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
|
; RUN: opt -mtriple=thumbv8.1m.main -mve-tail-predication -disable-mve-tail-predication=false -mattr=+mve %s -S -o - | FileCheck %s
; CHECK-LABEL: vec_mul_reduce_add
; CHECK: vector.body:
; CHECK-NOT: phi i32 [ 0, %vector.ph ]
; CHECK: [[ELTS:%[^ ]+]] = phi i32 [ %N, %vector.ph ], [ [[SUB:%[^ ]+]], %vector.body ]
; CHECK: [[VCTP:%[^ ]+]] = call <4 x i1> @llvm.arm.vctp32(i32 [[ELTS]])
; CHECK: [[SUB]] = sub i32 [[ELTS]], 4
; CHECK: call <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>* {{.*}}, i32 4, <4 x i1> [[VCTP]]
; CHECK: call <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>* {{.*}}, i32 4, <4 x i1> [[VCTP]],
; CHECK: middle.block:
; CHECK: [[VCTP_CLONE:%[^ ]+]] = call <4 x i1> @llvm.arm.vctp32(i32 [[ELTS]])
; CHECK: [[VPSEL:%[^ ]+]] = select <4 x i1> [[VCTP_CLONE]],
; CHECK: call i32 @llvm.experimental.vector.reduce.add.v4i32(<4 x i32> [[VPSEL]])
define i32 @vec_mul_reduce_add(i32* noalias nocapture readonly %a, i32* noalias nocapture readonly %b, i32 %N) {
entry:
%cmp8 = icmp eq i32 %N, 0
%0 = add i32 %N, 3
%1 = lshr i32 %0, 2
%2 = shl nuw i32 %1, 2
%3 = add i32 %2, -4
%4 = lshr i32 %3, 2
%5 = add nuw nsw i32 %4, 1
br i1 %cmp8, label %for.cond.cleanup, label %vector.ph
vector.ph: ; preds = %entry
%trip.count.minus.1 = add i32 %N, -1
%broadcast.splatinsert11 = insertelement <4 x i32> undef, i32 %trip.count.minus.1, i32 0
%broadcast.splat12 = shufflevector <4 x i32> %broadcast.splatinsert11, <4 x i32> undef, <4 x i32> zeroinitializer
call void @llvm.set.loop.iterations.i32(i32 %5)
br label %vector.body
vector.body: ; preds = %vector.body, %vector.ph
%index = phi i32 [ 0, %vector.ph ], [ %index.next, %vector.body ]
%lsr.iv2 = phi i32* [ %scevgep3, %vector.body ], [ %a, %vector.ph ]
%lsr.iv = phi i32* [ %scevgep, %vector.body ], [ %b, %vector.ph ]
%vec.phi = phi <4 x i32> [ zeroinitializer, %vector.ph ], [ %9, %vector.body ]
%6 = phi i32 [ %5, %vector.ph ], [ %10, %vector.body ]
%lsr.iv24 = bitcast i32* %lsr.iv2 to <4 x i32>*
%lsr.iv1 = bitcast i32* %lsr.iv to <4 x i32>*
%broadcast.splatinsert = insertelement <4 x i32> undef, i32 %index, i32 0
%broadcast.splat = shufflevector <4 x i32> %broadcast.splatinsert, <4 x i32> undef, <4 x i32> zeroinitializer
%induction = add <4 x i32> %broadcast.splat, <i32 0, i32 1, i32 2, i32 3>
%7 = icmp ule <4 x i32> %induction, %broadcast.splat12
%wide.masked.load = call <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>* %lsr.iv24, i32 4, <4 x i1> %7, <4 x i32> undef)
%wide.masked.load13 = call <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>* %lsr.iv1, i32 4, <4 x i1> %7, <4 x i32> undef)
%8 = mul nsw <4 x i32> %wide.masked.load13, %wide.masked.load
%9 = add nsw <4 x i32> %8, %vec.phi
%index.next = add i32 %index, 4
%scevgep = getelementptr i32, i32* %lsr.iv, i32 4
%scevgep3 = getelementptr i32, i32* %lsr.iv2, i32 4
%10 = call i32 @llvm.loop.decrement.reg.i32.i32.i32(i32 %6, i32 1)
%11 = icmp ne i32 %10, 0
br i1 %11, label %vector.body, label %middle.block
middle.block: ; preds = %vector.body
%12 = icmp ule <4 x i32> %induction, %broadcast.splat12
%13 = select <4 x i1> %12, <4 x i32> %9, <4 x i32> %vec.phi
%14 = call i32 @llvm.experimental.vector.reduce.add.v4i32(<4 x i32> %13)
br label %for.cond.cleanup
for.cond.cleanup: ; preds = %middle.block, %entry
%res.0.lcssa = phi i32 [ 0, %entry ], [ %14, %middle.block ]
ret i32 %res.0.lcssa
}
declare <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>*, i32 immarg, <4 x i1>, <4 x i32>)
declare i32 @llvm.experimental.vector.reduce.add.v4i32(<4 x i32>)
declare void @llvm.set.loop.iterations.i32(i32)
declare i32 @llvm.loop.decrement.reg.i32.i32.i32(i32, i32)
|