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
| ; RUN: llc -mtriple=amdgcn-mesa-mesa3d -mcpu=tahiti -stop-after finalize-isel -o %t.mir %s
; RUN: llc -run-pass=none -verify-machineinstrs %t.mir -o - | FileCheck %s
; Test that SIMachineFunctionInfo can be round trip serialized through
; MIR.
@lds = addrspace(3) global [512 x float] undef, align 4
; CHECK-LABEL: {{^}}name: kernel
; CHECK: machineFunctionInfo:
; CHECK-NEXT: explicitKernArgSize: 128
; CHECK-NEXT: maxKernArgAlign: 64
; CHECK-NEXT: ldsSize: 0
; CHECK-NEXT: isEntryFunction: true
; CHECK-NEXT: noSignedZerosFPMath: false
; CHECK-NEXT: memoryBound: false
; CHECK-NEXT: waveLimiter: false
; CHECK-NEXT: scratchRSrcReg: '$sgpr96_sgpr97_sgpr98_sgpr99'
; CHECK-NEXT: scratchWaveOffsetReg: '$sgpr101'
; CHECK-NEXT: frameOffsetReg: '$sgpr101'
; CHECK-NEXT: stackPtrOffsetReg: '$sgpr101'
; CHECK-NEXT: argumentInfo:
; CHECK-NEXT: privateSegmentBuffer: { reg: '$sgpr0_sgpr1_sgpr2_sgpr3' }
; CHECK-NEXT: kernargSegmentPtr: { reg: '$sgpr4_sgpr5' }
; CHECK-NEXT: workGroupIDX: { reg: '$sgpr6' }
; CHECK-NEXT: privateSegmentWaveByteOffset: { reg: '$sgpr7' }
; CHECK-NEXT: workItemIDX: { reg: '$vgpr0' }
; CHECK-NEXT: mode:
; CHECK-NEXT: ieee: true
; CHECK-NEXT: dx10-clamp: true
; CHECK-NEXT: highBitsOf32BitAddress: 0
; CHECK-NEXT: body:
define amdgpu_kernel void @kernel(i32 %arg0, i64 %arg1, <16 x i32> %arg2) {
%gep = getelementptr inbounds [512 x float], [512 x float] addrspace(3)* @lds, i32 0, i32 %arg0
store float 0.0, float addrspace(3)* %gep, align 4
ret void
}
; CHECK-LABEL: {{^}}name: ps_shader
; CHECK: machineFunctionInfo:
; CHECK-NEXT: explicitKernArgSize: 0
; CHECK-NEXT: maxKernArgAlign: 1
; CHECK-NEXT: ldsSize: 0
; CHECK-NEXT: isEntryFunction: true
; CHECK-NEXT: noSignedZerosFPMath: false
; CHECK-NEXT: memoryBound: false
; CHECK-NEXT: waveLimiter: false
; CHECK-NEXT: scratchRSrcReg: '$sgpr96_sgpr97_sgpr98_sgpr99'
; CHECK-NEXT: scratchWaveOffsetReg: '$sgpr101'
; CHECK-NEXT: frameOffsetReg: '$sgpr101'
; CHECK-NEXT: stackPtrOffsetReg: '$sgpr101'
; CHECK-NEXT: argumentInfo:
; CHECK-NEXT: privateSegmentWaveByteOffset: { reg: '$sgpr3' }
; CHECK-NEXT: implicitBufferPtr: { reg: '$sgpr0_sgpr1' }
; CHECK-NEXT: mode:
; CHECK-NEXT: ieee: false
; CHECK-NEXT: dx10-clamp: true
; CHECK-NEXT: highBitsOf32BitAddress: 0
; CHECK-NEXT: body:
define amdgpu_ps void @ps_shader(i32 %arg0, i32 inreg %arg1) {
ret void
}
; CHECK-LABEL: {{^}}name: function
; CHECK: machineFunctionInfo:
; CHECK-NEXT: explicitKernArgSize: 0
; CHECK-NEXT: maxKernArgAlign: 1
