diff --git a/llvm/lib/CodeGen/Spill2Reg.cpp b/llvm/lib/CodeGen/Spill2Reg.cpp
--- a/llvm/lib/CodeGen/Spill2Reg.cpp
+++ b/llvm/lib/CodeGen/Spill2Reg.cpp
@@ -16,6 +16,7 @@
 //===----------------------------------------------------------------------===//
 
 #include "AllocationOrder.h"
+#include "llvm/ADT/Statistic.h"
 #include "llvm/CodeGen/LiveRegUnits.h"
 #include "llvm/CodeGen/MachineFrameInfo.h"
 #include "llvm/CodeGen/MachineFunctionPass.h"
@@ -29,6 +30,9 @@
 
 using namespace llvm;
 
+#define DEBUG_TYPE "Spill2Reg"
+STATISTIC(NumSpill2RegInstrs, "Number of spills/reloads replaced by spill2reg");
+
 static cl::opt<bool> EnableSpill2Reg("enable-spill2reg", cl::Hidden,
                                      cl::init(true),
                                      cl::desc("Enable Spill2Reg pass"));
@@ -211,8 +215,7 @@
 }
 
 bool Spill2Reg::isProfitable(const MachineInstr *MI) const {
-  // TODO: Unimplemented.
-  return true;
+  return TII->isSpill2RegProfitable(MI, TRI, MRI);
 }
 
 bool Spill2Reg::allAccessesProfitable(const StackSlotDataEntry &Entry) const {
@@ -236,7 +239,33 @@
 // Replace stack-based spills/reloads with register-based ones.
 void Spill2Reg::replaceStackWithReg(StackSlotDataEntry &Entry,
                                     Register VectorReg) {
-  // TODO: Unimplemented
+  for (StackSlotDataEntry::MIData &SpillData : Entry.Spills) {
+    MachineInstr *StackSpill = SpillData.MI;
+    assert(SpillData.MO->isReg() && "Expected register MO");
+    Register OldReg = SpillData.MO->getReg();
+
+    MachineInstr *SpillToVector = TII->spill2RegInsertToVectorReg(
+        VectorReg, OldReg, SpillData.MemBits, StackSpill->getParent(),
+        /*InsertBeforeIt=*/StackSpill->getIterator(), TRI);
+
+    // Spill to stack is no longer needed.
+    StackSpill->eraseFromParent();
+    assert(OldReg.isPhysical() && "Otherwise we need to removeInterval()");
+  }
+
+  for (StackSlotDataEntry::MIData &ReloadData : Entry.Reloads) {
+    MachineInstr *StackReload = ReloadData.MI;
+    assert(ReloadData.MO->isReg() && "Expected Reg MO");
+    Register OldReg = ReloadData.MO->getReg();
+
+    MachineInstr *ReloadFromReg = TII->spill2RegExtractFromVectorReg(
+        OldReg, VectorReg, ReloadData.MemBits, StackReload->getParent(),
+        /*InsertBeforeIt=*/StackReload->getIterator(), TRI);
+
+    // Reload from stack is no longer needed.
+    StackReload->eraseFromParent();
+    assert(OldReg.isPhysical() && "Otherwise we need to removeInterval()");
+  }
 }
 
 void Spill2Reg::calculateLiveRegs(StackSlotDataEntry &Entry,
@@ -267,6 +296,8 @@
 
     // Replace stack accesses with register accesses.
     replaceStackWithReg(Entry, *PhysVectorRegOpt);
+
+    NumSpill2RegInstrs += Entry.Spills.size() + Entry.Reloads.size();
   }
 }
 
