5 files changed, 110 insertions, 0 deletions
diff --git a/lib/Target/R600/AMDGPU.h b/lib/Target/R600/AMDGPU.h
index fbf1fce..51d0d3c 100644
--- a/lib/Target/R600/AMDGPU.h
+++ b/lib/Target/R600/AMDGPU.h
@@ -45,6 +45,10 @@ FunctionPass *createAMDGPUConvertToISAPass(TargetMachine &tm);
 FunctionPass *createAMDGPUIndirectAddressingPass(TargetMachine &tm);
 FunctionPass *createAMDGPUISelDag(TargetMachine &tm);
 
+/// \brief Creates an AMDGPU-specific Target Transformation Info pass.
+ImmutablePass *
+createAMDGPUTargetTransformInfoPass(const AMDGPUTargetMachine *TM);
+
 extern Target TheAMDGPUTarget;
 
 } // End namespace llvm
diff --git a/lib/Target/R600/AMDGPUTargetMachine.cpp b/lib/Target/R600/AMDGPUTargetMachine.cpp
index 1dc1b6b..33e2dae 100644
--- a/lib/Target/R600/AMDGPUTargetMachine.cpp
+++ b/lib/Target/R600/AMDGPUTargetMachine.cpp
@@ -105,6 +105,18 @@ TargetPassConfig *AMDGPUTargetMachine::createPassConfig(PassManagerBase &PM) {
   return new AMDGPUPassConfig(this, PM);
 }
 
+//===----------------------------------------------------------------------===//
+// AMDGPU Analysis Pass Setup
+//===----------------------------------------------------------------------===//
+
+void AMDGPUTargetMachine::addAnalysisPasses(PassManagerBase &PM) {
+  // Add first the target-independent BasicTTI pass, then our AMDGPU pass. This
+  // allows the AMDGPU pass to delegate to the target independent layer when
+  // appropriate.
+  PM.add(createBasicTargetTransformInfoPass(this));
+  PM.add(createAMDGPUTargetTransformInfoPass(this));
+}
+
 bool
 AMDGPUPassConfig::addPreISel() {
   const AMDGPUSubtarget &ST = TM->getSubtarget<AMDGPUSubtarget>();
diff --git a/lib/Target/R600/AMDGPUTargetMachine.h b/lib/Target/R600/AMDGPUTargetMachine.h
index 26e95d3..f942614 100644
--- a/lib/Target/R600/AMDGPUTargetMachine.h
+++ b/lib/Target/R600/AMDGPUTargetMachine.h
@@ -61,6 +61,9 @@ public:
   }
   virtual const DataLayout *getDataLayout() const { return &Layout; }
   virtual TargetPassConfig *createPassConfig(PassManagerBase &PM);
+
+  /// \brief Register R600 analysis passes with a pass manager.
+  virtual void addAnalysisPasses(PassManagerBase &PM);
 };
 
 } // End namespace llvm
diff --git a/lib/Target/R600/AMDGPUTargetTransformInfo.cpp b/lib/Target/R600/AMDGPUTargetTransformInfo.cpp
new file mode 100644
index 0000000..8db319c
--- /dev/null
+++ b/lib/Target/R600/AMDGPUTargetTransformInfo.cpp
@@ -0,0 +1,90 @@
+//===-- AMDGPUTargetTransformInfo.cpp - AMDGPU specific TTI pass ---------===//
+//
+//                     The LLVM Compiler Infrastructure
+//
+// This file is distributed under the University of Illinois Open Source
+// License. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+//
+// \file
+// This file implements a TargetTransformInfo analysis pass specific to the
+// AMDGPU target machine. It uses the target's detailed information to provide
+// more precise answers to certain TTI queries, while letting the target
+// independent and default TTI implementations handle the rest.
+//
+//===----------------------------------------------------------------------===//
+
+#define DEBUG_TYPE "AMDGPUtti"
+#include "AMDGPU.h"
+#include "AMDGPUTargetMachine.h"
+#include "llvm/Analysis/TargetTransformInfo.h"
+#include "llvm/Support/Debug.h"
+#include "llvm/Target/TargetLowering.h"
+#include "llvm/Target/CostTable.h"
+using namespace llvm;
+
+// Declare the pass initialization routine locally as target-specific passes
+// don't have a target-wide initialization entry point, and so we rely on the
+// pass constructor initialization.
+namespace llvm {
+void initializeAMDGPUTTIPass(PassRegistry &);
+}
+
+namespace {
+
+class AMDGPUTTI : public ImmutablePass, public TargetTransformInfo {
+  const AMDGPUTargetMachine *TM;
+  const AMDGPUSubtarget *ST;
+  const AMDGPUTargetLowering *TLI;
+
+  /// Estimate the overhead of scalarizing an instruction. Insert and Extract
+  /// are set if the result needs to be inserted and/or extracted from vectors.
+  unsigned getScalarizationOverhead(Type *Ty, bool Insert, bool Extract) const;
+
+public:
+  AMDGPUTTI() : ImmutablePass(ID), TM(0), ST(0), TLI(0) {
+    llvm_unreachable("This pass cannot be directly constructed");
+  }
+
+  AMDGPUTTI(const AMDGPUTargetMachine *TM)
+      : ImmutablePass(ID), TM(TM), ST(TM->getSubtargetImpl()),
+        TLI(TM->getTargetLowering()) {
+    initializeAMDGPUTTIPass(*PassRegistry::getPassRegistry());
+  }
+
+  virtual void initializePass() { pushTTIStack(this); }
+
+  virtual void finalizePass() { popTTIStack(); }
+
+  virtual void getAnalysisUsage(AnalysisUsage &AU) const {
+    TargetTransformInfo::getAnalysisUsage(AU);
+  }
+
+  /// Pass identification.
+  static char ID;
+
+  /// Provide necessary pointer adjustments for the two base classes.
+  virtual void *getAdjustedAnalysisPointer(const void *ID) {
+    if (ID == &TargetTransformInfo::ID)
+      return (TargetTransformInfo *)this;
+    return this;
+  }
+
+  virtual bool hasBranchDivergence() const;
+
+  /// @}
+};
+
+} // end anonymous namespace
+
+INITIALIZE_AG_PASS(AMDGPUTTI, TargetTransformInfo, "AMDGPUtti",
+                   "AMDGPU Target Transform Info", true, true, false)
+char AMDGPUTTI::ID = 0;
+
+ImmutablePass *
+llvm::createAMDGPUTargetTransformInfoPass(const AMDGPUTargetMachine *TM) {
+  return new AMDGPUTTI(TM);
+}
+
+bool AMDGPUTTI::hasBranchDivergence() const { return true; }
diff --git a/lib/Target/R600/CMakeLists.txt b/lib/Target/R600/CMakeLists.txt
index 4f8665b..40d255a 100644
--- a/lib/Target/R600/CMakeLists.txt
+++ b/lib/Target/R600/CMakeLists.txt
@@ -23,6 +23,7 @@ add_llvm_target(R600CodeGen
   AMDGPUMachineFunction.cpp
   AMDGPUSubtarget.cpp
   AMDGPUTargetMachine.cpp
+  AMDGPUTargetTransformInfo.cpp
   AMDGPUISelLowering.cpp
   AMDGPUConvertToISA.cpp
   AMDGPUInstrInfo.cpp