1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
|
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -opaque-pointers=0 -mtriple=thumbv8.1m.main -mattr=+mve --verify-machineinstrs %s -o - | FileCheck %s
%struct.arm_2d_size_t = type { i16, i16 }
define void @__arm_2d_impl_rgb16_colour_filling_with_alpha(i16* noalias nocapture %phwTargetBase, i16 signext %iTargetStride, %struct.arm_2d_size_t* noalias nocapture readonly %ptCopySize, i16 zeroext %hwColour, i32 %chRatio) {
; CHECK-LABEL: __arm_2d_impl_rgb16_colour_filling_with_alpha:
; CHECK: @ %bb.0: @ %entry
; CHECK-NEXT: push {r4, r5, r6, r7, lr}
; CHECK-NEXT: sub sp, #4
; CHECK-NEXT: vpush {d8, d9, d10, d11, d12, d13, d14, d15}
; CHECK-NEXT: sub sp, #64
; CHECK-NEXT: ldrsh.w r12, [r2, #2]
; CHECK-NEXT: cmp.w r12, #1
; CHECK-NEXT: itt ge
; CHECK-NEXT: ldrshge.w r7, [r2]
; CHECK-NEXT: cmpge r7, #1
; CHECK-NEXT: blt.w .LBB0_5
; CHECK-NEXT: @ %bb.1: @ %for.cond3.preheader.us.preheader
; CHECK-NEXT: movs r2, #252
; CHECK-NEXT: ldr r4, [sp, #152]
; CHECK-NEXT: and.w r6, r2, r3, lsr #3
; CHECK-NEXT: movs r2, #120
; CHECK-NEXT: and.w r5, r2, r3, lsr #9
; CHECK-NEXT: lsls r3, r3, #3
; CHECK-NEXT: uxtb r3, r3
; CHECK-NEXT: muls r6, r4, r6
; CHECK-NEXT: rsb.w r2, r4, #256
; CHECK-NEXT: vmov.i16 q2, #0xfc
; CHECK-NEXT: mul lr, r5, r4
; CHECK-NEXT: vdup.16 q4, r6
; CHECK-NEXT: mov.w r6, #2016
; CHECK-NEXT: vmov.i16 q6, #0xf8
; CHECK-NEXT: mul r5, r3, r4
; CHECK-NEXT: adds r3, r7, #7
; CHECK-NEXT: bic r3, r3, #7
; CHECK-NEXT: vdup.16 q3, lr
; CHECK-NEXT: subs r3, #8
; CHECK-NEXT: movs r4, #1
; CHECK-NEXT: vdup.16 q0, r5
; CHECK-NEXT: lsls r1, r1, #1
; CHECK-NEXT: add.w r3, r4, r3, lsr #3
; CHECK-NEXT: vstrw.32 q0, [sp, #48] @ 16-byte Spill
; CHECK-NEXT: vmov.i16 q0, #0xf800
; CHECK-NEXT: movs r4, #0
; CHECK-NEXT: vdup.16 q5, r6
; CHECK-NEXT: vmov.i16 q7, #0x78
; CHECK-NEXT: vstrw.32 q0, [sp] @ 16-byte Spill
; CHECK-NEXT: vstrw.32 q2, [sp, #32] @ 16-byte Spill
; CHECK-NEXT: vstrw.32 q3, [sp, #16] @ 16-byte Spill
; CHECK-NEXT: .LBB0_2: @ %vector.ph
; CHECK-NEXT: @ =>This Loop Header: Depth=1
; CHECK-NEXT: @ Child Loop BB0_3 Depth 2
; CHECK-NEXT: mov r5, r0
; CHECK-NEXT: mov r6, r7
; CHECK-NEXT: dls lr, r3
; CHECK-NEXT: .LBB0_3: @ %vector.body
; CHECK-NEXT: @ Parent Loop BB0_2 Depth=1
; CHECK-NEXT: @ => This Inner Loop Header: Depth=2
; CHECK-NEXT: vctp.16 r6
; CHECK-NEXT: subs r6, #8
; CHECK-NEXT: vpst
; CHECK-NEXT: vldrht.u16 q0, [r5]
; CHECK-NEXT: vshr.u16 q1, q0, #3
