168 lines
5.0 KiB
LLVM
168 lines
5.0 KiB
LLVM
|
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
||
|
|
; RUN: llc < %s -mtriple=i686 -mattr=cmov | FileCheck %s --check-prefix=X86
|
||
|
|
; RUN: llc < %s -mtriple=x86_64-linux | FileCheck %s --check-prefix=X64
|
||
|
|
|
||
|
|
declare i4 @llvm.usub.sat.i4(i4, i4)
|
||
|
|
declare i8 @llvm.usub.sat.i8(i8, i8)
|
||
|
|
declare i16 @llvm.usub.sat.i16(i16, i16)
|
||
|
|
declare i32 @llvm.usub.sat.i32(i32, i32)
|
||
|
|
declare i64 @llvm.usub.sat.i64(i64, i64)
|
||
|
|
declare <4 x i32> @llvm.usub.sat.v4i32(<4 x i32>, <4 x i32>)
|
||
|
|
|
||
|
|
define i32 @func(i32 %x, i32 %y) nounwind {
|
||
|
|
; X86-LABEL: func:
|
||
|
|
; X86: # %bb.0:
|
||
|
|
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax
|
||
|
|
; X86-NEXT: xorl %ecx, %ecx
|
||
|
|
; X86-NEXT: subl {{[0-9]+}}(%esp), %eax
|
||
|
|
; X86-NEXT: cmovbl %ecx, %eax
|
||
|
|
; X86-NEXT: retl
|
||
|
|
;
|
||
|
|
; X64-LABEL: func:
|
||
|
|
; X64: # %bb.0:
|
||
|
|
; X64-NEXT: xorl %eax, %eax
|
||
|
|
; X64-NEXT: subl %esi, %edi
|
||
|
|
; X64-NEXT: cmovael %edi, %eax
|
||
|
|
; X64-NEXT: retq
|
||
|
|
%tmp = call i32 @llvm.usub.sat.i32(i32 %x, i32 %y)
|
||
|
|
ret i32 %tmp
|
||
|
|
}
|
||
|
|
|
||
|
|
define i64 @func2(i64 %x, i64 %y) nounwind {
|
||
|
|
; X86-LABEL: func2:
|
||
|
|
; X86: # %bb.0:
|
||
|
|
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax
|
||
|
|
; X86-NEXT: movl {{[0-9]+}}(%esp), %edx
|
||
|
|
; X86-NEXT: xorl %ecx, %ecx
|
||
|
|
; X86-NEXT: subl {{[0-9]+}}(%esp), %eax
|
||
|
|
; X86-NEXT: sbbl {{[0-9]+}}(%esp), %edx
|
||
|
|
; X86-NEXT: cmovbl %ecx, %edx
|
||
|
|
; X86-NEXT: cmovbl %ecx, %eax
|
||
|
|
; X86-NEXT: retl
|
||
|
|
;
|
||
|
|
; X64-LABEL: func2:
|
||
|
|
; X64: # %bb.0:
|
||
|
|
; X64-NEXT: xorl %eax, %eax
|
||
|
|
; X64-NEXT: subq %rsi, %rdi
|
||
|
|
; X64-NEXT: cmovaeq %rdi, %rax
|
||
|
|
; X64-NEXT: retq
|
||
|
|
%tmp = call i64 @llvm.usub.sat.i64(i64 %x, i64 %y)
|
||
|
|
ret i64 %tmp
|
||
|
|
}
|
||
|
|
|
||
|
|
define zeroext i16 @func16(i16 zeroext %x, i16 zeroext %y) nounwind {
|
||
|
|
; X86-LABEL: func16:
|
||
|
|
; X86: # %bb.0:
|
||
|
|
; X86-NEXT: movzwl {{[0-9]+}}(%esp), %eax
|
||
|
|
; X86-NEXT: xorl %ecx, %ecx
|
||
|
|
; X86-NEXT: subw {{[0-9]+}}(%esp), %ax
|
||
|
|
; X86-NEXT: cmovbl %ecx, %eax
|
||
|
|
; X86-NEXT: # kill: def $ax killed $ax killed $eax
|
||
|
|
; X86-NEXT: retl
|
||
|
|
;
|
||
|
|
; X64-LABEL: func16:
|
||
|
|
; X64: # %bb.0:
|
||
|
|
; X64-NEXT: xorl %eax, %eax
|
||
|
|
; X64-NEXT: subw %si, %di
|
||
|
|
; X64-NEXT: cmovael %edi, %eax
|
||
|
|
; X64-NEXT: # kill: def $ax killed $ax killed $eax
|
||
|
|
; X64-NEXT: retq
|
||
|
|
%tmp = call i16 @llvm.usub.sat.i16(i16 %x, i16 %y)
|
||
|
|
ret i16 %tmp
|
||
|
|
}
|
||
|
|
|
||
|
|
define zeroext i8 @func8(i8 zeroext %x, i8 zeroext %y) nounwind {
|
||
|
|
; X86-LABEL: func8:
|
||
|
|
; X86: # %bb.0:
|
||
|
|
; X86-NEXT: movb {{[0-9]+}}(%esp), %al
|
||
|
|
; X86-NEXT: xorl %ecx, %ecx
|
||
|
|
; X86-NEXT: subb {{[0-9]+}}(%esp), %al
