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
|
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt -O2 -S -mattr=avx < %s | FileCheck %s
; RUN: opt -passes='default<O2>' -S -mattr=avx < %s | FileCheck %s
target triple = "x86_64--"
target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
define i32 @ext_ext_or_reduction_v4i32(<4 x i32> %x, <4 x i32> %y) {
; CHECK-LABEL: @ext_ext_or_reduction_v4i32(
; CHECK-NEXT: [[Z:%.*]] = and <4 x i32> [[Y:%.*]], [[X:%.*]]
; CHECK-NEXT: [[TMP1:%.*]] = call i32 @llvm.vector.reduce.or.v4i32(<4 x i32> [[Z]])
; CHECK-NEXT: ret i32 [[TMP1]]
;
%z = and <4 x i32> %x, %y
%z0 = extractelement <4 x i32> %z, i32 0
%z1 = extractelement <4 x i32> %z, i32 1
%z01 = or i32 %z0, %z1
%z2 = extractelement <4 x i32> %z, i32 2
%z012 = or i32 %z01, %z2
%z3 = extractelement <4 x i32> %z, i32 3
%z0123 = or i32 %z3, %z012
ret i32 %z0123
}
define i32 @ext_ext_partial_add_reduction_v4i32(<4 x i32> %x) {
; CHECK-LABEL: @ext_ext_partial_add_reduction_v4i32(
; CHECK-NEXT: [[SHIFT:%.*]] = shufflevector <4 x i32> [[X:%.*]], <4 x i32> poison, <4 x i32> <i32 1, i32 undef, i32 undef, i32 undef>
; CHECK-NEXT: [[TMP1:%.*]] = add <4 x i32> [[SHIFT]], [[X]]
; CHECK-NEXT: [[SHIFT1:%.*]] = shufflevector <4 x i32> [[X]], <4 x i32> poison, <4 x i32> <i32 2, i32 undef, i32 undef, i32 undef>
; CHECK-NEXT: [[TMP2:%.*]] = add <4 x i32> [[TMP1]], [[SHIFT1]]
; CHECK-NEXT: [[X210:%.*]] = extractelement <4 x i32> [[TMP2]], i64 0
; CHECK-NEXT: ret i32 [[X210]]
;
%x0 = extractelement <4 x i32> %x, i32 0
%x1 = extractelement <4 x i32> %x, i32 1
%x10 = add i32 %x1, %x0
%x2 = extractelement <4 x i32> %x, i32 2
%x210 = add i32 %x2, %x10
ret i32 %x210
}
define i32 @ext_ext_partial_add_reduction_and_extra_add_v4i32(<4 x i32> %x, <4 x i32> %y) {
; CHECK-LABEL: @ext_ext_partial_add_reduction_and_extra_add_v4i32(
; CHECK-NEXT: [[TMP1:%.*]] = shufflevector <4 x i32> [[X:%.*]], <4 x i32> [[Y:%.*]], <4 x i32> <i32 4, i32 2, i32 5, i32 6>
; CHECK-NEXT: [[TMP2:%.*]] = call i32 @llvm.vector.reduce.add.v4i32(<4 x i32> [[TMP1]])
; CHECK-NEXT: ret i32 [[TMP2]]
;
%y0 = extractelement <4 x i32> %y, i32 0
%y1 = extractelement <4 x i32> %y, i32 1
%y10 = add i32 %y1, %y0
%y2 = extractelement <4 x i32> %y, i32 2
%y210 = add i32 %y2, %y10
%x2 = extractelement <4 x i32> %x, i32 2
%x2y210 = add i32 %x2, %y210
ret i32 %x2y210
}
; PR43953 - https://bugs.llvm.org/show_bug.cgi?id=43953
; We want to end up with a single reduction on the next 4 tests.
