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
|
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s --mattr=+mve.fp,+fp64 -o - | FileCheck %s
target triple = "thumbv8.1m.main-none-none-eabi"
; Expected to transform
define arm_aapcs_vfpcc <4 x float> @simple_mul(<4 x float> %a, <4 x float> %b) {
; CHECK-LABEL: simple_mul:
; CHECK: @ %bb.0: @ %entry
; CHECK-NEXT: vcmul.f32 q2, q0, q1, #0
; CHECK-NEXT: vcmla.f32 q2, q0, q1, #90
; CHECK-NEXT: vmov q0, q2
; CHECK-NEXT: bx lr
entry:
%strided.vec = shufflevector <4 x float> %a, <4 x float> poison, <2 x i32> <i32 0, i32 2>
%strided.vec17 = shufflevector <4 x float> %a, <4 x float> poison, <2 x i32> <i32 1, i32 3>
%strided.vec19 = shufflevector <4 x float> %b, <4 x float> poison, <2 x i32> <i32 0, i32 2>
%strided.vec20 = shufflevector <4 x float> %b, <4 x float> poison, <2 x i32> <i32 1, i32 3>
%0 = fmul fast <2 x float> %strided.vec20, %strided.vec
%1 = fmul fast <2 x float> %strided.vec19, %strided.vec17
%2 = fadd fast <2 x float> %1, %0
%3 = fmul fast <2 x float> %strided.vec19, %strided.vec
%4 = fmul fast <2 x float> %strided.vec17, %strided.vec20
%5 = fsub fast <2 x float> %3, %4
%interleaved.vec = shufflevector <2 x float> %5, <2 x float> %2, <4 x i32> <i32 0, i32 2, i32 1, i32 3>
ret <4 x float> %interleaved.vec
}
; Expected to not transform
define arm_aapcs_vfpcc <4 x float> @simple_mul_no_contract(<4 x float> %a, <4 x float> %b) {
; CHECK-LABEL: simple_mul_no_contract:
; CHECK: @ %bb.0: @ %entry
; CHECK-NEXT: .vsave {d8, d9, d10, d11}
; CHECK-NEXT: vpush {d8, d9, d10, d11}
; CHECK-NEXT: vmov.f32 s8, s5
; CHECK-NEXT: vmov.f32 s12, s1
; CHECK-NEXT: vmov.f32 s9, s7
; CHECK-NEXT: vmov.f32 s13, s3
; CHECK-NEXT: vmov.f32 s1, s2
; CHECK-NEXT: vmul.f32 q4, q3, q2
; CHECK-NEXT: vmov.f32 s5, s6
; CHECK-NEXT: vmul.f32 q2, q2, q0
; CHECK-NEXT: vmul.f32 q5, q1, q0
; CHECK-NEXT: vfma.f32 q2, q1, q3
; CHECK-NEXT: vsub.f32 q4, q5, q4
; CHECK-NEXT: vmov.f32 s1, s8
; CHECK-NEXT: vmov.f32 s0, s16
; CHECK-NEXT: vmov.f32 s2, s17
; CHECK-NEXT: vmov.f32 s3, s9
; CHECK-NEXT: vpop {d8, d9, d10, d11}
; CHECK-NEXT: bx lr
entry:
%strided.vec = shufflevector <4 x float> %a, <4 x float> poison, <2 x i32> <i32 0, i32 2>
%strided.vec17 = shufflevector <4 x float> %a, <4 x float> poison, <2 x i32> <i32 1, i32 3>
%strided.vec19 = shufflevector <4 x float> %b, <4 x float> poison, <2 x i32> <i32 0, i32 2>
%strided.vec20 = shufflevector <4 x float> %b, <4 x float> poison, <2 x i32> <i32 1, i32 3>
%0 = fmul fast <2 x float> %strided.vec20, %strided.vec
%1 = fmul fast <2 x float> %strided.vec19, %strided.vec17
%2 = fadd fast <2 x float> %1, %0
%3 = fmul fast <2 x float> %strided.vec19, %strided.vec
%4 = fmul fast <2 x float> %strided.vec17, %strided.vec20
%5 = fsub <2 x float> %3, %4
