File: AMDGPUCallingConv.td

package info (click to toggle)
llvm-toolchain-14 1%3A14.0.6-20
  • links: PTS, VCS
  • area: main
  • in suites: sid
  • size: 1,496,436 kB
  • sloc: cpp: 5,593,990; ansic: 986,873; asm: 585,869; python: 184,223; objc: 72,530; lisp: 31,119; f90: 27,793; javascript: 9,780; pascal: 9,762; sh: 9,482; perl: 7,468; ml: 5,432; awk: 3,523; makefile: 2,547; xml: 953; cs: 573; fortran: 567
file content (235 lines) | stat: -rw-r--r-- 10,293 bytes parent folder | download | duplicates (3)
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
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
//===---- AMDCallingConv.td - Calling Conventions for Radeon GPUs ---------===//
//
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
// See https://llvm.org/LICENSE.txt for license information.
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
//
//===----------------------------------------------------------------------===//
//
// This describes the calling conventions for the AMD Radeon GPUs.
//
//===----------------------------------------------------------------------===//

// Inversion of CCIfInReg
class CCIfNotInReg<CCAction A> : CCIf<"!ArgFlags.isInReg()", A> {}
class CCIfExtend<CCAction A>
  : CCIf<"ArgFlags.isSExt() || ArgFlags.isZExt()", A>;

// Calling convention for SI
def CC_SI_Gfx : CallingConv<[
  // 0-3 are reserved for the stack buffer descriptor
  // 30-31 are reserved for the return address
  // 32 is reserved for the stack pointer
  // 33 is reserved for the frame pointer
  // 34 is reserved for the base pointer
  CCIfInReg<CCIfType<[f32, i32, f16, i16, v2i16, v2f16] , CCAssignToReg<[
    SGPR4, SGPR5, SGPR6, SGPR7,
    SGPR8, SGPR9, SGPR10, SGPR11, SGPR12, SGPR13, SGPR14, SGPR15,
    SGPR16, SGPR17, SGPR18, SGPR19, SGPR20, SGPR21, SGPR22, SGPR23,
    SGPR24, SGPR25, SGPR26, SGPR27, SGPR28, SGPR29
  ]>>>,

  CCIfNotInReg<CCIfType<[f32, i32, f16, i16, v2i16, v2f16] , CCAssignToReg<[
    VGPR0, VGPR1, VGPR2, VGPR3, VGPR4, VGPR5, VGPR6, VGPR7,
    VGPR8, VGPR9, VGPR10, VGPR11, VGPR12, VGPR13, VGPR14, VGPR15,
    VGPR16, VGPR17, VGPR18, VGPR19, VGPR20, VGPR21, VGPR22, VGPR23,
    VGPR24, VGPR25, VGPR26, VGPR27, VGPR28, VGPR29, VGPR30, VGPR31
  ]>>>,

  CCIfType<[i32, f32, v2i16, v2f16, i16, f16, i1], CCAssignToStack<4, 4>>
]>;

def RetCC_SI_Gfx : CallingConv<[
  CCIfType<[i1], CCPromoteToType<i32>>,
  CCIfType<[i1, i16], CCIfExtend<CCPromoteToType<i32>>>,

  CCIfNotInReg<CCIfType<[f32, i32, f16, i16, v2i16, v2f16] , CCAssignToReg<[
    VGPR0, VGPR1, VGPR2, VGPR3, VGPR4, VGPR5, VGPR6, VGPR7,
    VGPR8, VGPR9, VGPR10, VGPR11, VGPR12, VGPR13, VGPR14, VGPR15,
    VGPR16, VGPR17, VGPR18, VGPR19, VGPR20, VGPR21, VGPR22, VGPR23,
    VGPR24, VGPR25, VGPR26, VGPR27, VGPR28, VGPR29, VGPR30, VGPR31,
    VGPR32, VGPR33, VGPR34, VGPR35, VGPR36, VGPR37, VGPR38, VGPR39,
    VGPR40, VGPR41, VGPR42, VGPR43, VGPR44, VGPR45, VGPR46, VGPR47,
    VGPR48, VGPR49, VGPR50, VGPR51, VGPR52, VGPR53, VGPR54, VGPR55,
    VGPR56, VGPR57, VGPR58, VGPR59, VGPR60, VGPR61, VGPR62, VGPR63,
    VGPR64, VGPR65, VGPR66, VGPR67, VGPR68, VGPR69, VGPR70, VGPR71,
    VGPR72, VGPR73, VGPR74, VGPR75, VGPR76, VGPR77, VGPR78, VGPR79,
    VGPR80, VGPR81, VGPR82, VGPR83, VGPR84, VGPR85, VGPR86, VGPR87,
    VGPR88, VGPR89, VGPR90, VGPR91, VGPR92, VGPR93, VGPR94, VGPR95,
    VGPR96, VGPR97, VGPR98, VGPR99, VGPR100, VGPR101, VGPR102, VGPR103,
    VGPR104, VGPR105, VGPR106, VGPR107, VGPR108, VGPR109, VGPR110, VGPR111,
    VGPR112, VGPR113, VGPR114, VGPR115, VGPR116, VGPR117, VGPR118, VGPR119,
    VGPR120, VGPR121, VGPR122, VGPR123, VGPR124, VGPR125, VGPR126, VGPR127,
    VGPR128, VGPR129, VGPR130, VGPR131, VGPR132, VGPR133, VGPR134, VGPR135
  ]>>>,
]>;

