[X86FixupLEAs] Turn optIncDec into a generic two address LEA optimizer. Support LEA64_32r properly.

INC/DEC is really a special case of a more generic issue. We should also turn leas into add reg/reg or add reg/imm regardless of the slow lea flags.

This also supports LEA64_32 which has 64 bit input registers and 32 bit output registers. So we need to convert the 64 bit inputs to their 32 bit equivalents to check if they are equal to base reg.

One thing to note, the original code preserved the kill flags by adding operands to the new instruction instead of using addReg. But I think tied operands aren't supposed to have the kill flag set. I dropped the kill flags, but I could probably try to preserve it in the add reg/reg case if we think its important. Not sure which operand its supposed to go on for the LEA64_32r instruction due to the super reg implicit uses. Though I'm also not sure those are needed since they were probably just created by an INSERT_SUBREG from a 32-bit input.

Differential Revision: https://reviews.llvm.org/D61472

llvm-svn: 361691

llvm/lib/Target/X86/X86FixupLEAs.cpp

@@ -8,7 +8,7 @@
 //
 // This file defines the pass that finds instructions that can be
 // re-written as LEA instructions in order to reduce pipeline delays.
-// When optimizing for size it replaces suitable LEAs with INC or DEC.
+// It replaces LEAs with ADD/INC/DEC when that is better for size/speed.
 //
 //===----------------------------------------------------------------------===//
 
@@ -70,10 +70,11 @@ class FixupLEAPass : public MachineFunctionPass {
   MachineInstr *processInstrForSlow3OpLEA(MachineInstr &MI,
                                           MachineBasicBlock &MBB);
 
-  /// Look for LEAs that add 1 to reg or subtract 1 from reg
+  /// Look for LEAs that are really two address LEAs that we might be able to
-  /// and convert them to INC or DEC respectively.
+  /// turn into regular ADD instructions.
-  bool fixupIncDec(MachineBasicBlock::iterator &I,
+  bool optTwoAddrLEA(MachineBasicBlock::iterator &I,
-                   MachineBasicBlock &MBB) const;
+                     MachineBasicBlock &MBB, bool OptIncDec,
+                     bool UseLEAForSP) const;
 
   /// Determine if an instruction references a machine register
   /// and, if so, whether it reads or writes the register.
@@ -114,7 +115,8 @@ public:
 
 private:
   TargetSchedModel TSM;
-  const X86InstrInfo *TII; // Machine instruction info.
+  const X86InstrInfo *TII;
+  const X86RegisterInfo *TRI;
 };
 }
 
@@ -197,13 +199,11 @@ bool FixupLEAPass::runOnMachineFunction(MachineFunction &MF) {
   bool LEAUsesAG = ST.LEAusesAG();
 
   bool OptIncDec = !ST.slowIncDec() || MF.getFunction().hasOptSize();
-  bool OptLEA = LEAUsesAG || IsSlowLEA || IsSlow3OpsLEA;
+  bool UseLEAForSP = ST.useLeaForSP();
-
-  if (!OptLEA && !OptIncDec)
-    return false;
 
   TSM.init(&ST);
   TII = ST.getInstrInfo();
+  TRI = ST.getRegisterInfo();
 
   LLVM_DEBUG(dbgs() << "Start X86FixupLEAs\n";);
   for (MachineBasicBlock &MBB : MF) {
@@ -212,7 +212,7 @@ bool FixupLEAPass::runOnMachineFunction(MachineFunction &MF) {
       if (!isLEA(I->getOpcode()))
         continue;
 
-      if (OptIncDec && fixupIncDec(I, MBB))
+      if (optTwoAddrLEA(I, MBB, OptIncDec, UseLEAForSP))
         continue;
 
       if (IsSlowLEA) {
@@ -323,8 +323,8 @@ static inline unsigned getADDrrFromLEA(unsigned LEAOpcode) {
   default:
     llvm_unreachable("Unexpected LEA instruction");
   case X86::LEA32r:
-    return X86::ADD32rr;
   case X86::LEA64_32r:
+    return X86::ADD32rr;
   case X86::LEA64r:
     return X86::ADD64rr;
   }
@@ -344,48 +344,106 @@ static inline unsigned getADDriFromLEA(unsigned LEAOpcode,
   }
 }
 
-/// isLEASimpleIncOrDec - Does this LEA have one these forms:
+static inline unsigned getINCDECFromLEA(unsigned LEAOpcode, bool IsINC) {
-/// lea  %reg, 1(%reg)
+  switch (LEAOpcode) {
-/// lea  %reg, -1(%reg)
+  default:
-static inline bool isLEASimpleIncOrDec(MachineInstr &LEA) {
+    llvm_unreachable("Unexpected LEA instruction");
-  unsigned SrcReg = LEA.getOperand(1 + X86::AddrBaseReg).getReg();
+  case X86::LEA32r:
-  unsigned DstReg = LEA.getOperand(0).getReg();
+  case X86::LEA64_32r:
-  const MachineOperand &AddrDisp = LEA.getOperand(1 + X86::AddrDisp);
+    return IsINC ? X86::INC32r : X86::DEC32r;
-  return SrcReg == DstReg &&
+  case X86::LEA64r:
-         LEA.getOperand(1 + X86::AddrIndexReg).getReg() == 0 &&
+    return IsINC ? X86::INC64r : X86::DEC64r;
-         LEA.getOperand(1 + X86::AddrSegmentReg).getReg() == 0 &&
+  }
-         AddrDisp.isImm() &&
-         (AddrDisp.getImm() == 1 || AddrDisp.getImm() == -1);
 }
 
-bool FixupLEAPass::fixupIncDec(MachineBasicBlock::iterator &I,
+bool FixupLEAPass::optTwoAddrLEA(MachineBasicBlock::iterator &I,
-                               MachineBasicBlock &MBB) const {
+                                 MachineBasicBlock &MBB, bool OptIncDec,
+                                 bool UseLEAForSP) const {
   MachineInstr &MI = *I;
 
-  if (isLEASimpleIncOrDec(MI) && TII->isSafeToClobberEFLAGS(MBB, I)) {
+  const MachineOperand &Base =    MI.getOperand(1 + X86::AddrBaseReg);
-    unsigned NewOpcode;
+  const MachineOperand &Scale =   MI.getOperand(1 + X86::AddrScaleAmt);
-    bool isINC = MI.getOperand(1 + X86::AddrDisp).getImm() == 1;
+  const MachineOperand &Index =   MI.getOperand(1 + X86::AddrIndexReg);
-    switch (MI.getOpcode()) {
+  const MachineOperand &Disp =    MI.getOperand(1 + X86::AddrDisp);
-    default:
+  const MachineOperand &Segment = MI.getOperand(1 + X86::AddrSegmentReg);
-      llvm_unreachable("Unexpected LEA instruction");
-    case X86::LEA32r:
-    case X86::LEA64_32r:
-      NewOpcode = isINC ? X86::INC32r : X86::DEC32r;
-      break;
-    case X86::LEA64r:
-      NewOpcode = isINC ? X86::INC64r : X86::DEC64r;
-      break;
-    }
 