%interleaved.vec = shufflevector <2 x float> %5, <2 x float> %2, <4 x i32> <i32 0, i32 2, i32 1, i32 3>
ret <4 x float> %interleaved.vec
}
; Expected to transform
define arm_aapcs_vfpcc <4 x float> @three_way_mul(<4 x float> %a, <4 x float> %b, <4 x float> %c) {
; CHECK-LABEL: three_way_mul:
; CHECK: @ %bb.0: @ %entry
; CHECK-NEXT: vcmul.f32 q3, q1, q0, #0
; CHECK-NEXT: vcmla.f32 q3, q1, q0, #90
; CHECK-NEXT: vcmul.f32 q0, q2, q3, #0
; CHECK-NEXT: vcmla.f32 q0, q2, q3, #90
; CHECK-NEXT: bx lr
entry:
%strided.vec = shufflevector <4 x float> %a, <4 x float> poison, <2 x i32> <i32 0, i32 2>
%strided.vec39 = shufflevector <4 x float> %a, <4 x float> poison, <2 x i32> <i32 1, i32 3>
%strided.vec41 = shufflevector <4 x float> %b, <4 x float> poison, <2 x i32> <i32 0, i32 2>
%strided.vec42 = shufflevector <4 x float> %b, <4 x float> poison, <2 x i32> <i32 1, i32 3>
%strided.vec44 = shufflevector <4 x float> %c, <4 x float> poison, <2 x i32> <i32 0, i32 2>
%strided.vec45 = shufflevector <4 x float> %c, <4 x float> poison, <2 x i32> <i32 1, i32 3>
%0 = fmul fast <2 x float> %strided.vec41, %strided.vec
%1 = fmul fast <2 x float> %strided.vec42, %strided.vec39
%2 = fsub fast <2 x float> %0, %1
%3 = fmul fast <2 x float> %2, %strided.vec45
%4 = fmul fast <2 x float> %strided.vec42, %strided.vec
%5 = fmul fast <2 x float> %strided.vec39, %strided.vec41
%6 = fadd fast <2 x float> %4, %5
%7 = fmul fast <2 x float> %6, %strided.vec44
%8 = fadd fast <2 x float> %3, %7
%9 = fmul fast <2 x float> %2, %strided.vec44
%10 = fmul fast <2 x float> %6, %strided.vec45
%11 = fsub fast <2 x float> %9, %10
%interleaved.vec = shufflevector <2 x float> %11, <2 x float> %8, <4 x i32> <i32 0, i32 2, i32 1, i32 3>
ret <4 x float> %interleaved.vec
}
; Expected to transform
define arm_aapcs_vfpcc <4 x float> @simple_add_90(<4 x float> %a, <4 x float> %b) {
; CHECK-LABEL: simple_add_90:
; CHECK: @ %bb.0: @ %entry
; CHECK-NEXT: vcadd.f32 q2, q1, q0, #90
; CHECK-NEXT: vmov q0, q2
; CHECK-NEXT: bx lr
entry:
%strided.vec = shufflevector <4 x float> %a, <4 x float> poison, <2 x i32> <i32 0, i32 2>
%strided.vec17 = shufflevector <4 x float> %a, <4 x float> poison, <2 x i32> <i32 1, i32 3>
%strided.vec19 = shufflevector <4 x float> %b, <4 x float> poison, <2 x i32> <i32 0, i32 2>
%strided.vec20 = shufflevector <4 x float> %b, <4 x float> poison, <2 x i32> <i32 1, i32 3>
%0 = fsub fast <2 x float> %strided.vec19, %strided.vec17
%1 = fadd fast <2 x float> %strided.vec20, %strided.vec
%interleaved.vec = shufflevector <2 x float> %0, <2 x float> %1, <4 x i32> <i32 0, i32 2, i32 1, i32 3>
ret <4 x float> %interleaved.vec
}
; Expected to not transform, fadd commutativity is not yet implemented
define arm_aapcs_vfpcc <4 x float> @simple_add_270_false(<4 x float> %a, <4 x float> %b) {
; CHECK-LABEL: simple_add_270_false:
; CHECK: @ %bb.0: @ %entry
