--- /dev/null
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: llc < %s -mcpu=generic -mtriple=x86_64-linux | FileCheck %s
+; RUN: llc < %s -mcpu=generic -mtriple=i686 -mattr=cmov | FileCheck %s --check-prefix=CHECK32
+
+declare i4 @llvm.sadd.sat.i4 (i4, i4)
+declare i32 @llvm.sadd.sat.i32 (i32, i32)
+declare i64 @llvm.sadd.sat.i64 (i64, i64)
+declare <4 x i32> @llvm.sadd.sat.v4i32(<4 x i32>, <4 x i32>)
+
+define i32 @func(i32 %x, i32 %y) {
+; CHECK-LABEL: func:
+; CHECK: # %bb.0:
+; CHECK-NEXT: xorl %eax, %eax
+; CHECK-NEXT: movl %edi, %ecx
+; CHECK-NEXT: addl %esi, %ecx
+; CHECK-NEXT: setns %al
+; CHECK-NEXT: addl $2147483647, %eax # imm = 0x7FFFFFFF
+; CHECK-NEXT: addl %esi, %edi
+; CHECK-NEXT: cmovnol %edi, %eax
+; CHECK-NEXT: retq
+;
+; CHECK32-LABEL: func:
+; CHECK32: # %bb.0:
+; CHECK32-NEXT: pushl %esi
+; CHECK32-NEXT: .cfi_def_cfa_offset 8
+; CHECK32-NEXT: .cfi_offset %esi, -8
+; CHECK32-NEXT: movl {{[0-9]+}}(%esp), %eax
+; CHECK32-NEXT: movl {{[0-9]+}}(%esp), %edx
+; CHECK32-NEXT: xorl %ecx, %ecx
+; CHECK32-NEXT: movl %eax, %esi
+; CHECK32-NEXT: addl %edx, %esi
+; CHECK32-NEXT: setns %cl
+; CHECK32-NEXT: addl $2147483647, %ecx # imm = 0x7FFFFFFF
+; CHECK32-NEXT: addl %edx, %eax
+; CHECK32-NEXT: cmovol %ecx, %eax
+; CHECK32-NEXT: popl %esi
+; CHECK32-NEXT: .cfi_def_cfa_offset 4
+; CHECK32-NEXT: retl
+ %tmp = call i32 @llvm.sadd.sat.i32(i32 %x, i32 %y);
+ ret i32 %tmp;
+}
+
+define i64 @func2(i64 %x, i64 %y) {
+; CHECK-LABEL: func2:
+; CHECK: # %bb.0:
+; CHECK-NEXT: xorl %ecx, %ecx
+; CHECK-NEXT: movq %rdi, %rax
+; CHECK-NEXT: addq %rsi, %rax
+; CHECK-NEXT: setns %cl
+; CHECK-NEXT: movabsq $9223372036854775807, %rax # imm = 0x7FFFFFFFFFFFFFFF
+; CHECK-NEXT: addq %rcx, %rax
+; CHECK-NEXT: addq %rsi, %rdi
+; CHECK-NEXT: cmovnoq %rdi, %rax
+; CHECK-NEXT: retq
+;
+; CHECK32-LABEL: func2:
+; CHECK32: # %bb.0:
+; CHECK32-NEXT: pushl %ebp
+; CHECK32-NEXT: .cfi_def_cfa_offset 8
+; CHECK32-NEXT: pushl %ebx
+; CHECK32-NEXT: .cfi_def_cfa_offset 12
+; CHECK32-NEXT: pushl %edi
+; CHECK32-NEXT: .cfi_def_cfa_offset 16
+; CHECK32-NEXT: pushl %esi
+; CHECK32-NEXT: .cfi_def_cfa_offset 20
+; CHECK32-NEXT: .cfi_offset %esi, -20
+; CHECK32-NEXT: .cfi_offset %edi, -16
+; CHECK32-NEXT: .cfi_offset %ebx, -12
