; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=x86_64-- -verify-machineinstrs | FileCheck %s --check-prefix=CHECK --check-prefix=X64
-; RUN: llc < %s -mtriple=i686-- -mattr=+sse2 -verify-machineinstrs | FileCheck %s --check-prefix=CHECK --check-prefix=X32
+; RUN: llc < %s -mtriple=i686-- -mattr=+sse2 -verify-machineinstrs | FileCheck %s --check-prefix=CHECK --check-prefix=X86
; 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.
; X64-NEXT: movb (%rdi), %al
; X64-NEXT: retq
;
-; X32-LABEL: add8:
-; X32: # %bb.0:
-; X32-NEXT: movl {{[0-9]+}}(%esp), %eax
-; X32-NEXT: mfence
-; X32-NEXT: movb (%eax), %al
-; X32-NEXT: retl
+; X86-LABEL: add8:
+; X86: # %bb.0:
+; X86-NEXT: movl {{[0-9]+}}(%esp), %eax
+; X86-NEXT: mfence
+; X86-NEXT: movb (%eax), %al
+; X86-NEXT: retl
%1 = atomicrmw add i8* %p, i8 0 monotonic
ret i8 %1
}
; X64-NEXT: movzwl (%rdi), %eax
; X64-NEXT: retq
;
-; X32-LABEL: or16:
-; X32: # %bb.0:
-; X32-NEXT: movl {{[0-9]+}}(%esp), %eax
-; X32-NEXT: mfence
-; X32-NEXT: movzwl (%eax), %eax
-; X32-NEXT: retl
+; X86-LABEL: or16:
+; X86: # %bb.0:
+; X86-NEXT: movl {{[0-9]+}}(%esp), %eax
+; X86-NEXT: mfence
+; X86-NEXT: movzwl (%eax), %eax
+; X86-NEXT: retl
%1 = atomicrmw or i16* %p, i16 0 acquire
ret i16 %1
}
; X64-NEXT: movl (%rdi), %eax
; X64-NEXT: retq
;
-; X32-LABEL: xor32:
-; X32: # %bb.0:
-; X32-NEXT: movl {{[0-9]+}}(%esp), %eax
-; X32-NEXT: mfence
-; X32-NEXT: movl (%eax), %eax
-; X32-NEXT: retl
+; X86-LABEL: xor32:
+; X86: # %bb.0:
+; X86-NEXT: movl {{[0-9]+}}(%esp), %eax
+; X86-NEXT: mfence
+; X86-NEXT: movl (%eax), %eax
+; X86-NEXT: retl
%1 = atomicrmw xor i32* %p, i32 0 release
ret i32 %1
}
; X64-NEXT: movq (%rdi), %rax
; X64-NEXT: retq
;
-; X32-LABEL: sub64:
-; X32: # %bb.0:
-; X32-NEXT: pushl %ebx
-; X32-NEXT: .cfi_def_cfa_offset 8
-; X32-NEXT: pushl %esi
-; X32-NEXT: .cfi_def_cfa_offset 12
-; X32-NEXT: .cfi_offset %esi, -12
-; X32-NEXT: .cfi_offset %ebx, -8
-; X32-NEXT: movl {{[0-9]+}}(%esp), %esi
-; X32-NEXT: movl (%esi), %eax
-; X32-NEXT: movl 4(%esi), %edx
-; X32-NEXT: .p2align 4, 0x90
-; X32-NEXT: .LBB3_1: # %atomicrmw.start
-; X32-NEXT: # =>This Inner Loop Header: Depth=1
-; X32-NEXT: movl %edx, %ecx
-; X32-NEXT: movl %eax, %ebx
-; X32-NEXT: lock cmpxchg8b (%esi)
-; X32-NEXT: jne .LBB3_1
-; X32-NEXT: # %bb.2: # %atomicrmw.end
-; X32-NEXT: popl %esi
-; X32-NEXT: .cfi_def_cfa_offset 8
-; X32-NEXT: popl %ebx
