llvm/test/CodeGen/X86/atomic-idempotent-syncscope.ll

; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=x86_64-- -verify-machineinstrs                           | FileCheck %s --check-prefix=X64
; RUN: llc < %s -mtriple=i686-- -verify-machineinstrs           -mattr=+sse2      | FileCheck %s --check-prefixes=X86,X86-GENERIC,X86-SSE2
; RUN: llc < %s -mtriple=i686-- -verify-machineinstrs -mcpu=slm -mattr=-sse2      | FileCheck %s --check-prefixes=X86,X86-GENERIC,X86-SLM
; RUN: llc < %s -mtriple=i686-- -verify-machineinstrs -mcpu=goldmont -mattr=-sse2 | FileCheck %s --check-prefixes=X86,X86-GENERIC,X86-SLM
; RUN: llc < %s -mtriple=i686-- -verify-machineinstrs -mcpu=knl -mattr=-sse2      | FileCheck %s --check-prefixes=X86,X86-GENERIC,X86-SLM
; RUN: llc < %s -mtriple=i686-- -verify-machineinstrs -mcpu=atom -mattr=-sse2     | FileCheck %s --check-prefixes=X86,X86-ATOM

; On x86, an atomic rmw operation that does not modify the value in memory
; (such as atomic add 0) can be replaced by an mfence followed by a mov.
; This is explained (with the motivation for such an optimization) in
; http://www.hpl.hp.com/techreports/2012/HPL-2012-68.pdf

define i8 @add8(ptr %p) #0 {
; X64-LABEL: add8:
; X64:       # %bb.0:
; X64-NEXT:    #MEMBARRIER
; X64-NEXT:    movzbl (%rdi), %eax
; X64-NEXT:    retq
;
; X86-GENERIC-LABEL: add8:
; X86-GENERIC:       # %bb.0:
; X86-GENERIC-NEXT:    movl {{[0-9]+}}(%esp), %eax
; X86-GENERIC-NEXT:    #MEMBARRIER
; X86-GENERIC-NEXT:    movzbl (%eax), %eax
; X86-GENERIC-NEXT:    retl
;
; X86-ATOM-LABEL: add8:
; X86-ATOM:       # %bb.0:
; X86-ATOM-NEXT:    movl {{[0-9]+}}(%esp), %eax
; X86-ATOM-NEXT:    #MEMBARRIER
; X86-ATOM-NEXT:    movzbl (%eax), %eax
; X86-ATOM-NEXT:    nop
; X86-ATOM-NEXT:    nop
; X86-ATOM-NEXT:    nop
; X86-ATOM-NEXT:    nop
; X86-ATOM-NEXT:    retl
  %1 = atomicrmw add ptr %p, i8 0 syncscope("singlethread") monotonic
  ret i8 %1
}

define i16 @or16(ptr %p) #0 {
; X64-LABEL: or16:
; X64:       # %bb.0:
; X64-NEXT:    #MEMBARRIER
; X64-NEXT:    movzwl (%rdi), %eax
; X64-NEXT:    retq
;
; X86-GENERIC-LABEL: or16:
; X86-GENERIC:       # %bb.0:
; X86-GENERIC-NEXT:    movl {{[0-9]+}}(%esp), %eax
; X86-GENERIC-NEXT:    #MEMBARRIER
; X86-GENERIC-NEXT:    movzwl (%eax), %eax
; X86-GENERIC-NEXT:    retl
;
; X86-ATOM-LABEL: or16:
; X86-ATOM:       # %bb.0:
; X86-ATOM-NEXT:    movl {{[0-9]+}}(%esp), %eax
; X86-ATOM-NEXT:    #MEMBARRIER
; X86-ATOM-NEXT:    movzwl (%eax), %eax
; X86-ATOM-NEXT:    nop
; X86-ATOM-NEXT:    nop
; X86-ATOM-NEXT:    nop
; X86-ATOM-NEXT:    nop
; X86-ATOM-NEXT:    retl
  %1 = atomicrmw or ptr %p, i16 0 syncscope("singlethread") acquire
  ret i16 %1
}