; CHECK-NEXT: vand q1, q1, q2
; CHECK-NEXT: vmov q2, q4
; CHECK-NEXT: vmla.i16 q2, q1, r2
; CHECK-NEXT: vshr.u16 q1, q2, #5
; CHECK-NEXT: vshl.i16 q2, q0, #3
; CHECK-NEXT: vand q3, q1, q5
; CHECK-NEXT: vmov q1, q7
; CHECK-NEXT: vand q2, q2, q6
; CHECK-NEXT: vmov q7, q6
; CHECK-NEXT: vmov q6, q5
; CHECK-NEXT: vmov q5, q4
; CHECK-NEXT: vldrw.u32 q4, [sp, #48] @ 16-byte Reload
; CHECK-NEXT: vshr.u16 q0, q0, #9
; CHECK-NEXT: vmla.i16 q4, q2, r2
; CHECK-NEXT: vshr.u16 q2, q4, #11
; CHECK-NEXT: vmov q4, q5
; CHECK-NEXT: vmov q5, q6
; CHECK-NEXT: vmov q6, q7
; CHECK-NEXT: vmov q7, q1
; CHECK-NEXT: vorr q1, q3, q2
; CHECK-NEXT: vldrw.u32 q2, [sp, #16] @ 16-byte Reload
; CHECK-NEXT: vand q0, q0, q7
; CHECK-NEXT: vmla.i16 q2, q0, r2
; CHECK-NEXT: vldrw.u32 q0, [sp] @ 16-byte Reload
; CHECK-NEXT: vand q0, q2, q0
; CHECK-NEXT: vldrw.u32 q2, [sp, #32] @ 16-byte Reload
; CHECK-NEXT: vorr q0, q1, q0
; CHECK-NEXT: vpst
; CHECK-NEXT: vstrht.16 q0, [r5], #16
; CHECK-NEXT: le lr, .LBB0_3
; CHECK-NEXT: @ %bb.4: @ %for.cond3.for.cond.cleanup7_crit_edge.us
; CHECK-NEXT: @ in Loop: Header=BB0_2 Depth=1
; CHECK-NEXT: adds r4, #1
; CHECK-NEXT: add r0, r1
; CHECK-NEXT: cmp r4, r12
; CHECK-NEXT: bne .LBB0_2
; CHECK-NEXT: .LBB0_5: @ %for.cond.cleanup
; CHECK-NEXT: add sp, #64
; CHECK-NEXT: vpop {d8, d9, d10, d11, d12, d13, d14, d15}
; CHECK-NEXT: add sp, #4
; CHECK-NEXT: pop {r4, r5, r6, r7, pc}
entry:
%iHeight = getelementptr inbounds %struct.arm_2d_size_t, %struct.arm_2d_size_t* %ptCopySize, i32 0, i32 1
%0 = load i16, i16* %iHeight, align 2
%conv1 = sext i16 %0 to i32
%and.i = shl i16 %hwColour, 3
%shl.i = and i16 %and.i, 248
%1 = lshr i16 %hwColour, 9
%shl4.i = and i16 %1, 120
%2 = lshr i16 %hwColour, 3
%3 = and i16 %2, 252
%4 = trunc i32 %chRatio to i16
%5 = sub i16 256, %4
%conv30 = sext i16 %iTargetStride to i32
%cmp61 = icmp sgt i16 %0, 0
br i1 %cmp61, label %for.cond3.preheader.lr.ph, label %for.cond.cleanup
for.cond3.preheader.lr.ph: ; preds = %entry
%iWidth = getelementptr inbounds %struct.arm_2d_size_t, %struct.arm_2d_size_t* %ptCopySize, i32 0, i32 0
%6 = load i16, i16* %iWidth, align 2
%conv4 = sext i16 %6 to i32
%cmp558 = icmp sgt i16 %6, 0
br i1 %cmp558, label %for.cond3.preheader.us.preheader, label %for.cond.cleanup
for.cond3.preheader.us.preheader: ; preds = %for.cond3.preheader.lr.ph
%conv15.us = mul i16 %shl.i, %4
%conv15.us.1 = mul i16 %3, %4
%conv15.us.2 = mul i16 %shl4.i, %4
