summaryrefslogtreecommitdiffstats
path: root/polly/www/experiments/matmul/matmul.s
blob: 22ea57b16878130088a762368a068937c3c1f36e (plain)
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
; ModuleID = 'matmul.c'
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-unknown-linux-gnu"

%struct._IO_FILE = type { i32, i8*, i8*, i8*, i8*, i8*, i8*, i8*, i8*, i8*, i8*, i8*, %struct._IO_marker*, %struct._IO_FILE*, i32, i32, i64, i16, i8, [1 x i8], i8*, i64, i8*, i8*, i8*, i8*, i64, i32, [20 x i8] }
%struct._IO_marker = type { %struct._IO_marker*, %struct._IO_FILE*, i32 }

@A = common global [1536 x [1536 x float]] zeroinitializer, align 16
@B = common global [1536 x [1536 x float]] zeroinitializer, align 16
@stdout = external global %struct._IO_FILE*
@.str = private unnamed_addr constant [5 x i8] c"%lf \00", align 1
@C = common global [1536 x [1536 x float]] zeroinitializer, align 16
@.str1 = private unnamed_addr constant [2 x i8] c"\0A\00", align 1

; Function Attrs: nounwind uwtable
define void @init_array() #0 {
entry:
  %i = alloca i32, align 4
  %j = alloca i32, align 4
  store i32 0, i32* %i, align 4
  br label %for.cond

for.cond:                                         ; preds = %for.inc17, %entry
  %0 = load i32* %i, align 4
  %cmp = icmp slt i32 %0, 1536
  br i1 %cmp, label %for.body, label %for.end19

for.body:                                         ; preds = %for.cond
  store i32 0, i32* %j, align 4
  br label %for.cond1

for.cond1:                                        ; preds = %for.inc, %for.body
  %1 = load i32* %j, align 4
  %cmp2 = icmp slt i32 %1, 1536
  br i1 %cmp2, label %for.body3, label %for.end

for.body3:                                        ; preds = %for.cond1
  %2 = load i32* %i, align 4
  %3 = load i32* %j, align 4
  %mul = mul nsw i32 %2, %3
  %rem = srem i32 %mul, 1024
  %add = add nsw i32 1, %rem
  %conv = sitofp i32 %add to double
  %div = fdiv double %conv, 2.000000e+00
  %conv4 = fptrunc double %div to float
  %4 = load i32* %j, align 4
  %idxprom = sext i32 %4 to i64
  %5 = load i32* %i, align 4
  %idxprom5 = sext i32 %5 to i64
  %arrayidx = getelementptr inbounds [1536 x [1536 x float]]* @A, i32 0, i64 %idxprom5
  %arrayidx6 = getelementptr inbounds [1536 x float]* %arrayidx, i32 0, i64 %idxprom
  store float %conv4, float* %arrayidx6, align 4
  %6 = load i32* %i, align 4
  %7 = load i32* %j, align 4
  %mul7 = mul nsw i32 %6, %7
  %rem8 = srem i32 %mul7, 1024
  %add9 = add nsw i32 1, %rem8
  %conv10 = sitofp i32 %add9 to double
  %div11 = fdiv double %conv10, 2.000000e+00
  %conv12 = fptrunc double %div11 to float
  %8 = load i32* %j, align 4
  %idxprom13 = sext i32 %8 to i64
  %9 = load i32* %i, align 4
  %idxprom14 = sext i32 %9 to i64
  %arrayidx15 = getelementptr inbounds [1536 x [1536 x float]]* @B, i32 0, i64 %idxprom14
  %arrayidx16 = getelementptr inbounds [1536 x float]* %arrayidx15, i32 0, i64 %idxprom13
  store float %conv12, float* %arrayidx16, align 4
  br label %for.inc

for.inc:                                          ; preds = %for.body3
  %10 = load i32* %j, align 4
  %inc = add nsw i32 %10, 1
  store i32 %inc, i32* %j, align 4
  br label %for.cond1

for.end:                                          ; preds = %for.cond1
  br label %for.inc17

for.inc17:                                        ; preds = %for.end
  %11 = load i32* %i, align 4
  %inc18 = add nsw i32 %11, 1
  store i32 %inc18, i32* %i, align 4
  br label %for.cond

for.end19:                                        ; preds = %for.cond
  ret void
}

