llvm/test/CodeGen/X86/icmp-shift-opt.ll

; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -mtriple=i686-- < %s | FileCheck %s --check-prefix=X86
; RUN: llc -mtriple=x86_64-- < %s | FileCheck %s --check-prefix=X64

; Optimize expanded SRL/SHL used as an input of
; SETCC comparing it with zero by removing rotation.
;
; See https://bugs.llvm.org/show_bug.cgi?id=50197
define i128 @opt_setcc_lt_power_of_2(i128 %a) nounwind {
; X86-LABEL: opt_setcc_lt_power_of_2:
; X86:       # %bb.0:
; X86-NEXT:    pushl %ebp
; X86-NEXT:    pushl %ebx
; X86-NEXT:    pushl %edi
; X86-NEXT:    pushl %esi
; X86-NEXT:    movl {{[0-9]+}}(%esp), %ebx
; X86-NEXT:    movl {{[0-9]+}}(%esp), %edx
; X86-NEXT:    movl {{[0-9]+}}(%esp), %esi
; X86-NEXT:    movl {{[0-9]+}}(%esp), %ecx
; X86-NEXT:    .p2align 4, 0x90
; X86-NEXT:  .LBB0_1: # %loop
; X86-NEXT:    # =>This Inner Loop Header: Depth=1
; X86-NEXT:    addl $1, %ecx
; X86-NEXT:    adcl $0, %esi
; X86-NEXT:    adcl $0, %edx
; X86-NEXT:    adcl $0, %ebx
; X86-NEXT:    movl %ebx, %edi
; X86-NEXT:    shldl $4, %edx, %edi
; X86-NEXT:    movl %edx, %ebp
; X86-NEXT:    shldl $4, %esi, %ebp
; X86-NEXT:    movl %ecx, %eax
; X86-NEXT:    movl %ebx, %ecx
; X86-NEXT:    shrl $28, %ecx
; X86-NEXT:    orl %ebp, %ecx
; X86-NEXT:    orl %edi, %ecx
; X86-NEXT:    movl %eax, %ecx
; X86-NEXT:    jne .LBB0_1
; X86-NEXT:  # %bb.2: # %exit
; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax
; X86-NEXT:    movl %ecx, (%eax)
; X86-NEXT:    movl %esi, 4(%eax)
; X86-NEXT:    movl %edx, 8(%eax)
; X86-NEXT:    movl %ebx, 12(%eax)
; X86-NEXT:    popl %esi
; X86-NEXT:    popl %edi
; X86-NEXT:    popl %ebx
; X86-NEXT:    popl %ebp
; X86-NEXT:    retl $4
;
; X64-LABEL: opt_setcc_lt_power_of_2:
; X64:       # %bb.0:
; X64-NEXT:    movq %rsi, %rdx
; X64-NEXT:    movq %rdi, %rax
; X64-NEXT:    .p2align 4, 0x90
; X64-NEXT:  .LBB0_1: # %loop
; X64-NEXT:    # =>This Inner Loop Header: Depth=1
; X64-NEXT:    addq $1, %rax
; X64-NEXT:    adcq $0, %rdx
; X64-NEXT:    movq %rdx, %rcx
; X64-NEXT:    shldq $4, %rax, %rcx
; X64-NEXT:    movq %rdx, %rsi
; X64-NEXT:    shrq $60, %rsi
; X64-NEXT:    orq %rcx, %rsi
; X64-NEXT:    jne .LBB0_1
; X64-NEXT:  # %bb.2: # %exit
; X64-NEXT:    retq
  br label %loop

loop:
  %phi.a = phi i128 [ %a, %0 ], [ %inc, %loop ]
  %inc = add i128 %phi.a, 1
  %cmp = icmp ult i128 %inc, 1152921504606846976
  br i1 %cmp, label %exit, label %loop

