diff --git a/llvm/lib/Support/AMDGPUMetadata.cpp b/llvm/lib/Support/AMDGPUMetadata.cpp
--- a/llvm/lib/Support/AMDGPUMetadata.cpp
+++ b/llvm/lib/Support/AMDGPUMetadata.cpp
@@ -12,7 +12,6 @@
 //
 //===----------------------------------------------------------------------===//
 
-#include "llvm/ADT/Twine.h"
 #include "llvm/Support/AMDGPUMetadata.h"
 #include "llvm/Support/YAMLTraits.h"
 
diff --git a/llvm/lib/Target/AMDGPU/AMDGPU.h b/llvm/lib/Target/AMDGPU/AMDGPU.h
--- a/llvm/lib/Target/AMDGPU/AMDGPU.h
+++ b/llvm/lib/Target/AMDGPU/AMDGPU.h
@@ -10,8 +10,6 @@
 #ifndef LLVM_LIB_TARGET_AMDGPU_AMDGPU_H
 #define LLVM_LIB_TARGET_AMDGPU_AMDGPU_H
 
-#include "llvm/IR/IntrinsicsAMDGPU.h" // TODO: Sink this.
-#include "llvm/IR/IntrinsicsR600.h"   // TODO: Sink this.
 #include "llvm/IR/PassManager.h"
 #include "llvm/Support/CodeGen.h"
 
diff --git a/llvm/lib/Target/AMDGPU/AMDGPUAliasAnalysis.h b/llvm/lib/Target/AMDGPU/AMDGPUAliasAnalysis.h
--- a/llvm/lib/Target/AMDGPU/AMDGPUAliasAnalysis.h
+++ b/llvm/lib/Target/AMDGPU/AMDGPUAliasAnalysis.h
@@ -13,13 +13,7 @@
 #define LLVM_LIB_TARGET_AMDGPU_AMDGPUALIASANALYSIS_H
 
 #include "AMDGPU.h"
-#include "llvm/ADT/Triple.h"
 #include "llvm/Analysis/AliasAnalysis.h"
-#include "llvm/IR/Function.h"
-#include "llvm/IR/Module.h"
-#include "llvm/Pass.h"
-#include <algorithm>
-#include <memory>
 
 namespace llvm {
 
@@ -34,8 +28,7 @@
   const DataLayout &DL;
 
 public:
-  explicit AMDGPUAAResult(const DataLayout &DL, Triple T) : AAResultBase(),
-    DL(DL) {}
+  explicit AMDGPUAAResult(const DataLayout &DL) : AAResultBase(), DL(DL) {}
   AMDGPUAAResult(AMDGPUAAResult &&Arg)
       : AAResultBase(std::move(Arg)), DL(Arg.DL) {}
 
@@ -63,8 +56,7 @@
   using Result = AMDGPUAAResult;
 
   AMDGPUAAResult run(Function &F, AnalysisManager<Function> &AM) {
-    return AMDGPUAAResult(F.getParent()->getDataLayout(),
-        Triple(F.getParent()->getTargetTriple()));
+    return AMDGPUAAResult(F.getParent()->getDataLayout());
   }
 };
 
@@ -83,8 +75,7 @@
   const AMDGPUAAResult &getResult() const { return *Result; }
 
   bool doInitialization(Module &M) override {
-    Result.reset(new AMDGPUAAResult(M.getDataLayout(),
-        Triple(M.getTargetTriple())));
+    Result.reset(new AMDGPUAAResult(M.getDataLayout()));
     return false;
   }
 
diff --git a/llvm/lib/Target/AMDGPU/AMDGPUAliasAnalysis.cpp b/llvm/lib/Target/AMDGPU/AMDGPUAliasAnalysis.cpp
--- a/llvm/lib/Target/AMDGPU/AMDGPUAliasAnalysis.cpp
+++ b/llvm/lib/Target/AMDGPU/AMDGPUAliasAnalysis.cpp
@@ -10,23 +10,8 @@
 //===----------------------------------------------------------------------===//
 
 #include "AMDGPUAliasAnalysis.h"
-#include "AMDGPU.h"
-#include "llvm/ADT/Triple.h"
-#include "llvm/Analysis/AliasAnalysis.h"
-#include "llvm/Analysis/MemoryLocation.h"
 #include "llvm/Analysis/ValueTracking.h"
-#include "llvm/IR/Argument.h"
-#include "llvm/IR/Attributes.h"
-#include "llvm/IR/CallingConv.h"
-#include "llvm/IR/Function.h"
-#include "llvm/IR/GlobalVariable.h"
 #include "llvm/IR/Instructions.h"
-#include "llvm/IR/Type.h"
-#include "llvm/IR/Value.h"
-#include "llvm/Pass.h"
-#include "llvm/Support/Casting.h"
-#include "llvm/Support/ErrorHandling.h"
-#include <cassert>
 
 using namespace llvm;
 
diff --git a/llvm/lib/Target/AMDGPU/AMDGPUAlwaysInlinePass.cpp b/llvm/lib/Target/AMDGPU/AMDGPUAlwaysInlinePass.cpp
--- a/llvm/lib/Target/AMDGPU/AMDGPUAlwaysInlinePass.cpp
+++ b/llvm/lib/Target/AMDGPU/AMDGPUAlwaysInlinePass.cpp
@@ -15,10 +15,9 @@
 #include "AMDGPU.h"
 #include "AMDGPUTargetMachine.h"
 #include "Utils/AMDGPUBaseInfo.h"
-#include "llvm/ADT/SmallPtrSet.h"
 #include "llvm/IR/Module.h"
-#include "llvm/IR/PassManager.h"
-#include "llvm/Transforms/Utils/Cloning.h"
+#include "llvm/Pass.h"
+#include "llvm/Support/CommandLine.h"
 
 using namespace llvm;
 
diff --git a/llvm/lib/Target/AMDGPU/AMDGPUAnnotateKernelFeatures.cpp b/llvm/lib/Target/AMDGPU/AMDGPUAnnotateKernelFeatures.cpp
--- a/llvm/lib/Target/AMDGPU/AMDGPUAnnotateKernelFeatures.cpp
+++ b/llvm/lib/Target/AMDGPU/AMDGPUAnnotateKernelFeatures.cpp
@@ -13,26 +13,11 @@
 
 #include "AMDGPU.h"
 #include "AMDGPUSubtarget.h"
-#include "Utils/AMDGPUBaseInfo.h"
-#include "llvm/ADT/SmallPtrSet.h"
-#include "llvm/ADT/SmallVector.h"
-#include "llvm/ADT/StringRef.h"
-#include "llvm/ADT/Triple.h"
 #include "llvm/Analysis/CallGraph.h"
 #include "llvm/Analysis/CallGraphSCCPass.h"
 #include "llvm/CodeGen/TargetPassConfig.h"
-#include "llvm/IR/Constant.h"
-#include "llvm/IR/Constants.h"
-#include "llvm/IR/Function.h"
-#include "llvm/IR/Instruction.h"
-#include "llvm/IR/Instructions.h"
-#include "llvm/IR/Intrinsics.h"
-#include "llvm/IR/Module.h"
-#include "llvm/IR/Type.h"
-#include "llvm/IR/Use.h"
-#include "llvm/Pass.h"
-#include "llvm/Support/Casting.h"
-#include "llvm/Support/ErrorHandling.h"
+#include "llvm/IR/IntrinsicsAMDGPU.h"
+#include "llvm/IR/IntrinsicsR600.h"
 #include "llvm/Target/TargetMachine.h"
 
 #define DEBUG_TYPE "amdgpu-annotate-kernel-features"
diff --git a/llvm/lib/Target/AMDGPU/AMDGPUAnnotateUniformValues.cpp b/llvm/lib/Target/AMDGPU/AMDGPUAnnotateUniformValues.cpp
--- a/llvm/lib/Target/AMDGPU/AMDGPUAnnotateUniformValues.cpp
+++ b/llvm/lib/Target/AMDGPU/AMDGPUAnnotateUniformValues.cpp
@@ -18,11 +18,8 @@
 #include "llvm/Analysis/LegacyDivergenceAnalysis.h"
 #include "llvm/Analysis/LoopInfo.h"
 #include "llvm/Analysis/MemoryDependenceAnalysis.h"
-#include "llvm/IR/IRBuilder.h"
 #include "llvm/IR/InstVisitor.h"
 #include "llvm/InitializePasses.h"
-#include "llvm/Support/Debug.h"
-#include "llvm/Support/raw_ostream.h"
 
 #define DEBUG_TYPE "amdgpu-annotate-uniform"
 
diff --git a/llvm/lib/Target/AMDGPU/AMDGPUArgumentUsageInfo.h b/llvm/lib/Target/AMDGPU/AMDGPUArgumentUsageInfo.h
--- a/llvm/lib/Target/AMDGPU/AMDGPUArgumentUsageInfo.h
+++ b/llvm/lib/Target/AMDGPU/AMDGPUArgumentUsageInfo.h
@@ -9,14 +9,13 @@
 #ifndef LLVM_LIB_TARGET_AMDGPU_AMDGPUARGUMENTUSAGEINFO_H
 #define LLVM_LIB_TARGET_AMDGPU_AMDGPUARGUMENTUSAGEINFO_H
 
-#include "llvm/ADT/DenseMap.h"
 #include "llvm/CodeGen/Register.h"
 #include "llvm/Pass.h"
-#include "llvm/Support/LowLevelTypeImpl.h"
 
 namespace llvm {
 
 class Function;
+class LLT;
 class raw_ostream;
 class TargetRegisterClass;
 class TargetRegisterInfo;
diff --git a/llvm/lib/Target/AMDGPU/AMDGPUArgumentUsageInfo.cpp b/llvm/lib/Target/AMDGPU/AMDGPUArgumentUsageInfo.cpp
--- a/llvm/lib/Target/AMDGPU/AMDGPUArgumentUsageInfo.cpp
+++ b/llvm/lib/Target/AMDGPU/AMDGPUArgumentUsageInfo.cpp
@@ -6,11 +6,13 @@
 //
 //===----------------------------------------------------------------------===//
 
-#include "AMDGPU.h"
 #include "AMDGPUArgumentUsageInfo.h"
+#include "AMDGPU.h"
 #include "AMDGPUTargetMachine.h"
 #include "MCTargetDesc/AMDGPUMCTargetDesc.h"
 #include "SIRegisterInfo.h"
+#include "llvm/CodeGen/TargetRegisterInfo.h"
+#include "llvm/IR/Function.h"
 #include "llvm/Support/NativeFormatting.h"
 #include "llvm/Support/raw_ostream.h"
 
diff --git a/llvm/lib/Target/AMDGPU/AMDGPUAsmPrinter.h b/llvm/lib/Target/AMDGPU/AMDGPUAsmPrinter.h
--- a/llvm/lib/Target/AMDGPU/AMDGPUAsmPrinter.h
+++ b/llvm/lib/Target/AMDGPU/AMDGPUAsmPrinter.h
@@ -14,19 +14,10 @@
 #ifndef LLVM_LIB_TARGET_AMDGPU_AMDGPUASMPRINTER_H
 #define LLVM_LIB_TARGET_AMDGPU_AMDGPUASMPRINTER_H
 
-#include "AMDGPU.h"
-#include "AMDKernelCodeT.h"
-#include "AMDGPUHSAMetadataStreamer.h"
 #include "SIProgramInfo.h"
-#include "llvm/ADT/StringRef.h"
 #include "llvm/CodeGen/AsmPrinter.h"
-#include "llvm/Support/AMDHSAKernelDescriptor.h"
-#include <cstddef>
-#include <cstdint>
-#include <limits>
-#include <memory>
-#include <string>
-#include <vector>
+
+struct amd_kernel_code_t;
 
 namespace llvm {
 
@@ -36,6 +27,16 @@
 class MCOperand;
 class GCNSubtarget;
 
+namespace AMDGPU {
+namespace HSAMD {
+class MetadataStreamer;
+}
+} // namespace AMDGPU
+
+namespace amdhsa {
+struct kernel_descriptor_t;
+}
+
 class AMDGPUAsmPrinter final : public AsmPrinter {
 private:
   // Track resource usage for callee functions.
diff --git a/llvm/lib/Target/AMDGPU/AMDGPUAsmPrinter.cpp b/llvm/lib/Target/AMDGPU/AMDGPUAsmPrinter.cpp
--- a/llvm/lib/Target/AMDGPU/AMDGPUAsmPrinter.cpp
+++ b/llvm/lib/Target/AMDGPU/AMDGPUAsmPrinter.cpp
@@ -17,37 +17,27 @@
 
 #include "AMDGPUAsmPrinter.h"
 #include "AMDGPU.h"
+#include "AMDGPUHSAMetadataStreamer.h"
 #include "AMDGPUSubtarget.h"
-#include "AMDGPUTargetMachine.h"
+#include "AMDKernelCodeT.h"
 #include "MCTargetDesc/AMDGPUInstPrinter.h"
-#include "MCTargetDesc/AMDGPUMCTargetDesc.h"
 #include "MCTargetDesc/AMDGPUTargetStreamer.h"
 #include "R600AsmPrinter.h"
-#include "R600Defines.h"
-#include "R600MachineFunctionInfo.h"
-#include "R600RegisterInfo.h"
-#include "SIDefines.h"
-#include "SIInstrInfo.h"
 #include "SIMachineFunctionInfo.h"
-#include "SIRegisterInfo.h"
 #include "TargetInfo/AMDGPUTargetInfo.h"
 #include "Utils/AMDGPUBaseInfo.h"
-#include "llvm/BinaryFormat/ELF.h"
-#include "llvm/CodeGen/MachineFrameInfo.h"
 #include "llvm/IR/DiagnosticInfo.h"
 #include "llvm/MC/MCAssembler.h"
 #include "llvm/MC/MCContext.h"
 #include "llvm/MC/MCSectionELF.h"
 #include "llvm/MC/MCStreamer.h"
-#include "llvm/Support/AMDGPUMetadata.h"
-#include "llvm/Support/MathExtras.h"
-#include "llvm/Support/TargetParser.h"
+#include "llvm/Support/AMDHSAKernelDescriptor.h"
 #include "llvm/Support/TargetRegistry.h"
 #include "llvm/Target/TargetLoweringObjectFile.h"
+#include "llvm/Target/TargetMachine.h"
 
 using namespace llvm;
 using namespace llvm::AMDGPU;
-using namespace llvm::AMDGPU::HSAMD;
 
 // We need to tell the runtime some amount ahead of time if we don't know the
 // true stack size. Assume a smaller number if this is only due to dynamic /
@@ -110,9 +100,9 @@
   : AsmPrinter(TM, std::move(Streamer)) {
   if (TM.getTargetTriple().getOS() == Triple::AMDHSA) {
     if (isHsaAbiVersion2(getGlobalSTI())) {
-      HSAMetadataStream.reset(new MetadataStreamerV2());
+      HSAMetadataStream.reset(new HSAMD::MetadataStreamerV2());
     } else {
-      HSAMetadataStream.reset(new MetadataStreamerV3());
+      HSAMetadataStream.reset(new HSAMD::MetadataStreamerV3());
     }
   }
 }
diff --git a/llvm/lib/Target/AMDGPU/AMDGPUAtomicOptimizer.cpp b/llvm/lib/Target/AMDGPU/AMDGPUAtomicOptimizer.cpp
--- a/llvm/lib/Target/AMDGPU/AMDGPUAtomicOptimizer.cpp
+++ b/llvm/lib/Target/AMDGPU/AMDGPUAtomicOptimizer.cpp
@@ -15,12 +15,13 @@
 
 #include "AMDGPU.h"
 #include "AMDGPUSubtarget.h"
-#include "SIDefines.h"
 #include "llvm/Analysis/LegacyDivergenceAnalysis.h"
 #include "llvm/CodeGen/TargetPassConfig.h"
 #include "llvm/IR/IRBuilder.h"
 #include "llvm/IR/InstVisitor.h"
+#include "llvm/IR/IntrinsicsAMDGPU.h"
 #include "llvm/InitializePasses.h"
+#include "llvm/Target/TargetMachine.h"
 #include "llvm/Transforms/Utils/BasicBlockUtils.h"
 
 #define DEBUG_TYPE "amdgpu-atomic-optimizer"
diff --git a/llvm/lib/Target/AMDGPU/AMDGPUCallLowering.h b/llvm/lib/Target/AMDGPU/AMDGPUCallLowering.h
--- a/llvm/lib/Target/AMDGPU/AMDGPUCallLowering.h
+++ b/llvm/lib/Target/AMDGPU/AMDGPUCallLowering.h
@@ -14,7 +14,6 @@
 #ifndef LLVM_LIB_TARGET_AMDGPU_AMDGPUCALLLOWERING_H
 #define LLVM_LIB_TARGET_AMDGPU_AMDGPUCALLLOWERING_H
 
-#include "AMDGPU.h"
 #include "llvm/CodeGen/GlobalISel/CallLowering.h"
 
 namespace llvm {
diff --git a/llvm/lib/Target/AMDGPU/AMDGPUCallLowering.cpp b/llvm/lib/Target/AMDGPU/AMDGPUCallLowering.cpp
--- a/llvm/lib/Target/AMDGPU/AMDGPUCallLowering.cpp
+++ b/llvm/lib/Target/AMDGPU/AMDGPUCallLowering.cpp
@@ -14,19 +14,14 @@
 
 #include "AMDGPUCallLowering.h"
 #include "AMDGPU.h"
-#include "AMDGPUISelLowering.h"
 #include "AMDGPULegalizerInfo.h"
 #include "AMDGPUSubtarget.h"
 #include "AMDGPUTargetMachine.h"
-#include "MCTargetDesc/AMDGPUMCTargetDesc.h"
-#include "SIISelLowering.h"
 #include "SIMachineFunctionInfo.h"
 #include "SIRegisterInfo.h"
 #include "llvm/CodeGen/Analysis.h"
-#include "llvm/CodeGen/CallingConvLower.h"
 #include "llvm/CodeGen/GlobalISel/MachineIRBuilder.h"
-#include "llvm/CodeGen/MachineInstrBuilder.h"
-#include "llvm/Support/LowLevelTypeImpl.h"
+#include "llvm/IR/IntrinsicsAMDGPU.h"
 
 #define DEBUG_TYPE "amdgpu-call-lowering"
 
diff --git a/llvm/lib/Target/AMDGPU/AMDGPUCodeGenPrepare.cpp b/llvm/lib/Target/AMDGPU/AMDGPUCodeGenPrepare.cpp
--- a/llvm/lib/Target/AMDGPU/AMDGPUCodeGenPrepare.cpp
+++ b/llvm/lib/Target/AMDGPU/AMDGPUCodeGenPrepare.cpp
@@ -15,39 +15,18 @@
 #include "AMDGPU.h"
 #include "AMDGPUSubtarget.h"
 #include "AMDGPUTargetMachine.h"
-#include "llvm/ADT/FloatingPointMode.h"
-#include "llvm/ADT/StringRef.h"
 #include "llvm/Analysis/AssumptionCache.h"
 #include "llvm/Analysis/ConstantFolding.h"
 #include "llvm/Analysis/LegacyDivergenceAnalysis.h"
-#include "llvm/Analysis/Loads.h"
 #include "llvm/Analysis/ValueTracking.h"
-#include "llvm/CodeGen/Passes.h"
 #include "llvm/CodeGen/TargetPassConfig.h"
-#include "llvm/IR/Attributes.h"
-#include "llvm/IR/BasicBlock.h"
-#include "llvm/IR/Constants.h"
-#include "llvm/IR/DerivedTypes.h"
 #include "llvm/IR/Dominators.h"
-#include "llvm/IR/Function.h"
-#include "llvm/IR/IRBuilder.h"
 #include "llvm/IR/InstVisitor.h"
-#include "llvm/IR/InstrTypes.h"
-#include "llvm/IR/Instruction.h"
-#include "llvm/IR/Instructions.h"
-#include "llvm/IR/IntrinsicInst.h"
-#include "llvm/IR/Intrinsics.h"
-#include "llvm/IR/LLVMContext.h"
-#include "llvm/IR/Operator.h"
-#include "llvm/IR/Type.h"
-#include "llvm/IR/Value.h"
+#include "llvm/IR/IntrinsicsAMDGPU.h"
 #include "llvm/InitializePasses.h"
 #include "llvm/Pass.h"
-#include "llvm/Support/Casting.h"
 #include "llvm/Support/KnownBits.h"
 #include "llvm/Transforms/Utils/IntegerDivision.h"
-#include <cassert>
-#include <iterator>
 
 #define DEBUG_TYPE "amdgpu-codegenprepare"
 
diff --git a/llvm/lib/Target/AMDGPU/AMDGPUExportClustering.h b/llvm/lib/Target/AMDGPU/AMDGPUExportClustering.h
--- a/llvm/lib/Target/AMDGPU/AMDGPUExportClustering.h
+++ b/llvm/lib/Target/AMDGPU/AMDGPUExportClustering.h
@@ -6,7 +6,8 @@
 //
 //===----------------------------------------------------------------------===//
 
-#include "llvm/CodeGen/MachineScheduler.h"
+#include "llvm/CodeGen/ScheduleDAGMutation.h"
+#include <memory>
 
 namespace llvm {
 
diff --git a/llvm/lib/Target/AMDGPU/AMDGPUExportClustering.cpp b/llvm/lib/Target/AMDGPU/AMDGPUExportClustering.cpp
--- a/llvm/lib/Target/AMDGPU/AMDGPUExportClustering.cpp
+++ b/llvm/lib/Target/AMDGPU/AMDGPUExportClustering.cpp
@@ -12,9 +12,9 @@
 //===----------------------------------------------------------------------===//
 
 #include "AMDGPUExportClustering.h"
-#include "AMDGPUSubtarget.h"
 #include "MCTargetDesc/AMDGPUMCTargetDesc.h"
 #include "SIInstrInfo.h"
+#include "llvm/CodeGen/ScheduleDAGInstrs.h"
 
 using namespace llvm;
 
diff --git a/llvm/lib/Target/AMDGPU/AMDGPUGlobalISelUtils.h b/llvm/lib/Target/AMDGPU/AMDGPUGlobalISelUtils.h
--- a/llvm/lib/Target/AMDGPU/AMDGPUGlobalISelUtils.h
+++ b/llvm/lib/Target/AMDGPU/AMDGPUGlobalISelUtils.h
@@ -10,11 +10,10 @@
 #define LLVM_LIB_TARGET_AMDGPU_AMDGPUGLOBALISELUTILS_H
 
 #include "llvm/CodeGen/Register.h"
-#include <tuple>
+#include <utility>
 
 namespace llvm {
 
-class MachineInstr;
 class MachineRegisterInfo;
 
 namespace AMDGPU {
diff --git a/llvm/lib/Target/AMDGPU/AMDGPUHSAMetadataStreamer.h b/llvm/lib/Target/AMDGPU/AMDGPUHSAMetadataStreamer.h
--- a/llvm/lib/Target/AMDGPU/AMDGPUHSAMetadataStreamer.h
+++ b/llvm/lib/Target/AMDGPU/AMDGPUHSAMetadataStreamer.h
@@ -15,9 +15,6 @@
 #ifndef LLVM_LIB_TARGET_AMDGPU_MCTARGETDESC_AMDGPUHSAMETADATASTREAMER_H
 #define LLVM_LIB_TARGET_AMDGPU_MCTARGETDESC_AMDGPUHSAMETADATASTREAMER_H
 
-#include "AMDGPU.h"
-#include "AMDKernelCodeT.h"
-#include "llvm/ADT/StringRef.h"
 #include "llvm/BinaryFormat/MsgPackDocument.h"
 #include "llvm/Support/AMDGPUMetadata.h"
 #include "llvm/Support/Alignment.h"
diff --git a/llvm/lib/Target/AMDGPU/AMDGPUHSAMetadataStreamer.cpp b/llvm/lib/Target/AMDGPU/AMDGPUHSAMetadataStreamer.cpp
--- a/llvm/lib/Target/AMDGPU/AMDGPUHSAMetadataStreamer.cpp
+++ b/llvm/lib/Target/AMDGPU/AMDGPUHSAMetadataStreamer.cpp
@@ -18,12 +18,7 @@
 #include "MCTargetDesc/AMDGPUTargetStreamer.h"
 #include "SIMachineFunctionInfo.h"
 #include "SIProgramInfo.h"
-#include "Utils/AMDGPUBaseInfo.h"
-#include "llvm/ADT/StringSwitch.h"
-#include "llvm/IR/Constants.h"
 #include "llvm/IR/Module.h"
-#include "llvm/Support/raw_ostream.h"
-
 using namespace llvm;
 
 static std::pair<Type *, Align> getArgumentTypeAlign(const Argument &Arg,
diff --git a/llvm/lib/Target/AMDGPU/AMDGPUISelDAGToDAG.cpp b/llvm/lib/Target/AMDGPU/AMDGPUISelDAGToDAG.cpp
--- a/llvm/lib/Target/AMDGPU/AMDGPUISelDAGToDAG.cpp
+++ b/llvm/lib/Target/AMDGPU/AMDGPUISelDAGToDAG.cpp
@@ -12,48 +12,22 @@
 //===----------------------------------------------------------------------===//
 
 #include "AMDGPU.h"
-#include "AMDGPUArgumentUsageInfo.h"
-#include "AMDGPUISelLowering.h" // For AMDGPUISD
-#include "AMDGPUInstrInfo.h"
-#include "AMDGPUPerfHintAnalysis.h"
 #include "AMDGPUSubtarget.h"
 #include "AMDGPUTargetMachine.h"
-#include "MCTargetDesc/AMDGPUMCTargetDesc.h"
-#include "SIDefines.h"
-#include "SIISelLowering.h"
-#include "SIInstrInfo.h"
 #include "SIMachineFunctionInfo.h"
-#include "SIRegisterInfo.h"
-#include "llvm/ADT/APInt.h"
-#include "llvm/ADT/SmallVector.h"
-#include "llvm/ADT/StringRef.h"
 #include "llvm/Analysis/LegacyDivergenceAnalysis.h"
-#include "llvm/Analysis/LoopInfo.h"
 #include "llvm/Analysis/ValueTracking.h"
 #include "llvm/CodeGen/FunctionLoweringInfo.h"
-#include "llvm/CodeGen/ISDOpcodes.h"
-#include "llvm/CodeGen/MachineFunction.h"
-#include "llvm/CodeGen/MachineRegisterInfo.h"
 #include "llvm/CodeGen/SelectionDAG.h"
 #include "llvm/CodeGen/SelectionDAGISel.h"
 #include "llvm/CodeGen/SelectionDAGNodes.h"
-#include "llvm/CodeGen/ValueTypes.h"
-#include "llvm/IR/BasicBlock.h"
+#include "llvm/IR/IntrinsicsAMDGPU.h"
 #include "llvm/InitializePasses.h"
+
 #ifdef EXPENSIVE_CHECKS
+#include "llvm/Analysis/LoopInfo.h"
 #include "llvm/IR/Dominators.h"
 #endif
-#include "llvm/IR/Instruction.h"
-#include "llvm/MC/MCInstrDesc.h"
-#include "llvm/Support/Casting.h"
-#include "llvm/Support/CodeGen.h"
-#include "llvm/Support/ErrorHandling.h"
-#include "llvm/Support/MachineValueType.h"
-#include "llvm/Support/MathExtras.h"
-#include <cassert>
-#include <cstdint>
-#include <new>
-#include <vector>
 
 #define DEBUG_TYPE "isel"
 
diff --git a/llvm/lib/Target/AMDGPU/AMDGPUISelLowering.h b/llvm/lib/Target/AMDGPU/AMDGPUISelLowering.h
--- a/llvm/lib/Target/AMDGPU/AMDGPUISelLowering.h
+++ b/llvm/lib/Target/AMDGPU/AMDGPUISelLowering.h
@@ -15,10 +15,8 @@
 #ifndef LLVM_LIB_TARGET_AMDGPU_AMDGPUISELLOWERING_H
 #define LLVM_LIB_TARGET_AMDGPU_AMDGPUISELLOWERING_H
 