; CHECK-NEXT: vmov.f32 s8, s4
; CHECK-NEXT: vmov.f32 s12, s1
; CHECK-NEXT: vmov.f32 s4, s5
; CHECK-NEXT: vmov.f32 s9, s6
; CHECK-NEXT: vmov.f32 s13, s3
; CHECK-NEXT: vmov.f32 s1, s2
; CHECK-NEXT: vsub.f32 q2, q3, q2
; CHECK-NEXT: vmov.f32 s5, s7
; CHECK-NEXT: vadd.f32 q1, q1, q0
; CHECK-NEXT: vmov.f32 s1, s8
; CHECK-NEXT: vmov.f32 s0, s4
; CHECK-NEXT: vmov.f32 s2, s5
; CHECK-NEXT: vmov.f32 s3, s9
; CHECK-NEXT: bx lr
entry:
%strided.vec = shufflevector <4 x float> %a, <4 x float> poison, <2 x i32> <i32 0, i32 2>
%strided.vec17 = shufflevector <4 x float> %a, <4 x float> poison, <2 x i32> <i32 1, i32 3>
%strided.vec19 = shufflevector <4 x float> %b, <4 x float> poison, <2 x i32> <i32 0, i32 2>
%strided.vec20 = shufflevector <4 x float> %b, <4 x float> poison, <2 x i32> <i32 1, i32 3>
%0 = fadd fast <2 x float> %strided.vec20, %strided.vec
%1 = fsub fast <2 x float> %strided.vec17, %strided.vec19
%interleaved.vec = shufflevector <2 x float> %0, <2 x float> %1, <4 x i32> <i32 0, i32 2, i32 1, i32 3>
ret <4 x float> %interleaved.vec
}
; Expected to transform
define arm_aapcs_vfpcc <4 x float> @simple_add_270_true(<4 x float> %a, <4 x float> %b) {
; CHECK-LABEL: simple_add_270_true:
; CHECK: @ %bb.0: @ %entry
; CHECK-NEXT: vcadd.f32 q2, q0, q1, #270
; CHECK-NEXT: vmov q0, q2
; CHECK-NEXT: bx lr
entry:
%strided.vec = shufflevector <4 x float> %a, <4 x float> poison, <2 x i32> <i32 0, i32 2>
%strided.vec17 = shufflevector <4 x float> %a, <4 x float> poison, <2 x i32> <i32 1, i32 3>
%strided.vec19 = shufflevector <4 x float> %b, <4 x float> poison, <2 x i32> <i32 0, i32 2>
%strided.vec20 = shufflevector <4 x float> %b, <4 x float> poison, <2 x i32> <i32 1, i32 3>
%0 = fadd fast <2 x float> %strided.vec, %strided.vec20
%1 = fsub fast <2 x float> %strided.vec17, %strided.vec19
%interleaved.vec = shufflevector <2 x float> %0, <2 x float> %1, <4 x i32> <i32 0, i32 2, i32 1, i32 3>
ret <4 x float> %interleaved.vec
}
; Expected to not transform
define arm_aapcs_vfpcc <4 x float> @add_external_use(<4 x float> %a, <4 x float> %b) {
; CHECK-LABEL: add_external_use:
; CHECK: @ %bb.0: @ %entry
; CHECK-NEXT: vmov.f32 s8, s4
; CHECK-NEXT: vmov.f32 s12, s1
; CHECK-NEXT: vmov.f32 s4, s5
; CHECK-NEXT: vmov.f32 s9, s6
; CHECK-NEXT: vmov.f32 s13, s3
; CHECK-NEXT: vmov.f32 s5, s7
; CHECK-NEXT: vadd.f32 q2, q3, q2
; CHECK-NEXT: vmov.f32 s1, s2
; CHECK-NEXT: vsub.f32 q1, q0, q1
; CHECK-NEXT: vmov.f32 s1, s8
; CHECK-NEXT: vmov.f32 s0, s4
; CHECK-NEXT: vmov.f32 s2, s5
; CHECK-NEXT: vmov.f32 s3, s9
; CHECK-NEXT: bx lr
entry:
%a.real = shufflevector <4 x float> %a, <4 x float> poison, <2 x i32> <i32 0, i32 2>
%a.imag = shufflevector <4 x float> %a, <4 x float> poison, <2 x i32> <i32 1, i32 3>
%b.real = shufflevector <4 x float> %b, <4 x float> poison, <2 x i32> <i32 0, i32 2>
