[MachineLICM] Relax overlay conservative PHI check (#67186)

Skip LICM if PHI belongs to the current loop, e.g. is in the
loop's header. This prevents LICM from bailing for CFGs like

L1:
  R = LoopInvariant // can be LICM'd
  BR L1
L2:
  PHI(R, ..)
  BR L2

Author: Hendrik Greving

llvm/lib/CodeGen/MachineLICM.cpp

@@ -1050,7 +1050,7 @@ bool MachineLICMBase::HasLoopPHIUse(const MachineInstr *MI,
         if (UseMI.isPHI()) {
           // A PHI inside the loop causes a copy because the live range of Reg is
           // extended across the PHI.
-          if (CurLoop->contains(&UseMI))
+          if (CurLoop->getHeader() == UseMI.getParent())
             return true;
           // A PHI in an exit block can cause a copy to be inserted if the PHI
           // has multiple predecessors in the loop with different values.

llvm/test/CodeGen/X86/2008-04-28-CoalescerBug.ll

@@ -15,7 +15,7 @@ define void @t(ptr %depth, ptr %bop, i32 %mode) nounwind  {
 ; CHECK-NEXT:    je LBB0_3
 ; CHECK-NEXT:  ## %bb.1: ## %entry
 ; CHECK-NEXT:    cmpl $1, %edx
-; CHECK-NEXT:    jne LBB0_10
+; CHECK-NEXT:    jne LBB0_9
 ; CHECK-NEXT:    .p2align 4, 0x90
 ; CHECK-NEXT:  LBB0_2: ## %bb2898.us
 ; CHECK-NEXT:    ## =>This Inner Loop Header: Depth=1
@@ -26,15 +26,12 @@ define void @t(ptr %depth, ptr %bop, i32 %mode) nounwind  {
 ; CHECK-NEXT:  LBB0_4: ## %bb13088
 ; CHECK-NEXT:    ## =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    testb %al, %al
-; CHECK-NEXT:    jne LBB0_5
-; CHECK-NEXT:  ## %bb.6: ## %bb13101
+; CHECK-NEXT:    movl $65535, %ecx ## imm = 0xFFFF
+; CHECK-NEXT:    jne LBB0_6
+; CHECK-NEXT:  ## %bb.5: ## %bb13101
 ; CHECK-NEXT:    ## in Loop: Header=BB0_4 Depth=1
 ; CHECK-NEXT:    xorl %ecx, %ecx
-; CHECK-NEXT:    jmp LBB0_7
-; CHECK-NEXT:    .p2align 4, 0x90
-; CHECK-NEXT:  LBB0_5: ## in Loop: Header=BB0_4 Depth=1
-; CHECK-NEXT:    movl $65535, %ecx ## imm = 0xFFFF
-; CHECK-NEXT:  LBB0_7: ## %bb13107
+; CHECK-NEXT:  LBB0_6: ## %bb13107
 ; CHECK-NEXT:    ## in Loop: Header=BB0_4 Depth=1
 ; CHECK-NEXT:    movl %ecx, %edx
 ; CHECK-NEXT:    shll $16, %edx
@@ -44,11 +41,11 @@ define void @t(ptr %depth, ptr %bop, i32 %mode) nounwind  {
 ; CHECK-NEXT:    subl %edx, %ecx
 ; CHECK-NEXT:    testw %cx, %cx
 ; CHECK-NEXT:    je LBB0_4
-; CHECK-NEXT:  ## %bb.8: ## %bb13236
+; CHECK-NEXT:  ## %bb.7: ## %bb13236
 ; CHECK-NEXT:    ## in Loop: Header=BB0_4 Depth=1
 ; CHECK-NEXT:    testb %al, %al
 ; CHECK-NEXT:    jne LBB0_4
-; CHECK-NEXT:  ## %bb.9: ## %bb13572
+; CHECK-NEXT:  ## %bb.8: ## %bb13572
 ; CHECK-NEXT:    ## in Loop: Header=BB0_4 Depth=1
 ; CHECK-NEXT:    movzwl %cx, %ecx
 ; CHECK-NEXT:    movl %ecx, %edx
@@ -58,7 +55,7 @@ define void @t(ptr %depth, ptr %bop, i32 %mode) nounwind  {
 ; CHECK-NEXT:    shrl $16, %edx
 ; CHECK-NEXT:    movw %dx, 0
 ; CHECK-NEXT:    jmp LBB0_4
-; CHECK-NEXT:  LBB0_10: ## %return
+; CHECK-NEXT:  LBB0_9: ## %return
 ; CHECK-NEXT:    retq
 entry:
 	switch i32 %mode, label %return [