; CHECK-NEXT: ldsSize: 0
; CHECK-NEXT: isEntryFunction: false
; CHECK-NEXT: noSignedZerosFPMath: false
; CHECK-NEXT: memoryBound: false
; CHECK-NEXT: waveLimiter: false
; CHECK-NEXT: scratchRSrcReg: '$sgpr0_sgpr1_sgpr2_sgpr3'
; CHECK-NEXT: scratchWaveOffsetReg: '$sgpr33'
; CHECK-NEXT: frameOffsetReg: '$sgpr34'
; CHECK-NEXT: stackPtrOffsetReg: '$sgpr32'
; CHECK-NEXT: argumentInfo:
; CHECK-NEXT: privateSegmentBuffer: { reg: '$sgpr0_sgpr1_sgpr2_sgpr3' }
; CHECK-NEXT: privateSegmentWaveByteOffset: { reg: '$sgpr33' }
; CHECK-NEXT: mode:
; CHECK-NEXT: ieee: true
; CHECK-NEXT: dx10-clamp: true
; CHECK-NEXT: highBitsOf32BitAddress: 0
; CHECK-NEXT: body:
define void @function() {
ret void
}
; CHECK-LABEL: {{^}}name: function_nsz
; CHECK: machineFunctionInfo:
; CHECK-NEXT: explicitKernArgSize: 0
; CHECK-NEXT: maxKernArgAlign: 1
; CHECK-NEXT: ldsSize: 0
; CHECK-NEXT: isEntryFunction: false
; CHECK-NEXT: noSignedZerosFPMath: true
; CHECK-NEXT: memoryBound: false
; CHECK-NEXT: waveLimiter: false
; CHECK-NEXT: scratchRSrcReg: '$sgpr0_sgpr1_sgpr2_sgpr3'
; CHECK-NEXT: scratchWaveOffsetReg: '$sgpr33'
; CHECK-NEXT: frameOffsetReg: '$sgpr34'
; CHECK-NEXT: stackPtrOffsetReg: '$sgpr32'
; CHECK-NEXT: argumentInfo:
; CHECK-NEXT: privateSegmentBuffer: { reg: '$sgpr0_sgpr1_sgpr2_sgpr3' }
; CHECK-NEXT: privateSegmentWaveByteOffset: { reg: '$sgpr33' }
; CHECK-NEXT: mode:
; CHECK-NEXT: ieee: true
; CHECK-NEXT: dx10-clamp: true
; CHECK-NEXT: highBitsOf32BitAddress: 0
; CHECK-NEXT: body:
define void @function_nsz() #0 {
ret void
}
; CHECK-LABEL: {{^}}name: function_dx10_clamp_off
; CHECK: mode:
; CHECK-NEXT: ieee: true
; CHECK-NEXT: dx10-clamp: false
define void @function_dx10_clamp_off() #1 {
ret void
}
; CHECK-LABEL: {{^}}name: function_ieee_off
; CHECK: mode:
; CHECK-NEXT: ieee: false
; CHECK-NEXT: dx10-clamp: true
define void @function_ieee_off() #2 {
ret void
}
; CHECK-LABEL: {{^}}name: function_ieee_off_dx10_clamp_off
; CHECK: mode:
; CHECK-NEXT: ieee: false
; CHECK-NEXT: dx10-clamp: false
define void @function_ieee_off_dx10_clamp_off() #3 {
ret void
}
; CHECK-LABEL: {{^}}name: high_address_bits
; CHECK: machineFunctionInfo:
; CHECK: highBitsOf32BitAddress: 4294934528
define amdgpu_ps void @high_address_bits() #4 {
ret void
}
attributes #0 = { "no-signed-zeros-fp-math" = "true" }
attributes #1 = { "amdgpu-dx10-clamp" = "false" }
attributes #2 = { "amdgpu-ieee" = "false" }
attributes #3 = { "amdgpu-dx10-clamp" = "false" "amdgpu-ieee" = "false" }
attributes #4 = { "amdgpu-32bit-address-high-bits"="0xffff8000" }
|