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
153
154
155
156
157
158
159
160
161
162
163
164
165
|
; RUN: llc < %s -march=amdgcn -show-mc-encoding -verify-machineinstrs | FileCheck --check-prefix=SI --check-prefix=GCN --check-prefix=SIVI %s
; RUN: llc < %s -march=amdgcn -mcpu=bonaire -show-mc-encoding -verify-machineinstrs | FileCheck --check-prefix=CI --check-prefix=GCN %s
; RUN: llc < %s -march=amdgcn -mcpu=tonga -show-mc-encoding -verify-machineinstrs | FileCheck --check-prefix=VI --check-prefix=GCN --check-prefix=SIVI %s
; SMRD load with an immediate offset.
; GCN-LABEL: {{^}}smrd0:
; SICI: s_load_dword s{{[0-9]}}, s[{{[0-9]:[0-9]}}], 0x1 ; encoding: [0x01
; VI: s_load_dword s{{[0-9]}}, s[{{[0-9]:[0-9]}}], 0x4
define void @smrd0(i32 addrspace(1)* %out, i32 addrspace(2)* %ptr) {
entry:
%0 = getelementptr i32, i32 addrspace(2)* %ptr, i64 1
%1 = load i32, i32 addrspace(2)* %0
store i32 %1, i32 addrspace(1)* %out
ret void
}
; SMRD load with the largest possible immediate offset.
; GCN-LABEL: {{^}}smrd1:
; SICI: s_load_dword s{{[0-9]}}, s[{{[0-9]:[0-9]}}], 0xff ; encoding: [0xff,0x{{[0-9]+[137]}}
; VI: s_load_dword s{{[0-9]}}, s[{{[0-9]:[0-9]}}], 0x3fc
define void @smrd1(i32 addrspace(1)* %out, i32 addrspace(2)* %ptr) {
entry:
%0 = getelementptr i32, i32 addrspace(2)* %ptr, i64 255
%1 = load i32, i32 addrspace(2)* %0
store i32 %1, i32 addrspace(1)* %out
ret void
}
; SMRD load with an offset greater than the largest possible immediate.
; GCN-LABEL: {{^}}smrd2:
; SI: s_movk_i32 s[[OFFSET:[0-9]]], 0x400
; SI: s_load_dword s{{[0-9]}}, s[{{[0-9]:[0-9]}}], s[[OFFSET]] ; encoding: [0x0[[OFFSET]]
; CI: s_load_dword s{{[0-9]}}, s[{{[0-9]:[0-9]}}], 0x100
; VI: s_load_dword s{{[0-9]}}, s[{{[0-9]:[0-9]}}], 0x400
; GCN: s_endpgm
define void @smrd2(i32 addrspace(1)* %out, i32 addrspace(2)* %ptr) {
entry:
%0 = getelementptr i32, i32 addrspace(2)* %ptr, i64 256
%1 = load i32, i32 addrspace(2)* %0
store i32 %1, i32 addrspace(1)* %out
ret void
}
; SMRD load with a 64-bit offset
; GCN-LABEL: {{^}}smrd3:
; FIXME: There are too many copies here because we don't fold immediates
; through REG_SEQUENCE
; SI: s_load_dwordx2 s[{{[0-9]:[0-9]}}], s[{{[0-9]:[0-9]}}], 0xb ; encoding: [0x0b
; TODO: Add VI checks
; GCN: s_endpgm
define void @smrd3(i32 addrspace(1)* %out, i32 addrspace(2)* %ptr) {
entry:
%0 = getelementptr i32, i32 addrspace(2)* %ptr, i64 4294967296 ; 2 ^ 32
%1 = load i32, i32 addrspace(2)* %0
store i32 %1, i32 addrspace(1)* %out
ret void
}
; SMRD load with the largest possible immediate offset on VI
; GCN-LABEL: {{^}}smrd4:
; SI: s_mov_b32 [[OFFSET:s[0-9]+]], 0xffffc
; SI: s_load_dword s{{[0-9]}}, s[{{[0-9]:[0-9]}}], [[OFFSET]]