%n.rnd.up = add nsw i32 %conv4, 7
%n.vec = and i32 %n.rnd.up, -8
%broadcast.splatinsert75 = insertelement <8 x i16> poison, i16 %5, i32 0
%broadcast.splat76 = shufflevector <8 x i16> %broadcast.splatinsert75, <8 x i16> poison, <8 x i32> zeroinitializer
%broadcast.splatinsert77 = insertelement <8 x i16> poison, i16 %conv15.us, i32 0
%broadcast.splat78 = shufflevector <8 x i16> %broadcast.splatinsert77, <8 x i16> poison, <8 x i32> zeroinitializer
%broadcast.splatinsert79 = insertelement <8 x i16> poison, i16 %conv15.us.1, i32 0
%broadcast.splat80 = shufflevector <8 x i16> %broadcast.splatinsert79, <8 x i16> poison, <8 x i32> zeroinitializer
%broadcast.splatinsert81 = insertelement <8 x i16> poison, i16 %conv15.us.2, i32 0
%broadcast.splat82 = shufflevector <8 x i16> %broadcast.splatinsert81, <8 x i16> poison, <8 x i32> zeroinitializer
br label %vector.ph
vector.ph: ; preds = %for.cond3.for.cond.cleanup7_crit_edge.us, %for.cond3.preheader.us.preheader
%phwTargetBase.addr.063.us = phi i16* [ %add.ptr.us, %for.cond3.for.cond.cleanup7_crit_edge.us ], [ %phwTargetBase, %for.cond3.preheader.us.preheader ]
%y.062.us = phi i32 [ %inc32.us, %for.cond3.for.cond.cleanup7_crit_edge.us ], [ 0, %for.cond3.preheader.us.preheader ]
br label %vector.body
vector.body: ; preds = %vector.body, %vector.ph
%index = phi i32 [ 0, %vector.ph ], [ %index.next, %vector.body ]
%next.gep = getelementptr i16, i16* %phwTargetBase.addr.063.us, i32 %index
%active.lane.mask = call <8 x i1> @llvm.get.active.lane.mask.v8i1.i32(i32 %index, i32 %conv4)
%7 = bitcast i16* %next.gep to <8 x i16>*
%wide.masked.load = call <8 x i16> @llvm.masked.load.v8i16.p0v8i16(<8 x i16>* %7, i32 2, <8 x i1> %active.lane.mask, <8 x i16> poison)
%8 = shl <8 x i16> %wide.masked.load, <i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3>
%9 = and <8 x i16> %8, <i16 248, i16 248, i16 248, i16 248, i16 248, i16 248, i16 248, i16 248>
%10 = lshr <8 x i16> %wide.masked.load, <i16 9, i16 9, i16 9, i16 9, i16 9, i16 9, i16 9, i16 9>
%11 = and <8 x i16> %10, <i16 120, i16 120, i16 120, i16 120, i16 120, i16 120, i16 120, i16 120>
%12 = lshr <8 x i16> %wide.masked.load, <i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3>
%13 = and <8 x i16> %12, <i16 252, i16 252, i16 252, i16 252, i16 252, i16 252, i16 252, i16 252>
%14 = mul <8 x i16> %9, %broadcast.splat76
%15 = add <8 x i16> %14, %broadcast.splat78
%16 = lshr <8 x i16> %15, <i16 11, i16 11, i16 11, i16 11, i16 11, i16 11, i16 11, i16 11>