define i32 @TestVectorsEqual(i32* noalias %Vec0, i32* noalias %Vec1, i32 %Tolerance) {
; CHECK-LABEL: @TestVectorsEqual(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[TMP0:%.*]] = bitcast i32* [[VEC0:%.*]] to <4 x i32>*
; CHECK-NEXT: [[TMP1:%.*]] = load <4 x i32>, <4 x i32>* [[TMP0]], align 4
; CHECK-NEXT: [[TMP2:%.*]] = bitcast i32* [[VEC1:%.*]] to <4 x i32>*
; CHECK-NEXT: [[TMP3:%.*]] = load <4 x i32>, <4 x i32>* [[TMP2]], align 4
; CHECK-NEXT: [[TMP4:%.*]] = sub nsw <4 x i32> [[TMP1]], [[TMP3]]
; CHECK-NEXT: [[TMP5:%.*]] = call <4 x i32> @llvm.abs.v4i32(<4 x i32> [[TMP4]], i1 true)
; CHECK-NEXT: [[TMP6:%.*]] = call i32 @llvm.vector.reduce.add.v4i32(<4 x i32> [[TMP5]])
; CHECK-NEXT: [[CMP5_NOT:%.*]] = icmp sle i32 [[TMP6]], [[TOLERANCE:%.*]]
; CHECK-NEXT: [[COND6:%.*]] = zext i1 [[CMP5_NOT]] to i32
; CHECK-NEXT: ret i32 [[COND6]]
;
entry:
br label %for.cond
for.cond:
%sum.0 = phi i32 [ 0, %entry ], [ %add, %for.inc ]
%Component.0 = phi i32 [ 0, %entry ], [ %inc, %for.inc ]
%cmp = icmp slt i32 %Component.0, 4
br i1 %cmp, label %for.body, label %for.cond.cleanup
for.cond.cleanup:
br label %for.end
for.body:
%idxprom = sext i32 %Component.0 to i64
%arrayidx = getelementptr inbounds i32, i32* %Vec0, i64 %idxprom
%0 = load i32, i32* %arrayidx, align 4
%idxprom1 = sext i32 %Component.0 to i64
%arrayidx2 = getelementptr inbounds i32, i32* %Vec1, i64 %idxprom1
%1 = load i32, i32* %arrayidx2, align 4
%sub = sub nsw i32 %0, %1
%cmp3 = icmp sge i32 %sub, 0
br i1 %cmp3, label %cond.true, label %cond.false
cond.true:
br label %cond.end
cond.false:
%sub4 = sub nsw i32 0, %sub
br label %cond.end
cond.end:
%cond = phi i32 [ %sub, %cond.true ], [ %sub4, %cond.false ]
%add = add nsw i32 %sum.0, %cond
br label %for.inc
for.inc:
%inc = add nsw i32 %Component.0, 1
br label %for.cond
for.end:
%cmp5 = icmp sle i32 %sum.0, %Tolerance
%2 = zext i1 %cmp5 to i64
%cond6 = select i1 %cmp5, i32 1, i32 0
ret i32 %cond6
}
define i32 @TestVectorsEqual_alt(i32* noalias %Vec0, i32* noalias %Vec1, i32 %Tolerance) {
; CHECK-LABEL: @TestVectorsEqual_alt(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[TMP0:%.*]] = bitcast i32* [[VEC0:%.*]] to <4 x i32>*
; CHECK-NEXT: [[TMP1:%.*]] = load <4 x i32>, <4 x i32>* [[TMP0]], align 4
; CHECK-NEXT: [[TMP2:%.*]] = bitcast i32* [[VEC1:%.*]] to <4 x i32>*
; CHECK-NEXT: [[TMP3:%.*]] = load <4 x i32>, <4 x i32>* [[TMP2]], align 4
; CHECK-NEXT: [[TMP4:%.*]] = sub <4 x i32> [[TMP1]], [[TMP3]]
; CHECK-NEXT: [[TMP5:%.*]] = call i32 @llvm.vector.reduce.add.v4i32(<4 x i32> [[TMP4]])
