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
|
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt -S -slp-vectorizer -mtriple=aarch64--linux-gnu -instcombine < %s | FileCheck %s
target datalayout = "e-m:e-i32:64-i128:128-n32:64-S128"
declare void @foo(i64, i64, i64, i64)
define void @test(<4 x i16> %a, <4 x i16> %b, i64* %p) {
; Make sure types of sub and its sources are not extended.
; CHECK-LABEL: @test(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[Z0:%.*]] = zext <4 x i16> [[A:%.*]] to <4 x i32>
; CHECK-NEXT: [[Z1:%.*]] = zext <4 x i16> [[B:%.*]] to <4 x i32>
; CHECK-NEXT: [[SUB0:%.*]] = sub nsw <4 x i32> [[Z0]], [[Z1]]
; CHECK-NEXT: [[TMP0:%.*]] = extractelement <4 x i32> [[SUB0]], i32 0
; CHECK-NEXT: [[TMP1:%.*]] = sext i32 [[TMP0]] to i64
; CHECK-NEXT: [[GEP0:%.*]] = getelementptr inbounds i64, i64* [[P:%.*]], i64 [[TMP1]]
; CHECK-NEXT: [[LOAD0:%.*]] = load i64, i64* [[GEP0]], align 4
; CHECK-NEXT: [[TMP2:%.*]] = extractelement <4 x i32> [[SUB0]], i32 1
; CHECK-NEXT: [[TMP3:%.*]] = sext i32 [[TMP2]] to i64
; CHECK-NEXT: [[GEP1:%.*]] = getelementptr inbounds i64, i64* [[P]], i64 [[TMP3]]
; CHECK-NEXT: [[LOAD1:%.*]] = load i64, i64* [[GEP1]], align 4
; CHECK-NEXT: [[TMP4:%.*]] = extractelement <4 x i32> [[SUB0]], i32 2
; CHECK-NEXT: [[TMP5:%.*]] = sext i32 [[TMP4]] to i64
; CHECK-NEXT: [[GEP2:%.*]] = getelementptr inbounds i64, i64* [[P]], i64 [[TMP5]]
; CHECK-NEXT: [[LOAD2:%.*]] = load i64, i64* [[GEP2]], align 4
; CHECK-NEXT: [[TMP6:%.*]] = extractelement <4 x i32> [[SUB0]], i32 3
; CHECK-NEXT: [[TMP7:%.*]] = sext i32 [[TMP6]] to i64
; CHECK-NEXT: [[GEP3:%.*]] = getelementptr inbounds i64, i64* [[P]], i64 [[TMP7]]
; CHECK-NEXT: [[LOAD3:%.*]] = load i64, i64* [[GEP3]], align 4
; CHECK-NEXT: call void @foo(i64 [[LOAD0]], i64 [[LOAD1]], i64 [[LOAD2]], i64 [[LOAD3]])
; CHECK-NEXT: ret void
;
entry:
%z0 = zext <4 x i16> %a to <4 x i32>
%z1 = zext <4 x i16> %b to <4 x i32>
%sub0 = sub <4 x i32> %z0, %z1
%e0 = extractelement <4 x i32> %sub0, i32 0
%s0 = sext i32 %e0 to i64
%gep0 = getelementptr inbounds i64, i64* %p, i64 %s0
%load0 = load i64, i64* %gep0
%e1 = extractelement <4 x i32> %sub0, i32 1
%s1 = sext i32 %e1 to i64
%gep1 = getelementptr inbounds i64, i64* %p, i64 %s1
%load1 = load i64, i64* %gep1
%e2 = extractelement <4 x i32> %sub0, i32 2
%s2 = sext i32 %e2 to i64
%gep2 = getelementptr inbounds i64, i64* %p, i64 %s2
%load2 = load i64, i64* %gep2
%e3 = extractelement <4 x i32> %sub0, i32 3
%s3 = sext i32 %e3 to i64
%gep3 = getelementptr inbounds i64, i64* %p, i64 %s3
%load3 = load i64, i64* %gep3
call void @foo(i64 %load0, i64 %load1, i64 %load2, i64 %load3)
ret void
}
|