llvm/test/CodeGen/X86/2012-01-10-UndefExceptionEdge.ll

@@ -33,11 +33,10 @@ define void @f(ptr nocapture %arg, ptr nocapture %arg1, ptr nocapture %arg2, ptr
 ; CHECK-NEXT:    .cfi_offset %esi, -20
 ; CHECK-NEXT:    .cfi_offset %edi, -16
 ; CHECK-NEXT:    .cfi_offset %ebx, -12
-; CHECK-NEXT:    xorl %eax, %eax
-; CHECK-NEXT:    xorl %edi, %edi
-; CHECK-NEXT:    testb %al, %al
+; CHECK-NEXT:    xorl %ebx, %ebx
+; CHECK-NEXT:    testb %bl, %bl
 ; CHECK-NEXT:  Ltmp0:
-; CHECK-NEXT:    ## implicit-def: $ebx
+; CHECK-NEXT:    ## implicit-def: $edi
 ; CHECK-NEXT:    calll __Znam
 ; CHECK-NEXT:  Ltmp1:
 ; CHECK-NEXT:  ## %bb.1: ## %bb11
@@ -86,16 +85,16 @@ define void @f(ptr nocapture %arg, ptr nocapture %arg1, ptr nocapture %arg2, ptr
 ; CHECK-NEXT:    jne LBB0_17
 ; CHECK-NEXT:  ## %bb.15: ## %bb49.preheader
 ; CHECK-NEXT:    ## in Loop: Header=BB0_13 Depth=2
-; CHECK-NEXT:    xorl %ecx, %ecx
-; CHECK-NEXT:    movl %esi, %edx
-; CHECK-NEXT:    movl %edi, %ebx
+; CHECK-NEXT:    movl %esi, %ecx
+; CHECK-NEXT:    movl %ebx, %edx
+; CHECK-NEXT:    xorl %edi, %edi
 ; CHECK-NEXT:  LBB0_16: ## %bb49
 ; CHECK-NEXT:    ## Parent Loop BB0_8 Depth=1
 ; CHECK-NEXT:    ## Parent Loop BB0_13 Depth=2
 ; CHECK-NEXT:    ## => This Inner Loop Header: Depth=3
-; CHECK-NEXT:    incl %ecx
-; CHECK-NEXT:    addl $4, %edx
-; CHECK-NEXT:    decl %ebx
+; CHECK-NEXT:    incl %edi
+; CHECK-NEXT:    addl $4, %ecx
+; CHECK-NEXT:    decl %edx
 ; CHECK-NEXT:    jne LBB0_16
 ; CHECK-NEXT:  LBB0_17: ## %bb57
 ; CHECK-NEXT:    ## in Loop: Header=BB0_13 Depth=2
@@ -113,7 +112,7 @@ define void @f(ptr nocapture %arg, ptr nocapture %arg1, ptr nocapture %arg2, ptr
 ; CHECK-NEXT:  ## %bb.20: ## %bb61.preheader
 ; CHECK-NEXT:    ## in Loop: Header=BB0_8 Depth=1
 ; CHECK-NEXT:    movl %esi, %eax
-; CHECK-NEXT:    movl %edi, %ecx
+; CHECK-NEXT:    movl %ebx, %ecx
 ; CHECK-NEXT:  LBB0_21: ## %bb61
 ; CHECK-NEXT:    ## Parent Loop BB0_8 Depth=1
 ; CHECK-NEXT:    ## => This Inner Loop Header: Depth=2
@@ -127,23 +126,23 @@ define void @f(ptr nocapture %arg, ptr nocapture %arg1, ptr nocapture %arg2, ptr
 ; CHECK-NEXT:    jmp LBB0_8
 ; CHECK-NEXT:  LBB0_18: ## %bb43
 ; CHECK-NEXT:  Ltmp5:
-; CHECK-NEXT:    movl %esi, %ebx
+; CHECK-NEXT:    movl %esi, %edi
 ; CHECK-NEXT:    calll _OnOverFlow
 ; CHECK-NEXT:  Ltmp6:
 ; CHECK-NEXT:    jmp LBB0_3
 ; CHECK-NEXT:  LBB0_2: ## %bb29
 ; CHECK-NEXT:  Ltmp7:
-; CHECK-NEXT:    movl %esi, %ebx
+; CHECK-NEXT:    movl %esi, %edi
 ; CHECK-NEXT:    calll _OnOverFlow
 ; CHECK-NEXT:  Ltmp8:
 ; CHECK-NEXT:  LBB0_3: ## %bb30
 ; CHECK-NEXT:    ud2
 ; CHECK-NEXT:  LBB0_4: ## %bb20.loopexit
 ; CHECK-NEXT:  Ltmp4:
 ; CHECK-NEXT:  LBB0_9:
-; CHECK-NEXT:    movl %esi, %ebx
+; CHECK-NEXT:    movl %esi, %edi
 ; CHECK-NEXT:  LBB0_6: ## %bb23
-; CHECK-NEXT:    testl %ebx, %ebx
+; CHECK-NEXT:    testl %edi, %edi
 ; CHECK-NEXT:    addl $28, %esp
 ; CHECK-NEXT:    popl %esi
 ; CHECK-NEXT:    popl %edi