; CHECK-NEXT: [[CMP3_NOT:%.*]] = icmp ule i32 [[TMP5]], [[TOLERANCE:%.*]]
; CHECK-NEXT: [[COND:%.*]] = zext i1 [[CMP3_NOT]] to i32
; CHECK-NEXT: ret i32 [[COND]]
;
entry:
br label %for.cond
for.cond:
%sum.0 = phi i32 [ 0, %entry ], [ %add, %for.inc ]
%Component.0 = phi i32 [ 0, %entry ], [ %inc, %for.inc ]
%cmp = icmp slt i32 %Component.0, 4
br i1 %cmp, label %for.body, label %for.cond.cleanup
for.cond.cleanup:
br label %for.end
for.body:
%idxprom = sext i32 %Component.0 to i64
%arrayidx = getelementptr inbounds i32, i32* %Vec0, i64 %idxprom
%0 = load i32, i32* %arrayidx, align 4
%idxprom1 = sext i32 %Component.0 to i64
%arrayidx2 = getelementptr inbounds i32, i32* %Vec1, i64 %idxprom1
%1 = load i32, i32* %arrayidx2, align 4
%sub = sub i32 %0, %1
%add = add i32 %sum.0, %sub
br label %for.inc
for.inc:
%inc = add nsw i32 %Component.0, 1
br label %for.cond
for.end:
%cmp3 = icmp ule i32 %sum.0, %Tolerance
%2 = zext i1 %cmp3 to i64
%cond = select i1 %cmp3, i32 1, i32 0
ret i32 %cond
}
define i32 @TestVectorsEqualFP(float* noalias %Vec0, float* noalias %Vec1, float %Tolerance) {
; CHECK-LABEL: @TestVectorsEqualFP(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[TMP0:%.*]] = bitcast float* [[VEC0:%.*]] to <4 x float>*
; CHECK-NEXT: [[TMP1:%.*]] = load <4 x float>, <4 x float>* [[TMP0]], align 4
; CHECK-NEXT: [[TMP2:%.*]] = bitcast float* [[VEC1:%.*]] to <4 x float>*
; CHECK-NEXT: [[TMP3:%.*]] = load <4 x float>, <4 x float>* [[TMP2]], align 4
; CHECK-NEXT: [[TMP4:%.*]] = fsub fast <4 x float> [[TMP1]], [[TMP3]]
; CHECK-NEXT: [[TMP5:%.*]] = call fast <4 x float> @llvm.fabs.v4f32(<4 x float> [[TMP4]])
; CHECK-NEXT: [[TMP6:%.*]] = call fast float @llvm.vector.reduce.fadd.v4f32(float -0.000000e+00, <4 x float> [[TMP5]])
; CHECK-NEXT: [[CMP4:%.*]] = fcmp fast ole float [[TMP6]], [[TOLERANCE:%.*]]
; CHECK-NEXT: [[COND5:%.*]] = zext i1 [[CMP4]] to i32
; CHECK-NEXT: ret i32 [[COND5]]
;
entry:
br label %for.cond
for.cond:
%sum.0 = phi float [ 0.000000e+00, %entry ], [ %add, %for.inc ]
%Component.0 = phi i32 [ 0, %entry ], [ %inc, %for.inc ]
%cmp = icmp slt i32 %Component.0, 4
br i1 %cmp, label %for.body, label %for.cond.cleanup
for.cond.cleanup:
br label %for.end
for.body:
%idxprom = sext i32 %Component.0 to i64
%arrayidx = getelementptr inbounds float, float* %Vec0, i64 %idxprom
%0 = load float, float* %arrayidx, align 4
%idxprom1 = sext i32 %Component.0 to i64
%arrayidx2 = getelementptr inbounds float, float* %Vec1, i64 %idxprom1
%1 = load float, float* %arrayidx2, align 4