-    MachineInstr *NewMI =
+  if (Segment.getReg() != 0 || !Disp.isImm() || Scale.getImm() > 1 ||
-        BuildMI(MBB, I, MI.getDebugLoc(), TII->get(NewOpcode))
+      !TII->isSafeToClobberEFLAGS(MBB, I))
-            .add(MI.getOperand(0))
+    return false;
-            .add(MI.getOperand(1 + X86::AddrBaseReg));
+
-    MBB.erase(I);
+  unsigned DestReg  = MI.getOperand(0).getReg();
-    I = static_cast<MachineBasicBlock::iterator>(NewMI);
+  unsigned BaseReg  = Base.getReg();
-    return true;
+  unsigned IndexReg = Index.getReg();
+
+  // Don't change stack adjustment LEAs.
+  if (UseLEAForSP && (DestReg == X86::ESP || DestReg == X86::RSP))
+    return false;
+
+  // LEA64_32 has 64-bit operands but 32-bit result.
+  if (MI.getOpcode() == X86::LEA64_32r) {
+    if (BaseReg != 0)
+      BaseReg = TRI->getSubReg(BaseReg, X86::sub_32bit);
+    if (IndexReg != 0)
+      IndexReg = TRI->getSubReg(IndexReg, X86::sub_32bit);
   }
-  return false;
+
+  MachineInstr *NewMI = nullptr;
+
+  // Look for lea(%reg1, %reg2), %reg1 or lea(%reg2, %reg1), %reg1
+  // which can be turned into add %reg2, %reg1
+  if (BaseReg != 0 && IndexReg != 0 && Disp.getImm() == 0 &&
+      (DestReg == BaseReg || DestReg == IndexReg)) {
+    unsigned NewOpcode = getADDrrFromLEA(MI.getOpcode());
+    if (DestReg != BaseReg)
+      std::swap(BaseReg, IndexReg);
+
+    if (MI.getOpcode() == X86::LEA64_32r) {
+      // TODO: Do we need the super register implicit use?
+      NewMI = BuildMI(MBB, I, MI.getDebugLoc(), TII->get(NewOpcode), DestReg)
+        .addReg(BaseReg).addReg(IndexReg)
+        .addReg(Base.getReg(), RegState::Implicit)
+        .addReg(Index.getReg(), RegState::Implicit);
+    } else {
+      NewMI = BuildMI(MBB, I, MI.getDebugLoc(), TII->get(NewOpcode), DestReg)
+        .addReg(BaseReg).addReg(IndexReg);
+    }
+  } else if (DestReg == BaseReg && IndexReg == 0) {
+    // This is an LEA with only a base register and a displacement,
+    // We can use ADDri or INC/DEC.
+
+    // Does this LEA have one these forms:
+    // lea  %reg, 1(%reg)
+    // lea  %reg, -1(%reg)
+    if (OptIncDec && (Disp.getImm() == 1 || Disp.getImm() == -1)) {
+      bool IsINC = Disp.getImm() == 1;
+      unsigned NewOpcode = getINCDECFromLEA(MI.getOpcode(), IsINC);
+
+      if (MI.getOpcode() == X86::LEA64_32r) {
+        // TODO: Do we need the super register implicit use?
+        NewMI = BuildMI(MBB, I, MI.getDebugLoc(), TII->get(NewOpcode), DestReg)
+          .addReg(BaseReg).addReg(Base.getReg(), RegState::Implicit);
+      } else {
+        NewMI = BuildMI(MBB, I, MI.getDebugLoc(), TII->get(NewOpcode), DestReg)
+          .addReg(BaseReg);
+      }
+    } else {
+      unsigned NewOpcode = getADDriFromLEA(MI.getOpcode(), Disp);
+      if (MI.getOpcode() == X86::LEA64_32r) {
+        // TODO: Do we need the super register implicit use?
+        NewMI = BuildMI(MBB, I, MI.getDebugLoc(), TII->get(NewOpcode), DestReg)
+          .addReg(BaseReg).addImm(Disp.getImm())
+          .addReg(Base.getReg(), RegState::Implicit);
+      } else {
+        NewMI = BuildMI(MBB, I, MI.getDebugLoc(), TII->get(NewOpcode), DestReg)
+          .addReg(BaseReg).addImm(Disp.getImm());
+      }
+    }
+  } else
+    return false;
+
+  MBB.erase(I);
+  I = NewMI;
+  return true;
 }
 
 void FixupLEAPass::processInstruction(MachineBasicBlock::iterator &I,

llvm/test/CodeGen/X86/GlobalISel/add-ext.ll

@@ -79,7 +79,7 @@ define i8* @gep8(i32 %i, i8* %x) {
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    addl $5, %edi
 ; CHECK-NEXT:    movslq %edi, %rax
-; CHECK-NEXT:    leaq (%rsi,%rax), %rax
+; CHECK-NEXT:    addq %rsi, %rax
 ; CHECK-NEXT:    retq
 
   %add = add nsw i32 %i, 5
@@ -166,16 +166,16 @@ define void @PR20134(i32* %a, i32 %i) {
 ; CHECK-NEXT:    cltq
 ; CHECK-NEXT:    movq $4, %rcx
 ; CHECK-NEXT:    imulq %rcx, %rax
-; CHECK-NEXT:    leaq (%rdi,%rax), %rax
+; CHECK-NEXT:    addq %rdi, %rax
 ; CHECK-NEXT:    leal 2(%rsi), %edx
 ; CHECK-NEXT:    movslq %edx, %rdx
 ; CHECK-NEXT:    imulq %rcx, %rdx
-; CHECK-NEXT:    leaq (%rdi,%rdx), %rdx
+; CHECK-NEXT:    addq %rdi, %rdx
 ; CHECK-NEXT:    movl (%rdx), %edx
 ; CHECK-NEXT:    addl (%rax), %edx
 ; CHECK-NEXT:    movslq %esi, %rax
 ; CHECK-NEXT:    imulq %rcx, %rax
-; CHECK-NEXT:    leaq (%rdi,%rax), %rax
+; CHECK-NEXT:    addq %rdi, %rax
 ; CHECK-NEXT:    movl %edx, (%rax)
 ; CHECK-NEXT:    retq
 