define i32 @xor32(ptr %p) #0 {
; X64-LABEL: xor32:
; X64:       # %bb.0:
; X64-NEXT:    #MEMBARRIER
; X64-NEXT:    movl (%rdi), %eax
; X64-NEXT:    retq
;
; X86-GENERIC-LABEL: xor32:
; X86-GENERIC:       # %bb.0:
; X86-GENERIC-NEXT:    movl {{[0-9]+}}(%esp), %eax
; X86-GENERIC-NEXT:    #MEMBARRIER
; X86-GENERIC-NEXT:    movl (%eax), %eax
; X86-GENERIC-NEXT:    retl
;
; X86-ATOM-LABEL: xor32:
; X86-ATOM:       # %bb.0:
; X86-ATOM-NEXT:    movl {{[0-9]+}}(%esp), %eax
; X86-ATOM-NEXT:    #MEMBARRIER
; X86-ATOM-NEXT:    movl (%eax), %eax
; X86-ATOM-NEXT:    nop
; X86-ATOM-NEXT:    nop
; X86-ATOM-NEXT:    nop
; X86-ATOM-NEXT:    nop
; X86-ATOM-NEXT:    retl
  %1 = atomicrmw xor ptr %p, i32 0 syncscope("singlethread") release
  ret i32 %1
}

define i64 @sub64(ptr %p) #0 {
; X64-LABEL: sub64:
; X64:       # %bb.0:
; X64-NEXT:    #MEMBARRIER
; X64-NEXT:    movq (%rdi), %rax
; X64-NEXT:    retq
;
; X86-LABEL: sub64:
; X86:       # %bb.0:
; X86-NEXT:    pushl %ebx
; X86-NEXT:    pushl %esi
; X86-NEXT:    movl {{[0-9]+}}(%esp), %esi
; X86-NEXT:    movl (%esi), %eax
; X86-NEXT:    movl 4(%esi), %edx
; X86-NEXT:    .p2align 4
; X86-NEXT:  .LBB3_1: # %atomicrmw.start
; X86-NEXT:    # =>This Inner Loop Header: Depth=1
; X86-NEXT:    movl %edx, %ecx
; X86-NEXT:    movl %eax, %ebx
; X86-NEXT:    lock cmpxchg8b (%esi)
; X86-NEXT:    jne .LBB3_1
; X86-NEXT:  # %bb.2: # %atomicrmw.end
; X86-NEXT:    popl %esi
; X86-NEXT:    popl %ebx
; X86-NEXT:    retl
  %1 = atomicrmw sub ptr %p, i64 0 syncscope("singlethread") seq_cst
  ret i64 %1
}

