1 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
2 ; RUN: llc -mtriple=riscv32 -mattr=+m,+d,+zfh,+v,+zvfh \
3 ; RUN: -verify-machineinstrs < %s \
4 ; RUN: | FileCheck %s --check-prefixes=CHECK,CHECK-RV32
5 ; RUN: llc -mtriple=riscv64 -mattr=+m,+d,+zfh,+v,+zvfh \
6 ; RUN: -verify-machineinstrs < %s \
7 ; RUN: | FileCheck %s --check-prefixes=CHECK,CHECK-RV64
9 declare void @llvm.experimental.vp.strided.store.v2i8.p0.i8(<2 x i8>, ptr, i8, <2 x i1>, i32)
11 define void @strided_vpstore_v2i8_i8(<2 x i8> %val, ptr %ptr, i8 signext %stride, <2 x i1> %m, i32 zeroext %evl) {
12 ; CHECK-LABEL: strided_vpstore_v2i8_i8:
14 ; CHECK-NEXT: vsetvli zero, a2, e8, mf8, ta, ma
15 ; CHECK-NEXT: vsse8.v v8, (a0), a1, v0.t
17 call void @llvm.experimental.vp.strided.store.v2i8.p0.i8(<2 x i8> %val, ptr %ptr, i8 %stride, <2 x i1> %m, i32 %evl)
21 declare void @llvm.experimental.vp.strided.store.v2i8.p0.i16(<2 x i8>, ptr, i16, <2 x i1>, i32)
23 define void @strided_vpstore_v2i8_i16(<2 x i8> %val, ptr %ptr, i16 signext %stride, <2 x i1> %m, i32 zeroext %evl) {
24 ; CHECK-LABEL: strided_vpstore_v2i8_i16:
26 ; CHECK-NEXT: vsetvli zero, a2, e8, mf8, ta, ma
27 ; CHECK-NEXT: vsse8.v v8, (a0), a1, v0.t
29 call void @llvm.experimental.vp.strided.store.v2i8.p0.i16(<2 x i8> %val, ptr %ptr, i16 %stride, <2 x i1> %m, i32 %evl)
33 declare void @llvm.experimental.vp.strided.store.v2i8.p0.i64(<2 x i8>, ptr, i64, <2 x i1>, i32)
35 define void @strided_vpstore_v2i8_i64(<2 x i8> %val, ptr %ptr, i64 signext %stride, <2 x i1> %m, i32 zeroext %evl) {
36 ; CHECK-RV32-LABEL: strided_vpstore_v2i8_i64:
37 ; CHECK-RV32: # %bb.0:
38 ; CHECK-RV32-NEXT: vsetvli zero, a3, e8, mf8, ta, ma
39 ; CHECK-RV32-NEXT: vsse8.v v8, (a0), a1, v0.t
40 ; CHECK-RV32-NEXT: ret
42 ; CHECK-RV64-LABEL: strided_vpstore_v2i8_i64:
43 ; CHECK-RV64: # %bb.0:
44 ; CHECK-RV64-NEXT: vsetvli zero, a2, e8, mf8, ta, ma
45 ; CHECK-RV64-NEXT: vsse8.v v8, (a0), a1, v0.t
46 ; CHECK-RV64-NEXT: ret
47 call void @llvm.experimental.vp.strided.store.v2i8.p0.i64(<2 x i8> %val, ptr %ptr, i64 %stride, <2 x i1> %m, i32 %evl)
51 declare void @llvm.experimental.vp.strided.store.v2i8.p0.i32(<2 x i8>, ptr, i32, <2 x i1>, i32)
53 define void @strided_vpstore_v2i8(<2 x i8> %val, ptr %ptr, i32 signext %stride, <2 x i1> %m, i32 zeroext %evl) {
54 ; CHECK-LABEL: strided_vpstore_v2i8:
56 ; CHECK-NEXT: vsetvli zero, a2, e8, mf8, ta, ma
57 ; CHECK-NEXT: vsse8.v v8, (a0), a1, v0.t
59 call void @llvm.experimental.vp.strided.store.v2i8.p0.i32(<2 x i8> %val, ptr %ptr, i32 %stride, <2 x i1> %m, i32 %evl)
63 declare void @llvm.experimental.vp.strided.store.v4i8.p0.i32(<4 x i8>, ptr, i32, <4 x i1>, i32)
