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
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
|
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -o - < %s | FileCheck %s
target datalayout = "e-m:e-p:32:32-Fi8-i64:64-v128:64:128-a:0:32-n32-S64"
target triple = "armv8-unknown-linux-gnueabihf"
define <4 x float> @test(float* %A) {
; CHECK-LABEL: test:
; CHECK: @ %bb.0:
; CHECK-NEXT: vld1.32 {d16, d17}, [r0]!
; CHECK-NEXT: vld1.32 {d18, d19}, [r0]!
; CHECK-NEXT: vadd.f32 q8, q8, q9
; CHECK-NEXT: vld1.32 {d18, d19}, [r0]
; CHECK-NEXT: vadd.f32 q0, q8, q9
; CHECK-NEXT: bx lr
%X.ptr = bitcast float* %A to <4 x float>*
%X = load <4 x float>, <4 x float>* %X.ptr, align 4
%Y.ptr.elt = getelementptr inbounds float, float* %A, i32 4
%Y.ptr = bitcast float* %Y.ptr.elt to <4 x float>*
%Y = load <4 x float>, <4 x float>* %Y.ptr, align 4
%Z.ptr.elt = getelementptr inbounds float, float* %A, i32 8
%Z.ptr = bitcast float* %Z.ptr.elt to <4 x float>*
%Z = load <4 x float>, <4 x float>* %Z.ptr, align 4
%tmp.sum = fadd <4 x float> %X, %Y
%sum = fadd <4 x float> %tmp.sum, %Z
ret <4 x float> %sum
}
define <4 x float> @test_stride(float* %A) {
; CHECK-LABEL: test_stride:
; CHECK: @ %bb.0:
; CHECK-NEXT: mov r1, #24
; CHECK-NEXT: vld1.32 {d16, d17}, [r0], r1
; CHECK-NEXT: vld1.32 {d18, d19}, [r0], r1
; CHECK-NEXT: vadd.f32 q8, q8, q9
; CHECK-NEXT: vld1.32 {d18, d19}, [r0]
; CHECK-NEXT: vadd.f32 q0, q8, q9
; CHECK-NEXT: bx lr
%X.ptr = bitcast float* %A to <4 x float>*
%X = load <4 x float>, <4 x float>* %X.ptr, align 4
%Y.ptr.elt = getelementptr inbounds float, float* %A, i32 6
%Y.ptr = bitcast float* %Y.ptr.elt to <4 x float>*
%Y = load <4 x float>, <4 x float>* %Y.ptr, align 4
%Z.ptr.elt = getelementptr inbounds float, float* %A, i32 12
%Z.ptr = bitcast float* %Z.ptr.elt to <4 x float>*
%Z = load <4 x float>, <4 x float>* %Z.ptr, align 4
%tmp.sum = fadd <4 x float> %X, %Y
%sum = fadd <4 x float> %tmp.sum, %Z
ret <4 x float> %sum
}
define <4 x float> @test_stride_mixed(float* %A) {
; CHECK-LABEL: test_stride_mixed:
; CHECK: @ %bb.0:
; CHECK-NEXT: mov r1, #24
; CHECK-NEXT: vld1.32 {d16, d17}, [r0], r1
; CHECK-NEXT: vld1.32 {d18, d19}, [r0]!