-; X32-NEXT: .cfi_def_cfa_offset 4
-; X32-NEXT: retl
+; X86-LABEL: sub64:
+; X86: # %bb.0:
+; X86-NEXT: pushl %ebx
+; X86-NEXT: .cfi_def_cfa_offset 8
+; X86-NEXT: pushl %esi
+; X86-NEXT: .cfi_def_cfa_offset 12
+; X86-NEXT: .cfi_offset %esi, -12
+; X86-NEXT: .cfi_offset %ebx, -8
+; X86-NEXT: movl {{[0-9]+}}(%esp), %esi
+; X86-NEXT: movl (%esi), %eax
+; X86-NEXT: movl 4(%esi), %edx
+; X86-NEXT: .p2align 4, 0x90
+; 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: .cfi_def_cfa_offset 8
+; X86-NEXT: popl %ebx
+; X86-NEXT: .cfi_def_cfa_offset 4
+; X86-NEXT: retl
%1 = atomicrmw sub i64* %p, i64 0 seq_cst
ret i64 %1
}
; X64-NEXT: .cfi_def_cfa_offset 8
; X64-NEXT: retq
;
-; X32-LABEL: or128:
-; X32: # %bb.0:
-; X32-NEXT: pushl %ebp
-; X32-NEXT: .cfi_def_cfa_offset 8
-; X32-NEXT: .cfi_offset %ebp, -8
-; X32-NEXT: movl %esp, %ebp
-; X32-NEXT: .cfi_def_cfa_register %ebp
-; X32-NEXT: pushl %edi
-; X32-NEXT: pushl %esi
-; X32-NEXT: andl $-8, %esp
-; X32-NEXT: subl $16, %esp
-; X32-NEXT: .cfi_offset %esi, -16
-; X32-NEXT: .cfi_offset %edi, -12
-; X32-NEXT: movl 8(%ebp), %esi
-; X32-NEXT: movl %esp, %eax
-; X32-NEXT: pushl $0
-; X32-NEXT: pushl $0
-; X32-NEXT: pushl $0
-; X32-NEXT: pushl $0
-; X32-NEXT: pushl 12(%ebp)
-; X32-NEXT: pushl %eax
-; X32-NEXT: calll __sync_fetch_and_or_16
-; X32-NEXT: addl $20, %esp
-; X32-NEXT: movl (%esp), %eax
-; X32-NEXT: movl {{[0-9]+}}(%esp), %ecx
-; X32-NEXT: movl {{[0-9]+}}(%esp), %edx
-; X32-NEXT: movl {{[0-9]+}}(%esp), %edi
-; X32-NEXT: movl %edi, 8(%esi)
-; X32-NEXT: movl %edx, 12(%esi)
-; X32-NEXT: movl %eax, (%esi)
-; X32-NEXT: movl %ecx, 4(%esi)
-; X32-NEXT: movl %esi, %eax
-; X32-NEXT: leal -8(%ebp), %esp
-; X32-NEXT: popl %esi
-; X32-NEXT: popl %edi
-; X32-NEXT: popl %ebp
-; X32-NEXT: .cfi_def_cfa %esp, 4
-; X32-NEXT: retl $4
+; X86-LABEL: or128:
+; X86: # %bb.0:
+; X86-NEXT: pushl %ebp
+; X86-NEXT: .cfi_def_cfa_offset 8
+; X86-NEXT: .cfi_offset %ebp, -8
+; X86-NEXT: movl %esp, %ebp
+; X86-NEXT: .cfi_def_cfa_register %ebp
+; X86-NEXT: pushl %edi
+; X86-NEXT: pushl %esi
+; X86-NEXT: andl $-8, %esp
+; X86-NEXT: subl $16, %esp
+; X86-NEXT: .cfi_offset %esi, -16
+; X86-NEXT: .cfi_offset %edi, -12
+; X86-NEXT: movl 8(%ebp), %esi
+; X86-NEXT: movl %esp, %eax
+; X86-NEXT: pushl $0
+; X86-NEXT: pushl $0
+; X86-NEXT: pushl $0
+; X86-NEXT: pushl $0
+; X86-NEXT: pushl 12(%ebp)
+; X86-NEXT: pushl %eax
