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
|
; RUN: opt -S -mtriple=amdgcn-- -mcpu=bonaire -loop-reduce < %s | FileCheck -check-prefix=OPT %s
; Test that loops with different maximum offsets for different address
; spaces are correctly handled.
; OPT-LABEL: @test_global_addressing_loop_uniform_index_max_offset_i32(
; OPT: .lr.ph.preheader:
; OPT: %scevgep2 = getelementptr i8, ptr addrspace(1) %arg1, i64 4095
; OPT: br label %.lr.ph
; OPT: {{^}}.lr.ph:
; OPT: %lsr.iv3 = phi ptr addrspace(1) [ %scevgep4, %.lr.ph ], [ %scevgep2, %.lr.ph.preheader ]
; OPT: load i8, ptr addrspace(1) %lsr.iv3, align 1
; OPT: %scevgep4 = getelementptr i8, ptr addrspace(1) %lsr.iv3, i64 1
define amdgpu_kernel void @test_global_addressing_loop_uniform_index_max_offset_i32(ptr addrspace(1) noalias nocapture %arg0, ptr addrspace(1) noalias nocapture readonly %arg1, i32 %n) #0 {
bb:
%tmp = icmp sgt i32 %n, 0
br i1 %tmp, label %.lr.ph.preheader, label %._crit_edge
.lr.ph.preheader: ; preds = %bb
br label %.lr.ph
._crit_edge.loopexit: ; preds = %.lr.ph
br label %._crit_edge
._crit_edge: ; preds = %._crit_edge.loopexit, %bb
ret void
.lr.ph: ; preds = %.lr.ph, %.lr.ph.preheader
%indvars.iv = phi i64 [ %indvars.iv.next, %.lr.ph ], [ 0, %.lr.ph.preheader ]
%tmp1 = add nuw nsw i64 %indvars.iv, 4095
%tmp2 = getelementptr inbounds i8, ptr addrspace(1) %arg1, i64 %tmp1
%tmp3 = load i8, ptr addrspace(1) %tmp2, align 1
%tmp4 = sext i8 %tmp3 to i32
%tmp5 = getelementptr inbounds i32, ptr addrspace(1) %arg0, i64 %indvars.iv
%tmp6 = load i32, ptr addrspace(1) %tmp5, align 4
%tmp7 = add nsw i32 %tmp6, %tmp4
store i32 %tmp7, ptr addrspace(1) %tmp5, align 4
%indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
%lftr.wideiv = trunc i64 %indvars.iv.next to i32
%exitcond = icmp eq i32 %lftr.wideiv, %n
br i1 %exitcond, label %._crit_edge.loopexit, label %.lr.ph
}
; OPT-LABEL: @test_global_addressing_loop_uniform_index_max_offset_p1_i32(
; OPT: {{^}}.lr.ph.preheader:
; OPT: %scevgep2 = getelementptr i8, ptr addrspace(1) %arg1, i64 4096
; OPT: br label %.lr.ph
; OPT: {{^}}.lr.ph:
; OPT: %lsr.iv3 = phi ptr addrspace(1) [ %scevgep4, %.lr.ph ], [ %scevgep2, %.lr.ph.preheader ]
; OPT: %scevgep4 = getelementptr i8, ptr addrspace(1) %lsr.iv3, i64 1
define amdgpu_kernel void @test_global_addressing_loop_uniform_index_max_offset_p1_i32(ptr addrspace(1) noalias nocapture %arg0, ptr addrspace(1) noalias nocapture readonly %arg1, i32 %n) #0 {
bb:
%tmp = icmp sgt i32 %n, 0
br i1 %tmp, label %.lr.ph.preheader, label %._crit_edge
.lr.ph.preheader: ; preds = %bb
br label %.lr.ph
._crit_edge.loopexit: ; preds = %.lr.ph
br label %._crit_edge
._crit_edge: ; preds = %._crit_edge.loopexit, %bb
ret void
.lr.ph: ; preds = %.lr.ph, %.lr.ph.preheader
%indvars.iv = phi i64 [ %indvars.iv.next, %.lr.ph ], [ 0, %.lr.ph.preheader ]
%tmp1 = add nuw nsw i64 %indvars.iv, 4096
%tmp2 = getelementptr inbounds i8, ptr addrspace(1) %arg1, i64 %tmp1
%tmp3 = load i8, ptr addrspace(1) %tmp2, align 1
%tmp4 = sext i8 %tmp3 to i32
%tmp5 = getelementptr inbounds i32, ptr addrspace(1) %arg0, i64 %indvars.iv
%tmp6 = load i32, ptr addrspace(1) %tmp5, align 4
%tmp7 = add nsw i32 %tmp6, %tmp4
store i32 %tmp7, ptr addrspace(1) %tmp5, align 4
%indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
%lftr.wideiv = trunc i64 %indvars.iv.next to i32
%exitcond = icmp eq i32 %lftr.wideiv, %n
br i1 %exitcond, label %._crit_edge.loopexit, label %.lr.ph
}
