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
|
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt < %s -basic-aa -slp-vectorizer -dce -S -mtriple=x86_64-apple-macosx10.8.0 -mcpu=corei7-avx | FileCheck %s
target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64-S128"
target triple = "x86_64-apple-macosx10.7.0"
@.str = private unnamed_addr constant [6 x i8] c"bingo\00", align 1
define void @reduce_compare(double* nocapture %A, i32 %n) {
; CHECK-LABEL: @reduce_compare(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[CONV:%.*]] = sitofp i32 [[N:%.*]] to double
; CHECK-NEXT: [[TMP0:%.*]] = insertelement <2 x double> poison, double [[CONV]], i32 0
; CHECK-NEXT: [[TMP1:%.*]] = insertelement <2 x double> [[TMP0]], double [[CONV]], i32 1
; CHECK-NEXT: br label [[FOR_BODY:%.*]]
; CHECK: for.body:
; CHECK-NEXT: [[INDVARS_IV:%.*]] = phi i64 [ 0, [[ENTRY:%.*]] ], [ [[INDVARS_IV_NEXT:%.*]], [[FOR_INC:%.*]] ]
; CHECK-NEXT: [[TMP2:%.*]] = shl nsw i64 [[INDVARS_IV]], 1
; CHECK-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds double, double* [[A:%.*]], i64 [[TMP2]]
; CHECK-NEXT: [[TMP3:%.*]] = bitcast double* [[ARRAYIDX]] to <2 x double>*
; CHECK-NEXT: [[TMP4:%.*]] = load <2 x double>, <2 x double>* [[TMP3]], align 8
; CHECK-NEXT: [[TMP5:%.*]] = fmul <2 x double> [[TMP1]], [[TMP4]]
; CHECK-NEXT: [[TMP6:%.*]] = fmul <2 x double> [[TMP5]], <double 7.000000e+00, double 4.000000e+00>
; CHECK-NEXT: [[TMP7:%.*]] = fadd <2 x double> [[TMP6]], <double 5.000000e+00, double 9.000000e+00>
; CHECK-NEXT: [[TMP8:%.*]] = extractelement <2 x double> [[TMP7]], i32 0
; CHECK-NEXT: [[TMP9:%.*]] = extractelement <2 x double> [[TMP7]], i32 1
; CHECK-NEXT: [[CMP11:%.*]] = fcmp ogt double [[TMP8]], [[TMP9]]
; CHECK-NEXT: br i1 [[CMP11]], label [[IF_THEN:%.*]], label [[FOR_INC]]
; CHECK: if.then:
; CHECK-NEXT: [[CALL:%.*]] = tail call i32 (i8*, ...) @printf(i8* getelementptr inbounds ([6 x i8], [6 x i8]* @.str, i64 0, i64 0))
; CHECK-NEXT: br label [[FOR_INC]]
; CHECK: for.inc:
; CHECK-NEXT: [[INDVARS_IV_NEXT]] = add i64 [[INDVARS_IV]], 1
; CHECK-NEXT: [[LFTR_WIDEIV:%.*]] = trunc i64 [[INDVARS_IV_NEXT]] to i32
; CHECK-NEXT: [[EXITCOND:%.*]] = icmp eq i32 [[LFTR_WIDEIV]], 100
; CHECK-NEXT: br i1 [[EXITCOND]], label [[FOR_END:%.*]], label [[FOR_BODY]]
; CHECK: for.end:
; CHECK-NEXT: ret void
;
entry:
%conv = sitofp i32 %n to double
br label %for.body
for.body: ; preds = %for.inc, %entry
%indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.inc ]
%0 = shl nsw i64 %indvars.iv, 1
%arrayidx = getelementptr inbounds double, double* %A, i64 %0
%1 = load double, double* %arrayidx, align 8
%mul1 = fmul double %conv, %1
%mul2 = fmul double %mul1, 7.000000e+00
%add = fadd double %mul2, 5.000000e+00
%2 = or i64 %0, 1
%arrayidx6 = getelementptr inbounds double, double* %A, i64 %2
%3 = load double, double* %arrayidx6, align 8
%mul8 = fmul double %conv, %3
%mul9 = fmul double %mul8, 4.000000e+00
%add10 = fadd double %mul9, 9.000000e+00
%cmp11 = fcmp ogt double %add, %add10
br i1 %cmp11, label %if.then, label %for.inc
if.then: ; preds = %for.body
%call = tail call i32 (i8*, ...) @printf(i8* getelementptr inbounds ([6 x i8], [6 x i8]* @.str, i64 0, i64 0))
br label %for.inc
for.inc: ; preds = %for.body, %if.then
%indvars.iv.next = add i64 %indvars.iv, 1
%lftr.wideiv = trunc i64 %indvars.iv.next to i32
%exitcond = icmp eq i32 %lftr.wideiv, 100
br i1 %exitcond, label %for.end, label %for.body
for.end: ; preds = %for.inc
ret void
}
declare i32 @printf(i8* nocapture, ...)