; Function Attrs: nounwind uwtable
define void @print_array() #0 {
entry:
  %i = alloca i32, align 4
  %j = alloca i32, align 4
  store i32 0, i32* %i, align 4
  br label %for.cond

for.cond:                                         ; preds = %for.inc10, %entry
  %0 = load i32* %i, align 4
  %cmp = icmp slt i32 %0, 1536
  br i1 %cmp, label %for.body, label %for.end12

for.body:                                         ; preds = %for.cond
  store i32 0, i32* %j, align 4
  br label %for.cond1

for.cond1:                                        ; preds = %for.inc, %for.body
  %1 = load i32* %j, align 4
  %cmp2 = icmp slt i32 %1, 1536
  br i1 %cmp2, label %for.body3, label %for.end

for.body3:                                        ; preds = %for.cond1
  %2 = load %struct._IO_FILE** @stdout, align 8
  %3 = load i32* %j, align 4
  %idxprom = sext i32 %3 to i64
  %4 = load i32* %i, align 4
  %idxprom4 = sext i32 %4 to i64
  %arrayidx = getelementptr inbounds [1536 x [1536 x float]]* @C, i32 0, i64 %idxprom4
  %arrayidx5 = getelementptr inbounds [1536 x float]* %arrayidx, i32 0, i64 %idxprom
  %5 = load float* %arrayidx5, align 4
  %conv = fpext float %5 to double
  %call = call i32 (%struct._IO_FILE*, i8*, ...)* @fprintf(%struct._IO_FILE* %2, i8* getelementptr inbounds ([5 x i8]* @.str, i32 0, i32 0), double %conv)
  %6 = load i32* %j, align 4
  %rem = srem i32 %6, 80
  %cmp6 = icmp eq i32 %rem, 79
  br i1 %cmp6, label %if.then, label %if.end

if.then:                                          ; preds = %for.body3
  %7 = load %struct._IO_FILE** @stdout, align 8
  %call8 = call i32 (%struct._IO_FILE*, i8*, ...)* @fprintf(%struct._IO_FILE* %7, i8* getelementptr inbounds ([2 x i8]* @.str1, i32 0, i32 0))
  br label %if.end

if.end:                                           ; preds = %if.then, %for.body3
  br label %for.inc

for.inc:                                          ; preds = %if.end
  %8 = load i32* %j, align 4
  %inc = add nsw i32 %8, 1
  store i32 %inc, i32* %j, align 4
  br label %for.cond1

for.end:                                          ; preds = %for.cond1
  %9 = load %struct._IO_FILE** @stdout, align 8
  %call9 = call i32 (%struct._IO_FILE*, i8*, ...)* @fprintf(%struct._IO_FILE* %9, i8* getelementptr inbounds ([2 x i8]* @.str1, i32 0, i32 0))
  br label %for.inc10

for.inc10:                                        ; preds = %for.end
  %10 = load i32* %i, align 4
  %inc11 = add nsw i32 %10, 1
  store i32 %inc11, i32* %i, align 4
  br label %for.cond

for.end12:                                        ; preds = %for.cond
  ret void
}

declare i32 @fprintf(%struct._IO_FILE*, i8*, ...) #1

; Function Attrs: nounwind uwtable
define i32 @main() #0 {
entry:
  %retval = alloca i32, align 4
  %i = alloca i32, align 4
  %j = alloca i32, align 4
  %k = alloca i32, align 4
  %t_start = alloca double, align 8
  %t_end = alloca double, align 8
  store i32 0, i32* %retval
  call void @init_array()
  store i32 0, i32* %i, align 4
  br label %for.cond

for.cond:                                         ; preds = %for.inc28, %entry
  %0 = load i32* %i, align 4
  %cmp = icmp slt i32 %0, 1536
  br i1 %cmp, label %for.body, label %for.end30

for.body:                                         ; preds = %for.cond
  store i32 0, i32* %j, align 4
  br label %for.cond1

for.cond1:                                        ; preds = %for.inc25, %for.body
  %1 = load i32* %j, align 4
  %cmp2 = icmp slt i32 %1, 1536
  br i1 %cmp2, label %for.body3, label %for.end27