llvm/test/CodeGen/X86/cmpxchg-clobber-flags.ll

@@ -137,8 +137,8 @@ define i32 @test_control_flow(ptr %p, i32 %i, i32 %j) nounwind {
 ; 32-ALL-NEXT:    # Parent Loop BB1_2 Depth=1
 ; 32-ALL-NEXT:    # => This Inner Loop Header: Depth=2
 ; 32-ALL-NEXT:    movl %edx, %eax
-; 32-ALL-NEXT:    xorl %edx, %edx
-; 32-ALL-NEXT:    testl %eax, %eax
+; 32-ALL-NEXT:    testl %edx, %edx
+; 32-ALL-NEXT:    movl $0, %edx
 ; 32-ALL-NEXT:    je .LBB1_3
 ; 32-ALL-NEXT:  # %bb.4: # %while.body.i
 ; 32-ALL-NEXT:    # in Loop: Header=BB1_2 Depth=1
@@ -148,33 +148,6 @@ define i32 @test_control_flow(ptr %p, i32 %i, i32 %j) nounwind {
 ; 32-ALL-NEXT:    xorl %eax, %eax
 ; 32-ALL-NEXT:  .LBB1_6: # %cond.end
 ; 32-ALL-NEXT:    retl
-;
-; 64-ALL-LABEL: test_control_flow:
-; 64-ALL:       # %bb.0: # %entry
-; 64-ALL-NEXT:    movl %esi, %eax
-; 64-ALL-NEXT:    cmpl %edx, %esi
-; 64-ALL-NEXT:    jle .LBB1_5
-; 64-ALL-NEXT:    .p2align 4, 0x90
-; 64-ALL-NEXT:  .LBB1_1: # %while.condthread-pre-split.i
-; 64-ALL-NEXT:    # =>This Loop Header: Depth=1
-; 64-ALL-NEXT:    # Child Loop BB1_2 Depth 2
-; 64-ALL-NEXT:    movl (%rdi), %ecx
-; 64-ALL-NEXT:    .p2align 4, 0x90
-; 64-ALL-NEXT:  .LBB1_2: # %while.cond.i
-; 64-ALL-NEXT:    # Parent Loop BB1_1 Depth=1
-; 64-ALL-NEXT:    # => This Inner Loop Header: Depth=2
-; 64-ALL-NEXT:    movl %ecx, %eax
-; 64-ALL-NEXT:    xorl %ecx, %ecx
-; 64-ALL-NEXT:    testl %eax, %eax
-; 64-ALL-NEXT:    je .LBB1_2
-; 64-ALL-NEXT:  # %bb.3: # %while.body.i
-; 64-ALL-NEXT:    # in Loop: Header=BB1_1 Depth=1
-; 64-ALL-NEXT:    lock cmpxchgl %eax, (%rdi)
-; 64-ALL-NEXT:    jne .LBB1_1
-; 64-ALL-NEXT:  # %bb.4:
-; 64-ALL-NEXT:    xorl %eax, %eax
-; 64-ALL-NEXT:  .LBB1_5: # %cond.end
-; 64-ALL-NEXT:    retq
 entry:
   %cmp = icmp sgt i32 %i, %j
   br i1 %cmp, label %loop_start, label %cond.end