@@ -204,10 +204,10 @@ define void @PR20134_zext(i32* %a, i32 %i) {
 ; CHECK-NEXT:    leal 1(%rsi), %eax
 ; CHECK-NEXT:    movq $4, %rcx
 ; CHECK-NEXT:    imulq %rcx, %rax
-; CHECK-NEXT:    leaq (%rdi,%rax), %rax
+; CHECK-NEXT:    addq %rdi, %rax
 ; CHECK-NEXT:    leal 2(%rsi), %edx
 ; CHECK-NEXT:    imulq %rcx, %rdx
-; CHECK-NEXT:    leaq (%rdi,%rdx), %rdx
+; CHECK-NEXT:    addq %rdi, %rdx
 ; CHECK-NEXT:    movl (%rdx), %edx
 ; CHECK-NEXT:    addl (%rax), %edx
 ; CHECK-NEXT:    imulq %rcx, %rsi

llvm/test/CodeGen/X86/GlobalISel/callingconv.ll

@@ -409,7 +409,7 @@ define void @test_variadic_call_2(i8** %addr_ptr, double* %val_ptr) {
 ; X32-NEXT:    movl 4(%ecx), %ecx
 ; X32-NEXT:    movl %eax, (%esp)
 ; X32-NEXT:    movl $4, %eax
-; X32-NEXT:    leal (%esp,%eax), %eax
+; X32-NEXT:    addl %esp, %eax
 ; X32-NEXT:    movl %edx, {{[0-9]+}}(%esp)
 ; X32-NEXT:    movl %ecx, 4(%eax)
 ; X32-NEXT:    calll variadic_callee

llvm/test/CodeGen/X86/GlobalISel/gep.ll

@@ -12,7 +12,7 @@ define i32* @test_gep_i8(i32 *%arr, i8 %ind) {
 ; X64_GISEL-NEXT:    sarq %cl, %rsi
 ; X64_GISEL-NEXT:    movq $4, %rax
 ; X64_GISEL-NEXT:    imulq %rsi, %rax
-; X64_GISEL-NEXT:    leaq (%rdi,%rax), %rax
+; X64_GISEL-NEXT:    addq %rdi, %rax
 ; X64_GISEL-NEXT:    retq
 ;
 ; X64-LABEL: test_gep_i8:
@@ -29,7 +29,7 @@ define i32* @test_gep_i8_const(i32 *%arr) {
 ; X64_GISEL-LABEL: test_gep_i8_const:
 ; X64_GISEL:       # %bb.0:
 ; X64_GISEL-NEXT:    movq $80, %rax
-; X64_GISEL-NEXT:    leaq (%rdi,%rax), %rax
+; X64_GISEL-NEXT:    addq %rdi, %rax
 ; X64_GISEL-NEXT:    retq
 ;
 ; X64-LABEL: test_gep_i8_const:
@@ -50,7 +50,7 @@ define i32* @test_gep_i16(i32 *%arr, i16 %ind) {
 ; X64_GISEL-NEXT:    sarq %cl, %rsi
 ; X64_GISEL-NEXT:    movq $4, %rax
 ; X64_GISEL-NEXT:    imulq %rsi, %rax
-; X64_GISEL-NEXT:    leaq (%rdi,%rax), %rax
+; X64_GISEL-NEXT:    addq %rdi, %rax
 ; X64_GISEL-NEXT:    retq
 ;
 ; X64-LABEL: test_gep_i16:
@@ -67,7 +67,7 @@ define i32* @test_gep_i16_const(i32 *%arr) {
 ; X64_GISEL-LABEL: test_gep_i16_const:
 ; X64_GISEL:       # %bb.0:
 ; X64_GISEL-NEXT:    movq $80, %rax
-; X64_GISEL-NEXT:    leaq (%rdi,%rax), %rax
+; X64_GISEL-NEXT:    addq %rdi, %rax
 ; X64_GISEL-NEXT:    retq
 ;
 ; X64-LABEL: test_gep_i16_const:
@@ -100,7 +100,7 @@ define i32* @test_gep_i32_const(i32 *%arr) {
 ; X64_GISEL-LABEL: test_gep_i32_const:
 ; X64_GISEL:       # %bb.0:
 ; X64_GISEL-NEXT:    movq $20, %rax
-; X64_GISEL-NEXT:    leaq (%rdi,%rax), %rax
+; X64_GISEL-NEXT:    addq %rdi, %rax
 ; X64_GISEL-NEXT:    retq
 ;
 ; X64-LABEL: test_gep_i32_const:
@@ -116,7 +116,7 @@ define i32* @test_gep_i64(i32 *%arr, i64 %ind) {
 ; X64_GISEL:       # %bb.0:
 ; X64_GISEL-NEXT:    movq $4, %rax
 ; X64_GISEL-NEXT:    imulq %rsi, %rax
-; X64_GISEL-NEXT:    leaq (%rdi,%rax), %rax
+; X64_GISEL-NEXT:    addq %rdi, %rax
 ; X64_GISEL-NEXT:    retq
 ;
 ; X64-LABEL: test_gep_i64:
@@ -131,7 +131,7 @@ define i32* @test_gep_i64_const(i32 *%arr) {
 ; X64_GISEL-LABEL: test_gep_i64_const:
 ; X64_GISEL:       # %bb.0:
 ; X64_GISEL-NEXT:    movq $20, %rax
-; X64_GISEL-NEXT:    leaq (%rdi,%rax), %rax
+; X64_GISEL-NEXT:    addq %rdi, %rax
 ; X64_GISEL-NEXT:    retq
 ;
 ; X64-LABEL: test_gep_i64_const:

llvm/test/CodeGen/X86/GlobalISel/memop-scalar.ll

@@ -181,7 +181,7 @@ define i32 @test_gep_folding_largeGepIndex(i32* %arr, i32 %val) {
 ; ALL-LABEL: test_gep_folding_largeGepIndex:
 ; ALL:       # %bb.0:
 ; ALL-NEXT:    movabsq $228719476720, %rax # imm = 0x3540BE3FF0
-; ALL-NEXT:    leaq (%rdi,%rax), %rax
+; ALL-NEXT:    addq %rdi, %rax
 ; ALL-NEXT:    movl %esi, (%rax)
 ; ALL-NEXT:    movl (%rax), %eax
 ; ALL-NEXT:    retq

