simd-load-zero-offset.ll
8.07 KB
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
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -verify-machineinstrs -mattr=+simd128 | FileCheck %s
; Test SIMD v128.load{32,64}_zero instructions
target datalayout = "e-m:e-p:32:32-i64:64-n32:64-S128"
target triple = "wasm32-unknown-unknown"
declare <4 x i32> @llvm.wasm.load32.zero(i32*)
declare <2 x i64> @llvm.wasm.load64.zero(i64*)
;===----------------------------------------------------------------------------
; v128.load32_zero
;===----------------------------------------------------------------------------
define <4 x i32> @load_zero_i32_no_offset(i32* %p) {
; CHECK-LABEL: load_zero_i32_no_offset:
; CHECK: .functype load_zero_i32_no_offset (i32) -> (v128)
; CHECK-NEXT: # %bb.0:
; CHECK-NEXT: local.get 0
; CHECK-NEXT: v128.load32_zero 0
; CHECK-NEXT: # fallthrough-return
%v = tail call <4 x i32> @llvm.wasm.load32.zero(i32* %p)
ret <4 x i32> %v
}
define <4 x i32> @load_zero_i32_with_folded_offset(i32* %p) {
; CHECK-LABEL: load_zero_i32_with_folded_offset:
; CHECK: .functype load_zero_i32_with_folded_offset (i32) -> (v128)
; CHECK-NEXT: # %bb.0:
; CHECK-NEXT: local.get 0
; CHECK-NEXT: v128.load32_zero 24
; CHECK-NEXT: # fallthrough-return
%q = ptrtoint i32* %p to i32
%r = add nuw i32 %q, 24
%s = inttoptr i32 %r to i32*
%t = tail call <4 x i32> @llvm.wasm.load32.zero(i32* %s)
ret <4 x i32> %t
}
define <4 x i32> @load_zero_i32_with_folded_gep_offset(i32* %p) {
; CHECK-LABEL: load_zero_i32_with_folded_gep_offset:
; CHECK: .functype load_zero_i32_with_folded_gep_offset (i32) -> (v128)
; CHECK-NEXT: # %bb.0:
; CHECK-NEXT: local.get 0
; CHECK-NEXT: v128.load32_zero 24
; CHECK-NEXT: # fallthrough-return
%s = getelementptr inbounds i32, i32* %p, i32 6
%t = tail call <4 x i32> @llvm.wasm.load32.zero(i32* %s)
ret <4 x i32> %t
}
define <4 x i32> @load_zero_i32_with_unfolded_gep_negative_offset(i32* %p) {
; CHECK-LABEL: load_zero_i32_with_unfolded_gep_negative_offset:
; CHECK: .functype load_zero_i32_with_unfolded_gep_negative_offset (i32) -> (v128)
; CHECK-NEXT: # %bb.0:
; CHECK-NEXT: local.get 0
; CHECK-NEXT: i32.const -24
; CHECK-NEXT: i32.add
; CHECK-NEXT: v128.load32_zero 0
; CHECK-NEXT: # fallthrough-return
%s = getelementptr inbounds i32, i32* %p, i32 -6
%t = tail call <4 x i32> @llvm.wasm.load32.zero(i32* %s)
ret <4 x i32> %t
}
define <4 x i32> @load_zero_i32_with_unfolded_offset(i32* %p) {
; CHECK-LABEL: load_zero_i32_with_unfolded_offset:
; CHECK: .functype load_zero_i32_with_unfolded_offset (i32) -> (v128)
; CHECK-NEXT: # %bb.0:
; CHECK-NEXT: local.get 0
; CHECK-NEXT: i32.const 24
; CHECK-NEXT: i32.add
; CHECK-NEXT: v128.load32_zero 0
; CHECK-NEXT: # fallthrough-return
%q = ptrtoint i32* %p to i32
%r = add nsw i32 %q, 24
%s = inttoptr i32 %r to i32*
%t = tail call <4 x i32> @llvm.wasm.load32.zero(i32* %s)
ret <4 x i32> %t
}
define <4 x i32> @load_zero_i32_with_unfolded_gep_offset(i32* %p) {
; CHECK-LABEL: load_zero_i32_with_unfolded_gep_offset:
; CHECK: .functype load_zero_i32_with_unfolded_gep_offset (i32) -> (v128)
; CHECK-NEXT: # %bb.0:
; CHECK-NEXT: local.get 0
; CHECK-NEXT: i32.const 24
; CHECK-NEXT: i32.add
; CHECK-NEXT: v128.load32_zero 0
; CHECK-NEXT: # fallthrough-return
%s = getelementptr i32, i32* %p, i32 6
%t = tail call <4 x i32> @llvm.wasm.load32.zero(i32* %s)
ret <4 x i32> %t
}
define <4 x i32> @load_zero_i32_from_numeric_address() {
; CHECK-LABEL: load_zero_i32_from_numeric_address:
; CHECK: .functype load_zero_i32_from_numeric_address () -> (v128)
; CHECK-NEXT: # %bb.0:
; CHECK-NEXT: i32.const 0
; CHECK-NEXT: v128.load32_zero 42
; CHECK-NEXT: # fallthrough-return
%s = inttoptr i32 42 to i32*
%t = tail call <4 x i32> @llvm.wasm.load32.zero(i32* %s)
ret <4 x i32> %t
}
@gv_i32 = global i32 0
define <4 x i32> @load_zero_i32_from_global_address() {
; CHECK-LABEL: load_zero_i32_from_global_address:
; CHECK: .functype load_zero_i32_from_global_address () -> (v128)