-#include "AMDGPU.h"
 #include "llvm/CodeGen/CallingConvLower.h"
 #include "llvm/CodeGen/TargetLowering.h"
-#include "llvm/Target/TargetMachine.h"
 
 namespace llvm {
 
@@ -145,16 +143,7 @@
 public:
   AMDGPUTargetLowering(const TargetMachine &TM, const AMDGPUSubtarget &STI);
 
-  bool mayIgnoreSignedZero(SDValue Op) const {
-    if (getTargetMachine().Options.NoSignedZerosFPMath)
-      return true;
-
-    const auto Flags = Op.getNode()->getFlags();
-    if (Flags.hasNoSignedZeros())
-      return true;
-
-    return false;
-  }
+  bool mayIgnoreSignedZero(SDValue Op) const;
 
   static inline SDValue stripBitcast(SDValue Val) {
     return Val.getOpcode() == ISD::BITCAST ? Val.getOperand(0) : Val;
diff --git a/llvm/lib/Target/AMDGPU/AMDGPUISelLowering.cpp b/llvm/lib/Target/AMDGPU/AMDGPUISelLowering.cpp
--- a/llvm/lib/Target/AMDGPU/AMDGPUISelLowering.cpp
+++ b/llvm/lib/Target/AMDGPU/AMDGPUISelLowering.cpp
@@ -14,25 +14,17 @@
 
 #include "AMDGPUISelLowering.h"
 #include "AMDGPU.h"
-#include "AMDGPUCallLowering.h"
-#include "AMDGPUFrameLowering.h"
+#include "AMDGPUInstrInfo.h"
+#include "AMDGPUMachineFunction.h"
 #include "AMDGPUSubtarget.h"
-#include "AMDGPUTargetMachine.h"
-#include "Utils/AMDGPUBaseInfo.h"
-#include "R600MachineFunctionInfo.h"
-#include "SIInstrInfo.h"
 #include "SIMachineFunctionInfo.h"
-#include "MCTargetDesc/AMDGPUMCTargetDesc.h"
 #include "llvm/CodeGen/Analysis.h"
-#include "llvm/CodeGen/CallingConvLower.h"
-#include "llvm/CodeGen/MachineFunction.h"
-#include "llvm/CodeGen/MachineRegisterInfo.h"
-#include "llvm/CodeGen/SelectionDAG.h"
-#include "llvm/CodeGen/TargetLoweringObjectFileImpl.h"
-#include "llvm/IR/DataLayout.h"
 #include "llvm/IR/DiagnosticInfo.h"
+#include "llvm/IR/IntrinsicsAMDGPU.h"
+#include "llvm/Support/CommandLine.h"
 #include "llvm/Support/KnownBits.h"
-#include "llvm/Support/MathExtras.h"
+#include "llvm/Target/TargetMachine.h"
+
 using namespace llvm;
 
 #include "AMDGPUGenCallingConv.inc"
@@ -573,6 +565,17 @@
   setTargetDAGCombine(ISD::INTRINSIC_WO_CHAIN);
 }
 
+bool AMDGPUTargetLowering::mayIgnoreSignedZero(SDValue Op) const {
+  if (getTargetMachine().Options.NoSignedZerosFPMath)
+    return true;
+
+  const auto Flags = Op.getNode()->getFlags();
+  if (Flags.hasNoSignedZeros())
+    return true;
+
+  return false;
+}
+
 //===----------------------------------------------------------------------===//
 // Target Information
 //===----------------------------------------------------------------------===//
diff --git a/llvm/lib/Target/AMDGPU/AMDGPUInline.cpp b/llvm/lib/Target/AMDGPU/AMDGPUInline.cpp
--- a/llvm/lib/Target/AMDGPU/AMDGPUInline.cpp
+++ b/llvm/lib/Target/AMDGPU/AMDGPUInline.cpp
@@ -18,19 +18,11 @@
 //===----------------------------------------------------------------------===//
 
 #include "AMDGPU.h"
-#include "llvm/Analysis/AssumptionCache.h"
-#include "llvm/Analysis/CallGraph.h"
-#include "llvm/Analysis/InlineCost.h"
 #include "llvm/Analysis/TargetTransformInfo.h"
 #include "llvm/Analysis/ValueTracking.h"
-#include "llvm/IR/DataLayout.h"
 #include "llvm/IR/Instructions.h"
-#include "llvm/IR/Module.h"
-#include "llvm/IR/Type.h"
 #include "llvm/InitializePasses.h"
 #include "llvm/Support/CommandLine.h"
-#include "llvm/Support/Debug.h"
-#include "llvm/Transforms/IPO.h"
 #include "llvm/Transforms/IPO/Inliner.h"
 
 using namespace llvm;
diff --git a/llvm/lib/Target/AMDGPU/AMDGPUInstCombineIntrinsic.cpp b/llvm/lib/Target/AMDGPU/AMDGPUInstCombineIntrinsic.cpp
--- a/llvm/lib/Target/AMDGPU/AMDGPUInstCombineIntrinsic.cpp
+++ b/llvm/lib/Target/AMDGPU/AMDGPUInstCombineIntrinsic.cpp
@@ -14,8 +14,9 @@
 //
 //===----------------------------------------------------------------------===//
 
+#include "AMDGPUInstrInfo.h"
 #include "AMDGPUTargetTransformInfo.h"
-#include "llvm/Support/KnownBits.h"
+#include "llvm/IR/IntrinsicsAMDGPU.h"
 #include "llvm/Transforms/InstCombine/InstCombiner.h"
 
 using namespace llvm;
diff --git a/llvm/lib/Target/AMDGPU/AMDGPUInstrInfo.h b/llvm/lib/Target/AMDGPU/AMDGPUInstrInfo.h
--- a/llvm/lib/Target/AMDGPU/AMDGPUInstrInfo.h
+++ b/llvm/lib/Target/AMDGPU/AMDGPUInstrInfo.h
@@ -15,9 +15,7 @@
 #ifndef LLVM_LIB_TARGET_AMDGPU_AMDGPUINSTRINFO_H
 #define LLVM_LIB_TARGET_AMDGPU_AMDGPUINSTRINFO_H
 
-#include "AMDGPU.h"
 #include "Utils/AMDGPUBaseInfo.h"
-#include "llvm/CodeGen/TargetInstrInfo.h"
 
 namespace llvm {
 
@@ -25,6 +23,7 @@
 class MachineFunction;
 class MachineInstr;
 class MachineInstrBuilder;
+class MachineMemOperand;
 
 class AMDGPUInstrInfo {
 public:
diff --git a/llvm/lib/Target/AMDGPU/AMDGPUInstrInfo.cpp b/llvm/lib/Target/AMDGPU/AMDGPUInstrInfo.cpp
--- a/llvm/lib/Target/AMDGPU/AMDGPUInstrInfo.cpp
+++ b/llvm/lib/Target/AMDGPU/AMDGPUInstrInfo.cpp
@@ -13,11 +13,11 @@
 //===----------------------------------------------------------------------===//
 
 #include "AMDGPUInstrInfo.h"
-#include "AMDGPUTargetMachine.h"
-#include "MCTargetDesc/AMDGPUMCTargetDesc.h"
-#include "llvm/CodeGen/MachineFrameInfo.h"
-#include "llvm/CodeGen/MachineInstrBuilder.h"
-#include "llvm/CodeGen/MachineRegisterInfo.h"
+#include "AMDGPU.h"
+#include "llvm/CodeGen/MachineMemOperand.h"
+#include "llvm/IR/Constants.h"
+#include "llvm/IR/Instruction.h"
+#include "llvm/IR/Value.h"
 
 using namespace llvm;
 
diff --git a/llvm/lib/Target/AMDGPU/AMDGPUInstructionSelector.h b/llvm/lib/Target/AMDGPU/AMDGPUInstructionSelector.h
--- a/llvm/lib/Target/AMDGPU/AMDGPUInstructionSelector.h
+++ b/llvm/lib/Target/AMDGPU/AMDGPUInstructionSelector.h
@@ -13,13 +13,11 @@
 #ifndef LLVM_LIB_TARGET_AMDGPU_AMDGPUINSTRUCTIONSELECTOR_H
 #define LLVM_LIB_TARGET_AMDGPU_AMDGPUINSTRUCTIONSELECTOR_H
 
-#include "AMDGPU.h"
-#include "AMDGPUArgumentUsageInfo.h"
-#include "llvm/ADT/ArrayRef.h"
-#include "llvm/ADT/SmallVector.h"
-#include "llvm/CodeGen/Register.h"
 #include "llvm/CodeGen/GlobalISel/InstructionSelector.h"
+#include "llvm/CodeGen/Register.h"
 #include "llvm/IR/InstrTypes.h"
+#include "llvm/IR/Intrinsics.h"
+#include "llvm/IR/IntrinsicsAMDGPU.h"
 
 namespace {
 #define GET_GLOBALISEL_PREDICATE_BITSET
@@ -37,6 +35,7 @@
 
 class AMDGPUInstrInfo;
 class AMDGPURegisterBankInfo;
+class AMDGPUTargetMachine;
 class GCNSubtarget;
 class MachineInstr;
 class MachineIRBuilder;
diff --git a/llvm/lib/Target/AMDGPU/AMDGPUInstructionSelector.cpp b/llvm/lib/Target/AMDGPU/AMDGPUInstructionSelector.cpp
--- a/llvm/lib/Target/AMDGPU/AMDGPUInstructionSelector.cpp
+++ b/llvm/lib/Target/AMDGPU/AMDGPUInstructionSelector.cpp
@@ -12,28 +12,18 @@
 //===----------------------------------------------------------------------===//
 
 #include "AMDGPUInstructionSelector.h"
-#include "AMDGPUInstrInfo.h"
+#include "AMDGPU.h"
 #include "AMDGPUGlobalISelUtils.h"
+#include "AMDGPUInstrInfo.h"
 #include "AMDGPURegisterBankInfo.h"
 #include "AMDGPUSubtarget.h"
 #include "AMDGPUTargetMachine.h"
-#include "MCTargetDesc/AMDGPUMCTargetDesc.h"
 #include "SIMachineFunctionInfo.h"
 #include "llvm/CodeGen/GlobalISel/GISelKnownBits.h"
-#include "llvm/CodeGen/GlobalISel/InstructionSelector.h"
 #include "llvm/CodeGen/GlobalISel/InstructionSelectorImpl.h"
-#include "llvm/CodeGen/GlobalISel/MachineIRBuilder.h"
 #include "llvm/CodeGen/GlobalISel/MIPatternMatch.h"
-#include "llvm/CodeGen/GlobalISel/Utils.h"
-#include "llvm/CodeGen/MachineBasicBlock.h"
-#include "llvm/CodeGen/MachineFunction.h"
-#include "llvm/CodeGen/MachineInstr.h"
-#include "llvm/CodeGen/MachineInstrBuilder.h"
-#include "llvm/CodeGen/MachineRegisterInfo.h"
+#include "llvm/CodeGen/GlobalISel/MachineIRBuilder.h"
 #include "llvm/IR/DiagnosticInfo.h"
-#include "llvm/IR/Type.h"
-#include "llvm/Support/Debug.h"
-#include "llvm/Support/raw_ostream.h"
 
 #define DEBUG_TYPE "amdgpu-isel"
 
diff --git a/llvm/lib/Target/AMDGPU/AMDGPULateCodeGenPrepare.cpp b/llvm/lib/Target/AMDGPU/AMDGPULateCodeGenPrepare.cpp
--- a/llvm/lib/Target/AMDGPU/AMDGPULateCodeGenPrepare.cpp
+++ b/llvm/lib/Target/AMDGPU/AMDGPULateCodeGenPrepare.cpp
@@ -16,15 +16,12 @@
 #include "llvm/Analysis/AssumptionCache.h"
 #include "llvm/Analysis/LegacyDivergenceAnalysis.h"
 #include "llvm/Analysis/ValueTracking.h"
-#include "llvm/CodeGen/Passes.h"
 #include "llvm/IR/IRBuilder.h"
 #include "llvm/IR/InstVisitor.h"
 #include "llvm/InitializePasses.h"
 #include "llvm/Support/CommandLine.h"
 #include "llvm/Support/KnownBits.h"
 #include "llvm/Transforms/Utils/Local.h"
-#include <cassert>
-#include <iterator>
 
 #define DEBUG_TYPE "amdgpu-late-codegenprepare"
 
diff --git a/llvm/lib/Target/AMDGPU/AMDGPULegalizerInfo.h b/llvm/lib/Target/AMDGPU/AMDGPULegalizerInfo.h
--- a/llvm/lib/Target/AMDGPU/AMDGPULegalizerInfo.h
+++ b/llvm/lib/Target/AMDGPU/AMDGPULegalizerInfo.h
@@ -24,6 +24,9 @@
 class LLVMContext;
 class GCNSubtarget;
 
+namespace AMDGPU {
+struct ImageDimIntrinsicInfo;
+}
 /// This class provides the information for the target register banks.
 class AMDGPULegalizerInfo final : public LegalizerInfo {
   const GCNSubtarget &ST;
diff --git a/llvm/lib/Target/AMDGPU/AMDGPULegalizerInfo.cpp b/llvm/lib/Target/AMDGPU/AMDGPULegalizerInfo.cpp
--- a/llvm/lib/Target/AMDGPU/AMDGPULegalizerInfo.cpp
+++ b/llvm/lib/Target/AMDGPU/AMDGPULegalizerInfo.cpp
@@ -15,19 +15,15 @@
 
 #include "AMDGPU.h"
 #include "AMDGPUGlobalISelUtils.h"
+#include "AMDGPUInstrInfo.h"
 #include "AMDGPUTargetMachine.h"
 #include "SIMachineFunctionInfo.h"
 #include "llvm/ADT/ScopeExit.h"
 #include "llvm/CodeGen/GlobalISel/LegalizerHelper.h"
-#include "llvm/CodeGen/GlobalISel/LegalizerInfo.h"
 #include "llvm/CodeGen/GlobalISel/MIPatternMatch.h"
 #include "llvm/CodeGen/GlobalISel/MachineIRBuilder.h"
-#include "llvm/CodeGen/TargetOpcodes.h"
-#include "llvm/CodeGen/ValueTypes.h"
-#include "llvm/IR/DerivedTypes.h"
 #include "llvm/IR/DiagnosticInfo.h"
-#include "llvm/IR/Type.h"
-#include "llvm/Support/Debug.h"
+#include "llvm/IR/IntrinsicsAMDGPU.h"
 
 #define DEBUG_TYPE "amdgpu-legalinfo"
 
diff --git a/llvm/lib/Target/AMDGPU/AMDGPULibCalls.cpp b/llvm/lib/Target/AMDGPU/AMDGPULibCalls.cpp
--- a/llvm/lib/Target/AMDGPU/AMDGPULibCalls.cpp
+++ b/llvm/lib/Target/AMDGPU/AMDGPULibCalls.cpp
@@ -14,27 +14,11 @@
 #include "AMDGPU.h"
 #include "AMDGPULibFunc.h"
 #include "AMDGPUSubtarget.h"
-#include "llvm/ADT/StringRef.h"
-#include "llvm/ADT/StringSet.h"
 #include "llvm/Analysis/AliasAnalysis.h"
 #include "llvm/Analysis/Loads.h"
-#include "llvm/IR/Constants.h"
-#include "llvm/IR/DerivedTypes.h"
-#include "llvm/IR/Function.h"
-#include "llvm/IR/IRBuilder.h"
-#include "llvm/IR/Instructions.h"
-#include "llvm/IR/Intrinsics.h"
-#include "llvm/IR/LLVMContext.h"
-#include "llvm/IR/Module.h"
-#include "llvm/IR/PassManager.h"
-#include "llvm/IR/ValueSymbolTable.h"
+#include "llvm/IR/IntrinsicsAMDGPU.h"
 #include "llvm/InitializePasses.h"
-#include "llvm/Support/Debug.h"
-#include "llvm/Support/MathExtras.h"
-#include "llvm/Support/raw_ostream.h"
 #include "llvm/Target/TargetMachine.h"
-#include <cmath>
-#include <vector>
 
 #define DEBUG_TYPE "amdgpu-simplifylib"
 
diff --git a/llvm/lib/Target/AMDGPU/AMDGPULibFunc.cpp b/llvm/lib/Target/AMDGPU/AMDGPULibFunc.cpp
--- a/llvm/lib/Target/AMDGPU/AMDGPULibFunc.cpp
+++ b/llvm/lib/Target/AMDGPU/AMDGPULibFunc.cpp
@@ -12,17 +12,14 @@
 
 #include "AMDGPULibFunc.h"
 #include "AMDGPU.h"
-#include "llvm/ADT/SmallString.h"
-#include "llvm/ADT/SmallVector.h"
 #include "llvm/ADT/StringExtras.h"
+#include "llvm/ADT/StringMap.h"
 #include "llvm/ADT/StringSwitch.h"
-#include "llvm/IR/Attributes.h"
 #include "llvm/IR/DerivedTypes.h"
 #include "llvm/IR/Function.h"
 #include "llvm/IR/Module.h"
 #include "llvm/IR/ValueSymbolTable.h"
 #include "llvm/Support/raw_ostream.h"
-#include <string>
 
 using namespace llvm;
 
diff --git a/llvm/lib/Target/AMDGPU/AMDGPULowerIntrinsics.cpp b/llvm/lib/Target/AMDGPU/AMDGPULowerIntrinsics.cpp
--- a/llvm/lib/Target/AMDGPU/AMDGPULowerIntrinsics.cpp
+++ b/llvm/lib/Target/AMDGPU/AMDGPULowerIntrinsics.cpp
@@ -8,12 +8,15 @@
 
 #include "AMDGPU.h"
 #include "AMDGPUSubtarget.h"
-#include "llvm/CodeGen/TargetPassConfig.h"
 #include "llvm/Analysis/TargetTransformInfo.h"
+#include "llvm/CodeGen/TargetPassConfig.h"
 #include "llvm/IR/Constants.h"
 #include "llvm/IR/Instructions.h"
 #include "llvm/IR/IntrinsicInst.h"
+#include "llvm/IR/IntrinsicsAMDGPU.h"
+#include "llvm/IR/IntrinsicsR600.h"
 #include "llvm/IR/Module.h"
+#include "llvm/Target/TargetMachine.h"
 #include "llvm/Transforms/Utils/LowerMemIntrinsics.h"
 
 #define DEBUG_TYPE "amdgpu-lower-intrinsics"
diff --git a/llvm/lib/Target/AMDGPU/AMDGPULowerKernelArguments.cpp b/llvm/lib/Target/AMDGPU/AMDGPULowerKernelArguments.cpp
--- a/llvm/lib/Target/AMDGPU/AMDGPULowerKernelArguments.cpp
+++ b/llvm/lib/Target/AMDGPU/AMDGPULowerKernelArguments.cpp
@@ -13,29 +13,10 @@
 
 #include "AMDGPU.h"
 #include "AMDGPUSubtarget.h"
-#include "AMDGPUTargetMachine.h"
-#include "llvm/ADT/StringRef.h"
-#include "llvm/Analysis/Loads.h"
-#include "llvm/CodeGen/Passes.h"
 #include "llvm/CodeGen/TargetPassConfig.h"
-#include "llvm/IR/Attributes.h"
-#include "llvm/IR/BasicBlock.h"
-#include "llvm/IR/Constants.h"
-#include "llvm/IR/DerivedTypes.h"
-#include "llvm/IR/Function.h"
-#include "llvm/IR/IRBuilder.h"
-#include "llvm/IR/InstrTypes.h"
-#include "llvm/IR/Instruction.h"
-#include "llvm/IR/Instructions.h"
-#include "llvm/IR/LLVMContext.h"
+#include "llvm/IR/IntrinsicsAMDGPU.h"
 #include "llvm/IR/MDBuilder.h"
-#include "llvm/IR/Metadata.h"
-#include "llvm/IR/Operator.h"
-#include "llvm/IR/Type.h"
-#include "llvm/IR/Value.h"
-#include "llvm/Pass.h"
-#include "llvm/Support/Casting.h"
-
+#include "llvm/Target/TargetMachine.h"
 #define DEBUG_TYPE "amdgpu-lower-kernel-arguments"
 
 using namespace llvm;
diff --git a/llvm/lib/Target/AMDGPU/AMDGPULowerKernelAttributes.cpp b/llvm/lib/Target/AMDGPU/AMDGPULowerKernelAttributes.cpp
--- a/llvm/lib/Target/AMDGPU/AMDGPULowerKernelAttributes.cpp
+++ b/llvm/lib/Target/AMDGPU/AMDGPULowerKernelAttributes.cpp
@@ -21,7 +21,7 @@
 #include "llvm/IR/Function.h"
 #include "llvm/IR/InstIterator.h"
 #include "llvm/IR/Instructions.h"
-#include "llvm/IR/PassManager.h"
+#include "llvm/IR/IntrinsicsAMDGPU.h"
 #include "llvm/IR/PatternMatch.h"
 #include "llvm/Pass.h"
 
diff --git a/llvm/lib/Target/AMDGPU/AMDGPUMCInstLower.cpp b/llvm/lib/Target/AMDGPU/AMDGPUMCInstLower.cpp
--- a/llvm/lib/Target/AMDGPU/AMDGPUMCInstLower.cpp
+++ b/llvm/lib/Target/AMDGPU/AMDGPUMCInstLower.cpp
@@ -16,9 +16,7 @@
 #include "AMDGPUSubtarget.h"
 #include "AMDGPUTargetMachine.h"
 #include "MCTargetDesc/AMDGPUInstPrinter.h"
-#include "MCTargetDesc/AMDGPUMCTargetDesc.h"
 #include "R600AsmPrinter.h"
-#include "SIInstrInfo.h"
 #include "llvm/CodeGen/MachineBasicBlock.h"
 #include "llvm/CodeGen/MachineInstr.h"
 #include "llvm/IR/Constants.h"
diff --git a/llvm/lib/Target/AMDGPU/AMDGPUMachineCFGStructurizer.cpp b/llvm/lib/Target/AMDGPU/AMDGPUMachineCFGStructurizer.cpp
--- a/llvm/lib/Target/AMDGPU/AMDGPUMachineCFGStructurizer.cpp
+++ b/llvm/lib/Target/AMDGPU/AMDGPUMachineCFGStructurizer.cpp
@@ -12,35 +12,16 @@
 
 #include "AMDGPU.h"
 #include "AMDGPUSubtarget.h"
-#include "SIInstrInfo.h"
-#include "llvm/ADT/ArrayRef.h"
-#include "llvm/ADT/DenseMap.h"
 #include "llvm/ADT/DenseSet.h"
 #include "llvm/ADT/PostOrderIterator.h"
 #include "llvm/ADT/SetVector.h"
 #include "llvm/ADT/SmallPtrSet.h"
-#include "llvm/ADT/SmallVector.h"
 #include "llvm/CodeGen/MachineBasicBlock.h"
-#include "llvm/CodeGen/MachineFunction.h"
-#include "llvm/CodeGen/MachineFunctionPass.h"
-#include "llvm/CodeGen/MachineInstr.h"
 #include "llvm/CodeGen/MachineInstrBuilder.h"
-#include "llvm/CodeGen/MachineOperand.h"
 #include "llvm/CodeGen/MachineRegionInfo.h"
 #include "llvm/CodeGen/MachineRegisterInfo.h"
-#include "llvm/CodeGen/TargetOpcodes.h"
 #include "llvm/CodeGen/TargetRegisterInfo.h"
-#include "llvm/Config/llvm-config.h"
-#include "llvm/IR/DebugLoc.h"
 #include "llvm/InitializePasses.h"
-#include "llvm/Pass.h"
-#include "llvm/Support/Compiler.h"
-#include "llvm/Support/Debug.h"
-#include "llvm/Support/ErrorHandling.h"
-#include "llvm/Support/raw_ostream.h"
-#include <cassert>
-#include <tuple>
-#include <utility>
 
 using namespace llvm;
 
diff --git a/llvm/lib/Target/AMDGPU/AMDGPUMachineFunction.h b/llvm/lib/Target/AMDGPU/AMDGPUMachineFunction.h
--- a/llvm/lib/Target/AMDGPU/AMDGPUMachineFunction.h
+++ b/llvm/lib/Target/AMDGPU/AMDGPUMachineFunction.h
@@ -12,7 +12,6 @@
 #include "Utils/AMDGPUBaseInfo.h"
 #include "llvm/ADT/DenseMap.h"
 #include "llvm/CodeGen/MachineFunction.h"
-#include "llvm/Support/Alignment.h"
 
 namespace llvm {
 
diff --git a/llvm/lib/Target/AMDGPU/AMDGPUMachineFunction.cpp b/llvm/lib/Target/AMDGPU/AMDGPUMachineFunction.cpp
--- a/llvm/lib/Target/AMDGPU/AMDGPUMachineFunction.cpp
+++ b/llvm/lib/Target/AMDGPU/AMDGPUMachineFunction.cpp
@@ -7,9 +7,10 @@
 //===----------------------------------------------------------------------===//
 
 #include "AMDGPUMachineFunction.h"
-#include "AMDGPUSubtarget.h"
 #include "AMDGPUPerfHintAnalysis.h"
+#include "AMDGPUSubtarget.h"
 #include "llvm/CodeGen/MachineModuleInfo.h"
+#include "llvm/Target/TargetMachine.h"
 
 using namespace llvm;
 
diff --git a/llvm/lib/Target/AMDGPU/AMDGPUMachineModuleInfo.h b/llvm/lib/Target/AMDGPU/AMDGPUMachineModuleInfo.h
--- a/llvm/lib/Target/AMDGPU/AMDGPUMachineModuleInfo.h
+++ b/llvm/lib/Target/AMDGPU/AMDGPUMachineModuleInfo.h
@@ -15,11 +15,7 @@
 #ifndef LLVM_LIB_TARGET_AMDGPU_AMDGPUMACHINEMODULEINFO_H
 #define LLVM_LIB_TARGET_AMDGPU_AMDGPUMACHINEMODULEINFO_H
 
-#include "llvm/ADT/None.h"
-#include "llvm/ADT/Optional.h"
-#include "llvm/CodeGen/MachineModuleInfo.h"
 #include "llvm/CodeGen/MachineModuleInfoImpls.h"
-#include "llvm/IR/LLVMContext.h"
 
 namespace llvm {
 
diff --git a/llvm/lib/Target/AMDGPU/AMDGPUMachineModuleInfo.cpp b/llvm/lib/Target/AMDGPU/AMDGPUMachineModuleInfo.cpp
--- a/llvm/lib/Target/AMDGPU/AMDGPUMachineModuleInfo.cpp
+++ b/llvm/lib/Target/AMDGPU/AMDGPUMachineModuleInfo.cpp
@@ -13,7 +13,6 @@
 //===----------------------------------------------------------------------===//
 
 #include "AMDGPUMachineModuleInfo.h"
-#include "llvm/IR/Module.h"
 
 namespace llvm {
 
diff --git a/llvm/lib/Target/AMDGPU/AMDGPUMacroFusion.h b/llvm/lib/Target/AMDGPU/AMDGPUMacroFusion.h
--- a/llvm/lib/Target/AMDGPU/AMDGPUMacroFusion.h
+++ b/llvm/lib/Target/AMDGPU/AMDGPUMacroFusion.h
@@ -6,7 +6,8 @@
 //
 //===----------------------------------------------------------------------===//
 
