Index: lib/MC/MCCodePadder.cpp
===================================================================
--- lib/MC/MCCodePadder.cpp
+++ lib/MC/MCCodePadder.cpp
@@ -39,10 +39,12 @@
   ArePoliciesActive = usePoliciesForBasicBlock(Context);
 
   bool InsertionPoint = basicBlockRequiresInsertionPoint(Context);
-  assert((!InsertionPoint ||
-          OS->getCurrentFragment()->getKind() != MCFragment::FT_Align) &&
-         "Cannot insert padding nops right after an alignment fragment as it "
-         "will ruin the alignment");
+  bool BasicBlockHasAlignment =
+      OS->getCurrentFragment() == nullptr ||
+      OS->getCurrentFragment()->getKind() == MCFragment::FT_Align;
+  assert((!InsertionPoint || !BasicBlockHasAlignment) &&
+         "Cannot insert padding nops right after a basic block that has "
+         "alignment");
 
   uint64_t PoliciesMask = MCPaddingFragment::PFK_None;
   if (ArePoliciesActive) {
Index: lib/Target/X86/MCTargetDesc/CMakeLists.txt
===================================================================
--- lib/Target/X86/MCTargetDesc/CMakeLists.txt
+++ lib/Target/X86/MCTargetDesc/CMakeLists.txt
@@ -3,6 +3,7 @@
   X86MCTargetDesc.cpp
   X86MCAsmInfo.cpp
   X86MCCodeEmitter.cpp
+  X86MCCodePadder.cpp
   X86MachObjectWriter.cpp
   X86ELFObjectWriter.cpp
   X86WinCOFFObjectWriter.cpp
Index: lib/Target/X86/MCTargetDesc/X86AsmBackend.cpp
===================================================================
--- lib/Target/X86/MCTargetDesc/X86AsmBackend.cpp
+++ lib/Target/X86/MCTargetDesc/X86AsmBackend.cpp
@@ -8,6 +8,7 @@
 //===----------------------------------------------------------------------===//
 
 #include "MCTargetDesc/X86BaseInfo.h"
+#include "MCTargetDesc/X86MCCodePadder.h"
 #include "MCTargetDesc/X86FixupKinds.h"
 #include "llvm/ADT/StringSwitch.h"
 #include "llvm/BinaryFormat/ELF.h"
@@ -73,10 +74,12 @@
   const StringRef CPU;
   bool HasNopl;
   const uint64_t MaxNopLength;
+
 public:
   X86AsmBackend(const Target &T, StringRef CPU)
-      : MCAsmBackend(), CPU(CPU),
-        MaxNopLength((CPU == "slm") ? 7 : 15) {
+      : MCAsmBackend(std::move(
+            std::unique_ptr<MCCodePadder>(new X86::X86MCCodePadder(CPU)))),
+        CPU(CPU), MaxNopLength((CPU == "slm") ? 7 : 15) {
     HasNopl = CPU != "generic" && CPU != "i386" && CPU != "i486" &&
               CPU != "i586" && CPU != "pentium" && CPU != "pentium-mmx" &&
               CPU != "i686" && CPU != "k6" && CPU != "k6-2" && CPU != "k6-3" &&
Index: lib/Target/X86/MCTargetDesc/X86MCCodePadder.h
===================================================================
--- /dev/null
+++ lib/Target/X86/MCTargetDesc/X86MCCodePadder.h
@@ -0,0 +1,114 @@
+//===-- X86MCCodePadder.h - X86 Specific Code Padding Handling --*- C++ -*-===//
+//
+//                     The LLVM Compiler Infrastructure
+//
+// This file is distributed under the University of Illinois Open Source
+// License. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+
+#ifndef LLVM_LIB_TARGET_X86_MCTARGETDESC_X86MCCODEPADDER_H
+#define LLVM_LIB_TARGET_X86_MCTARGETDESC_X86MCCODEPADDER_H
+
+#include "llvm/ADT/StringRef.h"
+#include "llvm/MC/MCCodePadder.h"
+
+namespace llvm {
+
+class MCPaddingFragment;
+class MCAsmLayout;
+
+namespace X86 {
+
+/// The X86-specific class incharge of all code padding decisions for the X86
+/// target.
