AVX512: Implemented DAG lowering for shuff62x2/shufi62x2 instructions ( shuffle packe...

[oota-llvm.git] / lib / Target / ARM / ARMSelectionDAGInfo.cpp

diff --git a/lib/Target/ARM/ARMSelectionDAGInfo.cpp b/lib/Target/ARM/ARMSelectionDAGInfo.cpp
index beed0fb432fd2fd32c40c3c5086f3392d3e5eae8..6fded9c8ab7387fe40b3f5d7e1e643aed827d579 100644 (file)
--- a/lib/Target/ARM/ARMSelectionDAGInfo.cpp
+++ b/lib/Target/ARM/ARMSelectionDAGInfo.cpp
@@ -18,12 +18,6 @@ using namespace llvm;
 
 #define DEBUG_TYPE "arm-selectiondag-info"
 
-ARMSelectionDAGInfo::ARMSelectionDAGInfo(const DataLayout &DL)
-    : TargetSelectionDAGInfo(&DL) {}
-
-ARMSelectionDAGInfo::~ARMSelectionDAGInfo() {
-}
-
 // Emit, if possible, a specialized version of the given Libcall. Typically this
 // means selecting the appropriately aligned version, but we also convert memset
 // of 0 into memclr.
@@ -83,7 +77,7 @@ EmitSpecializedLibcall(SelectionDAG &DAG, SDLoc dl,
 
   TargetLowering::ArgListTy Args;
   TargetLowering::ArgListEntry Entry;
-  Entry.Ty = TLI->getDataLayout()->getIntPtrType(*DAG.getContext());
+  Entry.Ty = DAG.getDataLayout().getIntPtrType(*DAG.getContext());
   Entry.Node = Dst;
   Args.push_back(Entry);
   if (AEABILibcall == AEABI_MEMCLR) {
@@ -121,12 +115,14 @@ EmitSpecializedLibcall(SelectionDAG &DAG, SDLoc dl,
     { "__aeabi_memclr",  "__aeabi_memclr4",  "__aeabi_memclr8"  }
   };
   TargetLowering::CallLoweringInfo CLI(DAG);
-  CLI.setDebugLoc(dl).setChain(Chain)
-    .setCallee(TLI->getLibcallCallingConv(LC),
-               Type::getVoidTy(*DAG.getContext()),
-               DAG.getExternalSymbol(FunctionNames[AEABILibcall][AlignVariant],
-                                     TLI->getPointerTy()), std::move(Args), 0)
-    .setDiscardResult();
+  CLI.setDebugLoc(dl)
+      .setChain(Chain)
+      .setCallee(
+           TLI->getLibcallCallingConv(LC), Type::getVoidTy(*DAG.getContext()),
+           DAG.getExternalSymbol(FunctionNames[AEABILibcall][AlignVariant],
+                                 TLI->getPointerTy(DAG.getDataLayout())),
+           std::move(Args), 0)
+      .setDiscardResult();
   std::pair<SDValue,SDValue> CallResult = TLI->LowerCallTo(CLI);
   
   return CallResult.second;
@@ -169,25 +165,26 @@ ARMSelectionDAGInfo::EmitTargetCodeForMemcpy(SelectionDAG &DAG, SDLoc dl,
   SDValue Loads[6];
   uint64_t SrcOff = 0, DstOff = 0;
 
-  // FIXME: We should invent a VMCOPY pseudo-instruction that lowers to
+  // FIXME: We should invent a VMEMCPY pseudo-instruction that lowers to
   // VLDM/VSTM and make this code emit it when appropriate. This would reduce
   // pressure on the general purpose registers. However this seems harder to map
   // onto the register allocator's view of the world.
 
-  // The number of MCOPY pseudo-instructions to emit. We use up to MaxLoadsInLDM
-  // registers per mcopy, which will get lowered into ldm/stm later on. This is
-  // a lower bound on the number of MCOPY operations we must emit.
-  unsigned NumMCOPYs = (NumMemOps + MaxLoadsInLDM - 1) / MaxLoadsInLDM;
+  // The number of MEMCPY pseudo-instructions to emit. We use up to
+  // MaxLoadsInLDM registers per mcopy, which will get lowered into ldm/stm
+  // later on. This is a lower bound on the number of MEMCPY operations we must
+  // emit.
+  unsigned NumMEMCPYs = (NumMemOps + MaxLoadsInLDM - 1) / MaxLoadsInLDM;
 
   SDVTList VTs = DAG.getVTList(MVT::i32, MVT::i32, MVT::Other, MVT::Glue);
 
-  for (unsigned I = 0; I != NumMCOPYs; ++I) {
-    // Evenly distribute registers among MCOPY operations to reduce register
+  for (unsigned I = 0; I != NumMEMCPYs; ++I) {
+    // Evenly distribute registers among MEMCPY operations to reduce register
     // pressure.
-    unsigned NextEmittedNumMemOps = NumMemOps * (I + 1) / NumMCOPYs;
+    unsigned NextEmittedNumMemOps = NumMemOps * (I + 1) / NumMEMCPYs;
     unsigned NumRegs = NextEmittedNumMemOps - EmittedNumMemOps;
 
-    Dst = DAG.getNode(ARMISD::MCOPY, dl, VTs, Chain, Dst, Src,
+    Dst = DAG.getNode(ARMISD::MEMCPY, dl, VTs, Chain, Dst, Src,
                       DAG.getConstant(NumRegs, dl, MVT::i32));
     Src = Dst.getValue(1);
     Chain = Dst.getValue(2);