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
|
/*
* Copyright 2016 Advanced Micro Devices, Inc.
*
* Permission is hereby granted, free of charge, to any person obtaining a
* copy of this software and associated documentation files (the "Software"),
* to deal in the Software without restriction, including without limitation
* on the rights to use, copy, modify, merge, publish, distribute, sub
* license, and/or sell copies of the Software, and to permit persons to whom
* the Software is furnished to do so, subject to the following conditions:
*
* The above copyright notice and this permission notice (including the next
* paragraph) shall be included in all copies or substantial portions of the
* Software.
*
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
* IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
* FITNESS FOR A PARTICULAR PURPOSE AND NON-INFRINGEMENT. IN NO EVENT SHALL
* THE AUTHOR(S) AND/OR THEIR SUPPLIERS BE LIABLE FOR ANY CLAIM,
* DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR
* OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE
* USE OR OTHER DEALINGS IN THE SOFTWARE.
*/
#ifndef SI_SHADER_PRIVATE_H
#define SI_SHADER_PRIVATE_H
#include "si_shader.h"
#include "gallivm/lp_bld_init.h"
#include "gallivm/lp_bld_tgsi.h"
#include "tgsi/tgsi_parse.h"
#include <llvm-c/Core.h>
#include <llvm-c/TargetMachine.h>
struct pipe_debug_callback;
struct radeon_shader_binary;
#define RADEON_LLVM_MAX_INPUT_SLOTS 32
#define RADEON_LLVM_MAX_INPUTS 32 * 4
#define RADEON_LLVM_MAX_OUTPUTS 32 * 4
#define RADEON_LLVM_INITIAL_CF_DEPTH 4
#define RADEON_LLVM_MAX_SYSTEM_VALUES 4
struct si_llvm_flow;
struct si_shader_context {
struct lp_build_tgsi_soa_context soa;
struct gallivm_state gallivm;
struct si_shader *shader;
struct si_screen *screen;
unsigned type; /* PIPE_SHADER_* specifies the type of shader. */
bool is_gs_copy_shader;
/* Whether to generate the optimized shader variant compiled as a whole
* (without a prolog and epilog)
*/
bool is_monolithic;
/** This function is responsible for initilizing the inputs array and will be
* called once for each input declared in the TGSI shader.
*/
void (*load_input)(struct si_shader_context *,
unsigned input_index,
const struct tgsi_full_declaration *decl,
LLVMValueRef out[4]);
void (*load_system_value)(struct si_shader_context *,
unsigned index,
const struct tgsi_full_declaration *decl);
void (*declare_memory_region)(struct si_shader_context *,
const struct tgsi_full_declaration *decl);
/** This array contains the input values for the shader. Typically these
* values will be in the form of a target intrinsic that will inform the
* backend how to load the actual inputs to the shader.
*/
struct tgsi_full_declaration input_decls[RADEON_LLVM_MAX_INPUT_SLOTS];
LLVMValueRef inputs[RADEON_LLVM_MAX_INPUTS];
LLVMValueRef outputs[RADEON_LLVM_MAX_OUTPUTS][TGSI_NUM_CHANNELS];
/** This pointer is used to contain the temporary values.
* The amount of temporary used in tgsi can't be bound to a max value and
* thus we must allocate this array at runtime.
*/
LLVMValueRef *temps;
unsigned temps_count;
LLVMValueRef system_values[RADEON_LLVM_MAX_SYSTEM_VALUES];
struct si_llvm_flow *flow;
unsigned flow_depth;
unsigned flow_depth_max;
struct tgsi_array_info *temp_arrays;
LLVMValueRef *temp_array_allocas;
LLVMValueRef undef_alloca;
LLVMValueRef main_fn;
LLVMTypeRef return_type;
int param_streamout_config;
int param_streamout_write_index;
int param_streamout_offset[4];
int param_vertex_id;
int param_rel_auto_id;
int param_vs_prim_id;
int param_instance_id;
int param_vertex_index0;
int param_tes_u;
int param_tes_v;
int param_tes_rel_patch_id;
int param_tes_patch_id;
int param_es2gs_offset;
int param_oc_lds;
/* Sets a bit if the dynamic HS control word was 0x80000000. The bit is
* 0x800000 for VS, 0x1 for ES.
