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
78
79
80
81
|
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s --mattr=+sve2 -o - | FileCheck %s
target triple = "aarch64"
; Expected to transform
define <vscale x 2 x i64> @complex_add_v2i64(<vscale x 2 x i64> %a, <vscale x 2 x i64> %b) {
; CHECK-LABEL: complex_add_v2i64:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: cadd z1.d, z1.d, z0.d, #90
; CHECK-NEXT: mov z0.d, z1.d
; CHECK-NEXT: ret
entry:
%a.deinterleaved = tail call { <vscale x 1 x i64>, <vscale x 1 x i64> } @llvm.vector.deinterleave2.nxv2i64(<vscale x 2 x i64> %a)
%a.real = extractvalue { <vscale x 1 x i64>, <vscale x 1 x i64> } %a.deinterleaved, 0
%a.imag = extractvalue { <vscale x 1 x i64>, <vscale x 1 x i64> } %a.deinterleaved, 1
%b.deinterleaved = tail call { <vscale x 1 x i64>, <vscale x 1 x i64> } @llvm.vector.deinterleave2.nxv2i64(<vscale x 2 x i64> %b)
%b.real = extractvalue { <vscale x 1 x i64>, <vscale x 1 x i64> } %b.deinterleaved, 0
%b.imag = extractvalue { <vscale x 1 x i64>, <vscale x 1 x i64> } %b.deinterleaved, 1
%0 = sub <vscale x 1 x i64> %b.real, %a.imag
%1 = add <vscale x 1 x i64> %b.imag, %a.real
%interleaved.vec = tail call <vscale x 2 x i64> @llvm.vector.interleave2.nxv2i64(<vscale x 1 x i64> %0, <vscale x 1 x i64> %1)
ret <vscale x 2 x i64> %interleaved.vec
}
; Expected to transform
define <vscale x 4 x i64> @complex_add_v4i64(<vscale x 4 x i64> %a, <vscale x 4 x i64> %b) {
; CHECK-LABEL: complex_add_v4i64:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: cadd z3.d, z3.d, z1.d, #90
; CHECK-NEXT: cadd z2.d, z2.d, z0.d, #90
; CHECK-NEXT: mov z0.d, z2.d
; CHECK-NEXT: mov z1.d, z3.d
; CHECK-NEXT: ret
entry:
%a.deinterleaved = tail call { <vscale x 2 x i64>, <vscale x 2 x i64> } @llvm.vector.deinterleave2.nxv4i64(<vscale x 4 x i64> %a)
%a.real = extractvalue { <vscale x 2 x i64>, <vscale x 2 x i64> } %a.deinterleaved, 0
%a.imag = extractvalue { <vscale x 2 x i64>, <vscale x 2 x i64> } %a.deinterleaved, 1
%b.deinterleaved = tail call { <vscale x 2 x i64>, <vscale x 2 x i64> } @llvm.vector.deinterleave2.nxv4i64(<vscale x 4 x i64> %b)
%b.real = extractvalue { <vscale x 2 x i64>, <vscale x 2 x i64> } %b.deinterleaved, 0
%b.imag = extractvalue { <vscale x 2 x i64>, <vscale x 2 x i64> } %b.deinterleaved, 1
%0 = sub <vscale x 2 x i64> %b.real, %a.imag
%1 = add <vscale x 2 x i64> %b.imag, %a.real
%interleaved.vec = tail call <vscale x 4 x i64> @llvm.vector.interleave2.nxv4i64(<vscale x 2 x i64> %0, <vscale x 2 x i64> %1)
ret <vscale x 4 x i64> %interleaved.vec
}
; Expected to transform
define <vscale x 8 x i64> @complex_add_v8i64(<vscale x 8 x i64> %a, <vscale x 8 x i64> %b) {
; CHECK-LABEL: complex_add_v8i64:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: cadd z6.d, z6.d, z2.d, #90
; CHECK-NEXT: cadd z4.d, z4.d, z0.d, #90
; CHECK-NEXT: cadd z5.d, z5.d, z1.d, #90
; CHECK-NEXT: cadd z7.d, z7.d, z3.d, #90
; CHECK-NEXT: mov z0.d, z4.d
; CHECK-NEXT: mov z1.d, z5.d
; CHECK-NEXT: mov z2.d, z6.d
; CHECK-NEXT: mov z3.d, z7.d
; CHECK-NEXT: ret
entry:
%a.deinterleaved = tail call { <vscale x 4 x i64>, <vscale x 4 x i64> } @llvm.vector.deinterleave2.nxv8i64(<vscale x 8 x i64> %a)
%a.real = extractvalue { <vscale x 4 x i64>, <vscale x 4 x i64> } %a.deinterleaved, 0
%a.imag = extractvalue { <vscale x 4 x i64>, <vscale x 4 x i64> } %a.deinterleaved, 1
%b.deinterleaved = tail call { <vscale x 4 x i64>, <vscale x 4 x i64> } @llvm.vector.deinterleave2.nxv8i64(<vscale x 8 x i64> %b)
%b.real = extractvalue { <vscale x 4 x i64>, <vscale x 4 x i64> } %b.deinterleaved, 0
%b.imag = extractvalue { <vscale x 4 x i64>, <vscale x 4 x i64> } %b.deinterleaved, 1
%0 = sub <vscale x 4 x i64> %b.real, %a.imag
%1 = add <vscale x 4 x i64> %b.imag, %a.real
%interleaved.vec = tail call <vscale x 8 x i64> @llvm.vector.interleave2.nxv8i64(<vscale x 4 x i64> %0, <vscale x 4 x i64> %1)
ret <vscale x 8 x i64> %interleaved.vec
}
declare { <vscale x 1 x i64>, <vscale x 1 x i64> } @llvm.vector.deinterleave2.nxv2i64(<vscale x 2 x i64>)
declare <vscale x 2 x i64> @llvm.vector.interleave2.nxv2i64(<vscale x 1 x i64>, <vscale x 1 x i64>)
declare { <vscale x 2 x i64>, <vscale x 2 x i64> } @llvm.vector.deinterleave2.nxv4i64(<vscale x 4 x i64>)
declare <vscale x 4 x i64> @llvm.vector.interleave2.nxv4i64(<vscale x 2 x i64>, <vscale x 2 x i64>)
declare { <vscale x 4 x i64>, <vscale x 4 x i64> } @llvm.vector.deinterleave2.nxv8i64(<vscale x 8 x i64>)
declare <vscale x 8 x i64> @llvm.vector.interleave2.nxv8i64(<vscale x 4 x i64>, <vscale x 4 x i64>)
|