+; CHECK32-NEXT: .cfi_offset %ebp, -8
+; CHECK32-NEXT: movl {{[0-9]+}}(%esp), %esi
+; CHECK32-NEXT: movl {{[0-9]+}}(%esp), %edi
+; CHECK32-NEXT: movl {{[0-9]+}}(%esp), %ebx
+; CHECK32-NEXT: addl {{[0-9]+}}(%esp), %edi
+; CHECK32-NEXT: movl %ebx, %ebp
+; CHECK32-NEXT: adcl %esi, %ebp
+; CHECK32-NEXT: movl %ebp, %eax
+; CHECK32-NEXT: sarl $31, %eax
+; CHECK32-NEXT: xorl %ecx, %ecx
+; CHECK32-NEXT: testl %ebp, %ebp
+; CHECK32-NEXT: setns %cl
+; CHECK32-NEXT: movl %ecx, %edx
+; CHECK32-NEXT: addl $2147483647, %edx # imm = 0x7FFFFFFF
+; CHECK32-NEXT: testl %ebx, %ebx
+; CHECK32-NEXT: setns %bl
+; CHECK32-NEXT: cmpb %cl, %bl
+; CHECK32-NEXT: setne %cl
+; CHECK32-NEXT: testl %esi, %esi
+; CHECK32-NEXT: setns %ch
+; CHECK32-NEXT: cmpb %ch, %bl
+; CHECK32-NEXT: sete %ch
+; CHECK32-NEXT: testb %cl, %ch
+; CHECK32-NEXT: cmovel %ebp, %edx
+; CHECK32-NEXT: cmovel %edi, %eax
+; CHECK32-NEXT: popl %esi
+; CHECK32-NEXT: .cfi_def_cfa_offset 16
+; CHECK32-NEXT: popl %edi
+; CHECK32-NEXT: .cfi_def_cfa_offset 12
+; CHECK32-NEXT: popl %ebx
+; CHECK32-NEXT: .cfi_def_cfa_offset 8
+; CHECK32-NEXT: popl %ebp
+; CHECK32-NEXT: .cfi_def_cfa_offset 4
+; CHECK32-NEXT: retl
+ %tmp = call i64 @llvm.sadd.sat.i64(i64 %x, i64 %y);
+ ret i64 %tmp;
+}
+
+define i4 @func3(i4 %x, i4 %y) {
+; CHECK-LABEL: func3:
+; CHECK: # %bb.0:
+; CHECK-NEXT: movl %edi, %eax
+; CHECK-NEXT: shlb $4, %sil
+; CHECK-NEXT: shlb $4, %al
+; CHECK-NEXT: movl %eax, %ecx
+; CHECK-NEXT: addb %sil, %cl
+; CHECK-NEXT: setns %cl
+; CHECK-NEXT: addb %sil, %al
+; CHECK-NEXT: jno .LBB2_2
+; CHECK-NEXT: # %bb.1:
+; CHECK-NEXT: addb $127, %cl
+; CHECK-NEXT: movl %ecx, %eax
+; CHECK-NEXT: .LBB2_2:
+; CHECK-NEXT: sarb $4, %al
+; CHECK-NEXT: # kill: def $al killed $al killed $eax
+; CHECK-NEXT: retq
+;
+; CHECK32-LABEL: func3:
+; CHECK32: # %bb.0:
+; CHECK32-NEXT: movb {{[0-9]+}}(%esp), %al
+; CHECK32-NEXT: movb {{[0-9]+}}(%esp), %dl
+; CHECK32-NEXT: shlb $4, %dl
+; CHECK32-NEXT: shlb $4, %al
+; CHECK32-NEXT: movl %eax, %ecx
+; CHECK32-NEXT: addb %dl, %cl
+; CHECK32-NEXT: setns %cl
+; CHECK32-NEXT: addb %dl, %al
+; CHECK32-NEXT: jno .LBB2_2
+; CHECK32-NEXT: # %bb.1:
+; CHECK32-NEXT: addb $127, %cl
+; CHECK32-NEXT: movl %ecx, %eax
+; CHECK32-NEXT: .LBB2_2:
+; CHECK32-NEXT: sarb $4, %al
+; CHECK32-NEXT: retl