; CHECK-NEXT: vadd.f32 q8, q8, q9
; CHECK-NEXT: vld1.32 {d18, d19}, [r0]
; CHECK-NEXT: vadd.f32 q0, q8, q9
; CHECK-NEXT: bx lr
%X.ptr = bitcast float* %A to <4 x float>*
%X = load <4 x float>, <4 x float>* %X.ptr, align 4
%Y.ptr.elt = getelementptr inbounds float, float* %A, i32 6
%Y.ptr = bitcast float* %Y.ptr.elt to <4 x float>*
%Y = load <4 x float>, <4 x float>* %Y.ptr, align 4
%Z.ptr.elt = getelementptr inbounds float, float* %A, i32 10
%Z.ptr = bitcast float* %Z.ptr.elt to <4 x float>*
%Z = load <4 x float>, <4 x float>* %Z.ptr, align 4
%tmp.sum = fadd <4 x float> %X, %Y
%sum = fadd <4 x float> %tmp.sum, %Z
ret <4 x float> %sum
}
; Refrain from using multiple stride registers
define <4 x float> @test_stride_noop(float* %A) {
; CHECK-LABEL: test_stride_noop:
; CHECK: @ %bb.0:
; CHECK-NEXT: mov r1, #24
; CHECK-NEXT: vld1.32 {d16, d17}, [r0], r1
; CHECK-NEXT: mov r1, #32
; CHECK-NEXT: vld1.32 {d18, d19}, [r0], r1
; CHECK-NEXT: vadd.f32 q8, q8, q9
; CHECK-NEXT: vld1.32 {d18, d19}, [r0]
; CHECK-NEXT: vadd.f32 q0, q8, q9
; CHECK-NEXT: bx lr
%X.ptr = bitcast float* %A to <4 x float>*
%X = load <4 x float>, <4 x float>* %X.ptr, align 4
%Y.ptr.elt = getelementptr inbounds float, float* %A, i32 6
%Y.ptr = bitcast float* %Y.ptr.elt to <4 x float>*
%Y = load <4 x float>, <4 x float>* %Y.ptr, align 4
%Z.ptr.elt = getelementptr inbounds float, float* %A, i32 14
%Z.ptr = bitcast float* %Z.ptr.elt to <4 x float>*
%Z = load <4 x float>, <4 x float>* %Z.ptr, align 4
%tmp.sum = fadd <4 x float> %X, %Y
%sum = fadd <4 x float> %tmp.sum, %Z
ret <4 x float> %sum
}
define <4 x float> @test_positive_initial_offset(float* %A) {
; CHECK-LABEL: test_positive_initial_offset:
; CHECK: @ %bb.0:
; CHECK-NEXT: add r0, r0, #32
; CHECK-NEXT: vld1.32 {d16, d17}, [r0]!
; CHECK-NEXT: vld1.32 {d18, d19}, [r0]!
; CHECK-NEXT: vadd.f32 q8, q8, q9
; CHECK-NEXT: vld1.32 {d18, d19}, [r0]
; CHECK-NEXT: vadd.f32 q0, q8, q9
; CHECK-NEXT: bx lr
%X.ptr.elt = getelementptr inbounds float, float* %A, i32 8
%X.ptr = bitcast float* %X.ptr.elt to <4 x float>*
%X = load <4 x float>, <4 x float>* %X.ptr, align 4
%Y.ptr.elt = getelementptr inbounds float, float* %A, i32 12
%Y.ptr = bitcast float* %Y.ptr.elt to <4 x float>*
%Y = load <4 x float>, <4 x float>* %Y.ptr, align 4
%Z.ptr.elt = getelementptr inbounds float, float* %A, i32 16
%Z.ptr = bitcast float* %Z.ptr.elt to <4 x float>*
%Z = load <4 x float>, <4 x float>* %Z.ptr, align 4
%tmp.sum = fadd <4 x float> %X, %Y
%sum = fadd <4 x float> %tmp.sum, %Z
ret <4 x float> %sum
}
define <4 x float> @test_negative_initial_offset(float* %A) {
; CHECK-LABEL: test_negative_initial_offset:
; CHECK: @ %bb.0:
; CHECK-NEXT: sub r0, r0, #64
; CHECK-NEXT: vld1.32 {d16, d17}, [r0]!
; CHECK-NEXT: vld1.32 {d18, d19}, [r0]!