; CI: s_load_dword s{{[0-9]}}, s[{{[0-9]:[0-9]}}], 0x3ffff
; VI: s_load_dword s{{[0-9]}}, s[{{[0-9]:[0-9]}}], 0xffffc
define void @smrd4(i32 addrspace(1)* %out, i32 addrspace(2)* %ptr) {
entry:
%0 = getelementptr i32, i32 addrspace(2)* %ptr, i64 262143
%1 = load i32, i32 addrspace(2)* %0
store i32 %1, i32 addrspace(1)* %out
ret void
}
; SMRD load with an offset greater than the largest possible immediate on VI
; GCN-LABEL: {{^}}smrd5:
; SIVI: s_mov_b32 [[OFFSET:s[0-9]+]], 0x100000
; SIVI: s_load_dword s{{[0-9]}}, s[{{[0-9]:[0-9]}}], [[OFFSET]]
; CI: s_load_dword s{{[0-9]}}, s[{{[0-9]:[0-9]}}], 0x40000
; GCN: s_endpgm
define void @smrd5(i32 addrspace(1)* %out, i32 addrspace(2)* %ptr) {
entry:
%0 = getelementptr i32, i32 addrspace(2)* %ptr, i64 262144
%1 = load i32, i32 addrspace(2)* %0
store i32 %1, i32 addrspace(1)* %out
ret void
}
; SMRD load using the load.const intrinsic with an immediate offset
; GCN-LABEL: {{^}}smrd_load_const0:
; SICI: s_buffer_load_dword s{{[0-9]}}, s[{{[0-9]:[0-9]}}], 0x4 ; encoding: [0x04
; VI: s_buffer_load_dword s{{[0-9]}}, s[{{[0-9]:[0-9]}}], 0x10
define amdgpu_ps void @smrd_load_const0(<16 x i8> addrspace(2)* inreg, <16 x i8> addrspace(2)* inreg, <32 x i8> addrspace(2)* inreg, i32 inreg, <2 x i32>, <2 x i32>, <2 x i32>, <3 x i32>, <2 x i32>, <2 x i32>, <2 x i32>, float, float, float, float, float, float, float, float, float) {
main_body:
%20 = getelementptr <16 x i8>, <16 x i8> addrspace(2)* %0, i32 0
%21 = load <16 x i8>, <16 x i8> addrspace(2)* %20
%22 = call float @llvm.SI.load.const(<16 x i8> %21, i32 16)
call void @llvm.SI.export(i32 15, i32 1, i32 1, i32 0, i32 0, float %22, float %22, float %22, float %22)
ret void
}
; SMRD load using the load.const intrinsic with the largest possible immediate
; offset.
; GCN-LABEL: {{^}}smrd_load_const1:
; SICI: s_buffer_load_dword s{{[0-9]}}, s[{{[0-9]:[0-9]}}], 0xff ; encoding: [0xff
; VI: s_buffer_load_dword s{{[0-9]}}, s[{{[0-9]:[0-9]}}], 0x3fc
define amdgpu_ps void @smrd_load_const1(<16 x i8> addrspace(2)* inreg, <16 x i8> addrspace(2)* inreg, <32 x i8> addrspace(2)* inreg, i32 inreg, <2 x i32>, <2 x i32>, <2 x i32>, <3 x i32>, <2 x i32>, <2 x i32>, <2 x i32>, float, float, float, float, float, float, float, float, float) {
main_body:
%20 = getelementptr <16 x i8>, <16 x i8> addrspace(2)* %0, i32 0
%21 = load <16 x i8>, <16 x i8> addrspace(2)* %20
%22 = call float @llvm.SI.load.const(<16 x i8> %21, i32 1020)
call void @llvm.SI.export(i32 15, i32 1, i32 1, i32 0, i32 0, float %22, float %22, float %22, float %22)
ret void
}
; SMRD load using the load.const intrinsic with an offset greater than the
; largets possible immediate.
; immediate offset.