%sub = fsub fast float %0, %1
%cmp3 = fcmp fast oge float %sub, 0.000000e+00
br i1 %cmp3, label %cond.true, label %cond.false
cond.true:
br label %cond.end
cond.false:
%fneg = fneg fast float %sub
br label %cond.end
cond.end:
%cond = phi fast float [ %sub, %cond.true ], [ %fneg, %cond.false ]
%add = fadd fast float %sum.0, %cond
br label %for.inc
for.inc:
%inc = add nsw i32 %Component.0, 1
br label %for.cond
for.end:
%cmp4 = fcmp fast ole float %sum.0, %Tolerance
%2 = zext i1 %cmp4 to i64
%cond5 = select i1 %cmp4, i32 1, i32 0
ret i32 %cond5
}
define i32 @TestVectorsEqualFP_alt(float* noalias %Vec0, float* noalias %Vec1, float %Tolerance) {
; CHECK-LABEL: @TestVectorsEqualFP_alt(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[TMP0:%.*]] = bitcast float* [[VEC0:%.*]] to <4 x float>*
; CHECK-NEXT: [[TMP1:%.*]] = load <4 x float>, <4 x float>* [[TMP0]], align 4
; CHECK-NEXT: [[TMP2:%.*]] = bitcast float* [[VEC1:%.*]] to <4 x float>*
; CHECK-NEXT: [[TMP3:%.*]] = load <4 x float>, <4 x float>* [[TMP2]], align 4
; CHECK-NEXT: [[TMP4:%.*]] = fsub fast <4 x float> [[TMP1]], [[TMP3]]
; CHECK-NEXT: [[TMP5:%.*]] = call fast float @llvm.vector.reduce.fadd.v4f32(float -0.000000e+00, <4 x float> [[TMP4]])
; CHECK-NEXT: [[CMP3:%.*]] = fcmp fast ole float [[TMP5]], [[TOLERANCE:%.*]]
; CHECK-NEXT: [[COND:%.*]] = zext i1 [[CMP3]] to i32
; CHECK-NEXT: ret i32 [[COND]]
;
entry:
br label %for.cond
for.cond:
%sum.0 = phi float [ 0.000000e+00, %entry ], [ %add, %for.inc ]
%Component.0 = phi i32 [ 0, %entry ], [ %inc, %for.inc ]
%cmp = icmp slt i32 %Component.0, 4
br i1 %cmp, label %for.body, label %for.cond.cleanup
for.cond.cleanup:
br label %for.end
for.body:
%idxprom = sext i32 %Component.0 to i64
%arrayidx = getelementptr inbounds float, float* %Vec0, i64 %idxprom
%0 = load float, float* %arrayidx, align 4
%idxprom1 = sext i32 %Component.0 to i64
%arrayidx2 = getelementptr inbounds float, float* %Vec1, i64 %idxprom1
%1 = load float, float* %arrayidx2, align 4
%sub = fsub fast float %0, %1
%add = fadd fast float %sum.0, %sub
br label %for.inc
for.inc:
%inc = add nsw i32 %Component.0, 1
br label %for.cond
for.end:
%cmp3 = fcmp fast ole float %sum.0, %Tolerance
%2 = zext i1 %cmp3 to i64
%cond = select i1 %cmp3, i32 1, i32 0
ret i32 %cond
}
; PR43745 - https://bugs.llvm.org/show_bug.cgi?id=43745
; FIXME: this should be vectorized
define i1 @cmp_lt_gt(double %a, double %b, double %c) {
; CHECK-LABEL: @cmp_lt_gt(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[FNEG:%.*]] = fneg double [[B:%.*]]
