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
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
|
; RUN: llc -verify-machineinstrs -mcpu=ppc64 < %s | FileCheck %s -check-prefix=GENERIC
; RUN: llc -verify-machineinstrs -mcpu=970 < %s | FileCheck %s -check-prefix=PWR
; RUN: llc -verify-machineinstrs -mcpu=a2 < %s | FileCheck %s -check-prefix=BASIC
; RUN: llc -verify-machineinstrs -mcpu=e500mc < %s | FileCheck %s -check-prefix=BASIC
; RUN: llc -verify-machineinstrs -mcpu=e5500 < %s | FileCheck %s -check-prefix=BASIC
; RUN: llc -verify-machineinstrs -mcpu=pwr4 < %s | FileCheck %s -check-prefix=PWR
; RUN: llc -verify-machineinstrs -mcpu=pwr5 < %s | FileCheck %s -check-prefix=PWR
; RUN: llc -verify-machineinstrs -mcpu=pwr5x < %s | FileCheck %s -check-prefix=PWR
; RUN: llc -verify-machineinstrs -mcpu=pwr6 < %s | FileCheck %s -check-prefix=PWR
; RUN: llc -verify-machineinstrs -mcpu=pwr6x < %s | FileCheck %s -check-prefix=PWR
; RUN: llc -verify-machineinstrs -mcpu=pwr7 < %s | FileCheck %s -check-prefix=PWR
; RUN: llc -verify-machineinstrs -mcpu=pwr8 < %s | FileCheck %s -check-prefix=PWR
target datalayout = "E-m:e-i64:64-n32:64"
target triple = "powerpc64-unknown-linux-gnu"
; Function Attrs: nounwind readnone
define signext i32 @foo(i32 signext %x) #0 {
entry:
%mul = shl nsw i32 %x, 1
ret i32 %mul
; GENERIC-LABEL: .globl foo
; BASIC-LABEL: .globl foo
; PWR-LABEL: .globl foo
; GENERIC: .p2align 2
; BASIC: .p2align 4
; PWR: .p2align 4
; GENERIC: @foo
; BASIC: @foo
; PWR: @foo
}
; Function Attrs: nounwind
define void @loop(i32 signext %x, i32* nocapture %a) #1 {
entry:
br label %vector.body
; GENERIC-LABEL: @loop
; BASIC-LABEL: @loop
; PWR-LABEL: @loop
; GENERIC: mtctr
; BASIC: mtctr
; PWR: mtctr
; GENERIC-NOT: .p2align
; BASIC: .p2align 4
; PWR: .p2align 4
; GENERIC: lwzu
; BASIC: lwzu
; PWR: lwzu
; GENERIC: bdnz
; BASIC: bdnz
; PWR: bdnz
vector.body: ; preds = %vector.body, %entry
%index = phi i64 [ 0, %entry ], [ %index.next, %vector.body ]
%induction45 = or i64 %index, 1
%0 = getelementptr inbounds i32, i32* %a, i64 %index
%1 = getelementptr inbounds i32, i32* %a, i64 %induction45
%2 = load i32, i32* %0, align 4
%3 = load i32, i32* %1, align 4
%4 = add nsw i32 %2, 4
%5 = add nsw i32 %3, 4
%6 = mul nsw i32 %4, 3
%7 = mul nsw i32 %5, 3
store i32 %6, i32* %0, align 4
store i32 %7, i32* %1, align 4
%index.next = add i64 %index, 2
%8 = icmp eq i64 %index.next, 2048
br i1 %8, label %for.end, label %vector.body
for.end: ; preds = %vector.body
ret void
}
; Function Attrs: nounwind
define void @sloop(i32 signext %x, i32* nocapture %a) #1 {
entry:
br label %for.body
; GENERIC-LABEL: @sloop
; BASIC-LABEL: @sloop
; PWR-LABEL: @sloop
; GENERIC: mtctr
; BASIC: mtctr
; PWR: mtctr
; GENERIC-NOT: .p2align
; BASIC: .p2align 4
; PWR: .p2align 5
; GENERIC: bdnz
; BASIC: bdnz
; PWR: bdnz
for.body: ; preds = %for.body, %entry
%indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
%arrayidx = getelementptr inbounds i32, i32* %a, i64 %indvars.iv
%0 = load i32, i32* %arrayidx, align 4
%add = add nsw i32 %0, 4
%mul = mul nsw i32 %add, 3
store i32 %mul, i32* %arrayidx, align 4
%indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
%exitcond = icmp eq i64 %indvars.iv.next, 2048
br i1 %exitcond, label %for.end, label %for.body
for.end: ; preds = %for.body
ret void
}
; Function Attrs: nounwind
define void @test_minsize(i32 signext %x, i32* nocapture %a) #2 {
entry:
br label %vector.body
; GENERIC-LABEL: @test_minsize
; BASIC-LABEL: @test_minsize
; PWR-LABEL: @test_minsize
; GENERIC: mtctr
; BASIC: mtctr
; PWR: mtctr
; GENERIC-NOT: .p2align
; BASIC-NOT: .p2align
; PWR-NOT: .p2align
; GENERIC: lwzu
; BASIC: lwzu
; PWR: lwzu
; GENERIC: bdnz
; BASIC: bdnz
; PWR: bdnz
vector.body: ; preds = %vector.body, %entry
%index = phi i64 [ 0, %entry ], [ %index.next, %vector.body ]
%induction45 = or i64 %index, 1
%0 = getelementptr inbounds i32, i32* %a, i64 %index
%1 = getelementptr inbounds i32, i32* %a, i64 %induction45
%2 = load i32, i32* %0, align 4
%3 = load i32, i32* %1, align 4
%4 = add nsw i32 %2, 4
%5 = add nsw i32 %3, 4
%6 = mul nsw i32 %4, 3
%7 = mul nsw i32 %5, 3
store i32 %6, i32* %0, align 4
store i32 %7, i32* %1, align 4
%index.next = add i64 %index, 2
%8 = icmp eq i64 %index.next, 2048
br i1 %8, label %for.end, label %vector.body
for.end: ; preds = %vector.body
ret void
}
attributes #0 = { nounwind readnone }
attributes #1 = { nounwind }
attributes #2 = { nounwind minsize}
|