-#include "llvm/CodeGen/MachineScheduler.h"
+#include "llvm/CodeGen/ScheduleDAGMutation.h"
+#include <memory>
 
 namespace llvm {
 
diff --git a/llvm/lib/Target/AMDGPU/AMDGPUMacroFusion.cpp b/llvm/lib/Target/AMDGPU/AMDGPUMacroFusion.cpp
--- a/llvm/lib/Target/AMDGPU/AMDGPUMacroFusion.cpp
+++ b/llvm/lib/Target/AMDGPU/AMDGPUMacroFusion.cpp
@@ -13,8 +13,6 @@
 
 #include "AMDGPUMacroFusion.h"
 #include "AMDGPUSubtarget.h"
-#include "SIInstrInfo.h"
-#include "MCTargetDesc/AMDGPUMCTargetDesc.h"
 
 #include "llvm/CodeGen/MacroFusion.h"
 
diff --git a/llvm/lib/Target/AMDGPU/AMDGPUOpenCLEnqueuedBlockLowering.cpp b/llvm/lib/Target/AMDGPU/AMDGPUOpenCLEnqueuedBlockLowering.cpp
--- a/llvm/lib/Target/AMDGPU/AMDGPUOpenCLEnqueuedBlockLowering.cpp
+++ b/llvm/lib/Target/AMDGPU/AMDGPUOpenCLEnqueuedBlockLowering.cpp
@@ -34,16 +34,11 @@
 #include "AMDGPU.h"
 #include "llvm/ADT/DenseSet.h"
 #include "llvm/ADT/SmallString.h"
-#include "llvm/ADT/StringRef.h"
-#include "llvm/IR/Constants.h"
-#include "llvm/IR/DerivedTypes.h"
 #include "llvm/IR/Instructions.h"
 #include "llvm/IR/Mangler.h"
 #include "llvm/IR/Module.h"
-#include "llvm/IR/User.h"
 #include "llvm/Pass.h"
 #include "llvm/Support/Debug.h"
-#include "llvm/Support/raw_ostream.h"
 
 #define DEBUG_TYPE "amdgpu-lower-enqueued-block"
 
diff --git a/llvm/lib/Target/AMDGPU/AMDGPUPTNote.h b/llvm/lib/Target/AMDGPU/AMDGPUPTNote.h
--- a/llvm/lib/Target/AMDGPU/AMDGPUPTNote.h
+++ b/llvm/lib/Target/AMDGPU/AMDGPUPTNote.h
@@ -16,6 +16,7 @@
 #ifndef LLVM_LIB_TARGET_AMDGPU_AMDGPUPTNOTE_H
 #define LLVM_LIB_TARGET_AMDGPU_AMDGPUPTNOTE_H
 
+namespace llvm {
 namespace AMDGPU {
 
 namespace ElfNote {
@@ -41,7 +42,7 @@
     NT_AMDGPU_HSA_HLDEBUG_TARGET = 102
 };
 
-}
-}
-
+} // End namespace ElfNote
+} // End namespace AMDGPU
+} // End namespace llvm
 #endif // LLVM_LIB_TARGET_AMDGPU_AMDGPUNOTETYPE_H
diff --git a/llvm/lib/Target/AMDGPU/AMDGPUPerfHintAnalysis.h b/llvm/lib/Target/AMDGPU/AMDGPUPerfHintAnalysis.h
--- a/llvm/lib/Target/AMDGPU/AMDGPUPerfHintAnalysis.h
+++ b/llvm/lib/Target/AMDGPU/AMDGPUPerfHintAnalysis.h
@@ -17,7 +17,6 @@
 
 #include "llvm/Analysis/CallGraphSCCPass.h"
 #include "llvm/IR/ValueMap.h"
-#include "llvm/Pass.h"
 
 namespace llvm {
 
diff --git a/llvm/lib/Target/AMDGPU/AMDGPUPerfHintAnalysis.cpp b/llvm/lib/Target/AMDGPU/AMDGPUPerfHintAnalysis.cpp
--- a/llvm/lib/Target/AMDGPU/AMDGPUPerfHintAnalysis.cpp
+++ b/llvm/lib/Target/AMDGPU/AMDGPUPerfHintAnalysis.cpp
@@ -22,11 +22,7 @@
 #include "llvm/CodeGen/TargetLowering.h"
 #include "llvm/CodeGen/TargetPassConfig.h"
 #include "llvm/CodeGen/TargetSubtargetInfo.h"
-#include "llvm/IR/Constants.h"
 #include "llvm/IR/Instructions.h"
-#include "llvm/IR/IntrinsicInst.h"
-#include "llvm/IR/Module.h"
-#include "llvm/IR/ValueMap.h"
 #include "llvm/Support/CommandLine.h"
 #include "llvm/Target/TargetMachine.h"
 
diff --git a/llvm/lib/Target/AMDGPU/AMDGPUPostLegalizerCombiner.cpp b/llvm/lib/Target/AMDGPU/AMDGPUPostLegalizerCombiner.cpp
--- a/llvm/lib/Target/AMDGPU/AMDGPUPostLegalizerCombiner.cpp
+++ b/llvm/lib/Target/AMDGPU/AMDGPUPostLegalizerCombiner.cpp
@@ -11,18 +11,17 @@
 //
 //===----------------------------------------------------------------------===//
 
-#include "AMDGPUTargetMachine.h"
+#include "AMDGPU.h"
 #include "AMDGPULegalizerInfo.h"
+#include "AMDGPUSubtarget.h"
 #include "llvm/CodeGen/GlobalISel/Combiner.h"
 #include "llvm/CodeGen/GlobalISel/CombinerHelper.h"
 #include "llvm/CodeGen/GlobalISel/CombinerInfo.h"
 #include "llvm/CodeGen/GlobalISel/GISelKnownBits.h"
 #include "llvm/CodeGen/GlobalISel/MIPatternMatch.h"
 #include "llvm/CodeGen/MachineDominators.h"
-#include "llvm/CodeGen/MachineFunctionPass.h"
 #include "llvm/CodeGen/TargetPassConfig.h"
-#include "llvm/Support/Debug.h"
-#include "MCTargetDesc/AMDGPUMCTargetDesc.h"
+#include "llvm/Target/TargetMachine.h"
 
 #define DEBUG_TYPE "amdgpu-postlegalizer-combiner"
 
diff --git a/llvm/lib/Target/AMDGPU/AMDGPUPreLegalizerCombiner.cpp b/llvm/lib/Target/AMDGPU/AMDGPUPreLegalizerCombiner.cpp
--- a/llvm/lib/Target/AMDGPU/AMDGPUPreLegalizerCombiner.cpp
+++ b/llvm/lib/Target/AMDGPU/AMDGPUPreLegalizerCombiner.cpp
@@ -11,17 +11,15 @@
 //
 //===----------------------------------------------------------------------===//
 
-#include "AMDGPUTargetMachine.h"
+#include "AMDGPU.h"
 #include "llvm/CodeGen/GlobalISel/Combiner.h"
 #include "llvm/CodeGen/GlobalISel/CombinerHelper.h"
 #include "llvm/CodeGen/GlobalISel/CombinerInfo.h"
 #include "llvm/CodeGen/GlobalISel/GISelKnownBits.h"
 #include "llvm/CodeGen/GlobalISel/MIPatternMatch.h"
 #include "llvm/CodeGen/MachineDominators.h"
-#include "llvm/CodeGen/MachineFunctionPass.h"
 #include "llvm/CodeGen/TargetPassConfig.h"
-#include "llvm/Support/Debug.h"
-#include "MCTargetDesc/AMDGPUMCTargetDesc.h"
+#include "llvm/Target/TargetMachine.h"
 
 #define DEBUG_TYPE "amdgpu-prelegalizer-combiner"
 
diff --git a/llvm/lib/Target/AMDGPU/AMDGPUPrintfRuntimeBinding.cpp b/llvm/lib/Target/AMDGPU/AMDGPUPrintfRuntimeBinding.cpp
--- a/llvm/lib/Target/AMDGPU/AMDGPUPrintfRuntimeBinding.cpp
+++ b/llvm/lib/Target/AMDGPU/AMDGPUPrintfRuntimeBinding.cpp
@@ -19,27 +19,14 @@
 //===----------------------------------------------------------------------===//
 
 #include "AMDGPU.h"
-#include "llvm/ADT/SmallString.h"
-#include "llvm/ADT/StringExtras.h"
-#include "llvm/ADT/Triple.h"
 #include "llvm/Analysis/InstructionSimplify.h"
 #include "llvm/Analysis/TargetLibraryInfo.h"
-#include "llvm/CodeGen/Passes.h"
-#include "llvm/IR/Constants.h"
-#include "llvm/IR/DataLayout.h"
 #include "llvm/IR/Dominators.h"
-#include "llvm/IR/GlobalVariable.h"
 #include "llvm/IR/IRBuilder.h"
 #include "llvm/IR/Instructions.h"
-#include "llvm/IR/Module.h"
-#include "llvm/IR/PassManager.h"
-#include "llvm/IR/Type.h"
 #include "llvm/InitializePasses.h"
-#include "llvm/Support/CommandLine.h"
-#include "llvm/Support/Debug.h"
-#include "llvm/Support/ErrorHandling.h"
-#include "llvm/Support/raw_ostream.h"
 #include "llvm/Transforms/Utils/BasicBlockUtils.h"
+
 using namespace llvm;
 
 #define DEBUG_TYPE "printfToRuntime"
diff --git a/llvm/lib/Target/AMDGPU/AMDGPUPromoteAlloca.cpp b/llvm/lib/Target/AMDGPU/AMDGPUPromoteAlloca.cpp
--- a/llvm/lib/Target/AMDGPU/AMDGPUPromoteAlloca.cpp
+++ b/llvm/lib/Target/AMDGPU/AMDGPUPromoteAlloca.cpp
@@ -13,53 +13,14 @@
 
 #include "AMDGPU.h"
 #include "AMDGPUSubtarget.h"
-#include "Utils/AMDGPUBaseInfo.h"
-#include "llvm/ADT/APInt.h"
-#include "llvm/ADT/None.h"
-#include "llvm/ADT/STLExtras.h"
-#include "llvm/ADT/StringRef.h"
-#include "llvm/ADT/Triple.h"
-#include "llvm/ADT/Twine.h"
 #include "llvm/Analysis/CaptureTracking.h"
 #include "llvm/Analysis/ValueTracking.h"
 #include "llvm/CodeGen/TargetPassConfig.h"
-#include "llvm/IR/Attributes.h"
-#include "llvm/IR/BasicBlock.h"
-#include "llvm/IR/Constant.h"
-#include "llvm/IR/Constants.h"
-#include "llvm/IR/DataLayout.h"
-#include "llvm/IR/DerivedTypes.h"
-#include "llvm/IR/Function.h"
-#include "llvm/IR/GlobalValue.h"
-#include "llvm/IR/GlobalVariable.h"
 #include "llvm/IR/IRBuilder.h"
-#include "llvm/IR/Instruction.h"
-#include "llvm/IR/Instructions.h"
-#include "llvm/IR/IntrinsicInst.h"
-#include "llvm/IR/Intrinsics.h"
 #include "llvm/IR/IntrinsicsAMDGPU.h"
 #include "llvm/IR/IntrinsicsR600.h"
-#include "llvm/IR/LLVMContext.h"
-#include "llvm/IR/Metadata.h"
-#include "llvm/IR/Module.h"
-#include "llvm/IR/PassManager.h"
-#include "llvm/IR/Type.h"
-#include "llvm/IR/User.h"
-#include "llvm/IR/Value.h"
 #include "llvm/Pass.h"
-#include "llvm/Support/Casting.h"
-#include "llvm/Support/Debug.h"
-#include "llvm/Support/ErrorHandling.h"
-#include "llvm/Support/MathExtras.h"
-#include "llvm/Support/raw_ostream.h"
 #include "llvm/Target/TargetMachine.h"
-#include <algorithm>
-#include <cassert>
-#include <cstdint>
-#include <map>
-#include <tuple>
-#include <utility>
-#include <vector>
 
 #define DEBUG_TYPE "amdgpu-promote-alloca"
 
diff --git a/llvm/lib/Target/AMDGPU/AMDGPUPropagateAttributes.cpp b/llvm/lib/Target/AMDGPU/AMDGPUPropagateAttributes.cpp
--- a/llvm/lib/Target/AMDGPU/AMDGPUPropagateAttributes.cpp
+++ b/llvm/lib/Target/AMDGPU/AMDGPUPropagateAttributes.cpp
@@ -28,18 +28,10 @@
 
 #include "AMDGPU.h"
 #include "AMDGPUSubtarget.h"
-#include "MCTargetDesc/AMDGPUMCTargetDesc.h"
-#include "Utils/AMDGPUBaseInfo.h"
 #include "llvm/ADT/SmallSet.h"
-#include "llvm/ADT/SmallVector.h"
 #include "llvm/CodeGen/TargetPassConfig.h"
-#include "llvm/IR/Function.h"
-#include "llvm/IR/Module.h"
-#include "llvm/IR/PassManager.h"
 #include "llvm/Target/TargetMachine.h"
 #include "llvm/Transforms/Utils/Cloning.h"
-#include <string>
-
 #define DEBUG_TYPE "amdgpu-propagate-attributes"
 
 using namespace llvm;
diff --git a/llvm/lib/Target/AMDGPU/AMDGPURegBankCombiner.cpp b/llvm/lib/Target/AMDGPU/AMDGPURegBankCombiner.cpp
--- a/llvm/lib/Target/AMDGPU/AMDGPURegBankCombiner.cpp
+++ b/llvm/lib/Target/AMDGPU/AMDGPURegBankCombiner.cpp
@@ -11,19 +11,18 @@
 //
 //===----------------------------------------------------------------------===//
 
-#include "AMDGPUTargetMachine.h"
+#include "AMDGPU.h"
 #include "AMDGPULegalizerInfo.h"
+#include "AMDGPUSubtarget.h"
+#include "AMDGPUTargetMachine.h"
 #include "llvm/CodeGen/GlobalISel/Combiner.h"
 #include "llvm/CodeGen/GlobalISel/CombinerHelper.h"
 #include "llvm/CodeGen/GlobalISel/CombinerInfo.h"
 #include "llvm/CodeGen/GlobalISel/GISelKnownBits.h"
 #include "llvm/CodeGen/GlobalISel/MIPatternMatch.h"
 #include "llvm/CodeGen/MachineDominators.h"
-#include "llvm/CodeGen/MachineFunctionPass.h"
 #include "llvm/CodeGen/TargetPassConfig.h"
-#include "llvm/Support/Debug.h"
-#include "MCTargetDesc/AMDGPUMCTargetDesc.h"
-
+#include "llvm/Target/TargetMachine.h"
 #define DEBUG_TYPE "amdgpu-regbank-combiner"
 
 using namespace llvm;
diff --git a/llvm/lib/Target/AMDGPU/AMDGPURegisterBankInfo.h b/llvm/lib/Target/AMDGPU/AMDGPURegisterBankInfo.h
--- a/llvm/lib/Target/AMDGPU/AMDGPURegisterBankInfo.h
+++ b/llvm/lib/Target/AMDGPU/AMDGPURegisterBankInfo.h
@@ -20,7 +20,6 @@
 
 #define GET_REGBANK_DECLARATIONS
 #include "AMDGPUGenRegisterBank.inc"
-#undef GET_REGBANK_DECLARATIONS
 
 namespace llvm {
 
@@ -39,6 +38,7 @@
 #define GET_TARGET_REGBANK_CLASS
 #include "AMDGPUGenRegisterBank.inc"
 };
+
 class AMDGPURegisterBankInfo final : public AMDGPUGenRegisterBankInfo {
 public:
   const GCNSubtarget &Subtarget;
diff --git a/llvm/lib/Target/AMDGPU/AMDGPURegisterBankInfo.cpp b/llvm/lib/Target/AMDGPU/AMDGPURegisterBankInfo.cpp
--- a/llvm/lib/Target/AMDGPU/AMDGPURegisterBankInfo.cpp
+++ b/llvm/lib/Target/AMDGPU/AMDGPURegisterBankInfo.cpp
@@ -70,21 +70,17 @@
 
 #include "AMDGPURegisterBankInfo.h"
 
+#include "AMDGPU.h"
 #include "AMDGPUGlobalISelUtils.h"
 #include "AMDGPUInstrInfo.h"
 #include "AMDGPUSubtarget.h"
-#include "MCTargetDesc/AMDGPUMCTargetDesc.h"
 #include "SIMachineFunctionInfo.h"
 #include "SIRegisterInfo.h"
-#include "llvm/CodeGen/GlobalISel/LegalizationArtifactCombiner.h"
 #include "llvm/CodeGen/GlobalISel/LegalizerHelper.h"
 #include "llvm/CodeGen/GlobalISel/MIPatternMatch.h"
 #include "llvm/CodeGen/GlobalISel/MachineIRBuilder.h"
 #include "llvm/CodeGen/GlobalISel/RegisterBank.h"
-#include "llvm/CodeGen/GlobalISel/RegisterBankInfo.h"
-#include "llvm/CodeGen/TargetRegisterInfo.h"
-#include "llvm/CodeGen/TargetSubtargetInfo.h"
-#include "llvm/IR/Constants.h"
+#include "llvm/IR/IntrinsicsAMDGPU.h"
 
 #define GET_TARGET_REGBANK_IMPL
 #include "AMDGPUGenRegisterBank.inc"
diff --git a/llvm/lib/Target/AMDGPU/AMDGPURewriteOutArguments.cpp b/llvm/lib/Target/AMDGPU/AMDGPURewriteOutArguments.cpp
--- a/llvm/lib/Target/AMDGPU/AMDGPURewriteOutArguments.cpp
+++ b/llvm/lib/Target/AMDGPU/AMDGPURewriteOutArguments.cpp
@@ -43,35 +43,16 @@
 
 #include "AMDGPU.h"
 #include "Utils/AMDGPUBaseInfo.h"
-#include "llvm/ADT/DenseMap.h"
-#include "llvm/ADT/STLExtras.h"
 #include "llvm/ADT/SmallSet.h"
-#include "llvm/ADT/SmallVector.h"
 #include "llvm/ADT/Statistic.h"
 #include "llvm/Analysis/MemoryDependenceAnalysis.h"
-#include "llvm/Analysis/MemoryLocation.h"
-#include "llvm/IR/Argument.h"
-#include "llvm/IR/Attributes.h"
-#include "llvm/IR/BasicBlock.h"
-#include "llvm/IR/Constants.h"
-#include "llvm/IR/DataLayout.h"
-#include "llvm/IR/DerivedTypes.h"
-#include "llvm/IR/Function.h"
 #include "llvm/IR/IRBuilder.h"
 #include "llvm/IR/Instructions.h"
-#include "llvm/IR/Module.h"
-#include "llvm/IR/Type.h"
-#include "llvm/IR/Use.h"
-#include "llvm/IR/User.h"
-#include "llvm/IR/Value.h"
 #include "llvm/InitializePasses.h"
 #include "llvm/Pass.h"
-#include "llvm/Support/Casting.h"
 #include "llvm/Support/CommandLine.h"
 #include "llvm/Support/Debug.h"
 #include "llvm/Support/raw_ostream.h"
-#include <cassert>
-#include <utility>
 
 #define DEBUG_TYPE "amdgpu-rewrite-out-arguments"
 
diff --git a/llvm/lib/Target/AMDGPU/AMDGPUSubtarget.h b/llvm/lib/Target/AMDGPU/AMDGPUSubtarget.h
--- a/llvm/lib/Target/AMDGPU/AMDGPUSubtarget.h
+++ b/llvm/lib/Target/AMDGPU/AMDGPUSubtarget.h
@@ -14,7 +14,6 @@
 #ifndef LLVM_LIB_TARGET_AMDGPU_AMDGPUSUBTARGET_H
 #define LLVM_LIB_TARGET_AMDGPU_AMDGPUSUBTARGET_H
 
-#include "AMDGPU.h"
 #include "AMDGPUCallLowering.h"
 #include "MCTargetDesc/AMDGPUMCTargetDesc.h"
 #include "R600FrameLowering.h"
@@ -23,20 +22,17 @@
 #include "SIFrameLowering.h"
 #include "SIISelLowering.h"
 #include "SIInstrInfo.h"
-#include "Utils/AMDGPUBaseInfo.h"
 #include "llvm/ADT/Triple.h"
-#include "llvm/CodeGen/GlobalISel/InlineAsmLowering.h"
-#include "llvm/CodeGen/GlobalISel/InstructionSelector.h"
-#include "llvm/CodeGen/GlobalISel/LegalizerInfo.h"
-#include "llvm/CodeGen/GlobalISel/RegisterBankInfo.h"
-#include "llvm/CodeGen/MachineFunction.h"
 #include "llvm/CodeGen/SelectionDAGTargetInfo.h"
-#include "llvm/MC/MCInstrItineraries.h"
-#include "llvm/Support/MathExtras.h"
-#include <cassert>
-#include <cstdint>
-#include <memory>
-#include <utility>
+#include "llvm/IR/CallingConv.h"
+#include "llvm/Support/Alignment.h"
+
+namespace llvm {
+
+class MCInst;
+class MCInstrInfo;
+
+} // namespace llvm
 
 #define GET_SUBTARGETINFO_HEADER
 #include "AMDGPUGenSubtargetInfo.inc"
@@ -45,7 +41,12 @@
 
 namespace llvm {
 
+class Function;
+class Instruction;
+class MachineFunction;
 class StringRef;
+class TargetMachine;
+class GCNTargetMachine;
 
 class AMDGPUSubtarget {
 public:
@@ -135,9 +136,7 @@
     return TargetTriple.getOS() == Triple::Mesa3D;
   }
 
-  bool isMesaKernel(const Function &F) const {
-    return isMesa3DOS() && !AMDGPU::isShader(F.getCallingConv());
-  }
+  bool isMesaKernel(const Function &F) const;
 
   bool isAmdHsaOrMesa(const Function &F) const {
     return isAmdHsaOS() || isMesaKernel(F);
@@ -249,11 +248,7 @@
 
   /// \returns Number of bytes of arguments that are passed to a shader or
   /// kernel in addition to the explicit ones declared for the function.
-  unsigned getImplicitArgNumBytes(const Function &F) const {
-    if (isMesaKernel(F))
-      return 16;
-    return AMDGPU::getIntegerAttribute(F, "amdgpu-implicitarg-num-bytes", 0);
-  }
+  unsigned getImplicitArgNumBytes(const Function &F) const;
   uint64_t getExplicitKernArgSize(const Function &F, Align &MaxAlign) const;
   unsigned getKernArgSegmentSize(const Function &F, Align &MaxAlign) const;
 
diff --git a/llvm/lib/Target/AMDGPU/AMDGPUSubtarget.cpp b/llvm/lib/Target/AMDGPU/AMDGPUSubtarget.cpp
--- a/llvm/lib/Target/AMDGPU/AMDGPUSubtarget.cpp
+++ b/llvm/lib/Target/AMDGPU/AMDGPUSubtarget.cpp
@@ -13,18 +13,20 @@
 
 #include "AMDGPUSubtarget.h"
 #include "AMDGPU.h"
-#include "AMDGPUTargetMachine.h"
 #include "AMDGPUCallLowering.h"
 #include "AMDGPUInstructionSelector.h"
 #include "AMDGPULegalizerInfo.h"
 #include "AMDGPURegisterBankInfo.h"
+#include "AMDGPUTargetMachine.h"
 #include "SIMachineFunctionInfo.h"
-#include "MCTargetDesc/AMDGPUMCTargetDesc.h"
 #include "llvm/ADT/SmallString.h"
+#include "llvm/CodeGen/GlobalISel/InlineAsmLowering.h"
 #include "llvm/CodeGen/MachineScheduler.h"
-#include "llvm/MC/MCSubtargetInfo.h"
-#include "llvm/IR/MDBuilder.h"
 #include "llvm/CodeGen/TargetFrameLowering.h"
+#include "llvm/IR/IntrinsicsAMDGPU.h"
+#include "llvm/IR/IntrinsicsR600.h"
+#include "llvm/IR/MDBuilder.h"
+#include "llvm/MC/MCSubtargetInfo.h"
 #include <algorithm>
 
 using namespace llvm;
@@ -481,6 +483,10 @@
   return std::numeric_limits<unsigned>::max();
 }
 
+bool AMDGPUSubtarget::isMesaKernel(const Function &F) const {
+  return isMesa3DOS() && !AMDGPU::isShader(F.getCallingConv());
+}
+
 unsigned AMDGPUSubtarget::getMaxWorkitemID(const Function &Kernel,
                                            unsigned Dimension) const {
   unsigned ReqdSize = getReqdWorkGroupSize(Kernel, Dimension);
@@ -551,6 +557,12 @@
   return true;
 }
 
+unsigned AMDGPUSubtarget::getImplicitArgNumBytes(const Function &F) const {
+  if (isMesaKernel(F))
+    return 16;
+  return AMDGPU::getIntegerAttribute(F, "amdgpu-implicitarg-num-bytes", 0);
+}
+
 uint64_t AMDGPUSubtarget::getExplicitKernArgSize(const Function &F,
                                                  Align &MaxAlign) const {
   assert(F.getCallingConv() == CallingConv::AMDGPU_KERNEL ||
diff --git a/llvm/lib/Target/AMDGPU/AMDGPUTargetMachine.h b/llvm/lib/Target/AMDGPU/AMDGPUTargetMachine.h
--- a/llvm/lib/Target/AMDGPU/AMDGPUTargetMachine.h
+++ b/llvm/lib/Target/AMDGPU/AMDGPUTargetMachine.h
@@ -15,13 +15,7 @@
 #define LLVM_LIB_TARGET_AMDGPU_AMDGPUTARGETMACHINE_H
 
 #include "AMDGPUSubtarget.h"
-#include "llvm/ADT/Optional.h"
-#include "llvm/ADT/StringMap.h"
-#include "llvm/ADT/StringRef.h"
-#include "llvm/Analysis/TargetTransformInfo.h"
-#include "llvm/Support/CodeGen.h"
 #include "llvm/Target/TargetMachine.h"
-#include <memory>
 
 namespace llvm {
 
@@ -61,11 +55,7 @@
   void registerDefaultAliasAnalyses(AAManager &) override;
 
   /// Get the integer value of a null pointer in the given address space.
-  static int64_t getNullPointerValue(unsigned AddrSpace) {
-    return (AddrSpace == AMDGPUAS::LOCAL_ADDRESS ||
-            AddrSpace == AMDGPUAS::PRIVATE_ADDRESS ||
-            AddrSpace == AMDGPUAS::REGION_ADDRESS) ? -1 : 0;
-  }
+  static int64_t getNullPointerValue(unsigned AddrSpace);
 
   bool isNoopAddrSpaceCast(unsigned SrcAS, unsigned DestAS) const override;
 
diff --git a/llvm/lib/Target/AMDGPU/AMDGPUTargetMachine.cpp b/llvm/lib/Target/AMDGPU/AMDGPUTargetMachine.cpp
--- a/llvm/lib/Target/AMDGPU/AMDGPUTargetMachine.cpp
+++ b/llvm/lib/Target/AMDGPU/AMDGPUTargetMachine.cpp
@@ -15,16 +15,12 @@
 #include "AMDGPUTargetMachine.h"
 #include "AMDGPU.h"
 #include "AMDGPUAliasAnalysis.h"
-#include "AMDGPUCallLowering.h"
 #include "AMDGPUExportClustering.h"
-#include "AMDGPUInstructionSelector.h"
-#include "AMDGPULegalizerInfo.h"
 #include "AMDGPUMacroFusion.h"
 #include "AMDGPUTargetObjectFile.h"
 #include "AMDGPUTargetTransformInfo.h"
 #include "GCNIterativeScheduler.h"
 #include "GCNSchedStrategy.h"
-#include "MCTargetDesc/AMDGPUMCTargetDesc.h"
 #include "R600MachineScheduler.h"
 #include "SIMachineFunctionInfo.h"
 #include "SIMachineScheduler.h"
@@ -36,19 +32,12 @@
 #include "llvm/CodeGen/GlobalISel/Localizer.h"
 #include "llvm/CodeGen/GlobalISel/RegBankSelect.h"
 #include "llvm/CodeGen/MIRParser/MIParser.h"
-#include "llvm/CodeGen/Passes.h"
 #include "llvm/CodeGen/TargetPassConfig.h"
-#include "llvm/IR/Attributes.h"
-#include "llvm/IR/Function.h"
 #include "llvm/IR/LegacyPassManager.h"
 #include "llvm/IR/PassManager.h"
 #include "llvm/InitializePasses.h"
-#include "llvm/Pass.h"
 #include "llvm/Passes/PassBuilder.h"
-#include "llvm/Support/CommandLine.h"
-#include "llvm/Support/Compiler.h"
 #include "llvm/Support/TargetRegistry.h"
-#include "llvm/Target/TargetLoweringObjectFile.h"
 #include "llvm/Transforms/IPO.h"
 #include "llvm/Transforms/IPO/AlwaysInliner.h"
 #include "llvm/Transforms/IPO/GlobalDCE.h"
@@ -60,7 +49,6 @@
 #include "llvm/Transforms/Utils.h"
 #include "llvm/Transforms/Utils/SimplifyLibCalls.h"
 #include "llvm/Transforms/Vectorize.h"
-#include <memory>
 
 using namespace llvm;
 