define i128 @or128(ptr %p) #0 {
; X64-LABEL: or128:
; X64:       # %bb.0:
; X64-NEXT:    pushq %rax
; X64-NEXT:    xorl %esi, %esi
; X64-NEXT:    xorl %edx, %edx
; X64-NEXT:    xorl %ecx, %ecx
; X64-NEXT:    callq __atomic_fetch_or_16@PLT
; X64-NEXT:    popq %rcx
; X64-NEXT:    retq
;
; X86-GENERIC-LABEL: or128:
; X86-GENERIC:       # %bb.0:
; X86-GENERIC-NEXT:    pushl %ebp
; X86-GENERIC-NEXT:    movl %esp, %ebp
; X86-GENERIC-NEXT:    pushl %ebx
; X86-GENERIC-NEXT:    pushl %edi
; X86-GENERIC-NEXT:    pushl %esi
; X86-GENERIC-NEXT:    andl $-16, %esp
; X86-GENERIC-NEXT:    subl $32, %esp
; X86-GENERIC-NEXT:    movl 12(%ebp), %edi
; X86-GENERIC-NEXT:    movl 12(%edi), %ecx
; X86-GENERIC-NEXT:    movl 8(%edi), %edx
; X86-GENERIC-NEXT:    movl (%edi), %ebx
; X86-GENERIC-NEXT:    movl 4(%edi), %esi
; X86-GENERIC-NEXT:    .p2align 4
; X86-GENERIC-NEXT:  .LBB4_1: # %atomicrmw.start
; X86-GENERIC-NEXT:    # =>This Inner Loop Header: Depth=1
; X86-GENERIC-NEXT:    movl %ebx, (%esp)
; X86-GENERIC-NEXT:    movl %esi, {{[0-9]+}}(%esp)
; X86-GENERIC-NEXT:    movl %edx, {{[0-9]+}}(%esp)
; X86-GENERIC-NEXT:    movl %ecx, {{[0-9]+}}(%esp)
; X86-GENERIC-NEXT:    movl %ecx, {{[0-9]+}}(%esp)
; X86-GENERIC-NEXT:    movl %edx, {{[0-9]+}}(%esp)
; X86-GENERIC-NEXT:    movl %esi, {{[0-9]+}}(%esp)
; X86-GENERIC-NEXT:    movl %ebx, {{[0-9]+}}(%esp)
; X86-GENERIC-NEXT:    pushl $0
; X86-GENERIC-NEXT:    pushl $0
; X86-GENERIC-NEXT:    leal {{[0-9]+}}(%esp), %eax
; X86-GENERIC-NEXT:    pushl %eax
; X86-GENERIC-NEXT:    leal {{[0-9]+}}(%esp), %eax
; X86-GENERIC-NEXT:    pushl %eax
; X86-GENERIC-NEXT:    pushl %edi
; X86-GENERIC-NEXT:    pushl $16
; X86-GENERIC-NEXT:    calll __atomic_compare_exchange@PLT
; X86-GENERIC-NEXT:    addl $24, %esp
; X86-GENERIC-NEXT:    movl {{[0-9]+}}(%esp), %ecx
; X86-GENERIC-NEXT:    movl {{[0-9]+}}(%esp), %edx
; X86-GENERIC-NEXT:    movl (%esp), %ebx
; X86-GENERIC-NEXT:    movl {{[0-9]+}}(%esp), %esi
; X86-GENERIC-NEXT:    testb %al, %al
; X86-GENERIC-NEXT:    je .LBB4_1
; X86-GENERIC-NEXT:  # %bb.2: # %atomicrmw.end
; X86-GENERIC-NEXT:    movl 8(%ebp), %eax
; X86-GENERIC-NEXT:    movl %ebx, (%eax)
; X86-GENERIC-NEXT:    movl %esi, 4(%eax)
; X86-GENERIC-NEXT:    movl %edx, 8(%eax)
; X86-GENERIC-NEXT:    movl %ecx, 12(%eax)
; X86-GENERIC-NEXT:    leal -12(%ebp), %esp
; X86-GENERIC-NEXT:    popl %esi
; X86-GENERIC-NEXT:    popl %edi
; X86-GENERIC-NEXT:    popl %ebx
; X86-GENERIC-NEXT:    popl %ebp
; X86-GENERIC-NEXT:    retl $4
;
; X86-ATOM-LABEL: or128:
; X86-ATOM:       # %bb.0:
; X86-ATOM-NEXT:    pushl %ebp
; X86-ATOM-NEXT:    movl %esp, %ebp
; X86-ATOM-NEXT:    pushl %ebx
; X86-ATOM-NEXT:    pushl %edi
; X86-ATOM-NEXT:    pushl %esi
; X86-ATOM-NEXT:    andl $-16, %esp
; X86-ATOM-NEXT:    leal -{{[0-9]+}}(%esp), %esp
; X86-ATOM-NEXT:    movl 12(%ebp), %edi
; X86-ATOM-NEXT:    movl 12(%edi), %ecx
; X86-ATOM-NEXT:    movl 8(%edi), %edx
; X86-ATOM-NEXT:    movl (%edi), %esi
; X86-ATOM-NEXT:    movl 4(%edi), %ebx
; X86-ATOM-NEXT:    .p2align 4
; X86-ATOM-NEXT:  .LBB4_1: # %atomicrmw.start
; X86-ATOM-NEXT:    # =>This Inner Loop Header: Depth=1
; X86-ATOM-NEXT:    movl %esi, (%esp)
; X86-ATOM-NEXT:    movl %ebx, {{[0-9]+}}(%esp)
; X86-ATOM-NEXT:    movl %edx, {{[0-9]+}}(%esp)
; X86-ATOM-NEXT:    movl %ecx, {{[0-9]+}}(%esp)
; X86-ATOM-NEXT:    movl %ecx, {{[0-9]+}}(%esp)
; X86-ATOM-NEXT:    movl %edx, {{[0-9]+}}(%esp)
; X86-ATOM-NEXT:    movl %ebx, {{[0-9]+}}(%esp)
; X86-ATOM-NEXT:    movl %esi, {{[0-9]+}}(%esp)
; X86-ATOM-NEXT:    pushl $0
; X86-ATOM-NEXT:    pushl $0
; X86-ATOM-NEXT:    leal {{[0-9]+}}(%esp), %eax
; X86-ATOM-NEXT:    pushl %eax
; X86-ATOM-NEXT:    leal {{[0-9]+}}(%esp), %eax
; X86-ATOM-NEXT:    pushl %eax
; X86-ATOM-NEXT:    pushl %edi
; X86-ATOM-NEXT:    pushl $16
; X86-ATOM-NEXT:    calll __atomic_compare_exchange@PLT
; X86-ATOM-NEXT:    leal {{[0-9]+}}(%esp), %esp
; X86-ATOM-NEXT:    movl {{[0-9]+}}(%esp), %ecx
; X86-ATOM-NEXT:    movl {{[0-9]+}}(%esp), %edx
; X86-ATOM-NEXT:    testb %al, %al
; X86-ATOM-NEXT:    movl (%esp), %esi
; X86-ATOM-NEXT:    movl {{[0-9]+}}(%esp), %ebx
; X86-ATOM-NEXT:    je .LBB4_1
; X86-ATOM-NEXT:  # %bb.2: # %atomicrmw.end
; X86-ATOM-NEXT:    movl 8(%ebp), %eax
; X86-ATOM-NEXT:    movl %esi, (%eax)
; X86-ATOM-NEXT:    movl %ebx, 4(%eax)
; X86-ATOM-NEXT:    movl %edx, 8(%eax)
; X86-ATOM-NEXT:    movl %ecx, 12(%eax)
; X86-ATOM-NEXT:    leal -12(%ebp), %esp
; X86-ATOM-NEXT:    popl %esi
; X86-ATOM-NEXT:    popl %edi
; X86-ATOM-NEXT:    popl %ebx
; X86-ATOM-NEXT:    popl %ebp
; X86-ATOM-NEXT:    retl $4
  %1 = atomicrmw or ptr %p, i128 0 syncscope("singlethread") monotonic
  ret i128 %1
}