65 define void @strided_vpstore_v4i8(<4 x i8> %val, ptr %ptr, i32 signext %stride, <4 x i1> %m, i32 zeroext %evl) {
66 ; CHECK-LABEL: strided_vpstore_v4i8:
68 ; CHECK-NEXT: vsetvli zero, a2, e8, mf4, ta, ma
69 ; CHECK-NEXT: vsse8.v v8, (a0), a1, v0.t
71 call void @llvm.experimental.vp.strided.store.v4i8.p0.i32(<4 x i8> %val, ptr %ptr, i32 %stride, <4 x i1> %m, i32 %evl)
75 declare void @llvm.experimental.vp.strided.store.v8i8.p0.i32(<8 x i8>, ptr, i32, <8 x i1>, i32)
77 define void @strided_vpstore_v8i8(<8 x i8> %val, ptr %ptr, i32 signext %stride, <8 x i1> %m, i32 zeroext %evl) {
78 ; CHECK-LABEL: strided_vpstore_v8i8:
80 ; CHECK-NEXT: vsetvli zero, a2, e8, mf2, ta, ma
81 ; CHECK-NEXT: vsse8.v v8, (a0), a1, v0.t
83 call void @llvm.experimental.vp.strided.store.v8i8.p0.i32(<8 x i8> %val, ptr %ptr, i32 %stride, <8 x i1> %m, i32 %evl)
87 define void @strided_vpstore_v8i8_unit_stride(<8 x i8> %val, ptr %ptr, <8 x i1> %m, i32 zeroext %evl) {
88 ; CHECK-LABEL: strided_vpstore_v8i8_unit_stride:
90 ; CHECK-NEXT: vsetvli zero, a1, e8, mf2, ta, ma
91 ; CHECK-NEXT: vse8.v v8, (a0), v0.t
93 call void @llvm.experimental.vp.strided.store.v8i8.p0.i32(<8 x i8> %val, ptr %ptr, i32 1, <8 x i1> %m, i32 %evl)
97 declare void @llvm.experimental.vp.strided.store.v2i16.p0.i32(<2 x i16>, ptr, i32, <2 x i1>, i32)
99 define void @strided_vpstore_v2i16(<2 x i16> %val, ptr %ptr, i32 signext %stride, <2 x i1> %m, i32 zeroext %evl) {
100 ; CHECK-LABEL: strided_vpstore_v2i16:
102 ; CHECK-NEXT: vsetvli zero, a2, e16, mf4, ta, ma
103 ; CHECK-NEXT: vsse16.v v8, (a0), a1, v0.t
105 call void @llvm.experimental.vp.strided.store.v2i16.p0.i32(<2 x i16> %val, ptr %ptr, i32 %stride, <2 x i1> %m, i32 %evl)
109 declare void @llvm.experimental.vp.strided.store.v4i16.p0.i32(<4 x i16>, ptr, i32, <4 x i1>, i32)
111 define void @strided_vpstore_v4i16(<4 x i16> %val, ptr %ptr, i32 signext %stride, <4 x i1> %m, i32 zeroext %evl) {
112 ; CHECK-LABEL: strided_vpstore_v4i16:
114 ; CHECK-NEXT: vsetvli zero, a2, e16, mf2, ta, ma
115 ; CHECK-NEXT: vsse16.v v8, (a0), a1, v0.t
117 call void @llvm.experimental.vp.strided.store.v4i16.p0.i32(<4 x i16> %val, ptr %ptr, i32 %stride, <4 x i1> %m, i32 %evl)
121 declare void @llvm.experimental.vp.strided.store.v8i16.p0.i32(<8 x i16>, ptr, i32, <8 x i1>, i32)
123 define void @strided_vpstore_v8i16(<8 x i16> %val, ptr %ptr, i32 signext %stride, <8 x i1> %m, i32 zeroext %evl) {
124 ; CHECK-LABEL: strided_vpstore_v8i16:
126 ; CHECK-NEXT: vsetvli zero, a2, e16, m1, ta, ma
127 ; CHECK-NEXT: vsse16.v v8, (a0), a1, v0.t
