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
| ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -mtriple=thumbv8.1m.main -mattr=+mve.fp -o - %s | FileCheck %s
; RUN: llc -mtriple=thumbv8.1m.main -mattr=+mve -o - %s | FileCheck %s
define arm_aapcs_vfpcc <4 x i32> @vector_add_by_value(<4 x i32> %lhs, <4 x i32>%rhs) {
; CHECK-LABEL: vector_add_by_value:
; CHECK: @ %bb.0:
; CHECK-NEXT: @APP
; CHECK-NEXT: vadd.i32 q0, q0, q1
; CHECK-NEXT: @NO_APP
; CHECK-NEXT: bx lr
%result = tail call <4 x i32> asm "vadd.i32 $0,$1,$2", "=t,t,t"(<4 x i32> %lhs, <4 x i32> %rhs)
ret <4 x i32> %result
}
define void @vector_add_by_reference(<4 x i32>* %resultp, <4 x i32>* %lhsp, <4 x i32>* %rhsp) {
; CHECK-LABEL: vector_add_by_reference:
; CHECK: @ %bb.0:
; CHECK-NEXT: vldrw.u32 q0, [r1]
; CHECK-NEXT: vldrw.u32 q1, [r2]
; CHECK-NEXT: @APP
; CHECK-NEXT: vadd.i32 q0, q0, q1
; CHECK-NEXT: @NO_APP
; CHECK-NEXT: vstrw.32 q0, [r0]
; CHECK-NEXT: bx lr
%lhs = load <4 x i32>, <4 x i32>* %lhsp, align 16
%rhs = load <4 x i32>, <4 x i32>* %rhsp, align 16
%result = tail call <4 x i32> asm "vadd.i32 $0,$1,$2", "=t,t,t"(<4 x i32> %lhs, <4 x i32> %rhs)
store <4 x i32> %result, <4 x i32>* %resultp, align 16
ret void
}
define void @vector_f64_copy(<2 x double>* %from, <2 x double>* %to) {
; CHECK-LABEL: vector_f64_copy:
; CHECK: @ %bb.0:
; CHECK-NEXT: vldrw.u32 q0, [r0]
; CHECK-NEXT: vstrw.32 q0, [r1]
; CHECK-NEXT: bx lr
%v = load <2 x double>, <2 x double>* %from, align 16
store <2 x double> %v, <2 x double>* %to, align 16
ret void
}
define arm_aapcs_vfpcc <16 x i8> @stack_slot_handling(<16 x i8> %a) #0 {
; CHECK-LABEL: stack_slot_handling:
; CHECK: @ %bb.0: @ %entry
; CHECK-NEXT: push {r4, r6, r7, lr}
; CHECK-NEXT: add r7, sp, #8
; CHECK-NEXT: sub sp, #16
; CHECK-NEXT: mov r4, sp
; CHECK-NEXT: bfc r4, #0, #4
; CHECK-NEXT: mov sp, r4
; CHECK-NEXT: mov r0, sp
; CHECK-NEXT: vstrw.32 q0, [r0]
; CHECK-NEXT: vldrw.u32 q0, [r0]
; CHECK-NEXT: sub.w r4, r7, #8
; CHECK-NEXT: mov sp, r4
; CHECK-NEXT: pop {r4, r6, r7, pc}
entry:
%a.addr = alloca <16 x i8>, align 8
store <16 x i8> %a, <16 x i8>* %a.addr, align 8
%0 = load <16 x i8>, <16 x i8>* %a.addr, align 8
ret <16 x i8> %0
}
attributes #0 = { noinline optnone }
|