|
||
|
|
; X86-NEXT: movzbl %al, %eax
|
||
|
|
; X86-NEXT: cmovbl %ecx, %eax
|
||
|
|
; X86-NEXT: # kill: def $al killed $al killed $eax
|
||
|
|
; X86-NEXT: retl
|
||
|
|
;
|
||
|
|
; X64-LABEL: func8:
|
||
|
|
; X64: # %bb.0:
|
||
|
|
; X64-NEXT: xorl %ecx, %ecx
|
||
|
|
; X64-NEXT: subb %sil, %dil
|
||
|
|
; X64-NEXT: movzbl %dil, %eax
|
||
|
|
; X64-NEXT: cmovbl %ecx, %eax
|
||
|
|
; X64-NEXT: # kill: def $al killed $al killed $eax
|
||
|
|
; X64-NEXT: retq
|
||
|
|
%tmp = call i8 @llvm.usub.sat.i8(i8 %x, i8 %y)
|
||
|
|
ret i8 %tmp
|
||
|
|
}
|
||
|
|
|
||
|
|
define zeroext i4 @func3(i4 zeroext %x, i4 zeroext %y) nounwind {
|
||
|
|
; X86-LABEL: func3:
|
||
|
|
; X86: # %bb.0:
|
||
|
|
; X86-NEXT: pushl %ebx
|
||
|
|
; X86-NEXT: movb {{[0-9]+}}(%esp), %al
|
||
|
|
; X86-NEXT: movb {{[0-9]+}}(%esp), %cl
|
||
|
|
; X86-NEXT: movzbl %cl, %edx
|
||
|
|
; X86-NEXT: movzbl %al, %ebx
|
||
|
|
; X86-NEXT: cmpb %al, %cl
|
||
|
|
; X86-NEXT: cmoval %edx, %ebx
|
||
|
|
; X86-NEXT: subb %al, %bl
|
||
|
|
; X86-NEXT: movzbl %bl, %eax
|
||
|
|
; X86-NEXT: andl $15, %eax
|
||
|
|
; X86-NEXT: popl %ebx
|
||
|
|
; X86-NEXT: retl
|
||
|
|
;
|
||
|
|
; X64-LABEL: func3:
|
||
|
|
; X64: # %bb.0:
|
||
|
|
; X64-NEXT: cmpb %sil, %dil
|
||
|
|
; X64-NEXT: movl %esi, %eax
|
||
|
|
; X64-NEXT: cmoval %edi, %eax
|
||
|
|
; X64-NEXT: subb %sil, %al
|
||
|
|
; X64-NEXT: movzbl %al, %eax
|
||
|
|
; X64-NEXT: andl $15, %eax
|
||
|
|
; X64-NEXT: retq
|
||
|
|
%tmp = call i4 @llvm.usub.sat.i4(i4 %x, i4 %y)
|
||
|
|
ret i4 %tmp
|
||
|
|
}
|
||
|
|
|
||
|
|
define <4 x i32> @vec(<4 x i32> %x, <4 x i32> %y) nounwind {
|
||
|
|
; X86-LABEL: vec:
|
||
|
|
; X86: # %bb.0:
|
||
|
|
; X86-NEXT: pushl %ebx
|
||
|
|
; 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 {{[0-9]+}}(%esp), %edi
|
||
|
|
; X86-NEXT: xorl %ebx, %ebx
|
||
|
|
; X86-NEXT: subl {{[0-9]+}}(%esp), %edi
|
||
|
|
; X86-NEXT: cmovbl %ebx, %edi
|
||
|
|
; X86-NEXT: subl {{[0-9]+}}(%esp), %esi
|
||
|
|
; X86-NEXT: cmovbl %ebx, %esi
|
||
|
|
; X86-NEXT: subl {{[0-9]+}}(%esp), %edx
|
||
|
|
; X86-NEXT: cmovbl %ebx, %edx
|
||
|
|
; X86-NEXT: subl {{[0-9]+}}(%esp), %ecx
|
||
|
|
; X86-NEXT: cmovbl %ebx, %ecx
|
||
|
|
; X86-NEXT: movl %ecx, 12(%eax)
|
||
|
|
; X86-NEXT: movl %edx, 8(%eax)
|
||
|
|
; X86-NEXT: movl %esi, 4(%eax)
|
||
|
|
; X86-NEXT: movl %edi, (%eax)
|
||
|
|
; X86-NEXT: popl %esi
|
||
|
|
; X86-NEXT: popl %edi
|
||
|
|
; X86-NEXT: popl %ebx
|
||
|
|
; X86-NEXT: retl $4
|
||
|
|
;
|
||
|
|
; X64-LABEL: vec:
|
||
|
|
; X64: # %bb.0:
|
||
|
|
; X64-NEXT: movdqa {{.*#+}} xmm2 = [2147483648,2147483648,2147483648,2147483648]
|
||
|
|
; X64-NEXT: movdqa %xmm1, %xmm3
|
||
|
|
; X64-NEXT: pxor %xmm2, %xmm3
|
||
|
|
; X64-NEXT: pxor %xmm0, %xmm2
|
||
|
|
; X64-NEXT: pcmpgtd %xmm3, %xmm2
|
||
|
|
; X64-NEXT: psubd %xmm1, %xmm0
|
||
|
|
; X64-NEXT: pand %xmm2, %xmm0
|
||
|
|
; X64-NEXT: retq
|
||
|
|
%tmp = call <4 x i32> @llvm.usub.sat.v4i32(<4 x i32> %x, <4 x i32> %y)
|
||
|
|
ret <4 x i32> %tmp
|
||
|
|
}
|