+ %tmp = call i4 @llvm.sadd.sat.i4(i4 %x, i4 %y);
+ ret i4 %tmp;
+}
+
+define <4 x i32> @vec(<4 x i32> %x, <4 x i32> %y) {
+; CHECK-LABEL: vec:
+; CHECK: # %bb.0:
+; CHECK-NEXT: pshufd {{.*#+}} xmm2 = xmm1[1,1,2,3]
+; CHECK-NEXT: movd %xmm2, %ecx
+; CHECK-NEXT: pshufd {{.*#+}} xmm2 = xmm0[1,1,2,3]
+; CHECK-NEXT: movd %xmm2, %r8d
+; CHECK-NEXT: xorl %edx, %edx
+; CHECK-NEXT: movl %r8d, %esi
+; CHECK-NEXT: addl %ecx, %esi
+; CHECK-NEXT: setns %dl
+; CHECK-NEXT: addl $2147483647, %edx # imm = 0x7FFFFFFF
+; CHECK-NEXT: addl %ecx, %r8d
+; CHECK-NEXT: cmovol %edx, %r8d
+; CHECK-NEXT: movd %xmm1, %edx
+; CHECK-NEXT: movd %xmm0, %ecx
+; CHECK-NEXT: xorl %esi, %esi
+; CHECK-NEXT: movl %ecx, %edi
+; CHECK-NEXT: addl %edx, %edi
+; CHECK-NEXT: setns %sil
+; CHECK-NEXT: addl $2147483647, %esi # imm = 0x7FFFFFFF
+; CHECK-NEXT: addl %edx, %ecx
+; CHECK-NEXT: cmovol %esi, %ecx
+; CHECK-NEXT: pshufd {{.*#+}} xmm2 = xmm1[2,3,0,1]
+; CHECK-NEXT: movd %xmm2, %edx
+; CHECK-NEXT: pshufd {{.*#+}} xmm2 = xmm0[2,3,0,1]
+; CHECK-NEXT: movd %xmm2, %eax
+; CHECK-NEXT: xorl %edi, %edi
+; CHECK-NEXT: movl %eax, %esi
+; CHECK-NEXT: addl %edx, %esi
+; CHECK-NEXT: setns %dil
+; CHECK-NEXT: addl $2147483647, %edi # imm = 0x7FFFFFFF
+; CHECK-NEXT: addl %edx, %eax
+; CHECK-NEXT: cmovol %edi, %eax
+; CHECK-NEXT: pshufd {{.*#+}} xmm1 = xmm1[3,1,2,3]
+; CHECK-NEXT: movd %xmm1, %r9d
+; CHECK-NEXT: pshufd {{.*#+}} xmm0 = xmm0[3,1,2,3]
+; CHECK-NEXT: movd %xmm0, %edx
+; CHECK-NEXT: xorl %edi, %edi
+; CHECK-NEXT: movl %edx, %esi
+; CHECK-NEXT: addl %r9d, %esi
+; CHECK-NEXT: setns %dil
+; CHECK-NEXT: addl $2147483647, %edi # imm = 0x7FFFFFFF
+; CHECK-NEXT: addl %r9d, %edx
+; CHECK-NEXT: cmovol %edi, %edx
+; CHECK-NEXT: movd %edx, %xmm0
+; CHECK-NEXT: movd %eax, %xmm1
+; CHECK-NEXT: punpckldq {{.*#+}} xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1]
+; CHECK-NEXT: movd %ecx, %xmm0
+; CHECK-NEXT: movd %r8d, %xmm2
+; CHECK-NEXT: punpckldq {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1]
+; CHECK-NEXT: punpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
+; CHECK-NEXT: retq
+;
+; CHECK32-LABEL: vec:
+; CHECK32: # %bb.0:
+; CHECK32-NEXT: pushl %ebp
+; CHECK32-NEXT: .cfi_def_cfa_offset 8
+; CHECK32-NEXT: pushl %ebx
+; CHECK32-NEXT: .cfi_def_cfa_offset 12
