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
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
|
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -mtriple=riscv64 -mattr=+m,+v -O2 < %s \
; RUN: | FileCheck %s -check-prefix=RV64IV
define <vscale x 1 x i64> @access_fixed_object(ptr %val) {
; RV64IV-LABEL: access_fixed_object:
; RV64IV: # %bb.0:
; RV64IV-NEXT: addi sp, sp, -528
; RV64IV-NEXT: .cfi_def_cfa_offset 528
; RV64IV-NEXT: addi a1, sp, 8
; RV64IV-NEXT: vl1re64.v v8, (a1)
; RV64IV-NEXT: ld a1, 520(sp)
; RV64IV-NEXT: sd a1, 0(a0)
; RV64IV-NEXT: addi sp, sp, 528
; RV64IV-NEXT: .cfi_def_cfa_offset 0
; RV64IV-NEXT: ret
%local = alloca i64
%array = alloca [64 x i64]
%v = load <vscale x 1 x i64>, ptr %array
%len = load i64, ptr %local
store i64 %len, ptr %val
ret <vscale x 1 x i64> %v
}
declare <vscale x 1 x i64> @llvm.riscv.vadd.nxv1i64.nxv1i64(
<vscale x 1 x i64>,
<vscale x 1 x i64>,
<vscale x 1 x i64>,
i64);
define <vscale x 1 x i64> @access_fixed_and_vector_objects(ptr %val) {
; RV64IV-LABEL: access_fixed_and_vector_objects:
; RV64IV: # %bb.0:
; RV64IV-NEXT: addi sp, sp, -528
; RV64IV-NEXT: .cfi_def_cfa_offset 528
; RV64IV-NEXT: csrr a0, vlenb
; RV64IV-NEXT: sub sp, sp, a0
; RV64IV-NEXT: .cfi_escape 0x0f, 0x0e, 0x72, 0x00, 0x11, 0x90, 0x04, 0x22, 0x11, 0x01, 0x92, 0xa2, 0x38, 0x00, 0x1e, 0x22 # sp + 528 + 1 * vlenb
; RV64IV-NEXT: addi a0, sp, 8
; RV64IV-NEXT: vl1re64.v v8, (a0)
; RV64IV-NEXT: addi a0, sp, 528
; RV64IV-NEXT: vl1re64.v v9, (a0)
; RV64IV-NEXT: ld a0, 520(sp)
; RV64IV-NEXT: vsetvli zero, a0, e64, m1, ta, ma
; RV64IV-NEXT: vadd.vv v8, v8, v9
; RV64IV-NEXT: csrr a0, vlenb
; RV64IV-NEXT: add sp, sp, a0
; RV64IV-NEXT: .cfi_def_cfa sp, 528
; RV64IV-NEXT: addi sp, sp, 528
; RV64IV-NEXT: .cfi_def_cfa_offset 0
; RV64IV-NEXT: ret
%local = alloca i64
%vector = alloca <vscale x 1 x i64>
%array = alloca [64 x i64]
%v1 = load <vscale x 1 x i64>, ptr %array
%v2 = load <vscale x 1 x i64>, ptr %vector
%len = load i64, ptr %local
%a = call <vscale x 1 x i64> @llvm.riscv.vadd.nxv1i64.nxv1i64(
<vscale x 1 x i64> undef,
<vscale x 1 x i64> %v1,
<vscale x 1 x i64> %v2,
i64 %len)
ret <vscale x 1 x i64> %a
}
define <vscale x 1 x i64> @probe_fixed_and_vector_objects(ptr %val, <vscale x 1 x i64> %dummy) "probe-stack"="inline-asm" {
; RV64IV-LABEL: probe_fixed_and_vector_objects:
; RV64IV: # %bb.0:
; RV64IV-NEXT: addi sp, sp, -528
; RV64IV-NEXT: .cfi_def_cfa_offset 528
; RV64IV-NEXT: csrr t1, vlenb
; RV64IV-NEXT: .cfi_def_cfa t1, -8
; RV64IV-NEXT: lui t2, 1
; RV64IV-NEXT: .LBB2_1: # =>This Inner Loop Header: Depth=1
; RV64IV-NEXT: sub sp, sp, t2
; RV64IV-NEXT: sd zero, 0(sp)
; RV64IV-NEXT: sub t1, t1, t2
; RV64IV-NEXT: bge t1, t2, .LBB2_1
; RV64IV-NEXT: # %bb.2:
; RV64IV-NEXT: .cfi_def_cfa_register sp
; RV64IV-NEXT: sub sp, sp, t1
; RV64IV-NEXT: .cfi_escape 0x0f, 0x0e, 0x72, 0x00, 0x11, 0x90, 0x04, 0x22, 0x11, 0x01, 0x92, 0xa2, 0x38, 0x00, 0x1e, 0x22 # sp + 528 + 1 * vlenb
; RV64IV-NEXT: addi a0, sp, 8
; RV64IV-NEXT: vl1re64.v v9, (a0)
; RV64IV-NEXT: addi a0, sp, 528
; RV64IV-NEXT: vl1re64.v v10, (a0)
; RV64IV-NEXT: ld a0, 520(sp)
; RV64IV-NEXT: vsetvli zero, a0, e64, m1, tu, ma
; RV64IV-NEXT: vadd.vv v8, v9, v10
; RV64IV-NEXT: csrr a0, vlenb
; RV64IV-NEXT: add sp, sp, a0
; RV64IV-NEXT: .cfi_def_cfa sp, 528
; RV64IV-NEXT: addi sp, sp, 528
; RV64IV-NEXT: .cfi_def_cfa_offset 0
; RV64IV-NEXT: ret
%local = alloca i64
%vector = alloca <vscale x 1 x i64>
%array = alloca [64 x i64]
%v1 = load <vscale x 1 x i64>, ptr %array
%v2 = load <vscale x 1 x i64>, ptr %vector
%len = load i64, ptr %local
%a = call <vscale x 1 x i64> @llvm.riscv.vadd.nxv1i64.nxv1i64(
<vscale x 1 x i64> %dummy,
<vscale x 1 x i64> %v1,
<vscale x 1 x i64> %v2,
i64 %len)
ret <vscale x 1 x i64> %a
}
|