diff --git a/llvm/test/CodeGen/X86/spill2reg_disable_when_noimplicitfloat.mir b/llvm/test/CodeGen/X86/spill2reg_disable_when_noimplicitfloat.mir
new file mode 100644
--- /dev/null
+++ b/llvm/test/CodeGen/X86/spill2reg_disable_when_noimplicitfloat.mir
@@ -0,0 +1,36 @@
+# RUN: llc %s -o - -mtriple=x86_64-unknown-linux -enable-spill2reg -mattr=+sse4.1 --run-pass=spill2reg -simplify-mir -spill2reg-mem-instrs=0 -spill2reg-vec-instrs=99999 | FileCheck %s
+
+# Check that Spill2reg is disabled if the NoImplicitFloat attribute is set.
+
+--- |
+  @D0 = dso_local local_unnamed_addr global i32 0, align 4
+  @U0 = dso_local local_unnamed_addr global i32 0, align 4
+  define void @func() #0 { ret void }
+
+  attributes #0 = { noimplicitfloat }
+...
+---
+name: func
+alignment:       16
+tracksRegLiveness: true
+tracksDebugUserValues: true
+frameInfo:
+  maxAlignment:    4
+stack:
+  - { id: 0, type: spill-slot, size: 4, alignment: 4 }
+machineFunctionInfo: {}
+body:             |
+ ; CHECK-LABEL:  bb.0:
+ ; CHECK-NEXT:    $eax = MOV32rm $rip, 1, $noreg, @D0, $noreg :: (dereferenceable load (s32) from @D0)
+ ; CHECK-NEXT:    MOV32mr %stack.0, 1, $noreg, 0, $noreg, killed renamable $eax :: (store (s32) into %stack.0)
+ ; CHECK-NEXT:    $eax = MOV32rm %stack.0, 1, $noreg, 0, $noreg :: (load (s32) from %stack.0)
+ ; CHECK-NEXT:    MOV32mr $rip, 1, $noreg, @U0, $noreg, killed renamable $eax :: (store (s32) into @U0)
+ ; CHECK-NEXT:    RET 0
+  bb.0:
+    $eax = MOV32rm $rip, 1, $noreg, @D0, $noreg :: (dereferenceable load (s32) from @D0)
+    MOV32mr %stack.0, 1, $noreg, 0, $noreg, killed renamable $eax :: (store (s32) into %stack.0)
+
+    $eax = MOV32rm %stack.0, 1, $noreg, 0, $noreg :: (load (s32) from %stack.0)
+    MOV32mr $rip, 1, $noreg, @U0, $noreg, killed renamable $eax :: (store (s32) into @U0)
+    RET 0
+...
diff --git a/llvm/test/CodeGen/X86/spill2reg_mask_spills.mir b/llvm/test/CodeGen/X86/spill2reg_mask_spills.mir
new file mode 100644
--- /dev/null
+++ b/llvm/test/CodeGen/X86/spill2reg_mask_spills.mir
@@ -0,0 +1,32 @@
+# NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+# RUN: llc %s -o - -mtriple=x86_64-unknown-linux -enable-spill2reg -mattr=+avx512f --run-pass=spill2reg -simplify-mir -spill2reg-mem-instrs=0 -spill2reg-vec-instrs=99999 | FileCheck %s
+
+# Checks that spills reading from $k mask registers are skipped by Spill2Reg.
+
+--- |
+  @D0 = dso_local local_unnamed_addr global i32 0, align 4
+  @U0 = dso_local local_unnamed_addr global i32 0, align 4
+  define void @func() { ret void }
+...
+---
+name: func
+alignment:       16
+tracksRegLiveness: true
+tracksDebugUserValues: true
+frameInfo:
+  maxAlignment:    4
+stack:
+  - { id: 0, type: spill-slot, size: 4, alignment: 4 }