llvm/test/CodeGen/X86/MergeConsecutiveStores.ll

@@ -632,7 +632,7 @@ define void @loadStoreBaseIndexOffsetSextNoSex(i8* %a, i8* %b, i8* %c, i32 %n) {
 ; BWON-NEXT:  .LBB12_1: # =>This Inner Loop Header: Depth=1
 ; BWON-NEXT:    movsbq (%rdi,%rcx), %rax
 ; BWON-NEXT:    movzbl (%rdx,%rax), %r9d
-; BWON-NEXT:    leal 1(%rax), %eax
+; BWON-NEXT:    incl %eax
 ; BWON-NEXT:    movsbq %al, %rax
 ; BWON-NEXT:    movzbl (%rdx,%rax), %eax
 ; BWON-NEXT:    movb %r9b, (%rsi,%rcx,2)
@@ -651,7 +651,7 @@ define void @loadStoreBaseIndexOffsetSextNoSex(i8* %a, i8* %b, i8* %c, i32 %n) {
 ; BWOFF-NEXT:  .LBB12_1: # =>This Inner Loop Header: Depth=1
 ; BWOFF-NEXT:    movsbq (%rdi,%rcx), %rax
 ; BWOFF-NEXT:    movb (%rdx,%rax), %r9b
-; BWOFF-NEXT:    leal 1(%rax), %eax
+; BWOFF-NEXT:    incl %eax
 ; BWOFF-NEXT:    movsbq %al, %rax
 ; BWOFF-NEXT:    movb (%rdx,%rax), %al
 ; BWOFF-NEXT:    movb %r9b, (%rsi,%rcx,2)

llvm/test/CodeGen/X86/atomic-unordered.ll

@@ -772,7 +772,7 @@ define i64 @load_fold_sdiv1(i64* %p) {
 ; CHECK-O3-NEXT:    movq %rdx, %rax
 ; CHECK-O3-NEXT:    shrq $63, %rax
 ; CHECK-O3-NEXT:    sarq $3, %rdx
-; CHECK-O3-NEXT:    leaq (%rdx,%rax), %rax
+; CHECK-O3-NEXT:    addq %rdx, %rax
 ; CHECK-O3-NEXT:    retq
   %v = load atomic i64, i64* %p unordered, align 8
   %ret = sdiv i64 %v, 15

llvm/test/CodeGen/X86/avx512vl-intrinsics-upgrade.ll

@@ -9268,7 +9268,7 @@ define i8@test_int_x86_avx512_ptestm_d_128(<4 x i32> %x0, <4 x i32> %x1, i8 %x2)
 ; X64-NEXT:    kandw %k1, %k0, %k1 # encoding: [0xc5,0xfc,0x41,0xc9]
 ; X64-NEXT:    kmovw %k1, %eax # encoding: [0xc5,0xf8,0x93,0xc1]
 ; X64-NEXT:    kmovw %k0, %ecx # encoding: [0xc5,0xf8,0x93,0xc8]
-; X64-NEXT:    leal (%rcx,%rax), %eax # encoding: [0x8d,0x04,0x01]
+; X64-NEXT:    addl %ecx, %eax # encoding: [0x01,0xc8]
 ; X64-NEXT:    # kill: def $al killed $al killed $eax
 ; X64-NEXT:    retq # encoding: [0xc3]
   %res = call i8 @llvm.x86.avx512.ptestm.d.128(<4 x i32> %x0, <4 x i32> %x1, i8 %x2)
@@ -9327,7 +9327,7 @@ define i8@test_int_x86_avx512_ptestm_q_128(<2 x i64> %x0, <2 x i64> %x1, i8 %x2)
 ; X64-NEXT:    kandw %k1, %k0, %k1 # encoding: [0xc5,0xfc,0x41,0xc9]
 ; X64-NEXT:    kmovw %k1, %eax # encoding: [0xc5,0xf8,0x93,0xc1]
 ; X64-NEXT:    kmovw %k0, %ecx # encoding: [0xc5,0xf8,0x93,0xc8]
-; X64-NEXT:    leal (%rcx,%rax), %eax # encoding: [0x8d,0x04,0x01]
+; X64-NEXT:    addl %ecx, %eax # encoding: [0x01,0xc8]
 ; X64-NEXT:    # kill: def $al killed $al killed $eax
 ; X64-NEXT:    retq # encoding: [0xc3]
   %res = call i8 @llvm.x86.avx512.ptestm.q.128(<2 x i64> %x0, <2 x i64> %x1, i8 %x2)
@@ -9359,7 +9359,7 @@ define i8@test_int_x86_avx512_ptestm_q_256(<4 x i64> %x0, <4 x i64> %x1, i8 %x2)
 ; X64-NEXT:    kandw %k1, %k0, %k1 # encoding: [0xc5,0xfc,0x41,0xc9]
 ; X64-NEXT:    kmovw %k1, %eax # encoding: [0xc5,0xf8,0x93,0xc1]
 ; X64-NEXT:    kmovw %k0, %ecx # encoding: [0xc5,0xf8,0x93,0xc8]
-; X64-NEXT:    leal (%rcx,%rax), %eax # encoding: [0x8d,0x04,0x01]
+; X64-NEXT:    addl %ecx, %eax # encoding: [0x01,0xc8]
 ; X64-NEXT:    # kill: def $al killed $al killed $eax
 ; X64-NEXT:    vzeroupper # encoding: [0xc5,0xf8,0x77]
 ; X64-NEXT:    retq # encoding: [0xc3]
@@ -9391,7 +9391,7 @@ define i8@test_int_x86_avx512_ptestnm_d_128(<4 x i32> %x0, <4 x i32> %x1, i8 %x2
 ; X64-NEXT:    kandw %k1, %k0, %k1 # encoding: [0xc5,0xfc,0x41,0xc9]
 ; X64-NEXT:    kmovw %k1, %eax # encoding: [0xc5,0xf8,0x93,0xc1]
 ; X64-NEXT:    kmovw %k0, %ecx # encoding: [0xc5,0xf8,0x93,0xc8]
-; X64-NEXT:    leal (%rcx,%rax), %eax # encoding: [0x8d,0x04,0x01]
+; X64-NEXT:    addl %ecx, %eax # encoding: [0x01,0xc8]
 ; X64-NEXT:    # kill: def $al killed $al killed $eax
 ; X64-NEXT:    retq # encoding: [0xc3]
   %res = call i8 @llvm.x86.avx512.ptestnm.d.128(<4 x i32> %x0, <4 x i32> %x1, i8 %x2)
@@ -9450,7 +9450,7 @@ define i8@test_int_x86_avx512_ptestnm_q_128(<2 x i64> %x0, <2 x i64> %x1, i8 %x2
 ; X64-NEXT:    kandw %k1, %k0, %k1 # encoding: [0xc5,0xfc,0x41,0xc9]
 ; X64-NEXT:    kmovw %k1, %eax # encoding: [0xc5,0xf8,0x93,0xc1]
 ; X64-NEXT:    kmovw %k0, %ecx # encoding: [0xc5,0xf8,0x93,0xc8]
-; X64-NEXT:    leal (%rcx,%rax), %eax # encoding: [0x8d,0x04,0x01]
+; X64-NEXT:    addl %ecx, %eax # encoding: [0x01,0xc8]
 ; X64-NEXT:    # kill: def $al killed $al killed $eax
 ; X64-NEXT:    retq # encoding: [0xc3]
   %res = call i8 @llvm.x86.avx512.ptestnm.q.128(<2 x i64> %x0, <2 x i64> %x1, i8 %x2)
@@ -9482,7 +9482,7 @@ define i8@test_int_x86_avx512_ptestnm_q_256(<4 x i64> %x0, <4 x i64> %x1, i8 %x2
 ; X64-NEXT:    kandw %k1, %k0, %k1 # encoding: [0xc5,0xfc,0x41,0xc9]
 ; X64-NEXT:    kmovw %k1, %eax # encoding: [0xc5,0xf8,0x93,0xc1]
 ; X64-NEXT:    kmovw %k0, %ecx # encoding: [0xc5,0xf8,0x93,0xc8]
-; X64-NEXT:    leal (%rcx,%rax), %eax # encoding: [0x8d,0x04,0x01]
+; X64-NEXT:    addl %ecx, %eax # encoding: [0x01,0xc8]
 ; X64-NEXT:    # kill: def $al killed $al killed $eax
 ; X64-NEXT:    vzeroupper # encoding: [0xc5,0xf8,0x77]
 ; X64-NEXT:    retq # encoding: [0xc3]

