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
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
|
; RUN: llc < %s -mtriple=thumbv7-apple-ios -mcpu=cortex-a8 -regalloc=fast -optimize-regalloc=0 | FileCheck %s -check-prefix=A8 -check-prefix=CHECK
; RUN: llc < %s -mtriple=thumbv7-apple-ios -mcpu=cortex-m3 -regalloc=fast -optimize-regalloc=0 | FileCheck %s -check-prefix=M3 -check-prefix=CHECK
; rdar://6949835
; RUN: llc < %s -mtriple=thumbv7-apple-ios -mcpu=cortex-a8 -regalloc=basic | FileCheck %s -check-prefix=BASIC -check-prefix=CHECK
; RUN: llc < %s -mtriple=thumbv7-apple-ios -mcpu=cortex-a8 -regalloc=greedy | FileCheck %s -check-prefix=GREEDY -check-prefix=CHECK
; RUN: llc < %s -mtriple=thumbv7-apple-ios -mcpu=swift | FileCheck %s -check-prefix=SWIFT -check-prefix=CHECK
; Magic ARM pair hints works best with linearscan / fast.
@b = external global i64*
; We use the following two to force values into specific registers.
declare i64* @get_ptr()
declare void @use_i64(i64 %v)
define void @test_ldrd(i64 %a) nounwind readonly {
; CHECK-LABEL: test_ldrd:
; CHECK: bl{{x?}} _get_ptr
; A8: ldrd r0, r1, [r0]
; Cortex-M3 errata 602117: LDRD with base in list may result in incorrect base
; register when interrupted or faulted.
; M3-NOT: ldrd r[[REGNUM:[0-9]+]], {{r[0-9]+}}, [r[[REGNUM]]]
; CHECK: bl{{x?}} _use_i64
%ptr = call i64* @get_ptr()
%v = load i64, i64* %ptr, align 8
call void @use_i64(i64 %v)
ret void
}
; rdar://10435045 mixed LDRi8/LDRi12
;
; In this case, LSR generate a sequence of LDRi8/LDRi12. We should be
; able to generate an LDRD pair here, but this is highly sensitive to
; regalloc hinting. So, this doubles as a register allocation
; test. RABasic currently does a better job within the inner loop
; because of its *lack* of hinting ability. Whereas RAGreedy keeps
; R0/R1/R2 live as the three arguments, forcing the LDRD's odd
; destination into R3. We then sensibly split LDRD again rather then
; evict another live range or use callee saved regs. Sorry if the test
; is sensitive to Regalloc changes, but it is an interesting case.
;
; BASIC: @f
; BASIC: %bb
; BASIC: ldrd
; BASIC: str
; GREEDY: @f
; GREEDY: %bb
; GREEDY: ldrd
; GREEDY: str
define void @f(i32* nocapture %a, i32* nocapture %b, i32 %n) nounwind {
entry:
%0 = add nsw i32 %n, -1 ; <i32> [#uses=2]
%1 = icmp sgt i32 %0, 0 ; <i1> [#uses=1]
br i1 %1, label %bb, label %return
bb: ; preds = %bb, %entry
%i.03 = phi i32 [ %tmp, %bb ], [ 0, %entry ] ; <i32> [#uses=3]
%scevgep = getelementptr i32, i32* %a, i32 %i.03 ; <i32*> [#uses=1]
%scevgep4 = getelementptr i32, i32* %b, i32 %i.03 ; <i32*> [#uses=1]
%tmp = add i32 %i.03, 1 ; <i32> [#uses=3]
%scevgep5 = getelementptr i32, i32* %a, i32 %tmp ; <i32*> [#uses=1]
%2 = load i32, i32* %scevgep, align 4 ; <i32> [#uses=1]
%3 = load i32, i32* %scevgep5, align 4 ; <i32> [#uses=1]
%4 = add nsw i32 %3, %2 ; <i32> [#uses=1]
store i32 %4, i32* %scevgep4, align 4
%exitcond = icmp eq i32 %tmp, %0 ; <i1> [#uses=1]
br i1 %exitcond, label %return, label %bb
return: ; preds = %bb, %entry
ret void
}
; rdar://13978317
; Pair of loads not formed when lifetime markers are set.