+machineFunctionInfo: {}
+body:             |
+ ; CHECK-LABEL:  bb.0:
+ ; CHECK-NEXT:    liveins: $k1
+ ; CHECK:         KMOVWmk %stack.0, 1, $noreg, 0, $noreg, renamable $k1 :: (store (s16) into %stack.0)
+ ; CHECK-NEXT:    renamable $k1 = KMOVWkm %stack.0, 1, $noreg, 0, $noreg :: (load (s16) from %stack.0)
+ ; CHECK-NEXT:    RET 0
+  bb.0:
+    liveins: $k1
+    KMOVWmk %stack.0, 1, $noreg, 0, $noreg, killed renamable $k1 :: (store (s16) into %stack.0)
+    renamable $k1 = KMOVWkm %stack.0, 1, $noreg, 0, $noreg :: (load (s16) from %stack.0)
+    RET 0
+...
diff --git a/llvm/test/CodeGen/X86/spill2reg_simple_1.mir b/llvm/test/CodeGen/X86/spill2reg_simple_1.mir
new file mode 100644
--- /dev/null
+++ b/llvm/test/CodeGen/X86/spill2reg_simple_1.mir
@@ -0,0 +1,47 @@
+# NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+# RUN: llc %s -o - -mtriple=x86_64-unknown-linux -enable-spill2reg -mattr=+sse4.1 --run-pass=spill2reg -simplify-mir -spill2reg-mem-instrs=0 -spill2reg-vec-instrs=99999 | FileCheck %s
+# RUN: llc %s -o - -mtriple=x86_64-unknown-linux -enable-spill2reg -mattr=-sse4.1 --run-pass=spill2reg -simplify-mir -spill2reg-mem-instrs=0 -spill2reg-vec-instrs=99999 | FileCheck --check-prefix=NOSSE %s
+
+# Simple test with a single spill-reload pair:
+#   spill stack.0
+#   reload stack.0
+
+--- |
+  @D0 = dso_local local_unnamed_addr global i32 0, align 4
+  @U0 = dso_local local_unnamed_addr global i32 0, align 4
+  define void @func() { ret void }
+...
+---
+name: func
+alignment:       16
+tracksRegLiveness: true
+tracksDebugUserValues: true
+frameInfo:
+  maxAlignment:    4
+stack:
+  - { id: 0, type: spill-slot, size: 4, alignment: 4 }
+machineFunctionInfo: {}
+body:             |
+ ; CHECK-LABEL:  bb.0:
+ ; CHECK-NEXT:    $eax = MOV32rm $rip, 1, $noreg, @D0, $noreg :: (dereferenceable load (s32) from @D0)
+ ; CHECK-NEXT:    $xmm0 = MOVDI2PDIrr $eax
+ ; CHECK-NEXT:    $eax = MOVPDI2DIrr $xmm0
+ ; CHECK-NEXT:    MOV32mr $rip, 1, $noreg, @U0, $noreg, killed renamable $eax :: (store (s32) into @U0)
+ ; CHECK-NEXT:    RET 0
+
+ ; NOSSE-LABEL:  bb.0:
+ ; NOSSE-NEXT:    $eax = MOV32rm $rip, 1, $noreg, @D0, $noreg :: (dereferenceable load (s32) from @D0)
+ ; NOSSE-NEXT:    MOV32mr %stack.0, 1, $noreg, 0, $noreg, killed renamable $eax :: (store (s32) into %stack.0)
+ ; NOSSE-NEXT:    $eax = MOV32rm %stack.0, 1, $noreg, 0, $noreg :: (load (s32) from %stack.0)
+ ; NOSSE-NEXT:    MOV32mr $rip, 1, $noreg, @U0, $noreg, killed renamable $eax :: (store (s32) into @U0)
+ ; NOSSE-NEXT:    RET 0
+
+  bb.0:
+    ; spill
+    $eax = MOV32rm $rip, 1, $noreg, @D0, $noreg :: (dereferenceable load (s32) from @D0)
+    MOV32mr %stack.0, 1, $noreg, 0, $noreg, killed renamable $eax :: (store (s32) into %stack.0)
+    ; reload
