max-mstore.ll
1.47 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
; RUN: opt -basic-aa -loop-vectorize -force-vector-interleave=1 -S -mcpu=core-avx2
target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
target triple = "x86_64-unknown-linux-gnu"
@b = common global [256 x i32] zeroinitializer, align 16
@a = common global [256 x i32] zeroinitializer, align 16
; unsigned int a[256], b[256];
; void foo() {
; for (i = 0; i < 256; i++) {
; if (b[i] > a[i])
; a[i] = b[i];
; }
; }
; CHECK-LABEL: foo
; CHECK: load <8 x i32>
; CHECK: icmp ugt <8 x i32>
; CHECK: masked.store
define void @foo() {
entry:
br label %for.body
for.body: ; preds = %for.inc, %entry
%indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.inc ]
%arrayidx = getelementptr inbounds [256 x i32], [256 x i32]* @b, i64 0, i64 %indvars.iv
%0 = load i32, i32* %arrayidx, align 4
%arrayidx2 = getelementptr inbounds [256 x i32], [256 x i32]* @a, i64 0, i64 %indvars.iv
%1 = load i32, i32* %arrayidx2, align 4
%cmp3 = icmp ugt i32 %0, %1
br i1 %cmp3, label %if.then, label %for.inc
if.then: ; preds = %for.body
store i32 %0, i32* %arrayidx2, align 4
br label %for.inc
for.inc: ; preds = %for.body, %if.then
%indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
%exitcond = icmp eq i64 %indvars.iv.next, 256
br i1 %exitcond, label %for.end, label %for.body
for.end: ; preds = %for.inc
ret void
}