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
|
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s --mattr=+complxnum,+neon,+fullfp16 -o - | FileCheck %s
target triple = "aarch64"
; Expected to transform
define <4 x float> @simple_mul(<4 x float> %a, <4 x float> %b) {
; CHECK-LABEL: simple_mul:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: movi v2.2d, #0000000000000000
; CHECK-NEXT: fcmla v2.4s, v0.4s, v1.4s, #0
; CHECK-NEXT: fcmla v2.4s, v0.4s, v1.4s, #90
; CHECK-NEXT: mov v0.16b, v2.16b
; CHECK-NEXT: ret
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 <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: ext v2.16b, v0.16b, v0.16b, #8
; CHECK-NEXT: ext v3.16b, v1.16b, v1.16b, #8
; CHECK-NEXT: zip1 v4.2s, v0.2s, v2.2s
; CHECK-NEXT: zip2 v0.2s, v0.2s, v2.2s
; CHECK-NEXT: zip2 v5.2s, v1.2s, v3.2s
; CHECK-NEXT: zip1 v1.2s, v1.2s, v3.2s
; CHECK-NEXT: fmul v2.2s, v5.2s, v4.2s
; CHECK-NEXT: fmul v3.2s, v1.2s, v4.2s
; CHECK-NEXT: fmul v4.2s, v0.2s, v5.2s
; CHECK-NEXT: fmla v2.2s, v0.2s, v1.2s
; CHECK-NEXT: fsub v0.2s, v3.2s, v4.2s
; CHECK-NEXT: zip1 v0.4s, v0.4s, v2.4s
; CHECK-NEXT: ret
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 <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: movi v4.2d, #0000000000000000
; CHECK-NEXT: movi v3.2d, #0000000000000000
; CHECK-NEXT: fcmla v4.4s, v1.4s, v0.4s, #0
; CHECK-NEXT: fcmla v4.4s, v1.4s, v0.4s, #90
; CHECK-NEXT: fcmla v3.4s, v2.4s, v4.4s, #0
; CHECK-NEXT: fcmla v3.4s, v2.4s, v4.4s, #90
; CHECK-NEXT: mov v0.16b, v3.16b
; CHECK-NEXT: ret
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 <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: fcadd v0.4s, v1.4s, v0.4s, #90
; CHECK-NEXT: ret
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 <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: fcadd v0.4s, v0.4s, v1.4s, #270
; CHECK-NEXT: ret
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 <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: fcadd v0.4s, v0.4s, v1.4s, #270
; CHECK-NEXT: ret
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 <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: ext v2.16b, v0.16b, v0.16b, #8
; CHECK-NEXT: ext v3.16b, v1.16b, v1.16b, #8
; CHECK-NEXT: zip1 v4.2s, v0.2s, v2.2s
; CHECK-NEXT: zip2 v0.2s, v0.2s, v2.2s
; CHECK-NEXT: zip1 v2.2s, v1.2s, v3.2s
; CHECK-NEXT: zip2 v1.2s, v1.2s, v3.2s
; CHECK-NEXT: fsub v1.2s, v4.2s, v1.2s
; CHECK-NEXT: fadd v0.2s, v0.2s, v2.2s
; CHECK-NEXT: zip1 v0.4s, v1.4s, v0.4s
; CHECK-NEXT: ret
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
}
; Expected to transform
define <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: movi v2.2d, #0000000000000000
; CHECK-NEXT: fcmla v2.4s, v1.4s, v0.4s, #270
; CHECK-NEXT: fcmla v2.4s, v1.4s, v0.4s, #180
; CHECK-NEXT: mov v0.16b, v2.16b
; CHECK-NEXT: ret
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 <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: ldr s21, [sp, #32]
; CHECK-NEXT: add x9, sp, #48
; CHECK-NEXT: // kill: def $s2 killed $s2 def $q2
; CHECK-NEXT: // kill: def $s0 killed $s0 def $q0
; CHECK-NEXT: ldr s23, [sp, #40]
