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
|
; NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py UTC_ARGS: --version 5
; RUN: llc -global-isel -mtriple=amdgcn-amd-amdhsa -mcpu=hawaii -stop-after=legalizer -o - %s | FileCheck %s
; Test behavior of legalizer when vector loads have range metadata,
; and are lowered by bitcasting to a scalar integer, so we have to
; drop the range metadata.
define <4 x i8> @global_load_v4i8_align4__rangemd(ptr addrspace(1) %ptr) {
; CHECK-LABEL: name: global_load_v4i8_align4__rangemd
; CHECK: bb.1 (%ir-block.0):
; CHECK-NEXT: liveins: $vgpr0, $vgpr1
; CHECK-NEXT: {{ $}}
; CHECK-NEXT: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
; CHECK-NEXT: [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr1
; CHECK-NEXT: [[MV:%[0-9]+]]:_(p1) = G_MERGE_VALUES [[COPY]](s32), [[COPY1]](s32)
; CHECK-NEXT: [[LOAD:%[0-9]+]]:_(s32) = G_LOAD [[MV]](p1) :: (load (s32) from %ir.ptr, addrspace 1)
; CHECK-NEXT: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 8
; CHECK-NEXT: [[LSHR:%[0-9]+]]:_(s32) = G_LSHR [[LOAD]], [[C]](s32)
; CHECK-NEXT: [[C1:%[0-9]+]]:_(s32) = G_CONSTANT i32 16
; CHECK-NEXT: [[LSHR1:%[0-9]+]]:_(s32) = G_LSHR [[LOAD]], [[C1]](s32)
; CHECK-NEXT: [[C2:%[0-9]+]]:_(s32) = G_CONSTANT i32 24
; CHECK-NEXT: [[LSHR2:%[0-9]+]]:_(s32) = G_LSHR [[LOAD]], [[C2]](s32)
; CHECK-NEXT: $vgpr0 = COPY [[LOAD]](s32)
; CHECK-NEXT: $vgpr1 = COPY [[LSHR]](s32)
; CHECK-NEXT: $vgpr2 = COPY [[LSHR1]](s32)
; CHECK-NEXT: $vgpr3 = COPY [[LSHR2]](s32)
; CHECK-NEXT: SI_RETURN implicit $vgpr0, implicit $vgpr1, implicit $vgpr2, implicit $vgpr3
%load = load <4 x i8>, ptr addrspace(1) %ptr, align 4, !range !0, !noundef !1
ret <4 x i8> %load
}
; This is also widened.
define <3 x i8> @global_load_v3i8_align4__rangemd(ptr addrspace(1) %ptr) {
; CHECK-LABEL: name: global_load_v3i8_align4__rangemd
; CHECK: bb.1 (%ir-block.0):
; CHECK-NEXT: liveins: $vgpr0, $vgpr1
; CHECK-NEXT: {{ $}}
; CHECK-NEXT: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
; CHECK-NEXT: [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr1
; CHECK-NEXT: [[MV:%[0-9]+]]:_(p1) = G_MERGE_VALUES [[COPY]](s32), [[COPY1]](s32)
; CHECK-NEXT: [[LOAD:%[0-9]+]]:_(s32) = G_LOAD [[MV]](p1) :: (load (s32) from %ir.ptr, addrspace 1)
; CHECK-NEXT: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 8
; CHECK-NEXT: [[LSHR:%[0-9]+]]:_(s32) = G_LSHR [[LOAD]], [[C]](s32)
; CHECK-NEXT: [[C1:%[0-9]+]]:_(s32) = G_CONSTANT i32 16
; CHECK-NEXT: [[LSHR1:%[0-9]+]]:_(s32) = G_LSHR [[LOAD]], [[C1]](s32)
; CHECK-NEXT: $vgpr0 = COPY [[LOAD]](s32)
; CHECK-NEXT: $vgpr1 = COPY [[LSHR]](s32)
; CHECK-NEXT: $vgpr2 = COPY [[LSHR1]](s32)
; CHECK-NEXT: SI_RETURN implicit $vgpr0, implicit $vgpr1, implicit $vgpr2
%load = load <3 x i8>, ptr addrspace(1) %ptr, align 4, !range !0, !noundef !1
ret <3 x i8> %load
}
define <2 x i8> @global_load_v2i8_align2__rangemd(ptr addrspace(1) %ptr) {
; CHECK-LABEL: name: global_load_v2i8_align2__rangemd
; CHECK: bb.1 (%ir-block.0):
; CHECK-NEXT: liveins: $vgpr0, $vgpr1
; CHECK-NEXT: {{ $}}
; CHECK-NEXT: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
; CHECK-NEXT: [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr1
; CHECK-NEXT: [[MV:%[0-9]+]]:_(p1) = G_MERGE_VALUES [[COPY]](s32), [[COPY1]](s32)
; CHECK-NEXT: [[LOAD:%[0-9]+]]:_(s32) = G_LOAD [[MV]](p1) :: (load (s16) from %ir.ptr, addrspace 1)
; CHECK-NEXT: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 8
; CHECK-NEXT: [[LSHR:%[0-9]+]]:_(s32) = G_LSHR [[LOAD]], [[C]](s32)
; CHECK-NEXT: $vgpr0 = COPY [[LOAD]](s32)
; CHECK-NEXT: $vgpr1 = COPY [[LSHR]](s32)
; CHECK-NEXT: SI_RETURN implicit $vgpr0, implicit $vgpr1
%load = load <2 x i8>, ptr addrspace(1) %ptr, align 2, !range !0, !noundef !1
ret <2 x i8> %load
}
define <2 x i64> @global_load_v2i64_align16__rangemd(ptr addrspace(1) %ptr) {
; CHECK-LABEL: name: global_load_v2i64_align16__rangemd
; CHECK: bb.1 (%ir-block.0):
; CHECK-NEXT: liveins: $vgpr0, $vgpr1
; CHECK-NEXT: {{ $}}
; CHECK-NEXT: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
; CHECK-NEXT: [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr1
; CHECK-NEXT: [[MV:%[0-9]+]]:_(p1) = G_MERGE_VALUES [[COPY]](s32), [[COPY1]](s32)
; CHECK-NEXT: [[LOAD:%[0-9]+]]:_(<2 x s64>) = G_LOAD [[MV]](p1) :: (load (<2 x s64>) from %ir.ptr, !range !2, addrspace 1)
; CHECK-NEXT: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32), [[UV2:%[0-9]+]]:_(s32), [[UV3:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[LOAD]](<2 x s64>)
; CHECK-NEXT: $vgpr0 = COPY [[UV]](s32)
; CHECK-NEXT: $vgpr1 = COPY [[UV1]](s32)
; CHECK-NEXT: $vgpr2 = COPY [[UV2]](s32)
; CHECK-NEXT: $vgpr3 = COPY [[UV3]](s32)
; CHECK-NEXT: SI_RETURN implicit $vgpr0, implicit $vgpr1, implicit $vgpr2, implicit $vgpr3
%load = load <2 x i64>, ptr addrspace(1) %ptr, align 16, !range !2, !noundef !1
ret <2 x i64> %load
}
; This goes the other direction and converts a scalar load to a vector.