; CHECK-NEXT: vadd.f32 q8, q8, q9
; CHECK-NEXT: vld1.32 {d18, d19}, [r0]
; CHECK-NEXT: vadd.f32 q0, q8, q9
; CHECK-NEXT: bx lr
%X.ptr.elt = getelementptr inbounds float, float* %A, i32 -16
%X.ptr = bitcast float* %X.ptr.elt to <4 x float>*
%X = load <4 x float>, <4 x float>* %X.ptr, align 4
%Y.ptr.elt = getelementptr inbounds float, float* %A, i32 -12
%Y.ptr = bitcast float* %Y.ptr.elt to <4 x float>*
%Y = load <4 x float>, <4 x float>* %Y.ptr, align 4
%Z.ptr.elt = getelementptr inbounds float, float* %A, i32 -8
%Z.ptr = bitcast float* %Z.ptr.elt to <4 x float>*
%Z = load <4 x float>, <4 x float>* %Z.ptr, align 4
%tmp.sum = fadd <4 x float> %X, %Y
%sum = fadd <4 x float> %tmp.sum, %Z
ret <4 x float> %sum
}
@global_float_array = external global [128 x float], align 4
define <4 x float> @test_global() {
; CHECK-LABEL: test_global:
; CHECK: @ %bb.0:
; CHECK-NEXT: movw r0, :lower16:global_float_array
; CHECK-NEXT: movt r0, :upper16:global_float_array
; CHECK-NEXT: add r0, r0, #32
; CHECK-NEXT: vld1.32 {d16, d17}, [r0]!
; CHECK-NEXT: vld1.32 {d18, d19}, [r0]!
; CHECK-NEXT: vadd.f32 q8, q8, q9
; CHECK-NEXT: vld1.32 {d18, d19}, [r0]
; CHECK-NEXT: vadd.f32 q0, q8, q9
; CHECK-NEXT: bx lr
%X = load <4 x float>, <4 x float>* bitcast (float* getelementptr inbounds ([128 x float], [128 x float]* @global_float_array, i32 0, i32 8) to <4 x float>*), align 4
%Y = load <4 x float>, <4 x float>* bitcast (float* getelementptr inbounds ([128 x float], [128 x float]* @global_float_array, i32 0, i32 12) to <4 x float>*), align 4
%Z = load <4 x float>, <4 x float>* bitcast (float* getelementptr inbounds ([128 x float], [128 x float]* @global_float_array, i32 0, i32 16) to <4 x float>*), align 4
%tmp.sum = fadd <4 x float> %X, %Y
%sum = fadd <4 x float> %tmp.sum, %Z
ret <4 x float> %sum
}
define <4 x float> @test_stack() {
; Use huge alignment to test that ADD would not be converted to OR
; CHECK-LABEL: test_stack:
; CHECK: @ %bb.0:
; CHECK-NEXT: .save {r4, r10, r11, lr}
; CHECK-NEXT: push {r4, r10, r11, lr}
; CHECK-NEXT: .setfp r11, sp, #8
; CHECK-NEXT: add r11, sp, #8
; CHECK-NEXT: .pad #240
; CHECK-NEXT: sub sp, sp, #240
; CHECK-NEXT: bfc sp, #0, #7
; CHECK-NEXT: mov r4, sp
; CHECK-NEXT: mov r0, r4
; CHECK-NEXT: bl external_function
; CHECK-NEXT: vld1.32 {d16, d17}, [r4:128]!
; CHECK-NEXT: vld1.32 {d18, d19}, [r4:128]!
; CHECK-NEXT: vadd.f32 q8, q8, q9
; CHECK-NEXT: vld1.64 {d18, d19}, [r4:128]
; CHECK-NEXT: vadd.f32 q0, q8, q9
; CHECK-NEXT: sub sp, r11, #8
; CHECK-NEXT: pop {r4, r10, r11, pc}
%array = alloca [32 x float], align 128
%arraydecay = getelementptr inbounds [32 x float], [32 x float]* %array, i32 0, i32 0
call void @external_function(float* %arraydecay)
%X.ptr = bitcast [32 x float]* %array to <4 x float>*
%X = load <4 x float>, <4 x float>* %X.ptr, align 4
%Y.ptr.elt = getelementptr inbounds [32 x float], [32 x float]* %array, i32 0, i32 4
%Y.ptr = bitcast float* %Y.ptr.elt to <4 x float>*
%Y = load <4 x float>, <4 x float>* %Y.ptr, align 4
%Z.ptr.elt = getelementptr inbounds [32 x float], [32 x float]* %array, i32 0, i32 8
%Z.ptr = bitcast float* %Z.ptr.elt to <4 x float>*
%Z = load <4 x float>, <4 x float>* %Z.ptr, align 4
%tmp.sum = fadd <4 x float> %X, %Y
%sum = fadd <4 x float> %tmp.sum, %Z
ret <4 x float> %sum
}
define <2 x double> @test_double(double* %A) {
; CHECK-LABEL: test_double:
; CHECK: @ %bb.0:
; CHECK-NEXT: add r0, r0, #64
; CHECK-NEXT: vld1.64 {d16, d17}, [r0]!