+class X86MCCodePadder : public MCCodePadder {
+  X86MCCodePadder() = delete;
+  X86MCCodePadder(const X86MCCodePadder &) = delete;
+  void operator=(const X86MCCodePadder &) = delete;
+
+protected:
+  bool basicBlockRequiresInsertionPoint(
+      const MCCodePaddingContext &Context) override;
+
+  bool usePoliciesForBasicBlock(const MCCodePaddingContext &Context) override;
+
+public:
+  X86MCCodePadder(StringRef CPU);
+  virtual ~X86MCCodePadder() {}
+};
+
+/// A padding policy that handles brach instructions (all types of jmps and
+/// calls) and the first instruction after a branch (i.e. first instruction in a
+/// basic block reachable by branch).
+/// This policy tries to enforce that:
+/// 1. Branch instructions and first instructions in basic blocks won't cross a
+///    16B aligned window.
+/// 2. Branch instructions will end at a 0mod16 address.
+///
+/// Note that this is also the order of importance implemented in the policy.
+///
+/// This policy essentially implements part of rule 12 of section 3.4.1.5 ("Code
+/// alignment") of Intel's Architectures Optimization Reference Manual:
+/// "When executing code from the legacy decode pipeline, direct branches that
+/// are mostly taken should have all their instruction bytes in a 16B aligned
+/// chunk of memory and nearer the end of that 16B aligned chunk."
+class BranchInstructionAndTargetAlignmentPolicy : public MCCodePaddingPolicy {
+  BranchInstructionAndTargetAlignmentPolicy(
+      const BranchInstructionAndTargetAlignmentPolicy &) = delete;
+  void operator=(const BranchInstructionAndTargetAlignmentPolicy &) = delete;
+
+protected:
+  /// Computes the penalty weight caused by having branch instruction or the
+  /// instruction after a branch (i.e. first instruction in a basic block
+  /// reachable by branch) being splitted over more than one instruction window,
+  /// and a branch instruction not being adjacent to the end of its 16B code
+  /// chunk.
+  ///
+  /// \param Window The instruction window.
+  /// \param Offset The offset of the parent section.
+  /// \param Layout Code layout information.
+  ///
+  /// \returns the penalty weight caused by having branch instruction or
+  /// instruction after a branch being splitted over more than one instruction
+  /// window, and a branch instruction not being adjacent to the end of its 16B
+  /// code chunk.
+  double computeWindowPenaltyWeight(const MCPFRange &Window, uint64_t Offset,
+                                    MCAsmLayout &Layout) const override;
+
+public:
+  BranchInstructionAndTargetAlignmentPolicy();
+  virtual ~BranchInstructionAndTargetAlignmentPolicy() {}
+
+  /// Determines if a basic block may cause the case of first instruction after
+  /// a branch (i.e. first instruction in a basic block reachable by branch)
+  /// being splitted over more than one instruction window.
+  ///
+  /// A basic block will be considered hazardous by this policy if it is
+  /// reachable by a branch (and not only via fallthrough).
+  ///
+  /// \param Context the context of the padding, Embeds the basic block's
+  /// parameters.
+  ///
+  /// \returns true iff \p Context indicates that the basic block is reachable
+  /// via branch.
+  bool basicBlockRequiresPaddingFragment(
+      const MCCodePaddingContext &Context) const override;
+
+  /// Determines if an instruction may cause the case of a branch instrucion
+  /// being splitted over more than one instruction window or a branch not
+  /// being adjacent to the end of its 16B code chunk.
+  ///
+  /// An instruction will be considered hazardous by this policy if it is
+  /// a branch (all types of jmps and calls).
+  ///
+  /// \param Inst Instruction to examine.
+  ///
+  /// \returns true iff \p Inst is a branch (all types of jmps and calls).
