1 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 3
2 ; RUN: llc < %s -mtriple=riscv64 -mattr=+m,+v,+xsfvcp \
3 ; RUN: -riscv-use-rematerializable-movimm=false | FileCheck %s --check-prefix=NOREMAT
4 ; RUN: llc < %s -mtriple=riscv64 -mattr=+m,+v,+xsfvcp \
5 ; RUN: --riscv-use-rematerializable-movimm=true | FileCheck %s --check-prefix=REMAT
7 define void @test(ptr %0, ptr %1, i64 %2) {
10 ; NOREMAT-NEXT: addi sp, sp, -368
11 ; NOREMAT-NEXT: .cfi_def_cfa_offset 368
12 ; NOREMAT-NEXT: sd ra, 360(sp) # 8-byte Folded Spill
13 ; NOREMAT-NEXT: sd s0, 352(sp) # 8-byte Folded Spill
14 ; NOREMAT-NEXT: sd s1, 344(sp) # 8-byte Folded Spill
15 ; NOREMAT-NEXT: sd s2, 336(sp) # 8-byte Folded Spill
16 ; NOREMAT-NEXT: sd s3, 328(sp) # 8-byte Folded Spill
17 ; NOREMAT-NEXT: sd s4, 320(sp) # 8-byte Folded Spill
18 ; NOREMAT-NEXT: sd s5, 312(sp) # 8-byte Folded Spill
19 ; NOREMAT-NEXT: sd s6, 304(sp) # 8-byte Folded Spill
20 ; NOREMAT-NEXT: sd s7, 296(sp) # 8-byte Folded Spill
21 ; NOREMAT-NEXT: sd s8, 288(sp) # 8-byte Folded Spill
22 ; NOREMAT-NEXT: sd s9, 280(sp) # 8-byte Folded Spill
23 ; NOREMAT-NEXT: sd s10, 272(sp) # 8-byte Folded Spill
24 ; NOREMAT-NEXT: sd s11, 264(sp) # 8-byte Folded Spill
25 ; NOREMAT-NEXT: .cfi_offset ra, -8
26 ; NOREMAT-NEXT: .cfi_offset s0, -16
27 ; NOREMAT-NEXT: .cfi_offset s1, -24
28 ; NOREMAT-NEXT: .cfi_offset s2, -32
29 ; NOREMAT-NEXT: .cfi_offset s3, -40
30 ; NOREMAT-NEXT: .cfi_offset s4, -48
31 ; NOREMAT-NEXT: .cfi_offset s5, -56
32 ; NOREMAT-NEXT: .cfi_offset s6, -64
33 ; NOREMAT-NEXT: .cfi_offset s7, -72
34 ; NOREMAT-NEXT: .cfi_offset s8, -80
35 ; NOREMAT-NEXT: .cfi_offset s9, -88
36 ; NOREMAT-NEXT: .cfi_offset s10, -96
37 ; NOREMAT-NEXT: .cfi_offset s11, -104
38 ; NOREMAT-NEXT: li a2, 32
39 ; NOREMAT-NEXT: vsetvli zero, a2, e32, m2, ta, ma
40 ; NOREMAT-NEXT: vle32.v v8, (a0)
41 ; NOREMAT-NEXT: addi a2, a0, 512
42 ; NOREMAT-NEXT: vle32.v v10, (a2)
43 ; NOREMAT-NEXT: addi a2, a0, 1024
44 ; NOREMAT-NEXT: vle32.v v12, (a2)
45 ; NOREMAT-NEXT: sf.vc.vv 3, 0, v8, v10
46 ; NOREMAT-NEXT: vle32.v v8, (a2)
47 ; NOREMAT-NEXT: addi a2, a0, 1536
48 ; NOREMAT-NEXT: vle32.v v14, (a2)
49 ; NOREMAT-NEXT: sf.vc.vv 3, 0, v10, v12
50 ; NOREMAT-NEXT: vle32.v v10, (a2)
51 ; NOREMAT-NEXT: li a2, 1
52 ; NOREMAT-NEXT: slli a2, a2, 11
53 ; NOREMAT-NEXT: sd a2, 256(sp) # 8-byte Folded Spill
54 ; NOREMAT-NEXT: add a2, a0, a2
55 ; NOREMAT-NEXT: vle32.v v12, (a2)
56 ; NOREMAT-NEXT: sf.vc.vv 3, 0, v8, v14
57 ; NOREMAT-NEXT: vle32.v v8, (a2)
58 ; NOREMAT-NEXT: li a4, 5
59 ; NOREMAT-NEXT: slli a2, a4, 9
60 ; NOREMAT-NEXT: sd a2, 248(sp) # 8-byte Folded Spill
61 ; NOREMAT-NEXT: add a2, a0, a2
62 ; NOREMAT-NEXT: vle32.v v14, (a2)
63 ; NOREMAT-NEXT: sf.vc.vv 3, 0, v10, v12
64 ; NOREMAT-NEXT: vle32.v v10, (a2)
65 ; NOREMAT-NEXT: li a5, 3
66 ; NOREMAT-NEXT: slli a2, a5, 10
67 ; NOREMAT-NEXT: sd a2, 240(sp) # 8-byte Folded Spill
68 ; NOREMAT-NEXT: add a2, a0, a2
69 ; NOREMAT-NEXT: vle32.v v12, (a2)
70 ; NOREMAT-NEXT: sf.vc.vv 3, 0, v8, v14
71 ; NOREMAT-NEXT: vle32.v v8, (a2)
72 ; NOREMAT-NEXT: li a3, 7
73 ; NOREMAT-NEXT: slli a2, a3, 9
74 ; NOREMAT-NEXT: sd a2, 232(sp) # 8-byte Folded Spill
75 ; NOREMAT-NEXT: add a2, a0, a2
76 ; NOREMAT-NEXT: vle32.v v14, (a2)
77 ; NOREMAT-NEXT: sf.vc.vv 3, 0, v10, v12
78 ; NOREMAT-NEXT: vle32.v v10, (a2)
79 ; NOREMAT-NEXT: lui a2, 1
80 ; NOREMAT-NEXT: add a2, a0, a2
81 ; NOREMAT-NEXT: vle32.v v12, (a2)
82 ; NOREMAT-NEXT: sf.vc.vv 3, 0, v8, v14
83 ; NOREMAT-NEXT: vle32.v v8, (a2)
84 ; NOREMAT-NEXT: li a2, 9
85 ; NOREMAT-NEXT: slli a6, a2, 9
86 ; NOREMAT-NEXT: sd a6, 224(sp) # 8-byte Folded Spill
87 ; NOREMAT-NEXT: add a6, a0, a6
88 ; NOREMAT-NEXT: vle32.v v14, (a6)
89 ; NOREMAT-NEXT: sf.vc.vv 3, 0, v10, v12
90 ; NOREMAT-NEXT: vle32.v v10, (a6)
91 ; NOREMAT-NEXT: slli a6, a4, 10
92 ; NOREMAT-NEXT: sd a6, 216(sp) # 8-byte Folded Spill
93 ; NOREMAT-NEXT: add a6, a0, a6
94 ; NOREMAT-NEXT: vle32.v v12, (a6)
95 ; NOREMAT-NEXT: sf.vc.vv 3, 0, v8, v14
96 ; NOREMAT-NEXT: vle32.v v8, (a6)
97 ; NOREMAT-NEXT: li s8, 11
98 ; NOREMAT-NEXT: slli a6, s8, 9
99 ; NOREMAT-NEXT: sd a6, 208(sp) # 8-byte Folded Spill
100 ; NOREMAT-NEXT: add a6, a0, a6
101 ; NOREMAT-NEXT: vle32.v v14, (a6)
102 ; NOREMAT-NEXT: sf.vc.vv 3, 0, v10, v12
103 ; NOREMAT-NEXT: vle32.v v10, (a6)
104 ; NOREMAT-NEXT: slli a5, a5, 11
105 ; NOREMAT-NEXT: sd a5, 200(sp) # 8-byte Folded Spill
106 ; NOREMAT-NEXT: add a5, a0, a5
107 ; NOREMAT-NEXT: vle32.v v12, (a5)
108 ; NOREMAT-NEXT: sf.vc.vv 3, 0, v8, v14
109 ; NOREMAT-NEXT: vle32.v v8, (a5)
110 ; NOREMAT-NEXT: li s2, 13
111 ; NOREMAT-NEXT: slli a5, s2, 9
112 ; NOREMAT-NEXT: sd a5, 192(sp) # 8-byte Folded Spill
113 ; NOREMAT-NEXT: add a5, a0, a5
114 ; NOREMAT-NEXT: vle32.v v14, (a5)
115 ; NOREMAT-NEXT: sf.vc.vv 3, 0, v10, v12
116 ; NOREMAT-NEXT: vle32.v v10, (a5)
117 ; NOREMAT-NEXT: slli a5, a3, 10
118 ; NOREMAT-NEXT: sd a5, 184(sp) # 8-byte Folded Spill
119 ; NOREMAT-NEXT: add a5, a0, a5
120 ; NOREMAT-NEXT: vle32.v v12, (a5)
121 ; NOREMAT-NEXT: sf.vc.vv 3, 0, v8, v14
122 ; NOREMAT-NEXT: vle32.v v8, (a5)
123 ; NOREMAT-NEXT: li t0, 15
124 ; NOREMAT-NEXT: slli a5, t0, 9
125 ; NOREMAT-NEXT: sd a5, 176(sp) # 8-byte Folded Spill
126 ; NOREMAT-NEXT: add a5, a0, a5
127 ; NOREMAT-NEXT: vle32.v v14, (a5)
128 ; NOREMAT-NEXT: sf.vc.vv 3, 0, v10, v12
129 ; NOREMAT-NEXT: vle32.v v10, (a5)
130 ; NOREMAT-NEXT: lui a5, 2
131 ; NOREMAT-NEXT: add a5, a0, a5
132 ; NOREMAT-NEXT: vle32.v v12, (a5)
133 ; NOREMAT-NEXT: sf.vc.vv 3, 0, v8, v14
134 ; NOREMAT-NEXT: vle32.v v8, (a5)
135 ; NOREMAT-NEXT: li a5, 17
136 ; NOREMAT-NEXT: slli a5, a5, 9
137 ; NOREMAT-NEXT: sd a5, 168(sp) # 8-byte Folded Spill
138 ; NOREMAT-NEXT: li a7, 17
139 ; NOREMAT-NEXT: add a5, a0, a5
140 ; NOREMAT-NEXT: vle32.v v14, (a5)
141 ; NOREMAT-NEXT: sf.vc.vv 3, 0, v10, v12
142 ; NOREMAT-NEXT: vle32.v v10, (a5)
143 ; NOREMAT-NEXT: slli a5, a2, 10
144 ; NOREMAT-NEXT: sd a5, 160(sp) # 8-byte Folded Spill
145 ; NOREMAT-NEXT: add a5, a0, a5
146 ; NOREMAT-NEXT: vle32.v v12, (a5)
147 ; NOREMAT-NEXT: sf.vc.vv 3, 0, v8, v14
148 ; NOREMAT-NEXT: vle32.v v8, (a5)
149 ; NOREMAT-NEXT: li a5, 19
150 ; NOREMAT-NEXT: slli a5, a5, 9
151 ; NOREMAT-NEXT: sd a5, 152(sp) # 8-byte Folded Spill
152 ; NOREMAT-NEXT: li a6, 19
153 ; NOREMAT-NEXT: add a5, a0, a5
154 ; NOREMAT-NEXT: vle32.v v14, (a5)
155 ; NOREMAT-NEXT: sf.vc.vv 3, 0, v10, v12
156 ; NOREMAT-NEXT: vle32.v v10, (a5)
157 ; NOREMAT-NEXT: slli a4, a4, 11
158 ; NOREMAT-NEXT: sd a4, 144(sp) # 8-byte Folded Spill
159 ; NOREMAT-NEXT: add a4, a0, a4
160 ; NOREMAT-NEXT: vle32.v v12, (a4)
161 ; NOREMAT-NEXT: sf.vc.vv 3, 0, v8, v14
162 ; NOREMAT-NEXT: vle32.v v8, (a4)
163 ; NOREMAT-NEXT: li s10, 21
164 ; NOREMAT-NEXT: slli a4, s10, 9
165 ; NOREMAT-NEXT: sd a4, 136(sp) # 8-byte Folded Spill
166 ; NOREMAT-NEXT: add a4, a0, a4
167 ; NOREMAT-NEXT: vle32.v v14, (a4)
168 ; NOREMAT-NEXT: sf.vc.vv 3, 0, v10, v12
169 ; NOREMAT-NEXT: vle32.v v10, (a4)
170 ; NOREMAT-NEXT: slli a4, s8, 10
171 ; NOREMAT-NEXT: sd a4, 128(sp) # 8-byte Folded Spill
172 ; NOREMAT-NEXT: add a4, a0, a4
173 ; NOREMAT-NEXT: vle32.v v12, (a4)
174 ; NOREMAT-NEXT: sf.vc.vv 3, 0, v8, v14
175 ; NOREMAT-NEXT: vle32.v v8, (a4)
176 ; NOREMAT-NEXT: li s6, 23
177 ; NOREMAT-NEXT: slli a4, s6, 9
178 ; NOREMAT-NEXT: sd a4, 120(sp) # 8-byte Folded Spill
179 ; NOREMAT-NEXT: add a4, a0, a4
180 ; NOREMAT-NEXT: vle32.v v14, (a4)
181 ; NOREMAT-NEXT: sf.vc.vv 3, 0, v10, v12
182 ; NOREMAT-NEXT: vle32.v v10, (a4)
183 ; NOREMAT-NEXT: lui a4, 3
184 ; NOREMAT-NEXT: add a4, a0, a4
185 ; NOREMAT-NEXT: vle32.v v12, (a4)
186 ; NOREMAT-NEXT: sf.vc.vv 3, 0, v8, v14
187 ; NOREMAT-NEXT: vle32.v v8, (a4)
188 ; NOREMAT-NEXT: li s3, 25
189 ; NOREMAT-NEXT: slli a4, s3, 9
190 ; NOREMAT-NEXT: sd a4, 112(sp) # 8-byte Folded Spill
191 ; NOREMAT-NEXT: add a4, a0, a4
192 ; NOREMAT-NEXT: vle32.v v14, (a4)
193 ; NOREMAT-NEXT: sf.vc.vv 3, 0, v10, v12
194 ; NOREMAT-NEXT: vle32.v v10, (a4)
195 ; NOREMAT-NEXT: slli a4, s2, 10
196 ; NOREMAT-NEXT: sd a4, 104(sp) # 8-byte Folded Spill
197 ; NOREMAT-NEXT: add a4, a0, a4
198 ; NOREMAT-NEXT: vle32.v v12, (a4)
199 ; NOREMAT-NEXT: sf.vc.vv 3, 0, v8, v14
200 ; NOREMAT-NEXT: vle32.v v8, (a4)
201 ; NOREMAT-NEXT: li t5, 27
202 ; NOREMAT-NEXT: slli a4, t5, 9
203 ; NOREMAT-NEXT: sd a4, 96(sp) # 8-byte Folded Spill
204 ; NOREMAT-NEXT: add a4, a0, a4
205 ; NOREMAT-NEXT: vle32.v v14, (a4)
206 ; NOREMAT-NEXT: sf.vc.vv 3, 0, v10, v12
207 ; NOREMAT-NEXT: vle32.v v10, (a4)
208 ; NOREMAT-NEXT: slli a3, a3, 11
209 ; NOREMAT-NEXT: sd a3, 88(sp) # 8-byte Folded Spill
210 ; NOREMAT-NEXT: add a3, a0, a3
211 ; NOREMAT-NEXT: vle32.v v12, (a3)
212 ; NOREMAT-NEXT: sf.vc.vv 3, 0, v8, v14
213 ; NOREMAT-NEXT: vle32.v v8, (a3)
214 ; NOREMAT-NEXT: li t2, 29
215 ; NOREMAT-NEXT: slli a3, t2, 9
216 ; NOREMAT-NEXT: sd a3, 80(sp) # 8-byte Folded Spill
217 ; NOREMAT-NEXT: add a3, a0, a3
218 ; NOREMAT-NEXT: vle32.v v14, (a3)
219 ; NOREMAT-NEXT: sf.vc.vv 3, 0, v10, v12
220 ; NOREMAT-NEXT: vle32.v v10, (a3)
221 ; NOREMAT-NEXT: slli a3, t0, 10
222 ; NOREMAT-NEXT: sd a3, 72(sp) # 8-byte Folded Spill
223 ; NOREMAT-NEXT: add a3, a0, a3
224 ; NOREMAT-NEXT: vle32.v v12, (a3)
225 ; NOREMAT-NEXT: sf.vc.vv 3, 0, v8, v14
226 ; NOREMAT-NEXT: vle32.v v8, (a3)
227 ; NOREMAT-NEXT: li a5, 31
228 ; NOREMAT-NEXT: slli a3, a5, 9
229 ; NOREMAT-NEXT: sd a3, 64(sp) # 8-byte Folded Spill
230 ; NOREMAT-NEXT: add a3, a0, a3
231 ; NOREMAT-NEXT: vle32.v v14, (a3)
232 ; NOREMAT-NEXT: sf.vc.vv 3, 0, v10, v12
233 ; NOREMAT-NEXT: vle32.v v10, (a3)
234 ; NOREMAT-NEXT: lui a4, 4
235 ; NOREMAT-NEXT: add a3, a0, a4
236 ; NOREMAT-NEXT: vle32.v v12, (a3)
237 ; NOREMAT-NEXT: sf.vc.vv 3, 0, v8, v14
238 ; NOREMAT-NEXT: vle32.v v8, (a3)
239 ; NOREMAT-NEXT: addiw a3, a4, 512
240 ; NOREMAT-NEXT: sd a3, 56(sp) # 8-byte Folded Spill
241 ; NOREMAT-NEXT: add a3, a0, a3
242 ; NOREMAT-NEXT: vle32.v v14, (a3)
243 ; NOREMAT-NEXT: sf.vc.vv 3, 0, v10, v12
244 ; NOREMAT-NEXT: vle32.v v10, (a3)
245 ; NOREMAT-NEXT: slli a3, a7, 10
246 ; NOREMAT-NEXT: sd a3, 48(sp) # 8-byte Folded Spill
247 ; NOREMAT-NEXT: add a3, a0, a3
248 ; NOREMAT-NEXT: vle32.v v12, (a3)
249 ; NOREMAT-NEXT: sf.vc.vv 3, 0, v8, v14
250 ; NOREMAT-NEXT: vle32.v v8, (a3)
251 ; NOREMAT-NEXT: addiw a3, a4, 1536
252 ; NOREMAT-NEXT: sd a3, 40(sp) # 8-byte Folded Spill
253 ; NOREMAT-NEXT: add a3, a0, a3
254 ; NOREMAT-NEXT: vle32.v v14, (a3)
255 ; NOREMAT-NEXT: sf.vc.vv 3, 0, v10, v12
256 ; NOREMAT-NEXT: vle32.v v10, (a3)
257 ; NOREMAT-NEXT: slli a2, a2, 11
258 ; NOREMAT-NEXT: sd a2, 32(sp) # 8-byte Folded Spill
259 ; NOREMAT-NEXT: add a2, a0, a2
260 ; NOREMAT-NEXT: vle32.v v12, (a2)
261 ; NOREMAT-NEXT: sf.vc.vv 3, 0, v8, v14
262 ; NOREMAT-NEXT: vle32.v v8, (a2)
263 ; NOREMAT-NEXT: lui s1, 5
264 ; NOREMAT-NEXT: addiw a2, s1, -1536
265 ; NOREMAT-NEXT: sd a2, 24(sp) # 8-byte Folded Spill
266 ; NOREMAT-NEXT: add a2, a0, a2
267 ; NOREMAT-NEXT: vle32.v v14, (a2)
268 ; NOREMAT-NEXT: sf.vc.vv 3, 0, v10, v12
269 ; NOREMAT-NEXT: vle32.v v10, (a2)
270 ; NOREMAT-NEXT: slli a2, a6, 10
271 ; NOREMAT-NEXT: sd a2, 16(sp) # 8-byte Folded Spill
272 ; NOREMAT-NEXT: add a2, a0, a2
273 ; NOREMAT-NEXT: vle32.v v12, (a2)
274 ; NOREMAT-NEXT: sf.vc.vv 3, 0, v8, v14
275 ; NOREMAT-NEXT: vle32.v v8, (a2)
276 ; NOREMAT-NEXT: addiw a2, s1, -512
277 ; NOREMAT-NEXT: sd a2, 8(sp) # 8-byte Folded Spill
278 ; NOREMAT-NEXT: add a2, a0, a2
279 ; NOREMAT-NEXT: vle32.v v14, (a2)
280 ; NOREMAT-NEXT: sf.vc.vv 3, 0, v10, v12
281 ; NOREMAT-NEXT: vle32.v v10, (a2)
282 ; NOREMAT-NEXT: add a2, a0, s1
283 ; NOREMAT-NEXT: vle32.v v12, (a2)
284 ; NOREMAT-NEXT: sf.vc.vv 3, 0, v8, v14
285 ; NOREMAT-NEXT: vle32.v v8, (a2)
286 ; NOREMAT-NEXT: addiw ra, s1, 512
287 ; NOREMAT-NEXT: add a2, a0, ra
288 ; NOREMAT-NEXT: vle32.v v14, (a2)
289 ; NOREMAT-NEXT: sf.vc.vv 3, 0, v10, v12
290 ; NOREMAT-NEXT: vle32.v v10, (a2)
291 ; NOREMAT-NEXT: slli s11, s10, 10
292 ; NOREMAT-NEXT: add a2, a0, s11
293 ; NOREMAT-NEXT: vle32.v v12, (a2)
294 ; NOREMAT-NEXT: sf.vc.vv 3, 0, v8, v14
295 ; NOREMAT-NEXT: vle32.v v8, (a2)
296 ; NOREMAT-NEXT: addiw s10, s1, 1536
297 ; NOREMAT-NEXT: add a2, a0, s10
298 ; NOREMAT-NEXT: vle32.v v14, (a2)
299 ; NOREMAT-NEXT: sf.vc.vv 3, 0, v10, v12
300 ; NOREMAT-NEXT: vle32.v v10, (a2)
301 ; NOREMAT-NEXT: slli s9, s8, 11
302 ; NOREMAT-NEXT: add a2, a0, s9
303 ; NOREMAT-NEXT: vle32.v v12, (a2)
304 ; NOREMAT-NEXT: sf.vc.vv 3, 0, v8, v14
305 ; NOREMAT-NEXT: vle32.v v8, (a2)
306 ; NOREMAT-NEXT: lui t1, 6
307 ; NOREMAT-NEXT: addiw s8, t1, -1536
308 ; NOREMAT-NEXT: add a2, a0, s8
309 ; NOREMAT-NEXT: vle32.v v14, (a2)
310 ; NOREMAT-NEXT: sf.vc.vv 3, 0, v10, v12
311 ; NOREMAT-NEXT: vle32.v v10, (a2)
312 ; NOREMAT-NEXT: slli s7, s6, 10
313 ; NOREMAT-NEXT: add a2, a0, s7
314 ; NOREMAT-NEXT: vle32.v v12, (a2)
315 ; NOREMAT-NEXT: sf.vc.vv 3, 0, v8, v14
316 ; NOREMAT-NEXT: vle32.v v8, (a2)
317 ; NOREMAT-NEXT: addiw s6, t1, -512
318 ; NOREMAT-NEXT: add a2, a0, s6
319 ; NOREMAT-NEXT: vle32.v v14, (a2)
320 ; NOREMAT-NEXT: sf.vc.vv 3, 0, v10, v12
321 ; NOREMAT-NEXT: vle32.v v10, (a2)
322 ; NOREMAT-NEXT: add a2, a0, t1
323 ; NOREMAT-NEXT: vle32.v v12, (a2)
324 ; NOREMAT-NEXT: sf.vc.vv 3, 0, v8, v14
325 ; NOREMAT-NEXT: vle32.v v8, (a2)
326 ; NOREMAT-NEXT: addiw s5, t1, 512
327 ; NOREMAT-NEXT: add a2, a0, s5