+    $eax = MOV32rm %stack.0, 1, $noreg, 0, $noreg :: (load (s32) from %stack.0)
+    MOV32mr $rip, 1, $noreg, @U0, $noreg, killed renamable $eax :: (store (s32) into @U0)
+    RET 0
+...
diff --git a/llvm/test/CodeGen/X86/spill2reg_simple_2.mir b/llvm/test/CodeGen/X86/spill2reg_simple_2.mir
new file mode 100644
--- /dev/null
+++ b/llvm/test/CodeGen/X86/spill2reg_simple_2.mir
@@ -0,0 +1,52 @@
+# NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+# RUN: llc %s -o - -mtriple=x86_64-unknown-linux -enable-spill2reg -mattr=+sse4.1 --run-pass=spill2reg -simplify-mir -spill2reg-mem-instrs=0 -spill2reg-vec-instrs=99999 | FileCheck %s
+
+# Simple test with two overlapping spill-reload pairs.
+#   spill stack.0
+#   spill stack.1
+#   reload stack.0
+#   reload stack.1
+
+--- |
+  @D0 = dso_local local_unnamed_addr global i32 0, align 4
+  @D1 = dso_local local_unnamed_addr global i32 0, align 4
+  @U0 = dso_local local_unnamed_addr global i32 0, align 4
+  @U1 = dso_local local_unnamed_addr global i32 0, align 4
+  define void @func() { ret void }
+...
+---
+name: func
+alignment:       16
+tracksRegLiveness: true
+tracksDebugUserValues: true
+frameInfo:
+  maxAlignment:    4
+stack:
+  - { id: 0, type: spill-slot, size: 4, alignment: 4 }
+  - { id: 1, type: spill-slot, size: 4, alignment: 4 }
+machineFunctionInfo: {}
+body:             |
+ ; CHECK-LABEL:  bb.0:
+ ; CHECK-NEXT:    $eax = MOV32rm $rip, 1, $noreg, @D0, $noreg :: (dereferenceable load (s32) from @D0)
+ ; CHECK-NEXT:    $xmm0 = MOVDI2PDIrr $eax
+ ; CHECK-NEXT:    $eax = MOV32rm $rip, 1, $noreg, @D1, $noreg :: (dereferenceable load (s32) from @D1)
+ ; CHECK-NEXT:    $xmm0 = MOVDI2PDIrr $eax
+ ; CHECK-NEXT:    $eax = MOVPDI2DIrr $xmm0
+ ; CHECK-NEXT:    MOV32mr $rip, 1, $noreg, @U0, $noreg, killed renamable $eax :: (store (s32) into @U0)
+ ; CHECK-NEXT:    $eax = MOVPDI2DIrr $xmm0
+ ; CHECK-NEXT:    MOV32mr $rip, 1, $noreg, @U1, $noreg, killed renamable $eax :: (store (s32) into @U1)
+ ; CHECK-NEXT:    RET 0
+
+  bb.0:
+    $eax = MOV32rm $rip, 1, $noreg, @D0, $noreg :: (dereferenceable load (s32) from @D0)
+    MOV32mr %stack.0, 1, $noreg, 0, $noreg, killed renamable $eax :: (store (s32) into %stack.0)
+    $eax = MOV32rm $rip, 1, $noreg, @D1, $noreg :: (dereferenceable load (s32) from @D1)
+    MOV32mr %stack.1, 1, $noreg, 0, $noreg, killed renamable $eax :: (store (s32) into %stack.1)
+
+    $eax = MOV32rm %stack.0, 1, $noreg, 0, $noreg :: (load (s32) from %stack.0)
+    MOV32mr $rip, 1, $noreg, @U0, $noreg, killed renamable $eax :: (store (s32) into @U0)
+    $eax = MOV32rm %stack.1, 1, $noreg, 0, $noreg :: (load (s32) from %stack.1)
+    MOV32mr $rip, 1, $noreg, @U1, $noreg, killed renamable $eax :: (store (s32) into @U1)
+    RET 0
+
+...