define i128 @global_load_i128_align16__rangemd(ptr addrspace(1) %ptr) {
; CHECK-LABEL: name: global_load_i128_align16__rangemd
; CHECK: bb.1 (%ir-block.0):
; CHECK-NEXT: liveins: $vgpr0, $vgpr1
; CHECK-NEXT: {{ $}}
; CHECK-NEXT: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
; CHECK-NEXT: [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr1
; CHECK-NEXT: [[MV:%[0-9]+]]:_(p1) = G_MERGE_VALUES [[COPY]](s32), [[COPY1]](s32)
; CHECK-NEXT: [[LOAD:%[0-9]+]]:_(<4 x s32>) = G_LOAD [[MV]](p1) :: (load (<4 x s32>) from %ir.ptr, addrspace 1)
; CHECK-NEXT: [[BITCAST:%[0-9]+]]:_(s128) = G_BITCAST [[LOAD]](<4 x s32>)
; CHECK-NEXT: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32), [[UV2:%[0-9]+]]:_(s32), [[UV3:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[BITCAST]](s128)
; CHECK-NEXT: $vgpr0 = COPY [[UV]](s32)
; CHECK-NEXT: $vgpr1 = COPY [[UV1]](s32)
; CHECK-NEXT: $vgpr2 = COPY [[UV2]](s32)
; CHECK-NEXT: $vgpr3 = COPY [[UV3]](s32)
; CHECK-NEXT: SI_RETURN implicit $vgpr0, implicit $vgpr1, implicit $vgpr2, implicit $vgpr3
%load = load i128, ptr addrspace(1) %ptr, align 16, !range !3, !noundef !1
ret i128 %load
}
; Load will be zero extended, so we should be able to extend the range
; metadata.
define i32 @global_sextload_i8_align1__rangemd(ptr addrspace(1) %ptr) {
; CHECK-LABEL: name: global_sextload_i8_align1__rangemd
; CHECK: bb.1 (%ir-block.0):
; CHECK-NEXT: liveins: $vgpr0, $vgpr1
; CHECK-NEXT: {{ $}}
; CHECK-NEXT: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
; CHECK-NEXT: [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr1
; CHECK-NEXT: [[MV:%[0-9]+]]:_(p1) = G_MERGE_VALUES [[COPY]](s32), [[COPY1]](s32)
; CHECK-NEXT: [[SEXTLOAD:%[0-9]+]]:_(s32) = G_SEXTLOAD [[MV]](p1) :: (load (s8) from %ir.ptr, !range !0, addrspace 1)
; CHECK-NEXT: $vgpr0 = COPY [[SEXTLOAD]](s32)
; CHECK-NEXT: SI_RETURN implicit $vgpr0
%load = load i8, ptr addrspace(1) %ptr, align 1, !range !0, !noundef !1
%ext = sext i8 %load to i32
ret i32 %ext
}
define i32 @global_zextload_i8_align1__rangemd(ptr addrspace(1) %ptr) {
; CHECK-LABEL: name: global_zextload_i8_align1__rangemd
; CHECK: bb.1 (%ir-block.0):
; CHECK-NEXT: liveins: $vgpr0, $vgpr1
; CHECK-NEXT: {{ $}}
; CHECK-NEXT: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
; CHECK-NEXT: [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr1
; CHECK-NEXT: [[MV:%[0-9]+]]:_(p1) = G_MERGE_VALUES [[COPY]](s32), [[COPY1]](s32)
; CHECK-NEXT: [[SEXTLOAD:%[0-9]+]]:_(s32) = G_SEXTLOAD [[MV]](p1) :: (load (s8) from %ir.ptr, !range !4, addrspace 1)
; CHECK-NEXT: $vgpr0 = COPY [[SEXTLOAD]](s32)
; CHECK-NEXT: SI_RETURN implicit $vgpr0
%load = load i8, ptr addrspace(1) %ptr, align 1, !range !4, !noundef !1
%ext = sext i8 %load to i32
ret i32 %ext
}
!0 = !{i8 -32, i8 64}
!1 = !{}
!2 = !{i64 -2048, i64 1024}
!3 = !{i128 -2048, i128 1024}
!4 = !{i8 8, i8 64}
|
