store-shuffle-bug.ll
1.78 KB
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
; RUN: opt -S -basic-aa -loop-vectorize -force-vector-interleave=1 -force-vector-width=4 -dce -instcombine < %s | 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"
@uf = common global [100 x i32] zeroinitializer, align 16
@xi = common global [100 x i32] zeroinitializer, align 16
@q = common global [100 x i32] zeroinitializer, align 16
; PR16455
; Due to a bug in the way we handled reverse induction stores we would generate
; a shuffle too many.
define void @t() {
entry:
br label %for.body
; CHECK-LABEL: @t(
; CHECK: vector.body:
; CHECK: [[VAR1:%[a-zA-Z0-9.]+]] = load <4 x i32>
; CHECK: [[VAR2:%[a-zA-Z0-9.]+]] = load <4 x i32>
; CHECK: [[VAR3:%[a-zA-Z0-9]+]] = add nsw <4 x i32> [[VAR2]], [[VAR1]]
; CHECK: store <4 x i32> [[VAR3]]
; CHECK: [[VAR4:%[a-zA-Z0-9.]+]] = load <4 x i32>
; CHECK: add nsw <4 x i32> [[VAR3]], [[VAR4]]
; CHECK-NOT: shufflevector
for.body:
%indvars.iv = phi i64 [ 93, %entry ], [ %indvars.iv.next, %for.body ]
%0 = add i64 %indvars.iv, 1
%arrayidx = getelementptr inbounds [100 x i32], [100 x i32]* @uf, i64 0, i64 %0
%arrayidx3 = getelementptr inbounds [100 x i32], [100 x i32]* @xi, i64 0, i64 %0
%1 = load i32, i32* %arrayidx3, align 4
%2 = load i32, i32* %arrayidx, align 4
%add4 = add nsw i32 %2, %1
store i32 %add4, i32* %arrayidx, align 4
%arrayidx7 = getelementptr inbounds [100 x i32], [100 x i32]* @q, i64 0, i64 %0
%3 = load i32, i32* %arrayidx7, align 4
%add8 = add nsw i32 %add4, %3
store i32 %add8, i32* %arrayidx, align 4
%indvars.iv.next = add i64 %indvars.iv, -1
%4 = trunc i64 %indvars.iv.next to i32
%cmp = icmp ugt i32 %4, 2
br i1 %cmp, label %for.body, label %for.end
for.end:
ret void
}