@@ -652,6 +640,14 @@
   return I.get();
 }
 
+int64_t AMDGPUTargetMachine::getNullPointerValue(unsigned AddrSpace) {
+  return (AddrSpace == AMDGPUAS::LOCAL_ADDRESS ||
+          AddrSpace == AMDGPUAS::PRIVATE_ADDRESS ||
+          AddrSpace == AMDGPUAS::REGION_ADDRESS)
+             ? -1
+             : 0;
+}
+
 bool AMDGPUTargetMachine::isNoopAddrSpaceCast(unsigned SrcAS,
                                               unsigned DestAS) const {
   return AMDGPU::isFlatGlobalAddrSpace(SrcAS) &&
diff --git a/llvm/lib/Target/AMDGPU/AMDGPUTargetObjectFile.cpp b/llvm/lib/Target/AMDGPU/AMDGPUTargetObjectFile.cpp
--- a/llvm/lib/Target/AMDGPU/AMDGPUTargetObjectFile.cpp
+++ b/llvm/lib/Target/AMDGPU/AMDGPUTargetObjectFile.cpp
@@ -7,13 +7,10 @@
 //===----------------------------------------------------------------------===//
 
 #include "AMDGPUTargetObjectFile.h"
-#include "AMDGPU.h"
-#include "AMDGPUTargetMachine.h"
 #include "Utils/AMDGPUBaseInfo.h"
-#include "llvm/BinaryFormat/ELF.h"
-#include "llvm/MC/MCContext.h"
-#include "llvm/MC/MCSectionELF.h"
-
+#include "llvm/IR/GlobalObject.h"
+#include "llvm/MC/SectionKind.h"
+#include "llvm/Target/TargetMachine.h"
 using namespace llvm;
 
 //===----------------------------------------------------------------------===//
diff --git a/llvm/lib/Target/AMDGPU/AMDGPUTargetTransformInfo.h b/llvm/lib/Target/AMDGPU/AMDGPUTargetTransformInfo.h
--- a/llvm/lib/Target/AMDGPU/AMDGPUTargetTransformInfo.h
+++ b/llvm/lib/Target/AMDGPU/AMDGPUTargetTransformInfo.h
@@ -19,16 +19,7 @@
 
 #include "AMDGPU.h"
 #include "AMDGPUSubtarget.h"
-#include "AMDGPUTargetMachine.h"
-#include "MCTargetDesc/AMDGPUMCTargetDesc.h"
-#include "Utils/AMDGPUBaseInfo.h"
-#include "llvm/ADT/ArrayRef.h"
-#include "llvm/Analysis/TargetTransformInfo.h"
 #include "llvm/CodeGen/BasicTTIImpl.h"
-#include "llvm/IR/Function.h"
-#include "llvm/MC/SubtargetFeature.h"
-#include "llvm/Support/MathExtras.h"
-#include <cassert>
 
 namespace llvm {
 
@@ -54,11 +45,7 @@
   const TargetLoweringBase *getTLI() const { return TLI; }
 
 public:
-  explicit AMDGPUTTIImpl(const AMDGPUTargetMachine *TM, const Function &F)
-      : BaseT(TM, F.getParent()->getDataLayout()),
-        TargetTriple(TM->getTargetTriple()),
-        ST(static_cast<const GCNSubtarget *>(TM->getSubtargetImpl(F))),
-        TLI(ST->getTargetLowering()) {}
+  explicit AMDGPUTTIImpl(const AMDGPUTargetMachine *TM, const Function &F);
 
   void getUnrollingPreferences(Loop *L, ScalarEvolution &SE,
                                TTI::UnrollingPreferences &UP);
@@ -137,19 +124,7 @@
   }
 
 public:
-  explicit GCNTTIImpl(const AMDGPUTargetMachine *TM, const Function &F)
-      : BaseT(TM, F.getParent()->getDataLayout()),
-        ST(static_cast<const GCNSubtarget *>(TM->getSubtargetImpl(F))),
-        TLI(ST->getTargetLowering()), CommonTTI(TM, F),
-        IsGraphics(AMDGPU::isGraphics(F.getCallingConv())),
-        MaxVGPRs(ST->getMaxNumVGPRs(
-            std::max(ST->getWavesPerEU(F).first,
-                     ST->getWavesPerEUForWorkGroup(
-                         ST->getFlatWorkGroupSizes(F).second)))) {
-    AMDGPU::SIModeRegisterDefaults Mode(F);
-    HasFP32Denormals = Mode.allFP32Denormals();
-    HasFP64FP16Denormals = Mode.allFP64FP16Denormals();
-  }
+  explicit GCNTTIImpl(const AMDGPUTargetMachine *TM, const Function &F);
 
   bool hasBranchDivergence() { return true; }
   bool useGPUDivergenceAnalysis() const;
@@ -278,11 +253,7 @@
   AMDGPUTTIImpl CommonTTI;
 
 public:
-  explicit R600TTIImpl(const AMDGPUTargetMachine *TM, const Function &F)
-    : BaseT(TM, F.getParent()->getDataLayout()),
-      ST(static_cast<const R600Subtarget*>(TM->getSubtargetImpl(F))),
-      TLI(ST->getTargetLowering()),
-      CommonTTI(TM, F) {}
+  explicit R600TTIImpl(const AMDGPUTargetMachine *TM, const Function &F);
 
   const R600Subtarget *getST() const { return ST; }
   const AMDGPUTargetLowering *getTLI() const { return TLI; }
diff --git a/llvm/lib/Target/AMDGPU/AMDGPUTargetTransformInfo.cpp b/llvm/lib/Target/AMDGPU/AMDGPUTargetTransformInfo.cpp
--- a/llvm/lib/Target/AMDGPU/AMDGPUTargetTransformInfo.cpp
+++ b/llvm/lib/Target/AMDGPU/AMDGPUTargetTransformInfo.cpp
@@ -15,41 +15,12 @@
 //===----------------------------------------------------------------------===//
 
 #include "AMDGPUTargetTransformInfo.h"
-#include "AMDGPUSubtarget.h"
-#include "Utils/AMDGPUBaseInfo.h"
-#include "llvm/ADT/STLExtras.h"
+#include "AMDGPUTargetMachine.h"
 #include "llvm/Analysis/LoopInfo.h"
-#include "llvm/Analysis/TargetTransformInfo.h"
 #include "llvm/Analysis/ValueTracking.h"
-#include "llvm/CodeGen/ISDOpcodes.h"
-#include "llvm/CodeGen/ValueTypes.h"
-#include "llvm/IR/Argument.h"
-#include "llvm/IR/Attributes.h"
-#include "llvm/IR/BasicBlock.h"
-#include "llvm/IR/CallingConv.h"
-#include "llvm/IR/DataLayout.h"
-#include "llvm/IR/DerivedTypes.h"
-#include "llvm/IR/Function.h"
-#include "llvm/IR/Instruction.h"
-#include "llvm/IR/Instructions.h"
-#include "llvm/IR/IntrinsicInst.h"
-#include "llvm/IR/Module.h"
+#include "llvm/IR/IntrinsicsAMDGPU.h"
 #include "llvm/IR/PatternMatch.h"
-#include "llvm/IR/Type.h"
-#include "llvm/IR/Value.h"
-#include "llvm/MC/SubtargetFeature.h"
-#include "llvm/Support/Casting.h"
-#include "llvm/Support/CommandLine.h"
-#include "llvm/Support/Debug.h"
-#include "llvm/Support/ErrorHandling.h"
 #include "llvm/Support/KnownBits.h"
-#include "llvm/Support/MachineValueType.h"
-#include "llvm/Support/raw_ostream.h"
-#include "llvm/Target/TargetMachine.h"
-#include <algorithm>
-#include <cassert>
-#include <limits>
-#include <utility>
 
 using namespace llvm;
 
@@ -104,6 +75,12 @@
   return false;
 }
 
+AMDGPUTTIImpl::AMDGPUTTIImpl(const AMDGPUTargetMachine *TM, const Function &F)
+    : BaseT(TM, F.getParent()->getDataLayout()),
+      TargetTriple(TM->getTargetTriple()),
+      ST(static_cast<const GCNSubtarget *>(TM->getSubtargetImpl(F))),
+      TLI(ST->getTargetLowering()) {}
+
 void AMDGPUTTIImpl::getUnrollingPreferences(Loop *L, ScalarEvolution &SE,
                                             TTI::UnrollingPreferences &UP) {
   const Function &F = *L->getHeader()->getParent();
@@ -261,6 +238,21 @@
                                           TTI::PeelingPreferences &PP) {
   BaseT::getPeelingPreferences(L, SE, PP);
 }
+
+GCNTTIImpl::GCNTTIImpl(const AMDGPUTargetMachine *TM, const Function &F)
+    : BaseT(TM, F.getParent()->getDataLayout()),
+      ST(static_cast<const GCNSubtarget *>(TM->getSubtargetImpl(F))),
+      TLI(ST->getTargetLowering()), CommonTTI(TM, F),
+      IsGraphics(AMDGPU::isGraphics(F.getCallingConv())),
+      MaxVGPRs(ST->getMaxNumVGPRs(
+          std::max(ST->getWavesPerEU(F).first,
+                   ST->getWavesPerEUForWorkGroup(
+                       ST->getFlatWorkGroupSizes(F).second)))) {
+  AMDGPU::SIModeRegisterDefaults Mode(F);
+  HasFP32Denormals = Mode.allFP32Denormals();
+  HasFP64FP16Denormals = Mode.allFP64FP16Denormals();
+}
+
 unsigned GCNTTIImpl::getHardwareNumberOfRegisters(bool Vec) const {
   // The concept of vector registers doesn't really exist. Some packed vector
   // operations operate on the normal 32-bit registers.
@@ -1121,6 +1113,11 @@
   CommonTTI.getPeelingPreferences(L, SE, PP);
 }
 
+R600TTIImpl::R600TTIImpl(const AMDGPUTargetMachine *TM, const Function &F)
+    : BaseT(TM, F.getParent()->getDataLayout()),
+      ST(static_cast<const R600Subtarget *>(TM->getSubtargetImpl(F))),
+      TLI(ST->getTargetLowering()), CommonTTI(TM, F) {}
+
 unsigned R600TTIImpl::getHardwareNumberOfRegisters(bool Vec) const {
   return 4 * 128; // XXX - 4 channels. Should these count as vector instead?
 }
diff --git a/llvm/lib/Target/AMDGPU/AMDGPUUnifyDivergentExitNodes.cpp b/llvm/lib/Target/AMDGPU/AMDGPUUnifyDivergentExitNodes.cpp
--- a/llvm/lib/Target/AMDGPU/AMDGPUUnifyDivergentExitNodes.cpp
+++ b/llvm/lib/Target/AMDGPU/AMDGPUUnifyDivergentExitNodes.cpp
@@ -38,6 +38,7 @@
 #include "llvm/IR/InstrTypes.h"
 #include "llvm/IR/Instructions.h"
 #include "llvm/IR/Intrinsics.h"
+#include "llvm/IR/IntrinsicsAMDGPU.h"
 #include "llvm/IR/Type.h"
 #include "llvm/InitializePasses.h"
 #include "llvm/Pass.h"
diff --git a/llvm/lib/Target/AMDGPU/AMDGPUUnifyMetadata.cpp b/llvm/lib/Target/AMDGPU/AMDGPUUnifyMetadata.cpp
--- a/llvm/lib/Target/AMDGPU/AMDGPUUnifyMetadata.cpp
+++ b/llvm/lib/Target/AMDGPU/AMDGPUUnifyMetadata.cpp
@@ -12,15 +12,10 @@
 //===----------------------------------------------------------------------===//
 
 #include "AMDGPU.h"
-#include "llvm/ADT/SmallVector.h"
-#include "llvm/ADT/StringRef.h"
 #include "llvm/IR/Constants.h"
-#include "llvm/IR/Metadata.h"
 #include "llvm/IR/Module.h"
 #include "llvm/IR/PassManager.h"
 #include "llvm/Pass.h"
-#include <algorithm>
-#include <cassert>
 
 using namespace llvm;
 
diff --git a/llvm/lib/Target/AMDGPU/AMDILCFGStructurizer.cpp b/llvm/lib/Target/AMDGPU/AMDILCFGStructurizer.cpp
--- a/llvm/lib/Target/AMDGPU/AMDILCFGStructurizer.cpp
+++ b/llvm/lib/Target/AMDGPU/AMDILCFGStructurizer.cpp
@@ -8,41 +8,15 @@
 
 #include "AMDGPU.h"
 #include "AMDGPUSubtarget.h"
-#include "MCTargetDesc/AMDGPUMCTargetDesc.h"
-#include "R600InstrInfo.h"
 #include "R600RegisterInfo.h"
-#include "llvm/ADT/DepthFirstIterator.h"
 #include "llvm/ADT/SCCIterator.h"
-#include "llvm/ADT/SmallPtrSet.h"
-#include "llvm/ADT/SmallVector.h"
 #include "llvm/ADT/Statistic.h"
-#include "llvm/ADT/StringRef.h"
-#include "llvm/CodeGen/MachineBasicBlock.h"
-#include "llvm/CodeGen/MachineDominators.h"
 #include "llvm/CodeGen/MachineFunction.h"
 #include "llvm/CodeGen/MachineFunctionPass.h"
-#include "llvm/CodeGen/MachineInstr.h"
-#include "llvm/CodeGen/MachineInstrBuilder.h"
 #include "llvm/CodeGen/MachineJumpTableInfo.h"
 #include "llvm/CodeGen/MachineLoopInfo.h"
-#include "llvm/CodeGen/MachineOperand.h"
 #include "llvm/CodeGen/MachinePostDominators.h"
-#include "llvm/CodeGen/MachineRegisterInfo.h"
-#include "llvm/IR/DebugLoc.h"
-#include "llvm/IR/LLVMContext.h"
 #include "llvm/InitializePasses.h"
-#include "llvm/Pass.h"
-#include "llvm/Support/Debug.h"
-#include "llvm/Support/ErrorHandling.h"
-#include "llvm/Support/MachineValueType.h"
-#include "llvm/Support/raw_ostream.h"
-#include <cassert>
-#include <cstddef>
-#include <deque>
-#include <iterator>
-#include <map>
-#include <utility>
-#include <vector>
 
 using namespace llvm;
 
diff --git a/llvm/lib/Target/AMDGPU/AMDKernelCodeT.h b/llvm/lib/Target/AMDGPU/AMDKernelCodeT.h
--- a/llvm/lib/Target/AMDGPU/AMDKernelCodeT.h
+++ b/llvm/lib/Target/AMDGPU/AMDKernelCodeT.h
@@ -11,12 +11,8 @@
 #ifndef AMDKERNELCODET_H
 #define AMDKERNELCODET_H
 
-#include "llvm/MC/SubtargetFeature.h"
-
-#include <cstddef>
 #include <cstdint>
 
-#include "llvm/Support/Debug.h"
 //---------------------------------------------------------------------------//
 // AMD Kernel Code, and its dependencies                                     //
 //---------------------------------------------------------------------------//
@@ -527,7 +523,7 @@
 /// the kernarg segment is constant for the duration of the kernel execution.
 ///
 
-typedef struct amd_kernel_code_s {
+struct amd_kernel_code_t {
   uint32_t amd_kernel_code_version_major;
   uint32_t amd_kernel_code_version_minor;
   uint16_t amd_machine_kind;
@@ -650,6 +646,6 @@
   uint8_t reserved3[12];
   uint64_t runtime_loader_kernel_symbol;
   uint64_t control_directives[16];
-} amd_kernel_code_t;
+};
 
 #endif // AMDKERNELCODET_H
diff --git a/llvm/lib/Target/AMDGPU/AsmParser/AMDGPUAsmParser.cpp b/llvm/lib/Target/AMDGPU/AsmParser/AMDGPUAsmParser.cpp
--- a/llvm/lib/Target/AMDGPU/AsmParser/AMDGPUAsmParser.cpp
+++ b/llvm/lib/Target/AMDGPU/AsmParser/AMDGPUAsmParser.cpp
@@ -6,7 +6,6 @@
 //
 //===----------------------------------------------------------------------===//
 
-#include "AMDGPU.h"
 #include "AMDKernelCodeT.h"
 #include "MCTargetDesc/AMDGPUMCTargetDesc.h"
 #include "MCTargetDesc/AMDGPUTargetStreamer.h"
@@ -17,49 +16,23 @@
 #include "Utils/AMDGPUBaseInfo.h"
 #include "Utils/AMDKernelCodeTUtils.h"
 #include "llvm/ADT/APFloat.h"
-#include "llvm/ADT/APInt.h"
-#include "llvm/ADT/ArrayRef.h"
-#include "llvm/ADT/STLExtras.h"
 #include "llvm/ADT/SmallBitVector.h"
-#include "llvm/ADT/SmallString.h"
-#include "llvm/ADT/StringRef.h"
-#include "llvm/ADT/StringSwitch.h"
+#include "llvm/ADT/StringSet.h"
 #include "llvm/ADT/Twine.h"
-#include "llvm/BinaryFormat/ELF.h"
 #include "llvm/MC/MCAsmInfo.h"
 #include "llvm/MC/MCContext.h"
 #include "llvm/MC/MCExpr.h"
 #include "llvm/MC/MCInst.h"
-#include "llvm/MC/MCInstrDesc.h"
-#include "llvm/MC/MCInstrInfo.h"
-#include "llvm/MC/MCParser/MCAsmLexer.h"
 #include "llvm/MC/MCParser/MCAsmParser.h"
-#include "llvm/MC/MCParser/MCAsmParserExtension.h"
 #include "llvm/MC/MCParser/MCParsedAsmOperand.h"
 #include "llvm/MC/MCParser/MCTargetAsmParser.h"
-#include "llvm/MC/MCRegisterInfo.h"
-#include "llvm/MC/MCStreamer.h"
-#include "llvm/MC/MCSubtargetInfo.h"
 #include "llvm/MC/MCSymbol.h"
 #include "llvm/Support/AMDGPUMetadata.h"
 #include "llvm/Support/AMDHSAKernelDescriptor.h"
 #include "llvm/Support/Casting.h"
-#include "llvm/Support/Compiler.h"
-#include "llvm/Support/Error.h"
 #include "llvm/Support/MachineValueType.h"
-#include "llvm/Support/MathExtras.h"
-#include "llvm/Support/SMLoc.h"
 #include "llvm/Support/TargetParser.h"
 #include "llvm/Support/TargetRegistry.h"
-#include "llvm/Support/raw_ostream.h"
-#include <algorithm>
-#include <cassert>
-#include <cstdint>
-#include <cstring>
-#include <iterator>
-#include <map>
-#include <memory>
-#include <string>
 
 using namespace llvm;
 using namespace llvm::AMDGPU;
diff --git a/llvm/lib/Target/AMDGPU/Disassembler/AMDGPUDisassembler.h b/llvm/lib/Target/AMDGPU/Disassembler/AMDGPUDisassembler.h
--- a/llvm/lib/Target/AMDGPU/Disassembler/AMDGPUDisassembler.h
+++ b/llvm/lib/Target/AMDGPU/Disassembler/AMDGPUDisassembler.h
@@ -15,16 +15,9 @@
 #ifndef LLVM_LIB_TARGET_AMDGPU_DISASSEMBLER_AMDGPUDISASSEMBLER_H
 #define LLVM_LIB_TARGET_AMDGPU_DISASSEMBLER_AMDGPUDISASSEMBLER_H
 
-#include "llvm/ADT/ArrayRef.h"
-#include "llvm/MC/MCContext.h"
 #include "llvm/MC/MCDisassembler/MCDisassembler.h"
-#include "llvm/MC/MCDisassembler/MCRelocationInfo.h"
-#include "llvm/MC/MCDisassembler/MCSymbolizer.h"
 #include "llvm/MC/MCInstrInfo.h"
 #include "llvm/Support/DataExtractor.h"
-
-#include <algorithm>
-#include <cstdint>
 #include <memory>
 
 namespace llvm {
diff --git a/llvm/lib/Target/AMDGPU/Disassembler/AMDGPUDisassembler.cpp b/llvm/lib/Target/AMDGPU/Disassembler/AMDGPUDisassembler.cpp
--- a/llvm/lib/Target/AMDGPU/Disassembler/AMDGPUDisassembler.cpp
+++ b/llvm/lib/Target/AMDGPU/Disassembler/AMDGPUDisassembler.cpp
@@ -17,36 +17,16 @@
 // ToDo: What to do with instruction suffixes (v_mov_b32 vs v_mov_b32_e32)?
 
 #include "Disassembler/AMDGPUDisassembler.h"
-#include "AMDGPU.h"
 #include "MCTargetDesc/AMDGPUMCTargetDesc.h"
-#include "SIDefines.h"
 #include "TargetInfo/AMDGPUTargetInfo.h"
 #include "Utils/AMDGPUBaseInfo.h"
-#include "llvm-c/Disassembler.h"
-#include "llvm/ADT/APInt.h"
-#include "llvm/ADT/ArrayRef.h"
-#include "llvm/ADT/Twine.h"
-#include "llvm/BinaryFormat/ELF.h"
+#include "llvm-c/DisassemblerTypes.h"
 #include "llvm/MC/MCAsmInfo.h"
 #include "llvm/MC/MCContext.h"
-#include "llvm/MC/MCDisassembler/MCDisassembler.h"
 #include "llvm/MC/MCExpr.h"
 #include "llvm/MC/MCFixedLenDisassembler.h"
-#include "llvm/MC/MCInst.h"
-#include "llvm/MC/MCSubtargetInfo.h"
 #include "llvm/Support/AMDHSAKernelDescriptor.h"
-#include "llvm/Support/Endian.h"
-#include "llvm/Support/ErrorHandling.h"
-#include "llvm/Support/MathExtras.h"
 #include "llvm/Support/TargetRegistry.h"
-#include "llvm/Support/raw_ostream.h"
-#include <algorithm>
-#include <cassert>
-#include <cstddef>
-#include <cstdint>
-#include <iterator>
-#include <tuple>
-#include <vector>
 
 using namespace llvm;
 
diff --git a/llvm/lib/Target/AMDGPU/GCNDPPCombine.cpp b/llvm/lib/Target/AMDGPU/GCNDPPCombine.cpp
--- a/llvm/lib/Target/AMDGPU/GCNDPPCombine.cpp
+++ b/llvm/lib/Target/AMDGPU/GCNDPPCombine.cpp
@@ -39,21 +39,8 @@
 
 #include "AMDGPU.h"
 #include "AMDGPUSubtarget.h"
-#include "SIInstrInfo.h"
-#include "MCTargetDesc/AMDGPUMCTargetDesc.h"
-#include "llvm/ADT/DenseMap.h"
-#include "llvm/ADT/SmallVector.h"
 #include "llvm/ADT/Statistic.h"
-#include "llvm/CodeGen/MachineBasicBlock.h"
-#include "llvm/CodeGen/MachineFunction.h"
 #include "llvm/CodeGen/MachineFunctionPass.h"
-#include "llvm/CodeGen/MachineInstr.h"
-#include "llvm/CodeGen/MachineInstrBuilder.h"
-#include "llvm/CodeGen/MachineOperand.h"
-#include "llvm/CodeGen/MachineRegisterInfo.h"
-#include "llvm/CodeGen/TargetRegisterInfo.h"
-#include "llvm/Pass.h"
-#include <cassert>
 
 using namespace llvm;
 
diff --git a/llvm/lib/Target/AMDGPU/GCNHazardRecognizer.cpp b/llvm/lib/Target/AMDGPU/GCNHazardRecognizer.cpp
--- a/llvm/lib/Target/AMDGPU/GCNHazardRecognizer.cpp
+++ b/llvm/lib/Target/AMDGPU/GCNHazardRecognizer.cpp
@@ -12,24 +12,9 @@
 
 #include "GCNHazardRecognizer.h"
 #include "AMDGPUSubtarget.h"
-#include "SIDefines.h"
-#include "SIInstrInfo.h"
-#include "SIRegisterInfo.h"
-#include "MCTargetDesc/AMDGPUMCTargetDesc.h"
-#include "Utils/AMDGPUBaseInfo.h"
-#include "llvm/ADT/iterator_range.h"
 #include "llvm/CodeGen/MachineFunction.h"
-#include "llvm/CodeGen/MachineInstr.h"
-#include "llvm/CodeGen/MachineInstrBuilder.h"
-#include "llvm/CodeGen/MachineOperand.h"
 #include "llvm/CodeGen/ScheduleDAG.h"
-#include "llvm/MC/MCInstrDesc.h"
-#include "llvm/Support/ErrorHandling.h"
-#include <algorithm>
-#include <cassert>
-#include <limits>
-#include <set>
-#include <vector>
+#include "llvm/Support/TargetParser.h"
 
 using namespace llvm;
 
diff --git a/llvm/lib/Target/AMDGPU/GCNILPSched.cpp b/llvm/lib/Target/AMDGPU/GCNILPSched.cpp
--- a/llvm/lib/Target/AMDGPU/GCNILPSched.cpp
+++ b/llvm/lib/Target/AMDGPU/GCNILPSched.cpp
@@ -11,7 +11,6 @@
 //===----------------------------------------------------------------------===//
 
 #include "llvm/CodeGen/ScheduleDAG.h"
-#include "llvm/Support/Debug.h"
 
 using namespace llvm;
 
diff --git a/llvm/lib/Target/AMDGPU/GCNIterativeScheduler.h b/llvm/lib/Target/AMDGPU/GCNIterativeScheduler.h
--- a/llvm/lib/Target/AMDGPU/GCNIterativeScheduler.h
+++ b/llvm/lib/Target/AMDGPU/GCNIterativeScheduler.h
@@ -18,13 +18,7 @@
 #define LLVM_LIB_TARGET_AMDGPU_GCNITERATIVESCHEDULER_H
 
 #include "GCNRegPressure.h"
-#include "llvm/ADT/ArrayRef.h"
-#include "llvm/CodeGen/MachineBasicBlock.h"
 #include "llvm/CodeGen/MachineScheduler.h"
-#include "llvm/Support/Allocator.h"
-#include <limits>
-#include <memory>
-#include <vector>
 
 namespace llvm {
 
diff --git a/llvm/lib/Target/AMDGPU/GCNIterativeScheduler.cpp b/llvm/lib/Target/AMDGPU/GCNIterativeScheduler.cpp
--- a/llvm/lib/Target/AMDGPU/GCNIterativeScheduler.cpp
+++ b/llvm/lib/Target/AMDGPU/GCNIterativeScheduler.cpp
@@ -13,28 +13,8 @@
 