llvm/test/CodeGen/X86/bitreverse.ll

@@ -347,7 +347,7 @@ define i8 @test_bitreverse_i8(i8 %a) {
 ; X64-NEXT:    addb %al, %al
 ; X64-NEXT:    andb $-86, %dil
 ; X64-NEXT:    shrb %dil
-; X64-NEXT:    leal (%rdi,%rax), %eax
+; X64-NEXT:    addl %edi, %eax
 ; X64-NEXT:    # kill: def $al killed $al killed $eax
 ; X64-NEXT:    retq
   %b = call i8 @llvm.bitreverse.i8(i8 %a)
@@ -391,7 +391,7 @@ define i4 @test_bitreverse_i4(i4 %a) {
 ; X64-NEXT:    addb %al, %al
 ; X64-NEXT:    andb $-96, %dil
 ; X64-NEXT:    shrb %dil
-; X64-NEXT:    leal (%rdi,%rax), %eax
+; X64-NEXT:    addl %edi, %eax
 ; X64-NEXT:    shrb $4, %al
 ; X64-NEXT:    # kill: def $al killed $al killed $eax
 ; X64-NEXT:    retq

llvm/test/CodeGen/X86/bswap_tree2.ll

@@ -81,7 +81,7 @@ define i32 @test2(i32 %x) nounwind {
 ; CHECK64-NEXT:    andl $-16777216, %edi # imm = 0xFF000000
 ; CHECK64-NEXT:    andl $16711680, %eax # imm = 0xFF0000
 ; CHECK64-NEXT:    orl %edi, %eax
-; CHECK64-NEXT:    leal (%rax,%rcx), %eax
+; CHECK64-NEXT:    addl %ecx, %eax
 ; CHECK64-NEXT:    retq
   %byte1 = lshr i32 %x, 8
   %byte0 = shl  i32 %x, 8

llvm/test/CodeGen/X86/bypass-slow-division-32.ll

@@ -143,7 +143,7 @@ define i32 @Test_use_div_reg_imm(i32 %a) nounwind {
 ; CHECK-NEXT:    movl %edx, %eax
 ; CHECK-NEXT:    shrl $31, %eax
 ; CHECK-NEXT:    sarl $3, %edx
-; CHECK-NEXT:    leal (%edx,%eax), %eax
+; CHECK-NEXT:    addl %edx, %eax
 ; CHECK-NEXT:    retl
   %resultdiv = sdiv i32 %a, 33
   ret i32 %resultdiv

llvm/test/CodeGen/X86/combine-srem.ll

@@ -61,7 +61,7 @@ define i32 @combine_srem_by_minsigned(i32 %x) {
 ; CHECK-NEXT:    shrl %eax
 ; CHECK-NEXT:    addl %edi, %eax
 ; CHECK-NEXT:    andl $-2147483648, %eax # imm = 0x80000000
-; CHECK-NEXT:    leal (%rax,%rdi), %eax
+; CHECK-NEXT:    addl %edi, %eax
 ; CHECK-NEXT:    retq
   %1 = srem i32 %x, -2147483648
   ret i32 %1

llvm/test/CodeGen/X86/dagcombine-shifts.ll

@@ -161,7 +161,7 @@ define i64 @fun11(i16 zeroext %v) {
 ; CHECK-NEXT:    shrl $4, %edi
 ; CHECK-NEXT:    movq %rdi, %rax
 ; CHECK-NEXT:    shlq $4, %rax
-; CHECK-NEXT:    leaq (%rax,%rdi), %rax
+; CHECK-NEXT:    addq %rdi, %rax
 ; CHECK-NEXT:    retq
 entry:
   %shr = lshr i16 %v, 4
@@ -178,7 +178,7 @@ define i64 @fun12(i32 zeroext %v) {
 ; CHECK-NEXT:    shrl $4, %edi
 ; CHECK-NEXT:    movq %rdi, %rax
 ; CHECK-NEXT:    shlq $4, %rax
-; CHECK-NEXT:    leaq (%rax,%rdi), %rax
+; CHECK-NEXT:    addq %rdi, %rax
 ; CHECK-NEXT:    retq
 entry:
   %shr = lshr i32 %v, 4

llvm/test/CodeGen/X86/fixup-bw-copy.ll

@@ -46,7 +46,7 @@ define i8 @test_movb_hreg(i16 %a0) {
 ; X64-NEXT:    # kill: def $edi killed $edi def $rdi
 ; X64-NEXT:    movl %edi, %eax
 ; X64-NEXT:    shrl $8, %eax
-; X64-NEXT:    leal (%rax,%rdi), %eax
+; X64-NEXT:    addl %edi, %eax
 ; X64-NEXT:    # kill: def $al killed $al killed $eax
 ; X64-NEXT:    retq
 ;