%17 = mul <8 x i16> %13, %broadcast.splat76
%18 = add <8 x i16> %17, %broadcast.splat80
%19 = mul <8 x i16> %11, %broadcast.splat76
%20 = add <8 x i16> %19, %broadcast.splat82
%21 = lshr <8 x i16> %18, <i16 5, i16 5, i16 5, i16 5, i16 5, i16 5, i16 5, i16 5>
%22 = and <8 x i16> %21, <i16 2016, i16 2016, i16 2016, i16 2016, i16 2016, i16 2016, i16 2016, i16 2016>
%23 = or <8 x i16> %22, %16
%24 = and <8 x i16> %20, <i16 -2048, i16 -2048, i16 -2048, i16 -2048, i16 -2048, i16 -2048, i16 -2048, i16 -2048>
%25 = or <8 x i16> %23, %24
%26 = bitcast i16* %next.gep to <8 x i16>*
call void @llvm.masked.store.v8i16.p0v8i16(<8 x i16> %25, <8 x i16>* %26, i32 2, <8 x i1> %active.lane.mask)
%index.next = add i32 %index, 8
%27 = icmp eq i32 %index.next, %n.vec
br i1 %27, label %for.cond3.for.cond.cleanup7_crit_edge.us, label %vector.body
for.cond3.for.cond.cleanup7_crit_edge.us: ; preds = %vector.body
%add.ptr.us = getelementptr inbounds i16, i16* %phwTargetBase.addr.063.us, i32 %conv30
%inc32.us = add nuw nsw i32 %y.062.us, 1
%exitcond66.not = icmp eq i32 %inc32.us, %conv1
br i1 %exitcond66.not, label %for.cond.cleanup, label %vector.ph
for.cond.cleanup: ; preds = %for.cond3.for.cond.cleanup7_crit_edge.us, %for.cond3.preheader.lr.ph, %entry
ret void
}
define void @__arm_2d_impl_rgb16_colour_filling_with_alpha_sched(i16* noalias nocapture %phwTargetBase, i16 signext %iTargetStride, %struct.arm_2d_size_t* noalias nocapture readonly %ptCopySize, i16 zeroext %hwColour, i32 %chRatio) "target-cpu"="cortex-m55" {
; CHECK-LABEL: __arm_2d_impl_rgb16_colour_filling_with_alpha_sched:
; CHECK: @ %bb.0: @ %entry
; CHECK-NEXT: push {r4, r5, r6, r7, lr}
; CHECK-NEXT: sub sp, #4
; CHECK-NEXT: vpush {d8, d9, d10, d11, d12, d13, d14, d15}
; CHECK-NEXT: sub sp, #80
; CHECK-NEXT: ldrsh.w r12, [r2, #2]
; CHECK-NEXT: cmp.w r12, #1
; CHECK-NEXT: blt.w .LBB1_6
; CHECK-NEXT: @ %bb.1: @ %for.cond3.preheader.lr.ph
; CHECK-NEXT: ldrsh.w r2, [r2]
; CHECK-NEXT: cmp r2, #1
; CHECK-NEXT: blt .LBB1_6
; CHECK-NEXT: @ %bb.2: @ %for.cond3.preheader.us.preheader
; CHECK-NEXT: ldr r7, [sp, #168]
; CHECK-NEXT: movs r5, #120
; CHECK-NEXT: lsls r6, r3, #3
; CHECK-NEXT: movs r4, #252
; CHECK-NEXT: and.w r5, r5, r3, lsr #9
; CHECK-NEXT: uxtb r6, r6
; CHECK-NEXT: and.w r3, r4, r3, lsr #3
; CHECK-NEXT: muls r6, r7, r6
; CHECK-NEXT: mul lr, r3, r7
; CHECK-NEXT: vdup.16 q0, r6
; CHECK-NEXT: vstrw.32 q0, [sp, #64] @ 16-byte Spill