129 call void @llvm.experimental.vp.strided.store.v8i16.p0.i32(<8 x i16> %val, ptr %ptr, i32 %stride, <8 x i1> %m, i32 %evl)
133 define void @strided_vpstore_v8i16_unit_stride(<8 x i16> %val, ptr %ptr, <8 x i1> %m, i32 zeroext %evl) {
134 ; CHECK-LABEL: strided_vpstore_v8i16_unit_stride:
136 ; CHECK-NEXT: vsetvli zero, a1, e16, m1, ta, ma
137 ; CHECK-NEXT: vse16.v v8, (a0), v0.t
139 call void @llvm.experimental.vp.strided.store.v8i16.p0.i32(<8 x i16> %val, ptr %ptr, i32 2, <8 x i1> %m, i32 %evl)
143 declare void @llvm.experimental.vp.strided.store.v2i32.p0.i32(<2 x i32>, ptr, i32, <2 x i1>, i32)
145 define void @strided_vpstore_v2i32(<2 x i32> %val, ptr %ptr, i32 signext %stride, <2 x i1> %m, i32 zeroext %evl) {
146 ; CHECK-LABEL: strided_vpstore_v2i32:
148 ; CHECK-NEXT: vsetvli zero, a2, e32, mf2, ta, ma
149 ; CHECK-NEXT: vsse32.v v8, (a0), a1, v0.t
151 call void @llvm.experimental.vp.strided.store.v2i32.p0.i32(<2 x i32> %val, ptr %ptr, i32 %stride, <2 x i1> %m, i32 %evl)
155 declare void @llvm.experimental.vp.strided.store.v4i32.p0.i32(<4 x i32>, ptr, i32, <4 x i1>, i32)
157 define void @strided_vpstore_v4i32(<4 x i32> %val, ptr %ptr, i32 signext %stride, <4 x i1> %m, i32 zeroext %evl) {
158 ; CHECK-LABEL: strided_vpstore_v4i32:
160 ; CHECK-NEXT: vsetvli zero, a2, e32, m1, ta, ma
161 ; CHECK-NEXT: vsse32.v v8, (a0), a1, v0.t
163 call void @llvm.experimental.vp.strided.store.v4i32.p0.i32(<4 x i32> %val, ptr %ptr, i32 %stride, <4 x i1> %m, i32 %evl)
167 define void @strided_vpstore_v4i32_unit_stride(<4 x i32> %val, ptr %ptr, <4 x i1> %m, i32 zeroext %evl) {
168 ; CHECK-LABEL: strided_vpstore_v4i32_unit_stride:
170 ; CHECK-NEXT: vsetvli zero, a1, e32, m1, ta, ma
171 ; CHECK-NEXT: vse32.v v8, (a0), v0.t
173 call void @llvm.experimental.vp.strided.store.v4i32.p0.i32(<4 x i32> %val, ptr %ptr, i32 4, <4 x i1> %m, i32 %evl)
177 declare void @llvm.experimental.vp.strided.store.v8i32.p0.i32(<8 x i32>, ptr, i32, <8 x i1>, i32)
179 define void @strided_vpstore_v8i32(<8 x i32> %val, ptr %ptr, i32 signext %stride, <8 x i1> %m, i32 zeroext %evl) {
180 ; CHECK-LABEL: strided_vpstore_v8i32:
182 ; CHECK-NEXT: vsetvli zero, a2, e32, m2, ta, ma
183 ; CHECK-NEXT: vsse32.v v8, (a0), a1, v0.t
185 call void @llvm.experimental.vp.strided.store.v8i32.p0.i32(<8 x i32> %val, ptr %ptr, i32 %stride, <8 x i1> %m, i32 %evl)
189 declare void @llvm.experimental.vp.strided.store.v2i64.p0.i32(<2 x i64>, ptr, i32, <2 x i1>, i32)
191 define void @strided_vpstore_v2i64(<2 x i64> %val, ptr %ptr, i32 signext %stride, <2 x i1> %m, i32 zeroext %evl) {
192 ; CHECK-LABEL: strided_vpstore_v2i64:
194 ; CHECK-NEXT: vsetvli zero, a2, e64, m1, ta, ma
195 ; CHECK-NEXT: vsse64.v v8, (a0), a1, v0.t
197 call void @llvm.experimental.vp.strided.store.v2i64.p0.i32(<2 x i64> %val, ptr %ptr, i32 %stride, <2 x i1> %m, i32 %evl)
201 define void @strided_vpstore_v2i64_unit_stride(<2 x i64> %val, ptr %ptr, <2 x i1> %m, i32 zeroext %evl) {
202 ; CHECK-LABEL: strided_vpstore_v2i64_unit_stride:
204 ; CHECK-NEXT: vsetvli zero, a1, e64, m1, ta, ma
205 ; CHECK-NEXT: vse64.v v8, (a0), v0.t
207 call void @llvm.experimental.vp.strided.store.v2i64.p0.i32(<2 x i64> %val, ptr %ptr, i32 8, <2 x i1> %m, i32 %evl)
211 declare void @llvm.experimental.vp.strided.store.v4i64.p0.i32(<4 x i64>, ptr, i32, <4 x i1>, i32)
213 define void @strided_vpstore_v4i64(<4 x i64> %val, ptr %ptr, i32 signext %stride, <4 x i1> %m, i32 zeroext %evl) {
214 ; CHECK-LABEL: strided_vpstore_v4i64:
216 ; CHECK-NEXT: vsetvli zero, a2, e64, m2, ta, ma
217 ; CHECK-NEXT: vsse64.v v8, (a0), a1, v0.t
219 call void @llvm.experimental.vp.strided.store.v4i64.p0.i32(<4 x i64> %val, ptr %ptr, i32 %stride, <4 x i1> %m, i32 %evl)
223 declare void @llvm.experimental.vp.strided.store.v8i64.p0.i32(<8 x i64>, ptr, i32, <8 x i1>, i32)
225 define void @strided_vpstore_v8i64(<8 x i64> %val, ptr %ptr, i32 signext %stride, <8 x i1> %m, i32 zeroext %evl) {
226 ; CHECK-LABEL: strided_vpstore_v8i64:
228 ; CHECK-NEXT: vsetvli zero, a2, e64, m4, ta, ma
229 ; CHECK-NEXT: vsse64.v v8, (a0), a1, v0.t
231 call void @llvm.experimental.vp.strided.store.v8i64.p0.i32(<8 x i64> %val, ptr %ptr, i32 %stride, <8 x i1> %m, i32 %evl)
235 declare void @llvm.experimental.vp.strided.store.v2f16.p0.i32(<2 x half>, ptr, i32, <2 x i1>, i32)
237 define void @strided_vpstore_v2f16(<2 x half> %val, ptr %ptr, i32 signext %stride, <2 x i1> %m, i32 zeroext %evl) {
238 ; CHECK-LABEL: strided_vpstore_v2f16:
240 ; CHECK-NEXT: vsetvli zero, a2, e16, mf4, ta, ma
241 ; CHECK-NEXT: vsse16.v v8, (a0), a1, v0.t
243 call void @llvm.experimental.vp.strided.store.v2f16.p0.i32(<2 x half> %val, ptr %ptr, i32 %stride, <2 x i1> %m, i32 %evl)
247 declare void @llvm.experimental.vp.strided.store.v4f16.p0.i32(<4 x half>, ptr, i32, <4 x i1>, i32)
249 define void @strided_vpstore_v4f16(<4 x half> %val, ptr %ptr, i32 signext %stride, <4 x i1> %m, i32 zeroext %evl) {
250 ; CHECK-LABEL: strided_vpstore_v4f16:
252 ; CHECK-NEXT: vsetvli zero, a2, e16, mf2, ta, ma
253 ; CHECK-NEXT: vsse16.v v8, (a0), a1, v0.t
255 call void @llvm.experimental.vp.strided.store.v4f16.p0.i32(<4 x half> %val, ptr %ptr, i32 %stride, <4 x i1> %m, i32 %evl)
259 declare void @llvm.experimental.vp.strided.store.v8f16.p0.i32(<8 x half>, ptr, i32, <8 x i1>, i32)