; For 'and', the idempotent value is (-1)
define i32 @and32 (ptr %p) #0 {
; X64-LABEL: and32:
; X64:       # %bb.0:
; X64-NEXT:    #MEMBARRIER
; X64-NEXT:    movl (%rdi), %eax
; X64-NEXT:    retq
;
; X86-GENERIC-LABEL: and32:
; X86-GENERIC:       # %bb.0:
; X86-GENERIC-NEXT:    movl {{[0-9]+}}(%esp), %eax
; X86-GENERIC-NEXT:    #MEMBARRIER
; X86-GENERIC-NEXT:    movl (%eax), %eax
; X86-GENERIC-NEXT:    retl
;
; X86-ATOM-LABEL: and32:
; X86-ATOM:       # %bb.0:
; X86-ATOM-NEXT:    movl {{[0-9]+}}(%esp), %eax
; X86-ATOM-NEXT:    #MEMBARRIER
; X86-ATOM-NEXT:    movl (%eax), %eax
; X86-ATOM-NEXT:    nop
; X86-ATOM-NEXT:    nop
; X86-ATOM-NEXT:    nop
; X86-ATOM-NEXT:    nop
; X86-ATOM-NEXT:    retl
  %1 = atomicrmw and ptr %p, i32 -1 syncscope("singlethread") acq_rel
  ret i32 %1
}

