PTX: Implement PTXSelectionDAGInfo

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@140549 91177308-0d34-0410-b5e6-96231b3b80d8

5 files changed, 214 insertions, 5 deletions

diff --git a/lib/Target/PTX/CMakeLists.txt b/lib/Target/PTX/CMakeLists.txt
index abf6dcd031..f711af93a4 100644
--- a/lib/Target/PTX/CMakeLists.txt
+++ b/lib/Target/PTX/CMakeLists.txt
@@ -18,6 +18,7 @@ add_llvm_target(PTXCodeGen
   PTXParamManager.cpp
   PTXRegAlloc.cpp
   PTXRegisterInfo.cpp
+  PTXSelectionDAGInfo.cpp
   PTXSubtarget.cpp
   PTXTargetMachine.cpp
   )
diff --git a/lib/Target/PTX/PTXSelectionDAGInfo.cpp b/lib/Target/PTX/PTXSelectionDAGInfo.cpp
new file mode 100644
index 0000000000..e333183fc9
--- /dev/null
+++ b/lib/Target/PTX/PTXSelectionDAGInfo.cpp
@@ -0,0 +1,148 @@
+//===-- PTXSelectionDAGInfo.cpp - PTX SelectionDAG Info -------------------===//
+//
+//                     The LLVM Compiler Infrastructure
+//
+// This file is distributed under the University of Illinois Open Source
+// License. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+//
+// This file implements the PTXSelectionDAGInfo class.
+//
+//===----------------------------------------------------------------------===//
+
+#define DEBUG_TYPE "ptx-selectiondag-info"
+#include "PTXTargetMachine.h"
+#include "llvm/DerivedTypes.h"
+#include "llvm/CodeGen/SelectionDAG.h"
+using namespace llvm;
+
+PTXSelectionDAGInfo::PTXSelectionDAGInfo(const TargetMachine &TM)
+  : TargetSelectionDAGInfo(TM),
+    Subtarget(&TM.getSubtarget<PTXSubtarget>()) {
+}
+
+PTXSelectionDAGInfo::~PTXSelectionDAGInfo() {
+}
+
+SDValue
+PTXSelectionDAGInfo::EmitTargetCodeForMemcpy(SelectionDAG &DAG, DebugLoc dl,
+                                             SDValue Chain,
+                                             SDValue Dst, SDValue Src,
+                                             SDValue Size, unsigned Align,
+                                             bool isVolatile, bool AlwaysInline,
+                                             MachinePointerInfo DstPtrInfo,
+                                          MachinePointerInfo SrcPtrInfo) const {
+  // Do repeated 4-byte loads and stores. To be improved.
+  // This requires 4-byte alignment.
+  if ((Align & 3) != 0)
+    return SDValue();
+  // This requires the copy size to be a constant, preferably
+  // within a subtarget-specific limit.
+  ConstantSDNode *ConstantSize = dyn_cast<ConstantSDNode>(Size);
+  if (!ConstantSize)
+    return SDValue();
+  uint64_t SizeVal = ConstantSize->getZExtValue();
+  // Always inline memcpys. In PTX, we do not have a C library that provides
+  // a memcpy function.
+  //if (!AlwaysInline)
+  //  return SDValue();
+
+  unsigned BytesLeft = SizeVal & 3;
+  unsigned NumMemOps = SizeVal >> 2;
+  unsigned EmittedNumMemOps = 0;
+  EVT VT = MVT::i32;
+  unsigned VTSize = 4;
+  unsigned i = 0;
+  const unsigned MAX_LOADS_IN_LDM = 6;
+  SDValue TFOps[MAX_LOADS_IN_LDM];
+  SDValue Loads[MAX_LOADS_IN_LDM];
+  uint64_t SrcOff = 0, DstOff = 0;
+
+  // Emit up to MAX_LOADS_IN_LDM loads, then a TokenFactor barrier, then the
+  // same number of stores.  The loads and stores will get combined into
+  // ldm/stm later on.
+  while (EmittedNumMemOps < NumMemOps) {
+    for (i = 0;
+         i < MAX_LOADS_IN_LDM && EmittedNumMemOps + i < NumMemOps; ++i) {
+      Loads[i] = DAG.getLoad(VT, dl, Chain,
+                             DAG.getNode(ISD::ADD, dl, MVT::i32, Src,
+                                         DAG.getConstant(SrcOff, MVT::i32)),
+                             SrcPtrInfo.getWithOffset(SrcOff), isVolatile,
+                             false, 0);
+      TFOps[i] = Loads[i].getValue(1);
+      SrcOff += VTSize;
+    }
+    Chain = DAG.getNode(ISD::TokenFactor, dl, MVT::Other, &TFOps[0], i);
+
+    for (i = 0;
+         i < MAX_LOADS_IN_LDM && EmittedNumMemOps + i < NumMemOps; ++i) {
+      TFOps[i] = DAG.getStore(Chain, dl, Loads[i],
+                              DAG.getNode(ISD::ADD, dl, MVT::i32, Dst,
+                                          DAG.getConstant(DstOff, MVT::i32)),
+                              DstPtrInfo.getWithOffset(DstOff),
+                              isVolatile, false, 0);
+      DstOff += VTSize;
+    }
+    Chain = DAG.getNode(ISD::TokenFactor, dl, MVT::Other, &TFOps[0], i);
+
+    EmittedNumMemOps += i;