 #include "GCNIterativeScheduler.h"
 #include "AMDGPUSubtarget.h"
-#include "GCNRegPressure.h"
 #include "GCNSchedStrategy.h"
 #include "SIMachineFunctionInfo.h"
-#include "llvm/ADT/ArrayRef.h"
-#include "llvm/ADT/STLExtras.h"
-#include "llvm/ADT/SmallVector.h"
-#include "llvm/CodeGen/LiveIntervals.h"
-#include "llvm/CodeGen/MachineBasicBlock.h"
-#include "llvm/CodeGen/MachineFunction.h"
-#include "llvm/CodeGen/RegisterPressure.h"
-#include "llvm/CodeGen/ScheduleDAG.h"
-#include "llvm/Config/llvm-config.h"
-#include "llvm/Support/Compiler.h"
-#include "llvm/Support/Debug.h"
-#include "llvm/Support/raw_ostream.h"
-#include <algorithm>
-#include <cassert>
-#include <iterator>
-#include <limits>
-#include <memory>
-#include <type_traits>
-#include <vector>
 
 using namespace llvm;
 
diff --git a/llvm/lib/Target/AMDGPU/GCNMinRegStrategy.cpp b/llvm/lib/Target/AMDGPU/GCNMinRegStrategy.cpp
--- a/llvm/lib/Target/AMDGPU/GCNMinRegStrategy.cpp
+++ b/llvm/lib/Target/AMDGPU/GCNMinRegStrategy.cpp
@@ -13,20 +13,7 @@
 ///
 //===----------------------------------------------------------------------===//
 
-#include "llvm/ADT/ArrayRef.h"
-#include "llvm/ADT/SmallPtrSet.h"
-#include "llvm/ADT/SmallVector.h"
-#include "llvm/ADT/ilist_node.h"
-#include "llvm/ADT/simple_ilist.h"
 #include "llvm/CodeGen/ScheduleDAG.h"
-#include "llvm/Support/Allocator.h"
-#include "llvm/Support/Debug.h"
-#include "llvm/Support/raw_ostream.h"
-#include <cassert>
-#include <cstdint>
-#include <limits>
-#include <vector>
-
 using namespace llvm;
 
 #define DEBUG_TYPE "machine-scheduler"
diff --git a/llvm/lib/Target/AMDGPU/GCNNSAReassign.cpp b/llvm/lib/Target/AMDGPU/GCNNSAReassign.cpp
--- a/llvm/lib/Target/AMDGPU/GCNNSAReassign.cpp
+++ b/llvm/lib/Target/AMDGPU/GCNNSAReassign.cpp
@@ -15,17 +15,12 @@
 
 #include "AMDGPU.h"
 #include "AMDGPUSubtarget.h"
-#include "SIInstrInfo.h"
 #include "SIMachineFunctionInfo.h"
 #include "llvm/ADT/Statistic.h"
-#include "llvm/CodeGen/LiveInterval.h"
 #include "llvm/CodeGen/LiveIntervals.h"
 #include "llvm/CodeGen/LiveRegMatrix.h"
 #include "llvm/CodeGen/MachineFunctionPass.h"
-#include "llvm/CodeGen/VirtRegMap.h"
 #include "llvm/InitializePasses.h"
-#include "llvm/Support/MathExtras.h"
-#include <algorithm>
 
 using namespace llvm;
 
diff --git a/llvm/lib/Target/AMDGPU/GCNRegBankReassign.cpp b/llvm/lib/Target/AMDGPU/GCNRegBankReassign.cpp
--- a/llvm/lib/Target/AMDGPU/GCNRegBankReassign.cpp
+++ b/llvm/lib/Target/AMDGPU/GCNRegBankReassign.cpp
@@ -32,20 +32,14 @@
 
 #include "AMDGPU.h"
 #include "AMDGPUSubtarget.h"
-#include "MCTargetDesc/AMDGPUMCTargetDesc.h"
-#include "SIInstrInfo.h"
 #include "SIMachineFunctionInfo.h"
-#include "Utils/AMDGPUBaseInfo.h"
 #include "llvm/ADT/SmallSet.h"
 #include "llvm/ADT/Statistic.h"
-#include "llvm/CodeGen/LiveInterval.h"
 #include "llvm/CodeGen/LiveIntervals.h"
 #include "llvm/CodeGen/LiveRegMatrix.h"
 #include "llvm/CodeGen/MachineFunctionPass.h"
 #include "llvm/CodeGen/MachineLoopInfo.h"
-#include "llvm/CodeGen/VirtRegMap.h"
 #include "llvm/InitializePasses.h"
-#include "llvm/Support/MathExtras.h"
 
 using namespace llvm;
 
diff --git a/llvm/lib/Target/AMDGPU/GCNRegPressure.h b/llvm/lib/Target/AMDGPU/GCNRegPressure.h
--- a/llvm/lib/Target/AMDGPU/GCNRegPressure.h
+++ b/llvm/lib/Target/AMDGPU/GCNRegPressure.h
@@ -18,20 +18,14 @@
 #define LLVM_LIB_TARGET_AMDGPU_GCNREGPRESSURE_H
 
 #include "AMDGPUSubtarget.h"
-#include "llvm/ADT/DenseMap.h"
 #include "llvm/CodeGen/LiveIntervals.h"
-#include "llvm/CodeGen/MachineBasicBlock.h"
-#include "llvm/CodeGen/MachineInstr.h"
-#include "llvm/CodeGen/SlotIndexes.h"
-#include "llvm/MC/LaneBitmask.h"
-#include "llvm/Support/Debug.h"
 #include <algorithm>
-#include <limits>
 
 namespace llvm {
 
 class MachineRegisterInfo;
 class raw_ostream;
+class SlotIndex;
 
 struct GCNRegPressure {
   enum RegKind {
diff --git a/llvm/lib/Target/AMDGPU/GCNRegPressure.cpp b/llvm/lib/Target/AMDGPU/GCNRegPressure.cpp
--- a/llvm/lib/Target/AMDGPU/GCNRegPressure.cpp
+++ b/llvm/lib/Target/AMDGPU/GCNRegPressure.cpp
@@ -13,24 +13,7 @@
 
 #include "GCNRegPressure.h"
 #include "AMDGPUSubtarget.h"
-#include "SIRegisterInfo.h"
-#include "llvm/ADT/SmallVector.h"
-#include "llvm/CodeGen/LiveInterval.h"
-#include "llvm/CodeGen/LiveIntervals.h"
-#include "llvm/CodeGen/MachineInstr.h"
-#include "llvm/CodeGen/MachineOperand.h"
-#include "llvm/CodeGen/MachineRegisterInfo.h"
 #include "llvm/CodeGen/RegisterPressure.h"
-#include "llvm/CodeGen/SlotIndexes.h"
-#include "llvm/CodeGen/TargetRegisterInfo.h"
-#include "llvm/Config/llvm-config.h"
-#include "llvm/MC/LaneBitmask.h"
-#include "llvm/Support/Compiler.h"
-#include "llvm/Support/Debug.h"
-#include "llvm/Support/ErrorHandling.h"
-#include "llvm/Support/raw_ostream.h"
-#include <algorithm>
-#include <cassert>
 
 using namespace llvm;
 
diff --git a/llvm/lib/Target/AMDGPU/GCNSchedStrategy.cpp b/llvm/lib/Target/AMDGPU/GCNSchedStrategy.cpp
--- a/llvm/lib/Target/AMDGPU/GCNSchedStrategy.cpp
+++ b/llvm/lib/Target/AMDGPU/GCNSchedStrategy.cpp
@@ -13,12 +13,7 @@
 
 #include "GCNSchedStrategy.h"
 #include "AMDGPUSubtarget.h"
-#include "SIInstrInfo.h"
 #include "SIMachineFunctionInfo.h"
-#include "SIRegisterInfo.h"
-#include "Utils/AMDGPUBaseInfo.h"
-#include "llvm/CodeGen/RegisterClassInfo.h"
-#include "llvm/Support/MathExtras.h"
 
 #define DEBUG_TYPE "machine-scheduler"
 
diff --git a/llvm/lib/Target/AMDGPU/MCTargetDesc/AMDGPUAsmBackend.cpp b/llvm/lib/Target/AMDGPU/MCTargetDesc/AMDGPUAsmBackend.cpp
--- a/llvm/lib/Target/AMDGPU/MCTargetDesc/AMDGPUAsmBackend.cpp
+++ b/llvm/lib/Target/AMDGPU/MCTargetDesc/AMDGPUAsmBackend.cpp
@@ -9,17 +9,14 @@
 
 #include "MCTargetDesc/AMDGPUFixupKinds.h"
 #include "MCTargetDesc/AMDGPUMCTargetDesc.h"
-#include "llvm/ADT/StringRef.h"
-#include "llvm/BinaryFormat/ELF.h"
+#include "Utils/AMDGPUBaseInfo.h"
 #include "llvm/MC/MCAsmBackend.h"
 #include "llvm/MC/MCAssembler.h"
 #include "llvm/MC/MCContext.h"
 #include "llvm/MC/MCFixupKindInfo.h"
 #include "llvm/MC/MCObjectWriter.h"
-#include "llvm/MC/MCValue.h"
 #include "llvm/Support/EndianStream.h"
 #include "llvm/Support/TargetRegistry.h"
-#include "Utils/AMDGPUBaseInfo.h"
 
 using namespace llvm;
 using namespace llvm::AMDGPU;
diff --git a/llvm/lib/Target/AMDGPU/MCTargetDesc/AMDGPUELFObjectWriter.cpp b/llvm/lib/Target/AMDGPU/MCTargetDesc/AMDGPUELFObjectWriter.cpp
--- a/llvm/lib/Target/AMDGPU/MCTargetDesc/AMDGPUELFObjectWriter.cpp
+++ b/llvm/lib/Target/AMDGPU/MCTargetDesc/AMDGPUELFObjectWriter.cpp
@@ -8,15 +8,9 @@
 
 #include "AMDGPUFixupKinds.h"
 #include "AMDGPUMCTargetDesc.h"
-#include "llvm/BinaryFormat/ELF.h"
 #include "llvm/MC/MCContext.h"
 #include "llvm/MC/MCELFObjectWriter.h"
-#include "llvm/MC/MCExpr.h"
-#include "llvm/MC/MCFixup.h"
-#include "llvm/MC/MCObjectWriter.h"
-#include "llvm/MC/MCSymbol.h"
 #include "llvm/MC/MCValue.h"
-#include "llvm/Support/ErrorHandling.h"
 
 using namespace llvm;
 
diff --git a/llvm/lib/Target/AMDGPU/MCTargetDesc/AMDGPUELFStreamer.h b/llvm/lib/Target/AMDGPU/MCTargetDesc/AMDGPUELFStreamer.h
--- a/llvm/lib/Target/AMDGPU/MCTargetDesc/AMDGPUELFStreamer.h
+++ b/llvm/lib/Target/AMDGPU/MCTargetDesc/AMDGPUELFStreamer.h
@@ -14,13 +14,15 @@
 #ifndef LLVM_LIB_TARGET_AMDGPU_MCTARGETDESC_AMDGPUELFSTREAMER_H
 #define LLVM_LIB_TARGET_AMDGPU_MCTARGETDESC_AMDGPUELFSTREAMER_H
 
-#include "llvm/MC/MCELFStreamer.h"
-
+#include <memory>
 namespace llvm {
 class MCAsmBackend;
 class MCCodeEmitter;
 class MCContext;
 class MCSubtargetInfo;
+class MCELFStreamer;
+class Triple;
+class MCObjectWriter;
 
 MCELFStreamer *createAMDGPUELFStreamer(const Triple &T, MCContext &Context,
                                        std::unique_ptr<MCAsmBackend> MAB,
diff --git a/llvm/lib/Target/AMDGPU/MCTargetDesc/AMDGPUELFStreamer.cpp b/llvm/lib/Target/AMDGPU/MCTargetDesc/AMDGPUELFStreamer.cpp
--- a/llvm/lib/Target/AMDGPU/MCTargetDesc/AMDGPUELFStreamer.cpp
+++ b/llvm/lib/Target/AMDGPU/MCTargetDesc/AMDGPUELFStreamer.cpp
@@ -7,10 +7,9 @@
 //===----------------------------------------------------------------------===//
 
 #include "AMDGPUELFStreamer.h"
-#include "Utils/AMDGPUBaseInfo.h"
-#include "llvm/BinaryFormat/ELF.h"
 #include "llvm/MC/MCAsmBackend.h"
 #include "llvm/MC/MCCodeEmitter.h"
+#include "llvm/MC/MCELFStreamer.h"
 #include "llvm/MC/MCObjectWriter.h"
 
 using namespace llvm;
diff --git a/llvm/lib/Target/AMDGPU/MCTargetDesc/AMDGPUInstPrinter.cpp b/llvm/lib/Target/AMDGPU/MCTargetDesc/AMDGPUInstPrinter.cpp
--- a/llvm/lib/Target/AMDGPU/MCTargetDesc/AMDGPUInstPrinter.cpp
+++ b/llvm/lib/Target/AMDGPU/MCTargetDesc/AMDGPUInstPrinter.cpp
@@ -16,13 +16,9 @@
 #include "llvm/MC/MCInst.h"
 #include "llvm/MC/MCInstrDesc.h"
 #include "llvm/MC/MCInstrInfo.h"
-#include "llvm/MC/MCRegisterInfo.h"
 #include "llvm/MC/MCSubtargetInfo.h"
 #include "llvm/Support/CommandLine.h"
-#include "llvm/Support/ErrorHandling.h"
-#include "llvm/Support/MathExtras.h"
-#include "llvm/Support/raw_ostream.h"
-#include <cassert>
+#include "llvm/Support/TargetParser.h"
 
 using namespace llvm;
 using namespace llvm::AMDGPU;
diff --git a/llvm/lib/Target/AMDGPU/MCTargetDesc/AMDGPUMCCodeEmitter.h b/llvm/lib/Target/AMDGPU/MCTargetDesc/AMDGPUMCCodeEmitter.h
--- a/llvm/lib/Target/AMDGPU/MCTargetDesc/AMDGPUMCCodeEmitter.h
+++ b/llvm/lib/Target/AMDGPU/MCTargetDesc/AMDGPUMCCodeEmitter.h
@@ -15,7 +15,7 @@
 #define LLVM_LIB_TARGET_AMDGPU_MCTARGETDESC_AMDGPUMCCODEEMITTER_H
 
 #include "llvm/MC/MCCodeEmitter.h"
-#include "llvm/Support/raw_ostream.h"
+#include <cstdint>
 
 namespace llvm {
 
diff --git a/llvm/lib/Target/AMDGPU/MCTargetDesc/AMDGPUMCTargetDesc.h b/llvm/lib/Target/AMDGPU/MCTargetDesc/AMDGPUMCTargetDesc.h
--- a/llvm/lib/Target/AMDGPU/MCTargetDesc/AMDGPUMCTargetDesc.h
+++ b/llvm/lib/Target/AMDGPU/MCTargetDesc/AMDGPUMCTargetDesc.h
@@ -15,8 +15,6 @@
 #ifndef LLVM_LIB_TARGET_AMDGPU_MCTARGETDESC_AMDGPUMCTARGETDESC_H
 #define LLVM_LIB_TARGET_AMDGPU_MCTARGETDESC_AMDGPUMCTARGETDESC_H
 
-#include "llvm/Support/DataTypes.h"
-
 #include <memory>
 
 namespace llvm {
@@ -58,34 +56,24 @@
 
 #define GET_REGINFO_ENUM
 #include "AMDGPUGenRegisterInfo.inc"
-#undef GET_REGINFO_ENUM
 
 #define GET_REGINFO_ENUM
 #include "R600GenRegisterInfo.inc"
-#undef GET_REGINFO_ENUM
 
 #define GET_INSTRINFO_ENUM
 #define GET_INSTRINFO_OPERAND_ENUM
 #define GET_INSTRINFO_SCHED_ENUM
 #include "AMDGPUGenInstrInfo.inc"
-#undef GET_INSTRINFO_SCHED_ENUM
-#undef GET_INSTRINFO_OPERAND_ENUM
-#undef GET_INSTRINFO_ENUM
 
 #define GET_INSTRINFO_ENUM
 #define GET_INSTRINFO_OPERAND_ENUM
 #define GET_INSTRINFO_SCHED_ENUM
 #include "R600GenInstrInfo.inc"
-#undef GET_INSTRINFO_SCHED_ENUM
-#undef GET_INSTRINFO_OPERAND_ENUM
-#undef GET_INSTRINFO_ENUM
 
 #define GET_SUBTARGETINFO_ENUM
 #include "AMDGPUGenSubtargetInfo.inc"
-#undef GET_SUBTARGETINFO_ENUM
 
 #define GET_SUBTARGETINFO_ENUM
 #include "R600GenSubtargetInfo.inc"
-#undef GET_SUBTARGETINFO_ENUM
 
 #endif
diff --git a/llvm/lib/Target/AMDGPU/MCTargetDesc/AMDGPUMCTargetDesc.cpp b/llvm/lib/Target/AMDGPU/MCTargetDesc/AMDGPUMCTargetDesc.cpp
--- a/llvm/lib/Target/AMDGPU/MCTargetDesc/AMDGPUMCTargetDesc.cpp
+++ b/llvm/lib/Target/AMDGPU/MCTargetDesc/AMDGPUMCTargetDesc.cpp
@@ -20,15 +20,15 @@
 #include "TargetInfo/AMDGPUTargetInfo.h"
 #include "llvm/MC/MCAsmBackend.h"
 #include "llvm/MC/MCCodeEmitter.h"
-#include "llvm/MC/MCContext.h"
+#include "llvm/MC/MCELFStreamer.h"
+#include "llvm/MC/MCInstPrinter.h"
 #include "llvm/MC/MCInstrAnalysis.h"
+#include "llvm/MC/MCInstrDesc.h"
 #include "llvm/MC/MCInstrInfo.h"
 #include "llvm/MC/MCObjectWriter.h"
-#include "llvm/MC/MCRegisterInfo.h"
+#include "llvm/MC/MCRegister.h"
 #include "llvm/MC/MCStreamer.h"
 #include "llvm/MC/MCSubtargetInfo.h"
-#include "llvm/MC/MachineLocation.h"
-#include "llvm/Support/ErrorHandling.h"
 #include "llvm/Support/TargetRegistry.h"
 
 using namespace llvm;
diff --git a/llvm/lib/Target/AMDGPU/MCTargetDesc/AMDGPUTargetStreamer.h b/llvm/lib/Target/AMDGPU/MCTargetDesc/AMDGPUTargetStreamer.h
--- a/llvm/lib/Target/AMDGPU/MCTargetDesc/AMDGPUTargetStreamer.h
+++ b/llvm/lib/Target/AMDGPU/MCTargetDesc/AMDGPUTargetStreamer.h
@@ -9,16 +9,12 @@
 #ifndef LLVM_LIB_TARGET_AMDGPU_MCTARGETDESC_AMDGPUTARGETSTREAMER_H
 #define LLVM_LIB_TARGET_AMDGPU_MCTARGETDESC_AMDGPUTARGETSTREAMER_H
 
-#include "AMDKernelCodeT.h"
 #include "Utils/AMDGPUPALMetadata.h"
-#include "llvm/BinaryFormat/MsgPackDocument.h"
 #include "llvm/MC/MCStreamer.h"
-#include "llvm/MC/MCSubtargetInfo.h"
-#include "llvm/Support/AMDGPUMetadata.h"
-#include "llvm/Support/AMDHSAKernelDescriptor.h"
+
+struct amd_kernel_code_t;
 
 namespace llvm {
-#include "AMDGPUPTNote.h"
 
 class DataLayout;
 class Function;
@@ -28,6 +24,16 @@
 class Module;
 class Type;
 
+namespace AMDGPU {
+namespace HSAMD {
+struct Metadata;
+}
+} // namespace AMDGPU
+
+namespace amdhsa {
+struct kernel_descriptor_t;
+}
+
 class AMDGPUTargetStreamer : public MCTargetStreamer {
   AMDGPUPALMetadata PALMetadata;
 
diff --git a/llvm/lib/Target/AMDGPU/MCTargetDesc/AMDGPUTargetStreamer.cpp b/llvm/lib/Target/AMDGPU/MCTargetDesc/AMDGPUTargetStreamer.cpp
--- a/llvm/lib/Target/AMDGPU/MCTargetDesc/AMDGPUTargetStreamer.cpp
+++ b/llvm/lib/Target/AMDGPU/MCTargetDesc/AMDGPUTargetStreamer.cpp
@@ -11,31 +11,21 @@
 //===----------------------------------------------------------------------===//
 
 #include "AMDGPUTargetStreamer.h"
-#include "AMDGPU.h"
-#include "SIDefines.h"
+#include "AMDGPUPTNote.h"
+#include "AMDKernelCodeT.h"
 #include "Utils/AMDGPUBaseInfo.h"
 #include "Utils/AMDKernelCodeTUtils.h"
-#include "llvm/ADT/Twine.h"
 #include "llvm/BinaryFormat/AMDGPUMetadataVerifier.h"
 #include "llvm/BinaryFormat/ELF.h"
-#include "llvm/IR/Constants.h"
-#include "llvm/IR/Function.h"
-#include "llvm/IR/Metadata.h"
-#include "llvm/IR/Module.h"
 #include "llvm/MC/MCContext.h"
 #include "llvm/MC/MCELFStreamer.h"
-#include "llvm/MC/MCObjectFileInfo.h"
 #include "llvm/MC/MCSectionELF.h"
+#include "llvm/Support/AMDGPUMetadata.h"
+#include "llvm/Support/AMDHSAKernelDescriptor.h"
 #include "llvm/Support/FormattedStream.h"
-#include "llvm/Support/TargetParser.h"
-
-namespace llvm {
-#include "AMDGPUPTNote.h"
-}
 
 using namespace llvm;
 using namespace llvm::AMDGPU;
-using namespace llvm::AMDGPU::HSAMD;
 
 //===----------------------------------------------------------------------===//
 // AMDGPUTargetStreamer
@@ -247,15 +237,15 @@
   if (HSAMD::toString(HSAMetadata, HSAMetadataString))
     return false;
 
-  OS << '\t' << AssemblerDirectiveBegin << '\n';
+  OS << '\t' << HSAMD::AssemblerDirectiveBegin << '\n';
   OS << HSAMetadataString << '\n';
-  OS << '\t' << AssemblerDirectiveEnd << '\n';
+  OS << '\t' << HSAMD::AssemblerDirectiveEnd << '\n';
   return true;
 }
 
 bool AMDGPUTargetAsmStreamer::EmitHSAMetadata(
     msgpack::Document &HSAMetadataDoc, bool Strict) {
-  V3::MetadataVerifier Verifier(Strict);
+  HSAMD::V3::MetadataVerifier Verifier(Strict);
   if (!Verifier.verify(HSAMetadataDoc.getRoot()))
     return false;
 
@@ -263,9 +253,9 @@
   raw_string_ostream StrOS(HSAMetadataString);
   HSAMetadataDoc.toYAML(StrOS);
 
-  OS << '\t' << V3::AssemblerDirectiveBegin << '\n';
+  OS << '\t' << HSAMD::V3::AssemblerDirectiveBegin << '\n';
   OS << StrOS.str() << '\n';
-  OS << '\t' << V3::AssemblerDirectiveEnd << '\n';
+  OS << '\t' << HSAMD::V3::AssemblerDirectiveEnd << '\n';
   return true;
 }
 
@@ -578,7 +568,7 @@
 
 bool AMDGPUTargetELFStreamer::EmitHSAMetadata(msgpack::Document &HSAMetadataDoc,
                                               bool Strict) {
-  V3::MetadataVerifier Verifier(Strict);
+  HSAMD::V3::MetadataVerifier Verifier(Strict);
   if (!Verifier.verify(HSAMetadataDoc.getRoot()))
     return false;
 
diff --git a/llvm/lib/Target/AMDGPU/MCTargetDesc/R600MCCodeEmitter.cpp b/llvm/lib/Target/AMDGPU/MCTargetDesc/R600MCCodeEmitter.cpp
--- a/llvm/lib/Target/AMDGPU/MCTargetDesc/R600MCCodeEmitter.cpp
+++ b/llvm/lib/Target/AMDGPU/MCTargetDesc/R600MCCodeEmitter.cpp
@@ -13,22 +13,15 @@
 //
 //===----------------------------------------------------------------------===//
 
-#include "MCTargetDesc/AMDGPUFixupKinds.h"
 #include "MCTargetDesc/AMDGPUMCTargetDesc.h"
 #include "R600Defines.h"
 #include "llvm/MC/MCCodeEmitter.h"
 #include "llvm/MC/MCContext.h"
-#include "llvm/MC/MCFixup.h"
 #include "llvm/MC/MCInst.h"
-#include "llvm/MC/MCInstrDesc.h"
 #include "llvm/MC/MCInstrInfo.h"
 #include "llvm/MC/MCRegisterInfo.h"
-#include "llvm/MC/MCSubtargetInfo.h"
-#include "llvm/Support/Endian.h"
+#include "llvm/MC/SubtargetFeature.h"
 #include "llvm/Support/EndianStream.h"
-#include "llvm/Support/raw_ostream.h"
-#include <cassert>
-#include <cstdint>
 
 using namespace llvm;
 
diff --git a/llvm/lib/Target/AMDGPU/MCTargetDesc/SIMCCodeEmitter.cpp b/llvm/lib/Target/AMDGPU/MCTargetDesc/SIMCCodeEmitter.cpp
--- a/llvm/lib/Target/AMDGPU/MCTargetDesc/SIMCCodeEmitter.cpp
+++ b/llvm/lib/Target/AMDGPU/MCTargetDesc/SIMCCodeEmitter.cpp
@@ -12,29 +12,15 @@
 //
 //===----------------------------------------------------------------------===//
 
-#include "AMDGPU.h"
 #include "MCTargetDesc/AMDGPUFixupKinds.h"
 #include "MCTargetDesc/AMDGPUMCCodeEmitter.h"
 #include "MCTargetDesc/AMDGPUMCTargetDesc.h"
 #include "SIDefines.h"
 #include "Utils/AMDGPUBaseInfo.h"
-#include "llvm/MC/MCCodeEmitter.h"
 #include "llvm/MC/MCContext.h"
 #include "llvm/MC/MCExpr.h"
-#include "llvm/MC/MCFixup.h"
-#include "llvm/MC/MCInst.h"
-#include "llvm/MC/MCInstrDesc.h"
 #include "llvm/MC/MCInstrInfo.h"
 #include "llvm/MC/MCRegisterInfo.h"
-#include "llvm/MC/MCSubtargetInfo.h"
-#include "llvm/MC/MCSymbol.h"
-#include "llvm/Support/Casting.h"
-#include "llvm/Support/ErrorHandling.h"
-#include "llvm/Support/MathExtras.h"
-#include "llvm/Support/raw_ostream.h"
-#include <cassert>
-#include <cstdint>
-#include <cstdlib>
 
 using namespace llvm;
 
diff --git a/llvm/lib/Target/AMDGPU/R600AsmPrinter.cpp b/llvm/lib/Target/AMDGPU/R600AsmPrinter.cpp
--- a/llvm/lib/Target/AMDGPU/R600AsmPrinter.cpp
+++ b/llvm/lib/Target/AMDGPU/R600AsmPrinter.cpp
@@ -18,7 +18,6 @@
 #include "AMDGPUSubtarget.h"
 #include "R600Defines.h"
 #include "R600MachineFunctionInfo.h"
-#include "MCTargetDesc/AMDGPUMCTargetDesc.h"
 #include "llvm/BinaryFormat/ELF.h"
 #include "llvm/MC/MCContext.h"
 #include "llvm/MC/MCSectionELF.h"
diff --git a/llvm/lib/Target/AMDGPU/R600ClauseMergePass.cpp b/llvm/lib/Target/AMDGPU/R600ClauseMergePass.cpp
--- a/llvm/lib/Target/AMDGPU/R600ClauseMergePass.cpp
+++ b/llvm/lib/Target/AMDGPU/R600ClauseMergePass.cpp
@@ -14,16 +14,6 @@
 