328 ; NOREMAT-NEXT: vle32.v v14, (a2)
329 ; NOREMAT-NEXT: sf.vc.vv 3, 0, v10, v12
330 ; NOREMAT-NEXT: vle32.v v10, (a2)
331 ; NOREMAT-NEXT: slli s4, s3, 10
332 ; NOREMAT-NEXT: add a2, a0, s4
333 ; NOREMAT-NEXT: vle32.v v12, (a2)
334 ; NOREMAT-NEXT: sf.vc.vv 3, 0, v8, v14
335 ; NOREMAT-NEXT: vle32.v v8, (a2)
336 ; NOREMAT-NEXT: addiw s3, t1, 1536
337 ; NOREMAT-NEXT: add a2, a0, s3
338 ; NOREMAT-NEXT: vle32.v v14, (a2)
339 ; NOREMAT-NEXT: sf.vc.vv 3, 0, v10, v12
340 ; NOREMAT-NEXT: vle32.v v10, (a2)
341 ; NOREMAT-NEXT: slli s2, s2, 11
342 ; NOREMAT-NEXT: add a2, a0, s2
343 ; NOREMAT-NEXT: vle32.v v12, (a2)
344 ; NOREMAT-NEXT: sf.vc.vv 3, 0, v8, v14
345 ; NOREMAT-NEXT: vle32.v v8, (a2)
346 ; NOREMAT-NEXT: lui a3, 7
347 ; NOREMAT-NEXT: addiw s0, a3, -1536
348 ; NOREMAT-NEXT: add a2, a0, s0
349 ; NOREMAT-NEXT: vle32.v v14, (a2)
350 ; NOREMAT-NEXT: sf.vc.vv 3, 0, v10, v12
351 ; NOREMAT-NEXT: vle32.v v10, (a2)
352 ; NOREMAT-NEXT: slli t6, t5, 10
353 ; NOREMAT-NEXT: add a2, a0, t6
354 ; NOREMAT-NEXT: vle32.v v12, (a2)
355 ; NOREMAT-NEXT: sf.vc.vv 3, 0, v8, v14
356 ; NOREMAT-NEXT: vle32.v v8, (a2)
357 ; NOREMAT-NEXT: addiw t5, a3, -512
358 ; NOREMAT-NEXT: add a2, a0, t5
359 ; NOREMAT-NEXT: vle32.v v14, (a2)
360 ; NOREMAT-NEXT: sf.vc.vv 3, 0, v10, v12
361 ; NOREMAT-NEXT: vle32.v v10, (a2)
362 ; NOREMAT-NEXT: add a2, a0, a3
363 ; NOREMAT-NEXT: vle32.v v12, (a2)
364 ; NOREMAT-NEXT: sf.vc.vv 3, 0, v8, v14
365 ; NOREMAT-NEXT: vle32.v v8, (a2)
366 ; NOREMAT-NEXT: addiw t4, a3, 512
367 ; NOREMAT-NEXT: add a2, a0, t4
368 ; NOREMAT-NEXT: vle32.v v14, (a2)
369 ; NOREMAT-NEXT: sf.vc.vv 3, 0, v10, v12
370 ; NOREMAT-NEXT: vle32.v v10, (a2)
371 ; NOREMAT-NEXT: slli t3, t2, 10
372 ; NOREMAT-NEXT: add a2, a0, t3
373 ; NOREMAT-NEXT: vle32.v v12, (a2)
374 ; NOREMAT-NEXT: sf.vc.vv 3, 0, v8, v14
375 ; NOREMAT-NEXT: vle32.v v8, (a2)
376 ; NOREMAT-NEXT: addiw t2, a3, 1536
377 ; NOREMAT-NEXT: add a2, a0, t2
378 ; NOREMAT-NEXT: vle32.v v14, (a2)
379 ; NOREMAT-NEXT: sf.vc.vv 3, 0, v10, v12
380 ; NOREMAT-NEXT: vle32.v v10, (a2)
381 ; NOREMAT-NEXT: slli t0, t0, 11
382 ; NOREMAT-NEXT: add a2, a0, t0
383 ; NOREMAT-NEXT: vle32.v v12, (a2)
384 ; NOREMAT-NEXT: sf.vc.vv 3, 0, v8, v14
385 ; NOREMAT-NEXT: vle32.v v8, (a2)
386 ; NOREMAT-NEXT: lui a2, 8
387 ; NOREMAT-NEXT: addiw a7, a2, -1536
388 ; NOREMAT-NEXT: add a4, a0, a7
389 ; NOREMAT-NEXT: vle32.v v14, (a4)
390 ; NOREMAT-NEXT: sf.vc.vv 3, 0, v10, v12
391 ; NOREMAT-NEXT: vle32.v v10, (a4)
392 ; NOREMAT-NEXT: slli a6, a5, 10
393 ; NOREMAT-NEXT: add a4, a0, a6
394 ; NOREMAT-NEXT: vle32.v v12, (a4)
395 ; NOREMAT-NEXT: sf.vc.vv 3, 0, v8, v14
396 ; NOREMAT-NEXT: vle32.v v8, (a4)
397 ; NOREMAT-NEXT: addiw a5, a2, -512
398 ; NOREMAT-NEXT: add a4, a0, a5
399 ; NOREMAT-NEXT: vle32.v v14, (a4)
400 ; NOREMAT-NEXT: sf.vc.vv 3, 0, v10, v12
401 ; NOREMAT-NEXT: vle32.v v10, (a4)
402 ; NOREMAT-NEXT: add a0, a0, a2
403 ; NOREMAT-NEXT: vle32.v v12, (a0)
404 ; NOREMAT-NEXT: sf.vc.vv 3, 0, v8, v14
405 ; NOREMAT-NEXT: sf.vc.vv 3, 0, v10, v12
406 ; NOREMAT-NEXT: sf.vc.v.i 2, 0, v8, 0
407 ; NOREMAT-NEXT: sf.vc.v.i 2, 0, v10, 0
408 ; NOREMAT-NEXT: addi a0, a1, 1024
409 ; NOREMAT-NEXT: vse32.v v8, (a0)
410 ; NOREMAT-NEXT: sf.vc.v.i 2, 0, v8, 0
411 ; NOREMAT-NEXT: addi a0, a1, 1536
412 ; NOREMAT-NEXT: vse32.v v10, (a0)
413 ; NOREMAT-NEXT: ld a0, 256(sp) # 8-byte Folded Reload
414 ; NOREMAT-NEXT: add a0, a1, a0
415 ; NOREMAT-NEXT: sf.vc.v.i 2, 0, v10, 0
416 ; NOREMAT-NEXT: vse32.v v8, (a0)
417 ; NOREMAT-NEXT: ld a0, 248(sp) # 8-byte Folded Reload
418 ; NOREMAT-NEXT: add a0, a1, a0
419 ; NOREMAT-NEXT: sf.vc.v.i 2, 0, v8, 0
420 ; NOREMAT-NEXT: vse32.v v10, (a0)
421 ; NOREMAT-NEXT: ld a0, 240(sp) # 8-byte Folded Reload
422 ; NOREMAT-NEXT: add a0, a1, a0
423 ; NOREMAT-NEXT: sf.vc.v.i 2, 0, v10, 0
424 ; NOREMAT-NEXT: vse32.v v8, (a0)
425 ; NOREMAT-NEXT: ld a0, 232(sp) # 8-byte Folded Reload
426 ; NOREMAT-NEXT: add a0, a1, a0
427 ; NOREMAT-NEXT: sf.vc.v.i 2, 0, v8, 0
428 ; NOREMAT-NEXT: vse32.v v10, (a0)
429 ; NOREMAT-NEXT: lui a0, 1
430 ; NOREMAT-NEXT: add a0, a1, a0
431 ; NOREMAT-NEXT: sf.vc.v.i 2, 0, v10, 0
432 ; NOREMAT-NEXT: vse32.v v8, (a0)
433 ; NOREMAT-NEXT: ld a0, 224(sp) # 8-byte Folded Reload
434 ; NOREMAT-NEXT: add a0, a1, a0
435 ; NOREMAT-NEXT: sf.vc.v.i 2, 0, v8, 0
436 ; NOREMAT-NEXT: vse32.v v10, (a0)
437 ; NOREMAT-NEXT: ld a0, 216(sp) # 8-byte Folded Reload
438 ; NOREMAT-NEXT: add a0, a1, a0
439 ; NOREMAT-NEXT: sf.vc.v.i 2, 0, v10, 0
440 ; NOREMAT-NEXT: vse32.v v8, (a0)
441 ; NOREMAT-NEXT: ld a0, 208(sp) # 8-byte Folded Reload
442 ; NOREMAT-NEXT: add a0, a1, a0
443 ; NOREMAT-NEXT: sf.vc.v.i 2, 0, v8, 0
444 ; NOREMAT-NEXT: vse32.v v10, (a0)
445 ; NOREMAT-NEXT: ld a0, 200(sp) # 8-byte Folded Reload
446 ; NOREMAT-NEXT: add a0, a1, a0
447 ; NOREMAT-NEXT: sf.vc.v.i 2, 0, v10, 0
448 ; NOREMAT-NEXT: vse32.v v8, (a0)
449 ; NOREMAT-NEXT: ld a0, 192(sp) # 8-byte Folded Reload
450 ; NOREMAT-NEXT: add a0, a1, a0
451 ; NOREMAT-NEXT: sf.vc.v.i 2, 0, v8, 0
452 ; NOREMAT-NEXT: vse32.v v10, (a0)
453 ; NOREMAT-NEXT: ld a0, 184(sp) # 8-byte Folded Reload
454 ; NOREMAT-NEXT: add a0, a1, a0
455 ; NOREMAT-NEXT: sf.vc.v.i 2, 0, v10, 0
456 ; NOREMAT-NEXT: vse32.v v8, (a0)
457 ; NOREMAT-NEXT: ld a0, 176(sp) # 8-byte Folded Reload
458 ; NOREMAT-NEXT: add a0, a1, a0
459 ; NOREMAT-NEXT: sf.vc.v.i 2, 0, v8, 0
460 ; NOREMAT-NEXT: vse32.v v10, (a0)
461 ; NOREMAT-NEXT: lui a0, 2
462 ; NOREMAT-NEXT: add a0, a1, a0
463 ; NOREMAT-NEXT: sf.vc.v.i 2, 0, v10, 0
464 ; NOREMAT-NEXT: vse32.v v8, (a0)
465 ; NOREMAT-NEXT: ld a0, 168(sp) # 8-byte Folded Reload
466 ; NOREMAT-NEXT: add a0, a1, a0
467 ; NOREMAT-NEXT: sf.vc.v.i 2, 0, v8, 0
468 ; NOREMAT-NEXT: vse32.v v10, (a0)
469 ; NOREMAT-NEXT: ld a0, 160(sp) # 8-byte Folded Reload
470 ; NOREMAT-NEXT: add a0, a1, a0
471 ; NOREMAT-NEXT: sf.vc.v.i 2, 0, v10, 0
472 ; NOREMAT-NEXT: vse32.v v8, (a0)
473 ; NOREMAT-NEXT: ld a0, 152(sp) # 8-byte Folded Reload
474 ; NOREMAT-NEXT: add a0, a1, a0
475 ; NOREMAT-NEXT: sf.vc.v.i 2, 0, v8, 0
476 ; NOREMAT-NEXT: vse32.v v10, (a0)
477 ; NOREMAT-NEXT: ld a0, 144(sp) # 8-byte Folded Reload
478 ; NOREMAT-NEXT: add a0, a1, a0
479 ; NOREMAT-NEXT: sf.vc.v.i 2, 0, v10, 0
480 ; NOREMAT-NEXT: vse32.v v8, (a0)
481 ; NOREMAT-NEXT: ld a0, 136(sp) # 8-byte Folded Reload
482 ; NOREMAT-NEXT: add a0, a1, a0
483 ; NOREMAT-NEXT: sf.vc.v.i 2, 0, v8, 0
484 ; NOREMAT-NEXT: vse32.v v10, (a0)
485 ; NOREMAT-NEXT: ld a0, 128(sp) # 8-byte Folded Reload
486 ; NOREMAT-NEXT: add a0, a1, a0
487 ; NOREMAT-NEXT: sf.vc.v.i 2, 0, v10, 0
488 ; NOREMAT-NEXT: vse32.v v8, (a0)
489 ; NOREMAT-NEXT: ld a0, 120(sp) # 8-byte Folded Reload
490 ; NOREMAT-NEXT: add a0, a1, a0
491 ; NOREMAT-NEXT: sf.vc.v.i 2, 0, v8, 0
492 ; NOREMAT-NEXT: vse32.v v10, (a0)
493 ; NOREMAT-NEXT: lui a0, 3
494 ; NOREMAT-NEXT: add a0, a1, a0
495 ; NOREMAT-NEXT: sf.vc.v.i 2, 0, v10, 0
496 ; NOREMAT-NEXT: vse32.v v8, (a0)
497 ; NOREMAT-NEXT: ld a0, 112(sp) # 8-byte Folded Reload
498 ; NOREMAT-NEXT: add a0, a1, a0
499 ; NOREMAT-NEXT: sf.vc.v.i 2, 0, v8, 0
500 ; NOREMAT-NEXT: vse32.v v10, (a0)
501 ; NOREMAT-NEXT: ld a0, 104(sp) # 8-byte Folded Reload
502 ; NOREMAT-NEXT: add a0, a1, a0
503 ; NOREMAT-NEXT: sf.vc.v.i 2, 0, v10, 0
504 ; NOREMAT-NEXT: vse32.v v8, (a0)
505 ; NOREMAT-NEXT: ld a0, 96(sp) # 8-byte Folded Reload
506 ; NOREMAT-NEXT: add a0, a1, a0
507 ; NOREMAT-NEXT: sf.vc.v.i 2, 0, v8, 0
508 ; NOREMAT-NEXT: vse32.v v10, (a0)
509 ; NOREMAT-NEXT: ld a0, 88(sp) # 8-byte Folded Reload
510 ; NOREMAT-NEXT: add a0, a1, a0
511 ; NOREMAT-NEXT: sf.vc.v.i 2, 0, v10, 0
512 ; NOREMAT-NEXT: vse32.v v8, (a0)
513 ; NOREMAT-NEXT: ld a0, 80(sp) # 8-byte Folded Reload
514 ; NOREMAT-NEXT: add a0, a1, a0
515 ; NOREMAT-NEXT: sf.vc.v.i 2, 0, v8, 0
516 ; NOREMAT-NEXT: vse32.v v10, (a0)
517 ; NOREMAT-NEXT: ld a0, 72(sp) # 8-byte Folded Reload
518 ; NOREMAT-NEXT: add a0, a1, a0
519 ; NOREMAT-NEXT: sf.vc.v.i 2, 0, v10, 0
520 ; NOREMAT-NEXT: vse32.v v8, (a0)
521 ; NOREMAT-NEXT: ld a0, 64(sp) # 8-byte Folded Reload
522 ; NOREMAT-NEXT: add a0, a1, a0
523 ; NOREMAT-NEXT: sf.vc.v.i 2, 0, v8, 0
524 ; NOREMAT-NEXT: vse32.v v10, (a0)
525 ; NOREMAT-NEXT: lui a0, 4
526 ; NOREMAT-NEXT: add a0, a1, a0
527 ; NOREMAT-NEXT: sf.vc.v.i 2, 0, v10, 0
528 ; NOREMAT-NEXT: vse32.v v8, (a0)
529 ; NOREMAT-NEXT: ld a0, 56(sp) # 8-byte Folded Reload
530 ; NOREMAT-NEXT: add a0, a1, a0
531 ; NOREMAT-NEXT: sf.vc.v.i 2, 0, v8, 0
532 ; NOREMAT-NEXT: vse32.v v10, (a0)
533 ; NOREMAT-NEXT: ld a0, 48(sp) # 8-byte Folded Reload
534 ; NOREMAT-NEXT: add a0, a1, a0
535 ; NOREMAT-NEXT: sf.vc.v.i 2, 0, v10, 0
536 ; NOREMAT-NEXT: vse32.v v8, (a0)
537 ; NOREMAT-NEXT: ld a0, 40(sp) # 8-byte Folded Reload
538 ; NOREMAT-NEXT: add a0, a1, a0
539 ; NOREMAT-NEXT: sf.vc.v.i 2, 0, v8, 0
540 ; NOREMAT-NEXT: vse32.v v10, (a0)
541 ; NOREMAT-NEXT: ld a0, 32(sp) # 8-byte Folded Reload
542 ; NOREMAT-NEXT: add a0, a1, a0
543 ; NOREMAT-NEXT: sf.vc.v.i 2, 0, v10, 0
544 ; NOREMAT-NEXT: vse32.v v8, (a0)
545 ; NOREMAT-NEXT: ld a0, 24(sp) # 8-byte Folded Reload
546 ; NOREMAT-NEXT: add a0, a1, a0
547 ; NOREMAT-NEXT: sf.vc.v.i 2, 0, v8, 0
548 ; NOREMAT-NEXT: vse32.v v10, (a0)
549 ; NOREMAT-NEXT: ld a0, 16(sp) # 8-byte Folded Reload
550 ; NOREMAT-NEXT: add a0, a1, a0
551 ; NOREMAT-NEXT: sf.vc.v.i 2, 0, v10, 0
552 ; NOREMAT-NEXT: vse32.v v8, (a0)
553 ; NOREMAT-NEXT: ld a0, 8(sp) # 8-byte Folded Reload
554 ; NOREMAT-NEXT: add a0, a1, a0
555 ; NOREMAT-NEXT: sf.vc.v.i 2, 0, v8, 0
556 ; NOREMAT-NEXT: vse32.v v10, (a0)
557 ; NOREMAT-NEXT: add s1, a1, s1
558 ; NOREMAT-NEXT: sf.vc.v.i 2, 0, v10, 0
559 ; NOREMAT-NEXT: vse32.v v8, (s1)
560 ; NOREMAT-NEXT: add ra, a1, ra
561 ; NOREMAT-NEXT: sf.vc.v.i 2, 0, v8, 0
562 ; NOREMAT-NEXT: vse32.v v10, (ra)
563 ; NOREMAT-NEXT: add s11, a1, s11
564 ; NOREMAT-NEXT: sf.vc.v.i 2, 0, v10, 0
565 ; NOREMAT-NEXT: vse32.v v8, (s11)
566 ; NOREMAT-NEXT: add s10, a1, s10
567 ; NOREMAT-NEXT: sf.vc.v.i 2, 0, v8, 0
568 ; NOREMAT-NEXT: vse32.v v10, (s10)
569 ; NOREMAT-NEXT: add s9, a1, s9
570 ; NOREMAT-NEXT: sf.vc.v.i 2, 0, v10, 0
571 ; NOREMAT-NEXT: vse32.v v8, (s9)
572 ; NOREMAT-NEXT: add s8, a1, s8
573 ; NOREMAT-NEXT: sf.vc.v.i 2, 0, v8, 0
574 ; NOREMAT-NEXT: vse32.v v10, (s8)
575 ; NOREMAT-NEXT: add s7, a1, s7
576 ; NOREMAT-NEXT: sf.vc.v.i 2, 0, v10, 0
577 ; NOREMAT-NEXT: vse32.v v8, (s7)
578 ; NOREMAT-NEXT: add s6, a1, s6
579 ; NOREMAT-NEXT: sf.vc.v.i 2, 0, v8, 0
580 ; NOREMAT-NEXT: vse32.v v10, (s6)
581 ; NOREMAT-NEXT: add t1, a1, t1
582 ; NOREMAT-NEXT: sf.vc.v.i 2, 0, v10, 0
583 ; NOREMAT-NEXT: vse32.v v8, (t1)
584 ; NOREMAT-NEXT: add s5, a1, s5
585 ; NOREMAT-NEXT: sf.vc.v.i 2, 0, v8, 0
586 ; NOREMAT-NEXT: vse32.v v10, (s5)
587 ; NOREMAT-NEXT: add s4, a1, s4
588 ; NOREMAT-NEXT: sf.vc.v.i 2, 0, v10, 0
589 ; NOREMAT-NEXT: vse32.v v8, (s4)
590 ; NOREMAT-NEXT: add s3, a1, s3
591 ; NOREMAT-NEXT: sf.vc.v.i 2, 0, v8, 0
592 ; NOREMAT-NEXT: vse32.v v10, (s3)
593 ; NOREMAT-NEXT: add s2, a1, s2
594 ; NOREMAT-NEXT: sf.vc.v.i 2, 0, v10, 0
595 ; NOREMAT-NEXT: vse32.v v8, (s2)
596 ; NOREMAT-NEXT: add s0, a1, s0
597 ; NOREMAT-NEXT: sf.vc.v.i 2, 0, v8, 0
598 ; NOREMAT-NEXT: vse32.v v10, (s0)
599 ; NOREMAT-NEXT: add t6, a1, t6
600 ; NOREMAT-NEXT: sf.vc.v.i 2, 0, v10, 0
601 ; NOREMAT-NEXT: vse32.v v8, (t6)
602 ; NOREMAT-NEXT: add t5, a1, t5
603 ; NOREMAT-NEXT: sf.vc.v.i 2, 0, v8, 0
604 ; NOREMAT-NEXT: vse32.v v10, (t5)
605 ; NOREMAT-NEXT: add a3, a1, a3
606 ; NOREMAT-NEXT: sf.vc.v.i 2, 0, v10, 0
607 ; NOREMAT-NEXT: vse32.v v8, (a3)
608 ; NOREMAT-NEXT: add t4, a1, t4
609 ; NOREMAT-NEXT: sf.vc.v.i 2, 0, v8, 0
610 ; NOREMAT-NEXT: vse32.v v10, (t4)
611 ; NOREMAT-NEXT: add t3, a1, t3
612 ; NOREMAT-NEXT: sf.vc.v.i 2, 0, v10, 0
613 ; NOREMAT-NEXT: vse32.v v8, (t3)
614 ; NOREMAT-NEXT: add t2, a1, t2
615 ; NOREMAT-NEXT: sf.vc.v.i 2, 0, v8, 0
616 ; NOREMAT-NEXT: vse32.v v10, (t2)
617 ; NOREMAT-NEXT: add t0, a1, t0
618 ; NOREMAT-NEXT: sf.vc.v.i 2, 0, v10, 0
619 ; NOREMAT-NEXT: vse32.v v8, (t0)
620 ; NOREMAT-NEXT: add a7, a1, a7
621 ; NOREMAT-NEXT: sf.vc.v.i 2, 0, v8, 0
622 ; NOREMAT-NEXT: vse32.v v10, (a7)
623 ; NOREMAT-NEXT: add a6, a1, a6
624 ; NOREMAT-NEXT: sf.vc.v.i 2, 0, v10, 0
625 ; NOREMAT-NEXT: vse32.v v8, (a6)
626 ; NOREMAT-NEXT: add a5, a1, a5
627 ; NOREMAT-NEXT: sf.vc.v.i 2, 0, v8, 0
628 ; NOREMAT-NEXT: vse32.v v10, (a5)
629 ; NOREMAT-NEXT: add a0, a1, a2
630 ; NOREMAT-NEXT: sf.vc.v.i 2, 0, v10, 0
631 ; NOREMAT-NEXT: vse32.v v8, (a0)
632 ; NOREMAT-NEXT: addiw a0, a2, 512
633 ; NOREMAT-NEXT: add a0, a1, a0
634 ; NOREMAT-NEXT: sf.vc.v.i 2, 0, v8, 0
635 ; NOREMAT-NEXT: vse32.v v10, (a0)
636 ; NOREMAT-NEXT: addiw a0, a2, 1024
637 ; NOREMAT-NEXT: add a0, a1, a0
638 ; NOREMAT-NEXT: sf.vc.v.i 2, 0, v10, 0
639 ; NOREMAT-NEXT: vse32.v v8, (a0)
640 ; NOREMAT-NEXT: addiw a0, a2, 1536
641 ; NOREMAT-NEXT: add a0, a1, a0
642 ; NOREMAT-NEXT: sf.vc.v.i 2, 0, v8, 0
643 ; NOREMAT-NEXT: vse32.v v10, (a0)
644 ; NOREMAT-NEXT: li a0, 17
645 ; NOREMAT-NEXT: slli a0, a0, 11
646 ; NOREMAT-NEXT: add a0, a1, a0
647 ; NOREMAT-NEXT: sf.vc.v.i 2, 0, v10, 0
648 ; NOREMAT-NEXT: vse32.v v8, (a0)
649 ; NOREMAT-NEXT: lui a0, 9
650 ; NOREMAT-NEXT: addiw a2, a0, -1536
651 ; NOREMAT-NEXT: add a2, a1, a2
652 ; NOREMAT-NEXT: sf.vc.v.i 2, 0, v8, 0
653 ; NOREMAT-NEXT: vse32.v v10, (a2)
