Move NVPTX subtarget dependent variables from the target machine

[oota-llvm.git] / lib / Target / NVPTX / NVPTXTargetMachine.cpp

diff --git a/lib/Target/NVPTX/NVPTXTargetMachine.cpp b/lib/Target/NVPTX/NVPTXTargetMachine.cpp
index 17cd9b75ba7b521155a337fcc972fac4a294897f..6e18322f824e9caf0a69244103f95f3bab81f236 100644 (file)
--- a/lib/Target/NVPTX/NVPTXTargetMachine.cpp
+++ b/lib/Target/NVPTX/NVPTXTargetMachine.cpp
@@ -16,16 +16,14 @@
 #include "NVPTX.h"
 #include "NVPTXAllocaHoisting.h"
 #include "NVPTXLowerAggrCopies.h"
-#include "NVPTXSplitBBatBar.h"
-#include "llvm/ADT/OwningPtr.h"
 #include "llvm/Analysis/Passes.h"
-#include "llvm/Analysis/Verifier.h"
-#include "llvm/Assembly/PrintModulePass.h"
 #include "llvm/CodeGen/AsmPrinter.h"
 #include "llvm/CodeGen/MachineFunctionAnalysis.h"
 #include "llvm/CodeGen/MachineModuleInfo.h"
 #include "llvm/CodeGen/Passes.h"
 #include "llvm/IR/DataLayout.h"
+#include "llvm/IR/IRPrintingPasses.h"
+#include "llvm/IR/Verifier.h"
 #include "llvm/MC/MCAsmInfo.h"
 #include "llvm/MC/MCInstrInfo.h"
 #include "llvm/MC/MCStreamer.h"
@@ -47,25 +45,36 @@
 
 using namespace llvm;
 
+namespace llvm {
+void initializeNVVMReflectPass(PassRegistry&);
+void initializeGenericToNVVMPass(PassRegistry&);
+void initializeNVPTXAssignValidGlobalNamesPass(PassRegistry&);
+void initializeNVPTXFavorNonGenericAddrSpacesPass(PassRegistry &);
+}
+
 extern "C" void LLVMInitializeNVPTXTarget() {
   // Register the target.
   RegisterTargetMachine<NVPTXTargetMachine32> X(TheNVPTXTarget32);
   RegisterTargetMachine<NVPTXTargetMachine64> Y(TheNVPTXTarget64);
 
-  RegisterMCAsmInfo<NVPTXMCAsmInfo> A(TheNVPTXTarget32);
-  RegisterMCAsmInfo<NVPTXMCAsmInfo> B(TheNVPTXTarget64);
-
+  // FIXME: This pass is really intended to be invoked during IR optimization,
+  // but it's very NVPTX-specific.
+  initializeNVVMReflectPass(*PassRegistry::getPassRegistry());
+  initializeGenericToNVVMPass(*PassRegistry::getPassRegistry());
+  initializeNVPTXAssignValidGlobalNamesPass(*PassRegistry::getPassRegistry());
+  initializeNVPTXFavorNonGenericAddrSpacesPass(
+    *PassRegistry::getPassRegistry());
 }
 
-NVPTXTargetMachine::NVPTXTargetMachine(
-    const Target &T, StringRef TT, StringRef CPU, StringRef FS,
-    const TargetOptions &Options, Reloc::Model RM, CodeModel::Model CM,
-    CodeGenOpt::Level OL, bool is64bit)
+NVPTXTargetMachine::NVPTXTargetMachine(const Target &T, StringRef TT,
+                                       StringRef CPU, StringRef FS,
+                                       const TargetOptions &Options,
+                                       Reloc::Model RM, CodeModel::Model CM,
+                                       CodeGenOpt::Level OL, bool is64bit)
     : LLVMTargetMachine(T, TT, CPU, FS, Options, RM, CM, OL),
-      Subtarget(TT, CPU, FS, is64bit), DL(Subtarget.getDataLayout()),
-      InstrInfo(*this), TLInfo(*this), TSInfo(*this),
-      FrameLowering(
-          *this, is64bit) /*FrameInfo(TargetFrameInfo::StackGrowsUp, 8, 0)*/ {}
+      Subtarget(TT, CPU, FS, *this, is64bit) {
+  initAsmInfo();
+}
 
 void NVPTXTargetMachine32::anchor() {}
 
@@ -83,7 +92,7 @@ NVPTXTargetMachine64::NVPTXTargetMachine64(
     CodeGenOpt::Level OL)
     : NVPTXTargetMachine(T, TT, CPU, FS, Options, RM, CM, OL, true) {}
 
-namespace llvm {
+namespace {
 class NVPTXPassConfig : public TargetPassConfig {
 public:
   NVPTXPassConfig(NVPTXTargetMachine *TM, PassManagerBase &PM)
@@ -93,22 +102,108 @@ public:
     return getTM<NVPTXTargetMachine>();
   }
 
