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
|
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -mcpu=pwr9 -verify-machineinstrs -ppc-asm-full-reg-names \
; RUN: -mtriple=powerpc64le-unknown-linux-gnu < %s | FileCheck %s --check-prefix=P9LE
; RUN: llc -mcpu=pwr9 -verify-machineinstrs -ppc-asm-full-reg-names \
; RUN: -mtriple=powerpc64-unknown-linux-gnu < %s | FileCheck %s --check-prefix=P9BE
; RUN: llc -mcpu=pwr8 -verify-machineinstrs -ppc-asm-full-reg-names \
; RUN: -mtriple=powerpc64le-unknown-linux-gnu < %s | FileCheck %s --check-prefix=P8LE
; RUN: llc -mcpu=pwr8 -verify-machineinstrs -ppc-asm-full-reg-names \
; RUN: -mtriple=powerpc64-unknown-linux-gnu < %s | FileCheck %s --check-prefix=P8BE
declare ppc_fp128 @llvm.fmuladd.ppcf128(ppc_fp128, ppc_fp128, ppc_fp128) #2
define ppc_fp128 @test_ctr0() {
; P9LE-LABEL: test_ctr0:
; P9LE: # %bb.0: # %bb
; P9LE-NEXT: mflr r0
; P9LE-NEXT: .cfi_def_cfa_offset 48
; P9LE-NEXT: .cfi_offset lr, 16
; P9LE-NEXT: .cfi_offset r30, -16
; P9LE-NEXT: std r30, -16(r1) # 8-byte Folded Spill
; P9LE-NEXT: stdu r1, -48(r1)
; P9LE-NEXT: li r3, 1
; P9LE-NEXT: xxlxor f1, f1, f1
; P9LE-NEXT: xxlxor f2, f2, f2
; P9LE-NEXT: std r0, 64(r1)
; P9LE-NEXT: rldic r30, r3, 62, 1
; P9LE-NEXT: .p2align 5
; P9LE-NEXT: .LBB0_1: # %bb6
; P9LE-NEXT: #
; P9LE-NEXT: xxlxor f3, f3, f3
; P9LE-NEXT: xxlxor f4, f4, f4
; P9LE-NEXT: bl __gcc_qadd
; P9LE-NEXT: nop
; P9LE-NEXT: addi r30, r30, -1
; P9LE-NEXT: cmpldi r30, 0
; P9LE-NEXT: bc 12, gt, .LBB0_1
; P9LE-NEXT: # %bb.2: # %bb14
; P9LE-NEXT: addi r1, r1, 48
; P9LE-NEXT: ld r0, 16(r1)
; P9LE-NEXT: ld r30, -16(r1) # 8-byte Folded Reload
; P9LE-NEXT: mtlr r0
; P9LE-NEXT: blr
;
; P9BE-LABEL: test_ctr0:
; P9BE: # %bb.0: # %bb
; P9BE-NEXT: mflr r0
; P9BE-NEXT: stdu r1, -128(r1)
; P9BE-NEXT: std r0, 144(r1)
; P9BE-NEXT: .cfi_def_cfa_offset 128
; P9BE-NEXT: .cfi_offset lr, 16
; P9BE-NEXT: .cfi_offset r30, -16
; P9BE-NEXT: li r3, 1
; P9BE-NEXT: std r30, 112(r1) # 8-byte Folded Spill
; P9BE-NEXT: xxlxor f1, f1, f1
; P9BE-NEXT: rldic r30, r3, 62, 1
; P9BE-NEXT: xxlxor f2, f2, f2
; P9BE-NEXT: .p2align 5
; P9BE-NEXT: .LBB0_1: # %bb6
; P9BE-NEXT: #
; P9BE-NEXT: xxlxor f3, f3, f3
; P9BE-NEXT: xxlxor f4, f4, f4
; P9BE-NEXT: bl __gcc_qadd
; P9BE-NEXT: nop
; P9BE-NEXT: addi r30, r30, -1
; P9BE-NEXT: cmpldi r30, 0
; P9BE-NEXT: bc 12, gt, .LBB0_1
