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
|
; RUN: opt -mtriple=amdgcn-amd-amdhsa -passes=load-store-vectorizer -S -o - %s | FileCheck %s
; RUN: opt -mtriple=amdgcn-amd-amdhsa -aa-pipeline=basic-aa -passes='function(load-store-vectorizer)' -S -o - %s | FileCheck %s
target datalayout = "e-p:64:64-p1:64:64-p2:32:32-p3:32:32-p4:64:64-p5:32:32-p6:32:32-i64:64-v16:16-v24:32-v32:32-v48:64-v96:128-v192:256-v256:256-v512:512-v1024:1024-v2048:2048-n32:64-S32-A5"
declare i32 @llvm.amdgcn.workitem.id.x() #1
; CHECK-LABEL: @basic_merge_sext_index(
; CHECK: sext i32 %id.x to i64
; CHECK: load <2 x float>
; CHECK: store <2 x float> zeroinitializer
define amdgpu_kernel void @basic_merge_sext_index(ptr addrspace(1) nocapture %a, ptr addrspace(1) nocapture %b, ptr addrspace(1) nocapture readonly %c) #0 {
entry:
%id.x = call i32 @llvm.amdgcn.workitem.id.x()
%sext.id.x = sext i32 %id.x to i64
%a.idx.x = getelementptr inbounds float, ptr addrspace(1) %a, i64 %sext.id.x
%c.idx.x = getelementptr inbounds float, ptr addrspace(1) %c, i64 %sext.id.x
%a.idx.x.1 = getelementptr inbounds float, ptr addrspace(1) %a.idx.x, i64 1
%c.idx.x.1 = getelementptr inbounds float, ptr addrspace(1) %c.idx.x, i64 1
%ld.c = load float, ptr addrspace(1) %c.idx.x, align 4
%ld.c.idx.1 = load float, ptr addrspace(1) %c.idx.x.1, align 4
store float 0.0, ptr addrspace(1) %a.idx.x, align 4
store float 0.0, ptr addrspace(1) %a.idx.x.1, align 4
%add = fadd float %ld.c, %ld.c.idx.1
store float %add, ptr addrspace(1) %b, align 4
ret void
}
; CHECK-LABEL: @basic_merge_zext_index(
; CHECK: zext i32 %id.x to i64
; CHECK: load <2 x float>
; CHECK: store <2 x float>
define amdgpu_kernel void @basic_merge_zext_index(ptr addrspace(1) nocapture %a, ptr addrspace(1) nocapture %b, ptr addrspace(1) nocapture readonly %c) #0 {
entry:
%id.x = call i32 @llvm.amdgcn.workitem.id.x()
%zext.id.x = zext i32 %id.x to i64
%a.idx.x = getelementptr inbounds float, ptr addrspace(1) %a, i64 %zext.id.x
%c.idx.x = getelementptr inbounds float, ptr addrspace(1) %c, i64 %zext.id.x
%a.idx.x.1 = getelementptr inbounds float, ptr addrspace(1) %a.idx.x, i64 1
%c.idx.x.1 = getelementptr inbounds float, ptr addrspace(1) %c.idx.x, i64 1
%ld.c = load float, ptr addrspace(1) %c.idx.x, align 4
%ld.c.idx.1 = load float, ptr addrspace(1) %c.idx.x.1, align 4
store float 0.0, ptr addrspace(1) %a.idx.x, align 4
store float 0.0, ptr addrspace(1) %a.idx.x.1, align 4
%add = fadd float %ld.c, %ld.c.idx.1
store float %add, ptr addrspace(1) %b, align 4
ret void
}
; CHECK-LABEL: @merge_op_zext_index(
; CHECK: load <2 x float>
; CHECK: store <2 x float>
define amdgpu_kernel void @merge_op_zext_index(ptr addrspace(1) nocapture noalias %a, ptr addrspace(1) nocapture noalias %b, ptr addrspace(1) nocapture readonly noalias %c) #0 {
entry:
%id.x = call i32 @llvm.amdgcn.workitem.id.x()
%shl = shl i32 %id.x, 2
%zext.id.x = zext i32 %shl to i64
%a.0 = getelementptr inbounds float, ptr addrspace(1) %a, i64 %zext.id.x
%c.0 = getelementptr inbounds float, ptr addrspace(1) %c, i64 %zext.id.x