; CHECK-NEXT: vld1.64 {d18, d19}, [r0]!
; CHECK-NEXT: vadd.f64 d20, d17, d19
; CHECK-NEXT: vadd.f64 d16, d16, d18
; CHECK-NEXT: vld1.64 {d22, d23}, [r0]
; CHECK-NEXT: vadd.f64 d1, d20, d23
; CHECK-NEXT: vadd.f64 d0, d16, d22
; CHECK-NEXT: bx lr
%X.ptr.elt = getelementptr inbounds double, double* %A, i32 8
%X.ptr = bitcast double* %X.ptr.elt to <2 x double>*
%X = load <2 x double>, <2 x double>* %X.ptr, align 8
%Y.ptr.elt = getelementptr inbounds double, double* %A, i32 10
%Y.ptr = bitcast double* %Y.ptr.elt to <2 x double>*
%Y = load <2 x double>, <2 x double>* %Y.ptr, align 8
%Z.ptr.elt = getelementptr inbounds double, double* %A, i32 12
%Z.ptr = bitcast double* %Z.ptr.elt to <2 x double>*
%Z = load <2 x double>, <2 x double>* %Z.ptr, align 8
%tmp.sum = fadd <2 x double> %X, %Y
%sum = fadd <2 x double> %tmp.sum, %Z
ret <2 x double> %sum
}
define void @test_various_instructions(float* %A) {
; CHECK-LABEL: test_various_instructions:
; CHECK: @ %bb.0:
; CHECK-NEXT: vld1.32 {d16, d17}, [r0]!
; CHECK-NEXT: vld1.32 {d18, d19}, [r0]!
; CHECK-NEXT: vadd.f32 q8, q8, q9
; CHECK-NEXT: vst1.32 {d16, d17}, [r0]
; CHECK-NEXT: bx lr
%X.ptr = bitcast float* %A to i8*
%X = call <4 x float> @llvm.arm.neon.vld1.v4f32.p0i8(i8* %X.ptr, i32 1)
%Y.ptr.elt = getelementptr inbounds float, float* %A, i32 4
%Y.ptr = bitcast float* %Y.ptr.elt to <4 x float>*
%Y = load <4 x float>, <4 x float>* %Y.ptr, align 4
%Z.ptr.elt = getelementptr inbounds float, float* %A, i32 8
%Z.ptr = bitcast float* %Z.ptr.elt to i8*
%Z = fadd <4 x float> %X, %Y
tail call void @llvm.arm.neon.vst1.p0i8.v4f32(i8* nonnull %Z.ptr, <4 x float> %Z, i32 4)
ret void
}
define void @test_lsr_geps(float* %a, float* %b, i32 %n) {
; CHECK-LABEL: test_lsr_geps:
; CHECK: @ %bb.0: @ %entry
; CHECK-NEXT: cmp r2, #1
; CHECK-NEXT: bxlt lr
; CHECK-NEXT: .LBB10_1: @ %for.body.preheader
; CHECK-NEXT: mov r12, #0
; CHECK-NEXT: .LBB10_2: @ %for.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT: add r3, r0, r12
; CHECK-NEXT: subs r2, r2, #1
; CHECK-NEXT: vld1.32 {d16, d17}, [r3]!
; CHECK-NEXT: vld1.32 {d18, d19}, [r3]!
; CHECK-NEXT: vld1.32 {d20, d21}, [r3]!
; CHECK-NEXT: vld1.32 {d22, d23}, [r3]
; CHECK-NEXT: add r3, r1, r12
; CHECK-NEXT: add r12, r12, #64
; CHECK-NEXT: vst1.32 {d16, d17}, [r3]!