261 define void @strided_vpstore_v8f16(<8 x half> %val, ptr %ptr, i32 signext %stride, <8 x i1> %m, i32 zeroext %evl) {
262 ; CHECK-LABEL: strided_vpstore_v8f16:
264 ; CHECK-NEXT: vsetvli zero, a2, e16, m1, ta, ma
265 ; CHECK-NEXT: vsse16.v v8, (a0), a1, v0.t
267 call void @llvm.experimental.vp.strided.store.v8f16.p0.i32(<8 x half> %val, ptr %ptr, i32 %stride, <8 x i1> %m, i32 %evl)
271 define void @strided_vpstore_v8f16_unit_stride(<8 x half> %val, ptr %ptr, <8 x i1> %m, i32 zeroext %evl) {
272 ; CHECK-LABEL: strided_vpstore_v8f16_unit_stride:
274 ; CHECK-NEXT: vsetvli zero, a1, e16, m1, ta, ma
275 ; CHECK-NEXT: vse16.v v8, (a0), v0.t
277 call void @llvm.experimental.vp.strided.store.v8f16.p0.i32(<8 x half> %val, ptr %ptr, i32 2, <8 x i1> %m, i32 %evl)
281 declare void @llvm.experimental.vp.strided.store.v2f32.p0.i32(<2 x float>, ptr, i32, <2 x i1>, i32)
283 define void @strided_vpstore_v2f32(<2 x float> %val, ptr %ptr, i32 signext %stride, <2 x i1> %m, i32 zeroext %evl) {
284 ; CHECK-LABEL: strided_vpstore_v2f32:
286 ; CHECK-NEXT: vsetvli zero, a2, e32, mf2, ta, ma
287 ; CHECK-NEXT: vsse32.v v8, (a0), a1, v0.t
289 call void @llvm.experimental.vp.strided.store.v2f32.p0.i32(<2 x float> %val, ptr %ptr, i32 %stride, <2 x i1> %m, i32 %evl)
293 declare void @llvm.experimental.vp.strided.store.v4f32.p0.i32(<4 x float>, ptr, i32, <4 x i1>, i32)
295 define void @strided_vpstore_v4f32(<4 x float> %val, ptr %ptr, i32 signext %stride, <4 x i1> %m, i32 zeroext %evl) {
296 ; CHECK-LABEL: strided_vpstore_v4f32:
298 ; CHECK-NEXT: vsetvli zero, a2, e32, m1, ta, ma
299 ; CHECK-NEXT: vsse32.v v8, (a0), a1, v0.t
301 call void @llvm.experimental.vp.strided.store.v4f32.p0.i32(<4 x float> %val, ptr %ptr, i32 %stride, <4 x i1> %m, i32 %evl)
305 define void @strided_vpstore_v4f32_unit_stride(<4 x float> %val, ptr %ptr, <4 x i1> %m, i32 zeroext %evl) {
306 ; CHECK-LABEL: strided_vpstore_v4f32_unit_stride:
308 ; CHECK-NEXT: vsetvli zero, a1, e32, m1, ta, ma
309 ; CHECK-NEXT: vse32.v v8, (a0), v0.t
311 call void @llvm.experimental.vp.strided.store.v4f32.p0.i32(<4 x float> %val, ptr %ptr, i32 4, <4 x i1> %m, i32 %evl)
315 declare void @llvm.experimental.vp.strided.store.v8f32.p0.i32(<8 x float>, ptr, i32, <8 x i1>, i32)
317 define void @strided_vpstore_v8f32(<8 x float> %val, ptr %ptr, i32 signext %stride, <8 x i1> %m, i32 zeroext %evl) {
318 ; CHECK-LABEL: strided_vpstore_v8f32:
320 ; CHECK-NEXT: vsetvli zero, a2, e32, m2, ta, ma
321 ; CHECK-NEXT: vsse32.v v8, (a0), a1, v0.t