; CHECK-NEXT: # %bb.0:
; CHECK-NEXT: i32.const 0
; CHECK-NEXT: v128.load32_zero gv_i32
; CHECK-NEXT: # fallthrough-return
%t = tail call <4 x i32> @llvm.wasm.load32.zero(i32* @gv_i32)
ret <4 x i32> %t
}
;===----------------------------------------------------------------------------
; v128.load64_zero
;===----------------------------------------------------------------------------
define <2 x i64> @load_zero_i64_no_offset(i64* %p) {
; CHECK-LABEL: load_zero_i64_no_offset:
; CHECK: .functype load_zero_i64_no_offset (i32) -> (v128)
; CHECK-NEXT: # %bb.0:
; CHECK-NEXT: local.get 0
; CHECK-NEXT: v128.load64_zero 0
; CHECK-NEXT: # fallthrough-return
%v = tail call <2 x i64> @llvm.wasm.load64.zero(i64* %p)
ret <2 x i64> %v
}
define <2 x i64> @load_zero_i64_with_folded_offset(i64* %p) {
; CHECK-LABEL: load_zero_i64_with_folded_offset:
; CHECK: .functype load_zero_i64_with_folded_offset (i32) -> (v128)
; CHECK-NEXT: # %bb.0:
; CHECK-NEXT: local.get 0
; CHECK-NEXT: v128.load64_zero 24
; CHECK-NEXT: # fallthrough-return
%q = ptrtoint i64* %p to i32
%r = add nuw i32 %q, 24
%s = inttoptr i32 %r to i64*
%t = tail call <2 x i64> @llvm.wasm.load64.zero(i64* %s)
ret <2 x i64> %t
}
define <2 x i64> @load_zero_i64_with_folded_gep_offset(i64* %p) {
; CHECK-LABEL: load_zero_i64_with_folded_gep_offset:
; CHECK: .functype load_zero_i64_with_folded_gep_offset (i32) -> (v128)
; CHECK-NEXT: # %bb.0:
; CHECK-NEXT: local.get 0
; CHECK-NEXT: v128.load64_zero 48
; CHECK-NEXT: # fallthrough-return
%s = getelementptr inbounds i64, i64* %p, i64 6
%t = tail call <2 x i64> @llvm.wasm.load64.zero(i64* %s)
ret <2 x i64> %t
}
define <2 x i64> @load_zero_i64_with_unfolded_gep_negative_offset(i64* %p) {
; CHECK-LABEL: load_zero_i64_with_unfolded_gep_negative_offset:
; CHECK: .functype load_zero_i64_with_unfolded_gep_negative_offset (i32) -> (v128)
; CHECK-NEXT: # %bb.0:
; CHECK-NEXT: local.get 0
; CHECK-NEXT: i32.const -48
; CHECK-NEXT: i32.add
; CHECK-NEXT: v128.load64_zero 0
; CHECK-NEXT: # fallthrough-return
%s = getelementptr inbounds i64, i64* %p, i64 -6
%t = tail call <2 x i64> @llvm.wasm.load64.zero(i64* %s)
ret <2 x i64> %t
}
define <2 x i64> @load_zero_i64_with_unfolded_offset(i64* %p) {
; CHECK-LABEL: load_zero_i64_with_unfolded_offset:
; CHECK: .functype load_zero_i64_with_unfolded_offset (i32) -> (v128)
; CHECK-NEXT: # %bb.0:
; CHECK-NEXT: local.get 0
; CHECK-NEXT: i32.const 24
; CHECK-NEXT: i32.add
; CHECK-NEXT: v128.load64_zero 0
; CHECK-NEXT: # fallthrough-return
%q = ptrtoint i64* %p to i32
%r = add nsw i32 %q, 24
%s = inttoptr i32 %r to i64*
%t = tail call <2 x i64> @llvm.wasm.load64.zero(i64* %s)
ret <2 x i64> %t
}
define <2 x i64> @load_zero_i64_with_unfolded_gep_offset(i64* %p) {
; CHECK-LABEL: load_zero_i64_with_unfolded_gep_offset:
; CHECK: .functype load_zero_i64_with_unfolded_gep_offset (i32) -> (v128)
; CHECK-NEXT: # %bb.0:
; CHECK-NEXT: local.get 0
; CHECK-NEXT: i32.const 48
; CHECK-NEXT: i32.add
; CHECK-NEXT: v128.load64_zero 0
; CHECK-NEXT: # fallthrough-return
%s = getelementptr i64, i64* %p, i64 6
%t = tail call <2 x i64> @llvm.wasm.load64.zero(i64* %s)
ret <2 x i64> %t
}
define <2 x i64> @load_zero_i64_from_numeric_address() {
; CHECK-LABEL: load_zero_i64_from_numeric_address:
; CHECK: .functype load_zero_i64_from_numeric_address () -> (v128)
; CHECK-NEXT: # %bb.0:
; CHECK-NEXT: i32.const 0
; CHECK-NEXT: v128.load64_zero 42
; CHECK-NEXT: # fallthrough-return
%s = inttoptr i32 42 to i64*
%t = tail call <2 x i64> @llvm.wasm.load64.zero(i64* %s)
ret <2 x i64> %t
}
@gv_i64 = global i64 0
define <2 x i64> @load_zero_i64_from_global_address() {
; CHECK-LABEL: load_zero_i64_from_global_address:
; CHECK: .functype load_zero_i64_from_global_address () -> (v128)
; CHECK-NEXT: # %bb.0:
; CHECK-NEXT: i32.const 0
; CHECK-NEXT: v128.load64_zero gv_i64
; CHECK-NEXT: # fallthrough-return
%t = tail call <2 x i64> @llvm.wasm.load64.zero(i64* @gv_i64)
ret <2 x i64> %t
}