exit:
  ret i128 %inc
}

define i1 @opt_setcc_srl_eq_zero(i128 %a) nounwind {
; X86-LABEL: opt_setcc_srl_eq_zero:
; X86:       # %bb.0:
; X86-NEXT:    pushl %edi
; X86-NEXT:    pushl %esi
; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax
; X86-NEXT:    movl {{[0-9]+}}(%esp), %ecx
; X86-NEXT:    movl {{[0-9]+}}(%esp), %edx
; X86-NEXT:    movl {{[0-9]+}}(%esp), %esi
; X86-NEXT:    movl %esi, %edi
; X86-NEXT:    shldl $15, %edx, %edi
; X86-NEXT:    shldl $15, %ecx, %edx
; X86-NEXT:    shrdl $17, %ecx, %eax
; X86-NEXT:    orl %edi, %eax
; X86-NEXT:    shrl $17, %esi
; X86-NEXT:    orl %edx, %esi
; X86-NEXT:    orl %eax, %esi
; X86-NEXT:    sete %al
; X86-NEXT:    popl %esi
; X86-NEXT:    popl %edi
; X86-NEXT:    retl
;
; X64-LABEL: opt_setcc_srl_eq_zero:
; X64:       # %bb.0:
; X64-NEXT:    shrdq $17, %rsi, %rdi
; X64-NEXT:    shrq $17, %rsi
; X64-NEXT:    orq %rdi, %rsi
; X64-NEXT:    sete %al
; X64-NEXT:    retq
   %srl = lshr i128 %a, 17
   %cmp = icmp eq i128 %srl, 0
   ret i1 %cmp
}

define i1 @opt_setcc_srl_ne_zero(i128 %a) nounwind {
; X86-LABEL: opt_setcc_srl_ne_zero:
; X86:       # %bb.0:
; X86-NEXT:    pushl %edi
; X86-NEXT:    pushl %esi
; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax
; X86-NEXT:    movl {{[0-9]+}}(%esp), %ecx
; X86-NEXT:    movl {{[0-9]+}}(%esp), %edx
; X86-NEXT:    movl {{[0-9]+}}(%esp), %esi
; X86-NEXT:    movl %esi, %edi
; X86-NEXT:    shldl $15, %edx, %edi
; X86-NEXT:    shldl $15, %ecx, %edx
; X86-NEXT:    shrdl $17, %ecx, %eax
; X86-NEXT:    orl %edi, %eax
; X86-NEXT:    shrl $17, %esi
; X86-NEXT:    orl %edx, %esi
; X86-NEXT:    orl %eax, %esi
; X86-NEXT:    setne %al
; X86-NEXT:    popl %esi
; X86-NEXT:    popl %edi
; X86-NEXT:    retl
;
; X64-LABEL: opt_setcc_srl_ne_zero:
; X64:       # %bb.0:
; X64-NEXT:    shrdq $17, %rsi, %rdi
; X64-NEXT:    shrq $17, %rsi
; X64-NEXT:    orq %rdi, %rsi
; X64-NEXT:    setne %al
; X64-NEXT:    retq
   %srl = lshr i128 %a, 17
   %cmp = icmp ne i128 %srl, 0
   ret i1 %cmp
}

define i1 @opt_setcc_shl_eq_zero(i128 %a) nounwind {
; X86-LABEL: opt_setcc_shl_eq_zero:
; X86:       # %bb.0:
; X86-NEXT:    pushl %esi
; X86-NEXT:    movl {{[0-9]+}}(%esp), %edx
; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax
; X86-NEXT:    movl {{[0-9]+}}(%esp), %ecx
; X86-NEXT:    movl {{[0-9]+}}(%esp), %esi
; X86-NEXT:    shldl $17, %esi, %edx
; X86-NEXT:    shldl $17, %ecx, %esi
; X86-NEXT:    shldl $17, %eax, %ecx
; X86-NEXT:    shll $17, %eax
; X86-NEXT:    orl %esi, %eax
; X86-NEXT:    orl %edx, %ecx
; X86-NEXT:    orl %eax, %ecx
; X86-NEXT:    sete %al
; X86-NEXT:    popl %esi
; X86-NEXT:    retl
;
; X64-LABEL: opt_setcc_shl_eq_zero:
; X64:       # %bb.0:
; X64-NEXT:    shldq $17, %rdi, %rsi
; X64-NEXT:    shlq $17, %rdi
; X64-NEXT:    orq %rsi, %rdi
; X64-NEXT:    sete %al
; X64-NEXT:    retq
   %shl = shl i128 %a, 17
   %cmp = icmp eq i128 %shl, 0
   ret i1 %cmp
}