; CHECK-NEXT: vst1.32 {d18, d19}, [r3]!
; CHECK-NEXT: vst1.32 {d20, d21}, [r3]!
; CHECK-NEXT: vst1.32 {d22, d23}, [r3]
; CHECK-NEXT: bne .LBB10_2
; CHECK-NEXT: @ %bb.3: @ %for.cond.cleanup
; CHECK-NEXT: bx lr
entry:
%cmp61 = icmp sgt i32 %n, 0
br i1 %cmp61, label %for.body.preheader, label %for.cond.cleanup
for.body.preheader:
br label %for.body
for.cond.cleanup:
ret void
for.body:
%lsr.iv1 = phi i32 [ 0, %for.body.preheader ], [ %lsr.iv.next2, %for.body ]
%lsr.iv = phi i32 [ %n, %for.body.preheader ], [ %lsr.iv.next, %for.body ]
%0 = bitcast float* %a to i8*
%1 = bitcast float* %b to i8*
%uglygep19 = getelementptr i8, i8* %0, i32 %lsr.iv1
%uglygep1920 = bitcast i8* %uglygep19 to <4 x float>*
%2 = load <4 x float>, <4 x float>* %uglygep1920, align 4
%uglygep16 = getelementptr i8, i8* %0, i32 %lsr.iv1
%uglygep1617 = bitcast i8* %uglygep16 to <4 x float>*
%scevgep18 = getelementptr <4 x float>, <4 x float>* %uglygep1617, i32 1
%3 = load <4 x float>, <4 x float>* %scevgep18, align 4
%uglygep13 = getelementptr i8, i8* %0, i32 %lsr.iv1
%uglygep1314 = bitcast i8* %uglygep13 to <4 x float>*
%scevgep15 = getelementptr <4 x float>, <4 x float>* %uglygep1314, i32 2
%4 = load <4 x float>, <4 x float>* %scevgep15, align 4
%uglygep10 = getelementptr i8, i8* %0, i32 %lsr.iv1
%uglygep1011 = bitcast i8* %uglygep10 to <4 x float>*
%scevgep12 = getelementptr <4 x float>, <4 x float>* %uglygep1011, i32 3
%5 = load <4 x float>, <4 x float>* %scevgep12, align 4
%uglygep8 = getelementptr i8, i8* %1, i32 %lsr.iv1
tail call void @llvm.arm.neon.vst1.p0i8.v4f32(i8* %uglygep8, <4 x float> %2, i32 4)
%uglygep6 = getelementptr i8, i8* %1, i32 %lsr.iv1
%scevgep7 = getelementptr i8, i8* %uglygep6, i32 16
tail call void @llvm.arm.neon.vst1.p0i8.v4f32(i8* nonnull %scevgep7, <4 x float> %3, i32 4)
%uglygep4 = getelementptr i8, i8* %1, i32 %lsr.iv1
%scevgep5 = getelementptr i8, i8* %uglygep4, i32 32
tail call void @llvm.arm.neon.vst1.p0i8.v4f32(i8* nonnull %scevgep5, <4 x float> %4, i32 4)
%uglygep = getelementptr i8, i8* %1, i32 %lsr.iv1
%scevgep = getelementptr i8, i8* %uglygep, i32 48
tail call void @llvm.arm.neon.vst1.p0i8.v4f32(i8* nonnull %scevgep, <4 x float> %5, i32 4)
%lsr.iv.next = add i32 %lsr.iv, -1
%lsr.iv.next2 = add nuw i32 %lsr.iv1, 64
%exitcond.not = icmp eq i32 %lsr.iv.next, 0
br i1 %exitcond.not, label %for.cond.cleanup, label %for.body
}
declare void @external_function(float*)
declare <4 x float> @llvm.arm.neon.vld1.v4f32.p0i8(i8*, i32) nounwind readonly
declare void @llvm.arm.neon.vst1.p0i8.v4f32(i8*, <4 x float>, i32) nounwind argmemonly
|
