add_shl.ll
4.97 KB
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
152
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=amdgcn-amd-mesa3d -mcpu=fiji -verify-machineinstrs | FileCheck -check-prefix=VI %s
; RUN: llc < %s -mtriple=amdgcn-amd-mesa3d -mcpu=gfx900 -verify-machineinstrs | FileCheck -check-prefix=GFX9 %s
; RUN: llc < %s -mtriple=amdgcn-amd-mesa3d -mcpu=gfx1010 -verify-machineinstrs | FileCheck -check-prefix=GFX10 %s
; ===================================================================================
; V_ADD_LSHL_U32
; ===================================================================================
define amdgpu_ps float @add_shl(i32 %a, i32 %b, i32 %c) {
; VI-LABEL: add_shl:
; VI: ; %bb.0:
; VI-NEXT: v_add_u32_e32 v0, vcc, v0, v1
; VI-NEXT: v_lshlrev_b32_e32 v0, v2, v0
; VI-NEXT: ; return to shader part epilog
;
; GFX9-LABEL: add_shl:
; GFX9: ; %bb.0:
; GFX9-NEXT: v_add_lshl_u32 v0, v0, v1, v2
; GFX9-NEXT: ; return to shader part epilog
;
; GFX10-LABEL: add_shl:
; GFX10: ; %bb.0:
; GFX10-NEXT: v_add_lshl_u32 v0, v0, v1, v2
; GFX10-NEXT: ; implicit-def: $vcc_hi
; GFX10-NEXT: ; return to shader part epilog
%x = add i32 %a, %b
%result = shl i32 %x, %c
%bc = bitcast i32 %result to float
ret float %bc
}
define amdgpu_ps float @add_shl_vgpr_c(i32 inreg %a, i32 inreg %b, i32 %c) {
; VI-LABEL: add_shl_vgpr_c:
; VI: ; %bb.0:
; VI-NEXT: s_add_i32 s2, s2, s3
; VI-NEXT: v_lshlrev_b32_e64 v0, v0, s2
; VI-NEXT: ; return to shader part epilog
;
; GFX9-LABEL: add_shl_vgpr_c:
; GFX9: ; %bb.0:
; GFX9-NEXT: s_add_i32 s2, s2, s3
; GFX9-NEXT: v_lshlrev_b32_e64 v0, v0, s2
; GFX9-NEXT: ; return to shader part epilog
;
; GFX10-LABEL: add_shl_vgpr_c:
; GFX10: ; %bb.0:
; GFX10-NEXT: v_add_lshl_u32 v0, s2, s3, v0
; GFX10-NEXT: ; implicit-def: $vcc_hi
; GFX10-NEXT: ; return to shader part epilog
%x = add i32 %a, %b
%result = shl i32 %x, %c
%bc = bitcast i32 %result to float
ret float %bc
}
define amdgpu_ps float @add_shl_vgpr_ac(i32 %a, i32 inreg %b, i32 %c) {
; VI-LABEL: add_shl_vgpr_ac:
; VI: ; %bb.0:
; VI-NEXT: v_add_u32_e32 v0, vcc, s2, v0
; VI-NEXT: v_lshlrev_b32_e32 v0, v1, v0
; VI-NEXT: ; return to shader part epilog
;
; GFX9-LABEL: add_shl_vgpr_ac:
; GFX9: ; %bb.0:
; GFX9-NEXT: v_add_lshl_u32 v0, v0, s2, v1
; GFX9-NEXT: ; return to shader part epilog
;
; GFX10-LABEL: add_shl_vgpr_ac:
; GFX10: ; %bb.0:
; GFX10-NEXT: v_add_lshl_u32 v0, v0, s2, v1
; GFX10-NEXT: ; implicit-def: $vcc_hi
; GFX10-NEXT: ; return to shader part epilog
%x = add i32 %a, %b
%result = shl i32 %x, %c
%bc = bitcast i32 %result to float
ret float %bc
}
define amdgpu_ps float @add_shl_vgpr_const(i32 %a, i32 %b) {
; VI-LABEL: add_shl_vgpr_const:
; VI: ; %bb.0:
; VI-NEXT: v_add_u32_e32 v0, vcc, v0, v1
; VI-NEXT: v_lshlrev_b32_e32 v0, 9, v0
; VI-NEXT: ; return to shader part epilog
;
; GFX9-LABEL: add_shl_vgpr_const:
; GFX9: ; %bb.0:
; GFX9-NEXT: v_add_lshl_u32 v0, v0, v1, 9
; GFX9-NEXT: ; return to shader part epilog
;
; GFX10-LABEL: add_shl_vgpr_const:
; GFX10: ; %bb.0:
; GFX10-NEXT: v_add_lshl_u32 v0, v0, v1, 9
; GFX10-NEXT: ; implicit-def: $vcc_hi
; GFX10-NEXT: ; return to shader part epilog
%x = add i32 %a, %b
%result = shl i32 %x, 9
%bc = bitcast i32 %result to float
ret float %bc
}
define amdgpu_ps float @add_shl_vgpr_const_inline_const(i32 %a) {
; VI-LABEL: add_shl_vgpr_const_inline_const:
; VI: ; %bb.0:
; VI-NEXT: v_lshlrev_b32_e32 v0, 9, v0
; VI-NEXT: v_add_u32_e32 v0, vcc, 0x7e800, v0
; VI-NEXT: ; return to shader part epilog
;
; GFX9-LABEL: add_shl_vgpr_const_inline_const:
; GFX9: ; %bb.0:
; GFX9-NEXT: v_mov_b32_e32 v1, 0x7e800
; GFX9-NEXT: v_lshl_add_u32 v0, v0, 9, v1
; GFX9-NEXT: ; return to shader part epilog
;
; GFX10-LABEL: add_shl_vgpr_const_inline_const:
; GFX10: ; %bb.0:
; GFX10-NEXT: v_lshl_add_u32 v0, v0, 9, 0x7e800
; GFX10-NEXT: ; implicit-def: $vcc_hi
; GFX10-NEXT: ; return to shader part epilog
%x = add i32 %a, 1012
%result = shl i32 %x, 9
%bc = bitcast i32 %result to float
ret float %bc
}
; TODO: Non-optimal code generation because SelectionDAG combines
; (shl (add x, CONST), y) ---> (add (shl x, y), CONST').
;
define amdgpu_ps float @add_shl_vgpr_inline_const_x2(i32 %a) {
; VI-LABEL: add_shl_vgpr_inline_const_x2:
; VI: ; %bb.0:
; VI-NEXT: v_lshlrev_b32_e32 v0, 9, v0
; VI-NEXT: v_add_u32_e32 v0, vcc, 0x600, v0
; VI-NEXT: ; return to shader part epilog
;
; GFX9-LABEL: add_shl_vgpr_inline_const_x2:
; GFX9: ; %bb.0:
; GFX9-NEXT: v_mov_b32_e32 v1, 0x600
; GFX9-NEXT: v_lshl_add_u32 v0, v0, 9, v1
; GFX9-NEXT: ; return to shader part epilog
;
; GFX10-LABEL: add_shl_vgpr_inline_const_x2:
; GFX10: ; %bb.0:
; GFX10-NEXT: v_lshl_add_u32 v0, v0, 9, 0x600
; GFX10-NEXT: ; implicit-def: $vcc_hi
; GFX10-NEXT: ; return to shader part epilog
%x = add i32 %a, 3
%result = shl i32 %x, 9
%bc = bitcast i32 %result to float
ret float %bc
}