define void @or32_nouse_monotonic(ptr %p) #0 {
; X64-LABEL: or32_nouse_monotonic:
; X64:       # %bb.0:
; X64-NEXT:    #MEMBARRIER
; X64-NEXT:    retq
;
; X86-GENERIC-LABEL: or32_nouse_monotonic:
; X86-GENERIC:       # %bb.0:
; X86-GENERIC-NEXT:    #MEMBARRIER
; X86-GENERIC-NEXT:    retl
;
; X86-ATOM-LABEL: or32_nouse_monotonic:
; X86-ATOM:       # %bb.0:
; X86-ATOM-NEXT:    #MEMBARRIER
; X86-ATOM-NEXT:    nop
; X86-ATOM-NEXT:    nop
; X86-ATOM-NEXT:    nop
; X86-ATOM-NEXT:    nop
; X86-ATOM-NEXT:    nop
; X86-ATOM-NEXT:    nop
; X86-ATOM-NEXT:    nop
; X86-ATOM-NEXT:    nop
; X86-ATOM-NEXT:    retl
  atomicrmw or ptr %p, i32 0 syncscope("singlethread") monotonic
  ret void
}


define void @or32_nouse_acquire(ptr %p) #0 {
; X64-LABEL: or32_nouse_acquire:
; X64:       # %bb.0:
; X64-NEXT:    #MEMBARRIER
; X64-NEXT:    retq
;
; X86-GENERIC-LABEL: or32_nouse_acquire:
; X86-GENERIC:       # %bb.0:
; X86-GENERIC-NEXT:    #MEMBARRIER
; X86-GENERIC-NEXT:    retl
;
; X86-ATOM-LABEL: or32_nouse_acquire:
; X86-ATOM:       # %bb.0:
; X86-ATOM-NEXT:    #MEMBARRIER
; X86-ATOM-NEXT:    nop
; X86-ATOM-NEXT:    nop
; X86-ATOM-NEXT:    nop
; X86-ATOM-NEXT:    nop
; X86-ATOM-NEXT:    nop
; X86-ATOM-NEXT:    nop
; X86-ATOM-NEXT:    nop
; X86-ATOM-NEXT:    nop
; X86-ATOM-NEXT:    retl
  atomicrmw or ptr %p, i32 0 acquire
  ret void
}

define void @or32_nouse_release(ptr %p) #0 {
; X64-LABEL: or32_nouse_release:
; X64:       # %bb.0:
; X64-NEXT:    #MEMBARRIER
; X64-NEXT:    retq
;
; X86-GENERIC-LABEL: or32_nouse_release:
; X86-GENERIC:       # %bb.0:
; X86-GENERIC-NEXT:    #MEMBARRIER
; X86-GENERIC-NEXT:    retl
;
; X86-ATOM-LABEL: or32_nouse_release:
; X86-ATOM:       # %bb.0:
; X86-ATOM-NEXT:    #MEMBARRIER
; X86-ATOM-NEXT:    nop
; X86-ATOM-NEXT:    nop
; X86-ATOM-NEXT:    nop
; X86-ATOM-NEXT:    nop
; X86-ATOM-NEXT:    nop
; X86-ATOM-NEXT:    nop
; X86-ATOM-NEXT:    nop
; X86-ATOM-NEXT:    nop
; X86-ATOM-NEXT:    retl
  atomicrmw or ptr %p, i32 0 syncscope("singlethread") release
  ret void
}

define void @or32_nouse_acq_rel(ptr %p) #0 {
; X64-LABEL: or32_nouse_acq_rel:
; X64:       # %bb.0:
; X64-NEXT:    #MEMBARRIER
; X64-NEXT:    retq
;
; X86-GENERIC-LABEL: or32_nouse_acq_rel:
; X86-GENERIC:       # %bb.0:
; X86-GENERIC-NEXT:    #MEMBARRIER
; X86-GENERIC-NEXT:    retl
;
; X86-ATOM-LABEL: or32_nouse_acq_rel:
; X86-ATOM:       # %bb.0:
; X86-ATOM-NEXT:    #MEMBARRIER
; X86-ATOM-NEXT:    nop
; X86-ATOM-NEXT:    nop
; X86-ATOM-NEXT:    nop
; X86-ATOM-NEXT:    nop
; X86-ATOM-NEXT:    nop
; X86-ATOM-NEXT:    nop
; X86-ATOM-NEXT:    nop
; X86-ATOM-NEXT:    nop
; X86-ATOM-NEXT:    retl
  atomicrmw or ptr %p, i32 0 syncscope("singlethread") acq_rel
  ret void
}