%b.imag = shufflevector <4 x float> %b, <4 x float> poison, <2 x i32> <i32 1, i32 3>
%0 = fsub fast <2 x float> %a.real, %b.imag
%1 = fadd fast <2 x float> %a.imag, %b.real
%interleaved.vec = shufflevector <2 x float> %0, <2 x float> %1, <4 x i32> <i32 0, i32 2, i32 1, i32 3>
%dup = shufflevector <2 x float> %0, <2 x float> poison, <4 x i32> <i32 0, i32 1, i32 0, i32 1>
%interleaved.vec2 = shufflevector <4 x float> %interleaved.vec, <4 x float> %dup, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
ret <4 x float> %interleaved.vec2
}
define arm_aapcs_vfpcc <4 x float> @mul_mul_with_fneg(<4 x float> %a, <4 x float> %b) {
; CHECK-LABEL: mul_mul_with_fneg:
; CHECK: @ %bb.0: @ %entry
; CHECK-NEXT: vcmul.f32 q2, q1, q0, #270
; CHECK-NEXT: vcmla.f32 q2, q1, q0, #180
; CHECK-NEXT: vmov q0, q2
; CHECK-NEXT: bx lr
entry:
%a.real = shufflevector <4 x float> %a, <4 x float> poison, <2 x i32> <i32 0, i32 2>
%a.imag = shufflevector <4 x float> %a, <4 x float> poison, <2 x i32> <i32 1, i32 3>
%b.real = shufflevector <4 x float> %b, <4 x float> poison, <2 x i32> <i32 0, i32 2>
%b.imag = shufflevector <4 x float> %b, <4 x float> poison, <2 x i32> <i32 1, i32 3>
%0 = fneg fast <2 x float> %a.imag
%1 = fmul fast <2 x float> %b.real, %0
%2 = fmul fast <2 x float> %a.real, %b.imag
%3 = fsub fast <2 x float> %1, %2
%4 = fmul fast <2 x float> %b.imag, %a.imag
%5 = fmul fast <2 x float> %a.real, %b.real
%6 = fsub fast <2 x float> %4, %5
%interleaved.vec = shufflevector <2 x float> %6, <2 x float> %3, <4 x i32> <i32 0, i32 2, i32 1, i32 3>
ret <4 x float> %interleaved.vec
}
; Expected to not transform
define arm_aapcs_vfpcc <12 x float> @abp90c12(<12 x float> %a, <12 x float> %b, <12 x float> %c) {
; CHECK-LABEL: abp90c12:
; CHECK: @ %bb.0: @ %entry
; CHECK-NEXT: .vsave {d8, d9, d10, d11, d12, d13, d14, d15}
; CHECK-NEXT: vpush {d8, d9, d10, d11, d12, d13, d14, d15}
; CHECK-NEXT: .pad #48
; CHECK-NEXT: sub sp, #48
; CHECK-NEXT: vldr s23, [sp, #124]
; CHECK-NEXT: vmov.f32 s20, s13
; CHECK-NEXT: vldr s22, [sp, #116]
; CHECK-NEXT: vmov.f32 s25, s11
; CHECK-NEXT: vmov.f32 s13, s10
; CHECK-NEXT: vldr s19, [sp, #120]
; CHECK-NEXT: vmov.f32 s11, s6
; CHECK-NEXT: vldr s18, [sp, #112]
; CHECK-NEXT: vmov.f32 s6, s5
; CHECK-NEXT: vldr s31, [sp, #172]
; CHECK-NEXT: vmov.f32 s10, s4
; CHECK-NEXT: vldr s30, [sp, #164]
; CHECK-NEXT: vmov.f32 s21, s15
; CHECK-NEXT: vldr s29, [sp, #156]
; CHECK-NEXT: vmov.f32 s5, s3
; CHECK-NEXT: vldr s28, [sp, #148]
; CHECK-NEXT: vmov.f32 s4, s1
; CHECK-NEXT: vmov.f32 s24, s9
; CHECK-NEXT: vmov.f32 s16, s12
; CHECK-NEXT: vstrw.32 q6, [sp, #16] @ 16-byte Spill
; CHECK-NEXT: vmov.f32 s12, s8
; CHECK-NEXT: vldr s27, [sp, #168]
; CHECK-NEXT: vmov.f32 s17, s14
; CHECK-NEXT: vldr s26, [sp, #160]
; CHECK-NEXT: vmov.f32 s9, s2
; CHECK-NEXT: vldr s25, [sp, #152]
