maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/llvm/test/CodeGen/X86/sadd_sat.ll

268 lines
9.2 KiB
LLVM
Raw Normal View History

[Intrinsic] Signed Saturation Addition Intrinsic Add an intrinsic that takes 2 integers and perform saturation addition on them. This is a part of implementing fixed point arithmetic in clang where some of the more complex operations will be implemented as intrinsics. Differential Revision: https://reviews.llvm.org/D53053 llvm-svn: 344629
2018-10-17 01:35:41 +08:00
; 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;
}