; CHECK-NEXT: vdup.16 q0, lr
; CHECK-NEXT: muls r5, r7, r5
; CHECK-NEXT: vstrw.32 q0, [sp, #48] @ 16-byte Spill
; CHECK-NEXT: vmov.i16 q0, #0xfc
; CHECK-NEXT: mov.w r6, #2016
; CHECK-NEXT: vstrw.32 q0, [sp, #32] @ 16-byte Spill
; CHECK-NEXT: vdup.16 q0, r5
; CHECK-NEXT: rsb.w r3, r7, #256
; CHECK-NEXT: lsls r7, r1, #1
; CHECK-NEXT: vstrw.32 q0, [sp, #16] @ 16-byte Spill
; CHECK-NEXT: vdup.16 q0, r6
; CHECK-NEXT: vmov.i16 q2, #0xf8
; CHECK-NEXT: vmov.i16 q5, #0x78
; CHECK-NEXT: vstrw.32 q0, [sp] @ 16-byte Spill
; CHECK-NEXT: vmov.i16 q6, #0xf800
; CHECK-NEXT: movs r4, #0
; CHECK-NEXT: vldrw.u32 q7, [sp] @ 16-byte Reload
; CHECK-NEXT: .p2align 2
; CHECK-NEXT: .LBB1_3: @ %vector.ph
; CHECK-NEXT: @ =>This Loop Header: Depth=1
; CHECK-NEXT: @ Child Loop BB1_4 Depth 2
; CHECK-NEXT: mov r5, r0
; CHECK-NEXT: dlstp.16 lr, r2
; CHECK-NEXT: .p2align 2
; CHECK-NEXT: .LBB1_4: @ %vector.body
; CHECK-NEXT: @ Parent Loop BB1_3 Depth=1
; CHECK-NEXT: @ => This Inner Loop Header: Depth=2
; CHECK-NEXT: vldrh.u16 q0, [r5]
; CHECK-NEXT: vshl.i16 q1, q0, #3
; CHECK-NEXT: vldrw.u32 q4, [sp, #64] @ 16-byte Reload
; CHECK-NEXT: vand q1, q1, q2
; CHECK-NEXT: vmla.i16 q4, q1, r3
; CHECK-NEXT: vmov.f64 d6, d4
; CHECK-NEXT: vmov.f64 d7, d5
; CHECK-NEXT: vldrw.u32 q1, [sp, #32] @ 16-byte Reload
; CHECK-NEXT: vshr.u16 q2, q0, #9
; CHECK-NEXT: vshr.u16 q0, q0, #3
; CHECK-NEXT: vand q0, q0, q1
; CHECK-NEXT: vldrw.u32 q1, [sp, #48] @ 16-byte Reload
; CHECK-NEXT: vmla.i16 q1, q0, r3
; CHECK-NEXT: vand q2, q2, q5
; CHECK-NEXT: vshr.u16 q0, q4, #11
; CHECK-NEXT: vldrw.u32 q4, [sp, #16] @ 16-byte Reload
; CHECK-NEXT: vshr.u16 q1, q1, #5
; CHECK-NEXT: vmla.i16 q4, q2, r3
; CHECK-NEXT: vand q1, q1, q7
; CHECK-NEXT: vorr q0, q1, q0
; CHECK-NEXT: vand q1, q4, q6
; CHECK-NEXT: vorr q0, q0, q1
; CHECK-NEXT: vstrh.16 q0, [r5], #16
; CHECK-NEXT: vmov.f64 d4, d6
; CHECK-NEXT: vmov.f64 d5, d7
; CHECK-NEXT: letp lr, .LBB1_4
; CHECK-NEXT: @ %bb.5: @ %for.cond3.for.cond.cleanup7_crit_edge.us
; CHECK-NEXT: @ in Loop: Header=BB1_3 Depth=1
; CHECK-NEXT: adds r4, #1
; CHECK-NEXT: add r0, r7
; CHECK-NEXT: cmp r4, r12
; CHECK-NEXT: bne .LBB1_3
; CHECK-NEXT: .LBB1_6: @ %for.cond.cleanup
; CHECK-NEXT: add sp, #80
; CHECK-NEXT: vpop {d8, d9, d10, d11, d12, d13, d14, d15}
; CHECK-NEXT: add sp, #4
; CHECK-NEXT: pop {r4, r5, r6, r7, pc}
entry:
%iHeight = getelementptr inbounds %struct.arm_2d_size_t, %struct.arm_2d_size_t* %ptCopySize, i32 0, i32 1
%0 = load i16, i16* %iHeight, align 2