+  bool instructionRequiresPaddingFragment(const MCInst &Inst) const override;
+};
+
+} // namespace X86
+} // namespace llvm
+
+#endif // LLVM_LIB_TARGET_X86_MCTARGETDESC_X86MCCODEPADDER_H
Index: lib/Target/X86/MCTargetDesc/X86MCCodePadder.cpp
===================================================================
--- /dev/null
+++ lib/Target/X86/MCTargetDesc/X86MCCodePadder.cpp
@@ -0,0 +1,169 @@
+///=== X86MCCodePadder.cpp - X86 Specific Code Padding Handling -*- C++ -*-===//
+//
+//                     The LLVM Compiler Infrastructure
+//
+// This file is distributed under the University of Illinois Open Source
+// License. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+
+#include "MCTargetDesc/X86MCCodePadder.h"
+#include "MCTargetDesc/X86BaseInfo.h"
+#include "llvm/ADT/SmallPtrSet.h"
+#include "llvm/ADT/SmallSet.h"
+#include "llvm/CodeGen/MachineBasicBlock.h"
+#include "llvm/CodeGen/MachineFunction.h"
+#include "llvm/CodeGen/MachineLoopInfo.h"
+#include "llvm/MC/MCAsmLayout.h"
+#include "llvm/MC/MCInst.h"
+#include "llvm/MC/MCObjectStreamer.h"
+#include "llvm/Target/TargetMachine.h"
+
+namespace llvm {
+namespace X86 {
+
+enum PerfNopFragmentKind {
+  BranchInstructionAndTargetAlignment =
+      MCPaddingFragment::FirstTargetPerfNopFragmentKind
+};
+
+//---------------------------------------------------------------------------
+// X86MCCodePadder
+//
+
+X86MCCodePadder::X86MCCodePadder(StringRef CPU) {
+
+  if (CPU != "sandybridge" && CPU != "corei7-avx" && CPU != "ivybridge" &&
+      CPU != "core-avx-i" && CPU != "haswell" && CPU != "core-avx2" &&
+      CPU != "broadwell" && CPU != "skylake")
+    return;
+
+  addPolicy(new BranchInstructionAndTargetAlignmentPolicy());
+}
+
+bool X86MCCodePadder::basicBlockRequiresInsertionPoint(
+    const MCCodePaddingContext &Context) {
+  // Insertion points are places that, if contain padding, then this padding
+  // will never be executed (unreachable code).
+  bool BasicBlockHasAlignment =
+      OS->getCurrentFragment() == nullptr ||
+      OS->getCurrentFragment()->getKind() == MCFragment::FT_Align;
+  return MCCodePadder::basicBlockRequiresInsertionPoint(Context) ||
+         (!Context.IsBasicBlockReachableViaFallthrough &&
+          !BasicBlockHasAlignment);
+}
+
+bool X86MCCodePadder::usePoliciesForBasicBlock(
+    const MCCodePaddingContext &Context) {
+  return MCCodePadder::usePoliciesForBasicBlock(Context) &&
+         Context.IsBasicBlockInsideInnermostLoop;
+}
+
+//---------------------------------------------------------------------------
+// Utility functions
+//
+
+static bool isConditionalJump(const MCInst &Inst) {
+  unsigned int opcode = Inst.getOpcode();
+  return
+      // Immidiate jmps
+      opcode == JAE_1 || opcode == JAE_2 || opcode == JAE_4 || opcode == JA_1 ||
+      opcode == JA_2 || opcode == JA_4 || opcode == JBE_1 || opcode == JBE_2 ||
+      opcode == JBE_4 || opcode == JB_1 || opcode == JB_2 || opcode == JB_4 ||
+      opcode == JCXZ || opcode == JECXZ || opcode == JE_1 || opcode == JE_2 ||
+      opcode == JE_4 || opcode == JGE_1 || opcode == JGE_2 || opcode == JGE_4 ||
+      opcode == JG_1 || opcode == JG_2 || opcode == JG_4 || opcode == JLE_1 ||
+      opcode == JLE_2 || opcode == JLE_4 || opcode == JL_1 || opcode == JL_2 ||