*/
int param_tess_offchip;
LLVMTargetMachineRef tm;
unsigned invariant_load_md_kind;
unsigned range_md_kind;
unsigned uniform_md_kind;
unsigned fpmath_md_kind;
LLVMValueRef fpmath_md_2p5_ulp;
LLVMValueRef empty_md;
/* Preloaded descriptors. */
LLVMValueRef esgs_ring;
LLVMValueRef gsvs_ring[4];
LLVMValueRef lds;
LLVMValueRef gs_next_vertex[4];
LLVMValueRef return_value;
LLVMTypeRef voidt;
LLVMTypeRef i1;
LLVMTypeRef i8;
LLVMTypeRef i32;
LLVMTypeRef i64;
LLVMTypeRef i128;
LLVMTypeRef f32;
LLVMTypeRef v16i8;
LLVMTypeRef v2i32;
LLVMTypeRef v4i32;
LLVMTypeRef v4f32;
LLVMTypeRef v8i32;
LLVMValueRef shared_memory;
};
static inline struct si_shader_context *
si_shader_context(struct lp_build_tgsi_context *bld_base)
{
return (struct si_shader_context*)bld_base;
}
void si_llvm_add_attribute(LLVMValueRef F, const char *name, int value);
void si_llvm_shader_type(LLVMValueRef F, unsigned type);
LLVMTargetRef si_llvm_get_amdgpu_target(const char *triple);
unsigned si_llvm_compile(LLVMModuleRef M, struct radeon_shader_binary *binary,
LLVMTargetMachineRef tm,
struct pipe_debug_callback *debug);
LLVMTypeRef tgsi2llvmtype(struct lp_build_tgsi_context *bld_base,
enum tgsi_opcode_type type);
LLVMValueRef bitcast(struct lp_build_tgsi_context *bld_base,
enum tgsi_opcode_type type, LLVMValueRef value);
LLVMValueRef si_llvm_bound_index(struct si_shader_context *ctx,
LLVMValueRef index,
unsigned num);
void si_llvm_context_init(struct si_shader_context *ctx,
const char *triple,
const struct tgsi_shader_info *info,
const struct tgsi_token *tokens);
void si_llvm_create_func(struct si_shader_context *ctx,
LLVMTypeRef *return_types, unsigned num_return_elems,
LLVMTypeRef *ParamTypes, unsigned ParamCount);
void si_llvm_dispose(struct si_shader_context *ctx);
void si_llvm_finalize_module(struct si_shader_context *ctx,
bool run_verifier);
LLVMValueRef si_llvm_emit_fetch_64bit(struct lp_build_tgsi_context *bld_base,
enum tgsi_opcode_type type,
LLVMValueRef ptr,
LLVMValueRef ptr2);
LLVMValueRef si_llvm_saturate(struct lp_build_tgsi_context *bld_base,
LLVMValueRef value);
LLVMValueRef si_llvm_emit_fetch(struct lp_build_tgsi_context *bld_base,
const struct tgsi_full_src_register *reg,
enum tgsi_opcode_type type,
unsigned swizzle);
void si_llvm_emit_store(struct lp_build_tgsi_context *bld_base,
const struct tgsi_full_instruction *inst,
const struct tgsi_opcode_info *info,
LLVMValueRef dst[4]);
void si_shader_context_init_alu(struct lp_build_tgsi_context *bld_base);
void si_prepare_cube_coords(struct lp_build_tgsi_context *bld_base,
struct lp_build_emit_data *emit_data,
LLVMValueRef *coords_arg,
LLVMValueRef *derivs_arg);
#endif
|