+; X86-NEXT: calll __sync_fetch_and_or_16
+; X86-NEXT: addl $20, %esp
+; X86-NEXT: movl (%esp), %eax
+; X86-NEXT: movl {{[0-9]+}}(%esp), %ecx
+; X86-NEXT: movl {{[0-9]+}}(%esp), %edx
+; X86-NEXT: movl {{[0-9]+}}(%esp), %edi
+; X86-NEXT: movl %edi, 8(%esi)
+; X86-NEXT: movl %edx, 12(%esi)
+; X86-NEXT: movl %eax, (%esi)
+; X86-NEXT: movl %ecx, 4(%esi)
+; X86-NEXT: movl %esi, %eax
+; X86-NEXT: leal -8(%ebp), %esp
+; X86-NEXT: popl %esi
+; X86-NEXT: popl %edi
+; X86-NEXT: popl %ebp
+; X86-NEXT: .cfi_def_cfa %esp, 4
+; X86-NEXT: retl $4
%1 = atomicrmw or i128* %p, i128 0 monotonic
ret i128 %1
}
; X64-NEXT: movl (%rdi), %eax
; X64-NEXT: retq
;
-; X32-LABEL: and32:
-; X32: # %bb.0:
-; X32-NEXT: movl {{[0-9]+}}(%esp), %eax
-; X32-NEXT: mfence
-; X32-NEXT: movl (%eax), %eax
-; X32-NEXT: retl
+; X86-LABEL: and32:
+; X86: # %bb.0:
+; X86-NEXT: movl {{[0-9]+}}(%esp), %eax
+; X86-NEXT: mfence
+; X86-NEXT: movl (%eax), %eax
+; X86-NEXT: retl
%1 = atomicrmw and i32* %p, i32 -1 acq_rel
ret i32 %1
}
; X64-NEXT: lock orl $0, (%rsp)
; X64-NEXT: retq
;
-; X32-LABEL: or32_nouse_seq_cst:
-; X32: # %bb.0:
-; X32-NEXT: lock orl $0, (%esp)
-; X32-NEXT: retl
+; X86-LABEL: or32_nouse_seq_cst:
+; X86: # %bb.0:
+; X86-NEXT: lock orl $0, (%esp)
+; X86-NEXT: retl
atomicrmw or i32* %p, i32 0 seq_cst
ret void
}
; X64-NEXT: lock orl $0, (%rsp)
; X64-NEXT: retq
;
-; X32-LABEL: or64_nouse_seq_cst:
-; X32: # %bb.0:
-; X32-NEXT: pushl %ebx
-; X32-NEXT: .cfi_def_cfa_offset 8
-; X32-NEXT: pushl %esi
-; X32-NEXT: .cfi_def_cfa_offset 12
-; X32-NEXT: .cfi_offset %esi, -12
-; X32-NEXT: .cfi_offset %ebx, -8
-; X32-NEXT: movl {{[0-9]+}}(%esp), %esi
-; X32-NEXT: movl (%esi), %eax
-; X32-NEXT: movl 4(%esi), %edx
-; X32-NEXT: .p2align 4, 0x90
-; X32-NEXT: .LBB11_1: # %atomicrmw.start
-; X32-NEXT: # =>This Inner Loop Header: Depth=1
-; X32-NEXT: movl %edx, %ecx
-; X32-NEXT: movl %eax, %ebx
-; X32-NEXT: lock cmpxchg8b (%esi)
-; X32-NEXT: jne .LBB11_1
-; X32-NEXT: # %bb.2: # %atomicrmw.end
-; X32-NEXT: popl %esi
-; X32-NEXT: .cfi_def_cfa_offset 8
-; X32-NEXT: popl %ebx
-; X32-NEXT: .cfi_def_cfa_offset 4
-; X32-NEXT: retl
+; X86-LABEL: or64_nouse_seq_cst:
+; X86: # %bb.0:
+; X86-NEXT: pushl %ebx
+; X86-NEXT: .cfi_def_cfa_offset 8
+; X86-NEXT: pushl %esi
+; X86-NEXT: .cfi_def_cfa_offset 12
+; X86-NEXT: .cfi_offset %esi, -12
+; X86-NEXT: .cfi_offset %ebx, -8