 #include "AMDGPU.h"
 #include "AMDGPUSubtarget.h"
-#include "R600Defines.h"
-#include "R600InstrInfo.h"
-#include "R600MachineFunctionInfo.h"
-#include "R600RegisterInfo.h"
-#include "MCTargetDesc/AMDGPUMCTargetDesc.h"
-#include "llvm/CodeGen/MachineFunctionPass.h"
-#include "llvm/CodeGen/MachineInstrBuilder.h"
-#include "llvm/CodeGen/MachineRegisterInfo.h"
-#include "llvm/Support/Debug.h"
-#include "llvm/Support/raw_ostream.h"
 
 using namespace llvm;
 
diff --git a/llvm/lib/Target/AMDGPU/R600ControlFlowFinalizer.cpp b/llvm/lib/Target/AMDGPU/R600ControlFlowFinalizer.cpp
--- a/llvm/lib/Target/AMDGPU/R600ControlFlowFinalizer.cpp
+++ b/llvm/lib/Target/AMDGPU/R600ControlFlowFinalizer.cpp
@@ -14,34 +14,8 @@
 
 #include "AMDGPU.h"
 #include "AMDGPUSubtarget.h"
-#include "R600Defines.h"
-#include "R600InstrInfo.h"
 #include "R600MachineFunctionInfo.h"
-#include "R600RegisterInfo.h"
-#include "MCTargetDesc/AMDGPUMCTargetDesc.h"
-#include "llvm/ADT/STLExtras.h"
-#include "llvm/ADT/SmallVector.h"
-#include "llvm/ADT/StringRef.h"
-#include "llvm/CodeGen/MachineBasicBlock.h"
-#include "llvm/CodeGen/MachineFunction.h"
-#include "llvm/CodeGen/MachineFunctionPass.h"
-#include "llvm/CodeGen/MachineInstr.h"
-#include "llvm/CodeGen/MachineInstrBuilder.h"
-#include "llvm/CodeGen/MachineOperand.h"
-#include "llvm/IR/CallingConv.h"
-#include "llvm/IR/DebugLoc.h"
-#include "llvm/IR/Function.h"
-#include "llvm/Pass.h"
-#include "llvm/Support/Compiler.h"
-#include "llvm/Support/Debug.h"
-#include "llvm/Support/MathExtras.h"
-#include "llvm/Support/raw_ostream.h"
-#include <algorithm>
-#include <cassert>
-#include <cstdint>
 #include <set>
-#include <utility>
-#include <vector>
 
 using namespace llvm;
 
diff --git a/llvm/lib/Target/AMDGPU/R600Defines.h b/llvm/lib/Target/AMDGPU/R600Defines.h
--- a/llvm/lib/Target/AMDGPU/R600Defines.h
+++ b/llvm/lib/Target/AMDGPU/R600Defines.h
@@ -10,8 +10,6 @@
 #ifndef LLVM_LIB_TARGET_AMDGPU_R600DEFINES_H
 #define LLVM_LIB_TARGET_AMDGPU_R600DEFINES_H
 
-#include "llvm/MC/MCRegisterInfo.h"
-
 // Operand Flags
 #define MO_FLAG_CLAMP (1 << 0)
 #define MO_FLAG_NEG   (1 << 1)
diff --git a/llvm/lib/Target/AMDGPU/R600EmitClauseMarkers.cpp b/llvm/lib/Target/AMDGPU/R600EmitClauseMarkers.cpp
--- a/llvm/lib/Target/AMDGPU/R600EmitClauseMarkers.cpp
+++ b/llvm/lib/Target/AMDGPU/R600EmitClauseMarkers.cpp
@@ -16,23 +16,6 @@
 #include "AMDGPU.h"
 #include "AMDGPUSubtarget.h"
 #include "R600Defines.h"
-#include "R600InstrInfo.h"
-#include "R600RegisterInfo.h"
-#include "MCTargetDesc/AMDGPUMCTargetDesc.h"
-#include "llvm/ADT/SmallVector.h"
-#include "llvm/ADT/StringRef.h"
-#include "llvm/CodeGen/MachineBasicBlock.h"
-#include "llvm/CodeGen/MachineFunction.h"
-#include "llvm/CodeGen/MachineFunctionPass.h"
-#include "llvm/CodeGen/MachineInstr.h"
-#include "llvm/CodeGen/MachineInstrBuilder.h"
-#include "llvm/CodeGen/MachineOperand.h"
-#include "llvm/Pass.h"
-#include "llvm/Support/ErrorHandling.h"
-#include <cassert>
-#include <cstdint>
-#include <utility>
-#include <vector>
 
 using namespace llvm;
 
diff --git a/llvm/lib/Target/AMDGPU/R600ExpandSpecialInstrs.cpp b/llvm/lib/Target/AMDGPU/R600ExpandSpecialInstrs.cpp
--- a/llvm/lib/Target/AMDGPU/R600ExpandSpecialInstrs.cpp
+++ b/llvm/lib/Target/AMDGPU/R600ExpandSpecialInstrs.cpp
@@ -16,19 +16,6 @@
 #include "AMDGPU.h"
 #include "AMDGPUSubtarget.h"
 #include "R600Defines.h"
-#include "R600InstrInfo.h"
-#include "R600RegisterInfo.h"
-#include "llvm/CodeGen/MachineBasicBlock.h"
-#include "llvm/CodeGen/MachineFunction.h"
-#include "MCTargetDesc/AMDGPUMCTargetDesc.h"
-#include "llvm/CodeGen/MachineFunctionPass.h"
-#include "llvm/CodeGen/MachineInstr.h"
-#include "llvm/CodeGen/MachineInstrBuilder.h"
-#include "llvm/CodeGen/MachineOperand.h"
-#include "llvm/Pass.h"
-#include <cassert>
-#include <cstdint>
-#include <iterator>
 
 using namespace llvm;
 
diff --git a/llvm/lib/Target/AMDGPU/R600FrameLowering.h b/llvm/lib/Target/AMDGPU/R600FrameLowering.h
--- a/llvm/lib/Target/AMDGPU/R600FrameLowering.h
+++ b/llvm/lib/Target/AMDGPU/R600FrameLowering.h
@@ -10,7 +10,6 @@
 #define LLVM_LIB_TARGET_AMDGPU_R600FRAMELOWERING_H
 
 #include "AMDGPUFrameLowering.h"
-#include "llvm/Support/TypeSize.h"
 
 namespace llvm {
 
diff --git a/llvm/lib/Target/AMDGPU/R600FrameLowering.cpp b/llvm/lib/Target/AMDGPU/R600FrameLowering.cpp
--- a/llvm/lib/Target/AMDGPU/R600FrameLowering.cpp
+++ b/llvm/lib/Target/AMDGPU/R600FrameLowering.cpp
@@ -8,10 +8,6 @@
 
 #include "R600FrameLowering.h"
 #include "AMDGPUSubtarget.h"
-#include "R600RegisterInfo.h"
-#include "llvm/CodeGen/MachineFrameInfo.h"
-#include "llvm/CodeGen/MachineFunction.h"
-#include "llvm/Support/MathExtras.h"
 
 using namespace llvm;
 
diff --git a/llvm/lib/Target/AMDGPU/R600ISelLowering.cpp b/llvm/lib/Target/AMDGPU/R600ISelLowering.cpp
--- a/llvm/lib/Target/AMDGPU/R600ISelLowering.cpp
+++ b/llvm/lib/Target/AMDGPU/R600ISelLowering.cpp
@@ -12,42 +12,14 @@
 //===----------------------------------------------------------------------===//
 
 #include "R600ISelLowering.h"
-#include "AMDGPUFrameLowering.h"
+#include "AMDGPU.h"
 #include "AMDGPUSubtarget.h"
+#include "MCTargetDesc/AMDGPUMCTargetDesc.h"
 #include "R600Defines.h"
-#include "R600FrameLowering.h"
 #include "R600InstrInfo.h"
 #include "R600MachineFunctionInfo.h"
-#include "MCTargetDesc/AMDGPUMCTargetDesc.h"
-#include "Utils/AMDGPUBaseInfo.h"
-#include "llvm/ADT/APFloat.h"
-#include "llvm/ADT/APInt.h"
-#include "llvm/ADT/ArrayRef.h"
-#include "llvm/ADT/DenseMap.h"
-#include "llvm/ADT/SmallVector.h"
-#include "llvm/CodeGen/CallingConvLower.h"
-#include "llvm/CodeGen/DAGCombine.h"
-#include "llvm/CodeGen/ISDOpcodes.h"
-#include "llvm/CodeGen/MachineBasicBlock.h"
-#include "llvm/CodeGen/MachineFunction.h"
-#include "llvm/CodeGen/MachineInstr.h"
-#include "llvm/CodeGen/MachineInstrBuilder.h"
-#include "llvm/CodeGen/MachineMemOperand.h"
-#include "llvm/CodeGen/MachineRegisterInfo.h"
-#include "llvm/CodeGen/SelectionDAG.h"
-#include "llvm/IR/Constants.h"
-#include "llvm/IR/DerivedTypes.h"
+#include "llvm/IR/IntrinsicsAMDGPU.h"
 #include "llvm/IR/IntrinsicsR600.h"
-#include "llvm/Support/Casting.h"
-#include "llvm/Support/Compiler.h"
-#include "llvm/Support/ErrorHandling.h"
-#include "llvm/Support/MachineValueType.h"
-#include "llvm/Support/MathExtras.h"
-#include <cassert>
-#include <cstdint>
-#include <iterator>
-#include <utility>
-#include <vector>
 
 using namespace llvm;
 
diff --git a/llvm/lib/Target/AMDGPU/R600InstrInfo.cpp b/llvm/lib/Target/AMDGPU/R600InstrInfo.cpp
--- a/llvm/lib/Target/AMDGPU/R600InstrInfo.cpp
+++ b/llvm/lib/Target/AMDGPU/R600InstrInfo.cpp
@@ -13,33 +13,9 @@
 
 #include "R600InstrInfo.h"
 #include "AMDGPU.h"
-#include "AMDGPUInstrInfo.h"
 #include "AMDGPUSubtarget.h"
 #include "R600Defines.h"
-#include "R600FrameLowering.h"
-#include "R600RegisterInfo.h"
-#include "MCTargetDesc/AMDGPUMCTargetDesc.h"
-#include "Utils/AMDGPUBaseInfo.h"
-#include "llvm/ADT/BitVector.h"
 #include "llvm/ADT/SmallSet.h"
-#include "llvm/ADT/SmallVector.h"
-#include "llvm/CodeGen/MachineBasicBlock.h"
-#include "llvm/CodeGen/MachineFrameInfo.h"
-#include "llvm/CodeGen/MachineFunction.h"
-#include "llvm/CodeGen/MachineInstr.h"
-#include "llvm/CodeGen/MachineInstrBuilder.h"
-#include "llvm/CodeGen/MachineOperand.h"
-#include "llvm/CodeGen/MachineRegisterInfo.h"
-#include "llvm/CodeGen/TargetRegisterInfo.h"
-#include "llvm/CodeGen/TargetSubtargetInfo.h"
-#include "llvm/Support/ErrorHandling.h"
-#include <algorithm>
-#include <cassert>
-#include <cstdint>
-#include <cstring>
-#include <iterator>
-#include <utility>
-#include <vector>
 
 using namespace llvm;
 
diff --git a/llvm/lib/Target/AMDGPU/R600MachineScheduler.cpp b/llvm/lib/Target/AMDGPU/R600MachineScheduler.cpp
--- a/llvm/lib/Target/AMDGPU/R600MachineScheduler.cpp
+++ b/llvm/lib/Target/AMDGPU/R600MachineScheduler.cpp
@@ -13,12 +13,6 @@
 
 #include "R600MachineScheduler.h"
 #include "AMDGPUSubtarget.h"
-#include "R600InstrInfo.h"
-#include "MCTargetDesc/AMDGPUMCTargetDesc.h"
-#include "llvm/CodeGen/MachineRegisterInfo.h"
-#include "llvm/IR/LegacyPassManager.h"
-#include "llvm/Pass.h"
-#include "llvm/Support/raw_ostream.h"
 
 using namespace llvm;
 
diff --git a/llvm/lib/Target/AMDGPU/R600OpenCLImageTypeLoweringPass.cpp b/llvm/lib/Target/AMDGPU/R600OpenCLImageTypeLoweringPass.cpp
--- a/llvm/lib/Target/AMDGPU/R600OpenCLImageTypeLoweringPass.cpp
+++ b/llvm/lib/Target/AMDGPU/R600OpenCLImageTypeLoweringPass.cpp
@@ -27,27 +27,12 @@
 #include "AMDGPU.h"
 #include "llvm/ADT/SmallVector.h"
 #include "llvm/ADT/StringRef.h"
-#include "llvm/ADT/Twine.h"
-#include "llvm/IR/Argument.h"
-#include "llvm/IR/DerivedTypes.h"
 #include "llvm/IR/Constants.h"
 #include "llvm/IR/Function.h"
-#include "llvm/IR/Instruction.h"
 #include "llvm/IR/Instructions.h"
 #include "llvm/IR/Metadata.h"
-#include "llvm/IR/Module.h"
-#include "llvm/IR/Type.h"
-#include "llvm/IR/Use.h"
-#include "llvm/IR/User.h"
 #include "llvm/Pass.h"
-#include "llvm/Support/Casting.h"
-#include "llvm/Support/ErrorHandling.h"
 #include "llvm/Transforms/Utils/Cloning.h"
-#include "llvm/Transforms/Utils/ValueMapper.h"
-#include <cassert>
-#include <cstddef>
-#include <cstdint>
-#include <tuple>
 
 using namespace llvm;
 
diff --git a/llvm/lib/Target/AMDGPU/R600OptimizeVectorRegisters.cpp b/llvm/lib/Target/AMDGPU/R600OptimizeVectorRegisters.cpp
--- a/llvm/lib/Target/AMDGPU/R600OptimizeVectorRegisters.cpp
+++ b/llvm/lib/Target/AMDGPU/R600OptimizeVectorRegisters.cpp
@@ -29,28 +29,8 @@
 #include "AMDGPU.h"
 #include "AMDGPUSubtarget.h"
 #include "R600Defines.h"
-#include "R600InstrInfo.h"
-#include "MCTargetDesc/AMDGPUMCTargetDesc.h"
-#include "llvm/ADT/DenseMap.h"
-#include "llvm/ADT/STLExtras.h"
-#include "llvm/ADT/StringRef.h"
-#include "llvm/CodeGen/MachineBasicBlock.h"
 #include "llvm/CodeGen/MachineDominators.h"
-#include "llvm/CodeGen/MachineFunction.h"
-#include "llvm/CodeGen/MachineFunctionPass.h"
-#include "llvm/CodeGen/MachineInstr.h"
-#include "llvm/CodeGen/MachineInstrBuilder.h"
 #include "llvm/CodeGen/MachineLoopInfo.h"
-#include "llvm/CodeGen/MachineOperand.h"
-#include "llvm/CodeGen/MachineRegisterInfo.h"
-#include "llvm/IR/DebugLoc.h"
-#include "llvm/Pass.h"
-#include "llvm/Support/Debug.h"
-#include "llvm/Support/ErrorHandling.h"
-#include "llvm/Support/raw_ostream.h"
-#include <cassert>
-#include <utility>
-#include <vector>
 
 using namespace llvm;
 
diff --git a/llvm/lib/Target/AMDGPU/R600Packetizer.cpp b/llvm/lib/Target/AMDGPU/R600Packetizer.cpp
--- a/llvm/lib/Target/AMDGPU/R600Packetizer.cpp
+++ b/llvm/lib/Target/AMDGPU/R600Packetizer.cpp
@@ -15,16 +15,10 @@
 
 #include "AMDGPU.h"
 #include "AMDGPUSubtarget.h"
-#include "R600InstrInfo.h"
-#include "MCTargetDesc/AMDGPUMCTargetDesc.h"
 #include "llvm/CodeGen/DFAPacketizer.h"
 #include "llvm/CodeGen/MachineDominators.h"
-#include "llvm/CodeGen/MachineFunctionPass.h"
 #include "llvm/CodeGen/MachineLoopInfo.h"
-#include "llvm/CodeGen/Passes.h"
 #include "llvm/CodeGen/ScheduleDAG.h"
-#include "llvm/Support/Debug.h"
-#include "llvm/Support/raw_ostream.h"
 
 using namespace llvm;
 
diff --git a/llvm/lib/Target/AMDGPU/R600RegisterInfo.cpp b/llvm/lib/Target/AMDGPU/R600RegisterInfo.cpp
--- a/llvm/lib/Target/AMDGPU/R600RegisterInfo.cpp
+++ b/llvm/lib/Target/AMDGPU/R600RegisterInfo.cpp
@@ -12,11 +12,8 @@
 //===----------------------------------------------------------------------===//
 
 #include "R600RegisterInfo.h"
-#include "AMDGPUTargetMachine.h"
+#include "AMDGPUSubtarget.h"
 #include "R600Defines.h"
-#include "R600InstrInfo.h"
-#include "R600MachineFunctionInfo.h"
-#include "MCTargetDesc/AMDGPUMCTargetDesc.h"
 
 using namespace llvm;
 
diff --git a/llvm/lib/Target/AMDGPU/SIAddIMGInit.cpp b/llvm/lib/Target/AMDGPU/SIAddIMGInit.cpp
--- a/llvm/lib/Target/AMDGPU/SIAddIMGInit.cpp
+++ b/llvm/lib/Target/AMDGPU/SIAddIMGInit.cpp
@@ -17,14 +17,7 @@
 
 #include "AMDGPU.h"
 #include "AMDGPUSubtarget.h"
-#include "MCTargetDesc/AMDGPUMCTargetDesc.h"
-#include "SIInstrInfo.h"
 #include "llvm/CodeGen/MachineFunctionPass.h"
-#include "llvm/CodeGen/MachineInstrBuilder.h"
-#include "llvm/CodeGen/MachineRegisterInfo.h"
-#include "llvm/IR/Function.h"
-#include "llvm/Support/Debug.h"
-#include "llvm/Target/TargetMachine.h"
 
 #define DEBUG_TYPE "si-img-init"
 
diff --git a/llvm/lib/Target/AMDGPU/SIAnnotateControlFlow.cpp b/llvm/lib/Target/AMDGPU/SIAnnotateControlFlow.cpp
--- a/llvm/lib/Target/AMDGPU/SIAnnotateControlFlow.cpp
+++ b/llvm/lib/Target/AMDGPU/SIAnnotateControlFlow.cpp
@@ -13,35 +13,17 @@
 
 #include "AMDGPU.h"
 #include "AMDGPUSubtarget.h"
-#include "llvm/ADT/DepthFirstIterator.h"
-#include "llvm/ADT/STLExtras.h"
-#include "llvm/ADT/SmallVector.h"
 #include "llvm/Analysis/LegacyDivergenceAnalysis.h"
 #include "llvm/Analysis/LoopInfo.h"
 #include "llvm/CodeGen/TargetPassConfig.h"
 #include "llvm/IR/BasicBlock.h"
-#include "llvm/IR/CFG.h"
-#include "llvm/IR/Constant.h"
 #include "llvm/IR/Constants.h"
-#include "llvm/IR/DerivedTypes.h"
 #include "llvm/IR/Dominators.h"
-#include "llvm/IR/Function.h"
-#include "llvm/IR/Instruction.h"
-#include "llvm/IR/Instructions.h"
-#include "llvm/IR/Intrinsics.h"
-#include "llvm/IR/Module.h"
-#include "llvm/IR/Type.h"
-#include "llvm/IR/ValueHandle.h"
+#include "llvm/IR/IntrinsicsAMDGPU.h"
 #include "llvm/InitializePasses.h"
-#include "llvm/Pass.h"
-#include "llvm/Support/Casting.h"
-#include "llvm/Support/Debug.h"
-#include "llvm/Support/ErrorHandling.h"
-#include "llvm/Support/raw_ostream.h"
+#include "llvm/Target/TargetMachine.h"
 #include "llvm/Transforms/Utils/BasicBlockUtils.h"
 #include "llvm/Transforms/Utils/Local.h"
-#include <cassert>
-#include <utility>
 
 using namespace llvm;
 
diff --git a/llvm/lib/Target/AMDGPU/SIFixSGPRCopies.cpp b/llvm/lib/Target/AMDGPU/SIFixSGPRCopies.cpp
--- a/llvm/lib/Target/AMDGPU/SIFixSGPRCopies.cpp
+++ b/llvm/lib/Target/AMDGPU/SIFixSGPRCopies.cpp
@@ -66,36 +66,9 @@
 
 #include "AMDGPU.h"
 #include "AMDGPUSubtarget.h"
-#include "MCTargetDesc/AMDGPUMCTargetDesc.h"
-#include "SIInstrInfo.h"
-#include "SIRegisterInfo.h"
-#include "llvm/ADT/DenseSet.h"
-#include "llvm/ADT/STLExtras.h"
-#include "llvm/ADT/SmallSet.h"
-#include "llvm/ADT/SmallVector.h"
-#include "llvm/CodeGen/MachineBasicBlock.h"
 #include "llvm/CodeGen/MachineDominators.h"
-#include "llvm/CodeGen/MachineFunction.h"
-#include "llvm/CodeGen/MachineFunctionPass.h"
-#include "llvm/CodeGen/MachineInstr.h"
-#include "llvm/CodeGen/MachineInstrBuilder.h"
-#include "llvm/CodeGen/MachineOperand.h"
-#include "llvm/CodeGen/MachineRegisterInfo.h"
-#include "llvm/CodeGen/TargetRegisterInfo.h"
 #include "llvm/InitializePasses.h"
-#include "llvm/Pass.h"
-#include "llvm/Support/CodeGen.h"
-#include "llvm/Support/CommandLine.h"
-#include "llvm/Support/Debug.h"
-#include "llvm/Support/raw_ostream.h"
 #include "llvm/Target/TargetMachine.h"
-#include <cassert>
-#include <cstdint>
-#include <iterator>
-#include <list>
-#include <map>
-#include <tuple>
-#include <utility>
 
 using namespace llvm;
 
diff --git a/llvm/lib/Target/AMDGPU/SIFixVGPRCopies.cpp b/llvm/lib/Target/AMDGPU/SIFixVGPRCopies.cpp
--- a/llvm/lib/Target/AMDGPU/SIFixVGPRCopies.cpp
+++ b/llvm/lib/Target/AMDGPU/SIFixVGPRCopies.cpp
@@ -13,8 +13,6 @@
 
 #include "AMDGPU.h"
 #include "AMDGPUSubtarget.h"
-#include "SIInstrInfo.h"
-#include "MCTargetDesc/AMDGPUMCTargetDesc.h"
 #include "llvm/CodeGen/MachineFunctionPass.h"
 
 using namespace llvm;
diff --git a/llvm/lib/Target/AMDGPU/SIFoldOperands.cpp b/llvm/lib/Target/AMDGPU/SIFoldOperands.cpp
--- a/llvm/lib/Target/AMDGPU/SIFoldOperands.cpp
+++ b/llvm/lib/Target/AMDGPU/SIFoldOperands.cpp
@@ -10,17 +10,9 @@
 
 #include "AMDGPU.h"
 #include "AMDGPUSubtarget.h"
-#include "SIInstrInfo.h"
 #include "SIMachineFunctionInfo.h"
-#include "MCTargetDesc/AMDGPUMCTargetDesc.h"
 #include "llvm/ADT/DepthFirstIterator.h"
-#include "llvm/ADT/SetVector.h"
 #include "llvm/CodeGen/MachineFunctionPass.h"
-#include "llvm/CodeGen/MachineInstrBuilder.h"
-#include "llvm/CodeGen/MachineRegisterInfo.h"
-#include "llvm/Support/Debug.h"
-#include "llvm/Support/raw_ostream.h"
-#include "llvm/Target/TargetMachine.h"
 
 #define DEBUG_TYPE "si-fold-operands"
 using namespace llvm;
diff --git a/llvm/lib/Target/AMDGPU/SIFormMemoryClauses.cpp b/llvm/lib/Target/AMDGPU/SIFormMemoryClauses.cpp
--- a/llvm/lib/Target/AMDGPU/SIFormMemoryClauses.cpp
+++ b/llvm/lib/Target/AMDGPU/SIFormMemoryClauses.cpp
@@ -16,13 +16,7 @@
 #include "AMDGPU.h"
 #include "AMDGPUSubtarget.h"
 #include "GCNRegPressure.h"
-#include "MCTargetDesc/AMDGPUMCTargetDesc.h"
-#include "SIInstrInfo.h"
 #include "SIMachineFunctionInfo.h"
-#include "SIRegisterInfo.h"
-#include "llvm/ADT/DenseMap.h"
-#include "llvm/CodeGen/LiveIntervals.h"
-#include "llvm/CodeGen/MachineFunctionPass.h"
 #include "llvm/InitializePasses.h"
 
 using namespace llvm;
diff --git a/llvm/lib/Target/AMDGPU/SIFrameLowering.h b/llvm/lib/Target/AMDGPU/SIFrameLowering.h
--- a/llvm/lib/Target/AMDGPU/SIFrameLowering.h
+++ b/llvm/lib/Target/AMDGPU/SIFrameLowering.h
@@ -10,7 +10,6 @@
 #define LLVM_LIB_TARGET_AMDGPU_SIFRAMELOWERING_H
 
 #include "AMDGPUFrameLowering.h"
-#include "llvm/Support/TypeSize.h"
 
 namespace llvm {
 
diff --git a/llvm/lib/Target/AMDGPU/SIFrameLowering.cpp b/llvm/lib/Target/AMDGPU/SIFrameLowering.cpp
--- a/llvm/lib/Target/AMDGPU/SIFrameLowering.cpp
+++ b/llvm/lib/Target/AMDGPU/SIFrameLowering.cpp
@@ -7,17 +7,13 @@
 //==-----------------------------------------------------------------------===//
 
 #include "SIFrameLowering.h"
+#include "AMDGPU.h"
 #include "AMDGPUSubtarget.h"
-#include "SIInstrInfo.h"
 #include "SIMachineFunctionInfo.h"
-#include "SIRegisterInfo.h"
-#include "MCTargetDesc/AMDGPUMCTargetDesc.h"
-
 #include "llvm/CodeGen/LivePhysRegs.h"
 #include "llvm/CodeGen/MachineFrameInfo.h"
-#include "llvm/CodeGen/MachineFunction.h"
-#include "llvm/CodeGen/MachineInstrBuilder.h"
 #include "llvm/CodeGen/RegisterScavenging.h"
+#include "llvm/Target/TargetMachine.h"
 
 using namespace llvm;
 
diff --git a/llvm/lib/Target/AMDGPU/SIISelLowering.h b/llvm/lib/Target/AMDGPU/SIISelLowering.h
--- a/llvm/lib/Target/AMDGPU/SIISelLowering.h
+++ b/llvm/lib/Target/AMDGPU/SIISelLowering.h
@@ -16,10 +16,17 @@
 