654 ; NOREMAT-NEXT: addiw a2, a0, -1024
655 ; NOREMAT-NEXT: add a2, a1, a2
656 ; NOREMAT-NEXT: sf.vc.v.i 2, 0, v10, 0
657 ; NOREMAT-NEXT: vse32.v v8, (a2)
658 ; NOREMAT-NEXT: addiw a2, a0, -512
659 ; NOREMAT-NEXT: add a2, a1, a2
660 ; NOREMAT-NEXT: sf.vc.v.i 2, 0, v8, 0
661 ; NOREMAT-NEXT: vse32.v v10, (a2)
662 ; NOREMAT-NEXT: add a2, a1, a0
663 ; NOREMAT-NEXT: sf.vc.v.i 2, 0, v10, 0
664 ; NOREMAT-NEXT: vse32.v v8, (a2)
665 ; NOREMAT-NEXT: addiw a2, a0, 512
666 ; NOREMAT-NEXT: add a2, a1, a2
667 ; NOREMAT-NEXT: sf.vc.v.i 2, 0, v8, 0
668 ; NOREMAT-NEXT: vse32.v v10, (a2)
669 ; NOREMAT-NEXT: addiw a2, a0, 1024
670 ; NOREMAT-NEXT: add a2, a1, a2
671 ; NOREMAT-NEXT: sf.vc.v.i 2, 0, v10, 0
672 ; NOREMAT-NEXT: vse32.v v8, (a2)
673 ; NOREMAT-NEXT: addiw a0, a0, 1536
674 ; NOREMAT-NEXT: add a0, a1, a0
675 ; NOREMAT-NEXT: sf.vc.v.i 2, 0, v8, 0
676 ; NOREMAT-NEXT: vse32.v v10, (a0)
677 ; NOREMAT-NEXT: li a0, 19
678 ; NOREMAT-NEXT: slli a0, a0, 11
679 ; NOREMAT-NEXT: add a0, a1, a0
680 ; NOREMAT-NEXT: sf.vc.v.i 2, 0, v10, 0
681 ; NOREMAT-NEXT: vse32.v v8, (a0)
682 ; NOREMAT-NEXT: lui a0, 10
683 ; NOREMAT-NEXT: addiw a2, a0, -1536
684 ; NOREMAT-NEXT: add a2, a1, a2
685 ; NOREMAT-NEXT: sf.vc.v.i 2, 0, v8, 0
686 ; NOREMAT-NEXT: vse32.v v10, (a2)
687 ; NOREMAT-NEXT: addiw a2, a0, -1024
688 ; NOREMAT-NEXT: add a2, a1, a2
689 ; NOREMAT-NEXT: sf.vc.v.i 2, 0, v10, 0
690 ; NOREMAT-NEXT: vse32.v v8, (a2)
691 ; NOREMAT-NEXT: addiw a2, a0, -512
692 ; NOREMAT-NEXT: add a2, a1, a2
693 ; NOREMAT-NEXT: sf.vc.v.i 2, 0, v8, 0
694 ; NOREMAT-NEXT: vse32.v v10, (a2)
695 ; NOREMAT-NEXT: add a2, a1, a0
696 ; NOREMAT-NEXT: sf.vc.v.i 2, 0, v10, 0
697 ; NOREMAT-NEXT: vse32.v v8, (a2)
698 ; NOREMAT-NEXT: addiw a0, a0, 512
699 ; NOREMAT-NEXT: add a0, a1, a0
700 ; NOREMAT-NEXT: sf.vc.v.i 2, 0, v8, 0
701 ; NOREMAT-NEXT: vse32.v v10, (a0)
702 ; NOREMAT-NEXT: sf.vc.v.i 2, 0, v8, 0
703 ; NOREMAT-NEXT: ld ra, 360(sp) # 8-byte Folded Reload
704 ; NOREMAT-NEXT: ld s0, 352(sp) # 8-byte Folded Reload
705 ; NOREMAT-NEXT: ld s1, 344(sp) # 8-byte Folded Reload
706 ; NOREMAT-NEXT: ld s2, 336(sp) # 8-byte Folded Reload
707 ; NOREMAT-NEXT: ld s3, 328(sp) # 8-byte Folded Reload
708 ; NOREMAT-NEXT: ld s4, 320(sp) # 8-byte Folded Reload
709 ; NOREMAT-NEXT: ld s5, 312(sp) # 8-byte Folded Reload
710 ; NOREMAT-NEXT: ld s6, 304(sp) # 8-byte Folded Reload
711 ; NOREMAT-NEXT: ld s7, 296(sp) # 8-byte Folded Reload
712 ; NOREMAT-NEXT: ld s8, 288(sp) # 8-byte Folded Reload
713 ; NOREMAT-NEXT: ld s9, 280(sp) # 8-byte Folded Reload
714 ; NOREMAT-NEXT: ld s10, 272(sp) # 8-byte Folded Reload
715 ; NOREMAT-NEXT: ld s11, 264(sp) # 8-byte Folded Reload
716 ; NOREMAT-NEXT: addi sp, sp, 368
721 ; REMAT-NEXT: addi sp, sp, -112
722 ; REMAT-NEXT: .cfi_def_cfa_offset 112
723 ; REMAT-NEXT: sd ra, 104(sp) # 8-byte Folded Spill
724 ; REMAT-NEXT: sd s0, 96(sp) # 8-byte Folded Spill
725 ; REMAT-NEXT: sd s1, 88(sp) # 8-byte Folded Spill
726 ; REMAT-NEXT: sd s2, 80(sp) # 8-byte Folded Spill
727 ; REMAT-NEXT: sd s3, 72(sp) # 8-byte Folded Spill
728 ; REMAT-NEXT: sd s4, 64(sp) # 8-byte Folded Spill
729 ; REMAT-NEXT: sd s5, 56(sp) # 8-byte Folded Spill
730 ; REMAT-NEXT: sd s6, 48(sp) # 8-byte Folded Spill
731 ; REMAT-NEXT: sd s7, 40(sp) # 8-byte Folded Spill
732 ; REMAT-NEXT: sd s8, 32(sp) # 8-byte Folded Spill
733 ; REMAT-NEXT: sd s9, 24(sp) # 8-byte Folded Spill
734 ; REMAT-NEXT: sd s10, 16(sp) # 8-byte Folded Spill
735 ; REMAT-NEXT: sd s11, 8(sp) # 8-byte Folded Spill
736 ; REMAT-NEXT: .cfi_offset ra, -8
737 ; REMAT-NEXT: .cfi_offset s0, -16
738 ; REMAT-NEXT: .cfi_offset s1, -24
739 ; REMAT-NEXT: .cfi_offset s2, -32
740 ; REMAT-NEXT: .cfi_offset s3, -40
741 ; REMAT-NEXT: .cfi_offset s4, -48
742 ; REMAT-NEXT: .cfi_offset s5, -56
743 ; REMAT-NEXT: .cfi_offset s6, -64
744 ; REMAT-NEXT: .cfi_offset s7, -72
745 ; REMAT-NEXT: .cfi_offset s8, -80
746 ; REMAT-NEXT: .cfi_offset s9, -88
747 ; REMAT-NEXT: .cfi_offset s10, -96
748 ; REMAT-NEXT: .cfi_offset s11, -104
749 ; REMAT-NEXT: li a2, 32
750 ; REMAT-NEXT: vsetvli zero, a2, e32, m2, ta, ma
751 ; REMAT-NEXT: vle32.v v8, (a0)
752 ; REMAT-NEXT: addi a2, a0, 512
753 ; REMAT-NEXT: vle32.v v10, (a2)
754 ; REMAT-NEXT: addi a2, a0, 1024
755 ; REMAT-NEXT: vle32.v v12, (a2)
756 ; REMAT-NEXT: sf.vc.vv 3, 0, v8, v10
757 ; REMAT-NEXT: vle32.v v8, (a2)
758 ; REMAT-NEXT: addi a2, a0, 1536
759 ; REMAT-NEXT: vle32.v v14, (a2)
760 ; REMAT-NEXT: sf.vc.vv 3, 0, v10, v12
761 ; REMAT-NEXT: vle32.v v10, (a2)
762 ; REMAT-NEXT: li a2, 1
763 ; REMAT-NEXT: slli a2, a2, 11
764 ; REMAT-NEXT: add a2, a0, a2
765 ; REMAT-NEXT: vle32.v v12, (a2)
766 ; REMAT-NEXT: sf.vc.vv 3, 0, v8, v14
767 ; REMAT-NEXT: vle32.v v8, (a2)
768 ; REMAT-NEXT: li a2, 5
769 ; REMAT-NEXT: slli a2, a2, 9
770 ; REMAT-NEXT: add a2, a0, a2
771 ; REMAT-NEXT: vle32.v v14, (a2)
772 ; REMAT-NEXT: sf.vc.vv 3, 0, v10, v12
773 ; REMAT-NEXT: vle32.v v10, (a2)
774 ; REMAT-NEXT: li a2, 3
775 ; REMAT-NEXT: slli a2, a2, 10
776 ; REMAT-NEXT: add a2, a0, a2
777 ; REMAT-NEXT: vle32.v v12, (a2)
778 ; REMAT-NEXT: sf.vc.vv 3, 0, v8, v14
779 ; REMAT-NEXT: vle32.v v8, (a2)
780 ; REMAT-NEXT: li a2, 7
781 ; REMAT-NEXT: slli a2, a2, 9
782 ; REMAT-NEXT: add a2, a0, a2
783 ; REMAT-NEXT: vle32.v v14, (a2)
784 ; REMAT-NEXT: sf.vc.vv 3, 0, v10, v12
785 ; REMAT-NEXT: vle32.v v10, (a2)
786 ; REMAT-NEXT: lui a2, 1
787 ; REMAT-NEXT: add a2, a0, a2
788 ; REMAT-NEXT: vle32.v v12, (a2)
789 ; REMAT-NEXT: sf.vc.vv 3, 0, v8, v14
790 ; REMAT-NEXT: vle32.v v8, (a2)
791 ; REMAT-NEXT: li a2, 9
792 ; REMAT-NEXT: slli a2, a2, 9
793 ; REMAT-NEXT: add a2, a0, a2
794 ; REMAT-NEXT: vle32.v v14, (a2)
795 ; REMAT-NEXT: sf.vc.vv 3, 0, v10, v12
796 ; REMAT-NEXT: vle32.v v10, (a2)
797 ; REMAT-NEXT: li a2, 5
798 ; REMAT-NEXT: slli a2, a2, 10
799 ; REMAT-NEXT: add a2, a0, a2
800 ; REMAT-NEXT: vle32.v v12, (a2)
801 ; REMAT-NEXT: sf.vc.vv 3, 0, v8, v14
802 ; REMAT-NEXT: vle32.v v8, (a2)
803 ; REMAT-NEXT: li a2, 11
804 ; REMAT-NEXT: slli a2, a2, 9
805 ; REMAT-NEXT: add a2, a0, a2
806 ; REMAT-NEXT: vle32.v v14, (a2)
807 ; REMAT-NEXT: sf.vc.vv 3, 0, v10, v12
808 ; REMAT-NEXT: vle32.v v10, (a2)
809 ; REMAT-NEXT: li a2, 3
810 ; REMAT-NEXT: slli a2, a2, 11
811 ; REMAT-NEXT: add a2, a0, a2
812 ; REMAT-NEXT: vle32.v v12, (a2)
813 ; REMAT-NEXT: sf.vc.vv 3, 0, v8, v14
814 ; REMAT-NEXT: vle32.v v8, (a2)
815 ; REMAT-NEXT: li a2, 13
816 ; REMAT-NEXT: slli a2, a2, 9
817 ; REMAT-NEXT: add a2, a0, a2
818 ; REMAT-NEXT: vle32.v v14, (a2)
819 ; REMAT-NEXT: sf.vc.vv 3, 0, v10, v12
820 ; REMAT-NEXT: vle32.v v10, (a2)
821 ; REMAT-NEXT: li a2, 7
822 ; REMAT-NEXT: slli a2, a2, 10
823 ; REMAT-NEXT: add a2, a0, a2
824 ; REMAT-NEXT: vle32.v v12, (a2)
825 ; REMAT-NEXT: sf.vc.vv 3, 0, v8, v14
826 ; REMAT-NEXT: vle32.v v8, (a2)
827 ; REMAT-NEXT: li a2, 15
828 ; REMAT-NEXT: slli a2, a2, 9
829 ; REMAT-NEXT: add a2, a0, a2
830 ; REMAT-NEXT: vle32.v v14, (a2)
831 ; REMAT-NEXT: sf.vc.vv 3, 0, v10, v12
832 ; REMAT-NEXT: vle32.v v10, (a2)
833 ; REMAT-NEXT: lui a2, 2
834 ; REMAT-NEXT: add a2, a0, a2
835 ; REMAT-NEXT: vle32.v v12, (a2)
836 ; REMAT-NEXT: sf.vc.vv 3, 0, v8, v14
837 ; REMAT-NEXT: vle32.v v8, (a2)
838 ; REMAT-NEXT: li a2, 17
839 ; REMAT-NEXT: slli a2, a2, 9
840 ; REMAT-NEXT: add a2, a0, a2
841 ; REMAT-NEXT: vle32.v v14, (a2)
842 ; REMAT-NEXT: sf.vc.vv 3, 0, v10, v12
843 ; REMAT-NEXT: vle32.v v10, (a2)
844 ; REMAT-NEXT: li a2, 9
845 ; REMAT-NEXT: slli a2, a2, 10
846 ; REMAT-NEXT: add a2, a0, a2
847 ; REMAT-NEXT: vle32.v v12, (a2)
848 ; REMAT-NEXT: sf.vc.vv 3, 0, v8, v14
849 ; REMAT-NEXT: vle32.v v8, (a2)
850 ; REMAT-NEXT: li a2, 19
851 ; REMAT-NEXT: slli a2, a2, 9
852 ; REMAT-NEXT: add a2, a0, a2
853 ; REMAT-NEXT: vle32.v v14, (a2)
854 ; REMAT-NEXT: sf.vc.vv 3, 0, v10, v12
855 ; REMAT-NEXT: vle32.v v10, (a2)
856 ; REMAT-NEXT: li a2, 5
857 ; REMAT-NEXT: slli a2, a2, 11
858 ; REMAT-NEXT: add a2, a0, a2
859 ; REMAT-NEXT: vle32.v v12, (a2)
860 ; REMAT-NEXT: sf.vc.vv 3, 0, v8, v14
861 ; REMAT-NEXT: vle32.v v8, (a2)
862 ; REMAT-NEXT: li a2, 21
863 ; REMAT-NEXT: slli a2, a2, 9
864 ; REMAT-NEXT: add a2, a0, a2
865 ; REMAT-NEXT: vle32.v v14, (a2)
866 ; REMAT-NEXT: sf.vc.vv 3, 0, v10, v12
867 ; REMAT-NEXT: vle32.v v10, (a2)
868 ; REMAT-NEXT: li a2, 11
869 ; REMAT-NEXT: slli a2, a2, 10
870 ; REMAT-NEXT: add a2, a0, a2
871 ; REMAT-NEXT: vle32.v v12, (a2)
872 ; REMAT-NEXT: sf.vc.vv 3, 0, v8, v14
873 ; REMAT-NEXT: vle32.v v8, (a2)
874 ; REMAT-NEXT: li a2, 23
875 ; REMAT-NEXT: slli a2, a2, 9
876 ; REMAT-NEXT: add a2, a0, a2
877 ; REMAT-NEXT: vle32.v v14, (a2)
878 ; REMAT-NEXT: sf.vc.vv 3, 0, v10, v12
879 ; REMAT-NEXT: vle32.v v10, (a2)
880 ; REMAT-NEXT: lui a2, 3
881 ; REMAT-NEXT: add a2, a0, a2
882 ; REMAT-NEXT: vle32.v v12, (a2)
883 ; REMAT-NEXT: sf.vc.vv 3, 0, v8, v14
884 ; REMAT-NEXT: vle32.v v8, (a2)
885 ; REMAT-NEXT: li a2, 25
886 ; REMAT-NEXT: slli a2, a2, 9
887 ; REMAT-NEXT: add a2, a0, a2
888 ; REMAT-NEXT: vle32.v v14, (a2)
889 ; REMAT-NEXT: sf.vc.vv 3, 0, v10, v12
890 ; REMAT-NEXT: vle32.v v10, (a2)
891 ; REMAT-NEXT: li a2, 13
892 ; REMAT-NEXT: slli a2, a2, 10
893 ; REMAT-NEXT: add a2, a0, a2
894 ; REMAT-NEXT: vle32.v v12, (a2)
895 ; REMAT-NEXT: sf.vc.vv 3, 0, v8, v14
896 ; REMAT-NEXT: vle32.v v8, (a2)
897 ; REMAT-NEXT: li a2, 27
898 ; REMAT-NEXT: slli a2, a2, 9
899 ; REMAT-NEXT: add a2, a0, a2
900 ; REMAT-NEXT: vle32.v v14, (a2)
901 ; REMAT-NEXT: sf.vc.vv 3, 0, v10, v12
902 ; REMAT-NEXT: vle32.v v10, (a2)
903 ; REMAT-NEXT: li a2, 7
904 ; REMAT-NEXT: slli a2, a2, 11
905 ; REMAT-NEXT: add a2, a0, a2
906 ; REMAT-NEXT: vle32.v v12, (a2)
907 ; REMAT-NEXT: sf.vc.vv 3, 0, v8, v14
908 ; REMAT-NEXT: vle32.v v8, (a2)
909 ; REMAT-NEXT: li a2, 29
910 ; REMAT-NEXT: slli a2, a2, 9
911 ; REMAT-NEXT: add a2, a0, a2
912 ; REMAT-NEXT: vle32.v v14, (a2)
913 ; REMAT-NEXT: sf.vc.vv 3, 0, v10, v12
914 ; REMAT-NEXT: vle32.v v10, (a2)
915 ; REMAT-NEXT: li a2, 15
916 ; REMAT-NEXT: slli a2, a2, 10
917 ; REMAT-NEXT: add a2, a0, a2
918 ; REMAT-NEXT: vle32.v v12, (a2)
919 ; REMAT-NEXT: sf.vc.vv 3, 0, v8, v14
920 ; REMAT-NEXT: vle32.v v8, (a2)
921 ; REMAT-NEXT: li a2, 31
922 ; REMAT-NEXT: slli a2, a2, 9
923 ; REMAT-NEXT: add a2, a0, a2
924 ; REMAT-NEXT: vle32.v v14, (a2)
925 ; REMAT-NEXT: sf.vc.vv 3, 0, v10, v12
926 ; REMAT-NEXT: vle32.v v10, (a2)
927 ; REMAT-NEXT: lui a2, 4
928 ; REMAT-NEXT: add a2, a0, a2
929 ; REMAT-NEXT: vle32.v v12, (a2)
930 ; REMAT-NEXT: sf.vc.vv 3, 0, v8, v14
931 ; REMAT-NEXT: vle32.v v8, (a2)
932 ; REMAT-NEXT: lui a2, 4
933 ; REMAT-NEXT: addiw a2, a2, 512
934 ; REMAT-NEXT: add a2, a0, a2
935 ; REMAT-NEXT: vle32.v v14, (a2)
936 ; REMAT-NEXT: sf.vc.vv 3, 0, v10, v12
937 ; REMAT-NEXT: vle32.v v10, (a2)
938 ; REMAT-NEXT: li a2, 17
939 ; REMAT-NEXT: slli a2, a2, 10
940 ; REMAT-NEXT: add a2, a0, a2
941 ; REMAT-NEXT: vle32.v v12, (a2)
942 ; REMAT-NEXT: sf.vc.vv 3, 0, v8, v14
943 ; REMAT-NEXT: vle32.v v8, (a2)
944 ; REMAT-NEXT: lui a2, 4
945 ; REMAT-NEXT: addiw a2, a2, 1536
946 ; REMAT-NEXT: add a2, a0, a2
947 ; REMAT-NEXT: vle32.v v14, (a2)
948 ; REMAT-NEXT: sf.vc.vv 3, 0, v10, v12
949 ; REMAT-NEXT: vle32.v v10, (a2)
950 ; REMAT-NEXT: li a2, 9
951 ; REMAT-NEXT: slli a2, a2, 11
952 ; REMAT-NEXT: add a2, a0, a2
953 ; REMAT-NEXT: vle32.v v12, (a2)
954 ; REMAT-NEXT: sf.vc.vv 3, 0, v8, v14
955 ; REMAT-NEXT: vle32.v v8, (a2)
956 ; REMAT-NEXT: lui a2, 5
957 ; REMAT-NEXT: addiw a2, a2, -1536
958 ; REMAT-NEXT: add a2, a0, a2
959 ; REMAT-NEXT: vle32.v v14, (a2)
960 ; REMAT-NEXT: sf.vc.vv 3, 0, v10, v12
961 ; REMAT-NEXT: vle32.v v10, (a2)
962 ; REMAT-NEXT: li a2, 19
963 ; REMAT-NEXT: slli a2, a2, 10
964 ; REMAT-NEXT: add a2, a0, a2
965 ; REMAT-NEXT: vle32.v v12, (a2)
966 ; REMAT-NEXT: sf.vc.vv 3, 0, v8, v14
967 ; REMAT-NEXT: vle32.v v8, (a2)
968 ; REMAT-NEXT: lui ra, 5
969 ; REMAT-NEXT: addiw ra, ra, -512
970 ; REMAT-NEXT: add a2, a0, ra
971 ; REMAT-NEXT: vle32.v v14, (a2)
972 ; REMAT-NEXT: sf.vc.vv 3, 0, v10, v12
973 ; REMAT-NEXT: vle32.v v10, (a2)
974 ; REMAT-NEXT: lui s11, 5
975 ; REMAT-NEXT: add a2, a0, s11
976 ; REMAT-NEXT: vle32.v v12, (a2)
977 ; REMAT-NEXT: sf.vc.vv 3, 0, v8, v14
978 ; REMAT-NEXT: vle32.v v8, (a2)
979 ; REMAT-NEXT: lui s10, 5
980 ; REMAT-NEXT: addiw s10, s10, 512
981 ; REMAT-NEXT: add a2, a0, s10
982 ; REMAT-NEXT: vle32.v v14, (a2)
983 ; REMAT-NEXT: sf.vc.vv 3, 0, v10, v12
984 ; REMAT-NEXT: vle32.v v10, (a2)
985 ; REMAT-NEXT: li s9, 21
986 ; REMAT-NEXT: slli s9, s9, 10
987 ; REMAT-NEXT: add a2, a0, s9
988 ; REMAT-NEXT: vle32.v v12, (a2)
989 ; REMAT-NEXT: sf.vc.vv 3, 0, v8, v14
990 ; REMAT-NEXT: vle32.v v8, (a2)
991 ; REMAT-NEXT: lui s8, 5
992 ; REMAT-NEXT: addiw s8, s8, 1536
993 ; REMAT-NEXT: add a2, a0, s8
994 ; REMAT-NEXT: vle32.v v14, (a2)
995 ; REMAT-NEXT: sf.vc.vv 3, 0, v10, v12
996 ; REMAT-NEXT: vle32.v v10, (a2)
997 ; REMAT-NEXT: li s7, 11
998 ; REMAT-NEXT: slli s7, s7, 11
999 ; REMAT-NEXT: add a2, a0, s7
1000 ; REMAT-NEXT: vle32.v v12, (a2)
1001 ; REMAT-NEXT: sf.vc.vv 3, 0, v8, v14
1002 ; REMAT-NEXT: vle32.v v8, (a2)
1003 ; REMAT-NEXT: lui s6, 6
1004 ; REMAT-NEXT: addiw s6, s6, -1536
1005 ; REMAT-NEXT: add a2, a0, s6
1006 ; REMAT-NEXT: vle32.v v14, (a2)
1007 ; REMAT-NEXT: sf.vc.vv 3, 0, v10, v12
1008 ; REMAT-NEXT: vle32.v v10, (a2)
1009 ; REMAT-NEXT: li s5, 23
1010 ; REMAT-NEXT: slli s5, s5, 10
1011 ; REMAT-NEXT: add a2, a0, s5