+      opcode == JL_4 || opcode == JNE_1 || opcode == JNE_2 || opcode == JNE_4 ||
+      opcode == JNO_1 || opcode == JNO_2 || opcode == JNO_4 ||
+      opcode == JNP_1 || opcode == JNP_2 || opcode == JNP_4 ||
+      opcode == JNS_1 || opcode == JNS_2 || opcode == JNS_4 || opcode == JO_1 ||
+      opcode == JO_2 || opcode == JO_4 || opcode == JP_1 || opcode == JP_2 ||
+      opcode == JP_4 || opcode == JRCXZ || opcode == JS_1 || opcode == JS_2 ||
+      opcode == JS_4;
+}
+
+static bool isFarOrIndirectUncoditionalJump(const MCInst &Inst) {
+  unsigned int opcode = Inst.getOpcode();
+  return
+      // Far jmps
+      opcode == FARJMP16i || opcode == FARJMP16m || opcode == FARJMP32i ||
+      opcode == FARJMP32m || opcode == FARJMP64 ||
+      // Memory and register jmps
+      opcode == JMP16m || opcode == JMP16r || opcode == JMP32m ||
+      opcode == JMP32r || opcode == JMP64m || opcode == JMP64r;
+}
+
+static bool isUnconditionalJump(const MCInst &Inst) {
+  unsigned int opcode = Inst.getOpcode();
+  return isFarOrIndirectUncoditionalJump(Inst) || opcode == JMP_1 ||
+         opcode == JMP_2 || opcode == JMP_4;
+}
+
+static bool isJump(const MCInst &Inst) {
+  return isConditionalJump(Inst) || isUnconditionalJump(Inst);
+}
+
+static bool isCall(const MCInst &Inst) {
+  unsigned int opcode = Inst.getOpcode();
+  return
+      // PC relative calls
+      opcode == CALL64pcrel32 || opcode == CALLpcrel16 ||
+      opcode == CALLpcrel32 ||
+      // Far calls
+      opcode == FARCALL16i || opcode == FARCALL16m || opcode == FARCALL32i ||
+      opcode == FARCALL32m || opcode == FARCALL64 ||
+      // Memory and register calls
+      opcode == CALL16m || opcode == CALL16r || opcode == CALL32m ||
+      opcode == CALL32r || opcode == CALL64m || opcode == CALL64r;
+}
+
+//---------------------------------------------------------------------------
+// BranchInstructionAndTargetAlignmentPolicy
+//
+
+BranchInstructionAndTargetAlignmentPolicy::
+    BranchInstructionAndTargetAlignmentPolicy()
+    : MCCodePaddingPolicy(BranchInstructionAndTargetAlignment, UINT64_C(16),
+                          false) {}
+
+bool BranchInstructionAndTargetAlignmentPolicy::
+    basicBlockRequiresPaddingFragment(
+        const MCCodePaddingContext &Context) const {
+  return Context.IsBasicBlockReachableViaBranch;
+}
+
+bool BranchInstructionAndTargetAlignmentPolicy::
+    instructionRequiresPaddingFragment(const MCInst &Inst) const {
+  return isJump(Inst) || isCall(Inst);
+}
+
+double BranchInstructionAndTargetAlignmentPolicy::computeWindowPenaltyWeight(
+    const MCPFRange &Window, uint64_t Offset, MCAsmLayout &Layout) const {
+
+  static const double SPLIT_INST_WEIGHT = 10.0;
+  static const double BRANCH_NOT_AT_CHUNK_END_WEIGHT = 1.0;
+
+  double Weight = 0.0;
+  for (const MCPaddingFragment *Fragment : Window) {
+    if (!Fragment->isInstructionInitialized())
+      continue;
+    uint64_t InstructionStartAddress = getNextFragmentOffset(Fragment, Layout);
+    uint64_t InstructionSecondByteAddress =
+        InstructionStartAddress + UINT64_C(1);
+    uint64_t InstructionEndAddress =
+        InstructionStartAddress + Fragment->getInstSize();
+    // Checking if the instruction pointed by the fragment splits over more than
+    // one window.