-  virtual bool addInstSelector();
-  virtual bool addPreRegAlloc();
+  void addIRPasses() override;
+  bool addInstSelector() override;
+  bool addPreRegAlloc() override;
+  bool addPostRegAlloc() override;
+
+  FunctionPass *createTargetRegisterAllocator(bool) override;
+  void addFastRegAlloc(FunctionPass *RegAllocPass) override;
+  void addOptimizedRegAlloc(FunctionPass *RegAllocPass) override;
 };
-}
+} // end anonymous namespace
 
 TargetPassConfig *NVPTXTargetMachine::createPassConfig(PassManagerBase &PM) {
   NVPTXPassConfig *PassConfig = new NVPTXPassConfig(this, PM);
   return PassConfig;
 }
 
+void NVPTXPassConfig::addIRPasses() {
+  // The following passes are known to not play well with virtual regs hanging
+  // around after register allocation (which in our case, is *all* registers).
+  // We explicitly disable them here.  We do, however, need some functionality
+  // of the PrologEpilogCodeInserter pass, so we emulate that behavior in the
+  // NVPTXPrologEpilog pass (see NVPTXPrologEpilogPass.cpp).
+  disablePass(&PrologEpilogCodeInserterID);
+  disablePass(&MachineCopyPropagationID);
+  disablePass(&BranchFolderPassID);
+  disablePass(&TailDuplicateID);
+
+  addPass(createNVPTXImageOptimizerPass());
+  TargetPassConfig::addIRPasses();
+  addPass(createNVPTXAssignValidGlobalNamesPass());
+  addPass(createGenericToNVVMPass());
+  addPass(createNVPTXFavorNonGenericAddrSpacesPass());
+  addPass(createSeparateConstOffsetFromGEPPass());
+  // The SeparateConstOffsetFromGEP pass creates variadic bases that can be used
+  // by multiple GEPs. Run GVN or EarlyCSE to really reuse them. GVN generates
+  // significantly better code than EarlyCSE for some of our benchmarks.
+  if (getOptLevel() == CodeGenOpt::Aggressive)
+    addPass(createGVNPass());
+  else
+    addPass(createEarlyCSEPass());
+  // Both FavorNonGenericAddrSpaces and SeparateConstOffsetFromGEP may leave
+  // some dead code.  We could remove dead code in an ad-hoc manner, but that
+  // requires manual work and might be error-prone.
+  //
+  // The FavorNonGenericAddrSpaces pass shortcuts unnecessary addrspacecasts,
+  // and leave them unused.
+  //
+  // SeparateConstOffsetFromGEP rebuilds a new index from the old index, and the
+  // old index and some of its intermediate results may become unused.
+  addPass(createDeadCodeEliminationPass());
+}
+
 bool NVPTXPassConfig::addInstSelector() {
+  const NVPTXSubtarget &ST =
+    getTM<NVPTXTargetMachine>().getSubtarget<NVPTXSubtarget>();
+
   addPass(createLowerAggrCopies());
-  addPass(createSplitBBatBarPass());
   addPass(createAllocaHoisting());
   addPass(createNVPTXISelDag(getNVPTXTargetMachine(), getOptLevel()));
+
+  if (!ST.hasImageHandles())
+    addPass(createNVPTXReplaceImageHandlesPass());
+
   return false;
 }
 
 bool NVPTXPassConfig::addPreRegAlloc() { return false; }
+bool NVPTXPassConfig::addPostRegAlloc() {
+  addPass(createNVPTXPrologEpilogPass());
+  return false;
+}
+
+FunctionPass *NVPTXPassConfig::createTargetRegisterAllocator(bool) {
+  return nullptr; // No reg alloc
+}
+
+void NVPTXPassConfig::addFastRegAlloc(FunctionPass *RegAllocPass) {
+  assert(!RegAllocPass && "NVPTX uses no regalloc!");
+  addPass(&PHIEliminationID);
+  addPass(&TwoAddressInstructionPassID);
+}
+
+void NVPTXPassConfig::addOptimizedRegAlloc(FunctionPass *RegAllocPass) {
+  assert(!RegAllocPass && "NVPTX uses no regalloc!");
+
+  addPass(&ProcessImplicitDefsID);
+  addPass(&LiveVariablesID);
+  addPass(&MachineLoopInfoID);
+  addPass(&PHIEliminationID);
+
+  addPass(&TwoAddressInstructionPassID);
+  addPass(&RegisterCoalescerID);
+
+  // PreRA instruction scheduling.
+  if (addPass(&MachineSchedulerID))
+    printAndVerify("After Machine Scheduling");
+
+
+  addPass(&StackSlotColoringID);
+
+  // FIXME: Needs physical registers
+  //addPass(&PostRAMachineLICMID);
+
+  printAndVerify("After StackSlotColoring");
+}