; PR41312 - the order of the reduction ops should not prevent forming a reduction.
; The 'wrong' member of the reduction requires a greater cost if grouped with the
; other candidates in the reduction because it does not have matching predicate
; and/or constant operand.
define float @merge_anyof_v4f32_wrong_first(<4 x float> %x) {
; CHECK-LABEL: @merge_anyof_v4f32_wrong_first(
; CHECK-NEXT: [[TMP1:%.*]] = extractelement <4 x float> [[X:%.*]], i32 3
; CHECK-NEXT: [[CMP3WRONG:%.*]] = fcmp olt float [[TMP1]], 4.200000e+01
; CHECK-NEXT: [[TMP2:%.*]] = fcmp ogt <4 x float> [[X]], <float 1.000000e+00, float 1.000000e+00, float 1.000000e+00, float 1.000000e+00>
; CHECK-NEXT: [[TMP3:%.*]] = call i1 @llvm.vector.reduce.or.v4i1(<4 x i1> [[TMP2]])
; CHECK-NEXT: [[TMP4:%.*]] = or i1 [[TMP3]], [[CMP3WRONG]]
; CHECK-NEXT: [[R:%.*]] = select i1 [[TMP4]], float -1.000000e+00, float 1.000000e+00
; CHECK-NEXT: ret float [[R]]
;
%x0 = extractelement <4 x float> %x, i32 0
%x1 = extractelement <4 x float> %x, i32 1
%x2 = extractelement <4 x float> %x, i32 2
%x3 = extractelement <4 x float> %x, i32 3
%cmp3wrong = fcmp olt float %x3, 42.0
%cmp0 = fcmp ogt float %x0, 1.0
%cmp1 = fcmp ogt float %x1, 1.0
%cmp2 = fcmp ogt float %x2, 1.0
%cmp3 = fcmp ogt float %x3, 1.0
%or03 = or i1 %cmp0, %cmp3wrong
%or031 = or i1 %or03, %cmp1
%or0312 = or i1 %or031, %cmp2
%or03123 = or i1 %or0312, %cmp3
%r = select i1 %or03123, float -1.0, float 1.0
ret float %r
}
define float @merge_anyof_v4f32_wrong_last(<4 x float> %x) {
; CHECK-LABEL: @merge_anyof_v4f32_wrong_last(
; CHECK-NEXT: [[TMP1:%.*]] = extractelement <4 x float> [[X:%.*]], i32 3
; CHECK-NEXT: [[CMP3WRONG:%.*]] = fcmp olt float [[TMP1]], 4.200000e+01
; CHECK-NEXT: [[TMP2:%.*]] = fcmp ogt <4 x float> [[X]], <float 1.000000e+00, float 1.000000e+00, float 1.000000e+00, float 1.000000e+00>
; CHECK-NEXT: [[TMP3:%.*]] = call i1 @llvm.vector.reduce.or.v4i1(<4 x i1> [[TMP2]])
; CHECK-NEXT: [[TMP4:%.*]] = or i1 [[TMP3]], [[CMP3WRONG]]
; CHECK-NEXT: [[R:%.*]] = select i1 [[TMP4]], float -1.000000e+00, float 1.000000e+00
; CHECK-NEXT: ret float [[R]]
;
%x0 = extractelement <4 x float> %x, i32 0
%x1 = extractelement <4 x float> %x, i32 1
%x2 = extractelement <4 x float> %x, i32 2
%x3 = extractelement <4 x float> %x, i32 3
%cmp3wrong = fcmp olt float %x3, 42.0
%cmp0 = fcmp ogt float %x0, 1.0
%cmp1 = fcmp ogt float %x1, 1.0
%cmp2 = fcmp ogt float %x2, 1.0
%cmp3 = fcmp ogt float %x3, 1.0
%or03 = or i1 %cmp0, %cmp3
%or031 = or i1 %or03, %cmp1
%or0312 = or i1 %or031, %cmp2
%or03123 = or i1 %or0312, %cmp3wrong