def CC_SI_SHADER : CallingConv<[

  CCIfInReg<CCIfType<[f32, i32, f16, i16, v2i16, v2f16] , CCAssignToReg<[
    SGPR0, SGPR1, SGPR2, SGPR3, SGPR4, SGPR5, SGPR6, SGPR7,
    SGPR8, SGPR9, SGPR10, SGPR11, SGPR12, SGPR13, SGPR14, SGPR15,
    SGPR16, SGPR17, SGPR18, SGPR19, SGPR20, SGPR21, SGPR22, SGPR23,
    SGPR24, SGPR25, SGPR26, SGPR27, SGPR28, SGPR29, SGPR30, SGPR31,
    SGPR32, SGPR33, SGPR34, SGPR35, SGPR36, SGPR37, SGPR38, SGPR39,
    SGPR40, SGPR41, SGPR42, SGPR43
  ]>>>,

  // 32*4 + 4 is the minimum for a fetch shader consumer with 32 inputs.
  CCIfNotInReg<CCIfType<[f32, i32, f16, i16, v2i16, v2f16] , CCAssignToReg<[
    VGPR0, VGPR1, VGPR2, VGPR3, VGPR4, VGPR5, VGPR6, VGPR7,
    VGPR8, VGPR9, VGPR10, VGPR11, VGPR12, VGPR13, VGPR14, VGPR15,
    VGPR16, VGPR17, VGPR18, VGPR19, VGPR20, VGPR21, VGPR22, VGPR23,
    VGPR24, VGPR25, VGPR26, VGPR27, VGPR28, VGPR29, VGPR30, VGPR31,
    VGPR32, VGPR33, VGPR34, VGPR35, VGPR36, VGPR37, VGPR38, VGPR39,
    VGPR40, VGPR41, VGPR42, VGPR43, VGPR44, VGPR45, VGPR46, VGPR47,
    VGPR48, VGPR49, VGPR50, VGPR51, VGPR52, VGPR53, VGPR54, VGPR55,
    VGPR56, VGPR57, VGPR58, VGPR59, VGPR60, VGPR61, VGPR62, VGPR63,
    VGPR64, VGPR65, VGPR66, VGPR67, VGPR68, VGPR69, VGPR70, VGPR71,
    VGPR72, VGPR73, VGPR74, VGPR75, VGPR76, VGPR77, VGPR78, VGPR79,
    VGPR80, VGPR81, VGPR82, VGPR83, VGPR84, VGPR85, VGPR86, VGPR87,
    VGPR88, VGPR89, VGPR90, VGPR91, VGPR92, VGPR93, VGPR94, VGPR95,
    VGPR96, VGPR97, VGPR98, VGPR99, VGPR100, VGPR101, VGPR102, VGPR103,
    VGPR104, VGPR105, VGPR106, VGPR107, VGPR108, VGPR109, VGPR110, VGPR111,
    VGPR112, VGPR113, VGPR114, VGPR115, VGPR116, VGPR117, VGPR118, VGPR119,
    VGPR120, VGPR121, VGPR122, VGPR123, VGPR124, VGPR125, VGPR126, VGPR127,
    VGPR128, VGPR129, VGPR130, VGPR131, VGPR132, VGPR133, VGPR134, VGPR135
  ]>>>
]>;