+; CHECK32-NEXT: pushl %edi
+; CHECK32-NEXT: .cfi_def_cfa_offset 16
+; CHECK32-NEXT: pushl %esi
+; CHECK32-NEXT: .cfi_def_cfa_offset 20
+; CHECK32-NEXT: .cfi_offset %esi, -20
+; CHECK32-NEXT: .cfi_offset %edi, -16
+; CHECK32-NEXT: .cfi_offset %ebx, -12
+; CHECK32-NEXT: .cfi_offset %ebp, -8
+; CHECK32-NEXT: movl {{[0-9]+}}(%esp), %ecx
+; CHECK32-NEXT: movl {{[0-9]+}}(%esp), %edx
+; CHECK32-NEXT: xorl %eax, %eax
+; CHECK32-NEXT: movl %ecx, %esi
+; CHECK32-NEXT: addl %edx, %esi
+; CHECK32-NEXT: setns %al
+; CHECK32-NEXT: addl $2147483647, %eax # imm = 0x7FFFFFFF
+; CHECK32-NEXT: addl %edx, %ecx
+; CHECK32-NEXT: movl {{[0-9]+}}(%esp), %edx
+; CHECK32-NEXT: cmovol %eax, %ecx
+; CHECK32-NEXT: movl {{[0-9]+}}(%esp), %esi
+; CHECK32-NEXT: xorl %eax, %eax
+; CHECK32-NEXT: movl %edx, %edi
+; CHECK32-NEXT: addl %esi, %edi
+; CHECK32-NEXT: setns %al
+; CHECK32-NEXT: addl $2147483647, %eax # imm = 0x7FFFFFFF
+; CHECK32-NEXT: addl %esi, %edx
+; CHECK32-NEXT: movl {{[0-9]+}}(%esp), %esi
+; CHECK32-NEXT: cmovol %eax, %edx
+; CHECK32-NEXT: movl {{[0-9]+}}(%esp), %edi
+; CHECK32-NEXT: xorl %eax, %eax
+; CHECK32-NEXT: movl %esi, %ebx
+; CHECK32-NEXT: addl %edi, %ebx
+; CHECK32-NEXT: setns %al
+; CHECK32-NEXT: addl $2147483647, %eax # imm = 0x7FFFFFFF
+; CHECK32-NEXT: addl %edi, %esi
+; CHECK32-NEXT: movl {{[0-9]+}}(%esp), %edi
+; CHECK32-NEXT: cmovol %eax, %esi
+; CHECK32-NEXT: movl {{[0-9]+}}(%esp), %eax
+; CHECK32-NEXT: xorl %ebx, %ebx
+; CHECK32-NEXT: movl %edi, %ebp
+; CHECK32-NEXT: addl %eax, %ebp
+; CHECK32-NEXT: setns %bl
+; CHECK32-NEXT: addl $2147483647, %ebx # imm = 0x7FFFFFFF
+; CHECK32-NEXT: addl %eax, %edi
+; CHECK32-NEXT: movl {{[0-9]+}}(%esp), %eax
+; CHECK32-NEXT: cmovol %ebx, %edi
+; CHECK32-NEXT: movl %ecx, 12(%eax)
+; CHECK32-NEXT: movl %edx, 8(%eax)
+; CHECK32-NEXT: movl %esi, 4(%eax)
+; CHECK32-NEXT: movl %edi, (%eax)
+; CHECK32-NEXT: popl %esi
+; CHECK32-NEXT: .cfi_def_cfa_offset 16
+; CHECK32-NEXT: popl %edi
+; CHECK32-NEXT: .cfi_def_cfa_offset 12
+; CHECK32-NEXT: popl %ebx
+; CHECK32-NEXT: .cfi_def_cfa_offset 8
+; CHECK32-NEXT: popl %ebp
+; CHECK32-NEXT: .cfi_def_cfa_offset 4
+; CHECK32-NEXT: retl $4
+ %tmp = call <4 x i32> @llvm.sadd.sat.v4i32(<4 x i32> %x, <4 x i32> %y);
+ ret <4 x i32> %tmp;
+}