llvm/test/CodeGen/X86/conditional-tailcall.ll

@@ -456,70 +456,74 @@ define zeroext i1 @pr31257(ptr nocapture readonly dereferenceable(8) %s) minsize
 ; WIN64-NEXT:  .LBB3_1: # %for.cond
 ; WIN64-NEXT:    # =>This Inner Loop Header: Depth=1
 ; WIN64-NEXT:    testq %rax, %rax # encoding: [0x48,0x85,0xc0]
-; WIN64-NEXT:    je .LBB3_11 # encoding: [0x74,A]
-; WIN64-NEXT:    # fixup A - offset: 1, value: .LBB3_11-1, kind: FK_PCRel_1
+; WIN64-NEXT:    je .LBB3_12 # encoding: [0x74,A]
+; WIN64-NEXT:    # fixup A - offset: 1, value: .LBB3_12-1, kind: FK_PCRel_1
 ; WIN64-NEXT:  # %bb.2: # %for.body
 ; WIN64-NEXT:    # in Loop: Header=BB3_1 Depth=1
 ; WIN64-NEXT:    cmpl $2, %r8d # encoding: [0x41,0x83,0xf8,0x02]
-; WIN64-NEXT:    je .LBB3_9 # encoding: [0x74,A]
-; WIN64-NEXT:    # fixup A - offset: 1, value: .LBB3_9-1, kind: FK_PCRel_1
+; WIN64-NEXT:    je .LBB3_10 # encoding: [0x74,A]
+; WIN64-NEXT:    # fixup A - offset: 1, value: .LBB3_10-1, kind: FK_PCRel_1
 ; WIN64-NEXT:  # %bb.3: # %for.body
 ; WIN64-NEXT:    # in Loop: Header=BB3_1 Depth=1
 ; WIN64-NEXT:    cmpl $1, %r8d # encoding: [0x41,0x83,0xf8,0x01]
-; WIN64-NEXT:    je .LBB3_7 # encoding: [0x74,A]
-; WIN64-NEXT:    # fixup A - offset: 1, value: .LBB3_7-1, kind: FK_PCRel_1
+; WIN64-NEXT:    je .LBB3_8 # encoding: [0x74,A]
+; WIN64-NEXT:    # fixup A - offset: 1, value: .LBB3_8-1, kind: FK_PCRel_1
 ; WIN64-NEXT:  # %bb.4: # %for.body
 ; WIN64-NEXT:    # in Loop: Header=BB3_1 Depth=1
 ; WIN64-NEXT:    testl %r8d, %r8d # encoding: [0x45,0x85,0xc0]
-; WIN64-NEXT:    jne .LBB3_10 # encoding: [0x75,A]
-; WIN64-NEXT:    # fixup A - offset: 1, value: .LBB3_10-1, kind: FK_PCRel_1
+; WIN64-NEXT:    jne .LBB3_11 # encoding: [0x75,A]
+; WIN64-NEXT:    # fixup A - offset: 1, value: .LBB3_11-1, kind: FK_PCRel_1
 ; WIN64-NEXT:  # %bb.5: # %sw.bb
 ; WIN64-NEXT:    # in Loop: Header=BB3_1 Depth=1
 ; WIN64-NEXT:    movzbl (%rcx), %r9d # encoding: [0x44,0x0f,0xb6,0x09]
 ; WIN64-NEXT:    cmpl $43, %r9d # encoding: [0x41,0x83,0xf9,0x2b]
 ; WIN64-NEXT:    movl $1, %r8d # encoding: [0x41,0xb8,0x01,0x00,0x00,0x00]
-; WIN64-NEXT:    je .LBB3_10 # encoding: [0x74,A]
-; WIN64-NEXT:    # fixup A - offset: 1, value: .LBB3_10-1, kind: FK_PCRel_1
+; WIN64-NEXT:    je .LBB3_11 # encoding: [0x74,A]
+; WIN64-NEXT:    # fixup A - offset: 1, value: .LBB3_11-1, kind: FK_PCRel_1
 ; WIN64-NEXT:  # %bb.6: # %sw.bb
 ; WIN64-NEXT:    # in Loop: Header=BB3_1 Depth=1
 ; WIN64-NEXT:    cmpl $45, %r9d # encoding: [0x41,0x83,0xf9,0x2d]
-; WIN64-NEXT:    je .LBB3_10 # encoding: [0x74,A]
-; WIN64-NEXT:    # fixup A - offset: 1, value: .LBB3_10-1, kind: FK_PCRel_1
-; WIN64-NEXT:    jmp .LBB3_8 # encoding: [0xeb,A]
-; WIN64-NEXT:    # fixup A - offset: 1, value: .LBB3_8-1, kind: FK_PCRel_1
-; WIN64-NEXT:  .LBB3_7: # %sw.bb14
-; WIN64-NEXT:    # in Loop: Header=BB3_1 Depth=1
-; WIN64-NEXT:    movzbl (%rcx), %r9d # encoding: [0x44,0x0f,0xb6,0x09]
-; WIN64-NEXT:  .LBB3_8: # %if.else
+; WIN64-NEXT:    je .LBB3_11 # encoding: [0x74,A]
+; WIN64-NEXT:    # fixup A - offset: 1, value: .LBB3_11-1, kind: FK_PCRel_1
+; WIN64-NEXT:  # %bb.7: # %if.else