%struct.Test = type { i32, i32, i32 }
@TestVar = external global %struct.Test
define void @Func1() nounwind ssp {
; CHECK: @Func1
entry:
; A8: movw [[BASE:r[0-9]+]], :lower16:{{.*}}TestVar{{.*}}
; A8: movt [[BASE]], :upper16:{{.*}}TestVar{{.*}}
; A8: ldrd [[FIELD1:r[0-9]+]], [[FIELD2:r[0-9]+]], {{\[}}[[BASE]], #4]
; A8-NEXT: add [[FIELD1]], [[FIELD2]]
; A8-NEXT: str [[FIELD1]], {{\[}}[[BASE]]{{\]}}
%orig_blocks = alloca [256 x i16], align 2
%0 = bitcast [256 x i16]* %orig_blocks to i8*call void @llvm.lifetime.start(i64 512, i8* %0) nounwind
%tmp1 = load i32, i32* getelementptr inbounds (%struct.Test, %struct.Test* @TestVar, i32 0, i32 1), align 4
%tmp2 = load i32, i32* getelementptr inbounds (%struct.Test, %struct.Test* @TestVar, i32 0, i32 2), align 4
%add = add nsw i32 %tmp2, %tmp1
store i32 %add, i32* getelementptr inbounds (%struct.Test, %struct.Test* @TestVar, i32 0, i32 0), align 4
call void @llvm.lifetime.end(i64 512, i8* %0) nounwind
ret void
}
declare void @extfunc(i32, i32, i32, i32)
; CHECK-LABEL: Func2:
; A8: ldrd
; A8: blx
; A8: pop
define void @Func2(i32* %p) {
entry:
%addr0 = getelementptr i32, i32* %p, i32 0
%addr1 = getelementptr i32, i32* %p, i32 1
%v0 = load i32, i32* %addr0
%v1 = load i32, i32* %addr1
; try to force %v0/%v1 into non-adjacent registers
call void @extfunc(i32 %v0, i32 0, i32 0, i32 %v1)
ret void
}
; CHECK-LABEL: strd_spill_ldrd_reload:
; A8: strd r1, r0, [sp, #-8]!
; M3: strd r1, r0, [sp, #-8]!
; BASIC: strd r1, r0, [sp, #-8]!
; GREEDY: strd r0, r1, [sp, #-8]!
; CHECK: @ InlineAsm Start
; CHECK: @ InlineAsm End
; A8: ldrd r2, r1, [sp]
; M3: ldrd r2, r1, [sp]
; BASIC: ldrd r2, r1, [sp]
; GREEDY: ldrd r1, r2, [sp]
; CHECK: bl{{x?}} _extfunc
define void @strd_spill_ldrd_reload(i32 %v0, i32 %v1) {
; force %v0 and %v1 to be spilled
call void asm sideeffect "", "~{r0},~{r1},~{r2},~{r3},~{r4},~{r5},~{r6},~{r7},~{r8},~{r9},~{r10},~{r11},~{r12},~{lr}"()
; force the reloaded %v0, %v1 into different registers
call void @extfunc(i32 0, i32 %v0, i32 %v1, i32 7)
ret void
}
declare void @extfunc2(i32*, i32, i32)
; CHECK-LABEL: ldrd_postupdate_dec:
; CHECK: ldrd r1, r2, [r0], #-8
; CHECK-NEXT: bl{{x?}} _extfunc
define void @ldrd_postupdate_dec(i32* %p0) {
%p0.1 = getelementptr i32, i32* %p0, i32 1
%v0 = load i32, i32* %p0
%v1 = load i32, i32* %p0.1
%p1 = getelementptr i32, i32* %p0, i32 -2
call void @extfunc2(i32* %p1, i32 %v0, i32 %v1)
ret void
}
; CHECK-LABEL: ldrd_postupdate_inc:
; CHECK: ldrd r1, r2, [r0], #8
; CHECK-NEXT: bl{{x?}} _extfunc
define void @ldrd_postupdate_inc(i32* %p0) {
%p0.1 = getelementptr i32, i32* %p0, i32 1
%v0 = load i32, i32* %p0
%v1 = load i32, i32* %p0.1
%p1 = getelementptr i32, i32* %p0, i32 2
call void @extfunc2(i32* %p1, i32 %v0, i32 %v1)
ret void
}
; CHECK-LABEL: strd_postupdate_dec:
; CHECK: strd r1, r2, [r0], #-8
; CHECK-NEXT: bx lr
define i32* @strd_postupdate_dec(i32* %p0, i32 %v0, i32 %v1) {
%p0.1 = getelementptr i32, i32* %p0, i32 1
store i32 %v0, i32* %p0
store i32 %v1, i32* %p0.1
%p1 = getelementptr i32, i32* %p0, i32 -2
ret i32* %p1
}
; CHECK-LABEL: strd_postupdate_inc:
; CHECK: strd r1, r2, [r0], #8
; CHECK-NEXT: bx lr
define i32* @strd_postupdate_inc(i32* %p0, i32 %v0, i32 %v1) {
%p0.1 = getelementptr i32, i32* %p0, i32 1
store i32 %v0, i32* %p0
store i32 %v1, i32* %p0.1
%p1 = getelementptr i32, i32* %p0, i32 2
ret i32* %p1
}
declare void @llvm.lifetime.start(i64, i8* nocapture) nounwind
declare void @llvm.lifetime.end(i64, i8* nocapture) nounwind
|