1012 ; REMAT-NEXT: vle32.v v12, (a2)
1013 ; REMAT-NEXT: sf.vc.vv 3, 0, v8, v14
1014 ; REMAT-NEXT: vle32.v v8, (a2)
1015 ; REMAT-NEXT: lui s4, 6
1016 ; REMAT-NEXT: addiw s4, s4, -512
1017 ; REMAT-NEXT: add a2, a0, s4
1018 ; REMAT-NEXT: vle32.v v14, (a2)
1019 ; REMAT-NEXT: sf.vc.vv 3, 0, v10, v12
1020 ; REMAT-NEXT: vle32.v v10, (a2)
1021 ; REMAT-NEXT: lui s3, 6
1022 ; REMAT-NEXT: add a2, a0, s3
1023 ; REMAT-NEXT: vle32.v v12, (a2)
1024 ; REMAT-NEXT: sf.vc.vv 3, 0, v8, v14
1025 ; REMAT-NEXT: vle32.v v8, (a2)
1026 ; REMAT-NEXT: lui s2, 6
1027 ; REMAT-NEXT: addiw s2, s2, 512
1028 ; REMAT-NEXT: add a2, a0, s2
1029 ; REMAT-NEXT: vle32.v v14, (a2)
1030 ; REMAT-NEXT: sf.vc.vv 3, 0, v10, v12
1031 ; REMAT-NEXT: vle32.v v10, (a2)
1032 ; REMAT-NEXT: li s1, 25
1033 ; REMAT-NEXT: slli s1, s1, 10
1034 ; REMAT-NEXT: add a2, a0, s1
1035 ; REMAT-NEXT: vle32.v v12, (a2)
1036 ; REMAT-NEXT: sf.vc.vv 3, 0, v8, v14
1037 ; REMAT-NEXT: vle32.v v8, (a2)
1038 ; REMAT-NEXT: lui s0, 6
1039 ; REMAT-NEXT: addiw s0, s0, 1536
1040 ; REMAT-NEXT: add a2, a0, s0
1041 ; REMAT-NEXT: vle32.v v14, (a2)
1042 ; REMAT-NEXT: sf.vc.vv 3, 0, v10, v12
1043 ; REMAT-NEXT: vle32.v v10, (a2)
1044 ; REMAT-NEXT: li t6, 13
1045 ; REMAT-NEXT: slli t6, t6, 11
1046 ; REMAT-NEXT: add a2, a0, t6
1047 ; REMAT-NEXT: vle32.v v12, (a2)
1048 ; REMAT-NEXT: sf.vc.vv 3, 0, v8, v14
1049 ; REMAT-NEXT: vle32.v v8, (a2)
1050 ; REMAT-NEXT: lui t5, 7
1051 ; REMAT-NEXT: addiw t5, t5, -1536
1052 ; REMAT-NEXT: add a2, a0, t5
1053 ; REMAT-NEXT: vle32.v v14, (a2)
1054 ; REMAT-NEXT: sf.vc.vv 3, 0, v10, v12
1055 ; REMAT-NEXT: vle32.v v10, (a2)
1056 ; REMAT-NEXT: li t4, 27
1057 ; REMAT-NEXT: slli t4, t4, 10
1058 ; REMAT-NEXT: add a2, a0, t4
1059 ; REMAT-NEXT: vle32.v v12, (a2)
1060 ; REMAT-NEXT: sf.vc.vv 3, 0, v8, v14
1061 ; REMAT-NEXT: vle32.v v8, (a2)
1062 ; REMAT-NEXT: lui t3, 7
1063 ; REMAT-NEXT: addiw t3, t3, -512
1064 ; REMAT-NEXT: add a2, a0, t3
1065 ; REMAT-NEXT: vle32.v v14, (a2)
1066 ; REMAT-NEXT: sf.vc.vv 3, 0, v10, v12
1067 ; REMAT-NEXT: vle32.v v10, (a2)
1068 ; REMAT-NEXT: lui t2, 7
1069 ; REMAT-NEXT: add a2, a0, t2
1070 ; REMAT-NEXT: vle32.v v12, (a2)
1071 ; REMAT-NEXT: sf.vc.vv 3, 0, v8, v14
1072 ; REMAT-NEXT: vle32.v v8, (a2)
1073 ; REMAT-NEXT: lui t1, 7
1074 ; REMAT-NEXT: addiw t1, t1, 512
1075 ; REMAT-NEXT: add a2, a0, t1
1076 ; REMAT-NEXT: vle32.v v14, (a2)
1077 ; REMAT-NEXT: sf.vc.vv 3, 0, v10, v12
1078 ; REMAT-NEXT: vle32.v v10, (a2)
1079 ; REMAT-NEXT: li t0, 29
1080 ; REMAT-NEXT: slli t0, t0, 10
1081 ; REMAT-NEXT: add a2, a0, t0
1082 ; REMAT-NEXT: vle32.v v12, (a2)
1083 ; REMAT-NEXT: sf.vc.vv 3, 0, v8, v14
1084 ; REMAT-NEXT: vle32.v v8, (a2)
1085 ; REMAT-NEXT: lui a7, 7
1086 ; REMAT-NEXT: addiw a7, a7, 1536
1087 ; REMAT-NEXT: add a2, a0, a7
1088 ; REMAT-NEXT: vle32.v v14, (a2)
1089 ; REMAT-NEXT: sf.vc.vv 3, 0, v10, v12
1090 ; REMAT-NEXT: vle32.v v10, (a2)
1091 ; REMAT-NEXT: li a6, 15
1092 ; REMAT-NEXT: slli a6, a6, 11
1093 ; REMAT-NEXT: add a2, a0, a6
1094 ; REMAT-NEXT: vle32.v v12, (a2)
1095 ; REMAT-NEXT: sf.vc.vv 3, 0, v8, v14
1096 ; REMAT-NEXT: vle32.v v8, (a2)
1097 ; REMAT-NEXT: lui a5, 8
1098 ; REMAT-NEXT: addiw a5, a5, -1536
1099 ; REMAT-NEXT: add a2, a0, a5
1100 ; REMAT-NEXT: vle32.v v14, (a2)
1101 ; REMAT-NEXT: sf.vc.vv 3, 0, v10, v12
1102 ; REMAT-NEXT: vle32.v v10, (a2)
1103 ; REMAT-NEXT: li a4, 31
1104 ; REMAT-NEXT: slli a4, a4, 10
1105 ; REMAT-NEXT: add a2, a0, a4
1106 ; REMAT-NEXT: vle32.v v12, (a2)
1107 ; REMAT-NEXT: sf.vc.vv 3, 0, v8, v14
1108 ; REMAT-NEXT: vle32.v v8, (a2)
1109 ; REMAT-NEXT: lui a3, 8
1110 ; REMAT-NEXT: addiw a3, a3, -512
1111 ; REMAT-NEXT: add a2, a0, a3
1112 ; REMAT-NEXT: vle32.v v14, (a2)
1113 ; REMAT-NEXT: sf.vc.vv 3, 0, v10, v12
1114 ; REMAT-NEXT: vle32.v v10, (a2)
1115 ; REMAT-NEXT: lui a2, 8
1116 ; REMAT-NEXT: add a0, a0, a2
1117 ; REMAT-NEXT: vle32.v v12, (a0)
1118 ; REMAT-NEXT: sf.vc.vv 3, 0, v8, v14
1119 ; REMAT-NEXT: sf.vc.vv 3, 0, v10, v12
1120 ; REMAT-NEXT: sf.vc.v.i 2, 0, v8, 0
1121 ; REMAT-NEXT: sf.vc.v.i 2, 0, v10, 0
1122 ; REMAT-NEXT: addi a0, a1, 1024
1123 ; REMAT-NEXT: vse32.v v8, (a0)
1124 ; REMAT-NEXT: sf.vc.v.i 2, 0, v8, 0
1125 ; REMAT-NEXT: addi a0, a1, 1536
1126 ; REMAT-NEXT: vse32.v v10, (a0)
1127 ; REMAT-NEXT: li a0, 1
1128 ; REMAT-NEXT: slli a0, a0, 11
1129 ; REMAT-NEXT: add a0, a1, a0
1130 ; REMAT-NEXT: sf.vc.v.i 2, 0, v10, 0
1131 ; REMAT-NEXT: vse32.v v8, (a0)
1132 ; REMAT-NEXT: li a0, 5
1133 ; REMAT-NEXT: slli a0, a0, 9
1134 ; REMAT-NEXT: add a0, a1, a0
1135 ; REMAT-NEXT: sf.vc.v.i 2, 0, v8, 0
1136 ; REMAT-NEXT: vse32.v v10, (a0)
1137 ; REMAT-NEXT: li a0, 3
1138 ; REMAT-NEXT: slli a0, a0, 10
1139 ; REMAT-NEXT: add a0, a1, a0
1140 ; REMAT-NEXT: sf.vc.v.i 2, 0, v10, 0
1141 ; REMAT-NEXT: vse32.v v8, (a0)
1142 ; REMAT-NEXT: li a0, 7
1143 ; REMAT-NEXT: slli a0, a0, 9
1144 ; REMAT-NEXT: add a0, a1, a0
1145 ; REMAT-NEXT: sf.vc.v.i 2, 0, v8, 0
1146 ; REMAT-NEXT: vse32.v v10, (a0)
1147 ; REMAT-NEXT: lui a0, 1
1148 ; REMAT-NEXT: add a0, a1, a0
1149 ; REMAT-NEXT: sf.vc.v.i 2, 0, v10, 0
1150 ; REMAT-NEXT: vse32.v v8, (a0)
1151 ; REMAT-NEXT: li a0, 9
1152 ; REMAT-NEXT: slli a0, a0, 9
1153 ; REMAT-NEXT: add a0, a1, a0
1154 ; REMAT-NEXT: sf.vc.v.i 2, 0, v8, 0
1155 ; REMAT-NEXT: vse32.v v10, (a0)
1156 ; REMAT-NEXT: li a0, 5
1157 ; REMAT-NEXT: slli a0, a0, 10
1158 ; REMAT-NEXT: add a0, a1, a0
1159 ; REMAT-NEXT: sf.vc.v.i 2, 0, v10, 0
1160 ; REMAT-NEXT: vse32.v v8, (a0)
1161 ; REMAT-NEXT: li a0, 11
1162 ; REMAT-NEXT: slli a0, a0, 9
1163 ; REMAT-NEXT: add a0, a1, a0
1164 ; REMAT-NEXT: sf.vc.v.i 2, 0, v8, 0
1165 ; REMAT-NEXT: vse32.v v10, (a0)
1166 ; REMAT-NEXT: li a0, 3
1167 ; REMAT-NEXT: slli a0, a0, 11
1168 ; REMAT-NEXT: add a0, a1, a0
1169 ; REMAT-NEXT: sf.vc.v.i 2, 0, v10, 0
1170 ; REMAT-NEXT: vse32.v v8, (a0)
1171 ; REMAT-NEXT: li a0, 13
1172 ; REMAT-NEXT: slli a0, a0, 9
1173 ; REMAT-NEXT: add a0, a1, a0
1174 ; REMAT-NEXT: sf.vc.v.i 2, 0, v8, 0
1175 ; REMAT-NEXT: vse32.v v10, (a0)
1176 ; REMAT-NEXT: li a0, 7
1177 ; REMAT-NEXT: slli a0, a0, 10
1178 ; REMAT-NEXT: add a0, a1, a0
1179 ; REMAT-NEXT: sf.vc.v.i 2, 0, v10, 0
1180 ; REMAT-NEXT: vse32.v v8, (a0)
1181 ; REMAT-NEXT: li a0, 15
1182 ; REMAT-NEXT: slli a0, a0, 9
1183 ; REMAT-NEXT: add a0, a1, a0
1184 ; REMAT-NEXT: sf.vc.v.i 2, 0, v8, 0
1185 ; REMAT-NEXT: vse32.v v10, (a0)
1186 ; REMAT-NEXT: lui a0, 2
1187 ; REMAT-NEXT: add a0, a1, a0
1188 ; REMAT-NEXT: sf.vc.v.i 2, 0, v10, 0
1189 ; REMAT-NEXT: vse32.v v8, (a0)
1190 ; REMAT-NEXT: li a0, 17
1191 ; REMAT-NEXT: slli a0, a0, 9
1192 ; REMAT-NEXT: add a0, a1, a0
1193 ; REMAT-NEXT: sf.vc.v.i 2, 0, v8, 0
1194 ; REMAT-NEXT: vse32.v v10, (a0)
1195 ; REMAT-NEXT: li a0, 9
1196 ; REMAT-NEXT: slli a0, a0, 10
1197 ; REMAT-NEXT: add a0, a1, a0
1198 ; REMAT-NEXT: sf.vc.v.i 2, 0, v10, 0
1199 ; REMAT-NEXT: vse32.v v8, (a0)
1200 ; REMAT-NEXT: li a0, 19
1201 ; REMAT-NEXT: slli a0, a0, 9
1202 ; REMAT-NEXT: add a0, a1, a0
1203 ; REMAT-NEXT: sf.vc.v.i 2, 0, v8, 0
1204 ; REMAT-NEXT: vse32.v v10, (a0)
1205 ; REMAT-NEXT: li a0, 5
1206 ; REMAT-NEXT: slli a0, a0, 11
1207 ; REMAT-NEXT: add a0, a1, a0
1208 ; REMAT-NEXT: sf.vc.v.i 2, 0, v10, 0
1209 ; REMAT-NEXT: vse32.v v8, (a0)
1210 ; REMAT-NEXT: li a0, 21
1211 ; REMAT-NEXT: slli a0, a0, 9
1212 ; REMAT-NEXT: add a0, a1, a0
1213 ; REMAT-NEXT: sf.vc.v.i 2, 0, v8, 0
1214 ; REMAT-NEXT: vse32.v v10, (a0)
1215 ; REMAT-NEXT: li a0, 11
1216 ; REMAT-NEXT: slli a0, a0, 10
1217 ; REMAT-NEXT: add a0, a1, a0
1218 ; REMAT-NEXT: sf.vc.v.i 2, 0, v10, 0
1219 ; REMAT-NEXT: vse32.v v8, (a0)
1220 ; REMAT-NEXT: li a0, 23
1221 ; REMAT-NEXT: slli a0, a0, 9
1222 ; REMAT-NEXT: add a0, a1, a0
1223 ; REMAT-NEXT: sf.vc.v.i 2, 0, v8, 0
1224 ; REMAT-NEXT: vse32.v v10, (a0)
1225 ; REMAT-NEXT: lui a0, 3
1226 ; REMAT-NEXT: add a0, a1, a0
1227 ; REMAT-NEXT: sf.vc.v.i 2, 0, v10, 0
1228 ; REMAT-NEXT: vse32.v v8, (a0)
1229 ; REMAT-NEXT: li a0, 25
1230 ; REMAT-NEXT: slli a0, a0, 9
1231 ; REMAT-NEXT: add a0, a1, a0
1232 ; REMAT-NEXT: sf.vc.v.i 2, 0, v8, 0
1233 ; REMAT-NEXT: vse32.v v10, (a0)
1234 ; REMAT-NEXT: li a0, 13
1235 ; REMAT-NEXT: slli a0, a0, 10
1236 ; REMAT-NEXT: add a0, a1, a0
1237 ; REMAT-NEXT: sf.vc.v.i 2, 0, v10, 0
1238 ; REMAT-NEXT: vse32.v v8, (a0)
1239 ; REMAT-NEXT: li a0, 27
1240 ; REMAT-NEXT: slli a0, a0, 9
1241 ; REMAT-NEXT: add a0, a1, a0
1242 ; REMAT-NEXT: sf.vc.v.i 2, 0, v8, 0
1243 ; REMAT-NEXT: vse32.v v10, (a0)
1244 ; REMAT-NEXT: li a0, 7
1245 ; REMAT-NEXT: slli a0, a0, 11
1246 ; REMAT-NEXT: add a0, a1, a0
1247 ; REMAT-NEXT: sf.vc.v.i 2, 0, v10, 0
1248 ; REMAT-NEXT: vse32.v v8, (a0)
1249 ; REMAT-NEXT: li a0, 29
1250 ; REMAT-NEXT: slli a0, a0, 9
1251 ; REMAT-NEXT: add a0, a1, a0
1252 ; REMAT-NEXT: sf.vc.v.i 2, 0, v8, 0
1253 ; REMAT-NEXT: vse32.v v10, (a0)
1254 ; REMAT-NEXT: li a0, 15
1255 ; REMAT-NEXT: slli a0, a0, 10
1256 ; REMAT-NEXT: add a0, a1, a0
1257 ; REMAT-NEXT: sf.vc.v.i 2, 0, v10, 0
1258 ; REMAT-NEXT: vse32.v v8, (a0)
1259 ; REMAT-NEXT: li a0, 31
1260 ; REMAT-NEXT: slli a0, a0, 9
1261 ; REMAT-NEXT: add a0, a1, a0
1262 ; REMAT-NEXT: sf.vc.v.i 2, 0, v8, 0
1263 ; REMAT-NEXT: vse32.v v10, (a0)
1264 ; REMAT-NEXT: lui a0, 4
1265 ; REMAT-NEXT: add a0, a1, a0
1266 ; REMAT-NEXT: sf.vc.v.i 2, 0, v10, 0
1267 ; REMAT-NEXT: vse32.v v8, (a0)
1268 ; REMAT-NEXT: lui a0, 4
1269 ; REMAT-NEXT: addiw a0, a0, 512
1270 ; REMAT-NEXT: add a0, a1, a0
1271 ; REMAT-NEXT: sf.vc.v.i 2, 0, v8, 0
1272 ; REMAT-NEXT: vse32.v v10, (a0)
1273 ; REMAT-NEXT: li a0, 17
1274 ; REMAT-NEXT: slli a0, a0, 10
1275 ; REMAT-NEXT: add a0, a1, a0
1276 ; REMAT-NEXT: sf.vc.v.i 2, 0, v10, 0
1277 ; REMAT-NEXT: vse32.v v8, (a0)
1278 ; REMAT-NEXT: lui a0, 4
1279 ; REMAT-NEXT: addiw a0, a0, 1536
1280 ; REMAT-NEXT: add a0, a1, a0
1281 ; REMAT-NEXT: sf.vc.v.i 2, 0, v8, 0
1282 ; REMAT-NEXT: vse32.v v10, (a0)
1283 ; REMAT-NEXT: li a0, 9
1284 ; REMAT-NEXT: slli a0, a0, 11
1285 ; REMAT-NEXT: add a0, a1, a0
1286 ; REMAT-NEXT: sf.vc.v.i 2, 0, v10, 0
1287 ; REMAT-NEXT: vse32.v v8, (a0)
1288 ; REMAT-NEXT: lui a0, 5
1289 ; REMAT-NEXT: addiw a0, a0, -1536
1290 ; REMAT-NEXT: add a0, a1, a0
1291 ; REMAT-NEXT: sf.vc.v.i 2, 0, v8, 0
1292 ; REMAT-NEXT: vse32.v v10, (a0)
1293 ; REMAT-NEXT: li a0, 19
1294 ; REMAT-NEXT: slli a0, a0, 10
1295 ; REMAT-NEXT: add a0, a1, a0
1296 ; REMAT-NEXT: sf.vc.v.i 2, 0, v10, 0
1297 ; REMAT-NEXT: vse32.v v8, (a0)
1298 ; REMAT-NEXT: add ra, a1, ra
1299 ; REMAT-NEXT: sf.vc.v.i 2, 0, v8, 0
1300 ; REMAT-NEXT: vse32.v v10, (ra)
1301 ; REMAT-NEXT: add s11, a1, s11
1302 ; REMAT-NEXT: sf.vc.v.i 2, 0, v10, 0
1303 ; REMAT-NEXT: vse32.v v8, (s11)
1304 ; REMAT-NEXT: add s10, a1, s10
1305 ; REMAT-NEXT: sf.vc.v.i 2, 0, v8, 0
1306 ; REMAT-NEXT: vse32.v v10, (s10)
1307 ; REMAT-NEXT: add s9, a1, s9
1308 ; REMAT-NEXT: sf.vc.v.i 2, 0, v10, 0
1309 ; REMAT-NEXT: vse32.v v8, (s9)
1310 ; REMAT-NEXT: add s8, a1, s8
1311 ; REMAT-NEXT: sf.vc.v.i 2, 0, v8, 0
1312 ; REMAT-NEXT: vse32.v v10, (s8)
1313 ; REMAT-NEXT: add s7, a1, s7
1314 ; REMAT-NEXT: sf.vc.v.i 2, 0, v10, 0
1315 ; REMAT-NEXT: vse32.v v8, (s7)
1316 ; REMAT-NEXT: add s6, a1, s6
1317 ; REMAT-NEXT: sf.vc.v.i 2, 0, v8, 0
1318 ; REMAT-NEXT: vse32.v v10, (s6)
1319 ; REMAT-NEXT: add s5, a1, s5
1320 ; REMAT-NEXT: sf.vc.v.i 2, 0, v10, 0
1321 ; REMAT-NEXT: vse32.v v8, (s5)
1322 ; REMAT-NEXT: add s4, a1, s4
1323 ; REMAT-NEXT: sf.vc.v.i 2, 0, v8, 0
1324 ; REMAT-NEXT: vse32.v v10, (s4)
1325 ; REMAT-NEXT: add s3, a1, s3
1326 ; REMAT-NEXT: sf.vc.v.i 2, 0, v10, 0
1327 ; REMAT-NEXT: vse32.v v8, (s3)
1328 ; REMAT-NEXT: add s2, a1, s2
1329 ; REMAT-NEXT: sf.vc.v.i 2, 0, v8, 0
1330 ; REMAT-NEXT: vse32.v v10, (s2)
1331 ; REMAT-NEXT: add s1, a1, s1
1332 ; REMAT-NEXT: sf.vc.v.i 2, 0, v10, 0
1333 ; REMAT-NEXT: vse32.v v8, (s1)
1334 ; REMAT-NEXT: add s0, a1, s0
1335 ; REMAT-NEXT: sf.vc.v.i 2, 0, v8, 0
1336 ; REMAT-NEXT: vse32.v v10, (s0)
1337 ; REMAT-NEXT: add t6, a1, t6
1338 ; REMAT-NEXT: sf.vc.v.i 2, 0, v10, 0
1339 ; REMAT-NEXT: vse32.v v8, (t6)
1340 ; REMAT-NEXT: add t5, a1, t5
1341 ; REMAT-NEXT: sf.vc.v.i 2, 0, v8, 0
1342 ; REMAT-NEXT: vse32.v v10, (t5)
1343 ; REMAT-NEXT: add t4, a1, t4
1344 ; REMAT-NEXT: sf.vc.v.i 2, 0, v10, 0
1345 ; REMAT-NEXT: vse32.v v8, (t4)
1346 ; REMAT-NEXT: add t3, a1, t3
1347 ; REMAT-NEXT: sf.vc.v.i 2, 0, v8, 0
1348 ; REMAT-NEXT: vse32.v v10, (t3)
1349 ; REMAT-NEXT: add t2, a1, t2
1350 ; REMAT-NEXT: sf.vc.v.i 2, 0, v10, 0
1351 ; REMAT-NEXT: vse32.v v8, (t2)
1352 ; REMAT-NEXT: add t1, a1, t1
1353 ; REMAT-NEXT: sf.vc.v.i 2, 0, v8, 0
1354 ; REMAT-NEXT: vse32.v v10, (t1)
1355 ; REMAT-NEXT: add t0, a1, t0
1356 ; REMAT-NEXT: sf.vc.v.i 2, 0, v10, 0
1357 ; REMAT-NEXT: vse32.v v8, (t0)
1358 ; REMAT-NEXT: add a7, a1, a7
1359 ; REMAT-NEXT: sf.vc.v.i 2, 0, v8, 0
1360 ; REMAT-NEXT: vse32.v v10, (a7)
1361 ; REMAT-NEXT: add a6, a1, a6
1362 ; REMAT-NEXT: sf.vc.v.i 2, 0, v10, 0
1363 ; REMAT-NEXT: vse32.v v8, (a6)
1364 ; REMAT-NEXT: add a5, a1, a5
1365 ; REMAT-NEXT: sf.vc.v.i 2, 0, v8, 0
1366 ; REMAT-NEXT: vse32.v v10, (a5)
1367 ; REMAT-NEXT: add a4, a1, a4
1368 ; REMAT-NEXT: sf.vc.v.i 2, 0, v10, 0
1369 ; REMAT-NEXT: vse32.v v8, (a4)
1370 ; REMAT-NEXT: add a3, a1, a3
1371 ; REMAT-NEXT: sf.vc.v.i 2, 0, v8, 0
1372 ; REMAT-NEXT: vse32.v v10, (a3)
1373 ; REMAT-NEXT: add a2, a1, a2
1374 ; REMAT-NEXT: sf.vc.v.i 2, 0, v10, 0
1375 ; REMAT-NEXT: vse32.v v8, (a2)