; CHECK-NEXT: vmov.f32 s8, s0
; CHECK-NEXT: vmul.f32 q0, q5, q1
; CHECK-NEXT: vmul.f32 q1, q4, q1
; CHECK-NEXT: vneg.f32 q0, q0
; CHECK-NEXT: vldr s24, [sp, #144]
; CHECK-NEXT: vfma.f32 q1, q5, q2
; CHECK-NEXT: vstrw.32 q0, [sp] @ 16-byte Spill
; CHECK-NEXT: vstrw.32 q3, [sp, #32] @ 16-byte Spill
; CHECK-NEXT: vsub.f32 q6, q6, q1
; CHECK-NEXT: vldrw.u32 q1, [sp] @ 16-byte Reload
; CHECK-NEXT: vldr s13, [sp, #140]
; CHECK-NEXT: vfma.f32 q1, q4, q2
; CHECK-NEXT: vldr s12, [sp, #132]
; CHECK-NEXT: vadd.f32 q1, q7, q1
; CHECK-NEXT: vldrw.u32 q7, [sp, #16] @ 16-byte Reload
; CHECK-NEXT: vldr s1, [sp, #136]
; CHECK-NEXT: vstrw.32 q3, [sp, #16] @ 16-byte Spill
; CHECK-NEXT: vmul.f32 q2, q3, q7
; CHECK-NEXT: vldr s0, [sp, #128]
; CHECK-NEXT: vldrw.u32 q3, [sp, #32] @ 16-byte Reload
; CHECK-NEXT: vneg.f32 q2, q2
; CHECK-NEXT: vldr s21, [sp, #184]
; CHECK-NEXT: vfma.f32 q2, q0, q3
; CHECK-NEXT: vmul.f32 q0, q0, q7
; CHECK-NEXT: vldrw.u32 q7, [sp, #16] @ 16-byte Reload
; CHECK-NEXT: vldr s20, [sp, #176]
; CHECK-NEXT: vldr s17, [sp, #188]
; CHECK-NEXT: vldr s16, [sp, #180]
; CHECK-NEXT: vfma.f32 q0, q7, q3
; CHECK-NEXT: vsub.f32 q3, q5, q0
; CHECK-NEXT: vmov.f32 s1, s4
; CHECK-NEXT: vadd.f32 q4, q4, q2
; CHECK-NEXT: vmov.f32 s3, s5
; CHECK-NEXT: vmov.f32 s5, s6
; CHECK-NEXT: vmov.f32 s0, s24
; CHECK-NEXT: vmov.f32 s2, s25
; CHECK-NEXT: vmov.f32 s4, s26
; CHECK-NEXT: vmov.f32 s6, s27
; CHECK-NEXT: vmov.f32 s8, s12
; CHECK-NEXT: vmov.f32 s9, s16
; CHECK-NEXT: vmov.f32 s10, s13
; CHECK-NEXT: vmov.f32 s11, s17
; CHECK-NEXT: add sp, #48
; CHECK-NEXT: vpop {d8, d9, d10, d11, d12, d13, d14, d15}
; CHECK-NEXT: bx lr
entry:
%ar = shufflevector <12 x float> %a, <12 x float> poison, <6 x i32> <i32 0, i32 2, i32 4, i32 6, i32 8, i32 10>
%ai = shufflevector <12 x float> %a, <12 x float> poison, <6 x i32> <i32 1, i32 3, i32 5, i32 7, i32 9, i32 11>
%br = shufflevector <12 x float> %b, <12 x float> poison, <6 x i32> <i32 0, i32 2, i32 4, i32 6, i32 8, i32 10>
%bi = shufflevector <12 x float> %b, <12 x float> poison, <6 x i32> <i32 1, i32 3, i32 5, i32 7, i32 9, i32 11>
%cr = shufflevector <12 x float> %c, <12 x float> poison, <6 x i32> <i32 0, i32 2, i32 4, i32 6, i32 8, i32 10>
%ci = shufflevector <12 x float> %c, <12 x float> poison, <6 x i32> <i32 1, i32 3, i32 5, i32 7, i32 9, i32 11>
%i6 = fmul fast <6 x float> %br, %ar
%i7 = fmul fast <6 x float> %bi, %ai
%xr = fsub fast <6 x float> %i6, %i7
%i9 = fmul fast <6 x float> %bi, %ar
%i10 = fmul fast <6 x float> %br, %ai
%xi = fadd fast <6 x float> %i9, %i10
%zr = fsub fast <6 x float> %cr, %xi
%zi = fadd fast <6 x float> %ci, %xr
%interleaved.vec = shufflevector <6 x float> %zr, <6 x float> %zi, <12 x i32> <i32 0, i32 6, i32 1, i32 7, i32 2, i32 8, i32 3, i32 9, i32 4, i32 10, i32 5, i32 11>
ret <12 x float> %interleaved.vec
}
|