 ; WIN64-NEXT:    # in Loop: Header=BB3_1 Depth=1
 ; WIN64-NEXT:    addl $-48, %r9d # encoding: [0x41,0x83,0xc1,0xd0]
-; WIN64-NEXT:    movl $2, %r8d # encoding: [0x41,0xb8,0x02,0x00,0x00,0x00]
 ; WIN64-NEXT:    cmpl $10, %r9d # encoding: [0x41,0x83,0xf9,0x0a]
-; WIN64-NEXT:    jb .LBB3_10 # encoding: [0x72,A]
-; WIN64-NEXT:    # fixup A - offset: 1, value: .LBB3_10-1, kind: FK_PCRel_1
-; WIN64-NEXT:    jmp .LBB3_12 # encoding: [0xeb,A]
-; WIN64-NEXT:    # fixup A - offset: 1, value: .LBB3_12-1, kind: FK_PCRel_1
-; WIN64-NEXT:  .LBB3_9: # %sw.bb22
+; WIN64-NEXT:    jmp .LBB3_9 # encoding: [0xeb,A]
+; WIN64-NEXT:    # fixup A - offset: 1, value: .LBB3_9-1, kind: FK_PCRel_1
+; WIN64-NEXT:  .LBB3_8: # %sw.bb14
+; WIN64-NEXT:    # in Loop: Header=BB3_1 Depth=1
+; WIN64-NEXT:    movzbl (%rcx), %r8d # encoding: [0x44,0x0f,0xb6,0x01]
+; WIN64-NEXT:    addl $-48, %r8d # encoding: [0x41,0x83,0xc0,0xd0]
+; WIN64-NEXT:    cmpl $10, %r8d # encoding: [0x41,0x83,0xf8,0x0a]
+; WIN64-NEXT:  .LBB3_9: # %if.else
 ; WIN64-NEXT:    # in Loop: Header=BB3_1 Depth=1
-; WIN64-NEXT:    movzbl (%rcx), %r9d # encoding: [0x44,0x0f,0xb6,0x09]
-; WIN64-NEXT:    addl $-48, %r9d # encoding: [0x41,0x83,0xc1,0xd0]
 ; WIN64-NEXT:    movl $2, %r8d # encoding: [0x41,0xb8,0x02,0x00,0x00,0x00]
-; WIN64-NEXT:    cmpl $10, %r9d # encoding: [0x41,0x83,0xf9,0x0a]
+; WIN64-NEXT:    jb .LBB3_11 # encoding: [0x72,A]
+; WIN64-NEXT:    # fixup A - offset: 1, value: .LBB3_11-1, kind: FK_PCRel_1
+; WIN64-NEXT:    jmp .LBB3_13 # encoding: [0xeb,A]
+; WIN64-NEXT:    # fixup A - offset: 1, value: .LBB3_13-1, kind: FK_PCRel_1
+; WIN64-NEXT:  .LBB3_10: # %sw.bb22
+; WIN64-NEXT:    # in Loop: Header=BB3_1 Depth=1
+; WIN64-NEXT:    movzbl (%rcx), %r8d # encoding: [0x44,0x0f,0xb6,0x01]
+; WIN64-NEXT:    addl $-48, %r8d # encoding: [0x41,0x83,0xc0,0xd0]
+; WIN64-NEXT:    cmpl $10, %r8d # encoding: [0x41,0x83,0xf8,0x0a]
+; WIN64-NEXT:    movl $2, %r8d # encoding: [0x41,0xb8,0x02,0x00,0x00,0x00]
 ; WIN64-NEXT:    jae _Z20isValidIntegerSuffixN9__gnu_cxx17__normal_iteratorIPKcSsEES3_ # TAILCALL
 ; WIN64-NEXT:    # encoding: [0x73,A]
 ; WIN64-NEXT:    # fixup A - offset: 1, value: _Z20isValidIntegerSuffixN9__gnu_cxx17__normal_iteratorIPKcSsEES3_-1, kind: FK_PCRel_1
-; WIN64-NEXT:  .LBB3_10: # %for.inc
+; WIN64-NEXT:  .LBB3_11: # %for.inc
 ; WIN64-NEXT:    # in Loop: Header=BB3_1 Depth=1
 ; WIN64-NEXT:    incq %rcx # encoding: [0x48,0xff,0xc1]
 ; WIN64-NEXT:    decq %rax # encoding: [0x48,0xff,0xc8]
 ; WIN64-NEXT:    jmp .LBB3_1 # encoding: [0xeb,A]
 ; WIN64-NEXT:    # fixup A - offset: 1, value: .LBB3_1-1, kind: FK_PCRel_1
-; WIN64-NEXT:  .LBB3_11:
+; WIN64-NEXT:  .LBB3_12:
 ; WIN64-NEXT:    cmpl $2, %r8d # encoding: [0x41,0x83,0xf8,0x02]
 ; WIN64-NEXT:    sete %al # encoding: [0x0f,0x94,0xc0]
 ; WIN64-NEXT:    # kill: def $al killed $al killed $eax
 ; WIN64-NEXT:    retq # encoding: [0xc3]
-; WIN64-NEXT:  .LBB3_12:
+; WIN64-NEXT:  .LBB3_13:
 ; WIN64-NEXT:    xorl %eax, %eax # encoding: [0x31,0xc0]
 ; WIN64-NEXT:    # kill: def $al killed $al killed $eax
 ; WIN64-NEXT:    retq # encoding: [0xc3]