; CHECK-NEXT: add x11, sp, #56
; CHECK-NEXT: mov v0.s[1], v2.s[0]
; CHECK-NEXT: ldr s2, [sp]
; CHECK-NEXT: add x10, sp, #16
; CHECK-NEXT: ld1 { v21.s }[1], [x9]
; CHECK-NEXT: add x9, sp, #64
; CHECK-NEXT: ld1 { v23.s }[1], [x11]
; CHECK-NEXT: // kill: def $s1 killed $s1 def $q1
; CHECK-NEXT: // kill: def $s3 killed $s3 def $q3
; CHECK-NEXT: ldr s22, [sp, #96]
; CHECK-NEXT: add x11, sp, #24
; CHECK-NEXT: ld1 { v2.s }[1], [x10]
; CHECK-NEXT: add x10, sp, #72
; CHECK-NEXT: mov v1.s[1], v3.s[0]
; CHECK-NEXT: ld1 { v21.s }[2], [x9]
; CHECK-NEXT: ldr s24, [sp, #8]
; CHECK-NEXT: add x9, sp, #112
; CHECK-NEXT: ld1 { v23.s }[2], [x10]
; CHECK-NEXT: add x10, sp, #80
; CHECK-NEXT: // kill: def $s5 killed $s5 def $q5
; CHECK-NEXT: ldr s18, [sp, #128]
; CHECK-NEXT: // kill: def $s7 killed $s7 def $q7
; CHECK-NEXT: // kill: def $s4 killed $s4 def $q4
; CHECK-NEXT: // kill: def $s6 killed $s6 def $q6
; CHECK-NEXT: mov v1.s[2], v5.s[0]
; CHECK-NEXT: ldr s20, [sp, #104]
; CHECK-NEXT: ld1 { v24.s }[1], [x11]
; CHECK-NEXT: add x11, sp, #88
; CHECK-NEXT: ld1 { v22.s }[1], [x9]
; CHECK-NEXT: add x9, sp, #144
; CHECK-NEXT: ld1 { v21.s }[3], [x10]
; CHECK-NEXT: add x10, sp, #120
; CHECK-NEXT: mov v0.s[2], v4.s[0]
; CHECK-NEXT: ld1 { v23.s }[3], [x11]
; CHECK-NEXT: ld1 { v18.s }[1], [x9]
; CHECK-NEXT: add x11, sp, #152
; CHECK-NEXT: ld1 { v20.s }[1], [x10]
; CHECK-NEXT: add x10, sp, #160
; CHECK-NEXT: mov v1.s[3], v7.s[0]
; CHECK-NEXT: ldr s17, [sp, #136]
; CHECK-NEXT: ldr s19, [sp, #192]
; CHECK-NEXT: add x9, sp, #208
; CHECK-NEXT: mov v0.s[3], v6.s[0]
; CHECK-NEXT: ld1 { v18.s }[2], [x10]
; CHECK-NEXT: ld1 { v17.s }[1], [x11]
; CHECK-NEXT: add x10, sp, #176
; CHECK-NEXT: fmul v3.4s, v23.4s, v1.4s
; CHECK-NEXT: ld1 { v19.s }[1], [x9]
; CHECK-NEXT: fmul v4.4s, v20.4s, v24.4s
; CHECK-NEXT: add x9, sp, #168
; CHECK-NEXT: fmul v1.4s, v21.4s, v1.4s
; CHECK-NEXT: ld1 { v18.s }[3], [x10]
; CHECK-NEXT: fmul v5.4s, v22.4s, v24.4s
; CHECK-NEXT: ldr s16, [sp, #200]
; CHECK-NEXT: ld1 { v17.s }[2], [x9]
; CHECK-NEXT: add x11, sp, #216
; CHECK-NEXT: fneg v3.4s, v3.4s
; CHECK-NEXT: add x9, sp, #184
; CHECK-NEXT: fneg v4.4s, v4.4s
; CHECK-NEXT: fmla v1.4s, v0.4s, v23.4s
; CHECK-NEXT: fmla v5.4s, v2.4s, v20.4s
; CHECK-NEXT: ld1 { v16.s }[1], [x11]
; CHECK-NEXT: ld1 { v17.s }[3], [x9]
; CHECK-NEXT: fmla v3.4s, v0.4s, v21.4s
; CHECK-NEXT: fmla v4.4s, v2.4s, v22.4s
; CHECK-NEXT: fsub v0.4s, v18.4s, v1.4s
; CHECK-NEXT: fsub v1.4s, v19.4s, v5.4s
; CHECK-NEXT: fadd v2.4s, v17.4s, v3.4s
; CHECK-NEXT: fadd v3.4s, v16.4s, v4.4s
; CHECK-NEXT: ext v4.16b, v0.16b, v1.16b, #12
; CHECK-NEXT: ext v5.16b, v2.16b, v3.16b, #12
; CHECK-NEXT: trn2 v1.4s, v1.4s, v3.4s
; CHECK-NEXT: ext v4.16b, v0.16b, v4.16b, #12
; CHECK-NEXT: zip2 v3.4s, v0.4s, v2.4s
; CHECK-NEXT: ext v5.16b, v2.16b, v5.16b, #8
; CHECK-NEXT: zip1 v0.4s, v0.4s, v2.4s
; CHECK-NEXT: rev64 v4.4s, v4.4s
; CHECK-NEXT: str q0, [x8]
; CHECK-NEXT: trn2 v4.4s, v4.4s, v5.4s
; CHECK-NEXT: ext v1.16b, v4.16b, v1.16b, #8
; CHECK-NEXT: mov v3.d[1], v4.d[0]
; CHECK-NEXT: stp q3, q1, [x8, #16]
; CHECK-NEXT: ret
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
}
|
