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
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
|
# RUN: not --crash llc -mtriple=amdgcn -mcpu=gfx90a -run-pass=machineverifier -o /dev/null %s 2>&1 | FileCheck %s
# RUN: not --crash llc -mtriple=amdgcn -mcpu=gfx90a --passes='machine-function(verify)' -o /dev/null %s 2>&1 | FileCheck %s
# Implicit uses are OK.
---
name: implicit_use
body: |
bb.0:
$vgpr1_vgpr2 = IMPLICIT_DEF
S_NOP 0, implicit $vgpr1_vgpr2
%0:vreg_64 = IMPLICIT_DEF
S_NOP 0, implicit %0
%1:sreg_64_xexec = IMPLICIT_DEF
%2:sreg_64_xexec = SI_CALL %1, 0, csr_amdgpu, implicit $vgpr1_vgpr2
; noreg is OK
DS_WRITE_B64_gfx9 $noreg, $noreg, 0, 0, implicit $exec
...
# The unaligned registers are allowed to exist, just not on any tuple instructions.
---
name: copy_like_generic
body: |
bb.0:
$vgpr1_vgpr2 = IMPLICIT_DEF
$vgpr3_vgpr4 = COPY $vgpr1_vgpr2
%0:vreg_64 = IMPLICIT_DEF
%1:vreg_64 = COPY %0
...
---
name: mov_32_unaligned_super
body: |
bb.0:
undef %0.sub1:vreg_64 = V_MOV_B32_e32 0, implicit $exec
%1:vgpr_32 = V_MOV_B32_e32 undef %2.sub1:vreg_64, implicit $exec
...
# Well-aligned subregister indexes are OK
---
name: aligned_sub_reg
body: |
bb.0:
%0:vreg_64_align2 = IMPLICIT_DEF
%1:vreg_128_align2 = IMPLICIT_DEF
GLOBAL_STORE_DWORDX2 %0, %1.sub0_sub1, 0, 0, implicit $exec
GLOBAL_STORE_DWORDX2 %0, %1.sub2_sub3, 0, 0, implicit $exec
...
---
name: unaligned_registers
body: |
bb.0:
liveins: $vgpr0_vgpr1, $vgpr3_vgpr4_vgpr5_vgpr6
%0:vreg_64_align2 = IMPLICIT_DEF
%1:vreg_64 = IMPLICIT_DEF
%2:vreg_96 = IMPLICIT_DEF
%3:vreg_128 = IMPLICIT_DEF
%4:areg_64 = IMPLICIT_DEF
%5:vreg_128_align2 = IMPLICIT_DEF
; Check virtual register uses
; CHECK: *** Bad machine code: Subtarget requires even aligned vector registers ***
; CHECK: *** Bad machine code: Subtarget requires even aligned vector registers ***
; CHECK: *** Bad machine code: Subtarget requires even aligned vector registers ***
GLOBAL_STORE_DWORDX2 %0, %1, 0, 0, implicit $exec
GLOBAL_STORE_DWORDX3 %0, %2, 0, 0, implicit $exec
GLOBAL_STORE_DWORDX4 %0, %3, 0, 0, implicit $exec
; Check virtual registers with subregisters
; CHECK: *** Bad machine code: Subtarget requires even aligned vector registers ***
; CHECK: *** Bad machine code: Subtarget requires even aligned vector registers ***
; CHECK: *** Bad machine code: Subtarget requires even aligned vector registers ***
; CHECK: *** Bad machine code: Subtarget requires even aligned vector registers ***
GLOBAL_STORE_DWORDX2 %0, %3.sub0_sub1, 0, 0, implicit $exec
GLOBAL_STORE_DWORDX2 %0, %3.sub2_sub3, 0, 0, implicit $exec
GLOBAL_STORE_DWORDX2 %0, %3.sub1_sub2, 0, 0, implicit $exec
GLOBAL_STORE_DWORDX2 %0, %5.sub1_sub2, 0, 0, implicit $exec
; Check physical register uses
; CHECK: *** Bad machine code: Subtarget requires even aligned vector registers ***
; CHECK: *** Bad machine code: Subtarget requires even aligned vector registers ***
; CHECK: *** Bad machine code: Subtarget requires even aligned vector registers ***
GLOBAL_STORE_DWORDX2 $vgpr0_vgpr1, $vgpr3_vgpr4, 0, 0, implicit $exec
GLOBAL_STORE_DWORDX3 $vgpr0_vgpr1, $vgpr3_vgpr4_vgpr5, 0, 0, implicit $exec
GLOBAL_STORE_DWORDX4 $vgpr0_vgpr1, $vgpr3_vgpr4_vgpr5_vgpr6, 0, 0, implicit $exec
; Check virtual register defs
; CHECK: *** Bad machine code: Subtarget requires even aligned vector registers ***
; CHECK: *** Bad machine code: Subtarget requires even aligned vector registers ***
; CHECK: *** Bad machine code: Subtarget requires even aligned vector registers ***
%6:vreg_64 = GLOBAL_LOAD_DWORDX2 %0, 0, 0, implicit $exec
%7:vreg_96 = GLOBAL_LOAD_DWORDX3 %0, 0, 0, implicit $exec
%8:vreg_128 = GLOBAL_LOAD_DWORDX4 %0, 0, 0, implicit $exec
; CHECK: *** Bad machine code: Subtarget requires even aligned vector registers ***
; CHECK: *** Bad machine code: Subtarget requires even aligned vector registers ***
; CHECK: *** Bad machine code: Subtarget requires even aligned vector registers ***
$vgpr1_vgpr2 = GLOBAL_LOAD_DWORDX2 %0, 0, 0, implicit $exec
$vgpr1_vgpr2_vgpr3 = GLOBAL_LOAD_DWORDX3 %0, 0, 0, implicit $exec
$vgpr1_vgpr2_vgpr3_vgpr4 = GLOBAL_LOAD_DWORDX4 %0, 0, 0, implicit $exec
; Check AGPRs
; CHECK: *** Bad machine code: Subtarget requires even aligned vector registers ***
; CHECK: *** Bad machine code: Subtarget requires even aligned vector registers ***
%9:vgpr_32 = IMPLICIT_DEF
%10:areg_64 = IMPLICIT_DEF
%11:areg_128_align2 = IMPLICIT_DEF
DS_WRITE_B64_gfx9 %9, %10, 0, 0, implicit $exec
DS_WRITE_B64_gfx9 %9, %11.sub1_sub2, 0, 0, implicit $exec
; Check aligned vgprs for FP32 Packed Math instructions.