1376 ; REMAT-NEXT: lui a0, 8
1377 ; REMAT-NEXT: addiw a0, a0, 512
1378 ; REMAT-NEXT: add a0, a1, a0
1379 ; REMAT-NEXT: sf.vc.v.i 2, 0, v8, 0
1380 ; REMAT-NEXT: vse32.v v10, (a0)
1381 ; REMAT-NEXT: lui a0, 8
1382 ; REMAT-NEXT: addiw a0, a0, 1024
1383 ; REMAT-NEXT: add a0, a1, a0
1384 ; REMAT-NEXT: sf.vc.v.i 2, 0, v10, 0
1385 ; REMAT-NEXT: vse32.v v8, (a0)
1386 ; REMAT-NEXT: lui a0, 8
1387 ; REMAT-NEXT: addiw a0, a0, 1536
1388 ; REMAT-NEXT: add a0, a1, a0
1389 ; REMAT-NEXT: sf.vc.v.i 2, 0, v8, 0
1390 ; REMAT-NEXT: vse32.v v10, (a0)
1391 ; REMAT-NEXT: li a0, 17
1392 ; REMAT-NEXT: slli a0, a0, 11
1393 ; REMAT-NEXT: add a0, a1, a0
1394 ; REMAT-NEXT: sf.vc.v.i 2, 0, v10, 0
1395 ; REMAT-NEXT: vse32.v v8, (a0)
1396 ; REMAT-NEXT: lui a0, 9
1397 ; REMAT-NEXT: addiw a0, a0, -1536
1398 ; REMAT-NEXT: add a0, a1, a0
1399 ; REMAT-NEXT: sf.vc.v.i 2, 0, v8, 0
1400 ; REMAT-NEXT: vse32.v v10, (a0)
1401 ; REMAT-NEXT: lui a0, 9
1402 ; REMAT-NEXT: addiw a0, a0, -1024
1403 ; REMAT-NEXT: add a0, a1, a0
1404 ; REMAT-NEXT: sf.vc.v.i 2, 0, v10, 0
1405 ; REMAT-NEXT: vse32.v v8, (a0)
1406 ; REMAT-NEXT: lui a0, 9
1407 ; REMAT-NEXT: addiw a0, a0, -512
1408 ; REMAT-NEXT: add a0, a1, a0
1409 ; REMAT-NEXT: sf.vc.v.i 2, 0, v8, 0
1410 ; REMAT-NEXT: vse32.v v10, (a0)
1411 ; REMAT-NEXT: lui a0, 9
1412 ; REMAT-NEXT: add a0, a1, a0
1413 ; REMAT-NEXT: sf.vc.v.i 2, 0, v10, 0
1414 ; REMAT-NEXT: vse32.v v8, (a0)
1415 ; REMAT-NEXT: lui a0, 9
1416 ; REMAT-NEXT: addiw a0, a0, 512
1417 ; REMAT-NEXT: add a0, a1, a0
1418 ; REMAT-NEXT: sf.vc.v.i 2, 0, v8, 0
1419 ; REMAT-NEXT: vse32.v v10, (a0)
1420 ; REMAT-NEXT: lui a0, 9
1421 ; REMAT-NEXT: addiw a0, a0, 1024
1422 ; REMAT-NEXT: add a0, a1, a0
1423 ; REMAT-NEXT: sf.vc.v.i 2, 0, v10, 0
1424 ; REMAT-NEXT: vse32.v v8, (a0)
1425 ; REMAT-NEXT: lui a0, 9
1426 ; REMAT-NEXT: addiw a0, a0, 1536
1427 ; REMAT-NEXT: add a0, a1, a0
1428 ; REMAT-NEXT: sf.vc.v.i 2, 0, v8, 0
1429 ; REMAT-NEXT: vse32.v v10, (a0)
1430 ; REMAT-NEXT: li a0, 19
1431 ; REMAT-NEXT: slli a0, a0, 11
1432 ; REMAT-NEXT: add a0, a1, a0
1433 ; REMAT-NEXT: sf.vc.v.i 2, 0, v10, 0
1434 ; REMAT-NEXT: vse32.v v8, (a0)
1435 ; REMAT-NEXT: lui a0, 10
1436 ; REMAT-NEXT: addiw a0, a0, -1536
1437 ; REMAT-NEXT: add a0, a1, a0
1438 ; REMAT-NEXT: sf.vc.v.i 2, 0, v8, 0
1439 ; REMAT-NEXT: vse32.v v10, (a0)
1440 ; REMAT-NEXT: lui a0, 10
1441 ; REMAT-NEXT: addiw a0, a0, -1024
1442 ; REMAT-NEXT: add a0, a1, a0
1443 ; REMAT-NEXT: sf.vc.v.i 2, 0, v10, 0
1444 ; REMAT-NEXT: vse32.v v8, (a0)
1445 ; REMAT-NEXT: lui a0, 10
1446 ; REMAT-NEXT: addiw a0, a0, -512
1447 ; REMAT-NEXT: add a0, a1, a0
1448 ; REMAT-NEXT: sf.vc.v.i 2, 0, v8, 0
1449 ; REMAT-NEXT: vse32.v v10, (a0)
1450 ; REMAT-NEXT: lui a0, 10
1451 ; REMAT-NEXT: add a0, a1, a0
1452 ; REMAT-NEXT: sf.vc.v.i 2, 0, v10, 0
1453 ; REMAT-NEXT: vse32.v v8, (a0)
1454 ; REMAT-NEXT: lui a0, 10
1455 ; REMAT-NEXT: addiw a0, a0, 512
1456 ; REMAT-NEXT: add a0, a1, a0
1457 ; REMAT-NEXT: sf.vc.v.i 2, 0, v8, 0
1458 ; REMAT-NEXT: vse32.v v10, (a0)
1459 ; REMAT-NEXT: sf.vc.v.i 2, 0, v8, 0
1460 ; REMAT-NEXT: ld ra, 104(sp) # 8-byte Folded Reload
1461 ; REMAT-NEXT: ld s0, 96(sp) # 8-byte Folded Reload
1462 ; REMAT-NEXT: ld s1, 88(sp) # 8-byte Folded Reload
1463 ; REMAT-NEXT: ld s2, 80(sp) # 8-byte Folded Reload
1464 ; REMAT-NEXT: ld s3, 72(sp) # 8-byte Folded Reload
1465 ; REMAT-NEXT: ld s4, 64(sp) # 8-byte Folded Reload
1466 ; REMAT-NEXT: ld s5, 56(sp) # 8-byte Folded Reload
1467 ; REMAT-NEXT: ld s6, 48(sp) # 8-byte Folded Reload
1468 ; REMAT-NEXT: ld s7, 40(sp) # 8-byte Folded Reload
1469 ; REMAT-NEXT: ld s8, 32(sp) # 8-byte Folded Reload
1470 ; REMAT-NEXT: ld s9, 24(sp) # 8-byte Folded Reload
1471 ; REMAT-NEXT: ld s10, 16(sp) # 8-byte Folded Reload
1472 ; REMAT-NEXT: ld s11, 8(sp) # 8-byte Folded Reload
1473 ; REMAT-NEXT: addi sp, sp, 112
1475 %4 = tail call i64 @llvm.riscv.vsetvli.i64(i64 32, i64 2, i64 1)
1476 %5 = tail call <vscale x 4 x i32> @llvm.riscv.vle.nxv4i32.i64(<vscale x 4 x i32> poison, ptr %0, i64 %4)
1477 %6 = getelementptr inbounds i32, ptr %0, i64 128
1478 %7 = tail call <vscale x 4 x i32> @llvm.riscv.vle.nxv4i32.i64(<vscale x 4 x i32> poison, ptr %6, i64 %4)
1479 %8 = getelementptr inbounds i32, ptr %0, i64 256
1480 %9 = tail call <vscale x 4 x i32> @llvm.riscv.vle.nxv4i32.i64(<vscale x 4 x i32> poison, ptr %8, i64 %4)
1481 tail call void @llvm.riscv.sf.vc.vv.se.i64.nxv4i32.nxv4i32.i64(i64 3, i64 0, <vscale x 4 x i32> %5, <vscale x 4 x i32> %7, i64 %4)
1482 %10 = tail call <vscale x 4 x i32> @llvm.riscv.vle.nxv4i32.i64(<vscale x 4 x i32> poison, ptr %8, i64 %4)
1483 %11 = getelementptr inbounds i32, ptr %0, i64 384
1484 %12 = tail call <vscale x 4 x i32> @llvm.riscv.vle.nxv4i32.i64(<vscale x 4 x i32> poison, ptr %11, i64 %4)
1485 tail call void @llvm.riscv.sf.vc.vv.se.i64.nxv4i32.nxv4i32.i64(i64 3, i64 0, <vscale x 4 x i32> %7, <vscale x 4 x i32> %9, i64 %4)
1486 %13 = tail call <vscale x 4 x i32> @llvm.riscv.vle.nxv4i32.i64(<vscale x 4 x i32> poison, ptr %11, i64 %4)
1487 %14 = getelementptr inbounds i32, ptr %0, i64 512
1488 %15 = tail call <vscale x 4 x i32> @llvm.riscv.vle.nxv4i32.i64(<vscale x 4 x i32> poison, ptr %14, i64 %4)
1489 tail call void @llvm.riscv.sf.vc.vv.se.i64.nxv4i32.nxv4i32.i64(i64 3, i64 0, <vscale x 4 x i32> %10, <vscale x 4 x i32> %12, i64 %4)
1490 %16 = tail call <vscale x 4 x i32> @llvm.riscv.vle.nxv4i32.i64(<vscale x 4 x i32> poison, ptr %14, i64 %4)
1491 %17 = getelementptr inbounds i32, ptr %0, i64 640
1492 %18 = tail call <vscale x 4 x i32> @llvm.riscv.vle.nxv4i32.i64(<vscale x 4 x i32> poison, ptr %17, i64 %4)
1493 tail call void @llvm.riscv.sf.vc.vv.se.i64.nxv4i32.nxv4i32.i64(i64 3, i64 0, <vscale x 4 x i32> %13, <vscale x 4 x i32> %15, i64 %4)
1494 %19 = tail call <vscale x 4 x i32> @llvm.riscv.vle.nxv4i32.i64(<vscale x 4 x i32> poison, ptr %17, i64 %4)
1495 %20 = getelementptr inbounds i32, ptr %0, i64 768
1496 %21 = tail call <vscale x 4 x i32> @llvm.riscv.vle.nxv4i32.i64(<vscale x 4 x i32> poison, ptr %20, i64 %4)
1497 tail call void @llvm.riscv.sf.vc.vv.se.i64.nxv4i32.nxv4i32.i64(i64 3, i64 0, <vscale x 4 x i32> %16, <vscale x 4 x i32> %18, i64 %4)
1498 %22 = tail call <vscale x 4 x i32> @llvm.riscv.vle.nxv4i32.i64(<vscale x 4 x i32> poison, ptr %20, i64 %4)
1499 %23 = getelementptr inbounds i32, ptr %0, i64 896
1500 %24 = tail call <vscale x 4 x i32> @llvm.riscv.vle.nxv4i32.i64(<vscale x 4 x i32> poison, ptr %23, i64 %4)
1501 tail call void @llvm.riscv.sf.vc.vv.se.i64.nxv4i32.nxv4i32.i64(i64 3, i64 0, <vscale x 4 x i32> %19, <vscale x 4 x i32> %21, i64 %4)
1502 %25 = tail call <vscale x 4 x i32> @llvm.riscv.vle.nxv4i32.i64(<vscale x 4 x i32> poison, ptr %23, i64 %4)
1503 %26 = getelementptr inbounds i32, ptr %0, i64 1024
1504 %27 = tail call <vscale x 4 x i32> @llvm.riscv.vle.nxv4i32.i64(<vscale x 4 x i32> poison, ptr %26, i64 %4)
1505 tail call void @llvm.riscv.sf.vc.vv.se.i64.nxv4i32.nxv4i32.i64(i64 3, i64 0, <vscale x 4 x i32> %22, <vscale x 4 x i32> %24, i64 %4)
1506 %28 = tail call <vscale x 4 x i32> @llvm.riscv.vle.nxv4i32.i64(<vscale x 4 x i32> poison, ptr %26, i64 %4)
1507 %29 = getelementptr inbounds i32, ptr %0, i64 1152
1508 %30 = tail call <vscale x 4 x i32> @llvm.riscv.vle.nxv4i32.i64(<vscale x 4 x i32> poison, ptr %29, i64 %4)
1509 tail call void @llvm.riscv.sf.vc.vv.se.i64.nxv4i32.nxv4i32.i64(i64 3, i64 0, <vscale x 4 x i32> %25, <vscale x 4 x i32> %27, i64 %4)
1510 %31 = tail call <vscale x 4 x i32> @llvm.riscv.vle.nxv4i32.i64(<vscale x 4 x i32> poison, ptr %29, i64 %4)
1511 %32 = getelementptr inbounds i32, ptr %0, i64 1280
1512 %33 = tail call <vscale x 4 x i32> @llvm.riscv.vle.nxv4i32.i64(<vscale x 4 x i32> poison, ptr %32, i64 %4)
1513 tail call void @llvm.riscv.sf.vc.vv.se.i64.nxv4i32.nxv4i32.i64(i64 3, i64 0, <vscale x 4 x i32> %28, <vscale x 4 x i32> %30, i64 %4)
1514 %34 = tail call <vscale x 4 x i32> @llvm.riscv.vle.nxv4i32.i64(<vscale x 4 x i32> poison, ptr %32, i64 %4)
1515 %35 = getelementptr inbounds i32, ptr %0, i64 1408
1516 %36 = tail call <vscale x 4 x i32> @llvm.riscv.vle.nxv4i32.i64(<vscale x 4 x i32> poison, ptr %35, i64 %4)
1517 tail call void @llvm.riscv.sf.vc.vv.se.i64.nxv4i32.nxv4i32.i64(i64 3, i64 0, <vscale x 4 x i32> %31, <vscale x 4 x i32> %33, i64 %4)
1518 %37 = tail call <vscale x 4 x i32> @llvm.riscv.vle.nxv4i32.i64(<vscale x 4 x i32> poison, ptr %35, i64 %4)
1519 %38 = getelementptr inbounds i32, ptr %0, i64 1536
1520 %39 = tail call <vscale x 4 x i32> @llvm.riscv.vle.nxv4i32.i64(<vscale x 4 x i32> poison, ptr %38, i64 %4)
1521 tail call void @llvm.riscv.sf.vc.vv.se.i64.nxv4i32.nxv4i32.i64(i64 3, i64 0, <vscale x 4 x i32> %34, <vscale x 4 x i32> %36, i64 %4)
1522 %40 = tail call <vscale x 4 x i32> @llvm.riscv.vle.nxv4i32.i64(<vscale x 4 x i32> poison, ptr %38, i64 %4)
1523 %41 = getelementptr inbounds i32, ptr %0, i64 1664
1524 %42 = tail call <vscale x 4 x i32> @llvm.riscv.vle.nxv4i32.i64(<vscale x 4 x i32> poison, ptr %41, i64 %4)
1525 tail call void @llvm.riscv.sf.vc.vv.se.i64.nxv4i32.nxv4i32.i64(i64 3, i64 0, <vscale x 4 x i32> %37, <vscale x 4 x i32> %39, i64 %4)
1526 %43 = tail call <vscale x 4 x i32> @llvm.riscv.vle.nxv4i32.i64(<vscale x 4 x i32> poison, ptr %41, i64 %4)
1527 %44 = getelementptr inbounds i32, ptr %0, i64 1792
1528 %45 = tail call <vscale x 4 x i32> @llvm.riscv.vle.nxv4i32.i64(<vscale x 4 x i32> poison, ptr %44, i64 %4)
1529 tail call void @llvm.riscv.sf.vc.vv.se.i64.nxv4i32.nxv4i32.i64(i64 3, i64 0, <vscale x 4 x i32> %40, <vscale x 4 x i32> %42, i64 %4)
1530 %46 = tail call <vscale x 4 x i32> @llvm.riscv.vle.nxv4i32.i64(<vscale x 4 x i32> poison, ptr %44, i64 %4)
1531 %47 = getelementptr inbounds i32, ptr %0, i64 1920
1532 %48 = tail call <vscale x 4 x i32> @llvm.riscv.vle.nxv4i32.i64(<vscale x 4 x i32> poison, ptr %47, i64 %4)
1533 tail call void @llvm.riscv.sf.vc.vv.se.i64.nxv4i32.nxv4i32.i64(i64 3, i64 0, <vscale x 4 x i32> %43, <vscale x 4 x i32> %45, i64 %4)
1534 %49 = tail call <vscale x 4 x i32> @llvm.riscv.vle.nxv4i32.i64(<vscale x 4 x i32> poison, ptr %47, i64 %4)
1535 %50 = getelementptr inbounds i32, ptr %0, i64 2048
1536 %51 = tail call <vscale x 4 x i32> @llvm.riscv.vle.nxv4i32.i64(<vscale x 4 x i32> poison, ptr %50, i64 %4)
1537 tail call void @llvm.riscv.sf.vc.vv.se.i64.nxv4i32.nxv4i32.i64(i64 3, i64 0, <vscale x 4 x i32> %46, <vscale x 4 x i32> %48, i64 %4)
1538 %52 = tail call <vscale x 4 x i32> @llvm.riscv.vle.nxv4i32.i64(<vscale x 4 x i32> poison, ptr %50, i64 %4)
1539 %53 = getelementptr inbounds i32, ptr %0, i64 2176
1540 %54 = tail call <vscale x 4 x i32> @llvm.riscv.vle.nxv4i32.i64(<vscale x 4 x i32> poison, ptr %53, i64 %4)
1541 tail call void @llvm.riscv.sf.vc.vv.se.i64.nxv4i32.nxv4i32.i64(i64 3, i64 0, <vscale x 4 x i32> %49, <vscale x 4 x i32> %51, i64 %4)
1542 %55 = tail call <vscale x 4 x i32> @llvm.riscv.vle.nxv4i32.i64(<vscale x 4 x i32> poison, ptr %53, i64 %4)
1543 %56 = getelementptr inbounds i32, ptr %0, i64 2304
1544 %57 = tail call <vscale x 4 x i32> @llvm.riscv.vle.nxv4i32.i64(<vscale x 4 x i32> poison, ptr %56, i64 %4)
1545 tail call void @llvm.riscv.sf.vc.vv.se.i64.nxv4i32.nxv4i32.i64(i64 3, i64 0, <vscale x 4 x i32> %52, <vscale x 4 x i32> %54, i64 %4)
1546 %58 = tail call <vscale x 4 x i32> @llvm.riscv.vle.nxv4i32.i64(<vscale x 4 x i32> poison, ptr %56, i64 %4)
1547 %59 = getelementptr inbounds i32, ptr %0, i64 2432
1548 %60 = tail call <vscale x 4 x i32> @llvm.riscv.vle.nxv4i32.i64(<vscale x 4 x i32> poison, ptr %59, i64 %4)
1549 tail call void @llvm.riscv.sf.vc.vv.se.i64.nxv4i32.nxv4i32.i64(i64 3, i64 0, <vscale x 4 x i32> %55, <vscale x 4 x i32> %57, i64 %4)
1550 %61 = tail call <vscale x 4 x i32> @llvm.riscv.vle.nxv4i32.i64(<vscale x 4 x i32> poison, ptr %59, i64 %4)
1551 %62 = getelementptr inbounds i32, ptr %0, i64 2560
1552 %63 = tail call <vscale x 4 x i32> @llvm.riscv.vle.nxv4i32.i64(<vscale x 4 x i32> poison, ptr %62, i64 %4)
1553 tail call void @llvm.riscv.sf.vc.vv.se.i64.nxv4i32.nxv4i32.i64(i64 3, i64 0, <vscale x 4 x i32> %58, <vscale x 4 x i32> %60, i64 %4)
1554 %64 = tail call <vscale x 4 x i32> @llvm.riscv.vle.nxv4i32.i64(<vscale x 4 x i32> poison, ptr %62, i64 %4)
1555 %65 = getelementptr inbounds i32, ptr %0, i64 2688
1556 %66 = tail call <vscale x 4 x i32> @llvm.riscv.vle.nxv4i32.i64(<vscale x 4 x i32> poison, ptr %65, i64 %4)
1557 tail call void @llvm.riscv.sf.vc.vv.se.i64.nxv4i32.nxv4i32.i64(i64 3, i64 0, <vscale x 4 x i32> %61, <vscale x 4 x i32> %63, i64 %4)
1558 %67 = tail call <vscale x 4 x i32> @llvm.riscv.vle.nxv4i32.i64(<vscale x 4 x i32> poison, ptr %65, i64 %4)
1559 %68 = getelementptr inbounds i32, ptr %0, i64 2816
1560 %69 = tail call <vscale x 4 x i32> @llvm.riscv.vle.nxv4i32.i64(<vscale x 4 x i32> poison, ptr %68, i64 %4)
1561 tail call void @llvm.riscv.sf.vc.vv.se.i64.nxv4i32.nxv4i32.i64(i64 3, i64 0, <vscale x 4 x i32> %64, <vscale x 4 x i32> %66, i64 %4)
1562 %70 = tail call <vscale x 4 x i32> @llvm.riscv.vle.nxv4i32.i64(<vscale x 4 x i32> poison, ptr %68, i64 %4)
1563 %71 = getelementptr inbounds i32, ptr %0, i64 2944
1564 %72 = tail call <vscale x 4 x i32> @llvm.riscv.vle.nxv4i32.i64(<vscale x 4 x i32> poison, ptr %71, i64 %4)