llvm/test/CodeGen/X86/fixup-lea.ll

@@ -129,7 +129,7 @@ define void @foo_nosize(i32 inreg %dns) {
 ; FAST-NEXT:  .LBB4_1: # %for.body
 ; FAST-NEXT:    # =>This Inner Loop Header: Depth=1
 ; FAST-NEXT:    movzwl %cx, %edx
-; FAST-NEXT:    leal -1(%ecx), %ecx
+; FAST-NEXT:    addl $-1, %ecx
 ; FAST-NEXT:    cmpl %eax, %edx
 ; FAST-NEXT:    jl .LBB4_1
 ; FAST-NEXT:  # %bb.2: # %for.end
@@ -169,7 +169,7 @@ define void @bar_nosize(i32 inreg %dns) {
 ; FAST-NEXT:  .LBB5_1: # %for.body
 ; FAST-NEXT:    # =>This Inner Loop Header: Depth=1
 ; FAST-NEXT:    movzwl %cx, %edx
-; FAST-NEXT:    leal 1(%ecx), %ecx
+; FAST-NEXT:    addl $1, %ecx
 ; FAST-NEXT:    cmpl %eax, %edx
 ; FAST-NEXT:    jl .LBB5_1
 ; FAST-NEXT:  # %bb.2: # %for.end

llvm/test/CodeGen/X86/imul.ll

@@ -220,7 +220,7 @@ define i32 @mul33_32(i32 %A) {
 ; X64-NEXT:    # kill: def $edi killed $edi def $rdi
 ; X64-NEXT:    movl %edi, %eax
 ; X64-NEXT:    shll $5, %eax
-; X64-NEXT:    leal (%rax,%rdi), %eax
+; X64-NEXT:    addl %edi, %eax
 ; X64-NEXT:    retq
 ;
 ; X86-LABEL: mul33_32:
@@ -349,7 +349,7 @@ define i32 @test2(i32 %a) {
 ; X64-NEXT:    # kill: def $edi killed $edi def $rdi
 ; X64-NEXT:    movl %edi, %eax
 ; X64-NEXT:    shll $5, %eax
-; X64-NEXT:    leal (%rax,%rdi), %eax
+; X64-NEXT:    addl %edi, %eax
 ; X64-NEXT:    retq
 ;
 ; X86-LABEL: test2:
@@ -370,7 +370,7 @@ define i32 @test3(i32 %a) {
 ; X64-NEXT:    # kill: def $edi killed $edi def $rdi
 ; X64-NEXT:    movl %edi, %eax
 ; X64-NEXT:    shll $5, %eax
-; X64-NEXT:    leal (%rax,%rdi), %eax
+; X64-NEXT:    addl %edi, %eax
 ; X64-NEXT:    negl %eax
 ; X64-NEXT:    retq
 ;
@@ -448,7 +448,7 @@ define i64 @test6(i64 %a) {
 ; X64:       # %bb.0: # %entry
 ; X64-NEXT:    movq %rdi, %rax
 ; X64-NEXT:    shlq $5, %rax
-; X64-NEXT:    leaq (%rax,%rdi), %rax
+; X64-NEXT:    addq %rdi, %rax
 ; X64-NEXT:    retq
 ;
 ; X86-LABEL: test6:
@@ -471,7 +471,7 @@ define i64 @test7(i64 %a) {
 ; X64:       # %bb.0: # %entry
 ; X64-NEXT:    movq %rdi, %rax
 ; X64-NEXT:    shlq $5, %rax
-; X64-NEXT:    leaq (%rax,%rdi), %rax
+; X64-NEXT:    addq %rdi, %rax
 ; X64-NEXT:    negq %rax
 ; X64-NEXT:    retq
 ;

llvm/test/CodeGen/X86/leaFixup32.mir

@@ -174,7 +174,7 @@ frameInfo:
 body:             |
   bb.0 (%ir-block.0):
     liveins: $eax, $ebp
-    ; CHECK: $ebp = ADD32rr $ebp, killed $eax
+    ; CHECK: $ebp = ADD32rr $ebp, $eax
  
     $ebp = LEA32r killed $ebp, 1, killed $eax, 0, $noreg
     RETQ $ebp

llvm/test/CodeGen/X86/leaFixup64.mir

@@ -247,7 +247,7 @@ frameInfo:
 body:             |
   bb.0 (%ir-block.0):
     liveins: $rax, $rbp
-    ; CHECK: $ebp = LEA64_32r killed $rax, 1, killed $rbp, 0
+    ; CHECK: $ebp = ADD32rr $ebp, $eax, implicit-def $eflags, implicit $rbp, implicit $rax
  
     $ebp = LEA64_32r killed $rbp, 1, killed $rax, 0, $noreg
     RETQ $ebp
@@ -351,7 +351,7 @@ frameInfo:
 body:             |
   bb.0 (%ir-block.0):
     liveins: $rax, $rbp
-    ; CHECK: $rbp = ADD64rr $rbp, killed $rax
+    ; CHECK: $rbp = ADD64rr $rbp, $rax
  
     $rbp = LEA64r killed $rbp, 1, killed $rax, 0, $noreg
     RETQ $ebp

llvm/test/CodeGen/X86/mul-constant-i16.ll

@@ -321,7 +321,7 @@ define i16 @test_mul_by_17(i16 %x) {
 ; X64-NEXT:    # kill: def $edi killed $edi def $rdi
 ; X64-NEXT:    movl %edi, %eax
 ; X64-NEXT:    shll $4, %eax
-; X64-NEXT:    leal (%rax,%rdi), %eax
+; X64-NEXT:    addl %edi, %eax
 ; X64-NEXT:    # kill: def $ax killed $ax killed $eax
 ; X64-NEXT:    retq
   %mul = mul nsw i16 %x, 17

llvm/test/CodeGen/X86/mul-constant-i32.ll

@@ -490,7 +490,7 @@ define i32 @test_mul_by_17(i32 %x) {
 ; X64-NEXT:    # kill: def $edi killed $edi def $rdi
 ; X64-NEXT:    movl %edi, %eax
 ; X64-NEXT:    shll $4, %eax
-; X64-NEXT:    leal (%rax,%rdi), %eax
+; X64-NEXT:    addl %edi, %eax
 ; X64-NEXT:    retq
 ;
 ; X86-NOOPT-LABEL: test_mul_by_17:
@@ -1183,7 +1183,7 @@ define i32 @test_mul_by_66(i32 %x) {
 ; X64-SLM-NEXT:    # kill: def $edi killed $edi def $rdi
 ; X64-SLM-NEXT:    movl %edi, %eax
 ; X64-SLM-NEXT:    shll $6, %eax
-; X64-SLM-NEXT:    leal (%rax,%rdi), %eax
+; X64-SLM-NEXT:    addl %edi, %eax
 ; X64-SLM-NEXT:    addl %edi, %eax
 ; X64-SLM-NEXT:    retq
   %mul = mul nsw i32 %x, 66

