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
113
114
115
116
117
118
119
120
121
122
123
124
125
126
|
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -mtriple=riscv32 -mattr=+m -mattr=+v -O2 < %s \
; RUN: | FileCheck --check-prefix=SPILL-O2 %s
define <vscale x 1 x i32> @test_vector_std(<vscale x 1 x i32> %va) nounwind {
; SPILL-O2-LABEL: test_vector_std:
; SPILL-O2: # %bb.0: # %entry
; SPILL-O2-NEXT: addi sp, sp, -16
; SPILL-O2-NEXT: csrr a0, vlenb
; SPILL-O2-NEXT: slli a0, a0, 1
; SPILL-O2-NEXT: sub sp, sp, a0
; SPILL-O2-NEXT: addi a0, sp, 16
; SPILL-O2-NEXT: vs1r.v v8, (a0) # Unknown-size Folded Spill
; SPILL-O2-NEXT: #APP
; SPILL-O2-NEXT: #NO_APP
; SPILL-O2-NEXT: vl1r.v v8, (a0) # Unknown-size Folded Reload
; SPILL-O2-NEXT: csrr a0, vlenb
; SPILL-O2-NEXT: slli a0, a0, 1
; SPILL-O2-NEXT: add sp, sp, a0
; SPILL-O2-NEXT: addi sp, sp, 16
; SPILL-O2-NEXT: ret
entry:
call void asm sideeffect "",
"~{v0},~{v1},~{v2},~{v3},~{v4},~{v5},~{v6},~{v7},~{v8},~{v9},~{v10},~{v11},~{v12},~{v13},~{v14},~{v15},~{v16},~{v17},~{v18},~{v19},~{v20},~{v21},~{v22},~{v23},~{v24},~{v25},~{v26},~{v27},~{v28},~{v29},~{v30},~{v31}"()
ret <vscale x 1 x i32> %va
}
define riscv_vector_cc <vscale x 1 x i32> @test_vector_callee(<vscale x 1 x i32> %va) nounwind {
; SPILL-O2-LABEL: test_vector_callee:
; SPILL-O2: # %bb.0: # %entry
; SPILL-O2-NEXT: addi sp, sp, -16
; SPILL-O2-NEXT: csrr a0, vlenb
; SPILL-O2-NEXT: slli a0, a0, 4
; SPILL-O2-NEXT: sub sp, sp, a0
; SPILL-O2-NEXT: csrr a0, vlenb
; SPILL-O2-NEXT: slli a1, a0, 4
; SPILL-O2-NEXT: sub a0, a1, a0
; SPILL-O2-NEXT: add a0, sp, a0
; SPILL-O2-NEXT: addi a0, a0, 16
; SPILL-O2-NEXT: vs1r.v v1, (a0) # Unknown-size Folded Spill
; SPILL-O2-NEXT: csrr a0, vlenb
; SPILL-O2-NEXT: li a1, 13
; SPILL-O2-NEXT: mul a0, a0, a1
; SPILL-O2-NEXT: add a0, sp, a0
; SPILL-O2-NEXT: addi a0, a0, 16
; SPILL-O2-NEXT: vs2r.v v2, (a0) # Unknown-size Folded Spill
; SPILL-O2-NEXT: csrr a0, vlenb
; SPILL-O2-NEXT: slli a1, a0, 3
; SPILL-O2-NEXT: add a0, a1, a0
; SPILL-O2-NEXT: add a0, sp, a0
; SPILL-O2-NEXT: addi a0, a0, 16
; SPILL-O2-NEXT: vs4r.v v4, (a0) # Unknown-size Folded Spill
; SPILL-O2-NEXT: csrr a0, vlenb
; SPILL-O2-NEXT: add a0, sp, a0
; SPILL-O2-NEXT: addi a0, a0, 16
; SPILL-O2-NEXT: vs8r.v v24, (a0) # Unknown-size Folded Spill
; SPILL-O2-NEXT: addi a0, sp, 16
; SPILL-O2-NEXT: vs1r.v v8, (a0) # Unknown-size Folded Spill
; SPILL-O2-NEXT: #APP
; SPILL-O2-NEXT: #NO_APP
; SPILL-O2-NEXT: vl1r.v v8, (a0) # Unknown-size Folded Reload
; SPILL-O2-NEXT: csrr a0, vlenb