 #include "AMDGPUISelLowering.h"
 #include "AMDGPUArgumentUsageInfo.h"
-#include "SIInstrInfo.h"
 
 namespace llvm {
 
+class GCNSubtarget;
+class SIMachineFunctionInfo;
+class SIRegisterInfo;
+
+namespace AMDGPU {
+struct ImageDimIntrinsicInfo;
+}
+
 class SITargetLowering final : public AMDGPUTargetLowering {
 private:
   const GCNSubtarget *Subtarget;
@@ -285,10 +292,7 @@
   bool isMemOpUniform(const SDNode *N) const;
   bool isMemOpHasNoClobberedMemOperand(const SDNode *N) const;
 
-  static bool isNonGlobalAddrSpace(unsigned AS) {
-    return AS == AMDGPUAS::LOCAL_ADDRESS || AS == AMDGPUAS::REGION_ADDRESS ||
-           AS == AMDGPUAS::PRIVATE_ADDRESS;
-  }
+  static bool isNonGlobalAddrSpace(unsigned AS);
 
   bool isFreeAddrSpaceCast(unsigned SrcAS, unsigned DestAS) const override;
 
diff --git a/llvm/lib/Target/AMDGPU/SIISelLowering.cpp b/llvm/lib/Target/AMDGPU/SIISelLowering.cpp
--- a/llvm/lib/Target/AMDGPU/SIISelLowering.cpp
+++ b/llvm/lib/Target/AMDGPU/SIISelLowering.cpp
@@ -13,73 +13,22 @@
 
 #include "SIISelLowering.h"
 #include "AMDGPU.h"
+#include "AMDGPUInstrInfo.h"
 #include "AMDGPUSubtarget.h"
 #include "AMDGPUTargetMachine.h"
-#include "MCTargetDesc/AMDGPUMCTargetDesc.h"
-#include "SIDefines.h"
-#include "SIInstrInfo.h"
 #include "SIMachineFunctionInfo.h"
 #include "SIRegisterInfo.h"
-#include "Utils/AMDGPUBaseInfo.h"
-#include "llvm/ADT/APFloat.h"
-#include "llvm/ADT/APInt.h"
-#include "llvm/ADT/ArrayRef.h"
-#include "llvm/ADT/BitVector.h"
-#include "llvm/ADT/SmallVector.h"
 #include "llvm/ADT/Statistic.h"
-#include "llvm/ADT/StringRef.h"
-#include "llvm/ADT/StringSwitch.h"
-#include "llvm/ADT/Twine.h"
 #include "llvm/Analysis/LegacyDivergenceAnalysis.h"
 #include "llvm/CodeGen/Analysis.h"
-#include "llvm/CodeGen/CallingConvLower.h"
-#include "llvm/CodeGen/DAGCombine.h"
 #include "llvm/CodeGen/FunctionLoweringInfo.h"
 #include "llvm/CodeGen/GlobalISel/GISelKnownBits.h"
-#include "llvm/CodeGen/ISDOpcodes.h"
-#include "llvm/CodeGen/MachineBasicBlock.h"
-#include "llvm/CodeGen/MachineFrameInfo.h"
-#include "llvm/CodeGen/MachineFunction.h"
-#include "llvm/CodeGen/MachineInstr.h"
-#include "llvm/CodeGen/MachineInstrBuilder.h"
 #include "llvm/CodeGen/MachineLoopInfo.h"
-#include "llvm/CodeGen/MachineMemOperand.h"
-#include "llvm/CodeGen/MachineModuleInfo.h"
-#include "llvm/CodeGen/MachineOperand.h"
-#include "llvm/CodeGen/MachineRegisterInfo.h"
-#include "llvm/CodeGen/SelectionDAG.h"
-#include "llvm/CodeGen/SelectionDAGNodes.h"
-#include "llvm/CodeGen/TargetCallingConv.h"
-#include "llvm/CodeGen/TargetRegisterInfo.h"
-#include "llvm/CodeGen/ValueTypes.h"
-#include "llvm/IR/Constants.h"
-#include "llvm/IR/DataLayout.h"
-#include "llvm/IR/DebugLoc.h"
-#include "llvm/IR/DerivedTypes.h"
 #include "llvm/IR/DiagnosticInfo.h"
-#include "llvm/IR/Function.h"
-#include "llvm/IR/GlobalValue.h"
-#include "llvm/IR/InstrTypes.h"
-#include "llvm/IR/Instruction.h"
-#include "llvm/IR/Instructions.h"
-#include "llvm/IR/IntrinsicInst.h"
-#include "llvm/IR/Type.h"
-#include "llvm/Support/Casting.h"
-#include "llvm/Support/CodeGen.h"
+#include "llvm/IR/IntrinsicsAMDGPU.h"
+#include "llvm/IR/IntrinsicsR600.h"
 #include "llvm/Support/CommandLine.h"
-#include "llvm/Support/Compiler.h"
-#include "llvm/Support/ErrorHandling.h"
 #include "llvm/Support/KnownBits.h"
-#include "llvm/Support/MachineValueType.h"
-#include "llvm/Support/MathExtras.h"
-#include "llvm/Target/TargetOptions.h"
-#include <cassert>
-#include <cmath>
-#include <cstdint>
-#include <iterator>
-#include <tuple>
-#include <utility>
-#include <vector>
 
 using namespace llvm;
 
@@ -1565,6 +1514,11 @@
   return I && I->getMetadata("amdgpu.noclobber");
 }
 
+bool SITargetLowering::isNonGlobalAddrSpace(unsigned AS) {
+  return AS == AMDGPUAS::LOCAL_ADDRESS || AS == AMDGPUAS::REGION_ADDRESS ||
+         AS == AMDGPUAS::PRIVATE_ADDRESS;
+}
+
 bool SITargetLowering::isFreeAddrSpaceCast(unsigned SrcAS,
                                            unsigned DestAS) const {
   // Flat -> private/local is a simple truncate.
diff --git a/llvm/lib/Target/AMDGPU/SIInsertHardClauses.cpp b/llvm/lib/Target/AMDGPU/SIInsertHardClauses.cpp
--- a/llvm/lib/Target/AMDGPU/SIInsertHardClauses.cpp
+++ b/llvm/lib/Target/AMDGPU/SIInsertHardClauses.cpp
@@ -31,8 +31,8 @@
 //
 //===----------------------------------------------------------------------===//
 
+#include "AMDGPU.h"
 #include "AMDGPUSubtarget.h"
-#include "SIInstrInfo.h"
 #include "llvm/ADT/SmallVector.h"
 
 using namespace llvm;
diff --git a/llvm/lib/Target/AMDGPU/SIInsertSkips.cpp b/llvm/lib/Target/AMDGPU/SIInsertSkips.cpp
--- a/llvm/lib/Target/AMDGPU/SIInsertSkips.cpp
+++ b/llvm/lib/Target/AMDGPU/SIInsertSkips.cpp
@@ -15,29 +15,9 @@
 
 #include "AMDGPU.h"
 #include "AMDGPUSubtarget.h"
-#include "SIInstrInfo.h"
-#include "SIMachineFunctionInfo.h"
-#include "MCTargetDesc/AMDGPUMCTargetDesc.h"
 #include "llvm/ADT/DepthFirstIterator.h"
-#include "llvm/ADT/SmallVector.h"
-#include "llvm/ADT/StringRef.h"
-#include "llvm/CodeGen/MachineBasicBlock.h"
 #include "llvm/CodeGen/MachineDominators.h"
-#include "llvm/CodeGen/MachineFunction.h"
-#include "llvm/CodeGen/MachineFunctionPass.h"
-#include "llvm/CodeGen/MachineInstr.h"
-#include "llvm/CodeGen/MachineInstrBuilder.h"
-#include "llvm/CodeGen/MachineOperand.h"
-#include "llvm/IR/CallingConv.h"
-#include "llvm/IR/DebugLoc.h"
 #include "llvm/InitializePasses.h"
-#include "llvm/MC/MCAsmInfo.h"
-#include "llvm/Pass.h"
-#include "llvm/Support/CommandLine.h"
-#include "llvm/Target/TargetMachine.h"
-#include <cassert>
-#include <cstdint>
-#include <iterator>
 
 using namespace llvm;
 
diff --git a/llvm/lib/Target/AMDGPU/SIInsertWaitcnts.cpp b/llvm/lib/Target/AMDGPU/SIInsertWaitcnts.cpp
--- a/llvm/lib/Target/AMDGPU/SIInsertWaitcnts.cpp
+++ b/llvm/lib/Target/AMDGPU/SIInsertWaitcnts.cpp
@@ -25,40 +25,13 @@
 
 #include "AMDGPU.h"
 #include "AMDGPUSubtarget.h"
-#include "SIDefines.h"
-#include "SIInstrInfo.h"
 #include "SIMachineFunctionInfo.h"
-#include "SIRegisterInfo.h"
-#include "Utils/AMDGPUBaseInfo.h"
-#include "llvm/ADT/DenseMap.h"
-#include "llvm/ADT/DenseSet.h"
 #include "llvm/ADT/MapVector.h"
 #include "llvm/ADT/PostOrderIterator.h"
-#include "llvm/ADT/STLExtras.h"
-#include "llvm/ADT/SmallVector.h"
-#include "llvm/CodeGen/MachineBasicBlock.h"
-#include "llvm/CodeGen/MachineFunction.h"
-#include "llvm/CodeGen/MachineFunctionPass.h"
-#include "llvm/CodeGen/MachineInstr.h"
-#include "llvm/CodeGen/MachineInstrBuilder.h"
-#include "llvm/CodeGen/MachineMemOperand.h"
-#include "llvm/CodeGen/MachineOperand.h"
 #include "llvm/CodeGen/MachinePostDominators.h"
-#include "llvm/CodeGen/MachineRegisterInfo.h"
 #include "llvm/InitializePasses.h"
-#include "llvm/IR/DebugLoc.h"
-#include "llvm/Pass.h"
-#include "llvm/Support/Debug.h"
 #include "llvm/Support/DebugCounter.h"
-#include "llvm/Support/ErrorHandling.h"
-#include "llvm/Support/raw_ostream.h"
-#include <algorithm>
-#include <cassert>
-#include <cstdint>
-#include <cstring>
-#include <memory>
-#include <utility>
-
+#include "llvm/Support/TargetParser.h"
 using namespace llvm;
 
 #define DEBUG_TYPE "si-insert-waitcnts"
diff --git a/llvm/lib/Target/AMDGPU/SIInstrInfo.h b/llvm/lib/Target/AMDGPU/SIInstrInfo.h
--- a/llvm/lib/Target/AMDGPU/SIInstrInfo.h
+++ b/llvm/lib/Target/AMDGPU/SIInstrInfo.h
@@ -14,22 +14,11 @@
 #ifndef LLVM_LIB_TARGET_AMDGPU_SIINSTRINFO_H
 #define LLVM_LIB_TARGET_AMDGPU_SIINSTRINFO_H
 
-#include "AMDGPUInstrInfo.h"
-#include "SIDefines.h"
 #include "SIRegisterInfo.h"
 #include "Utils/AMDGPUBaseInfo.h"
-#include "llvm/ADT/ArrayRef.h"
 #include "llvm/ADT/SetVector.h"
-#include "llvm/CodeGen/MachineBasicBlock.h"
-#include "llvm/CodeGen/MachineFunction.h"
-#include "llvm/CodeGen/MachineInstr.h"
-#include "llvm/CodeGen/MachineInstrBuilder.h"
-#include "llvm/CodeGen/MachineOperand.h"
+#include "llvm/CodeGen/TargetInstrInfo.h"
 #include "llvm/CodeGen/TargetSchedule.h"
-#include "llvm/MC/MCInstrDesc.h"
-#include "llvm/Support/Compiler.h"
-#include <cassert>
-#include <cstdint>
 
 #define GET_INSTRINFO_HEADER
 #include "AMDGPUGenInstrInfo.inc"
@@ -37,11 +26,13 @@
 namespace llvm {
 
 class APInt;
+class GCNSubtarget;
+class LiveVariables;
 class MachineDominatorTree;
 class MachineRegisterInfo;
 class RegScavenger;
-class GCNSubtarget;
 class TargetRegisterClass;
+class ScheduleHazardRecognizer;
 
 class SIInstrInfo final : public AMDGPUGenInstrInfo {
 private:
diff --git a/llvm/lib/Target/AMDGPU/SIInstrInfo.cpp b/llvm/lib/Target/AMDGPU/SIInstrInfo.cpp
--- a/llvm/lib/Target/AMDGPU/SIInstrInfo.cpp
+++ b/llvm/lib/Target/AMDGPU/SIInstrInfo.cpp
@@ -13,53 +13,19 @@
 
 #include "SIInstrInfo.h"
 #include "AMDGPU.h"
+#include "AMDGPUInstrInfo.h"
 #include "AMDGPUSubtarget.h"
 #include "GCNHazardRecognizer.h"
-#include "MCTargetDesc/AMDGPUMCTargetDesc.h"
-#include "SIDefines.h"
 #include "SIMachineFunctionInfo.h"
-#include "SIRegisterInfo.h"
-#include "Utils/AMDGPUBaseInfo.h"
-#include "llvm/ADT/APInt.h"
-#include "llvm/ADT/ArrayRef.h"
-#include "llvm/ADT/SmallVector.h"
-#include "llvm/ADT/StringRef.h"
-#include "llvm/ADT/iterator_range.h"
-#include "llvm/Analysis/MemoryLocation.h"
 #include "llvm/Analysis/ValueTracking.h"
 #include "llvm/CodeGen/LiveVariables.h"
-#include "llvm/CodeGen/MachineBasicBlock.h"
 #include "llvm/CodeGen/MachineDominators.h"
-#include "llvm/CodeGen/MachineFrameInfo.h"
-#include "llvm/CodeGen/MachineFunction.h"
-#include "llvm/CodeGen/MachineInstr.h"
-#include "llvm/CodeGen/MachineInstrBuilder.h"
-#include "llvm/CodeGen/MachineInstrBundle.h"
-#include "llvm/CodeGen/MachineMemOperand.h"
-#include "llvm/CodeGen/MachineOperand.h"
-#include "llvm/CodeGen/MachineRegisterInfo.h"
 #include "llvm/CodeGen/RegisterScavenging.h"
 #include "llvm/CodeGen/ScheduleDAG.h"
-#include "llvm/CodeGen/SelectionDAGNodes.h"
-#include "llvm/CodeGen/TargetOpcodes.h"
-#include "llvm/CodeGen/TargetRegisterInfo.h"
-#include "llvm/IR/DebugLoc.h"
 #include "llvm/IR/DiagnosticInfo.h"
-#include "llvm/IR/Function.h"
-#include "llvm/IR/InlineAsm.h"
-#include "llvm/IR/LLVMContext.h"
-#include "llvm/MC/MCInstrDesc.h"
-#include "llvm/Support/Casting.h"
+#include "llvm/IR/IntrinsicsAMDGPU.h"
 #include "llvm/Support/CommandLine.h"
-#include "llvm/Support/Compiler.h"
-#include "llvm/Support/ErrorHandling.h"
-#include "llvm/Support/MachineValueType.h"
-#include "llvm/Support/MathExtras.h"
 #include "llvm/Target/TargetMachine.h"
-#include <cassert>
-#include <cstdint>
-#include <iterator>
-#include <utility>
 
 using namespace llvm;
 
diff --git a/llvm/lib/Target/AMDGPU/SILoadStoreOptimizer.cpp b/llvm/lib/Target/AMDGPU/SILoadStoreOptimizer.cpp
--- a/llvm/lib/Target/AMDGPU/SILoadStoreOptimizer.cpp
+++ b/llvm/lib/Target/AMDGPU/SILoadStoreOptimizer.cpp
@@ -59,32 +59,9 @@
 
 #include "AMDGPU.h"
 #include "AMDGPUSubtarget.h"
-#include "MCTargetDesc/AMDGPUMCTargetDesc.h"
-#include "SIInstrInfo.h"
-#include "SIRegisterInfo.h"
-#include "Utils/AMDGPUBaseInfo.h"
-#include "llvm/ADT/ArrayRef.h"
-#include "llvm/ADT/SmallVector.h"
-#include "llvm/ADT/StringRef.h"
 #include "llvm/Analysis/AliasAnalysis.h"
-#include "llvm/CodeGen/MachineBasicBlock.h"
-#include "llvm/CodeGen/MachineFunction.h"
 #include "llvm/CodeGen/MachineFunctionPass.h"
-#include "llvm/CodeGen/MachineInstr.h"
-#include "llvm/CodeGen/MachineInstrBuilder.h"
-#include "llvm/CodeGen/MachineOperand.h"
-#include "llvm/CodeGen/MachineRegisterInfo.h"
-#include "llvm/IR/DebugLoc.h"
 #include "llvm/InitializePasses.h"
-#include "llvm/Pass.h"
-#include "llvm/Support/Debug.h"
-#include "llvm/Support/MathExtras.h"
-#include "llvm/Support/raw_ostream.h"
-#include <algorithm>
-#include <cassert>
-#include <cstdlib>
-#include <iterator>
-#include <utility>
 
 using namespace llvm;
 
diff --git a/llvm/lib/Target/AMDGPU/SILowerControlFlow.cpp b/llvm/lib/Target/AMDGPU/SILowerControlFlow.cpp
--- a/llvm/lib/Target/AMDGPU/SILowerControlFlow.cpp
+++ b/llvm/lib/Target/AMDGPU/SILowerControlFlow.cpp
@@ -49,27 +49,9 @@
 
 #include "AMDGPU.h"
 #include "AMDGPUSubtarget.h"
-#include "SIInstrInfo.h"
-#include "MCTargetDesc/AMDGPUMCTargetDesc.h"
-#include "llvm/ADT/SetVector.h"
 #include "llvm/ADT/SmallSet.h"
-#include "llvm/ADT/SmallVector.h"
-#include "llvm/ADT/StringRef.h"
 #include "llvm/CodeGen/LiveIntervals.h"
-#include "llvm/CodeGen/MachineBasicBlock.h"
-#include "llvm/CodeGen/MachineFunction.h"
 #include "llvm/CodeGen/MachineFunctionPass.h"
-#include "llvm/CodeGen/MachineInstr.h"
-#include "llvm/CodeGen/MachineInstrBuilder.h"
-#include "llvm/CodeGen/MachineOperand.h"
-#include "llvm/CodeGen/MachineRegisterInfo.h"
-#include "llvm/CodeGen/Passes.h"
-#include "llvm/CodeGen/SlotIndexes.h"
-#include "llvm/CodeGen/TargetRegisterInfo.h"
-#include "llvm/MC/MCRegisterInfo.h"
-#include "llvm/Pass.h"
-#include <cassert>
-#include <iterator>
 
 using namespace llvm;
 
diff --git a/llvm/lib/Target/AMDGPU/SILowerI1Copies.cpp b/llvm/lib/Target/AMDGPU/SILowerI1Copies.cpp
--- a/llvm/lib/Target/AMDGPU/SILowerI1Copies.cpp
+++ b/llvm/lib/Target/AMDGPU/SILowerI1Copies.cpp
@@ -23,19 +23,11 @@
 
 #include "AMDGPU.h"
 #include "AMDGPUSubtarget.h"
-#include "MCTargetDesc/AMDGPUMCTargetDesc.h"
-#include "SIInstrInfo.h"
 #include "llvm/CodeGen/MachineDominators.h"
 #include "llvm/CodeGen/MachineFunctionPass.h"
-#include "llvm/CodeGen/MachineInstrBuilder.h"
 #include "llvm/CodeGen/MachinePostDominators.h"
-#include "llvm/CodeGen/MachineRegisterInfo.h"
 #include "llvm/CodeGen/MachineSSAUpdater.h"
-#include "llvm/IR/Function.h"
-#include "llvm/IR/LLVMContext.h"
 #include "llvm/InitializePasses.h"
-#include "llvm/Support/Debug.h"
-#include "llvm/Target/TargetMachine.h"
 
 #define DEBUG_TYPE "si-i1-copies"
 
diff --git a/llvm/lib/Target/AMDGPU/SILowerSGPRSpills.cpp b/llvm/lib/Target/AMDGPU/SILowerSGPRSpills.cpp
--- a/llvm/lib/Target/AMDGPU/SILowerSGPRSpills.cpp
+++ b/llvm/lib/Target/AMDGPU/SILowerSGPRSpills.cpp
@@ -17,19 +17,10 @@
 
 #include "AMDGPU.h"
 #include "AMDGPUSubtarget.h"
-#include "SIInstrInfo.h"
 #include "SIMachineFunctionInfo.h"
 #include "llvm/CodeGen/LiveIntervals.h"
-#include "llvm/CodeGen/MachineBasicBlock.h"
-#include "llvm/CodeGen/MachineFunction.h"
-#include "llvm/CodeGen/MachineFunctionPass.h"
-#include "llvm/CodeGen/MachineInstr.h"
-#include "llvm/CodeGen/MachineInstrBuilder.h"
-#include "llvm/CodeGen/MachineOperand.h"
 #include "llvm/CodeGen/RegisterScavenging.h"
-#include "llvm/CodeGen/VirtRegMap.h"
 #include "llvm/InitializePasses.h"
-#include "llvm/Target/TargetMachine.h"
 
 using namespace llvm;
 
diff --git a/llvm/lib/Target/AMDGPU/SIMachineFunctionInfo.h b/llvm/lib/Target/AMDGPU/SIMachineFunctionInfo.h
--- a/llvm/lib/Target/AMDGPU/SIMachineFunctionInfo.h
+++ b/llvm/lib/Target/AMDGPU/SIMachineFunctionInfo.h
@@ -17,28 +17,17 @@
 #include "AMDGPUMachineFunction.h"
 #include "MCTargetDesc/AMDGPUMCTargetDesc.h"
 #include "SIInstrInfo.h"
-#include "SIRegisterInfo.h"
-#include "llvm/ADT/ArrayRef.h"
-#include "llvm/ADT/DenseMap.h"
-#include "llvm/ADT/Optional.h"
-#include "llvm/ADT/STLExtras.h"
-#include "llvm/ADT/SmallVector.h"
-#include "llvm/ADT/SparseBitVector.h"
 #include "llvm/CodeGen/MIRYamlMapping.h"
 #include "llvm/CodeGen/PseudoSourceValue.h"
-#include "llvm/CodeGen/TargetInstrInfo.h"
-#include "llvm/MC/MCRegisterInfo.h"
-#include "llvm/Support/ErrorHandling.h"
-#include <array>
-#include <cassert>
-#include <utility>
-#include <vector>
+#include "llvm/Support/raw_ostream.h"
 
 namespace llvm {
 
 class MachineFrameInfo;
 class MachineFunction;
 class TargetRegisterClass;
+class SIMachineFunctionInfo;
+class SIRegisterInfo;
 
 class AMDGPUPseudoSourceValue : public PseudoSourceValue {
 public:
diff --git a/llvm/lib/Target/AMDGPU/SIMachineFunctionInfo.cpp b/llvm/lib/Target/AMDGPU/SIMachineFunctionInfo.cpp
--- a/llvm/lib/Target/AMDGPU/SIMachineFunctionInfo.cpp
+++ b/llvm/lib/Target/AMDGPU/SIMachineFunctionInfo.cpp
@@ -7,21 +7,8 @@
 //===----------------------------------------------------------------------===//
 
 #include "SIMachineFunctionInfo.h"
-#include "AMDGPUArgumentUsageInfo.h"
 #include "AMDGPUTargetMachine.h"
 #include "AMDGPUSubtarget.h"
-#include "SIRegisterInfo.h"
-#include "MCTargetDesc/AMDGPUMCTargetDesc.h"
-#include "Utils/AMDGPUBaseInfo.h"
-#include "llvm/ADT/Optional.h"
-#include "llvm/CodeGen/MachineBasicBlock.h"
-#include "llvm/CodeGen/MachineFrameInfo.h"
-#include "llvm/CodeGen/MachineFunction.h"
-#include "llvm/CodeGen/MachineRegisterInfo.h"
-#include "llvm/IR/CallingConv.h"
-#include "llvm/IR/Function.h"
-#include <cassert>
-#include <vector>
 
 #define MAX_LANES 64
 
diff --git a/llvm/lib/Target/AMDGPU/SIMachineScheduler.h b/llvm/lib/Target/AMDGPU/SIMachineScheduler.h
--- a/llvm/lib/Target/AMDGPU/SIMachineScheduler.h
+++ b/llvm/lib/Target/AMDGPU/SIMachineScheduler.h
@@ -14,20 +14,18 @@
 #ifndef LLVM_LIB_TARGET_AMDGPU_SIMACHINESCHEDULER_H
 #define LLVM_LIB_TARGET_AMDGPU_SIMACHINESCHEDULER_H
 
-#include "SIInstrInfo.h"
-#include "llvm/CodeGen/MachineBasicBlock.h"
 #include "llvm/CodeGen/MachineScheduler.h"
 #include "llvm/CodeGen/RegisterPressure.h"
 #include "llvm/CodeGen/ScheduleDAG.h"
-#include <cassert>
 #include <cstdint>
-#include <map>
-#include <memory>
 #include <set>
 #include <vector>
 
 namespace llvm {
 
+class SIInstrInfo;
+class SIRegisterInfo;
+
 enum SIScheduleCandReason {
   NoCand,
   RegUsage,
diff --git a/llvm/lib/Target/AMDGPU/SIMachineScheduler.cpp b/llvm/lib/Target/AMDGPU/SIMachineScheduler.cpp
--- a/llvm/lib/Target/AMDGPU/SIMachineScheduler.cpp
+++ b/llvm/lib/Target/AMDGPU/SIMachineScheduler.cpp
@@ -12,29 +12,10 @@
 //===----------------------------------------------------------------------===//
 
 #include "SIMachineScheduler.h"
-#include "AMDGPU.h"
 #include "SIInstrInfo.h"
-#include "SIRegisterInfo.h"
 #include "MCTargetDesc/AMDGPUMCTargetDesc.h"
-#include "llvm/ADT/STLExtras.h"
-#include "llvm/ADT/SmallVector.h"
-#include "llvm/CodeGen/LiveInterval.h"
 #include "llvm/CodeGen/LiveIntervals.h"
-#include "llvm/CodeGen/MachineInstr.h"
 #include "llvm/CodeGen/MachineRegisterInfo.h"
-#include "llvm/CodeGen/MachineScheduler.h"
-#include "llvm/CodeGen/RegisterPressure.h"
-#include "llvm/CodeGen/SlotIndexes.h"
-#include "llvm/CodeGen/TargetRegisterInfo.h"
-#include "llvm/Support/Debug.h"
-#include "llvm/Support/ErrorHandling.h"
-#include "llvm/Support/raw_ostream.h"
-#include <algorithm>
-#include <cassert>
-#include <map>
-#include <set>
-#include <utility>
-#include <vector>
 
 using namespace llvm;
 
diff --git a/llvm/lib/Target/AMDGPU/SIMemoryLegalizer.cpp b/llvm/lib/Target/AMDGPU/SIMemoryLegalizer.cpp
--- a/llvm/lib/Target/AMDGPU/SIMemoryLegalizer.cpp
+++ b/llvm/lib/Target/AMDGPU/SIMemoryLegalizer.cpp
@@ -16,30 +16,11 @@
 #include "AMDGPU.h"
 #include "AMDGPUMachineModuleInfo.h"
 #include "AMDGPUSubtarget.h"
-#include "SIDefines.h"
-#include "SIInstrInfo.h"
-#include "MCTargetDesc/AMDGPUMCTargetDesc.h"
-#include "Utils/AMDGPUBaseInfo.h"
 #include "llvm/ADT/BitmaskEnum.h"
-#include "llvm/ADT/None.h"
-#include "llvm/ADT/Optional.h"
 #include "llvm/CodeGen/MachineBasicBlock.h"
-#include "llvm/CodeGen/MachineFunction.h"
-#include "llvm/CodeGen/MachineFunctionPass.h"
-#include "llvm/CodeGen/MachineInstrBuilder.h"
-#include "llvm/CodeGen/MachineMemOperand.h"
-#include "llvm/CodeGen/MachineModuleInfo.h"
-#include "llvm/CodeGen/MachineOperand.h"
-#include "llvm/IR/DebugLoc.h"
 #include "llvm/IR/DiagnosticInfo.h"
-#include "llvm/IR/Function.h"
-#include "llvm/IR/LLVMContext.h"
-#include "llvm/MC/MCInstrDesc.h"
-#include "llvm/Pass.h"
 #include "llvm/Support/AtomicOrdering.h"
-#include "llvm/Support/MathExtras.h"
-#include <cassert>
-#include <list>
+#include "llvm/Support/TargetParser.h"
 
 using namespace llvm;
 using namespace llvm::AMDGPU;
diff --git a/llvm/lib/Target/AMDGPU/SIModeRegister.cpp b/llvm/lib/Target/AMDGPU/SIModeRegister.cpp
--- a/llvm/lib/Target/AMDGPU/SIModeRegister.cpp
+++ b/llvm/lib/Target/AMDGPU/SIModeRegister.cpp
@@ -14,20 +14,8 @@
 //===----------------------------------------------------------------------===//
 //
 #include "AMDGPU.h"
-#include "AMDGPUInstrInfo.h"
 #include "AMDGPUSubtarget.h"
-#include "SIInstrInfo.h"
-#include "SIMachineFunctionInfo.h"
 #include "llvm/ADT/Statistic.h"
-#include "llvm/CodeGen/MachineFunctionPass.h"
-#include "llvm/CodeGen/MachineInstrBuilder.h"
-#include "llvm/CodeGen/MachineRegisterInfo.h"
-#include "llvm/IR/Constants.h"
-#include "llvm/IR/Function.h"
-#include "llvm/IR/LLVMContext.h"
-#include "llvm/Support/Debug.h"
-#include "llvm/Support/raw_ostream.h"
-#include "llvm/Target/TargetMachine.h"
 #include <queue>
 
