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
|
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -mtriple=aarch64--linux-gnu -mattr=+sve < %s | FileCheck %s
define void @dead_masked_store(<vscale x 4 x i32> %val, ptr %a, <vscale x 4 x i1> %mask) {
; CHECK-LABEL: dead_masked_store:
; CHECK: // %bb.0:
; CHECK-NEXT: st1w { z0.s }, p0, [x0]
; CHECK-NEXT: ret
call void @llvm.masked.store.nxv4i32(<vscale x 4 x i32> %val, ptr %a, i32 4, <vscale x 4 x i1> %mask)
call void @llvm.masked.store.nxv4i32(<vscale x 4 x i32> %val, ptr %a, i32 4, <vscale x 4 x i1> %mask)
ret void
}
define void @dead_masked_store_alltrue_same(<vscale x 4 x i32> %val, ptr %a, <vscale x 4 x i1> %mask) {
; CHECK-LABEL: dead_masked_store_alltrue_same:
; CHECK: // %bb.0:
; CHECK-NEXT: ptrue p0.s
; CHECK-NEXT: st1w { z0.s }, p0, [x0]
; CHECK-NEXT: ret
%alltrue.ins = insertelement <vscale x 4 x i1> poison, i1 true, i32 0
%alltrue = shufflevector <vscale x 4 x i1> %alltrue.ins, <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer
call void @llvm.masked.store.nxv4i32(<vscale x 4 x i32> %val, ptr %a, i32 4, <vscale x 4 x i1> %mask)
call void @llvm.masked.store.nxv4i32(<vscale x 4 x i32> %val, ptr %a, i32 4, <vscale x 4 x i1> %alltrue)
ret void
}
define void @dead_masked_store_alltrue_bigger(<vscale x 4 x i16> %val, <vscale x 4 x i32> %val1, ptr %a, <vscale x 4 x i1> %mask) {
; CHECK-LABEL: dead_masked_store_alltrue_bigger:
; CHECK: // %bb.0:
; CHECK-NEXT: ptrue p0.s
; CHECK-NEXT: st1w { z1.s }, p0, [x0]
; CHECK-NEXT: ret
%alltrue.ins = insertelement <vscale x 4 x i1> poison, i1 true, i32 0
%alltrue = shufflevector <vscale x 4 x i1> %alltrue.ins, <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer
call void @llvm.masked.store.nxv4i16(<vscale x 4 x i16> %val, ptr %a, i32 4, <vscale x 4 x i1> %mask)
call void @llvm.masked.store.nxv4i32(<vscale x 4 x i32> %val1, ptr %a, i32 4, <vscale x 4 x i1> %alltrue)
ret void
}
define void @dead_masked_store_alltrue_smaller(<vscale x 4 x i32> %val, <vscale x 4 x i16> %val1, ptr %a, <vscale x 4 x i1> %mask) {
; CHECK-LABEL: dead_masked_store_alltrue_smaller:
; CHECK: // %bb.0:
; CHECK-NEXT: ptrue p1.s
; CHECK-NEXT: st1w { z0.s }, p0, [x0]
; CHECK-NEXT: st1h { z1.s }, p1, [x0]
; CHECK-NEXT: ret
%alltrue.ins = insertelement <vscale x 4 x i1> poison, i1 true, i32 0
%alltrue = shufflevector <vscale x 4 x i1> %alltrue.ins, <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer
call void @llvm.masked.store.nxv4i32(<vscale x 4 x i32> %val, ptr %a, i32 4, <vscale x 4 x i1> %mask)
call void @llvm.masked.store.nxv4i16(<vscale x 4 x i16> %val1, ptr %a, i32 4, <vscale x 4 x i1> %alltrue)
ret void
}
define void @dead_masked_store_same_mask_smaller_type(<vscale x 4 x i32> %val, <vscale x 4 x i16> %val1, ptr %a, <vscale x 4 x i1> %mask) {
; CHECK-LABEL: dead_masked_store_same_mask_smaller_type:
; CHECK: // %bb.0:
; CHECK-NEXT: st1w { z0.s }, p0, [x0]
; CHECK-NEXT: st1h { z1.s }, p0, [x0]
; CHECK-NEXT: ret
call void @llvm.masked.store.nxv4i32(<vscale x 4 x i32> %val, ptr %a, i32 4, <vscale x 4 x i1> %mask)
call void @llvm.masked.store.nxv4i16(<vscale x 4 x i16> %val1, ptr %a, i32 4, <vscale x 4 x i1> %mask)
ret void
}
define void @dead_masked_store_same_mask_bigger_type(<vscale x 4 x i16> %val, <vscale x 4 x i32> %val1, ptr %a, <vscale x 4 x i1> %mask) {
; CHECK-LABEL: dead_masked_store_same_mask_bigger_type:
; CHECK: // %bb.0:
; CHECK-NEXT: st1h { z0.s }, p0, [x0]
; CHECK-NEXT: st1w { z1.s }, p0, [x0]
; CHECK-NEXT: ret
call void @llvm.masked.store.nxv4i16(<vscale x 4 x i16> %val, ptr %a, i32 4, <vscale x 4 x i1> %mask)
call void @llvm.masked.store.nxv4i32(<vscale x 4 x i32> %val1, ptr %a, i32 4, <vscale x 4 x i1> %mask)
ret void
}
declare void @llvm.masked.store.nxv4i16(<vscale x 4 x i16>, <vscale x 4 x i16>*, i32, <vscale x 4 x i1>)
declare void @llvm.masked.store.nxv4i32(<vscale x 4 x i32>, <vscale x 4 x i32>*, i32, <vscale x 4 x i1>)
|