llvm/test/CodeGen/X86/licm-nested.ll

@@ -1,5 +1,5 @@
 ; REQUIRES: asserts
-; RUN: llc -mtriple=x86_64-apple-darwin < %s -o /dev/null -stats -info-output-file - | grep "hoisted out of loops" | grep 3
+; RUN: llc -mtriple=x86_64-apple-darwin < %s -o /dev/null -stats -info-output-file - | grep "hoisted out of loops" | grep 7
 
 ; MachineLICM should be able to hoist the symbolic addresses out of
 ; the inner loops.

llvm/test/CodeGen/X86/loop-strength-reduce7.ll

@@ -17,15 +17,15 @@ define fastcc void @outer_loop(ptr nocapture %gfp, ptr nocapture %xr, i32 %targ_
 ; CHECK-NEXT:  LBB0_2: ## %bb28.i37
 ; CHECK-NEXT:    ## =>This Loop Header: Depth=1
 ; CHECK-NEXT:    ## Child Loop BB0_3 Depth 2
-; CHECK-NEXT:    xorl %edx, %edx
-; CHECK-NEXT:    movl %eax, %esi
+; CHECK-NEXT:    movl %eax, %edx
+; CHECK-NEXT:    xorl %esi, %esi
 ; CHECK-NEXT:    .p2align 4, 0x90
 ; CHECK-NEXT:  LBB0_3: ## %bb29.i38
 ; CHECK-NEXT:    ## Parent Loop BB0_2 Depth=1
 ; CHECK-NEXT:    ## => This Inner Loop Header: Depth=2
-; CHECK-NEXT:    incl %edx
-; CHECK-NEXT:    addl $12, %esi
-; CHECK-NEXT:    cmpl $11, %edx
+; CHECK-NEXT:    incl %esi
+; CHECK-NEXT:    addl $12, %edx
+; CHECK-NEXT:    cmpl $11, %esi
 ; CHECK-NEXT:    jbe LBB0_3
 ; CHECK-NEXT:  ## %bb.1: ## %bb28.i37.loopexit
 ; CHECK-NEXT:    ## in Loop: Header=BB0_2 Depth=1