; GCN-LABEL: {{^}}smrd_load_const2:
; SI: s_movk_i32 s[[OFFSET:[0-9]]], 0x400
; SI: s_buffer_load_dword s{{[0-9]}}, s[{{[0-9]:[0-9]}}], s[[OFFSET]] ; encoding: [0x0[[OFFSET]]
; CI: s_buffer_load_dword s{{[0-9]}}, s[{{[0-9]:[0-9]}}], 0x100
; VI: s_buffer_load_dword s{{[0-9]}}, s[{{[0-9]:[0-9]}}], 0x400
define amdgpu_ps void @smrd_load_const2(<16 x i8> addrspace(2)* inreg, <16 x i8> addrspace(2)* inreg, <32 x i8> addrspace(2)* inreg, i32 inreg, <2 x i32>, <2 x i32>, <2 x i32>, <3 x i32>, <2 x i32>, <2 x i32>, <2 x i32>, float, float, float, float, float, float, float, float, float) {
main_body:
%20 = getelementptr <16 x i8>, <16 x i8> addrspace(2)* %0, i32 0
%21 = load <16 x i8>, <16 x i8> addrspace(2)* %20
%22 = call float @llvm.SI.load.const(<16 x i8> %21, i32 1024)
call void @llvm.SI.export(i32 15, i32 1, i32 1, i32 0, i32 0, float %22, float %22, float %22, float %22)
ret void
}
; SMRD load with the largest possible immediate offset on VI
; GCN-LABEL: {{^}}smrd_load_const3:
; SI: s_mov_b32 [[OFFSET:s[0-9]+]], 0xffffc
; SI: s_buffer_load_dword s{{[0-9]}}, s[{{[0-9]:[0-9]}}], [[OFFSET]]
; CI: s_buffer_load_dword s{{[0-9]}}, s[{{[0-9]:[0-9]}}], 0x3ffff
; VI: s_buffer_load_dword s{{[0-9]}}, s[{{[0-9]:[0-9]}}], 0xffffc
define amdgpu_ps void @smrd_load_const3(<16 x i8> addrspace(2)* inreg, <16 x i8> addrspace(2)* inreg, <32 x i8> addrspace(2)* inreg, i32 inreg, <2 x i32>, <2 x i32>, <2 x i32>, <3 x i32>, <2 x i32>, <2 x i32>, <2 x i32>, float, float, float, float, float, float, float, float, float) {
main_body:
%20 = getelementptr <16 x i8>, <16 x i8> addrspace(2)* %0, i32 0
%21 = load <16 x i8>, <16 x i8> addrspace(2)* %20
%22 = call float @llvm.SI.load.const(<16 x i8> %21, i32 1048572)
call void @llvm.SI.export(i32 15, i32 1, i32 1, i32 0, i32 0, float %22, float %22, float %22, float %22)
ret void
}
; SMRD load with an offset greater than the largest possible immediate on VI
; GCN-LABEL: {{^}}smrd_load_const4:
; SIVI: s_mov_b32 [[OFFSET:s[0-9]+]], 0x100000
; SIVI: s_buffer_load_dword s{{[0-9]}}, s[{{[0-9]:[0-9]}}], [[OFFSET]]
; CI: s_buffer_load_dword s{{[0-9]}}, s[{{[0-9]:[0-9]}}], 0x40000
; GCN: s_endpgm
define amdgpu_ps void @smrd_load_const4(<16 x i8> addrspace(2)* inreg, <16 x i8> addrspace(2)* inreg, <32 x i8> addrspace(2)* inreg, i32 inreg, <2 x i32>, <2 x i32>, <2 x i32>, <3 x i32>, <2 x i32>, <2 x i32>, <2 x i32>, float, float, float, float, float, float, float, float, float) {
main_body:
%20 = getelementptr <16 x i8>, <16 x i8> addrspace(2)* %0, i32 0
%21 = load <16 x i8>, <16 x i8> addrspace(2)* %20
%22 = call float @llvm.SI.load.const(<16 x i8> %21, i32 1048576)
call void @llvm.SI.export(i32 15, i32 1, i32 1, i32 0, i32 0, float %22, float %22, float %22, float %22)
ret void
}
; Function Attrs: nounwind readnone
declare float @llvm.SI.load.const(<16 x i8>, i32) #0
declare void @llvm.SI.export(i32, i32, i32, i32, i32, float, float, float, float)
attributes #0 = { nounwind readnone }
|