def RetCC_SI_Shader : CallingConv<[
  CCIfType<[i1, i16], CCIfExtend<CCPromoteToType<i32>>>,
  CCIfType<[i32, i16] , CCAssignToReg<[
    SGPR0, SGPR1, SGPR2, SGPR3, SGPR4, SGPR5, SGPR6, SGPR7,
    SGPR8, SGPR9, SGPR10, SGPR11, SGPR12, SGPR13, SGPR14, SGPR15,
    SGPR16, SGPR17, SGPR18, SGPR19, SGPR20, SGPR21, SGPR22, SGPR23,
    SGPR24, SGPR25, SGPR26, SGPR27, SGPR28, SGPR29, SGPR30, SGPR31,
    SGPR32, SGPR33, SGPR34, SGPR35, SGPR36, SGPR37, SGPR38, SGPR39,
    SGPR40, SGPR41, SGPR42, SGPR43
  ]>>,

  // 32*4 + 4 is the minimum for a fetch shader with 32 outputs.
  CCIfType<[f32, f16, v2f16] , CCAssignToReg<[
    VGPR0, VGPR1, VGPR2, VGPR3, VGPR4, VGPR5, VGPR6, VGPR7,
    VGPR8, VGPR9, VGPR10, VGPR11, VGPR12, VGPR13, VGPR14, VGPR15,
    VGPR16, VGPR17, VGPR18, VGPR19, VGPR20, VGPR21, VGPR22, VGPR23,
    VGPR24, VGPR25, VGPR26, VGPR27, VGPR28, VGPR29, VGPR30, VGPR31,
    VGPR32, VGPR33, VGPR34, VGPR35, VGPR36, VGPR37, VGPR38, VGPR39,
    VGPR40, VGPR41, VGPR42, VGPR43, VGPR44, VGPR45, VGPR46, VGPR47,
    VGPR48, VGPR49, VGPR50, VGPR51, VGPR52, VGPR53, VGPR54, VGPR55,
    VGPR56, VGPR57, VGPR58, VGPR59, VGPR60, VGPR61, VGPR62, VGPR63,
    VGPR64, VGPR65, VGPR66, VGPR67, VGPR68, VGPR69, VGPR70, VGPR71,
    VGPR72, VGPR73, VGPR74, VGPR75, VGPR76, VGPR77, VGPR78, VGPR79,
    VGPR80, VGPR81, VGPR82, VGPR83, VGPR84, VGPR85, VGPR86, VGPR87,
    VGPR88, VGPR89, VGPR90, VGPR91, VGPR92, VGPR93, VGPR94, VGPR95,
    VGPR96, VGPR97, VGPR98, VGPR99, VGPR100, VGPR101, VGPR102, VGPR103,
    VGPR104, VGPR105, VGPR106, VGPR107, VGPR108, VGPR109, VGPR110, VGPR111,
    VGPR112, VGPR113, VGPR114, VGPR115, VGPR116, VGPR117, VGPR118, VGPR119,
    VGPR120, VGPR121, VGPR122, VGPR123, VGPR124, VGPR125, VGPR126, VGPR127,
    VGPR128, VGPR129, VGPR130, VGPR131, VGPR132, VGPR133, VGPR134, VGPR135
  ]>>
]>;

def CSR_AMDGPU_VGPRs : CalleeSavedRegs<
  // The CSRs & scratch-registers are interleaved at a split boundary of 8.
  (add (sequence "VGPR%u", 40, 47),
    (sequence "VGPR%u", 56, 63),
    (sequence "VGPR%u", 72, 79),
    (sequence "VGPR%u", 88, 95),
    (sequence "VGPR%u", 104, 111),
    (sequence "VGPR%u", 120, 127),
    (sequence "VGPR%u", 136, 143),
    (sequence "VGPR%u", 152, 159),
    (sequence "VGPR%u", 168, 175),
    (sequence "VGPR%u", 184, 191),
    (sequence "VGPR%u", 200, 207),
    (sequence "VGPR%u", 216, 223),
    (sequence "VGPR%u", 232, 239),
    (sequence "VGPR%u", 248, 255))
>;

def CSR_AMDGPU_AGPRs_32_255 : CalleeSavedRegs<
  (sequence "AGPR%u", 32, 255)
>;

def CSR_AMDGPU_SGPRs_32_105 : CalleeSavedRegs<
  (sequence "SGPR%u", 32, 105)
>;

def CSR_AMDGPU_SI_Gfx_SGPRs_4_29 : CalleeSavedRegs<
  (sequence "SGPR%u", 4, 29)
>;

def CSR_AMDGPU_SI_Gfx_SGPRs_64_105 : CalleeSavedRegs<
  (sequence "SGPR%u", 64, 105)
>;