define void @or32_nouse_seq_cst(ptr %p) #0 {
; X64-LABEL: or32_nouse_seq_cst:
; X64:       # %bb.0:
; X64-NEXT:    #MEMBARRIER
; X64-NEXT:    retq
;
; X86-GENERIC-LABEL: or32_nouse_seq_cst:
; X86-GENERIC:       # %bb.0:
; X86-GENERIC-NEXT:    #MEMBARRIER
; X86-GENERIC-NEXT:    retl
;
; X86-ATOM-LABEL: or32_nouse_seq_cst:
; X86-ATOM:       # %bb.0:
; X86-ATOM-NEXT:    #MEMBARRIER
; X86-ATOM-NEXT:    nop
; X86-ATOM-NEXT:    nop
; X86-ATOM-NEXT:    nop
; X86-ATOM-NEXT:    nop
; X86-ATOM-NEXT:    nop
; X86-ATOM-NEXT:    nop
; X86-ATOM-NEXT:    nop
; X86-ATOM-NEXT:    nop
; X86-ATOM-NEXT:    retl
  atomicrmw or ptr %p, i32 0 syncscope("singlethread") seq_cst
  ret void
}

; TODO: The value isn't used on 32 bit, so the cmpxchg8b is unneeded
define void @or64_nouse_seq_cst(ptr %p) #0 {
; X64-LABEL: or64_nouse_seq_cst:
; X64:       # %bb.0:
; X64-NEXT:    #MEMBARRIER
; X64-NEXT:    retq
;
; X86-LABEL: or64_nouse_seq_cst:
; X86:       # %bb.0:
; X86-NEXT:    pushl %ebx
; X86-NEXT:    pushl %esi
; X86-NEXT:    movl {{[0-9]+}}(%esp), %esi
; X86-NEXT:    movl (%esi), %eax
; X86-NEXT:    movl 4(%esi), %edx
; X86-NEXT:    .p2align 4
; X86-NEXT:  .LBB11_1: # %atomicrmw.start
; X86-NEXT:    # =>This Inner Loop Header: Depth=1
; X86-NEXT:    movl %edx, %ecx
; X86-NEXT:    movl %eax, %ebx
; X86-NEXT:    lock cmpxchg8b (%esi)
; X86-NEXT:    jne .LBB11_1
; X86-NEXT:  # %bb.2: # %atomicrmw.end
; X86-NEXT:    popl %esi
; X86-NEXT:    popl %ebx
; X86-NEXT:    retl
  atomicrmw or ptr %p, i64 0 syncscope("singlethread") seq_cst
  ret void
}