 #define DEBUG_TYPE "si-mode-register"
diff --git a/llvm/lib/Target/AMDGPU/SIOptimizeExecMasking.cpp b/llvm/lib/Target/AMDGPU/SIOptimizeExecMasking.cpp
--- a/llvm/lib/Target/AMDGPU/SIOptimizeExecMasking.cpp
+++ b/llvm/lib/Target/AMDGPU/SIOptimizeExecMasking.cpp
@@ -8,14 +8,8 @@
 
 #include "AMDGPU.h"
 #include "AMDGPUSubtarget.h"
-#include "MCTargetDesc/AMDGPUMCTargetDesc.h"
-#include "SIInstrInfo.h"
-#include "llvm/ADT/SmallSet.h"
 #include "llvm/CodeGen/MachineFunctionPass.h"
-#include "llvm/CodeGen/MachineInstrBuilder.h"
-#include "llvm/CodeGen/MachineRegisterInfo.h"
 #include "llvm/InitializePasses.h"
-#include "llvm/Support/Debug.h"
 
 using namespace llvm;
 
diff --git a/llvm/lib/Target/AMDGPU/SIOptimizeExecMaskingPreRA.cpp b/llvm/lib/Target/AMDGPU/SIOptimizeExecMaskingPreRA.cpp
--- a/llvm/lib/Target/AMDGPU/SIOptimizeExecMaskingPreRA.cpp
+++ b/llvm/lib/Target/AMDGPU/SIOptimizeExecMaskingPreRA.cpp
@@ -14,8 +14,6 @@
 
 #include "AMDGPU.h"
 #include "AMDGPUSubtarget.h"
-#include "MCTargetDesc/AMDGPUMCTargetDesc.h"
-#include "SIInstrInfo.h"
 #include "llvm/CodeGen/LiveIntervals.h"
 #include "llvm/CodeGen/MachineFunctionPass.h"
 #include "llvm/InitializePasses.h"
diff --git a/llvm/lib/Target/AMDGPU/SIPeepholeSDWA.cpp b/llvm/lib/Target/AMDGPU/SIPeepholeSDWA.cpp
--- a/llvm/lib/Target/AMDGPU/SIPeepholeSDWA.cpp
+++ b/llvm/lib/Target/AMDGPU/SIPeepholeSDWA.cpp
@@ -21,36 +21,9 @@
 
 #include "AMDGPU.h"
 #include "AMDGPUSubtarget.h"
-#include "SIDefines.h"
-#include "SIInstrInfo.h"
-#include "SIRegisterInfo.h"
-#include "MCTargetDesc/AMDGPUMCTargetDesc.h"
-#include "Utils/AMDGPUBaseInfo.h"
 #include "llvm/ADT/MapVector.h"
-#include "llvm/ADT/None.h"
-#include "llvm/ADT/Optional.h"
-#include "llvm/ADT/STLExtras.h"
-#include "llvm/ADT/SmallVector.h"
 #include "llvm/ADT/Statistic.h"
-#include "llvm/CodeGen/MachineBasicBlock.h"
-#include "llvm/CodeGen/MachineFunction.h"
 #include "llvm/CodeGen/MachineFunctionPass.h"
-#include "llvm/CodeGen/MachineInstr.h"
-#include "llvm/CodeGen/MachineInstrBuilder.h"
-#include "llvm/CodeGen/MachineOperand.h"
-#include "llvm/CodeGen/MachineRegisterInfo.h"
-#include "llvm/CodeGen/TargetRegisterInfo.h"
-#include "llvm/Config/llvm-config.h"
-#include "llvm/MC/LaneBitmask.h"
-#include "llvm/MC/MCInstrDesc.h"
-#include "llvm/Pass.h"
-#include "llvm/Support/Debug.h"
-#include "llvm/Support/raw_ostream.h"
-#include <algorithm>
-#include <cassert>
-#include <cstdint>
-#include <memory>
-#include <unordered_map>
 
 using namespace llvm;
 
diff --git a/llvm/lib/Target/AMDGPU/SIPostRABundler.cpp b/llvm/lib/Target/AMDGPU/SIPostRABundler.cpp
--- a/llvm/lib/Target/AMDGPU/SIPostRABundler.cpp
+++ b/llvm/lib/Target/AMDGPU/SIPostRABundler.cpp
@@ -14,12 +14,8 @@
 
 #include "AMDGPU.h"
 #include "AMDGPUSubtarget.h"
-#include "SIDefines.h"
-#include "SIInstrInfo.h"
 #include "llvm/ADT/SmallSet.h"
 #include "llvm/CodeGen/MachineFunctionPass.h"
-#include "llvm/CodeGen/MachineInstrBundle.h"
-#include "llvm/InitializePasses.h"
 
 using namespace llvm;
 
diff --git a/llvm/lib/Target/AMDGPU/SIPreAllocateWWMRegs.cpp b/llvm/lib/Target/AMDGPU/SIPreAllocateWWMRegs.cpp
--- a/llvm/lib/Target/AMDGPU/SIPreAllocateWWMRegs.cpp
+++ b/llvm/lib/Target/AMDGPU/SIPreAllocateWWMRegs.cpp
@@ -13,18 +13,11 @@
 
 #include "AMDGPU.h"
 #include "AMDGPUSubtarget.h"
-#include "MCTargetDesc/AMDGPUMCTargetDesc.h"
-#include "SIInstrInfo.h"
 #include "SIMachineFunctionInfo.h"
-#include "SIRegisterInfo.h"
 #include "llvm/ADT/PostOrderIterator.h"
-#include "llvm/CodeGen/LiveInterval.h"
 #include "llvm/CodeGen/LiveIntervals.h"
 #include "llvm/CodeGen/LiveRegMatrix.h"
-#include "llvm/CodeGen/MachineDominators.h"
 #include "llvm/CodeGen/MachineFunctionPass.h"
-#include "llvm/CodeGen/RegisterClassInfo.h"
-#include "llvm/CodeGen/VirtRegMap.h"
 #include "llvm/InitializePasses.h"
 
 using namespace llvm;
diff --git a/llvm/lib/Target/AMDGPU/SIPreEmitPeephole.cpp b/llvm/lib/Target/AMDGPU/SIPreEmitPeephole.cpp
--- a/llvm/lib/Target/AMDGPU/SIPreEmitPeephole.cpp
+++ b/llvm/lib/Target/AMDGPU/SIPreEmitPeephole.cpp
@@ -13,11 +13,8 @@
 
 #include "AMDGPU.h"
 #include "AMDGPUSubtarget.h"
-#include "MCTargetDesc/AMDGPUMCTargetDesc.h"
-#include "SIInstrInfo.h"
 #include "SIMachineFunctionInfo.h"
 #include "llvm/CodeGen/MachineFunctionPass.h"
-#include "llvm/Support/CommandLine.h"
 
 using namespace llvm;
 
diff --git a/llvm/lib/Target/AMDGPU/SIRegisterInfo.h b/llvm/lib/Target/AMDGPU/SIRegisterInfo.h
--- a/llvm/lib/Target/AMDGPU/SIRegisterInfo.h
+++ b/llvm/lib/Target/AMDGPU/SIRegisterInfo.h
@@ -17,13 +17,11 @@
 #define GET_REGINFO_HEADER
 #include "AMDGPUGenRegisterInfo.inc"
 
-#include "SIDefines.h"
-#include "llvm/CodeGen/MachineRegisterInfo.h"
-
 namespace llvm {
 
 class GCNSubtarget;
 class LiveIntervals;
+class RegisterBank;
 class SIMachineFunctionInfo;
 
 class SIRegisterInfo final : public AMDGPUGenRegisterInfo {
@@ -155,14 +153,7 @@
     return isSGPRClass(getRegClass(RCID));
   }
 
-  bool isSGPRReg(const MachineRegisterInfo &MRI, Register Reg) const {
-    const TargetRegisterClass *RC;
-    if (Reg.isVirtual())
-      RC = MRI.getRegClass(Reg);
-    else
-      RC = getPhysRegClass(Reg);
-    return isSGPRClass(RC);
-  }
+  bool isSGPRReg(const MachineRegisterInfo &MRI, Register Reg) const;
 
   /// \returns true if this class contains only AGPR registers
   bool isAGPRClass(const TargetRegisterClass *RC) const {
@@ -205,11 +196,7 @@
 
   /// \returns True if operands defined with this operand type can accept
   /// a literal constant (i.e. any 32-bit immediate).
-  bool opCanUseLiteralConstant(unsigned OpType) const {
-    // TODO: 64-bit operands have extending behavior from 32-bit literal.
-    return OpType >= AMDGPU::OPERAND_REG_IMM_FIRST &&
-           OpType <= AMDGPU::OPERAND_REG_IMM_LAST;
-  }
+  bool opCanUseLiteralConstant(unsigned OpType) const;
 
   /// \returns True if operands defined with this operand type can accept
   /// an inline constant. i.e. An integer value in the range (-16, 64) or
diff --git a/llvm/lib/Target/AMDGPU/SIRegisterInfo.cpp b/llvm/lib/Target/AMDGPU/SIRegisterInfo.cpp
--- a/llvm/lib/Target/AMDGPU/SIRegisterInfo.cpp
+++ b/llvm/lib/Target/AMDGPU/SIRegisterInfo.cpp
@@ -12,22 +12,14 @@
 //===----------------------------------------------------------------------===//
 
 #include "SIRegisterInfo.h"
+#include "AMDGPU.h"
 #include "AMDGPURegisterBankInfo.h"
 #include "AMDGPUSubtarget.h"
-#include "SIInstrInfo.h"
-#include "SIMachineFunctionInfo.h"
 #include "MCTargetDesc/AMDGPUInstPrinter.h"
-#include "MCTargetDesc/AMDGPUMCTargetDesc.h"
+#include "SIMachineFunctionInfo.h"
 #include "llvm/CodeGen/LiveIntervals.h"
 #include "llvm/CodeGen/MachineDominators.h"
-#include "llvm/CodeGen/MachineFrameInfo.h"
-#include "llvm/CodeGen/MachineInstrBuilder.h"
 #include "llvm/CodeGen/RegisterScavenging.h"
-#include "llvm/CodeGen/SlotIndexes.h"
-#include "llvm/IR/Function.h"
-#include "llvm/IR/LLVMContext.h"
-#include <vector>
-
 using namespace llvm;
 
 #define GET_REGINFO_TARGET_DESC
@@ -1878,6 +1870,16 @@
   return nullptr;
 }
 
+bool SIRegisterInfo::isSGPRReg(const MachineRegisterInfo &MRI,
+                               Register Reg) const {
+  const TargetRegisterClass *RC;
+  if (Reg.isVirtual())
+    RC = MRI.getRegClass(Reg);
+  else
+    RC = getPhysRegClass(Reg);
+  return isSGPRClass(RC);
+}
+
 // TODO: It might be helpful to have some target specific flags in
 // TargetRegisterClass to mark which classes are VGPRs to make this trivial.
 bool SIRegisterInfo::hasVGPRs(const TargetRegisterClass *RC) const {
@@ -1986,6 +1988,12 @@
   return getCommonSubClass(DefRC, SrcRC) != nullptr;
 }
 
+bool SIRegisterInfo::opCanUseLiteralConstant(unsigned OpType) const {
+  // TODO: 64-bit operands have extending behavior from 32-bit literal.
+  return OpType >= AMDGPU::OPERAND_REG_IMM_FIRST &&
+         OpType <= AMDGPU::OPERAND_REG_IMM_LAST;
+}
+
 /// Returns a lowest register that is not used at any point in the function.
 ///        If all registers are used, then this function will return
 ///         AMDGPU::NoRegister. If \p ReserveHighestVGPR = true, then return
diff --git a/llvm/lib/Target/AMDGPU/SIRemoveShortExecBranches.cpp b/llvm/lib/Target/AMDGPU/SIRemoveShortExecBranches.cpp
--- a/llvm/lib/Target/AMDGPU/SIRemoveShortExecBranches.cpp
+++ b/llvm/lib/Target/AMDGPU/SIRemoveShortExecBranches.cpp
@@ -15,8 +15,6 @@
 
 #include "AMDGPU.h"
 #include "AMDGPUSubtarget.h"
-#include "MCTargetDesc/AMDGPUMCTargetDesc.h"
-#include "SIInstrInfo.h"
 #include "llvm/CodeGen/MachineFunctionPass.h"
 #include "llvm/Support/CommandLine.h"
 
diff --git a/llvm/lib/Target/AMDGPU/SIShrinkInstructions.cpp b/llvm/lib/Target/AMDGPU/SIShrinkInstructions.cpp
--- a/llvm/lib/Target/AMDGPU/SIShrinkInstructions.cpp
+++ b/llvm/lib/Target/AMDGPU/SIShrinkInstructions.cpp
@@ -10,18 +10,8 @@
 
 #include "AMDGPU.h"
 #include "AMDGPUSubtarget.h"
-#include "SIInstrInfo.h"
-#include "MCTargetDesc/AMDGPUMCTargetDesc.h"
 #include "llvm/ADT/Statistic.h"
 #include "llvm/CodeGen/MachineFunctionPass.h"
-#include "llvm/CodeGen/MachineInstrBuilder.h"
-#include "llvm/CodeGen/MachineRegisterInfo.h"
-#include "llvm/IR/Constants.h"
-#include "llvm/IR/Function.h"
-#include "llvm/IR/LLVMContext.h"
-#include "llvm/Support/Debug.h"
-#include "llvm/Support/raw_ostream.h"
-#include "llvm/Target/TargetMachine.h"
 
 #define DEBUG_TYPE "si-shrink-instructions"
 
diff --git a/llvm/lib/Target/AMDGPU/SIWholeQuadMode.cpp b/llvm/lib/Target/AMDGPU/SIWholeQuadMode.cpp
--- a/llvm/lib/Target/AMDGPU/SIWholeQuadMode.cpp
+++ b/llvm/lib/Target/AMDGPU/SIWholeQuadMode.cpp
@@ -57,34 +57,15 @@
 
 #include "AMDGPU.h"
 #include "AMDGPUSubtarget.h"
-#include "MCTargetDesc/AMDGPUMCTargetDesc.h"
-#include "SIInstrInfo.h"
-#include "SIMachineFunctionInfo.h"
-#include "llvm/ADT/DenseMap.h"
 #include "llvm/ADT/MapVector.h"
 #include "llvm/ADT/PostOrderIterator.h"
-#include "llvm/ADT/SmallVector.h"
-#include "llvm/ADT/StringRef.h"
-#include "llvm/CodeGen/LiveInterval.h"
 #include "llvm/CodeGen/LiveIntervals.h"
 #include "llvm/CodeGen/MachineBasicBlock.h"
-#include "llvm/CodeGen/MachineFunction.h"
 #include "llvm/CodeGen/MachineFunctionPass.h"
 #include "llvm/CodeGen/MachineInstr.h"
-#include "llvm/CodeGen/MachineInstrBuilder.h"
-#include "llvm/CodeGen/MachineOperand.h"
-#include "llvm/CodeGen/MachineRegisterInfo.h"
-#include "llvm/CodeGen/SlotIndexes.h"
-#include "llvm/CodeGen/TargetRegisterInfo.h"
 #include "llvm/IR/CallingConv.h"
-#include "llvm/IR/DebugLoc.h"
 #include "llvm/InitializePasses.h"
-#include "llvm/MC/MCRegisterInfo.h"
-#include "llvm/Pass.h"
-#include "llvm/Support/Debug.h"
 #include "llvm/Support/raw_ostream.h"
-#include <cassert>
-#include <vector>
 
 using namespace llvm;
 
diff --git a/llvm/lib/Target/AMDGPU/Utils/AMDGPUAsmUtils.h b/llvm/lib/Target/AMDGPU/Utils/AMDGPUAsmUtils.h
--- a/llvm/lib/Target/AMDGPU/Utils/AMDGPUAsmUtils.h
+++ b/llvm/lib/Target/AMDGPU/Utils/AMDGPUAsmUtils.h
@@ -9,9 +9,10 @@
 #ifndef LLVM_LIB_TARGET_AMDGPU_UTILS_AMDGPUASMUTILS_H
 #define LLVM_LIB_TARGET_AMDGPU_UTILS_AMDGPUASMUTILS_H
 
-#include "llvm/ADT/StringRef.h"
-
 namespace llvm {
+
+class StringLiteral;
+
 namespace AMDGPU {
 
 namespace SendMsg { // Symbolic names for the sendmsg(...) syntax.
diff --git a/llvm/lib/Target/AMDGPU/Utils/AMDGPUAsmUtils.cpp b/llvm/lib/Target/AMDGPU/Utils/AMDGPUAsmUtils.cpp
--- a/llvm/lib/Target/AMDGPU/Utils/AMDGPUAsmUtils.cpp
+++ b/llvm/lib/Target/AMDGPU/Utils/AMDGPUAsmUtils.cpp
@@ -8,6 +8,8 @@
 #include "AMDGPUAsmUtils.h"
 #include "SIDefines.h"
 
+#include "llvm/ADT/StringRef.h"
+
 namespace llvm {
 namespace AMDGPU {
 namespace SendMsg {
diff --git a/llvm/lib/Target/AMDGPU/Utils/AMDGPUBaseInfo.h b/llvm/lib/Target/AMDGPU/Utils/AMDGPUBaseInfo.h
--- a/llvm/lib/Target/AMDGPU/Utils/AMDGPUBaseInfo.h
+++ b/llvm/lib/Target/AMDGPU/Utils/AMDGPUBaseInfo.h
@@ -9,22 +9,15 @@
 #ifndef LLVM_LIB_TARGET_AMDGPU_UTILS_AMDGPUBASEINFO_H
 #define LLVM_LIB_TARGET_AMDGPU_UTILS_AMDGPUBASEINFO_H
 
-#include "AMDGPU.h"
-#include "AMDKernelCodeT.h"
 #include "SIDefines.h"
 #include "llvm/IR/CallingConv.h"
-#include "llvm/MC/MCInstrDesc.h"
-#include "llvm/Support/AMDHSAKernelDescriptor.h"
 #include "llvm/Support/Alignment.h"
-#include "llvm/Support/Compiler.h"
-#include "llvm/Support/ErrorHandling.h"
-#include "llvm/Support/TargetParser.h"
-#include <cstdint>
-#include <string>
-#include <utility>
+
+struct amd_kernel_code_t;
 
 namespace llvm {
 
+struct Align;
 class Argument;
 class Function;
 class GCNSubtarget;
@@ -35,8 +28,14 @@
 class StringRef;
 class Triple;
 
+namespace amdhsa {
+struct kernel_descriptor_t;
+}
+
 namespace AMDGPU {
 
+struct IsaVersion;
+
 /// \returns HSA OS ABI Version identification.
 Optional<uint8_t> getHsaAbiVersion(const MCSubtargetInfo *STI);
 /// \returns True if HSA OS ABI Version identification is 2,
diff --git a/llvm/lib/Target/AMDGPU/Utils/AMDGPUBaseInfo.cpp b/llvm/lib/Target/AMDGPU/Utils/AMDGPUBaseInfo.cpp
--- a/llvm/lib/Target/AMDGPU/Utils/AMDGPUBaseInfo.cpp
+++ b/llvm/lib/Target/AMDGPU/Utils/AMDGPUBaseInfo.cpp
@@ -9,45 +9,23 @@
 #include "AMDGPUBaseInfo.h"
 #include "AMDGPU.h"
 #include "AMDGPUAsmUtils.h"
-#include "AMDGPUTargetTransformInfo.h"
-#include "SIDefines.h"
-#include "llvm/ADT/StringRef.h"
-#include "llvm/ADT/Triple.h"
+#include "AMDGPUSubtarget.h"
+#include "AMDKernelCodeT.h"
 #include "llvm/BinaryFormat/ELF.h"
-#include "llvm/CodeGen/MachineMemOperand.h"
 #include "llvm/IR/Attributes.h"
-#include "llvm/IR/Constants.h"
 #include "llvm/IR/Function.h"
 #include "llvm/IR/GlobalValue.h"
-#include "llvm/IR/Instruction.h"
 #include "llvm/IR/IntrinsicsAMDGPU.h"
 #include "llvm/IR/IntrinsicsR600.h"
 #include "llvm/IR/LLVMContext.h"
-#include "llvm/IR/Module.h"
-#include "llvm/MC/MCContext.h"
-#include "llvm/MC/MCInstrDesc.h"
-#include "llvm/MC/MCInstrInfo.h"
-#include "llvm/MC/MCRegisterInfo.h"
-#include "llvm/MC/MCSectionELF.h"
 #include "llvm/MC/MCSubtargetInfo.h"
-#include "llvm/MC/SubtargetFeature.h"
-#include "llvm/Support/Casting.h"
+#include "llvm/Support/AMDHSAKernelDescriptor.h"
 #include "llvm/Support/CommandLine.h"
-#include "llvm/Support/ErrorHandling.h"
-#include "llvm/Support/MathExtras.h"
-#include <algorithm>
-#include <cassert>
-#include <cstdint>
-#include <cstring>
-#include <utility>
-
-#include "MCTargetDesc/AMDGPUMCTargetDesc.h"
+#include "llvm/Support/TargetParser.h"
 
 #define GET_INSTRINFO_NAMED_OPS
 #define GET_INSTRMAP_INFO
 #include "AMDGPUGenInstrInfo.inc"
-#undef GET_INSTRMAP_INFO
-#undef GET_INSTRINFO_NAMED_OPS
 
 static llvm::cl::opt<unsigned> AmdhsaCodeObjectVersion(
   "amdhsa-code-object-version", llvm::cl::Hidden,
diff --git a/llvm/lib/Target/AMDGPU/Utils/AMDGPUPALMetadata.h b/llvm/lib/Target/AMDGPU/Utils/AMDGPUPALMetadata.h
--- a/llvm/lib/Target/AMDGPU/Utils/AMDGPUPALMetadata.h
+++ b/llvm/lib/Target/AMDGPU/Utils/AMDGPUPALMetadata.h
@@ -13,12 +13,11 @@
 
 #ifndef LLVM_LIB_TARGET_AMDGPU_AMDGPUPALMETADATA_H
 #define LLVM_LIB_TARGET_AMDGPU_AMDGPUPALMETADATA_H
-
 #include "llvm/BinaryFormat/MsgPackDocument.h"
-#include "llvm/CodeGen/MachineFunction.h"
 
 namespace llvm {
 
+class MachineFunction;
 class Module;
 class StringRef;
 
diff --git a/llvm/lib/Target/AMDGPU/Utils/AMDGPUPALMetadata.cpp b/llvm/lib/Target/AMDGPU/Utils/AMDGPUPALMetadata.cpp
--- a/llvm/lib/Target/AMDGPU/Utils/AMDGPUPALMetadata.cpp
+++ b/llvm/lib/Target/AMDGPU/Utils/AMDGPUPALMetadata.cpp
@@ -15,12 +15,10 @@
 //
 
 #include "AMDGPUPALMetadata.h"
-#include "AMDGPU.h"
-#include "AMDGPUAsmPrinter.h"
-#include "MCTargetDesc/AMDGPUTargetStreamer.h"
+#include "AMDGPUPTNote.h"
 #include "SIDefines.h"
 #include "llvm/BinaryFormat/ELF.h"
-#include "llvm/IR/CallingConv.h"
+#include "llvm/CodeGen/MachineFunction.h"
 #include "llvm/IR/Constants.h"
 #include "llvm/IR/Module.h"
 #include "llvm/Support/AMDGPUMetadata.h"
diff --git a/llvm/lib/Target/AMDGPU/Utils/AMDKernelCodeTUtils.h b/llvm/lib/Target/AMDGPU/Utils/AMDKernelCodeTUtils.h
--- a/llvm/lib/Target/AMDGPU/Utils/AMDKernelCodeTUtils.h
+++ b/llvm/lib/Target/AMDGPU/Utils/AMDKernelCodeTUtils.h
@@ -13,7 +13,7 @@
 #ifndef LLVM_LIB_TARGET_AMDGPU_UTILS_AMDKERNELCODETUTILS_H
 #define LLVM_LIB_TARGET_AMDGPU_UTILS_AMDKERNELCODETUTILS_H
 
-#include "AMDKernelCodeT.h"
+struct amd_kernel_code_t;
 
 namespace llvm {
 
diff --git a/llvm/lib/Target/AMDGPU/Utils/AMDKernelCodeTUtils.cpp b/llvm/lib/Target/AMDGPU/Utils/AMDKernelCodeTUtils.cpp
--- a/llvm/lib/Target/AMDGPU/Utils/AMDKernelCodeTUtils.cpp
+++ b/llvm/lib/Target/AMDGPU/Utils/AMDKernelCodeTUtils.cpp
@@ -11,6 +11,7 @@
 //===----------------------------------------------------------------------===//
 
 #include "AMDKernelCodeTUtils.h"
+#include "AMDKernelCodeT.h"
 #include "SIDefines.h"
 #include "llvm/ADT/ArrayRef.h"
 #include "llvm/ADT/StringMap.h"
@@ -18,9 +19,6 @@
 #include "llvm/MC/MCParser/MCAsmLexer.h"
 #include "llvm/MC/MCParser/MCAsmParser.h"
 #include "llvm/Support/raw_ostream.h"
-#include <cassert>
-#include <cstdint>
-#include <utility>
 
 using namespace llvm;
 
diff --git a/llvm/lib/Transforms/Utils/AMDGPUEmitPrintf.cpp b/llvm/lib/Transforms/Utils/AMDGPUEmitPrintf.cpp
--- a/llvm/lib/Transforms/Utils/AMDGPUEmitPrintf.cpp
+++ b/llvm/lib/Transforms/Utils/AMDGPUEmitPrintf.cpp
@@ -17,9 +17,6 @@
 #include "llvm/Transforms/Utils/AMDGPUEmitPrintf.h"
 #include "llvm/ADT/SparseBitVector.h"
 #include "llvm/Analysis/ValueTracking.h"
-#include "llvm/IR/IRBuilder.h"
-
-#include <iostream>
 
 using namespace llvm;