// Just to get the regmask, not for calling convention purposes.
def CSR_AMDGPU_AllVGPRs : CalleeSavedRegs<
  (sequence "VGPR%u", 0, 255)
>;

def CSR_AMDGPU_AllAGPRs : CalleeSavedRegs<
  (sequence "AGPR%u", 0, 255)
>;
def CSR_AMDGPU_AllVectorRegs : CalleeSavedRegs<
  (add CSR_AMDGPU_AllVGPRs, CSR_AMDGPU_AllAGPRs)
>;

// Just to get the regmask, not for calling convention purposes.
def CSR_AMDGPU_AllAllocatableSRegs : CalleeSavedRegs<
  (add (sequence "SGPR%u", 0, 105), VCC_LO, VCC_HI)
>;

def CSR_AMDGPU_HighRegs : CalleeSavedRegs<
  (add CSR_AMDGPU_VGPRs, CSR_AMDGPU_SGPRs_32_105)
>;

def CSR_AMDGPU_HighRegs_With_AGPRs : CalleeSavedRegs<
  (add CSR_AMDGPU_HighRegs, CSR_AMDGPU_AGPRs_32_255)
>;

def CSR_AMDGPU_SI_Gfx : CalleeSavedRegs<
  (add CSR_AMDGPU_VGPRs, CSR_AMDGPU_SI_Gfx_SGPRs_4_29, CSR_AMDGPU_SI_Gfx_SGPRs_64_105)
>;

def CSR_AMDGPU_SI_Gfx_With_AGPRs : CalleeSavedRegs<
  (add CSR_AMDGPU_SI_Gfx, CSR_AMDGPU_AGPRs_32_255)
>;

def CSR_AMDGPU_NoRegs : CalleeSavedRegs<(add)>;

// Calling convention for leaf functions
def CC_AMDGPU_Func : CallingConv<[
  CCIfByVal<CCPassByVal<4, 4>>,
  CCIfType<[i1], CCPromoteToType<i32>>,
  CCIfType<[i8, i16], CCIfExtend<CCPromoteToType<i32>>>,
  CCIfType<[i32, f32, i16, f16, v2i16, v2f16, i1], CCAssignToReg<[
    VGPR0, VGPR1, VGPR2, VGPR3, VGPR4, VGPR5, VGPR6, VGPR7,
    VGPR8, VGPR9, VGPR10, VGPR11, VGPR12, VGPR13, VGPR14, VGPR15,
    VGPR16, VGPR17, VGPR18, VGPR19, VGPR20, VGPR21, VGPR22, VGPR23,
    VGPR24, VGPR25, VGPR26, VGPR27, VGPR28, VGPR29, VGPR30, VGPR31]>>,
  CCIfType<[i32, f32, v2i16, v2f16, i16, f16, i1], CCAssignToStack<4, 4>>
]>;

// Calling convention for leaf functions
def RetCC_AMDGPU_Func : CallingConv<[
  CCIfType<[i1], CCPromoteToType<i32>>,
  CCIfType<[i1, i16], CCIfExtend<CCPromoteToType<i32>>>,
  CCIfType<[i32, f32, i16, f16, v2i16, v2f16], CCAssignToReg<[
    VGPR0, VGPR1, VGPR2, VGPR3, VGPR4, VGPR5, VGPR6, VGPR7,
    VGPR8, VGPR9, VGPR10, VGPR11, VGPR12, VGPR13, VGPR14, VGPR15,
    VGPR16, VGPR17, VGPR18, VGPR19, VGPR20, VGPR21, VGPR22, VGPR23,
    VGPR24, VGPR25, VGPR26, VGPR27, VGPR28, VGPR29, VGPR30, VGPR31]>>,
]>;

def CC_AMDGPU : CallingConv<[
   CCIf<"static_cast<const GCNSubtarget&>"
         "(State.getMachineFunction().getSubtarget()).getGeneration() >= "
           "AMDGPUSubtarget::SOUTHERN_ISLANDS",
        CCDelegateTo<CC_SI_SHADER>>,
   CCIf<"static_cast<const GCNSubtarget&>"
         "(State.getMachineFunction().getSubtarget()).getGeneration() >= "
           "AMDGPUSubtarget::SOUTHERN_ISLANDS && State.getCallingConv() == CallingConv::C",
        CCDelegateTo<CC_AMDGPU_Func>>
]>;