1565 tail call void @llvm.riscv.sf.vc.vv.se.i64.nxv4i32.nxv4i32.i64(i64 3, i64 0, <vscale x 4 x i32> %67, <vscale x 4 x i32> %69, i64 %4)
1566 %73 = tail call <vscale x 4 x i32> @llvm.riscv.vle.nxv4i32.i64(<vscale x 4 x i32> poison, ptr %71, i64 %4)
1567 %74 = getelementptr inbounds i32, ptr %0, i64 3072
1568 %75 = tail call <vscale x 4 x i32> @llvm.riscv.vle.nxv4i32.i64(<vscale x 4 x i32> poison, ptr %74, i64 %4)
1569 tail call void @llvm.riscv.sf.vc.vv.se.i64.nxv4i32.nxv4i32.i64(i64 3, i64 0, <vscale x 4 x i32> %70, <vscale x 4 x i32> %72, i64 %4)
1570 %76 = tail call <vscale x 4 x i32> @llvm.riscv.vle.nxv4i32.i64(<vscale x 4 x i32> poison, ptr %74, i64 %4)
1571 %77 = getelementptr inbounds i32, ptr %0, i64 3200
1572 %78 = tail call <vscale x 4 x i32> @llvm.riscv.vle.nxv4i32.i64(<vscale x 4 x i32> poison, ptr %77, i64 %4)
1573 tail call void @llvm.riscv.sf.vc.vv.se.i64.nxv4i32.nxv4i32.i64(i64 3, i64 0, <vscale x 4 x i32> %73, <vscale x 4 x i32> %75, i64 %4)
1574 %79 = tail call <vscale x 4 x i32> @llvm.riscv.vle.nxv4i32.i64(<vscale x 4 x i32> poison, ptr %77, i64 %4)
1575 %80 = getelementptr inbounds i32, ptr %0, i64 3328
1576 %81 = tail call <vscale x 4 x i32> @llvm.riscv.vle.nxv4i32.i64(<vscale x 4 x i32> poison, ptr %80, i64 %4)
1577 tail call void @llvm.riscv.sf.vc.vv.se.i64.nxv4i32.nxv4i32.i64(i64 3, i64 0, <vscale x 4 x i32> %76, <vscale x 4 x i32> %78, i64 %4)
1578 %82 = tail call <vscale x 4 x i32> @llvm.riscv.vle.nxv4i32.i64(<vscale x 4 x i32> poison, ptr %80, i64 %4)
1579 %83 = getelementptr inbounds i32, ptr %0, i64 3456
1580 %84 = tail call <vscale x 4 x i32> @llvm.riscv.vle.nxv4i32.i64(<vscale x 4 x i32> poison, ptr %83, i64 %4)
1581 tail call void @llvm.riscv.sf.vc.vv.se.i64.nxv4i32.nxv4i32.i64(i64 3, i64 0, <vscale x 4 x i32> %79, <vscale x 4 x i32> %81, i64 %4)
1582 %85 = tail call <vscale x 4 x i32> @llvm.riscv.vle.nxv4i32.i64(<vscale x 4 x i32> poison, ptr %83, i64 %4)
1583 %86 = getelementptr inbounds i32, ptr %0, i64 3584
1584 %87 = tail call <vscale x 4 x i32> @llvm.riscv.vle.nxv4i32.i64(<vscale x 4 x i32> poison, ptr %86, i64 %4)
1585 tail call void @llvm.riscv.sf.vc.vv.se.i64.nxv4i32.nxv4i32.i64(i64 3, i64 0, <vscale x 4 x i32> %82, <vscale x 4 x i32> %84, i64 %4)
1586 %88 = tail call <vscale x 4 x i32> @llvm.riscv.vle.nxv4i32.i64(<vscale x 4 x i32> poison, ptr %86, i64 %4)
1587 %89 = getelementptr inbounds i32, ptr %0, i64 3712
1588 %90 = tail call <vscale x 4 x i32> @llvm.riscv.vle.nxv4i32.i64(<vscale x 4 x i32> poison, ptr %89, i64 %4)
1589 tail call void @llvm.riscv.sf.vc.vv.se.i64.nxv4i32.nxv4i32.i64(i64 3, i64 0, <vscale x 4 x i32> %85, <vscale x 4 x i32> %87, i64 %4)
1590 %91 = tail call <vscale x 4 x i32> @llvm.riscv.vle.nxv4i32.i64(<vscale x 4 x i32> poison, ptr %89, i64 %4)
1591 %92 = getelementptr inbounds i32, ptr %0, i64 3840
1592 %93 = tail call <vscale x 4 x i32> @llvm.riscv.vle.nxv4i32.i64(<vscale x 4 x i32> poison, ptr %92, i64 %4)
1593 tail call void @llvm.riscv.sf.vc.vv.se.i64.nxv4i32.nxv4i32.i64(i64 3, i64 0, <vscale x 4 x i32> %88, <vscale x 4 x i32> %90, i64 %4)
1594 %94 = tail call <vscale x 4 x i32> @llvm.riscv.vle.nxv4i32.i64(<vscale x 4 x i32> poison, ptr %92, i64 %4)
1595 %95 = getelementptr inbounds i32, ptr %0, i64 3968
1596 %96 = tail call <vscale x 4 x i32> @llvm.riscv.vle.nxv4i32.i64(<vscale x 4 x i32> poison, ptr %95, i64 %4)
1597 tail call void @llvm.riscv.sf.vc.vv.se.i64.nxv4i32.nxv4i32.i64(i64 3, i64 0, <vscale x 4 x i32> %91, <vscale x 4 x i32> %93, i64 %4)
1598 %97 = tail call <vscale x 4 x i32> @llvm.riscv.vle.nxv4i32.i64(<vscale x 4 x i32> poison, ptr %95, i64 %4)
1599 %98 = getelementptr inbounds i32, ptr %0, i64 4096
1600 %99 = tail call <vscale x 4 x i32> @llvm.riscv.vle.nxv4i32.i64(<vscale x 4 x i32> poison, ptr %98, i64 %4)
1601 tail call void @llvm.riscv.sf.vc.vv.se.i64.nxv4i32.nxv4i32.i64(i64 3, i64 0, <vscale x 4 x i32> %94, <vscale x 4 x i32> %96, i64 %4)
1602 %100 = tail call <vscale x 4 x i32> @llvm.riscv.vle.nxv4i32.i64(<vscale x 4 x i32> poison, ptr %98, i64 %4)
1603 %101 = getelementptr inbounds i32, ptr %0, i64 4224
1604 %102 = tail call <vscale x 4 x i32> @llvm.riscv.vle.nxv4i32.i64(<vscale x 4 x i32> poison, ptr %101, i64 %4)
1605 tail call void @llvm.riscv.sf.vc.vv.se.i64.nxv4i32.nxv4i32.i64(i64 3, i64 0, <vscale x 4 x i32> %97, <vscale x 4 x i32> %99, i64 %4)
1606 %103 = tail call <vscale x 4 x i32> @llvm.riscv.vle.nxv4i32.i64(<vscale x 4 x i32> poison, ptr %101, i64 %4)
1607 %104 = getelementptr inbounds i32, ptr %0, i64 4352
1608 %105 = tail call <vscale x 4 x i32> @llvm.riscv.vle.nxv4i32.i64(<vscale x 4 x i32> poison, ptr %104, i64 %4)
1609 tail call void @llvm.riscv.sf.vc.vv.se.i64.nxv4i32.nxv4i32.i64(i64 3, i64 0, <vscale x 4 x i32> %100, <vscale x 4 x i32> %102, i64 %4)
1610 %106 = tail call <vscale x 4 x i32> @llvm.riscv.vle.nxv4i32.i64(<vscale x 4 x i32> poison, ptr %104, i64 %4)
1611 %107 = getelementptr inbounds i32, ptr %0, i64 4480
1612 %108 = tail call <vscale x 4 x i32> @llvm.riscv.vle.nxv4i32.i64(<vscale x 4 x i32> poison, ptr %107, i64 %4)
1613 tail call void @llvm.riscv.sf.vc.vv.se.i64.nxv4i32.nxv4i32.i64(i64 3, i64 0, <vscale x 4 x i32> %103, <vscale x 4 x i32> %105, i64 %4)
1614 %109 = tail call <vscale x 4 x i32> @llvm.riscv.vle.nxv4i32.i64(<vscale x 4 x i32> poison, ptr %107, i64 %4)
1615 %110 = getelementptr inbounds i32, ptr %0, i64 4608
1616 %111 = tail call <vscale x 4 x i32> @llvm.riscv.vle.nxv4i32.i64(<vscale x 4 x i32> poison, ptr %110, i64 %4)
1617 tail call void @llvm.riscv.sf.vc.vv.se.i64.nxv4i32.nxv4i32.i64(i64 3, i64 0, <vscale x 4 x i32> %106, <vscale x 4 x i32> %108, i64 %4)
1618 %112 = tail call <vscale x 4 x i32> @llvm.riscv.vle.nxv4i32.i64(<vscale x 4 x i32> poison, ptr %110, i64 %4)
1619 %113 = getelementptr inbounds i32, ptr %0, i64 4736
1620 %114 = tail call <vscale x 4 x i32> @llvm.riscv.vle.nxv4i32.i64(<vscale x 4 x i32> poison, ptr %113, i64 %4)
1621 tail call void @llvm.riscv.sf.vc.vv.se.i64.nxv4i32.nxv4i32.i64(i64 3, i64 0, <vscale x 4 x i32> %109, <vscale x 4 x i32> %111, i64 %4)
1622 %115 = tail call <vscale x 4 x i32> @llvm.riscv.vle.nxv4i32.i64(<vscale x 4 x i32> poison, ptr %113, i64 %4)
1623 %116 = getelementptr inbounds i32, ptr %0, i64 4864
1624 %117 = tail call <vscale x 4 x i32> @llvm.riscv.vle.nxv4i32.i64(<vscale x 4 x i32> poison, ptr %116, i64 %4)
1625 tail call void @llvm.riscv.sf.vc.vv.se.i64.nxv4i32.nxv4i32.i64(i64 3, i64 0, <vscale x 4 x i32> %112, <vscale x 4 x i32> %114, i64 %4)
1626 %118 = tail call <vscale x 4 x i32> @llvm.riscv.vle.nxv4i32.i64(<vscale x 4 x i32> poison, ptr %116, i64 %4)
1627 %119 = getelementptr inbounds i32, ptr %0, i64 4992
1628 %120 = tail call <vscale x 4 x i32> @llvm.riscv.vle.nxv4i32.i64(<vscale x 4 x i32> poison, ptr %119, i64 %4)
1629 tail call void @llvm.riscv.sf.vc.vv.se.i64.nxv4i32.nxv4i32.i64(i64 3, i64 0, <vscale x 4 x i32> %115, <vscale x 4 x i32> %117, i64 %4)
1630 %121 = tail call <vscale x 4 x i32> @llvm.riscv.vle.nxv4i32.i64(<vscale x 4 x i32> poison, ptr %119, i64 %4)
1631 %122 = getelementptr inbounds i32, ptr %0, i64 5120
1632 %123 = tail call <vscale x 4 x i32> @llvm.riscv.vle.nxv4i32.i64(<vscale x 4 x i32> poison, ptr %122, i64 %4)
1633 tail call void @llvm.riscv.sf.vc.vv.se.i64.nxv4i32.nxv4i32.i64(i64 3, i64 0, <vscale x 4 x i32> %118, <vscale x 4 x i32> %120, i64 %4)
1634 %124 = tail call <vscale x 4 x i32> @llvm.riscv.vle.nxv4i32.i64(<vscale x 4 x i32> poison, ptr %122, i64 %4)
1635 %125 = getelementptr inbounds i32, ptr %0, i64 5248
1636 %126 = tail call <vscale x 4 x i32> @llvm.riscv.vle.nxv4i32.i64(<vscale x 4 x i32> poison, ptr %125, i64 %4)
1637 tail call void @llvm.riscv.sf.vc.vv.se.i64.nxv4i32.nxv4i32.i64(i64 3, i64 0, <vscale x 4 x i32> %121, <vscale x 4 x i32> %123, i64 %4)
1638 %127 = tail call <vscale x 4 x i32> @llvm.riscv.vle.nxv4i32.i64(<vscale x 4 x i32> poison, ptr %125, i64 %4)
1639 %128 = getelementptr inbounds i32, ptr %0, i64 5376
1640 %129 = tail call <vscale x 4 x i32> @llvm.riscv.vle.nxv4i32.i64(<vscale x 4 x i32> poison, ptr %128, i64 %4)
1641 tail call void @llvm.riscv.sf.vc.vv.se.i64.nxv4i32.nxv4i32.i64(i64 3, i64 0, <vscale x 4 x i32> %124, <vscale x 4 x i32> %126, i64 %4)
1642 %130 = tail call <vscale x 4 x i32> @llvm.riscv.vle.nxv4i32.i64(<vscale x 4 x i32> poison, ptr %128, i64 %4)
1643 %131 = getelementptr inbounds i32, ptr %0, i64 5504
1644 %132 = tail call <vscale x 4 x i32> @llvm.riscv.vle.nxv4i32.i64(<vscale x 4 x i32> poison, ptr %131, i64 %4)
1645 tail call void @llvm.riscv.sf.vc.vv.se.i64.nxv4i32.nxv4i32.i64(i64 3, i64 0, <vscale x 4 x i32> %127, <vscale x 4 x i32> %129, i64 %4)
1646 %133 = tail call <vscale x 4 x i32> @llvm.riscv.vle.nxv4i32.i64(<vscale x 4 x i32> poison, ptr %131, i64 %4)
1647 %134 = getelementptr inbounds i32, ptr %0, i64 5632
1648 %135 = tail call <vscale x 4 x i32> @llvm.riscv.vle.nxv4i32.i64(<vscale x 4 x i32> poison, ptr %134, i64 %4)
1649 tail call void @llvm.riscv.sf.vc.vv.se.i64.nxv4i32.nxv4i32.i64(i64 3, i64 0, <vscale x 4 x i32> %130, <vscale x 4 x i32> %132, i64 %4)
1650 %136 = tail call <vscale x 4 x i32> @llvm.riscv.vle.nxv4i32.i64(<vscale x 4 x i32> poison, ptr %134, i64 %4)
1651 %137 = getelementptr inbounds i32, ptr %0, i64 5760
1652 %138 = tail call <vscale x 4 x i32> @llvm.riscv.vle.nxv4i32.i64(<vscale x 4 x i32> poison, ptr %137, i64 %4)
1653 tail call void @llvm.riscv.sf.vc.vv.se.i64.nxv4i32.nxv4i32.i64(i64 3, i64 0, <vscale x 4 x i32> %133, <vscale x 4 x i32> %135, i64 %4)
1654 %139 = tail call <vscale x 4 x i32> @llvm.riscv.vle.nxv4i32.i64(<vscale x 4 x i32> poison, ptr %137, i64 %4)
1655 %140 = getelementptr inbounds i32, ptr %0, i64 5888
1656 %141 = tail call <vscale x 4 x i32> @llvm.riscv.vle.nxv4i32.i64(<vscale x 4 x i32> poison, ptr %140, i64 %4)
1657 tail call void @llvm.riscv.sf.vc.vv.se.i64.nxv4i32.nxv4i32.i64(i64 3, i64 0, <vscale x 4 x i32> %136, <vscale x 4 x i32> %138, i64 %4)
1658 %142 = tail call <vscale x 4 x i32> @llvm.riscv.vle.nxv4i32.i64(<vscale x 4 x i32> poison, ptr %140, i64 %4)
1659 %143 = getelementptr inbounds i32, ptr %0, i64 6016
1660 %144 = tail call <vscale x 4 x i32> @llvm.riscv.vle.nxv4i32.i64(<vscale x 4 x i32> poison, ptr %143, i64 %4)
1661 tail call void @llvm.riscv.sf.vc.vv.se.i64.nxv4i32.nxv4i32.i64(i64 3, i64 0, <vscale x 4 x i32> %139, <vscale x 4 x i32> %141, i64 %4)
1662 %145 = tail call <vscale x 4 x i32> @llvm.riscv.vle.nxv4i32.i64(<vscale x 4 x i32> poison, ptr %143, i64 %4)
1663 %146 = getelementptr inbounds i32, ptr %0, i64 6144
1664 %147 = tail call <vscale x 4 x i32> @llvm.riscv.vle.nxv4i32.i64(<vscale x 4 x i32> poison, ptr %146, i64 %4)
1665 tail call void @llvm.riscv.sf.vc.vv.se.i64.nxv4i32.nxv4i32.i64(i64 3, i64 0, <vscale x 4 x i32> %142, <vscale x 4 x i32> %144, i64 %4)
1666 %148 = tail call <vscale x 4 x i32> @llvm.riscv.vle.nxv4i32.i64(<vscale x 4 x i32> poison, ptr %146, i64 %4)
1667 %149 = getelementptr inbounds i32, ptr %0, i64 6272
1668 %150 = tail call <vscale x 4 x i32> @llvm.riscv.vle.nxv4i32.i64(<vscale x 4 x i32> poison, ptr %149, i64 %4)
1669 tail call void @llvm.riscv.sf.vc.vv.se.i64.nxv4i32.nxv4i32.i64(i64 3, i64 0, <vscale x 4 x i32> %145, <vscale x 4 x i32> %147, i64 %4)
1670 %151 = tail call <vscale x 4 x i32> @llvm.riscv.vle.nxv4i32.i64(<vscale x 4 x i32> poison, ptr %149, i64 %4)
1671 %152 = getelementptr inbounds i32, ptr %0, i64 6400
1672 %153 = tail call <vscale x 4 x i32> @llvm.riscv.vle.nxv4i32.i64(<vscale x 4 x i32> poison, ptr %152, i64 %4)
1673 tail call void @llvm.riscv.sf.vc.vv.se.i64.nxv4i32.nxv4i32.i64(i64 3, i64 0, <vscale x 4 x i32> %148, <vscale x 4 x i32> %150, i64 %4)
1674 %154 = tail call <vscale x 4 x i32> @llvm.riscv.vle.nxv4i32.i64(<vscale x 4 x i32> poison, ptr %152, i64 %4)
1675 %155 = getelementptr inbounds i32, ptr %0, i64 6528
1676 %156 = tail call <vscale x 4 x i32> @llvm.riscv.vle.nxv4i32.i64(<vscale x 4 x i32> poison, ptr %155, i64 %4)
1677 tail call void @llvm.riscv.sf.vc.vv.se.i64.nxv4i32.nxv4i32.i64(i64 3, i64 0, <vscale x 4 x i32> %151, <vscale x 4 x i32> %153, i64 %4)
1678 %157 = tail call <vscale x 4 x i32> @llvm.riscv.vle.nxv4i32.i64(<vscale x 4 x i32> poison, ptr %155, i64 %4)
1679 %158 = getelementptr inbounds i32, ptr %0, i64 6656
1680 %159 = tail call <vscale x 4 x i32> @llvm.riscv.vle.nxv4i32.i64(<vscale x 4 x i32> poison, ptr %158, i64 %4)
1681 tail call void @llvm.riscv.sf.vc.vv.se.i64.nxv4i32.nxv4i32.i64(i64 3, i64 0, <vscale x 4 x i32> %154, <vscale x 4 x i32> %156, i64 %4)
1682 %160 = tail call <vscale x 4 x i32> @llvm.riscv.vle.nxv4i32.i64(<vscale x 4 x i32> poison, ptr %158, i64 %4)
1683 %161 = getelementptr inbounds i32, ptr %0, i64 6784
1684 %162 = tail call <vscale x 4 x i32> @llvm.riscv.vle.nxv4i32.i64(<vscale x 4 x i32> poison, ptr %161, i64 %4)
1685 tail call void @llvm.riscv.sf.vc.vv.se.i64.nxv4i32.nxv4i32.i64(i64 3, i64 0, <vscale x 4 x i32> %157, <vscale x 4 x i32> %159, i64 %4)
1686 %163 = tail call <vscale x 4 x i32> @llvm.riscv.vle.nxv4i32.i64(<vscale x 4 x i32> poison, ptr %161, i64 %4)
1687 %164 = getelementptr inbounds i32, ptr %0, i64 6912
1688 %165 = tail call <vscale x 4 x i32> @llvm.riscv.vle.nxv4i32.i64(<vscale x 4 x i32> poison, ptr %164, i64 %4)