%conv1 = sext i16 %0 to i32
%and.i = shl i16 %hwColour, 3
%shl.i = and i16 %and.i, 248
%1 = lshr i16 %hwColour, 9
%shl4.i = and i16 %1, 120
%2 = lshr i16 %hwColour, 3
%3 = and i16 %2, 252
%4 = trunc i32 %chRatio to i16
%5 = sub i16 256, %4
%conv30 = sext i16 %iTargetStride to i32
%cmp61 = icmp sgt i16 %0, 0
br i1 %cmp61, label %for.cond3.preheader.lr.ph, label %for.cond.cleanup
for.cond3.preheader.lr.ph: ; preds = %entry
%iWidth = getelementptr inbounds %struct.arm_2d_size_t, %struct.arm_2d_size_t* %ptCopySize, i32 0, i32 0
%6 = load i16, i16* %iWidth, align 2
%conv4 = sext i16 %6 to i32
%cmp558 = icmp sgt i16 %6, 0
br i1 %cmp558, label %for.cond3.preheader.us.preheader, label %for.cond.cleanup
for.cond3.preheader.us.preheader: ; preds = %for.cond3.preheader.lr.ph
%conv15.us = mul i16 %shl.i, %4
%conv15.us.1 = mul i16 %3, %4
%conv15.us.2 = mul i16 %shl4.i, %4
%n.rnd.up = add nsw i32 %conv4, 7
%n.vec = and i32 %n.rnd.up, -8
%broadcast.splatinsert75 = insertelement <8 x i16> poison, i16 %5, i32 0
%broadcast.splat76 = shufflevector <8 x i16> %broadcast.splatinsert75, <8 x i16> poison, <8 x i32> zeroinitializer
%broadcast.splatinsert77 = insertelement <8 x i16> poison, i16 %conv15.us, i32 0
%broadcast.splat78 = shufflevector <8 x i16> %broadcast.splatinsert77, <8 x i16> poison, <8 x i32> zeroinitializer
%broadcast.splatinsert79 = insertelement <8 x i16> poison, i16 %conv15.us.1, i32 0
%broadcast.splat80 = shufflevector <8 x i16> %broadcast.splatinsert79, <8 x i16> poison, <8 x i32> zeroinitializer
%broadcast.splatinsert81 = insertelement <8 x i16> poison, i16 %conv15.us.2, i32 0
%broadcast.splat82 = shufflevector <8 x i16> %broadcast.splatinsert81, <8 x i16> poison, <8 x i32> zeroinitializer
br label %vector.ph
vector.ph: ; preds = %for.cond3.for.cond.cleanup7_crit_edge.us, %for.cond3.preheader.us.preheader
%phwTargetBase.addr.063.us = phi i16* [ %add.ptr.us, %for.cond3.for.cond.cleanup7_crit_edge.us ], [ %phwTargetBase, %for.cond3.preheader.us.preheader ]
%y.062.us = phi i32 [ %inc32.us, %for.cond3.for.cond.cleanup7_crit_edge.us ], [ 0, %for.cond3.preheader.us.preheader ]
br label %vector.body
vector.body: ; preds = %vector.body, %vector.ph
%index = phi i32 [ 0, %vector.ph ], [ %index.next, %vector.body ]
%next.gep = getelementptr i16, i16* %phwTargetBase.addr.063.us, i32 %index
%active.lane.mask = call <8 x i1> @llvm.get.active.lane.mask.v8i1.i32(i32 %index, i32 %conv4)
%7 = bitcast i16* %next.gep to <8 x i16>*