; P9BE-NEXT: # %bb.2: # %bb14
; P9BE-NEXT: ld r30, 112(r1) # 8-byte Folded Reload
; P9BE-NEXT: addi r1, r1, 128
; P9BE-NEXT: ld r0, 16(r1)
; P9BE-NEXT: mtlr r0
; P9BE-NEXT: blr
;
; P8LE-LABEL: test_ctr0:
; P8LE: # %bb.0: # %bb
; P8LE-NEXT: mflr r0
; P8LE-NEXT: .cfi_def_cfa_offset 48
; P8LE-NEXT: .cfi_offset lr, 16
; P8LE-NEXT: .cfi_offset r30, -16
; P8LE-NEXT: std r30, -16(r1) # 8-byte Folded Spill
; P8LE-NEXT: stdu r1, -48(r1)
; P8LE-NEXT: xxlxor f1, f1, f1
; P8LE-NEXT: li r3, 1
; P8LE-NEXT: std r0, 64(r1)
; P8LE-NEXT: xxlxor f2, f2, f2
; P8LE-NEXT: rldic r30, r3, 62, 1
; P8LE-NEXT: .p2align 5
; P8LE-NEXT: .LBB0_1: # %bb6
; P8LE-NEXT: #
; P8LE-NEXT: xxlxor f3, f3, f3
; P8LE-NEXT: xxlxor f4, f4, f4
; P8LE-NEXT: bl __gcc_qadd
; P8LE-NEXT: nop
; P8LE-NEXT: addi r30, r30, -1
; P8LE-NEXT: cmpldi r30, 0
; P8LE-NEXT: bc 12, gt, .LBB0_1
; P8LE-NEXT: # %bb.2: # %bb14
; P8LE-NEXT: addi r1, r1, 48
; P8LE-NEXT: ld r0, 16(r1)
; P8LE-NEXT: ld r30, -16(r1) # 8-byte Folded Reload
; P8LE-NEXT: mtlr r0
; P8LE-NEXT: blr
;
; P8BE-LABEL: test_ctr0:
; P8BE: # %bb.0: # %bb
; P8BE-NEXT: mflr r0
; P8BE-NEXT: stdu r1, -128(r1)
; P8BE-NEXT: std r0, 144(r1)
; P8BE-NEXT: .cfi_def_cfa_offset 128
; P8BE-NEXT: .cfi_offset lr, 16
; P8BE-NEXT: .cfi_offset r30, -16
; P8BE-NEXT: xxlxor f1, f1, f1
; P8BE-NEXT: li r3, 1
; P8BE-NEXT: std r30, 112(r1) # 8-byte Folded Spill
; P8BE-NEXT: xxlxor f2, f2, f2
; P8BE-NEXT: rldic r30, r3, 62, 1
; P8BE-NEXT: .p2align 5
; P8BE-NEXT: .LBB0_1: # %bb6
; P8BE-NEXT: #
; P8BE-NEXT: xxlxor f3, f3, f3
; P8BE-NEXT: xxlxor f4, f4, f4
; P8BE-NEXT: bl __gcc_qadd
; P8BE-NEXT: nop
; P8BE-NEXT: addi r30, r30, -1
; P8BE-NEXT: cmpldi r30, 0
; P8BE-NEXT: bc 12, gt, .LBB0_1
; P8BE-NEXT: # %bb.2: # %bb14
; P8BE-NEXT: ld r30, 112(r1) # 8-byte Folded Reload
; P8BE-NEXT: addi r1, r1, 128
; P8BE-NEXT: ld r0, 16(r1)
; P8BE-NEXT: mtlr r0
; P8BE-NEXT: blr
bb:
br label %bb6
bb6: ; preds = %bb6, %bb
%i = phi ppc_fp128 [ %i8, %bb6 ], [ 0xM00000000000000000000000000000000, %bb ]
%i7 = phi i64 [ %i9, %bb6 ], [ 0, %bb ]
%i8 = tail call ppc_fp128 @llvm.fmuladd.ppcf128(ppc_fp128 0xM00000000000000000000000000000000, ppc_fp128 0xM00000000000000000000000000000000, ppc_fp128 %i) #4
%i9 = add i64 %i7, -4
%i10 = icmp eq i64 %i9, 0
br i1 %i10, label %bb14, label %bb6
bb14: ; preds = %bb6
ret ppc_fp128 %i8
}
|