1689 tail call void @llvm.riscv.sf.vc.vv.se.i64.nxv4i32.nxv4i32.i64(i64 3, i64 0, <vscale x 4 x i32> %160, <vscale x 4 x i32> %162, i64 %4)
1690 %166 = tail call <vscale x 4 x i32> @llvm.riscv.vle.nxv4i32.i64(<vscale x 4 x i32> poison, ptr %164, i64 %4)
1691 %167 = getelementptr inbounds i32, ptr %0, i64 7040
1692 %168 = tail call <vscale x 4 x i32> @llvm.riscv.vle.nxv4i32.i64(<vscale x 4 x i32> poison, ptr %167, i64 %4)
1693 tail call void @llvm.riscv.sf.vc.vv.se.i64.nxv4i32.nxv4i32.i64(i64 3, i64 0, <vscale x 4 x i32> %163, <vscale x 4 x i32> %165, i64 %4)
1694 %169 = tail call <vscale x 4 x i32> @llvm.riscv.vle.nxv4i32.i64(<vscale x 4 x i32> poison, ptr %167, i64 %4)
1695 %170 = getelementptr inbounds i32, ptr %0, i64 7168
1696 %171 = tail call <vscale x 4 x i32> @llvm.riscv.vle.nxv4i32.i64(<vscale x 4 x i32> poison, ptr %170, i64 %4)
1697 tail call void @llvm.riscv.sf.vc.vv.se.i64.nxv4i32.nxv4i32.i64(i64 3, i64 0, <vscale x 4 x i32> %166, <vscale x 4 x i32> %168, i64 %4)
1698 %172 = tail call <vscale x 4 x i32> @llvm.riscv.vle.nxv4i32.i64(<vscale x 4 x i32> poison, ptr %170, i64 %4)
1699 %173 = getelementptr inbounds i32, ptr %0, i64 7296
1700 %174 = tail call <vscale x 4 x i32> @llvm.riscv.vle.nxv4i32.i64(<vscale x 4 x i32> poison, ptr %173, i64 %4)
1701 tail call void @llvm.riscv.sf.vc.vv.se.i64.nxv4i32.nxv4i32.i64(i64 3, i64 0, <vscale x 4 x i32> %169, <vscale x 4 x i32> %171, i64 %4)
1702 %175 = tail call <vscale x 4 x i32> @llvm.riscv.vle.nxv4i32.i64(<vscale x 4 x i32> poison, ptr %173, i64 %4)
1703 %176 = getelementptr inbounds i32, ptr %0, i64 7424
1704 %177 = tail call <vscale x 4 x i32> @llvm.riscv.vle.nxv4i32.i64(<vscale x 4 x i32> poison, ptr %176, i64 %4)
1705 tail call void @llvm.riscv.sf.vc.vv.se.i64.nxv4i32.nxv4i32.i64(i64 3, i64 0, <vscale x 4 x i32> %172, <vscale x 4 x i32> %174, i64 %4)
1706 %178 = tail call <vscale x 4 x i32> @llvm.riscv.vle.nxv4i32.i64(<vscale x 4 x i32> poison, ptr %176, i64 %4)
1707 %179 = getelementptr inbounds i32, ptr %0, i64 7552
1708 %180 = tail call <vscale x 4 x i32> @llvm.riscv.vle.nxv4i32.i64(<vscale x 4 x i32> poison, ptr %179, i64 %4)
1709 tail call void @llvm.riscv.sf.vc.vv.se.i64.nxv4i32.nxv4i32.i64(i64 3, i64 0, <vscale x 4 x i32> %175, <vscale x 4 x i32> %177, i64 %4)
1710 %181 = tail call <vscale x 4 x i32> @llvm.riscv.vle.nxv4i32.i64(<vscale x 4 x i32> poison, ptr %179, i64 %4)
1711 %182 = getelementptr inbounds i32, ptr %0, i64 7680
1712 %183 = tail call <vscale x 4 x i32> @llvm.riscv.vle.nxv4i32.i64(<vscale x 4 x i32> poison, ptr %182, i64 %4)
1713 tail call void @llvm.riscv.sf.vc.vv.se.i64.nxv4i32.nxv4i32.i64(i64 3, i64 0, <vscale x 4 x i32> %178, <vscale x 4 x i32> %180, i64 %4)
1714 %184 = tail call <vscale x 4 x i32> @llvm.riscv.vle.nxv4i32.i64(<vscale x 4 x i32> poison, ptr %182, i64 %4)
1715 %185 = getelementptr inbounds i32, ptr %0, i64 7808
1716 %186 = tail call <vscale x 4 x i32> @llvm.riscv.vle.nxv4i32.i64(<vscale x 4 x i32> poison, ptr %185, i64 %4)
1717 tail call void @llvm.riscv.sf.vc.vv.se.i64.nxv4i32.nxv4i32.i64(i64 3, i64 0, <vscale x 4 x i32> %181, <vscale x 4 x i32> %183, i64 %4)
1718 %187 = tail call <vscale x 4 x i32> @llvm.riscv.vle.nxv4i32.i64(<vscale x 4 x i32> poison, ptr %185, i64 %4)
1719 %188 = getelementptr inbounds i32, ptr %0, i64 7936
1720 %189 = tail call <vscale x 4 x i32> @llvm.riscv.vle.nxv4i32.i64(<vscale x 4 x i32> poison, ptr %188, i64 %4)
1721 tail call void @llvm.riscv.sf.vc.vv.se.i64.nxv4i32.nxv4i32.i64(i64 3, i64 0, <vscale x 4 x i32> %184, <vscale x 4 x i32> %186, i64 %4)
1722 %190 = tail call <vscale x 4 x i32> @llvm.riscv.vle.nxv4i32.i64(<vscale x 4 x i32> poison, ptr %188, i64 %4)
1723 %191 = getelementptr inbounds i32, ptr %0, i64 8064
1724 %192 = tail call <vscale x 4 x i32> @llvm.riscv.vle.nxv4i32.i64(<vscale x 4 x i32> poison, ptr %191, i64 %4)
1725 tail call void @llvm.riscv.sf.vc.vv.se.i64.nxv4i32.nxv4i32.i64(i64 3, i64 0, <vscale x 4 x i32> %187, <vscale x 4 x i32> %189, i64 %4)
1726 %193 = tail call <vscale x 4 x i32> @llvm.riscv.vle.nxv4i32.i64(<vscale x 4 x i32> poison, ptr %191, i64 %4)
1727 %194 = getelementptr inbounds i32, ptr %0, i64 8192
1728 %195 = tail call <vscale x 4 x i32> @llvm.riscv.vle.nxv4i32.i64(<vscale x 4 x i32> poison, ptr %194, i64 %4)
1729 tail call void @llvm.riscv.sf.vc.vv.se.i64.nxv4i32.nxv4i32.i64(i64 3, i64 0, <vscale x 4 x i32> %190, <vscale x 4 x i32> %192, i64 %4)
1730 tail call void @llvm.riscv.sf.vc.vv.se.i64.nxv4i32.nxv4i32.i64(i64 3, i64 0, <vscale x 4 x i32> %193, <vscale x 4 x i32> %195, i64 %4)
1731 %196 = tail call <vscale x 4 x i32> @llvm.riscv.sf.vc.v.i.se.nxv4i32.i64.i64.i64(i64 2, i64 0, i64 0, i64 %4)
1732 %197 = tail call <vscale x 4 x i32> @llvm.riscv.sf.vc.v.i.se.nxv4i32.i64.i64.i64(i64 2, i64 0, i64 0, i64 %4)
1733 %198 = getelementptr inbounds i32, ptr %1, i64 256
1734 tail call void @llvm.riscv.vse.nxv4i32.i64(<vscale x 4 x i32> %196, ptr %198, i64 %4)
1735 %199 = getelementptr inbounds i32, ptr %1, i64 384
1736 %200 = tail call <vscale x 4 x i32> @llvm.riscv.sf.vc.v.i.se.nxv4i32.i64.i64.i64(i64 2, i64 0, i64 0, i64 %4)
1737 tail call void @llvm.riscv.vse.nxv4i32.i64(<vscale x 4 x i32> %197, ptr %199, i64 %4)
1738 %201 = getelementptr inbounds i32, ptr %1, i64 512
1739 %202 = tail call <vscale x 4 x i32> @llvm.riscv.sf.vc.v.i.se.nxv4i32.i64.i64.i64(i64 2, i64 0, i64 0, i64 %4)
1740 tail call void @llvm.riscv.vse.nxv4i32.i64(<vscale x 4 x i32> %200, ptr %201, i64 %4)
1741 %203 = getelementptr inbounds i32, ptr %1, i64 640
1742 %204 = tail call <vscale x 4 x i32> @llvm.riscv.sf.vc.v.i.se.nxv4i32.i64.i64.i64(i64 2, i64 0, i64 0, i64 %4)
1743 tail call void @llvm.riscv.vse.nxv4i32.i64(<vscale x 4 x i32> %202, ptr %203, i64 %4)
1744 %205 = getelementptr inbounds i32, ptr %1, i64 768
1745 %206 = tail call <vscale x 4 x i32> @llvm.riscv.sf.vc.v.i.se.nxv4i32.i64.i64.i64(i64 2, i64 0, i64 0, i64 %4)
1746 tail call void @llvm.riscv.vse.nxv4i32.i64(<vscale x 4 x i32> %204, ptr %205, i64 %4)
1747 %207 = getelementptr inbounds i32, ptr %1, i64 896
1748 %208 = tail call <vscale x 4 x i32> @llvm.riscv.sf.vc.v.i.se.nxv4i32.i64.i64.i64(i64 2, i64 0, i64 0, i64 %4)
1749 tail call void @llvm.riscv.vse.nxv4i32.i64(<vscale x 4 x i32> %206, ptr %207, i64 %4)
1750 %209 = getelementptr inbounds i32, ptr %1, i64 1024
1751 %210 = tail call <vscale x 4 x i32> @llvm.riscv.sf.vc.v.i.se.nxv4i32.i64.i64.i64(i64 2, i64 0, i64 0, i64 %4)
1752 tail call void @llvm.riscv.vse.nxv4i32.i64(<vscale x 4 x i32> %208, ptr %209, i64 %4)
1753 %211 = getelementptr inbounds i32, ptr %1, i64 1152
1754 %212 = tail call <vscale x 4 x i32> @llvm.riscv.sf.vc.v.i.se.nxv4i32.i64.i64.i64(i64 2, i64 0, i64 0, i64 %4)
1755 tail call void @llvm.riscv.vse.nxv4i32.i64(<vscale x 4 x i32> %210, ptr %211, i64 %4)
1756 %213 = getelementptr inbounds i32, ptr %1, i64 1280
1757 %214 = tail call <vscale x 4 x i32> @llvm.riscv.sf.vc.v.i.se.nxv4i32.i64.i64.i64(i64 2, i64 0, i64 0, i64 %4)
1758 tail call void @llvm.riscv.vse.nxv4i32.i64(<vscale x 4 x i32> %212, ptr %213, i64 %4)
1759 %215 = getelementptr inbounds i32, ptr %1, i64 1408
1760 %216 = tail call <vscale x 4 x i32> @llvm.riscv.sf.vc.v.i.se.nxv4i32.i64.i64.i64(i64 2, i64 0, i64 0, i64 %4)
1761 tail call void @llvm.riscv.vse.nxv4i32.i64(<vscale x 4 x i32> %214, ptr %215, i64 %4)
1762 %217 = getelementptr inbounds i32, ptr %1, i64 1536
1763 %218 = tail call <vscale x 4 x i32> @llvm.riscv.sf.vc.v.i.se.nxv4i32.i64.i64.i64(i64 2, i64 0, i64 0, i64 %4)
1764 tail call void @llvm.riscv.vse.nxv4i32.i64(<vscale x 4 x i32> %216, ptr %217, i64 %4)
1765 %219 = getelementptr inbounds i32, ptr %1, i64 1664
1766 %220 = tail call <vscale x 4 x i32> @llvm.riscv.sf.vc.v.i.se.nxv4i32.i64.i64.i64(i64 2, i64 0, i64 0, i64 %4)
1767 tail call void @llvm.riscv.vse.nxv4i32.i64(<vscale x 4 x i32> %218, ptr %219, i64 %4)
1768 %221 = getelementptr inbounds i32, ptr %1, i64 1792
1769 %222 = tail call <vscale x 4 x i32> @llvm.riscv.sf.vc.v.i.se.nxv4i32.i64.i64.i64(i64 2, i64 0, i64 0, i64 %4)
1770 tail call void @llvm.riscv.vse.nxv4i32.i64(<vscale x 4 x i32> %220, ptr %221, i64 %4)
1771 %223 = getelementptr inbounds i32, ptr %1, i64 1920
1772 %224 = tail call <vscale x 4 x i32> @llvm.riscv.sf.vc.v.i.se.nxv4i32.i64.i64.i64(i64 2, i64 0, i64 0, i64 %4)
1773 tail call void @llvm.riscv.vse.nxv4i32.i64(<vscale x 4 x i32> %222, ptr %223, i64 %4)
1774 %225 = getelementptr inbounds i32, ptr %1, i64 2048
1775 %226 = tail call <vscale x 4 x i32> @llvm.riscv.sf.vc.v.i.se.nxv4i32.i64.i64.i64(i64 2, i64 0, i64 0, i64 %4)
1776 tail call void @llvm.riscv.vse.nxv4i32.i64(<vscale x 4 x i32> %224, ptr %225, i64 %4)
1777 %227 = getelementptr inbounds i32, ptr %1, i64 2176
1778 %228 = tail call <vscale x 4 x i32> @llvm.riscv.sf.vc.v.i.se.nxv4i32.i64.i64.i64(i64 2, i64 0, i64 0, i64 %4)
1779 tail call void @llvm.riscv.vse.nxv4i32.i64(<vscale x 4 x i32> %226, ptr %227, i64 %4)
1780 %229 = getelementptr inbounds i32, ptr %1, i64 2304
1781 %230 = tail call <vscale x 4 x i32> @llvm.riscv.sf.vc.v.i.se.nxv4i32.i64.i64.i64(i64 2, i64 0, i64 0, i64 %4)
1782 tail call void @llvm.riscv.vse.nxv4i32.i64(<vscale x 4 x i32> %228, ptr %229, i64 %4)
1783 %231 = getelementptr inbounds i32, ptr %1, i64 2432
1784 %232 = tail call <vscale x 4 x i32> @llvm.riscv.sf.vc.v.i.se.nxv4i32.i64.i64.i64(i64 2, i64 0, i64 0, i64 %4)
1785 tail call void @llvm.riscv.vse.nxv4i32.i64(<vscale x 4 x i32> %230, ptr %231, i64 %4)
1786 %233 = getelementptr inbounds i32, ptr %1, i64 2560
1787 %234 = tail call <vscale x 4 x i32> @llvm.riscv.sf.vc.v.i.se.nxv4i32.i64.i64.i64(i64 2, i64 0, i64 0, i64 %4)
1788 tail call void @llvm.riscv.vse.nxv4i32.i64(<vscale x 4 x i32> %232, ptr %233, i64 %4)
1789 %235 = getelementptr inbounds i32, ptr %1, i64 2688
1790 %236 = tail call <vscale x 4 x i32> @llvm.riscv.sf.vc.v.i.se.nxv4i32.i64.i64.i64(i64 2, i64 0, i64 0, i64 %4)
1791 tail call void @llvm.riscv.vse.nxv4i32.i64(<vscale x 4 x i32> %234, ptr %235, i64 %4)
1792 %237 = getelementptr inbounds i32, ptr %1, i64 2816
1793 %238 = tail call <vscale x 4 x i32> @llvm.riscv.sf.vc.v.i.se.nxv4i32.i64.i64.i64(i64 2, i64 0, i64 0, i64 %4)
1794 tail call void @llvm.riscv.vse.nxv4i32.i64(<vscale x 4 x i32> %236, ptr %237, i64 %4)
1795 %239 = getelementptr inbounds i32, ptr %1, i64 2944
1796 %240 = tail call <vscale x 4 x i32> @llvm.riscv.sf.vc.v.i.se.nxv4i32.i64.i64.i64(i64 2, i64 0, i64 0, i64 %4)
1797 tail call void @llvm.riscv.vse.nxv4i32.i64(<vscale x 4 x i32> %238, ptr %239, i64 %4)
1798 %241 = getelementptr inbounds i32, ptr %1, i64 3072
1799 %242 = tail call <vscale x 4 x i32> @llvm.riscv.sf.vc.v.i.se.nxv4i32.i64.i64.i64(i64 2, i64 0, i64 0, i64 %4)
1800 tail call void @llvm.riscv.vse.nxv4i32.i64(<vscale x 4 x i32> %240, ptr %241, i64 %4)
1801 %243 = getelementptr inbounds i32, ptr %1, i64 3200
1802 %244 = tail call <vscale x 4 x i32> @llvm.riscv.sf.vc.v.i.se.nxv4i32.i64.i64.i64(i64 2, i64 0, i64 0, i64 %4)
1803 tail call void @llvm.riscv.vse.nxv4i32.i64(<vscale x 4 x i32> %242, ptr %243, i64 %4)
1804 %245 = getelementptr inbounds i32, ptr %1, i64 3328
1805 %246 = tail call <vscale x 4 x i32> @llvm.riscv.sf.vc.v.i.se.nxv4i32.i64.i64.i64(i64 2, i64 0, i64 0, i64 %4)
1806 tail call void @llvm.riscv.vse.nxv4i32.i64(<vscale x 4 x i32> %244, ptr %245, i64 %4)
1807 %247 = getelementptr inbounds i32, ptr %1, i64 3456
1808 %248 = tail call <vscale x 4 x i32> @llvm.riscv.sf.vc.v.i.se.nxv4i32.i64.i64.i64(i64 2, i64 0, i64 0, i64 %4)
1809 tail call void @llvm.riscv.vse.nxv4i32.i64(<vscale x 4 x i32> %246, ptr %247, i64 %4)
1810 %249 = getelementptr inbounds i32, ptr %1, i64 3584
1811 %250 = tail call <vscale x 4 x i32> @llvm.riscv.sf.vc.v.i.se.nxv4i32.i64.i64.i64(i64 2, i64 0, i64 0, i64 %4)
1812 tail call void @llvm.riscv.vse.nxv4i32.i64(<vscale x 4 x i32> %248, ptr %249, i64 %4)
1813 %251 = getelementptr inbounds i32, ptr %1, i64 3712
1814 %252 = tail call <vscale x 4 x i32> @llvm.riscv.sf.vc.v.i.se.nxv4i32.i64.i64.i64(i64 2, i64 0, i64 0, i64 %4)
1815 tail call void @llvm.riscv.vse.nxv4i32.i64(<vscale x 4 x i32> %250, ptr %251, i64 %4)
1816 %253 = getelementptr inbounds i32, ptr %1, i64 3840
1817 %254 = tail call <vscale x 4 x i32> @llvm.riscv.sf.vc.v.i.se.nxv4i32.i64.i64.i64(i64 2, i64 0, i64 0, i64 %4)
1818 tail call void @llvm.riscv.vse.nxv4i32.i64(<vscale x 4 x i32> %252, ptr %253, i64 %4)
1819 %255 = getelementptr inbounds i32, ptr %1, i64 3968
1820 %256 = tail call <vscale x 4 x i32> @llvm.riscv.sf.vc.v.i.se.nxv4i32.i64.i64.i64(i64 2, i64 0, i64 0, i64 %4)
1821 tail call void @llvm.riscv.vse.nxv4i32.i64(<vscale x 4 x i32> %254, ptr %255, i64 %4)
1822 %257 = getelementptr inbounds i32, ptr %1, i64 4096
1823 %258 = tail call <vscale x 4 x i32> @llvm.riscv.sf.vc.v.i.se.nxv4i32.i64.i64.i64(i64 2, i64 0, i64 0, i64 %4)
1824 tail call void @llvm.riscv.vse.nxv4i32.i64(<vscale x 4 x i32> %256, ptr %257, i64 %4)
1825 %259 = getelementptr inbounds i32, ptr %1, i64 4224
1826 %260 = tail call <vscale x 4 x i32> @llvm.riscv.sf.vc.v.i.se.nxv4i32.i64.i64.i64(i64 2, i64 0, i64 0, i64 %4)
1827 tail call void @llvm.riscv.vse.nxv4i32.i64(<vscale x 4 x i32> %258, ptr %259, i64 %4)
1828 %261 = getelementptr inbounds i32, ptr %1, i64 4352