define i1 @opt_setcc_shl_ne_zero(i128 %a) nounwind {
; X86-LABEL: opt_setcc_shl_ne_zero:
; X86:       # %bb.0:
; X86-NEXT:    pushl %esi
; X86-NEXT:    movl {{[0-9]+}}(%esp), %edx
; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax
; X86-NEXT:    movl {{[0-9]+}}(%esp), %ecx
; X86-NEXT:    movl {{[0-9]+}}(%esp), %esi
; X86-NEXT:    shldl $17, %esi, %edx
; X86-NEXT:    shldl $17, %ecx, %esi
; X86-NEXT:    shldl $17, %eax, %ecx
; X86-NEXT:    shll $17, %eax
; X86-NEXT:    orl %esi, %eax
; X86-NEXT:    orl %edx, %ecx
; X86-NEXT:    orl %eax, %ecx
; X86-NEXT:    setne %al
; X86-NEXT:    popl %esi
; X86-NEXT:    retl
;
; X64-LABEL: opt_setcc_shl_ne_zero:
; X64:       # %bb.0:
; X64-NEXT:    shldq $17, %rdi, %rsi
; X64-NEXT:    shlq $17, %rdi
; X64-NEXT:    orq %rsi, %rdi
; X64-NEXT:    setne %al
; X64-NEXT:    retq
   %shl = shl i128 %a, 17
   %cmp = icmp ne i128 %shl, 0
   ret i1 %cmp
}

; Negative test: optimization should not be applied if shift has multiple users.
define i1 @opt_setcc_shl_eq_zero_multiple_shl_users(i128 %a) nounwind {
; X86-LABEL: opt_setcc_shl_eq_zero_multiple_shl_users:
; X86:       # %bb.0:
; X86-NEXT:    pushl %ebx
; X86-NEXT:    pushl %edi
; X86-NEXT:    pushl %esi
; X86-NEXT:    movl {{[0-9]+}}(%esp), %edx
; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax
; X86-NEXT:    movl {{[0-9]+}}(%esp), %ecx
; X86-NEXT:    movl {{[0-9]+}}(%esp), %esi
; X86-NEXT:    shldl $17, %esi, %edx
; X86-NEXT:    shldl $17, %ecx, %esi
; X86-NEXT:    shldl $17, %eax, %ecx
; X86-NEXT:    shll $17, %eax
; X86-NEXT:    movl %ecx, %edi
; X86-NEXT:    orl %edx, %edi
; X86-NEXT:    movl %eax, %ebx
; X86-NEXT:    orl %esi, %ebx
; X86-NEXT:    orl %edi, %ebx
; X86-NEXT:    sete %bl
; X86-NEXT:    pushl %edx
; X86-NEXT:    pushl %esi
; X86-NEXT:    pushl %ecx
; X86-NEXT:    pushl %eax
; X86-NEXT:    calll use@PLT
; X86-NEXT:    addl $16, %esp
; X86-NEXT:    movl %ebx, %eax
; X86-NEXT:    popl %esi
; X86-NEXT:    popl %edi
; X86-NEXT:    popl %ebx
; X86-NEXT:    retl
;
; X64-LABEL: opt_setcc_shl_eq_zero_multiple_shl_users:
; X64:       # %bb.0:
; X64-NEXT:    pushq %rbx
; X64-NEXT:    shldq $17, %rdi, %rsi
; X64-NEXT:    shlq $17, %rdi
; X64-NEXT:    movq %rdi, %rax
; X64-NEXT:    orq %rsi, %rax
; X64-NEXT:    sete %bl
; X64-NEXT:    callq use@PLT
; X64-NEXT:    movl %ebx, %eax
; X64-NEXT:    popq %rbx
; X64-NEXT:    retq
   %shl = shl i128 %a, 17
   %cmp = icmp eq i128 %shl, 0
   call void @use(i128 %shl)
   ret i1 %cmp
}