+  }
+
+  if (BytesLeft == 0)
+    return Chain;
+
+  // Issue loads / stores for the trailing (1 - 3) bytes.
+  unsigned BytesLeftSave = BytesLeft;
+  i = 0;
+  while (BytesLeft) {
+    if (BytesLeft >= 2) {
+      VT = MVT::i16;
+      VTSize = 2;
+    } else {
+      VT = MVT::i8;
+      VTSize = 1;
+    }
+
+    Loads[i] = DAG.getLoad(VT, dl, Chain,
+                           DAG.getNode(ISD::ADD, dl, MVT::i32, Src,
+                                       DAG.getConstant(SrcOff, MVT::i32)),
+                           SrcPtrInfo.getWithOffset(SrcOff), false, false, 0);
+    TFOps[i] = Loads[i].getValue(1);
+    ++i;
+    SrcOff += VTSize;
+    BytesLeft -= VTSize;
+  }
+  Chain = DAG.getNode(ISD::TokenFactor, dl, MVT::Other, &TFOps[0], i);
+
+  i = 0;
+  BytesLeft = BytesLeftSave;
+  while (BytesLeft) {
+    if (BytesLeft >= 2) {
+      VT = MVT::i16;
+      VTSize = 2;
+    } else {
+      VT = MVT::i8;
+      VTSize = 1;
+    }
+
+    TFOps[i] = DAG.getStore(Chain, dl, Loads[i],
+                            DAG.getNode(ISD::ADD, dl, MVT::i32, Dst,
+                                        DAG.getConstant(DstOff, MVT::i32)),
+                            DstPtrInfo.getWithOffset(DstOff), false, false, 0);
+    ++i;
+    DstOff += VTSize;
+    BytesLeft -= VTSize;
+  }
+  return DAG.getNode(ISD::TokenFactor, dl, MVT::Other, &TFOps[0], i);
+}
+
+SDValue PTXSelectionDAGInfo::
+EmitTargetCodeForMemset(SelectionDAG &DAG, DebugLoc dl,
+                        SDValue Chain, SDValue Dst,
+                        SDValue Src, SDValue Size,
+                        unsigned Align, bool isVolatile,
+                        MachinePointerInfo DstPtrInfo) const {
+  llvm_unreachable("memset lowering not implemented for PTX yet");
+}
+
diff --git a/lib/Target/PTX/PTXSelectionDAGInfo.h b/lib/Target/PTX/PTXSelectionDAGInfo.h
new file mode 100644
index 0000000000..e0c716718f
--- /dev/null
+++ b/lib/Target/PTX/PTXSelectionDAGInfo.h
@@ -0,0 +1,53 @@
+//===-- PTXSelectionDAGInfo.h - PTX SelectionDAG Info -----------*- C++ -*-===//
+//
+//                     The LLVM Compiler Infrastructure
+//
+// This file is distributed under the University of Illinois Open Source
+// License. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+//
+// This file defines the PTX subclass for TargetSelectionDAGInfo.
+//
+//===----------------------------------------------------------------------===//
+
+#ifndef PTXSELECTIONDAGINFO_H
+#define PTXSELECTIONDAGINFO_H
+
+#include "llvm/Target/TargetSelectionDAGInfo.h"
+
+namespace llvm {
+
+/// PTXSelectionDAGInfo - TargetSelectionDAGInfo sub-class for the PTX target.
+/// At the moment, this is mostly just a copy of ARMSelectionDAGInfo.
+class PTXSelectionDAGInfo : public TargetSelectionDAGInfo {
+  /// Subtarget - Keep a pointer to the PTXSubtarget around so that we can
+  /// make the right decision when generating code for different targets.
+  const PTXSubtarget *Subtarget;
+
+public:
+  explicit PTXSelectionDAGInfo(const TargetMachine &TM);
+  ~PTXSelectionDAGInfo();
+
+  virtual
+  SDValue EmitTargetCodeForMemcpy(SelectionDAG &DAG, DebugLoc dl,
+                                  SDValue Chain,
+                                  SDValue Dst, SDValue Src,
+                                  SDValue Size, unsigned Align,
+                                  bool isVolatile, bool AlwaysInline,
+                                  MachinePointerInfo DstPtrInfo,
+                                  MachinePointerInfo SrcPtrInfo) const;
+
+  virtual
+  SDValue EmitTargetCodeForMemset(SelectionDAG &DAG, DebugLoc dl,
+                                  SDValue Chain,
+                                  SDValue Op1, SDValue Op2,
+                                  SDValue Op3, unsigned Align,
+                                  bool isVolatile,
+                                  MachinePointerInfo DstPtrInfo) const;
+};
+
+}
+
+#endif
+
diff --git a/lib/Target/PTX/PTXTargetMachine.cpp b/lib/Target/PTX/PTXTargetMachine.cpp
index a6db0b7f2e..1f3f1721a6 100644
--- a/lib/Target/PTX/PTXTargetMachine.cpp
+++ b/lib/Target/PTX/PTXTargetMachine.cpp
@@ -94,6 +94,7 @@ PTXTargetMachine::PTXTargetMachine(const Target &T,
     Subtarget(TT, CPU, FS, is64Bit),
     FrameLowering(Subtarget),
     InstrInfo(*this),
+    TSInfo(*this),
     TLInfo(*this) {
 }
 