1829 %262 = tail call <vscale x 4 x i32> @llvm.riscv.sf.vc.v.i.se.nxv4i32.i64.i64.i64(i64 2, i64 0, i64 0, i64 %4)
1830 tail call void @llvm.riscv.vse.nxv4i32.i64(<vscale x 4 x i32> %260, ptr %261, i64 %4)
1831 %263 = getelementptr inbounds i32, ptr %1, i64 4480
1832 %264 = tail call <vscale x 4 x i32> @llvm.riscv.sf.vc.v.i.se.nxv4i32.i64.i64.i64(i64 2, i64 0, i64 0, i64 %4)
1833 tail call void @llvm.riscv.vse.nxv4i32.i64(<vscale x 4 x i32> %262, ptr %263, i64 %4)
1834 %265 = getelementptr inbounds i32, ptr %1, i64 4608
1835 %266 = tail call <vscale x 4 x i32> @llvm.riscv.sf.vc.v.i.se.nxv4i32.i64.i64.i64(i64 2, i64 0, i64 0, i64 %4)
1836 tail call void @llvm.riscv.vse.nxv4i32.i64(<vscale x 4 x i32> %264, ptr %265, i64 %4)
1837 %267 = getelementptr inbounds i32, ptr %1, i64 4736
1838 %268 = tail call <vscale x 4 x i32> @llvm.riscv.sf.vc.v.i.se.nxv4i32.i64.i64.i64(i64 2, i64 0, i64 0, i64 %4)
1839 tail call void @llvm.riscv.vse.nxv4i32.i64(<vscale x 4 x i32> %266, ptr %267, i64 %4)
1840 %269 = getelementptr inbounds i32, ptr %1, i64 4864
1841 %270 = tail call <vscale x 4 x i32> @llvm.riscv.sf.vc.v.i.se.nxv4i32.i64.i64.i64(i64 2, i64 0, i64 0, i64 %4)
1842 tail call void @llvm.riscv.vse.nxv4i32.i64(<vscale x 4 x i32> %268, ptr %269, i64 %4)
1843 %271 = getelementptr inbounds i32, ptr %1, i64 4992
1844 %272 = tail call <vscale x 4 x i32> @llvm.riscv.sf.vc.v.i.se.nxv4i32.i64.i64.i64(i64 2, i64 0, i64 0, i64 %4)
1845 tail call void @llvm.riscv.vse.nxv4i32.i64(<vscale x 4 x i32> %270, ptr %271, i64 %4)
1846 %273 = getelementptr inbounds i32, ptr %1, i64 5120
1847 %274 = tail call <vscale x 4 x i32> @llvm.riscv.sf.vc.v.i.se.nxv4i32.i64.i64.i64(i64 2, i64 0, i64 0, i64 %4)
1848 tail call void @llvm.riscv.vse.nxv4i32.i64(<vscale x 4 x i32> %272, ptr %273, i64 %4)
1849 %275 = getelementptr inbounds i32, ptr %1, i64 5248
1850 %276 = tail call <vscale x 4 x i32> @llvm.riscv.sf.vc.v.i.se.nxv4i32.i64.i64.i64(i64 2, i64 0, i64 0, i64 %4)
1851 tail call void @llvm.riscv.vse.nxv4i32.i64(<vscale x 4 x i32> %274, ptr %275, i64 %4)
1852 %277 = getelementptr inbounds i32, ptr %1, i64 5376
1853 %278 = tail call <vscale x 4 x i32> @llvm.riscv.sf.vc.v.i.se.nxv4i32.i64.i64.i64(i64 2, i64 0, i64 0, i64 %4)
1854 tail call void @llvm.riscv.vse.nxv4i32.i64(<vscale x 4 x i32> %276, ptr %277, i64 %4)
1855 %279 = getelementptr inbounds i32, ptr %1, i64 5504
1856 %280 = tail call <vscale x 4 x i32> @llvm.riscv.sf.vc.v.i.se.nxv4i32.i64.i64.i64(i64 2, i64 0, i64 0, i64 %4)
1857 tail call void @llvm.riscv.vse.nxv4i32.i64(<vscale x 4 x i32> %278, ptr %279, i64 %4)
1858 %281 = getelementptr inbounds i32, ptr %1, i64 5632
1859 %282 = tail call <vscale x 4 x i32> @llvm.riscv.sf.vc.v.i.se.nxv4i32.i64.i64.i64(i64 2, i64 0, i64 0, i64 %4)
1860 tail call void @llvm.riscv.vse.nxv4i32.i64(<vscale x 4 x i32> %280, ptr %281, i64 %4)
1861 %283 = getelementptr inbounds i32, ptr %1, i64 5760
1862 %284 = tail call <vscale x 4 x i32> @llvm.riscv.sf.vc.v.i.se.nxv4i32.i64.i64.i64(i64 2, i64 0, i64 0, i64 %4)
1863 tail call void @llvm.riscv.vse.nxv4i32.i64(<vscale x 4 x i32> %282, ptr %283, i64 %4)
1864 %285 = getelementptr inbounds i32, ptr %1, i64 5888
1865 %286 = tail call <vscale x 4 x i32> @llvm.riscv.sf.vc.v.i.se.nxv4i32.i64.i64.i64(i64 2, i64 0, i64 0, i64 %4)
1866 tail call void @llvm.riscv.vse.nxv4i32.i64(<vscale x 4 x i32> %284, ptr %285, i64 %4)
1867 %287 = getelementptr inbounds i32, ptr %1, i64 6016
1868 %288 = tail call <vscale x 4 x i32> @llvm.riscv.sf.vc.v.i.se.nxv4i32.i64.i64.i64(i64 2, i64 0, i64 0, i64 %4)
1869 tail call void @llvm.riscv.vse.nxv4i32.i64(<vscale x 4 x i32> %286, ptr %287, i64 %4)
1870 %289 = getelementptr inbounds i32, ptr %1, i64 6144
1871 %290 = tail call <vscale x 4 x i32> @llvm.riscv.sf.vc.v.i.se.nxv4i32.i64.i64.i64(i64 2, i64 0, i64 0, i64 %4)
1872 tail call void @llvm.riscv.vse.nxv4i32.i64(<vscale x 4 x i32> %288, ptr %289, i64 %4)
1873 %291 = getelementptr inbounds i32, ptr %1, i64 6272
1874 %292 = tail call <vscale x 4 x i32> @llvm.riscv.sf.vc.v.i.se.nxv4i32.i64.i64.i64(i64 2, i64 0, i64 0, i64 %4)
1875 tail call void @llvm.riscv.vse.nxv4i32.i64(<vscale x 4 x i32> %290, ptr %291, i64 %4)
1876 %293 = getelementptr inbounds i32, ptr %1, i64 6400
1877 %294 = tail call <vscale x 4 x i32> @llvm.riscv.sf.vc.v.i.se.nxv4i32.i64.i64.i64(i64 2, i64 0, i64 0, i64 %4)
1878 tail call void @llvm.riscv.vse.nxv4i32.i64(<vscale x 4 x i32> %292, ptr %293, i64 %4)
1879 %295 = getelementptr inbounds i32, ptr %1, i64 6528
1880 %296 = tail call <vscale x 4 x i32> @llvm.riscv.sf.vc.v.i.se.nxv4i32.i64.i64.i64(i64 2, i64 0, i64 0, i64 %4)
1881 tail call void @llvm.riscv.vse.nxv4i32.i64(<vscale x 4 x i32> %294, ptr %295, i64 %4)
1882 %297 = getelementptr inbounds i32, ptr %1, i64 6656
1883 %298 = tail call <vscale x 4 x i32> @llvm.riscv.sf.vc.v.i.se.nxv4i32.i64.i64.i64(i64 2, i64 0, i64 0, i64 %4)
1884 tail call void @llvm.riscv.vse.nxv4i32.i64(<vscale x 4 x i32> %296, ptr %297, i64 %4)
1885 %299 = getelementptr inbounds i32, ptr %1, i64 6784
1886 %300 = tail call <vscale x 4 x i32> @llvm.riscv.sf.vc.v.i.se.nxv4i32.i64.i64.i64(i64 2, i64 0, i64 0, i64 %4)
1887 tail call void @llvm.riscv.vse.nxv4i32.i64(<vscale x 4 x i32> %298, ptr %299, i64 %4)
1888 %301 = getelementptr inbounds i32, ptr %1, i64 6912
1889 %302 = tail call <vscale x 4 x i32> @llvm.riscv.sf.vc.v.i.se.nxv4i32.i64.i64.i64(i64 2, i64 0, i64 0, i64 %4)
1890 tail call void @llvm.riscv.vse.nxv4i32.i64(<vscale x 4 x i32> %300, ptr %301, i64 %4)
1891 %303 = getelementptr inbounds i32, ptr %1, i64 7040
1892 %304 = tail call <vscale x 4 x i32> @llvm.riscv.sf.vc.v.i.se.nxv4i32.i64.i64.i64(i64 2, i64 0, i64 0, i64 %4)
1893 tail call void @llvm.riscv.vse.nxv4i32.i64(<vscale x 4 x i32> %302, ptr %303, i64 %4)
1894 %305 = getelementptr inbounds i32, ptr %1, i64 7168
1895 %306 = tail call <vscale x 4 x i32> @llvm.riscv.sf.vc.v.i.se.nxv4i32.i64.i64.i64(i64 2, i64 0, i64 0, i64 %4)
1896 tail call void @llvm.riscv.vse.nxv4i32.i64(<vscale x 4 x i32> %304, ptr %305, i64 %4)
1897 %307 = getelementptr inbounds i32, ptr %1, i64 7296
1898 %308 = tail call <vscale x 4 x i32> @llvm.riscv.sf.vc.v.i.se.nxv4i32.i64.i64.i64(i64 2, i64 0, i64 0, i64 %4)
1899 tail call void @llvm.riscv.vse.nxv4i32.i64(<vscale x 4 x i32> %306, ptr %307, i64 %4)
1900 %309 = getelementptr inbounds i32, ptr %1, i64 7424
1901 %310 = tail call <vscale x 4 x i32> @llvm.riscv.sf.vc.v.i.se.nxv4i32.i64.i64.i64(i64 2, i64 0, i64 0, i64 %4)
1902 tail call void @llvm.riscv.vse.nxv4i32.i64(<vscale x 4 x i32> %308, ptr %309, i64 %4)
1903 %311 = getelementptr inbounds i32, ptr %1, i64 7552
1904 %312 = tail call <vscale x 4 x i32> @llvm.riscv.sf.vc.v.i.se.nxv4i32.i64.i64.i64(i64 2, i64 0, i64 0, i64 %4)
1905 tail call void @llvm.riscv.vse.nxv4i32.i64(<vscale x 4 x i32> %310, ptr %311, i64 %4)
1906 %313 = getelementptr inbounds i32, ptr %1, i64 7680
1907 %314 = tail call <vscale x 4 x i32> @llvm.riscv.sf.vc.v.i.se.nxv4i32.i64.i64.i64(i64 2, i64 0, i64 0, i64 %4)
1908 tail call void @llvm.riscv.vse.nxv4i32.i64(<vscale x 4 x i32> %312, ptr %313, i64 %4)
1909 %315 = getelementptr inbounds i32, ptr %1, i64 7808
1910 %316 = tail call <vscale x 4 x i32> @llvm.riscv.sf.vc.v.i.se.nxv4i32.i64.i64.i64(i64 2, i64 0, i64 0, i64 %4)
1911 tail call void @llvm.riscv.vse.nxv4i32.i64(<vscale x 4 x i32> %314, ptr %315, i64 %4)
1912 %317 = getelementptr inbounds i32, ptr %1, i64 7936
1913 %318 = tail call <vscale x 4 x i32> @llvm.riscv.sf.vc.v.i.se.nxv4i32.i64.i64.i64(i64 2, i64 0, i64 0, i64 %4)
1914 tail call void @llvm.riscv.vse.nxv4i32.i64(<vscale x 4 x i32> %316, ptr %317, i64 %4)
1915 %319 = getelementptr inbounds i32, ptr %1, i64 8064
1916 %320 = tail call <vscale x 4 x i32> @llvm.riscv.sf.vc.v.i.se.nxv4i32.i64.i64.i64(i64 2, i64 0, i64 0, i64 %4)
1917 tail call void @llvm.riscv.vse.nxv4i32.i64(<vscale x 4 x i32> %318, ptr %319, i64 %4)
1918 %321 = getelementptr inbounds i32, ptr %1, i64 8192
1919 %322 = tail call <vscale x 4 x i32> @llvm.riscv.sf.vc.v.i.se.nxv4i32.i64.i64.i64(i64 2, i64 0, i64 0, i64 %4)
1920 tail call void @llvm.riscv.vse.nxv4i32.i64(<vscale x 4 x i32> %320, ptr %321, i64 %4)
1921 %323 = getelementptr inbounds i32, ptr %1, i64 8320
1922 %324 = tail call <vscale x 4 x i32> @llvm.riscv.sf.vc.v.i.se.nxv4i32.i64.i64.i64(i64 2, i64 0, i64 0, i64 %4)
1923 tail call void @llvm.riscv.vse.nxv4i32.i64(<vscale x 4 x i32> %322, ptr %323, i64 %4)
1924 %325 = getelementptr inbounds i32, ptr %1, i64 8448
1925 %326 = tail call <vscale x 4 x i32> @llvm.riscv.sf.vc.v.i.se.nxv4i32.i64.i64.i64(i64 2, i64 0, i64 0, i64 %4)
1926 tail call void @llvm.riscv.vse.nxv4i32.i64(<vscale x 4 x i32> %324, ptr %325, i64 %4)
1927 %327 = getelementptr inbounds i32, ptr %1, i64 8576
1928 %328 = tail call <vscale x 4 x i32> @llvm.riscv.sf.vc.v.i.se.nxv4i32.i64.i64.i64(i64 2, i64 0, i64 0, i64 %4)
1929 tail call void @llvm.riscv.vse.nxv4i32.i64(<vscale x 4 x i32> %326, ptr %327, i64 %4)
1930 %329 = getelementptr inbounds i32, ptr %1, i64 8704
1931 %330 = tail call <vscale x 4 x i32> @llvm.riscv.sf.vc.v.i.se.nxv4i32.i64.i64.i64(i64 2, i64 0, i64 0, i64 %4)
1932 tail call void @llvm.riscv.vse.nxv4i32.i64(<vscale x 4 x i32> %328, ptr %329, i64 %4)
1933 %331 = getelementptr inbounds i32, ptr %1, i64 8832
1934 %332 = tail call <vscale x 4 x i32> @llvm.riscv.sf.vc.v.i.se.nxv4i32.i64.i64.i64(i64 2, i64 0, i64 0, i64 %4)
1935 tail call void @llvm.riscv.vse.nxv4i32.i64(<vscale x 4 x i32> %330, ptr %331, i64 %4)
1936 %333 = getelementptr inbounds i32, ptr %1, i64 8960
1937 %334 = tail call <vscale x 4 x i32> @llvm.riscv.sf.vc.v.i.se.nxv4i32.i64.i64.i64(i64 2, i64 0, i64 0, i64 %4)
1938 tail call void @llvm.riscv.vse.nxv4i32.i64(<vscale x 4 x i32> %332, ptr %333, i64 %4)
1939 %335 = getelementptr inbounds i32, ptr %1, i64 9088
1940 %336 = tail call <vscale x 4 x i32> @llvm.riscv.sf.vc.v.i.se.nxv4i32.i64.i64.i64(i64 2, i64 0, i64 0, i64 %4)
1941 tail call void @llvm.riscv.vse.nxv4i32.i64(<vscale x 4 x i32> %334, ptr %335, i64 %4)
1942 %337 = getelementptr inbounds i32, ptr %1, i64 9216
1943 %338 = tail call <vscale x 4 x i32> @llvm.riscv.sf.vc.v.i.se.nxv4i32.i64.i64.i64(i64 2, i64 0, i64 0, i64 %4)
1944 tail call void @llvm.riscv.vse.nxv4i32.i64(<vscale x 4 x i32> %336, ptr %337, i64 %4)
1945 %339 = getelementptr inbounds i32, ptr %1, i64 9344
1946 %340 = tail call <vscale x 4 x i32> @llvm.riscv.sf.vc.v.i.se.nxv4i32.i64.i64.i64(i64 2, i64 0, i64 0, i64 %4)
1947 tail call void @llvm.riscv.vse.nxv4i32.i64(<vscale x 4 x i32> %338, ptr %339, i64 %4)
1948 %341 = getelementptr inbounds i32, ptr %1, i64 9472
1949 %342 = tail call <vscale x 4 x i32> @llvm.riscv.sf.vc.v.i.se.nxv4i32.i64.i64.i64(i64 2, i64 0, i64 0, i64 %4)
1950 tail call void @llvm.riscv.vse.nxv4i32.i64(<vscale x 4 x i32> %340, ptr %341, i64 %4)
1951 %343 = getelementptr inbounds i32, ptr %1, i64 9600
1952 %344 = tail call <vscale x 4 x i32> @llvm.riscv.sf.vc.v.i.se.nxv4i32.i64.i64.i64(i64 2, i64 0, i64 0, i64 %4)
1953 tail call void @llvm.riscv.vse.nxv4i32.i64(<vscale x 4 x i32> %342, ptr %343, i64 %4)
1954 %345 = getelementptr inbounds i32, ptr %1, i64 9728
1955 %346 = tail call <vscale x 4 x i32> @llvm.riscv.sf.vc.v.i.se.nxv4i32.i64.i64.i64(i64 2, i64 0, i64 0, i64 %4)
1956 tail call void @llvm.riscv.vse.nxv4i32.i64(<vscale x 4 x i32> %344, ptr %345, i64 %4)
1957 %347 = getelementptr inbounds i32, ptr %1, i64 9856
1958 %348 = tail call <vscale x 4 x i32> @llvm.riscv.sf.vc.v.i.se.nxv4i32.i64.i64.i64(i64 2, i64 0, i64 0, i64 %4)
1959 tail call void @llvm.riscv.vse.nxv4i32.i64(<vscale x 4 x i32> %346, ptr %347, i64 %4)
1960 %349 = getelementptr inbounds i32, ptr %1, i64 9984
1961 %350 = tail call <vscale x 4 x i32> @llvm.riscv.sf.vc.v.i.se.nxv4i32.i64.i64.i64(i64 2, i64 0, i64 0, i64 %4)
1962 tail call void @llvm.riscv.vse.nxv4i32.i64(<vscale x 4 x i32> %348, ptr %349, i64 %4)
1963 %351 = getelementptr inbounds i32, ptr %1, i64 10112
1964 %352 = tail call <vscale x 4 x i32> @llvm.riscv.sf.vc.v.i.se.nxv4i32.i64.i64.i64(i64 2, i64 0, i64 0, i64 %4)
1965 tail call void @llvm.riscv.vse.nxv4i32.i64(<vscale x 4 x i32> %350, ptr %351, i64 %4)
1966 %353 = getelementptr inbounds i32, ptr %1, i64 10240
1967 %354 = tail call <vscale x 4 x i32> @llvm.riscv.sf.vc.v.i.se.nxv4i32.i64.i64.i64(i64 2, i64 0, i64 0, i64 %4)
1968 tail call void @llvm.riscv.vse.nxv4i32.i64(<vscale x 4 x i32> %352, ptr %353, i64 %4)
1969 %355 = getelementptr inbounds i32, ptr %1, i64 10368
1970 %356 = tail call <vscale x 4 x i32> @llvm.riscv.sf.vc.v.i.se.nxv4i32.i64.i64.i64(i64 2, i64 0, i64 0, i64 %4)
1971 tail call void @llvm.riscv.vse.nxv4i32.i64(<vscale x 4 x i32> %354, ptr %355, i64 %4)
1972 %357 = tail call <vscale x 4 x i32> @llvm.riscv.sf.vc.v.i.se.nxv4i32.i64.i64.i64(i64 2, i64 0, i64 0, i64 %4)
1976 declare i64 @llvm.riscv.vsetvli.i64(i64, i64, i64)
1977 declare <vscale x 4 x i32> @llvm.riscv.vle.nxv4i32.i64(<vscale x 4 x i32>, ptr, i64)
1978 declare void @llvm.riscv.sf.vc.vv.se.i64.nxv4i32.nxv4i32.i64(i64, i64, <vscale x 4 x i32>, <vscale x 4 x i32>, i64)
1979 declare <vscale x 4 x i32> @llvm.riscv.sf.vc.v.i.se.nxv4i32.i64.i64.i64(i64, i64, i64, i64)
1980 declare void @llvm.riscv.vse.nxv4i32.i64(<vscale x 4 x i32>, ptr, i64)