llvm/test/CodeGen/X86/mul-constant-i64.ll

@@ -515,26 +515,12 @@ define i64 @test_mul_by_17(i64 %x) {
 ; X86-NOOPT-NEXT:    addl %ecx, %edx
 ; X86-NOOPT-NEXT:    retl
 ;
-; X64-HSW-LABEL: test_mul_by_17:
+; X64-OPT-LABEL: test_mul_by_17:
-; X64-HSW:       # %bb.0:
+; X64-OPT:       # %bb.0:
-; X64-HSW-NEXT:    movq %rdi, %rax
+; X64-OPT-NEXT:    movq %rdi, %rax
-; X64-HSW-NEXT:    shlq $4, %rax
+; X64-OPT-NEXT:    shlq $4, %rax
-; X64-HSW-NEXT:    leaq (%rax,%rdi), %rax
+; X64-OPT-NEXT:    addq %rdi, %rax
-; X64-HSW-NEXT:    retq
+; X64-OPT-NEXT:    retq
-;
-; X64-JAG-LABEL: test_mul_by_17:
-; X64-JAG:       # %bb.0:
-; X64-JAG-NEXT:    movq %rdi, %rax
-; X64-JAG-NEXT:    shlq $4, %rax
-; X64-JAG-NEXT:    leaq (%rax,%rdi), %rax
-; X64-JAG-NEXT:    retq
-;
-; X64-SLM-LABEL: test_mul_by_17:
-; X64-SLM:       # %bb.0:
-; X64-SLM-NEXT:    movq %rdi, %rax
-; X64-SLM-NEXT:    shlq $4, %rax
-; X64-SLM-NEXT:    addq %rdi, %rax
-; X64-SLM-NEXT:    retq
 ;
 ; X64-NOOPT-LABEL: test_mul_by_17:
 ; X64-NOOPT:       # %bb.0:

llvm/test/CodeGen/X86/mul-constant-i8.ll

@@ -191,7 +191,7 @@ define i8 @test_mul_by_17(i8 %x) {
 ; X64-NEXT:    # kill: def $edi killed $edi def $rdi
 ; X64-NEXT:    movl %edi, %eax
 ; X64-NEXT:    shll $4, %eax
-; X64-NEXT:    leal (%rax,%rdi), %eax
+; X64-NEXT:    addl %edi, %eax
 ; X64-NEXT:    # kill: def $al killed $al killed $eax
 ; X64-NEXT:    retq
   %m = mul i8 %x, 17

llvm/test/CodeGen/X86/popcnt.ll

@@ -39,7 +39,7 @@ define i8 @cnt8(i8 %x) nounwind readnone {
 ; X64-NEXT:    addb %al, %dil
 ; X64-NEXT:    movl %edi, %eax
 ; X64-NEXT:    shrb $4, %al
-; X64-NEXT:    leal (%rax,%rdi), %eax
+; X64-NEXT:    addl %edi, %eax
 ; X64-NEXT:    andb $15, %al
 ; X64-NEXT:    # kill: def $al killed $al killed $eax
 ; X64-NEXT:    retq
@@ -227,7 +227,7 @@ define i64 @cnt64(i64 %x) nounwind readnone {
 ; X64-NEXT:    addq %rcx, %rdi
 ; X64-NEXT:    movq %rdi, %rax
 ; X64-NEXT:    shrq $4, %rax
-; X64-NEXT:    leaq (%rax,%rdi), %rax
+; X64-NEXT:    addq %rdi, %rax
 ; X64-NEXT:    movabsq $1085102592571150095, %rcx # imm = 0xF0F0F0F0F0F0F0F
 ; X64-NEXT:    andq %rax, %rcx
 ; X64-NEXT:    movabsq $72340172838076673, %rax # imm = 0x101010101010101
@@ -347,7 +347,7 @@ define i64 @cnt64_noimplicitfloat(i64 %x) nounwind readnone noimplicitfloat  {
 ; X64-NEXT:    addq %rcx, %rdi
 ; X64-NEXT:    movq %rdi, %rax
 ; X64-NEXT:    shrq $4, %rax
-; X64-NEXT:    leaq (%rax,%rdi), %rax
+; X64-NEXT:    addq %rdi, %rax
 ; X64-NEXT:    movabsq $1085102592571150095, %rcx # imm = 0xF0F0F0F0F0F0F0F
 ; X64-NEXT:    andq %rax, %rcx
 ; X64-NEXT:    movabsq $72340172838076673, %rax # imm = 0x101010101010101

llvm/test/CodeGen/X86/ragreedy-hoist-spill.ll

@@ -166,7 +166,7 @@ define i8* @SyFgets(i8* %line, i64 %length, i64 %fid) {
 ; CHECK-NEXT:  LBB0_34: ## %if.end517
 ; CHECK-NEXT:    ## in Loop: Header=BB0_13 Depth=1
 ; CHECK-NEXT:    movq {{[-0-9]+}}(%r{{[sb]}}p), %rax ## 8-byte Reload
-; CHECK-NEXT:    leal -324(%rax), %eax
+; CHECK-NEXT:    addl $-324, %eax ## imm = 0xFEBC
 ; CHECK-NEXT:    cmpl $59, %eax
 ; CHECK-NEXT:    ja LBB0_35
 ; CHECK-NEXT:  ## %bb.57: ## %if.end517

llvm/test/CodeGen/X86/reverse_branches.ll

@@ -62,7 +62,7 @@ define i32 @test_branches_order() uwtable ssp {
 ; CHECK-NEXT:    ## in Loop: Header=BB0_3 Depth=2
 ; CHECK-NEXT:    addq $1002, %rbp ## imm = 0x3EA
 ; CHECK-NEXT:    movq %rbx, %rdi
-; CHECK-NEXT:    leaq 1001(%rbx), %rbx
+; CHECK-NEXT:    addq $1001, %rbx ## imm = 0x3E9
 ; CHECK-NEXT:    movl $1000, %edx ## imm = 0x3E8
 ; CHECK-NEXT:    movl $120, %esi
 ; CHECK-NEXT:    callq _memchr