; Check that optimization is applied to DAG having appropriate shape
; even if there were no actual shift's expansion.
define i1 @opt_setcc_expanded_shl_correct_shifts(i64 %a, i64 %b) nounwind {
; X86-LABEL: opt_setcc_expanded_shl_correct_shifts:
; X86:       # %bb.0:
; X86-NEXT:    pushl %esi
; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax
; X86-NEXT:    movl {{[0-9]+}}(%esp), %ecx
; X86-NEXT:    movl {{[0-9]+}}(%esp), %edx
; X86-NEXT:    movl {{[0-9]+}}(%esp), %esi
; X86-NEXT:    shldl $17, %edx, %esi
; X86-NEXT:    shldl $17, %ecx, %edx
; X86-NEXT:    shldl $17, %eax, %ecx
; X86-NEXT:    shll $17, %eax
; X86-NEXT:    orl %edx, %eax
; X86-NEXT:    orl %esi, %ecx
; X86-NEXT:    orl %eax, %ecx
; X86-NEXT:    sete %al
; X86-NEXT:    popl %esi
; X86-NEXT:    retl
;
; X64-LABEL: opt_setcc_expanded_shl_correct_shifts:
; X64:       # %bb.0:
; X64-NEXT:    shldq $17, %rsi, %rdi
; X64-NEXT:    shlq $17, %rsi
; X64-NEXT:    orq %rdi, %rsi
; X64-NEXT:    sete %al
; X64-NEXT:    retq
  %shl.a = shl i64 %a, 17
  %srl.b = lshr i64 %b, 47
  %or.0 = or i64 %shl.a, %srl.b
  %shl.b = shl i64 %b, 17
  %or.1 = or i64 %or.0, %shl.b
  %cmp = icmp eq i64 %or.1, 0
  ret i1 %cmp
}

; Negative test: optimization should not be applied as
; constants used in shifts do not match.
define i1 @opt_setcc_expanded_shl_wrong_shifts(i64 %a, i64 %b) nounwind {
; X86-LABEL: opt_setcc_expanded_shl_wrong_shifts:
; X86:       # %bb.0:
; X86-NEXT:    pushl %esi
; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax
; X86-NEXT:    movl {{[0-9]+}}(%esp), %ecx
; X86-NEXT:    movl {{[0-9]+}}(%esp), %edx
; X86-NEXT:    movl {{[0-9]+}}(%esp), %esi
; X86-NEXT:    shldl $17, %edx, %esi
; X86-NEXT:    shldl $17, %ecx, %edx
; X86-NEXT:    shldl $18, %eax, %ecx
; X86-NEXT:    shll $18, %eax
; X86-NEXT:    orl %edx, %eax
; X86-NEXT:    orl %esi, %ecx
; X86-NEXT:    orl %eax, %ecx
; X86-NEXT:    sete %al
; X86-NEXT:    popl %esi
; X86-NEXT:    retl
;
; X64-LABEL: opt_setcc_expanded_shl_wrong_shifts:
; X64:       # %bb.0:
; X64-NEXT:    shldq $17, %rsi, %rdi
; X64-NEXT:    shlq $18, %rsi
; X64-NEXT:    orq %rdi, %rsi
; X64-NEXT:    sete %al
; X64-NEXT:    retq
  %shl.a = shl i64 %a, 17
  %srl.b = lshr i64 %b, 47
  %or.0 = or i64 %shl.a, %srl.b
  %shl.b = shl i64 %b, 18
  %or.1 = or i64 %or.0, %shl.b
  %cmp = icmp eq i64 %or.1, 0
  ret i1 %cmp
}

declare void @use(i128 %a)