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
|
; RUN: opt %loadPolly -polly-detect-unprofitable -basicaa -polly-codegen-isl -polly-vectorizer=polly -S < %s | FileCheck %s
;#define N 1024
;float A[N];
;float B[N];
;
;void simple_vec_const(void) {
; int i;
;
; for (i = 0; i < 4; i++)
; B[i] = A[0];
;}
;int main()
;{
; simple_vec_const();
; return A[42];
;}
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"
target triple = "x86_64-unknown-linux-gnu"
@A = common global [1024 x float] zeroinitializer, align 16
@B = common global [1024 x float] zeroinitializer, align 16
define void @simple_vec_const() nounwind {
; <label>:0
br label %1
; <label>:1 ; preds = %4, %0
%indvar = phi i64 [ %indvar.next, %4 ], [ 0, %0 ]
%scevgep = getelementptr [1024 x float], [1024 x float]* @B, i64 0, i64 %indvar
%exitcond = icmp ne i64 %indvar, 4
br i1 %exitcond, label %2, label %5
; <label>:2 ; preds = %1
%3 = load float, float* getelementptr inbounds ([1024 x float], [1024 x float]* @A, i64 0, i64 0), align 16
store float %3, float* %scevgep, align 4
br label %4
; <label>:4 ; preds = %2
%indvar.next = add i64 %indvar, 1
br label %1
; <label>:5 ; preds = %1
ret void
}
define i32 @main() nounwind {
call void @simple_vec_const()
%1 = load float, float* getelementptr inbounds ([1024 x float], [1024 x float]* @A, i64 0, i64 42), align 8
%2 = fptosi float %1 to i32
ret i32 %2
}
; CHECK: load <1 x float>, <1 x float>* bitcast ([1024 x float]* @A to <1 x float>*)
; CHECK: shufflevector <1 x float> {{.*}}, <1 x float> {{.*}} <4 x i32> zeroinitializer
|