diff --git a/lib/Target/PTX/PTXTargetMachine.h b/lib/Target/PTX/PTXTargetMachine.h
index d5726b9866..5b7c82b1f4 100644
--- a/lib/Target/PTX/PTXTargetMachine.h
+++ b/lib/Target/PTX/PTXTargetMachine.h
@@ -17,6 +17,7 @@
 #include "PTXISelLowering.h"
 #include "PTXInstrInfo.h"
 #include "PTXFrameLowering.h"
+#include "PTXSelectionDAGInfo.h"
 #include "PTXSubtarget.h"
 #include "llvm/Target/TargetData.h"
 #include "llvm/Target/TargetFrameLowering.h"
@@ -25,11 +26,12 @@
 namespace llvm {
 class PTXTargetMachine : public LLVMTargetMachine {
   private:
-    const TargetData  DataLayout;
-    PTXSubtarget      Subtarget; // has to be initialized before FrameLowering
-    PTXFrameLowering  FrameLowering;
-    PTXInstrInfo      InstrInfo;
-    PTXTargetLowering TLInfo;
+    const TargetData    DataLayout;
+    PTXSubtarget        Subtarget; // has to be initialized before FrameLowering
+    PTXFrameLowering    FrameLowering;
+    PTXInstrInfo        InstrInfo;
+    PTXSelectionDAGInfo TSInfo;
+    PTXTargetLowering   TLInfo;
 
   public:
     PTXTargetMachine(const Target &T, StringRef TT,
@@ -50,6 +52,10 @@ class PTXTargetMachine : public LLVMTargetMachine {
     virtual const PTXTargetLowering *getTargetLowering() const {
       return &TLInfo; }
 
+    virtual const PTXSelectionDAGInfo* getSelectionDAGInfo() const {
+      return &TSInfo;
+    }
+
     virtual const PTXSubtarget *getSubtargetImpl() const { return &Subtarget; }
 
     virtual bool addInstSelector(PassManagerBase &PM,