%r = select i1 %or03123, float -1.0, float 1.0
ret float %r
}
define i32 @merge_anyof_v4i32_wrong_middle(<4 x i32> %x) {
; CHECK-LABEL: @merge_anyof_v4i32_wrong_middle(
; CHECK-NEXT: [[TMP1:%.*]] = extractelement <4 x i32> [[X:%.*]], i32 3
; CHECK-NEXT: [[CMP3WRONG:%.*]] = icmp slt i32 [[TMP1]], 42
; CHECK-NEXT: [[TMP2:%.*]] = icmp sgt <4 x i32> [[X]], <i32 1, i32 1, i32 1, i32 1>
; CHECK-NEXT: [[TMP3:%.*]] = call i1 @llvm.vector.reduce.or.v4i1(<4 x i1> [[TMP2]])
; CHECK-NEXT: [[TMP4:%.*]] = or i1 [[TMP3]], [[CMP3WRONG]]
; CHECK-NEXT: [[R:%.*]] = select i1 [[TMP4]], i32 -1, i32 1
; CHECK-NEXT: ret i32 [[R]]
;
%x0 = extractelement <4 x i32> %x, i32 0
%x1 = extractelement <4 x i32> %x, i32 1
%x2 = extractelement <4 x i32> %x, i32 2
%x3 = extractelement <4 x i32> %x, i32 3
%cmp3wrong = icmp slt i32 %x3, 42
%cmp0 = icmp sgt i32 %x0, 1
%cmp1 = icmp sgt i32 %x1, 1
%cmp2 = icmp sgt i32 %x2, 1
%cmp3 = icmp sgt i32 %x3, 1
%or03 = or i1 %cmp0, %cmp3
%or033 = or i1 %or03, %cmp3wrong
%or0332 = or i1 %or033, %cmp2
%or03321 = or i1 %or0332, %cmp1
%r = select i1 %or03321, i32 -1, i32 1
ret i32 %r
}
; Operand/predicate swapping allows forming a reduction, but the
; ideal reduction groups all of the original 'sgt' ops together.
define i32 @merge_anyof_v4i32_wrong_middle_better_rdx(<4 x i32> %x, <4 x i32> %y) {
; CHECK-LABEL: @merge_anyof_v4i32_wrong_middle_better_rdx(
; CHECK-NEXT: [[TMP1:%.*]] = extractelement <4 x i32> [[Y:%.*]], i32 3
; CHECK-NEXT: [[TMP2:%.*]] = extractelement <4 x i32> [[X:%.*]], i32 3
; CHECK-NEXT: [[CMP3WRONG:%.*]] = icmp slt i32 [[TMP2]], [[TMP1]]
; CHECK-NEXT: [[TMP3:%.*]] = icmp sgt <4 x i32> [[X]], [[Y]]
; CHECK-NEXT: [[TMP4:%.*]] = call i1 @llvm.vector.reduce.or.v4i1(<4 x i1> [[TMP3]])
; CHECK-NEXT: [[TMP5:%.*]] = or i1 [[TMP4]], [[CMP3WRONG]]
; CHECK-NEXT: [[R:%.*]] = select i1 [[TMP5]], i32 -1, i32 1
; CHECK-NEXT: ret i32 [[R]]
;
%x0 = extractelement <4 x i32> %x, i32 0
%x1 = extractelement <4 x i32> %x, i32 1
%x2 = extractelement <4 x i32> %x, i32 2
%x3 = extractelement <4 x i32> %x, i32 3
%y0 = extractelement <4 x i32> %y, i32 0
%y1 = extractelement <4 x i32> %y, i32 1
%y2 = extractelement <4 x i32> %y, i32 2
%y3 = extractelement <4 x i32> %y, i32 3
%cmp3wrong = icmp slt i32 %x3, %y3
%cmp0 = icmp sgt i32 %x0, %y0
%cmp1 = icmp sgt i32 %x1, %y1
%cmp2 = icmp sgt i32 %x2, %y2
%cmp3 = icmp sgt i32 %x3, %y3
%or03 = or i1 %cmp0, %cmp3
%or033 = or i1 %or03, %cmp3wrong
%or0332 = or i1 %or033, %cmp2
%or03321 = or i1 %or0332, %cmp1
%r = select i1 %or03321, i32 -1, i32 1
ret i32 %r
}
|