; CHECK: *** Bad machine code: Subtarget requires even aligned vector registers ***
; CHECK: *** Bad machine code: Subtarget requires even aligned vector registers ***
; CHECK: *** Bad machine code: Subtarget requires even aligned vector registers ***
; CHECK: *** Bad machine code: Subtarget requires even aligned vector registers ***
; CHECK: *** Bad machine code: Subtarget requires even aligned vector registers ***
; CHECK: *** Bad machine code: Subtarget requires even aligned vector registers ***
; CHECK: *** Bad machine code: Subtarget requires even aligned vector registers ***
; CHECK: *** Bad machine code: Subtarget requires even aligned vector registers ***
; CHECK: *** Bad machine code: Subtarget requires even aligned vector registers ***
; CHECK: *** Bad machine code: Subtarget requires even aligned vector registers ***
; CHECK: *** Bad machine code: Subtarget requires even aligned vector registers ***
; CHECK: *** Bad machine code: Subtarget requires even aligned vector registers ***
%12:vreg_64 = IMPLICIT_DEF
%13:vreg_64_align2 = IMPLICIT_DEF
%14:areg_96_align2 = IMPLICIT_DEF
$vgpr3_vgpr4 = V_PK_MOV_B32 8, 0, 8, 0, 0, 0, 0, 0, 0, implicit $exec
$vgpr0_vgpr1 = V_PK_ADD_F32 0, %12, 11, %13, 0, 0, 0, 0, implicit $mode, implicit $exec
$vgpr0_vgpr1 = V_PK_ADD_F32 0, %13, 11, %12, 0, 0, 0, 0, 0, implicit $mode, implicit $exec
$vgpr0_vgpr1 = V_PK_ADD_F32 0, %13, 11, %14.sub1_sub2, 0, 0, 0, 0, 0, implicit $mode, implicit $exec
$vgpr0_vgpr1 = V_PK_ADD_F32 0, %14.sub1_sub2, 11, %13, 0, 0, 0, 0, implicit $mode, implicit $exec
$vgpr0_vgpr1 = V_PK_MUL_F32 0, %12, 11, %13, 0, 0, 0, 0, implicit $mode, implicit $exec
$vgpr0_vgpr1 = V_PK_MUL_F32 0, %13, 11, %12, 0, 0, 0, 0, 0, implicit $mode, implicit $exec
$vgpr0_vgpr1 = V_PK_MUL_F32 0, %13, 11, %14.sub1_sub2, 0, 0, 0, 0, 0, implicit $mode, implicit $exec
$vgpr0_vgpr1 = V_PK_MUL_F32 0, %14.sub1_sub2, 11, %13, 0, 0, 0, 0, implicit $mode, implicit $exec
$vgpr0_vgpr1 = nofpexcept V_PK_FMA_F32 8, %12, 8, %13, 11, %14.sub0_sub1, 0, 0, 0, 0, 0, implicit $mode, implicit $exec
$vgpr0_vgpr1 = nofpexcept V_PK_FMA_F32 8, %13, 8, %12, 11, %14.sub0_sub1, 0, 0, 0, 0, 0, implicit $mode, implicit $exec
$vgpr0_vgpr1 = nofpexcept V_PK_FMA_F32 8, %13, 8, %13, 11, %14.sub1_sub2, 0, 0, 0, 0, 0, implicit $mode, implicit $exec
...
# FIXME: Inline asm is not verified
# ; Check inline asm
# ; XCHECK: *** Bad machine code: Subtarget requires even aligned vector registers ***
# ; XCHECK: *** Bad machine code: Subtarget requires even aligned vector registers ***
# ; XCHECK: *** Bad machine code: Subtarget requires even aligned vector registers ***
# INLINEASM &"; use $0 ", 1 /* sideeffect attdialect */, 9 /* reguse */, $vgpr1_vgpr2
# INLINEASM &"; use $0 ", 1 /* sideeffect attdialect */, 9 /* reguse */, %4
# INLINEASM &"; use $0 ", 1 /* sideeffect attdialect */, 9 /* reguse */, %5.sub1_sub2
|