+    if (alignTo(InstructionSecondByteAddress, WindowSize) !=
+        alignTo(InstructionEndAddress, WindowSize))
+      Weight += SPLIT_INST_WEIGHT;
+    if (instructionRequiresPaddingFragment(Fragment->getInst()) &&
+        (InstructionEndAddress & UINT64_C(0xF)) != UINT64_C(0))
+      Weight += BRANCH_NOT_AT_CHUNK_END_WEIGHT;
+  }
+  return Weight;
+}
+
+} // namespace X86
+} // namespace llvm
Index: test/CodeGen/X86/branch-instructions-end-of-16B-chunk-perf-nops.mir
===================================================================
--- /dev/null
+++ test/CodeGen/X86/branch-instructions-end-of-16B-chunk-perf-nops.mir
@@ -0,0 +1,163 @@
+# RUN: llc -mcpu=haswell -filetype=obj -start-before stack-protector -O2 %s -o - | llvm-objdump -d - | FileCheck %s
+
+# Source C code:
+# volatile int y;
+# volatile int x;
+# 
+# int perfNopsInsertion(int z, int w) {
+# 	int result = 0;
+# 	while (x > 0 && y < 0) {
+# 		switch(z) {
+# 			case 0:
+# 			result+=result*5;break;
+# 			case 1:
+# 			result--; break;
+# 			case 2:
+# 			result *= result; break;
+# 			case 3:
+# 			result <<= 7; break;
+# 			case 4:
+# 			result >>= 7; break;
+# 			case 5:
+# 			result = result * 16 | ~result; break;
+# 		}
+# 	}
+# 	return result;
+# }
+
+# The test:    Branch instructions should be pushed to the end of their 16B code
+#              Chunks.
+#              Expect insertion of nops in unreachable code space to make this
+#              happen.
+# CHECK:       49:       eb 65   jmp     101 <perfNopsInsertion+0xB0>
+# CHECK-NEXT:  4b:       0f 1f 80 00 00 00 00    nopl    (%rax)
+# CHECK:       5e:       eb 50   jmp     80 <perfNopsInsertion+0xB0>
+# CHECK-NEXT:  60:       66 90   nop
+# CHECK:       6e:       eb 40   jmp     64 <perfNopsInsertion+0xB0>
+# CHECK-NEXT:  70:       66 90   nop
+# CHECK:       7e:       eb 30   jmp     48 <perfNopsInsertion+0xB0>
+# CHECK-NEXT:  80:       66 90   nop
+# CHECK:       8e:       eb 20   jmp     32 <perfNopsInsertion+0xB0>
+# CHECK-NEXT:  90:       66 2e 0f 1f 84 00 00 00 00 00   nopw    %cs:(%rax,%rax)
+# CHECK:       aa:       0f 8f 70 ff ff ff       jg      -144 <perfNopsInsertion+0x20>
+# CHECK-NEXT:  b0:
+--- |
+  ; ModuleID = 'branch_instruction_and_target_split_perf_nops.c'
+  source_filename = "branch_instruction_and_target_split_perf_nops.c"
+  target datalayout = "e-m:w-i64:64-f80:128-n8:16:32:64-S128"
+  target triple = "x86_64-haswell-linux-gnu"
+ 
+  
+  @x = common global i32 0, align 4
+  @y = common global i32 0, align 4
+  
+  ; Function Attrs: norecurse nounwind uwtable
+  define i32 @perfNopsInsertion(i32 %z, i32 %w) local_unnamed_addr #0 {
+  entry:
+    %0 = load volatile i32, i32* @x, align 4, !tbaa !3
+    %cmp19 = icmp sgt i32 %0, 0
+    br i1 %cmp19, label %land.rhs.preheader, label %while.end
+  
+  land.rhs.preheader:                               ; preds = %entry
+    br label %land.rhs
+  
+  land.rhs:                                         ; preds = %land.rhs.preheader, %sw.epilog
+    %result.020 = phi i32 [ %result.1, %sw.epilog ], [ 0, %land.rhs.preheader ]
+    %1 = load volatile i32, i32* @y, align 4, !tbaa !3
+    %cmp1 = icmp slt i32 %1, 0
+    br i1 %cmp1, label %while.body, label %while.end
+  
+  while.body:                                       ; preds = %land.rhs
+    switch i32 %z, label %sw.epilog [
+      i32 0, label %sw.bb
+      i32 1, label %sw.bb2
+      i32 2, label %sw.bb3
+      i32 3, label %sw.bb5
+      i32 4, label %sw.bb6
+      i32 5, label %sw.bb7
+    ]