%id.x.1 = or i32 %shl, 1
%id.x.1.ext = zext i32 %id.x.1 to i64
%a.1 = getelementptr inbounds float, ptr addrspace(1) %a, i64 %id.x.1.ext
%c.1 = getelementptr inbounds float, ptr addrspace(1) %c, i64 %id.x.1.ext
%ld.c.0 = load float, ptr addrspace(1) %c.0, align 4
store float 0.0, ptr addrspace(1) %a.0, align 4
%ld.c.1 = load float, ptr addrspace(1) %c.1, align 4
store float 0.0, ptr addrspace(1) %a.1, align 4
%add = fadd float %ld.c.0, %ld.c.1
store float %add, ptr addrspace(1) %b, align 4
ret void
}
; CHECK-LABEL: @merge_op_sext_index(
; CHECK: load <2 x float>
; CHECK: store <2 x float>
define amdgpu_kernel void @merge_op_sext_index(ptr addrspace(1) nocapture noalias %a, ptr addrspace(1) nocapture noalias %b, ptr addrspace(1) nocapture readonly noalias %c) #0 {
entry:
%id.x = call i32 @llvm.amdgcn.workitem.id.x()
%shl = shl i32 %id.x, 2
%zext.id.x = sext i32 %shl to i64
%a.0 = getelementptr inbounds float, ptr addrspace(1) %a, i64 %zext.id.x
%c.0 = getelementptr inbounds float, ptr addrspace(1) %c, i64 %zext.id.x
%id.x.1 = or i32 %shl, 1
%id.x.1.ext = sext i32 %id.x.1 to i64
%a.1 = getelementptr inbounds float, ptr addrspace(1) %a, i64 %id.x.1.ext
%c.1 = getelementptr inbounds float, ptr addrspace(1) %c, i64 %id.x.1.ext
%ld.c.0 = load float, ptr addrspace(1) %c.0, align 4
store float 0.0, ptr addrspace(1) %a.0, align 4
%ld.c.1 = load float, ptr addrspace(1) %c.1, align 4
store float 0.0, ptr addrspace(1) %a.1, align 4
%add = fadd float %ld.c.0, %ld.c.1
store float %add, ptr addrspace(1) %b, align 4
ret void
}
; This case fails to vectorize if not using the extra extension
; handling in isConsecutiveAccess.
; CHECK-LABEL: @zext_trunc_phi_1(
; CHECK: loop:
; CHECK: load <2 x i32>
; CHECK: store <2 x i32>
define amdgpu_kernel void @zext_trunc_phi_1(ptr addrspace(1) nocapture noalias %a, ptr addrspace(1) nocapture noalias %b, ptr addrspace(1) nocapture readonly noalias %c, i32 %n, i64 %arst, i64 %aoeu) #0 {
entry:
%cmp0 = icmp eq i32 %n, 0
br i1 %cmp0, label %exit, label %loop
loop:
%indvars.iv = phi i64 [ %indvars.iv.next, %loop ], [ 0, %entry ]
%trunc.iv = trunc i64 %indvars.iv to i32
%idx = shl i32 %trunc.iv, 4
%idx.ext = zext i32 %idx to i64
%c.0 = getelementptr inbounds i32, ptr addrspace(1) %c, i64 %idx.ext
%a.0 = getelementptr inbounds i32, ptr addrspace(1) %a, i64 %idx.ext
%idx.1 = or i32 %idx, 1
%idx.1.ext = zext i32 %idx.1 to i64
%c.1 = getelementptr inbounds i32, ptr addrspace(1) %c, i64 %idx.1.ext
%a.1 = getelementptr inbounds i32, ptr addrspace(1) %a, i64 %idx.1.ext
%ld.c.0 = load i32, ptr addrspace(1) %c.0, align 4
store i32 %ld.c.0, ptr addrspace(1) %a.0, align 4
%ld.c.1 = load i32, ptr addrspace(1) %c.1, align 4
store i32 %ld.c.1, ptr addrspace(1) %a.1, align 4
%indvars.iv.next = add i64 %indvars.iv, 1
%lftr.wideiv = trunc i64 %indvars.iv.next to i32
%exitcond = icmp eq i32 %lftr.wideiv, %n
br i1 %exitcond, label %exit, label %loop
exit:
ret void
}
attributes #0 = { nounwind }
attributes #1 = { nounwind readnone }
|