; SPILL-O2-NEXT: slli a1, a0, 4
; SPILL-O2-NEXT: sub a0, a1, a0
; SPILL-O2-NEXT: add a0, sp, a0
; SPILL-O2-NEXT: addi a0, a0, 16
; SPILL-O2-NEXT: vl1r.v v1, (a0) # Unknown-size Folded Reload
; SPILL-O2-NEXT: csrr a0, vlenb
; SPILL-O2-NEXT: li a1, 13
; SPILL-O2-NEXT: mul a0, a0, a1
; SPILL-O2-NEXT: add a0, sp, a0
; SPILL-O2-NEXT: addi a0, a0, 16
; SPILL-O2-NEXT: vl2r.v v2, (a0) # Unknown-size Folded Reload
; SPILL-O2-NEXT: csrr a0, vlenb
; SPILL-O2-NEXT: slli a1, a0, 3
; SPILL-O2-NEXT: add a0, a1, a0
; SPILL-O2-NEXT: add a0, sp, a0
; SPILL-O2-NEXT: addi a0, a0, 16
; SPILL-O2-NEXT: vl4r.v v4, (a0) # Unknown-size Folded Reload
; SPILL-O2-NEXT: csrr a0, vlenb
; SPILL-O2-NEXT: add a0, sp, a0
; SPILL-O2-NEXT: addi a0, a0, 16
; SPILL-O2-NEXT: vl8r.v v24, (a0) # Unknown-size Folded Reload
; SPILL-O2-NEXT: csrr a0, vlenb
; SPILL-O2-NEXT: slli a0, a0, 4
; SPILL-O2-NEXT: add sp, sp, a0
; SPILL-O2-NEXT: addi sp, sp, 16
; SPILL-O2-NEXT: ret
entry:
call void asm sideeffect "",
"~{v0},~{v1},~{v2},~{v3},~{v4},~{v5},~{v6},~{v7},~{v8},~{v9},~{v10},~{v11},~{v12},~{v13},~{v14},~{v15},~{v16},~{v17},~{v18},~{v19},~{v20},~{v21},~{v22},~{v23},~{v24},~{v25},~{v26},~{v27},~{v28},~{v29},~{v30},~{v31}"()
ret <vscale x 1 x i32> %va
}
; Make sure the local stack allocation pass doesn't count vector registers. The
; sizes are chosen to be on the edge of what RISCVRegister::needsFrameBaseReg
; considers to need a virtual base register.
define riscv_vector_cc void @local_stack_allocation_frame_pointer() "frame-pointer"="all" {
; SPILL-O2-LABEL: local_stack_allocation_frame_pointer:
; SPILL-O2: # %bb.0:
; SPILL-O2-NEXT: addi sp, sp, -2032
; SPILL-O2-NEXT: .cfi_def_cfa_offset 2032
; SPILL-O2-NEXT: sw ra, 2028(sp) # 4-byte Folded Spill
; SPILL-O2-NEXT: sw s0, 2024(sp) # 4-byte Folded Spill
; SPILL-O2-NEXT: .cfi_offset ra, -4
; SPILL-O2-NEXT: .cfi_offset s0, -8
; SPILL-O2-NEXT: addi s0, sp, 2032
; SPILL-O2-NEXT: .cfi_def_cfa s0, 0
; SPILL-O2-NEXT: addi sp, sp, -480
; SPILL-O2-NEXT: lbu a0, -1912(s0)
; SPILL-O2-NEXT: sb a0, -1912(s0)
; SPILL-O2-NEXT: addi sp, s0, -2048
; SPILL-O2-NEXT: addi sp, sp, -464
; SPILL-O2-NEXT: addi sp, sp, 480
; SPILL-O2-NEXT: lw ra, 2028(sp) # 4-byte Folded Reload
; SPILL-O2-NEXT: lw s0, 2024(sp) # 4-byte Folded Reload
; SPILL-O2-NEXT: addi sp, sp, 2032
; SPILL-O2-NEXT: ret
%va = alloca [2500 x i8], align 4
%va_gep = getelementptr [2000 x i8], ptr %va, i64 0, i64 600
%load = load volatile i8, ptr %va_gep, align 4
store volatile i8 %load, ptr %va_gep, align 4
ret void
}
|
