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
82
83
84
85
|
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s --mattr=+mve.fp,+fp64 -o - | FileCheck %s
target triple = "thumbv8.1m.main-none-none-eabi"
; Expected to not transform
define arm_aapcs_vfpcc <2 x double> @complex_add_v2f64(<2 x double> %a, <2 x double> %b) {
; CHECK-LABEL: complex_add_v2f64:
; CHECK: @ %bb.0: @ %entry
; CHECK-NEXT: vadd.f64 d3, d3, d0
; CHECK-NEXT: vsub.f64 d2, d2, d1
; CHECK-NEXT: vmov q0, q1
; CHECK-NEXT: bx lr
entry:
%a.real = shufflevector <2 x double> %a, <2 x double> zeroinitializer, <1 x i32> <i32 0>
%a.imag = shufflevector <2 x double> %a, <2 x double> zeroinitializer, <1 x i32> <i32 1>
%b.real = shufflevector <2 x double> %b, <2 x double> zeroinitializer, <1 x i32> <i32 0>
%b.imag = shufflevector <2 x double> %b, <2 x double> zeroinitializer, <1 x i32> <i32 1>
%0 = fsub fast <1 x double> %b.real, %a.imag
%1 = fadd fast <1 x double> %b.imag, %a.real
%interleaved.vec = shufflevector <1 x double> %0, <1 x double> %1, <2 x i32> <i32 0, i32 1>
ret <2 x double> %interleaved.vec
}
; Expected to not transform
define arm_aapcs_vfpcc <4 x double> @complex_add_v4f64(<4 x double> %a, <4 x double> %b) {
; CHECK-LABEL: complex_add_v4f64:
; CHECK: @ %bb.0: @ %entry
; CHECK-NEXT: vadd.f64 d5, d5, d0
; CHECK-NEXT: vsub.f64 d4, d4, d1
; CHECK-NEXT: vadd.f64 d7, d7, d2
; CHECK-NEXT: vmov q0, q2
; CHECK-NEXT: vsub.f64 d6, d6, d3
; CHECK-NEXT: vmov q1, q3
; CHECK-NEXT: bx lr
entry:
%a.real = shufflevector <4 x double> %a, <4 x double> zeroinitializer, <2 x i32> <i32 0, i32 2>
%a.imag = shufflevector <4 x double> %a, <4 x double> zeroinitializer, <2 x i32> <i32 1, i32 3>
%b.real = shufflevector <4 x double> %b, <4 x double> zeroinitializer, <2 x i32> <i32 0, i32 2>
%b.imag = shufflevector <4 x double> %b, <4 x double> zeroinitializer, <2 x i32> <i32 1, i32 3>
%0 = fsub fast <2 x double> %b.real, %a.imag
%1 = fadd fast <2 x double> %b.imag, %a.real
%interleaved.vec = shufflevector <2 x double> %0, <2 x double> %1, <4 x i32> <i32 0, i32 2, i32 1, i32 3>
ret <4 x double> %interleaved.vec
}
; Expected to not transform
define arm_aapcs_vfpcc <8 x double> @complex_add_v8f64(<8 x double> %a, <8 x double> %b) {
; CHECK-LABEL: complex_add_v8f64:
; CHECK: @ %bb.0: @ %entry
; CHECK-NEXT: .vsave {d8, d9, d10, d11}
; CHECK-NEXT: vpush {d8, d9, d10, d11}
; CHECK-NEXT: add r0, sp, #32
; CHECK-NEXT: vmov q4, q1
; CHECK-NEXT: vmov q1, q0
; CHECK-NEXT: vldrw.u32 q0, [r0]
; CHECK-NEXT: add r0, sp, #48
; CHECK-NEXT: vadd.f64 d1, d1, d2
; CHECK-NEXT: vsub.f64 d0, d0, d3
; CHECK-NEXT: vldrw.u32 q1, [r0]
; CHECK-NEXT: add r0, sp, #64
; CHECK-NEXT: vadd.f64 d3, d3, d8
; CHECK-NEXT: vsub.f64 d2, d2, d9
; CHECK-NEXT: vldrw.u32 q4, [r0]
; CHECK-NEXT: add r0, sp, #80
; CHECK-NEXT: vadd.f64 d9, d9, d4
; CHECK-NEXT: vsub.f64 d8, d8, d5
; CHECK-NEXT: vldrw.u32 q2, [r0]
; CHECK-NEXT: vadd.f64 d11, d5, d6
; CHECK-NEXT: vsub.f64 d10, d4, d7
; CHECK-NEXT: vmov q2, q4
; CHECK-NEXT: vmov q3, q5
; CHECK-NEXT: vpop {d8, d9, d10, d11}
; CHECK-NEXT: bx lr
entry:
%a.real = shufflevector <8 x double> %a, <8 x double> zeroinitializer, <4 x i32> <i32 0, i32 2, i32 4, i32 6>
%a.imag = shufflevector <8 x double> %a, <8 x double> zeroinitializer, <4 x i32> <i32 1, i32 3, i32 5, i32 7>
%b.real = shufflevector <8 x double> %b, <8 x double> zeroinitializer, <4 x i32> <i32 0, i32 2, i32 4, i32 6>
%b.imag = shufflevector <8 x double> %b, <8 x double> zeroinitializer, <4 x i32> <i32 1, i32 3, i32 5, i32 7>
%0 = fsub fast <4 x double> %b.real, %a.imag
%1 = fadd fast <4 x double> %b.imag, %a.real
%interleaved.vec = shufflevector <4 x double> %0, <4 x double> %1, <8 x i32> <i32 0, i32 4, i32 1, i32 5, i32 2, i32 6, i32 3, i32 7>
ret <8 x double> %interleaved.vec
}
|