+  
+  sw.bb:                                            ; preds = %while.body
+    %add = mul nsw i32 %result.020, 6
+    br label %sw.epilog
+  
+  sw.bb2:                                           ; preds = %while.body
+    %dec = add nsw i32 %result.020, -1
+    br label %sw.epilog
+  
+  sw.bb3:                                           ; preds = %while.body
+    %mul4 = mul nsw i32 %result.020, %result.020
+    br label %sw.epilog
+  
+  sw.bb5:                                           ; preds = %while.body
+    %shl = shl i32 %result.020, 7
+    br label %sw.epilog
+  
+  sw.bb6:                                           ; preds = %while.body
+    %shr = ashr i32 %result.020, 7
+    br label %sw.epilog
+  
+  sw.bb7:                                           ; preds = %while.body
+    %mul8 = shl nsw i32 %result.020, 4
+    %neg = xor i32 %result.020, -1
+    %or = or i32 %mul8, %neg
+    br label %sw.epilog
+  
+  sw.epilog:                                        ; preds = %while.body, %sw.bb7, %sw.bb6, %sw.bb5, %sw.bb3, %sw.bb2, %sw.bb
+    %result.1 = phi i32 [ %result.020, %while.body ], [ %or, %sw.bb7 ], [ %shr, %sw.bb6 ], [ %shl, %sw.bb5 ], [ %mul4, %sw.bb3 ], [ %dec, %sw.bb2 ], [ %add, %sw.bb ]
+    %2 = load volatile i32, i32* @x, align 4, !tbaa !3
+    %cmp = icmp sgt i32 %2, 0
+    br i1 %cmp, label %land.rhs, label %while.end
+  
+  while.end:                                        ; preds = %land.rhs, %sw.epilog, %entry
+    %result.0.lcssa = phi i32 [ 0, %entry ], [ %result.1, %sw.epilog ], [ %result.020, %land.rhs ]
+    ret i32 %result.0.lcssa
+  }
+  
+  attributes #0 = { norecurse nounwind uwtable "correctly-rounded-divide-sqrt-fp-math"="false" "disable-tail-calls"="false" "less-precise-fpmad"="false" "no-frame-pointer-elim"="false" "no-infs-fp-math"="false" "no-jump-tables"="false" "no-nans-fp-math"="false" "no-signed-zeros-fp-math"="false" "no-trapping-math"="false" "stack-protector-buffer-size"="8" "target-cpu"="haswell" "target-features"="+aes,+avx,+avx2,+bmi,+bmi2,+cx16,+f16c,+fma,+fsgsbase,+fxsr,+lzcnt,+mmx,+movbe,+pclmul,+popcnt,+rdrnd,+sse,+sse2,+sse3,+sse4.1,+sse4.2,+ssse3,+x87,+xsave,+xsaveopt" "unsafe-fp-math"="false" "use-soft-float"="false" }
+  
+  !llvm.module.flags = !{!0, !1}
+  !llvm.ident = !{!2}
+  
+  !0 = !{i32 1, !"wchar_size", i32 2}
+  !1 = !{i32 7, !"PIC Level", i32 2}
+  !2 = !{!"clang version 6.0.0 (ssh://git-amr-1.devtools.intel.com:29418/dpd_icl-llvm_clang_worldread 3789ad4283ec09df1ed8411abbb227d76e7ef8cb) (ssh://git-amr-1.devtools.intel.com:29418/dpd_icl-llvm_llvm_worldread 4dc3dc453fd737d29001434b891a613f5fc22638)"}
+  !3 = !{!4, !4, i64 0}
+  !4 = !{!"int", !5, i64 0}
+  !5 = !{!"omnipotent char", !6, i64 0}
+  !6 = !{!"Simple C/C++ TBAA"}
+...
+---
+name:            perfNopsInsertion
+alignment:       4
+exposesReturnsTwice: false
+legalized:       false
+regBankSelected: false
+selected:        false
+tracksRegLiveness: true
+registers:       
+liveins:         
+frameInfo:       
+  isFrameAddressTaken: false
+  isReturnAddressTaken: false
+  hasStackMap:     false
+  hasPatchPoint:   false
+  stackSize:       0
+  offsetAdjustment: 0
+  maxAlignment:    0
+  adjustsStack:    false
+  hasCalls:        false
+  stackProtector:  ''
+  maxCallFrameSize: 4294967295
+  hasOpaqueSPAdjustment: false
+  hasVAStart:      false
+  hasMustTailInVarArgFunc: false
+  savePoint:       ''
+  restorePoint:    ''
+fixedStack:      
+stack:           
+constants:      
+ 
+body:             |
+
+...