; TODO: Don't need to lower as sync_and_fetch call
define void @or128_nouse_seq_cst(ptr %p) #0 {
; X64-LABEL: or128_nouse_seq_cst:
; X64:       # %bb.0:
; X64-NEXT:    pushq %rax
; X64-NEXT:    xorl %esi, %esi
; X64-NEXT:    xorl %edx, %edx
; X64-NEXT:    movl $5, %ecx
; X64-NEXT:    callq __atomic_fetch_or_16@PLT
; X64-NEXT:    popq %rax
; X64-NEXT:    retq
;
; X86-GENERIC-LABEL: or128_nouse_seq_cst:
; X86-GENERIC:       # %bb.0:
; X86-GENERIC-NEXT:    pushl %ebp
; X86-GENERIC-NEXT:    movl %esp, %ebp
; X86-GENERIC-NEXT:    pushl %ebx
; X86-GENERIC-NEXT:    pushl %edi
; X86-GENERIC-NEXT:    pushl %esi
; X86-GENERIC-NEXT:    andl $-16, %esp
; X86-GENERIC-NEXT:    subl $32, %esp
; X86-GENERIC-NEXT:    movl 8(%ebp), %esi
; X86-GENERIC-NEXT:    movl 12(%esi), %ecx
; X86-GENERIC-NEXT:    movl 8(%esi), %edi
; X86-GENERIC-NEXT:    movl (%esi), %edx
; X86-GENERIC-NEXT:    movl 4(%esi), %ebx
; X86-GENERIC-NEXT:    .p2align 4
; X86-GENERIC-NEXT:  .LBB12_1: # %atomicrmw.start
; X86-GENERIC-NEXT:    # =>This Inner Loop Header: Depth=1
; X86-GENERIC-NEXT:    movl %edx, (%esp)
; X86-GENERIC-NEXT:    movl %ebx, {{[0-9]+}}(%esp)
; X86-GENERIC-NEXT:    movl %edi, {{[0-9]+}}(%esp)
; X86-GENERIC-NEXT:    movl %ecx, {{[0-9]+}}(%esp)
; X86-GENERIC-NEXT:    movl %ecx, {{[0-9]+}}(%esp)
; X86-GENERIC-NEXT:    movl %edi, {{[0-9]+}}(%esp)
; X86-GENERIC-NEXT:    movl %ebx, {{[0-9]+}}(%esp)
; X86-GENERIC-NEXT:    movl %edx, {{[0-9]+}}(%esp)
; X86-GENERIC-NEXT:    pushl $5
; X86-GENERIC-NEXT:    pushl $5
; X86-GENERIC-NEXT:    leal {{[0-9]+}}(%esp), %eax
; X86-GENERIC-NEXT:    pushl %eax
; X86-GENERIC-NEXT:    leal {{[0-9]+}}(%esp), %eax
; X86-GENERIC-NEXT:    pushl %eax
; X86-GENERIC-NEXT:    pushl %esi
; X86-GENERIC-NEXT:    pushl $16
; X86-GENERIC-NEXT:    calll __atomic_compare_exchange@PLT
; X86-GENERIC-NEXT:    addl $24, %esp
; X86-GENERIC-NEXT:    movl {{[0-9]+}}(%esp), %ecx
; X86-GENERIC-NEXT:    movl {{[0-9]+}}(%esp), %edi
; X86-GENERIC-NEXT:    movl (%esp), %edx
; X86-GENERIC-NEXT:    movl {{[0-9]+}}(%esp), %ebx
; X86-GENERIC-NEXT:    testb %al, %al
; X86-GENERIC-NEXT:    je .LBB12_1
; X86-GENERIC-NEXT:  # %bb.2: # %atomicrmw.end
; X86-GENERIC-NEXT:    leal -12(%ebp), %esp
; X86-GENERIC-NEXT:    popl %esi
; X86-GENERIC-NEXT:    popl %edi
; X86-GENERIC-NEXT:    popl %ebx
; X86-GENERIC-NEXT:    popl %ebp
; X86-GENERIC-NEXT:    retl
;
; X86-ATOM-LABEL: or128_nouse_seq_cst:
; X86-ATOM:       # %bb.0:
; X86-ATOM-NEXT:    pushl %ebp
; X86-ATOM-NEXT:    movl %esp, %ebp
; X86-ATOM-NEXT:    pushl %ebx
; X86-ATOM-NEXT:    pushl %edi
; X86-ATOM-NEXT:    pushl %esi
; X86-ATOM-NEXT:    andl $-16, %esp
; X86-ATOM-NEXT:    leal -{{[0-9]+}}(%esp), %esp
; X86-ATOM-NEXT:    movl 8(%ebp), %esi
; X86-ATOM-NEXT:    movl %esp, %ebx
; X86-ATOM-NEXT:    movl 12(%esi), %ecx
; X86-ATOM-NEXT:    movl 8(%esi), %edx
; X86-ATOM-NEXT:    movl (%esi), %eax
; X86-ATOM-NEXT:    movl 4(%esi), %edi
; X86-ATOM-NEXT:    .p2align 4
; X86-ATOM-NEXT:  .LBB12_1: # %atomicrmw.start
; X86-ATOM-NEXT:    # =>This Inner Loop Header: Depth=1
; X86-ATOM-NEXT:    movl %eax, (%esp)
; X86-ATOM-NEXT:    movl %edi, {{[0-9]+}}(%esp)
; X86-ATOM-NEXT:    movl %edx, {{[0-9]+}}(%esp)
; X86-ATOM-NEXT:    movl %ecx, {{[0-9]+}}(%esp)
; X86-ATOM-NEXT:    movl %ecx, {{[0-9]+}}(%esp)
; X86-ATOM-NEXT:    movl %edx, {{[0-9]+}}(%esp)
; X86-ATOM-NEXT:    movl %edi, {{[0-9]+}}(%esp)
; X86-ATOM-NEXT:    movl %eax, {{[0-9]+}}(%esp)
; X86-ATOM-NEXT:    pushl $5
; X86-ATOM-NEXT:    pushl $5
; X86-ATOM-NEXT:    leal {{[0-9]+}}(%esp), %eax
; X86-ATOM-NEXT:    pushl %eax
; X86-ATOM-NEXT:    pushl %ebx
; X86-ATOM-NEXT:    pushl %esi
; X86-ATOM-NEXT:    pushl $16
; X86-ATOM-NEXT:    calll __atomic_compare_exchange@PLT
; X86-ATOM-NEXT:    leal {{[0-9]+}}(%esp), %esp
; X86-ATOM-NEXT:    testb %al, %al
; X86-ATOM-NEXT:    movl {{[0-9]+}}(%esp), %ecx
; X86-ATOM-NEXT:    movl {{[0-9]+}}(%esp), %edx
; X86-ATOM-NEXT:    movl (%esp), %eax
; X86-ATOM-NEXT:    movl {{[0-9]+}}(%esp), %edi
; X86-ATOM-NEXT:    je .LBB12_1
; X86-ATOM-NEXT:  # %bb.2: # %atomicrmw.end
; X86-ATOM-NEXT:    leal -12(%ebp), %esp
; X86-ATOM-NEXT:    popl %esi
; X86-ATOM-NEXT:    popl %edi
; X86-ATOM-NEXT:    popl %ebx
; X86-ATOM-NEXT:    popl %ebp
; X86-ATOM-NEXT:    retl
  atomicrmw or ptr %p, i128 0 syncscope("singlethread") seq_cst
  ret void
}


