Drop ISD::MEMSET, ISD::MEMMOVE, and ISD::MEMCPY, which are not Legal

on any current target and aren't optimized in DAGCombiner. Instead
of using intermediate nodes, expand the operations, choosing between
simple loads/stores, target-specific code, and library calls,
immediately.

Previously, the code to emit optimized code for these operations
was only used at initial SelectionDAG construction time; now it is
used at all times. This fixes some cases where rep;movs was being
used for small copies where simple loads/stores would be better.

This also cleans up code that checks for alignments less than 4;
let the targets make that decision instead of doing it in
target-independent code. This allows x86 to use rep;movs in
low-alignment cases.

Also, this fixes a bug that resulted in the use of rep;stos for
memsets of 0 with non-constant memory size when the alignment was
at least 4. It's better to use the library in this case, which
can be significantly faster when the size is large.

This also preserves more SourceValue information when memory
intrinsics are lowered into simple loads/stores.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@49572 91177308-0d34-0410-b5e6-96231b3b80d8

1 files changed, 1 insertions, 54 deletions

diff --git a/lib/CodeGen/SelectionDAG/TargetLowering.cpp b/lib/CodeGen/SelectionDAG/TargetLowering.cpp
index a0894ddebc..f69f0462a0 100644
--- a/lib/CodeGen/SelectionDAG/TargetLowering.cpp
+++ b/lib/CodeGen/SelectionDAG/TargetLowering.cpp
@@ -17,7 +17,7 @@
 #include "llvm/Target/TargetData.h"
 #include "llvm/Target/TargetMachine.h"
 #include "llvm/Target/TargetRegisterInfo.h"
-#include "llvm/CallingConv.h"
+#include "llvm/GlobalVariable.h"
 #include "llvm/DerivedTypes.h"
 #include "llvm/CodeGen/SelectionDAG.h"
 #include "llvm/ADT/StringExtras.h"
@@ -234,59 +234,6 @@ TargetLowering::TargetLowering(TargetMachine &tm)
 
 TargetLowering::~TargetLowering() {}
 
-
-SDOperand TargetLowering::LowerMEMCPY(SDOperand Op, SelectionDAG &DAG) {
-  assert(getSubtarget() && "Subtarget not defined");
-  SDOperand ChainOp = Op.getOperand(0);
-  SDOperand DestOp = Op.getOperand(1);
-  SDOperand SourceOp = Op.getOperand(2);
-  SDOperand CountOp = Op.getOperand(3);
-  SDOperand AlignOp = Op.getOperand(4);
-  SDOperand AlwaysInlineOp = Op.getOperand(5);
-
-  bool AlwaysInline = (bool)cast<ConstantSDNode>(AlwaysInlineOp)->getValue();
-  unsigned Align = (unsigned)cast<ConstantSDNode>(AlignOp)->getValue();
-  if (Align == 0) Align = 1;
-
-  // If size is unknown, call memcpy.
-  ConstantSDNode *I = dyn_cast<ConstantSDNode>(CountOp);
-  if (!I) {
-    assert(!AlwaysInline && "Cannot inline copy of unknown size");
-    return LowerMEMCPYCall(ChainOp, DestOp, SourceOp, CountOp, DAG);
-  }
-
-  // If not DWORD aligned or if size is more than threshold, then call memcpy.
-  // The libc version is likely to be faster for the following cases. It can
-  // use the address value and run time information about the CPU.
-  // With glibc 2.6.1 on a core 2, coping an array of 100M longs was 30% faster
-  unsigned Size = I->getValue();
-  if (AlwaysInline ||
-      (Size <= getSubtarget()->getMaxInlineSizeThreshold() &&
-       (Align & 3) == 0))
-    return LowerMEMCPYInline(ChainOp, DestOp, SourceOp, Size, Align, DAG);
-  return LowerMEMCPYCall(ChainOp, DestOp, SourceOp, CountOp, DAG);
-}
-
-
-SDOperand TargetLowering::LowerMEMCPYCall(SDOperand Chain,
-                                          SDOperand Dest,
-                                          SDOperand Source,
-                                          SDOperand Count,
-                                          SelectionDAG &DAG) {
-  MVT::ValueType IntPtr = getPointerTy();
-  TargetLowering::ArgListTy Args;
-  TargetLowering::ArgListEntry Entry;
-  Entry.Ty = getTargetData()->getIntPtrType();
-  Entry.Node = Dest; Args.push_back(Entry);
-  Entry.Node = Source; Args.push_back(Entry);
-  Entry.Node = Count; Args.push_back(Entry);
-  std::pair<SDOperand,SDOperand> CallResult =
-      LowerCallTo(Chain, Type::VoidTy, false, false, false, CallingConv::C,
-                  false, DAG.getExternalSymbol("memcpy", IntPtr), Args, DAG);
-  return CallResult.second;
-}
-
-
 /// computeRegisterProperties - Once all of the register classes are added,
 /// this allows us to compute derived properties we expose.
 void TargetLowering::computeRegisterProperties() {