; OPT-LABEL: @test_local_addressing_loop_uniform_index_max_offset_i32(
; OPT: .lr.ph.preheader:
; OPT: %scevgep2 = getelementptr i8, ptr addrspace(3) %arg1, i32 65535
; OPT: br label %.lr.ph
; OPT: {{^}}.lr.ph
; OPT: %lsr.iv3 = phi ptr addrspace(3) [ %scevgep4, %.lr.ph ], [ %scevgep2, %.lr.ph.preheader ]
; OPT: %tmp4 = load i8, ptr addrspace(3) %lsr.iv3, align 1
; OPT: %scevgep4 = getelementptr i8, ptr addrspace(3) %lsr.iv3, i32 1
define amdgpu_kernel void @test_local_addressing_loop_uniform_index_max_offset_i32(ptr addrspace(1) noalias nocapture %arg0, ptr addrspace(3) noalias nocapture readonly %arg1, i32 %n) #0 {
bb:
%tmp = icmp sgt i32 %n, 0
br i1 %tmp, label %.lr.ph.preheader, label %._crit_edge
.lr.ph.preheader: ; preds = %bb
br label %.lr.ph
._crit_edge.loopexit: ; preds = %.lr.ph
br label %._crit_edge
._crit_edge: ; preds = %._crit_edge.loopexit, %bb
ret void
.lr.ph: ; preds = %.lr.ph, %.lr.ph.preheader
%indvars.iv = phi i64 [ %indvars.iv.next, %.lr.ph ], [ 0, %.lr.ph.preheader ]
%tmp1 = add nuw nsw i64 %indvars.iv, 65535
%tmp2 = trunc i64 %tmp1 to i32
%tmp3 = getelementptr inbounds i8, ptr addrspace(3) %arg1, i32 %tmp2
%tmp4 = load i8, ptr addrspace(3) %tmp3, align 1
%tmp5 = sext i8 %tmp4 to i32
%tmp6 = getelementptr inbounds i32, ptr addrspace(1) %arg0, i64 %indvars.iv
%tmp7 = load i32, ptr addrspace(1) %tmp6, align 4
%tmp8 = add nsw i32 %tmp7, %tmp5
store i32 %tmp8, ptr addrspace(1) %tmp6, align 4
%indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
%lftr.wideiv = trunc i64 %indvars.iv.next to i32
%exitcond = icmp eq i32 %lftr.wideiv, %n
br i1 %exitcond, label %._crit_edge.loopexit, label %.lr.ph
}
; OPT-LABEL: @test_local_addressing_loop_uniform_index_max_offset_p1_i32(
; OPT: {{^}}.lr.ph.preheader:
; OPT: %scevgep2 = getelementptr i8, ptr addrspace(3) %arg1, i32 65536
; OPT: br label %.lr.ph
; OPT: {{^}}.lr.ph:
; OPT: %lsr.iv3 = phi ptr addrspace(3) [ %scevgep4, %.lr.ph ], [ %scevgep2, %.lr.ph.preheader ]
; OPT: %scevgep4 = getelementptr i8, ptr addrspace(3) %lsr.iv3, i32 1
define amdgpu_kernel void @test_local_addressing_loop_uniform_index_max_offset_p1_i32(ptr addrspace(1) noalias nocapture %arg0, ptr addrspace(3) noalias nocapture readonly %arg1, i32 %n) #0 {
bb:
%tmp = icmp sgt i32 %n, 0
br i1 %tmp, label %.lr.ph.preheader, label %._crit_edge
.lr.ph.preheader: ; preds = %bb
br label %.lr.ph
._crit_edge.loopexit: ; preds = %.lr.ph
br label %._crit_edge
._crit_edge: ; preds = %._crit_edge.loopexit, %bb
ret void
.lr.ph: ; preds = %.lr.ph, %.lr.ph.preheader
%indvars.iv = phi i64 [ %indvars.iv.next, %.lr.ph ], [ 0, %.lr.ph.preheader ]
%tmp1 = add nuw nsw i64 %indvars.iv, 65536
%tmp2 = trunc i64 %tmp1 to i32
%tmp3 = getelementptr inbounds i8, ptr addrspace(3) %arg1, i32 %tmp2
%tmp4 = load i8, ptr addrspace(3) %tmp3, align 1
%tmp5 = sext i8 %tmp4 to i32
%tmp6 = getelementptr inbounds i32, ptr addrspace(1) %arg0, i64 %indvars.iv
%tmp7 = load i32, ptr addrspace(1) %tmp6, align 4
%tmp8 = add nsw i32 %tmp7, %tmp5
store i32 %tmp8, ptr addrspace(1) %tmp6, align 4
%indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
%lftr.wideiv = trunc i64 %indvars.iv.next to i32
%exitcond = icmp eq i32 %lftr.wideiv, %n
br i1 %exitcond, label %._crit_edge.loopexit, label %.lr.ph
}
attributes #0 = { nounwind "less-precise-fpmad"="false" "frame-pointer"="all" "no-infs-fp-math"="false" "no-nans-fp-math"="false" "stack-protector-buffer-size"="8" "target-cpu"="hawaii" "unsafe-fp-math"="false" "use-soft-float"="false" }
|
