vst2lane.v2f32(i8*, <2 x float>, <2 x float>, i32) nounwind
 
+declare void @llvm.arm.neon.vst2lane.v8i16(i8*, <8 x i16>, <8 x i16>, i32) nounwind
+declare void @llvm.arm.neon.vst2lane.v4i32(i8*, <4 x i32>, <4 x i32>, i32) nounwind
+declare void @llvm.arm.neon.vst2lane.v4f32(i8*, <4 x float>, <4 x float>, i32) nounwind
+
 define void @vst3lanei8(i8* %A, <8 x i8>* %B) nounwind {
 ;CHECK: vst3lanei8:
 ;CHECK: vst3.8