X-Git-Url: http://plrg.eecs.uci.edu/git/?a=blobdiff_plain;f=lib%2FTarget%2FX86%2FX86TargetMachine.cpp;h=0e7e4c0c84a96d725c61e88c1cb16d9f4583b69a;hb=177b35e464b0a17afad4f2d4da61447da027d059;hp=33576f1771f0d3f7bac3002d48761f57958c2898;hpb=7e80a67d35ca6f7f1e299d68991e17d5fba43620;p=oota-llvm.git

diff --git a/lib/Target/X86/X86TargetMachine.cpp b/lib/Target/X86/X86TargetMachine.cpp
index 33576f1771f..0e7e4c0c84a 100644
--- a/lib/Target/X86/X86TargetMachine.cpp
+++ b/lib/Target/X86/X86TargetMachine.cpp
@@ -24,10 +24,21 @@
 #include "llvm/Target/TargetOptions.h"
 using namespace llvm;
 
+static cl::opt<bool> EnableMachineCombinerPass("x86-machine-combiner",
+                               cl::desc("Enable the machine combiner pass"),
+                               cl::init(true), cl::Hidden);
+
+namespace llvm {
+void initializeWinEHStatePassPass(PassRegistry &);
+}
+
 extern "C" void LLVMInitializeX86Target() {
   // Register the target.
   RegisterTargetMachine<X86TargetMachine> X(TheX86_32Target);
   RegisterTargetMachine<X86TargetMachine> Y(TheX86_64Target);
+
+  PassRegistry &PR = *PassRegistry::getPassRegistry();
+  initializeWinEHStatePassPass(PR);
 }
 
 static std::unique_ptr<TargetLoweringObjectFile> createTLOF(const Triple &TT) {
@@ -41,7 +52,7 @@ static std::unique_ptr<TargetLoweringObjectFile> createTLOF(const Triple &TT) {
     return make_unique<X86LinuxNaClTargetObjectFile>();
   if (TT.isOSBinFormatELF())
     return make_unique<X86ELFTargetObjectFile>();
-  if (TT.isKnownWindowsMSVCEnvironment())
+  if (TT.isKnownWindowsMSVCEnvironment() || TT.isWindowsCoreCLREnvironment())
     return make_unique<X86WindowsTargetObjectFile>();
   if (TT.isOSBinFormatCOFF())
     return make_unique<TargetLoweringObjectFileCOFF>();
@@ -90,13 +101,14 @@ static std::string computeDataLayout(const Triple &TT) {
 
 /// X86TargetMachine ctor - Create an X86 target.
 ///
-X86TargetMachine::X86TargetMachine(const Target &T, StringRef TT, StringRef CPU,
-                                   StringRef FS, const TargetOptions &Options,
+X86TargetMachine::X86TargetMachine(const Target &T, const Triple &TT,
+                                   StringRef CPU, StringRef FS,
+                                   const TargetOptions &Options,
                                    Reloc::Model RM, CodeModel::Model CM,
                                    CodeGenOpt::Level OL)
-    : LLVMTargetMachine(T, computeDataLayout(Triple(TT)), TT, CPU, FS, Options,
-                        RM, CM, OL),
-      TLOF(createTLOF(Triple(getTargetTriple()))),
+    : LLVMTargetMachine(T, computeDataLayout(TT), TT, CPU, FS, Options, RM, CM,
+                        OL),
+      TLOF(createTLOF(getTargetTriple())),
       Subtarget(TT, CPU, FS, *this, Options.StackAlignmentOverride) {
   // Windows stack unwinder gets confused when execution flow "falls through"
   // after a call to 'noreturn' function.
@@ -105,12 +117,15 @@ X86TargetMachine::X86TargetMachine(const Target &T, StringRef TT, StringRef CPU,
   if (Subtarget.isTargetWin64())
     this->Options.TrapUnreachable = true;
 
-  // TODO: By default, all reciprocal estimate operations are off because
-  // that matches the behavior before TargetRecip was added (except for btver2
-  // which used subtarget features to enable this type of codegen).
-  // We should change this to match GCC behavior where everything but
-  // scalar division estimates are turned on by default with -ffast-math.
-  this->Options.Reciprocals.setDefaults("all", false, 1);
+  // By default (and when -ffast-math is on), enable estimate codegen for
+  // everything except scalar division. By default, use 1 refinement step for
+  // all operations. Defaults may be overridden by using command-line options.
+  // Scalar division estimates are disabled because they break too much
+  // real-world code. These defaults match GCC behavior.
+  this->Options.Reciprocals.setDefaults("sqrtf", true, 1);
+  this->Options.Reciprocals.setDefaults("divf", false, 1);
+  this->Options.Reciprocals.setDefaults("vec-sqrtf", true, 1);
+  this->Options.Reciprocals.setDefaults("vec-divf", true, 1);
 
   initAsmInfo();
 }
@@ -167,8 +182,9 @@ UseVZeroUpper("x86-use-vzeroupper", cl::Hidden,
 //===----------------------------------------------------------------------===//
 
 TargetIRAnalysis X86TargetMachine::getTargetIRAnalysis() {
-  return TargetIRAnalysis(
-      [this](Function &F) { return TargetTransformInfo(X86TTIImpl(this, F)); });
+  return TargetIRAnalysis([this](const Function &F) {
+    return TargetTransformInfo(X86TTIImpl(this, F));
+  });
 }
 
 
@@ -213,7 +229,7 @@ bool X86PassConfig::addInstSelector() {
   addPass(createX86ISelDag(getX86TargetMachine(), getOptLevel()));
 
   // For ELF, cleanup any local-dynamic TLS accesses.
-  if (Triple(TM->getTargetTriple()).isOSBinFormatELF() &&
+  if (TM->getTargetTriple().isOSBinFormatELF() &&
       getOptLevel() != CodeGenOpt::None)
     addPass(createCleanupLocalDynamicTLSPass());
 
@@ -224,18 +240,23 @@ bool X86PassConfig::addInstSelector() {
 
 bool X86PassConfig::addILPOpts() {
   addPass(&EarlyIfConverterID);
+  if (EnableMachineCombinerPass)
+    addPass(&MachineCombinerID);
   return true;
 }
 
 bool X86PassConfig::addPreISel() {
-  // Only add this pass for 32-bit x86.
-  Triple TT(TM->getTargetTriple());
-  if (TT.getArch() == Triple::x86)
+  // Only add this pass for 32-bit x86 Windows.
+  const Triple &TT = TM->getTargetTriple();
+  if (TT.isOSWindows() && TT.getArch() == Triple::x86)
     addPass(createX86WinEHStatePass());
   return true;
 }
 
 void X86PassConfig::addPreRegAlloc() {
+  if (getOptLevel() != CodeGenOpt::None)
+    addPass(createX86OptimizeLEAs());
+
   addPass(createX86CallFrameOptimization());
 }