define void @or16_nouse_seq_cst(ptr %p) #0 {
; X64-LABEL: or16_nouse_seq_cst:
; X64:       # %bb.0:
; X64-NEXT:    #MEMBARRIER
; X64-NEXT:    retq
;
; X86-GENERIC-LABEL: or16_nouse_seq_cst:
; X86-GENERIC:       # %bb.0:
; X86-GENERIC-NEXT:    #MEMBARRIER
; X86-GENERIC-NEXT:    retl
;
; X86-ATOM-LABEL: or16_nouse_seq_cst:
; X86-ATOM:       # %bb.0:
; X86-ATOM-NEXT:    #MEMBARRIER
; X86-ATOM-NEXT:    nop
; X86-ATOM-NEXT:    nop
; X86-ATOM-NEXT:    nop
; X86-ATOM-NEXT:    nop
; X86-ATOM-NEXT:    nop
; X86-ATOM-NEXT:    nop
; X86-ATOM-NEXT:    nop
; X86-ATOM-NEXT:    nop
; X86-ATOM-NEXT:    retl
  atomicrmw or ptr %p, i16 0 syncscope("singlethread") seq_cst
  ret void
}

define void @or8_nouse_seq_cst(ptr %p) #0 {
; X64-LABEL: or8_nouse_seq_cst:
; X64:       # %bb.0:
; X64-NEXT:    #MEMBARRIER
; X64-NEXT:    retq
;
; X86-GENERIC-LABEL: or8_nouse_seq_cst:
; X86-GENERIC:       # %bb.0:
; X86-GENERIC-NEXT:    #MEMBARRIER
; X86-GENERIC-NEXT:    retl
;
; X86-ATOM-LABEL: or8_nouse_seq_cst:
; X86-ATOM:       # %bb.0:
; X86-ATOM-NEXT:    #MEMBARRIER
; X86-ATOM-NEXT:    nop
; X86-ATOM-NEXT:    nop
; X86-ATOM-NEXT:    nop
; X86-ATOM-NEXT:    nop
; X86-ATOM-NEXT:    nop
; X86-ATOM-NEXT:    nop
; X86-ATOM-NEXT:    nop
; X86-ATOM-NEXT:    nop
; X86-ATOM-NEXT:    retl
  atomicrmw or ptr %p, i8 0 syncscope("singlethread") seq_cst
  ret void
}

attributes #0 = { nounwind }

;; NOTE: These prefixes are unused and the list is autogenerated. Do not add tests below this line:
; X86-SLM: {{.*}}
; X86-SSE2: {{.*}}