; CHECK-NEXT: [[MUL:%.*]] = fmul double [[A:%.*]], 2.000000e+00
; CHECK-NEXT: [[TMP0:%.*]] = insertelement <2 x double> poison, double [[C:%.*]], i64 1
; CHECK-NEXT: [[TMP1:%.*]] = insertelement <2 x double> [[TMP0]], double [[FNEG]], i64 0
; CHECK-NEXT: [[TMP2:%.*]] = insertelement <2 x double> poison, double [[C]], i64 0
; CHECK-NEXT: [[TMP3:%.*]] = insertelement <2 x double> [[TMP2]], double [[B]], i64 1
; CHECK-NEXT: [[TMP4:%.*]] = fsub <2 x double> [[TMP1]], [[TMP3]]
; CHECK-NEXT: [[TMP5:%.*]] = insertelement <2 x double> poison, double [[MUL]], i64 0
; CHECK-NEXT: [[TMP6:%.*]] = shufflevector <2 x double> [[TMP5]], <2 x double> poison, <2 x i32> zeroinitializer
; CHECK-NEXT: [[TMP7:%.*]] = fdiv <2 x double> [[TMP4]], [[TMP6]]
; CHECK-NEXT: [[TMP8:%.*]] = extractelement <2 x double> [[TMP7]], i64 1
; CHECK-NEXT: [[CMP:%.*]] = fcmp olt double [[TMP8]], 0x3EB0C6F7A0B5ED8D
; CHECK-NEXT: [[TMP9:%.*]] = extractelement <2 x double> [[TMP7]], i64 0
; CHECK-NEXT: [[CMP4:%.*]] = fcmp olt double [[TMP9]], 0x3EB0C6F7A0B5ED8D
; CHECK-NEXT: [[OR_COND:%.*]] = select i1 [[CMP]], i1 [[CMP4]], i1 false
; CHECK-NEXT: br i1 [[OR_COND]], label [[CLEANUP:%.*]], label [[LOR_LHS_FALSE:%.*]]
; CHECK: lor.lhs.false:
; CHECK-NEXT: [[TMP10:%.*]] = fcmp ule <2 x double> [[TMP7]], <double 1.000000e+00, double 1.000000e+00>
; CHECK-NEXT: [[TMP11:%.*]] = extractelement <2 x i1> [[TMP10]], i64 0
; CHECK-NEXT: [[TMP12:%.*]] = extractelement <2 x i1> [[TMP10]], i64 1
; CHECK-NEXT: [[OR_COND1:%.*]] = select i1 [[TMP12]], i1 true, i1 [[TMP11]]
; CHECK-NEXT: br label [[CLEANUP]]
; CHECK: cleanup:
; CHECK-NEXT: [[RETVAL_0:%.*]] = phi i1 [ false, [[ENTRY:%.*]] ], [ [[OR_COND1]], [[LOR_LHS_FALSE]] ]
; CHECK-NEXT: ret i1 [[RETVAL_0]]
;
entry:
%fneg = fneg double %b
%add = fadd double %fneg, %c
%mul = fmul double 2.0, %a
%div = fdiv double %add, %mul
%fneg1 = fneg double %b
%sub = fsub double %fneg1, %c
%mul2 = fmul double 2.0, %a
%div3 = fdiv double %sub, %mul2
%cmp = fcmp olt double %div, 0x3EB0C6F7A0B5ED8D
br i1 %cmp, label %land.lhs.true, label %lor.lhs.false
land.lhs.true:
%cmp4 = fcmp olt double %div3, 0x3EB0C6F7A0B5ED8D
br i1 %cmp4, label %if.then, label %lor.lhs.false
lor.lhs.false:
%cmp5 = fcmp ogt double %div, 1.0
br i1 %cmp5, label %land.lhs.true6, label %if.end
land.lhs.true6:
%cmp7 = fcmp ogt double %div3, 1.0
br i1 %cmp7, label %if.then, label %if.end
if.then:
br label %cleanup
if.end:
br label %cleanup
cleanup:
%retval.0 = phi i1 [ false, %if.then ], [ true, %if.end ]
ret i1 %retval.0
}
|