%wide.masked.load = call <8 x i16> @llvm.masked.load.v8i16.p0v8i16(<8 x i16>* %7, i32 2, <8 x i1> %active.lane.mask, <8 x i16> poison)
%8 = shl <8 x i16> %wide.masked.load, <i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3>
%9 = and <8 x i16> %8, <i16 248, i16 248, i16 248, i16 248, i16 248, i16 248, i16 248, i16 248>
%10 = lshr <8 x i16> %wide.masked.load, <i16 9, i16 9, i16 9, i16 9, i16 9, i16 9, i16 9, i16 9>
%11 = and <8 x i16> %10, <i16 120, i16 120, i16 120, i16 120, i16 120, i16 120, i16 120, i16 120>
%12 = lshr <8 x i16> %wide.masked.load, <i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3, i16 3>
%13 = and <8 x i16> %12, <i16 252, i16 252, i16 252, i16 252, i16 252, i16 252, i16 252, i16 252>
%14 = mul <8 x i16> %9, %broadcast.splat76
%15 = add <8 x i16> %14, %broadcast.splat78
%16 = lshr <8 x i16> %15, <i16 11, i16 11, i16 11, i16 11, i16 11, i16 11, i16 11, i16 11>
%17 = mul <8 x i16> %13, %broadcast.splat76
%18 = add <8 x i16> %17, %broadcast.splat80
%19 = mul <8 x i16> %11, %broadcast.splat76
%20 = add <8 x i16> %19, %broadcast.splat82
%21 = lshr <8 x i16> %18, <i16 5, i16 5, i16 5, i16 5, i16 5, i16 5, i16 5, i16 5>
%22 = and <8 x i16> %21, <i16 2016, i16 2016, i16 2016, i16 2016, i16 2016, i16 2016, i16 2016, i16 2016>
%23 = or <8 x i16> %22, %16
%24 = and <8 x i16> %20, <i16 -2048, i16 -2048, i16 -2048, i16 -2048, i16 -2048, i16 -2048, i16 -2048, i16 -2048>
%25 = or <8 x i16> %23, %24
%26 = bitcast i16* %next.gep to <8 x i16>*
call void @llvm.masked.store.v8i16.p0v8i16(<8 x i16> %25, <8 x i16>* %26, i32 2, <8 x i1> %active.lane.mask)
%index.next = add i32 %index, 8
%27 = icmp eq i32 %index.next, %n.vec
br i1 %27, label %for.cond3.for.cond.cleanup7_crit_edge.us, label %vector.body
for.cond3.for.cond.cleanup7_crit_edge.us: ; preds = %vector.body
%add.ptr.us = getelementptr inbounds i16, i16* %phwTargetBase.addr.063.us, i32 %conv30
%inc32.us = add nuw nsw i32 %y.062.us, 1
%exitcond66.not = icmp eq i32 %inc32.us, %conv1
br i1 %exitcond66.not, label %for.cond.cleanup, label %vector.ph
for.cond.cleanup: ; preds = %for.cond3.for.cond.cleanup7_crit_edge.us, %for.cond3.preheader.lr.ph, %entry
ret void
}
declare <8 x i1> @llvm.get.active.lane.mask.v8i1.i32(i32, i32) #1
declare <8 x i16> @llvm.masked.load.v8i16.p0v8i16(<8 x i16>*, i32 immarg, <8 x i1>, <8 x i16>) #2
declare void @llvm.masked.store.v8i16.p0v8i16(<8 x i16>, <8 x i16>*, i32 immarg, <8 x i1>) #3
|
