1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
| ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -mtriple=i686-unknown-linux-gnu < %s | FileCheck %s --check-prefixes=CHECK,X86
; RUN: llc -mtriple=x86_64-unknown-linux-gnu < %s | FileCheck %s --check-prefixes=CHECK,X64
; On X86, division in expensive. BuildRemEqFold should therefore run even
; when optimizing for size. Only optimizing for minimum size retains a plain div.
define i32 @test_minsize(i32 %X) optsize minsize nounwind readnone {
; X86-LABEL: test_minsize:
; X86: # %bb.0:
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax
; X86-NEXT: pushl $5
; X86-NEXT: popl %ecx
; X86-NEXT: xorl %edx, %edx
; X86-NEXT: divl %ecx
; X86-NEXT: testl %edx, %edx
; X86-NEXT: je .LBB0_1
; X86-NEXT: # %bb.2:
; X86-NEXT: pushl $-10
; X86-NEXT: popl %eax
; X86-NEXT: retl
; X86-NEXT: .LBB0_1:
; X86-NEXT: pushl $42
; X86-NEXT: popl %eax
; X86-NEXT: retl
;
; X64-LABEL: test_minsize:
; X64: # %bb.0:
; X64-NEXT: movl %edi, %eax
; X64-NEXT: pushq $5
; X64-NEXT: popq %rcx
; X64-NEXT: xorl %edx, %edx
; X64-NEXT: divl %ecx
; X64-NEXT: testl %edx, %edx
; X64-NEXT: pushq $42
; X64-NEXT: popq %rcx
; X64-NEXT: pushq $-10
; X64-NEXT: popq %rax
; X64-NEXT: cmovel %ecx, %eax
; X64-NEXT: retq
%rem = urem i32 %X, 5
%cmp = icmp eq i32 %rem, 0
%ret = select i1 %cmp, i32 42, i32 -10
ret i32 %ret
}
define i32 @test_optsize(i32 %X) optsize nounwind readnone {
; X86-LABEL: test_optsize:
; X86: # %bb.0:
; X86-NEXT: imull $-858993459, {{[0-9]+}}(%esp), %eax # imm = 0xCCCCCCCD
; X86-NEXT: cmpl $858993460, %eax # imm = 0x33333334
; X86-NEXT: movl $42, %eax
; X86-NEXT: jb .LBB1_2
; X86-NEXT: # %bb.1:
; X86-NEXT: movl $-10, %eax
; X86-NEXT: .LBB1_2:
; X86-NEXT: retl
;
; X64-LABEL: test_optsize:
; X64: # %bb.0:
; X64-NEXT: imull $-858993459, %edi, %eax # imm = 0xCCCCCCCD
; X64-NEXT: cmpl $858993460, %eax # imm = 0x33333334
; X64-NEXT: movl $42, %ecx
; X64-NEXT: movl $-10, %eax
; X64-NEXT: cmovbl %ecx, %eax
; X64-NEXT: retq
%rem = urem i32 %X, 5
%cmp = icmp eq i32 %rem, 0
%ret = select i1 %cmp, i32 42, i32 -10
ret i32 %ret
}
|