for.body3:                                        ; preds = %for.cond1
  %2 = load i32* %j, align 4
  %idxprom = sext i32 %2 to i64
  %3 = load i32* %i, align 4
  %idxprom4 = sext i32 %3 to i64
  %arrayidx = getelementptr inbounds [1536 x [1536 x float]]* @C, i32 0, i64 %idxprom4
  %arrayidx5 = getelementptr inbounds [1536 x float]* %arrayidx, i32 0, i64 %idxprom
  store float 0.000000e+00, float* %arrayidx5, align 4
  store i32 0, i32* %k, align 4
  br label %for.cond6

for.cond6:                                        ; preds = %for.inc, %for.body3
  %4 = load i32* %k, align 4
  %cmp7 = icmp slt i32 %4, 1536
  br i1 %cmp7, label %for.body8, label %for.end

for.body8:                                        ; preds = %for.cond6
  %5 = load i32* %j, align 4
  %idxprom9 = sext i32 %5 to i64
  %6 = load i32* %i, align 4
  %idxprom10 = sext i32 %6 to i64
  %arrayidx11 = getelementptr inbounds [1536 x [1536 x float]]* @C, i32 0, i64 %idxprom10
  %arrayidx12 = getelementptr inbounds [1536 x float]* %arrayidx11, i32 0, i64 %idxprom9
  %7 = load float* %arrayidx12, align 4
  %8 = load i32* %k, align 4
  %idxprom13 = sext i32 %8 to i64
  %9 = load i32* %i, align 4
  %idxprom14 = sext i32 %9 to i64
  %arrayidx15 = getelementptr inbounds [1536 x [1536 x float]]* @A, i32 0, i64 %idxprom14
  %arrayidx16 = getelementptr inbounds [1536 x float]* %arrayidx15, i32 0, i64 %idxprom13
  %10 = load float* %arrayidx16, align 4
  %11 = load i32* %j, align 4
  %idxprom17 = sext i32 %11 to i64
  %12 = load i32* %k, align 4
  %idxprom18 = sext i32 %12 to i64
  %arrayidx19 = getelementptr inbounds [1536 x [1536 x float]]* @B, i32 0, i64 %idxprom18
  %arrayidx20 = getelementptr inbounds [1536 x float]* %arrayidx19, i32 0, i64 %idxprom17
  %13 = load float* %arrayidx20, align 4
  %mul = fmul float %10, %13
  %add = fadd float %7, %mul
  %14 = load i32* %j, align 4
  %idxprom21 = sext i32 %14 to i64
  %15 = load i32* %i, align 4
  %idxprom22 = sext i32 %15 to i64
  %arrayidx23 = getelementptr inbounds [1536 x [1536 x float]]* @C, i32 0, i64 %idxprom22
  %arrayidx24 = getelementptr inbounds [1536 x float]* %arrayidx23, i32 0, i64 %idxprom21
  store float %add, float* %arrayidx24, align 4
  br label %for.inc

for.inc:                                          ; preds = %for.body8
  %16 = load i32* %k, align 4
  %inc = add nsw i32 %16, 1
  store i32 %inc, i32* %k, align 4
  br label %for.cond6

for.end:                                          ; preds = %for.cond6
  br label %for.inc25

for.inc25:                                        ; preds = %for.end
  %17 = load i32* %j, align 4
  %inc26 = add nsw i32 %17, 1
  store i32 %inc26, i32* %j, align 4
  br label %for.cond1

for.end27:                                        ; preds = %for.cond1
  br label %for.inc28

for.inc28:                                        ; preds = %for.end27
  %18 = load i32* %i, align 4
  %inc29 = add nsw i32 %18, 1
  store i32 %inc29, i32* %i, align 4
  br label %for.cond

for.end30:                                        ; preds = %for.cond
  ret i32 0
}

attributes #0 = { nounwind uwtable "less-precise-fpmad"="false" "no-frame-pointer-elim"="true" "no-frame-pointer-elim-non-leaf"="true" "no-infs-fp-math"="false" "no-nans-fp-math"="false" "unsafe-fp-math"="false" "use-soft-float"="false" }
attributes #1 = { "less-precise-fpmad"="false" "no-frame-pointer-elim"="true" "no-frame-pointer-elim-non-leaf"="true" "no-infs-fp-math"="false" "no-nans-fp-math"="false" "unsafe-fp-math"="false" "use-soft-float"="false" }
OpenPOWER on IntegriCloud