llvm/test/CodeGen/X86/rotate-extract.ll

@@ -156,7 +156,7 @@ define i64 @no_extract_shl(i64 %i) nounwind {
 ; X64-NEXT:    shlq $5, %rax
 ; X64-NEXT:    shlq $10, %rdi
 ; X64-NEXT:    shrq $57, %rax
-; X64-NEXT:    leaq (%rax,%rdi), %rax
+; X64-NEXT:    addq %rdi, %rax
 ; X64-NEXT:    retq
   %lhs_mul = shl i64 %i, 5
   %rhs_mul = shl i64 %i, 10
@@ -184,7 +184,7 @@ define i32 @no_extract_shrl(i32 %i) nounwind {
 ; X64-NEXT:    andl $-8, %eax
 ; X64-NEXT:    shll $25, %eax
 ; X64-NEXT:    shrl $9, %edi
-; X64-NEXT:    leal (%rdi,%rax), %eax
+; X64-NEXT:    addl %edi, %eax
 ; X64-NEXT:    retq
   %lhs_div = lshr i32 %i, 3
   %rhs_div = lshr i32 %i, 9

llvm/test/CodeGen/X86/sat-add.ll

@@ -236,7 +236,7 @@ define i16 @unsigned_sat_variable_i16_using_min(i16 %x, i16 %y) {
 ; ANY-NEXT:    notl %eax
 ; ANY-NEXT:    cmpw %ax, %di
 ; ANY-NEXT:    cmovbl %edi, %eax
-; ANY-NEXT:    leal (%rax,%rsi), %eax
+; ANY-NEXT:    addl %esi, %eax
 ; ANY-NEXT:    # kill: def $ax killed $ax killed $eax
 ; ANY-NEXT:    retq
   %noty = xor i16 %y, -1
@@ -287,7 +287,7 @@ define i32 @unsigned_sat_variable_i32_using_min(i32 %x, i32 %y) {
 ; ANY-NEXT:    notl %eax
 ; ANY-NEXT:    cmpl %eax, %edi
 ; ANY-NEXT:    cmovbl %edi, %eax
-; ANY-NEXT:    leal (%rax,%rsi), %eax
+; ANY-NEXT:    addl %esi, %eax
 ; ANY-NEXT:    retq
   %noty = xor i32 %y, -1
   %c = icmp ult i32 %x, %noty
@@ -334,7 +334,7 @@ define i64 @unsigned_sat_variable_i64_using_min(i64 %x, i64 %y) {
 ; ANY-NEXT:    notq %rax
 ; ANY-NEXT:    cmpq %rax, %rdi
 ; ANY-NEXT:    cmovbq %rdi, %rax
-; ANY-NEXT:    leaq (%rax,%rsi), %rax
+; ANY-NEXT:    addq %rsi, %rax
 ; ANY-NEXT:    retq
   %noty = xor i64 %y, -1
   %c = icmp ult i64 %x, %noty

llvm/test/CodeGen/X86/twoaddr-lea.ll

@@ -69,7 +69,7 @@ bb2:
 
 bb3:
 ; CHECK: subl %e[[REG0:[a-z0-9]+]],
-; CHECK: leaq 4({{%[a-z0-9]+}}), %r[[REG0]]
+; CHECK: addq $4, %r[[REG0]]
   %tmp14 = phi i64 [ %tmp15, %bb5 ], [ 0, %bb1 ]
   %tmp15 = add nuw i64 %tmp14, 4
   %tmp16 = trunc i64 %tmp14 to i32

llvm/test/CodeGen/X86/vector-bitreverse.ll

@@ -27,7 +27,7 @@ define i8 @test_bitreverse_i8(i8 %a) nounwind {
 ; SSE-NEXT:    addb %al, %al
 ; SSE-NEXT:    andb $-86, %dil
 ; SSE-NEXT:    shrb %dil
-; SSE-NEXT:    leal (%rdi,%rax), %eax
+; SSE-NEXT:    addl %edi, %eax
 ; SSE-NEXT:    # kill: def $al killed $al killed $eax
 ; SSE-NEXT:    retq
 ;
@@ -46,7 +46,7 @@ define i8 @test_bitreverse_i8(i8 %a) nounwind {
 ; AVX-NEXT:    addb %al, %al
 ; AVX-NEXT:    andb $-86, %dil
 ; AVX-NEXT:    shrb %dil
-; AVX-NEXT:    leal (%rdi,%rax), %eax
+; AVX-NEXT:    addl %edi, %eax
 ; AVX-NEXT:    # kill: def $al killed $al killed $eax
 ; AVX-NEXT:    retq
 ;

llvm/test/CodeGen/X86/win_coreclr_chkstk.ll

@@ -21,7 +21,7 @@ entry:
 ; WIN_X64:# %bb.1:
 ; WIN_X64:	andq	$-4096, %rdx
 ; WIN_X64:.LBB0_2:
-; WIN_X64:	leaq	-4096(%rcx), %rcx
+; WIN_X64:	addq	$-4096, %rcx
 ; WIN_X64:	movb	$0, (%rcx)
 ; WIN_X64:	cmpq	%rcx, %rdx
 ; WIN_X64:	jne	.LBB0_2

llvm/test/Transforms/LoopStrengthReduce/X86/ivchain-X86.ll

@@ -243,14 +243,14 @@ define void @extrastride(i8* nocapture %main, i32 %main_stride, i32* nocapture %
 ; X32-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X32-NEXT:    movl (%ebx,%esi), %ebp
 ; X32-NEXT:    addl (%ebx), %ebp
-; X32-NEXT:    leal (%ebx,%esi), %ebx
+; X32-NEXT:    addl %esi, %ebx
 ; X32-NEXT:    addl (%esi,%ebx), %ebp
-; X32-NEXT:    leal (%ebx,%esi), %ebx
+; X32-NEXT:    addl %esi, %ebx
 ; X32-NEXT:    addl (%esi,%ebx), %ebp
-; X32-NEXT:    leal (%ebx,%esi), %ebx
+; X32-NEXT:    addl %esi, %ebx
 ; X32-NEXT:    addl (%esi,%ebx), %ebp
 ; X32-NEXT:    movl %ebp, (%edx)
-; X32-NEXT:    leal (%ebx,%esi), %ebx
+; X32-NEXT:    addl %esi, %ebx
 ; X32-NEXT:    addl %edi, %ebx
 ; X32-NEXT:    addl %ecx, %edx
 ; X32-NEXT:    decl %eax