323 call void @llvm.experimental.vp.strided.store.v8f32.p0.i32(<8 x float> %val, ptr %ptr, i32 %stride, <8 x i1> %m, i32 %evl)
327 declare void @llvm.experimental.vp.strided.store.v2f64.p0.i32(<2 x double>, ptr, i32, <2 x i1>, i32)
329 define void @strided_vpstore_v2f64(<2 x double> %val, ptr %ptr, i32 signext %stride, <2 x i1> %m, i32 zeroext %evl) {
330 ; CHECK-LABEL: strided_vpstore_v2f64:
332 ; CHECK-NEXT: vsetvli zero, a2, e64, m1, ta, ma
333 ; CHECK-NEXT: vsse64.v v8, (a0), a1, v0.t
335 call void @llvm.experimental.vp.strided.store.v2f64.p0.i32(<2 x double> %val, ptr %ptr, i32 %stride, <2 x i1> %m, i32 %evl)
339 define void @strided_vpstore_v2f64_unit_stride(<2 x double> %val, ptr %ptr, <2 x i1> %m, i32 zeroext %evl) {
340 ; CHECK-LABEL: strided_vpstore_v2f64_unit_stride:
342 ; CHECK-NEXT: vsetvli zero, a1, e64, m1, ta, ma
343 ; CHECK-NEXT: vse64.v v8, (a0), v0.t
345 call void @llvm.experimental.vp.strided.store.v2f64.p0.i32(<2 x double> %val, ptr %ptr, i32 8, <2 x i1> %m, i32 %evl)
349 declare void @llvm.experimental.vp.strided.store.v4f64.p0.i32(<4 x double>, ptr, i32, <4 x i1>, i32)
351 define void @strided_vpstore_v4f64(<4 x double> %val, ptr %ptr, i32 signext %stride, <4 x i1> %m, i32 zeroext %evl) {
352 ; CHECK-LABEL: strided_vpstore_v4f64:
354 ; CHECK-NEXT: vsetvli zero, a2, e64, m2, ta, ma
355 ; CHECK-NEXT: vsse64.v v8, (a0), a1, v0.t
357 call void @llvm.experimental.vp.strided.store.v4f64.p0.i32(<4 x double> %val, ptr %ptr, i32 %stride, <4 x i1> %m, i32 %evl)
361 declare void @llvm.experimental.vp.strided.store.v8f64.p0.i32(<8 x double>, ptr, i32, <8 x i1>, i32)
363 define void @strided_vpstore_v8f64(<8 x double> %val, ptr %ptr, i32 signext %stride, <8 x i1> %m, i32 zeroext %evl) {
364 ; CHECK-LABEL: strided_vpstore_v8f64:
366 ; CHECK-NEXT: vsetvli zero, a2, e64, m4, ta, ma
367 ; CHECK-NEXT: vsse64.v v8, (a0), a1, v0.t
369 call void @llvm.experimental.vp.strided.store.v8f64.p0.i32(<8 x double> %val, ptr %ptr, i32 %stride, <8 x i1> %m, i32 %evl)
373 define void @strided_vpstore_v2i8_allones_mask(<2 x i8> %val, ptr %ptr, i32 signext %stride, i32 zeroext %evl) {
374 ; CHECK-LABEL: strided_vpstore_v2i8_allones_mask:
376 ; CHECK-NEXT: vsetvli zero, a2, e8, mf8, ta, ma
377 ; CHECK-NEXT: vsse8.v v8, (a0), a1
379 call void @llvm.experimental.vp.strided.store.v2i8.p0.i32(<2 x i8> %val, ptr %ptr, i32 %stride, <2 x i1> splat (i1 true), i32 %evl)
384 define void @strided_vpstore_v3f32(<3 x float> %v, ptr %ptr, i32 signext %stride, <3 x i1> %mask, i32 zeroext %evl) {
385 ; CHECK-LABEL: strided_vpstore_v3f32:
387 ; CHECK-NEXT: vsetvli zero, a2, e32, m1, ta, ma
388 ; CHECK-NEXT: vsse32.v v8, (a0), a1, v0.t