+; X86-NEXT: movl {{[0-9]+}}(%esp), %esi
+; X86-NEXT: movl (%esi), %eax
+; X86-NEXT: movl 4(%esi), %edx
+; X86-NEXT: .p2align 4, 0x90
+; 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: .cfi_def_cfa_offset 8
+; X86-NEXT: popl %ebx
+; X86-NEXT: .cfi_def_cfa_offset 4
+; X86-NEXT: retl
atomicrmw or i64* %p, i64 0 seq_cst
ret void
}
; X64-NEXT: .cfi_def_cfa_offset 8
; X64-NEXT: retq
;
-; X32-LABEL: or128_nouse_seq_cst:
-; X32: # %bb.0:
-; X32-NEXT: pushl %ebp
-; X32-NEXT: .cfi_def_cfa_offset 8
-; X32-NEXT: .cfi_offset %ebp, -8
-; X32-NEXT: movl %esp, %ebp
-; X32-NEXT: .cfi_def_cfa_register %ebp
-; X32-NEXT: andl $-8, %esp
-; X32-NEXT: subl $16, %esp
-; X32-NEXT: movl %esp, %eax
-; X32-NEXT: pushl $0
-; X32-NEXT: pushl $0
-; X32-NEXT: pushl $0
-; X32-NEXT: pushl $0
-; X32-NEXT: pushl 8(%ebp)
-; X32-NEXT: pushl %eax
-; X32-NEXT: calll __sync_fetch_and_or_16
-; X32-NEXT: addl $20, %esp
-; X32-NEXT: movl %ebp, %esp
-; X32-NEXT: popl %ebp
-; X32-NEXT: .cfi_def_cfa %esp, 4
-; X32-NEXT: retl
-; X128-LABEL: or128_nouse_seq_cst:
-; X128: # %bb.0:
-; X128-NEXT: lock orl $0, -{{[0-9]+}}(%esp)
-; X128-NEXT: retl
+; X86-LABEL: or128_nouse_seq_cst:
+; X86: # %bb.0:
+; X86-NEXT: pushl %ebp
+; X86-NEXT: .cfi_def_cfa_offset 8
+; X86-NEXT: .cfi_offset %ebp, -8
+; X86-NEXT: movl %esp, %ebp
+; X86-NEXT: .cfi_def_cfa_register %ebp
+; X86-NEXT: andl $-8, %esp
+; X86-NEXT: subl $16, %esp
+; X86-NEXT: movl %esp, %eax
+; X86-NEXT: pushl $0
+; X86-NEXT: pushl $0
+; X86-NEXT: pushl $0
+; X86-NEXT: pushl $0
+; X86-NEXT: pushl 8(%ebp)
+; X86-NEXT: pushl %eax
+; X86-NEXT: calll __sync_fetch_and_or_16
+; X86-NEXT: addl $20, %esp
+; X86-NEXT: movl %ebp, %esp
+; X86-NEXT: popl %ebp
+; X86-NEXT: .cfi_def_cfa %esp, 4
+; X86-NEXT: retl
atomicrmw or i128* %p, i128 0 seq_cst
ret void
}
; X64-NEXT: lock orl $0, (%rsp)
; X64-NEXT: retq
;
-; X32-LABEL: or16_nouse_seq_cst:
-; X32: # %bb.0:
-; X32-NEXT: lock orl $0, (%esp)
-; X32-NEXT: retl
+; X86-LABEL: or16_nouse_seq_cst:
+; X86: # %bb.0:
+; X86-NEXT: lock orl $0, (%esp)
+; X86-NEXT: retl
atomicrmw or i16* %p, i16 0 seq_cst
ret void
}
; X64-NEXT: lock orl $0, (%rsp)
; X64-NEXT: retq
;
-; X32-LABEL: or8_nouse_seq_cst:
-; X32: # %bb.0:
-; X32-NEXT: lock orl $0, (%esp)
-; X32-NEXT: retl
+; X86-LABEL: or8_nouse_seq_cst:
+; X86: # %bb.0:
+; X86-NEXT: lock orl $0, (%esp)
+; X86-NEXT: retl
atomicrmw or i8* %p, i8 0 seq_cst
ret void
}