390 call void @llvm.experimental.vp.strided.store.v3f32.p0.i32(<3 x float> %v, ptr %ptr, i32 %stride, <3 x i1> %mask, i32 %evl)
394 define void @strided_vpstore_v3f32_allones_mask(<3 x float> %v, ptr %ptr, i32 signext %stride, i32 zeroext %evl) {
395 ; CHECK-LABEL: strided_vpstore_v3f32_allones_mask:
397 ; CHECK-NEXT: vsetvli zero, a2, e32, m1, ta, ma
398 ; CHECK-NEXT: vsse32.v v8, (a0), a1
400 call void @llvm.experimental.vp.strided.store.v3f32.p0.i32(<3 x float> %v, ptr %ptr, i32 %stride, <3 x i1> splat (i1 true), i32 %evl)
404 declare void @llvm.experimental.vp.strided.store.v3f32.p0.i32(<3 x float>, ptr , i32, <3 x i1>, i32)
407 define void @strided_store_v32f64(<32 x double> %v, ptr %ptr, i32 signext %stride, <32 x i1> %mask, i32 zeroext %evl) {
408 ; CHECK-LABEL: strided_store_v32f64:
410 ; CHECK-NEXT: li a4, 16
411 ; CHECK-NEXT: mv a3, a2
412 ; CHECK-NEXT: bltu a2, a4, .LBB34_2
413 ; CHECK-NEXT: # %bb.1:
414 ; CHECK-NEXT: li a3, 16
415 ; CHECK-NEXT: .LBB34_2:
416 ; CHECK-NEXT: vsetvli zero, a3, e64, m8, ta, ma
417 ; CHECK-NEXT: vsse64.v v8, (a0), a1, v0.t
418 ; CHECK-NEXT: mul a3, a3, a1
419 ; CHECK-NEXT: add a0, a0, a3
420 ; CHECK-NEXT: addi a3, a2, -16
421 ; CHECK-NEXT: sltu a2, a2, a3
422 ; CHECK-NEXT: addi a2, a2, -1
423 ; CHECK-NEXT: vsetivli zero, 2, e8, mf4, ta, ma
424 ; CHECK-NEXT: vslidedown.vi v0, v0, 2
425 ; CHECK-NEXT: and a2, a2, a3
426 ; CHECK-NEXT: vsetvli zero, a2, e64, m8, ta, ma
427 ; CHECK-NEXT: vsse64.v v16, (a0), a1, v0.t
429 call void @llvm.experimental.vp.strided.store.v32f64.p0.i32(<32 x double> %v, ptr %ptr, i32 %stride, <32 x i1> %mask, i32 %evl)
433 define void @strided_store_v32f64_allones_mask(<32 x double> %v, ptr %ptr, i32 signext %stride, i32 zeroext %evl) {
434 ; CHECK-LABEL: strided_store_v32f64_allones_mask:
436 ; CHECK-NEXT: li a4, 16
437 ; CHECK-NEXT: mv a3, a2
438 ; CHECK-NEXT: bltu a2, a4, .LBB35_2
439 ; CHECK-NEXT: # %bb.1:
440 ; CHECK-NEXT: li a3, 16
441 ; CHECK-NEXT: .LBB35_2:
442 ; CHECK-NEXT: vsetvli zero, a3, e64, m8, ta, ma
443 ; CHECK-NEXT: vsse64.v v8, (a0), a1
444 ; CHECK-NEXT: mul a3, a3, a1
445 ; CHECK-NEXT: add a0, a0, a3
446 ; CHECK-NEXT: addi a3, a2, -16
447 ; CHECK-NEXT: sltu a2, a2, a3
448 ; CHECK-NEXT: addi a2, a2, -1
449 ; CHECK-NEXT: and a2, a2, a3
450 ; CHECK-NEXT: vsetvli zero, a2, e64, m8, ta, ma
451 ; CHECK-NEXT: vsse64.v v16, (a0), a1
453 call void @llvm.experimental.vp.strided.store.v32f64.p0.i32(<32 x double> %v, ptr %ptr, i32 %stride, <32 x i1> splat (i1 true), i32 %evl)
457 declare void @llvm.experimental.vp.strided.store.v32f64.p0.i32(<32 x double>, ptr, i32, <32 x i1>, i32)