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
|
/*
* Copyright 2011 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
* the rights to use, copy, modify, merge, publish, distribute, sublicense,
* 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 NONINFRINGEMENT. IN NO EVENT SHALL
* THE AUTHORS OR COPYRIGHT HOLDERS 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.
*
* Authors: Tom Stellard <thomas.stellard@amd.com>
*
*/
#ifndef RADEON_LLVM_H
#define RADEON_LLVM_H
#include <llvm-c/Core.h>
#include "gallivm/lp_bld_init.h"
#include "gallivm/lp_bld_tgsi.h"
#define RADEON_LLVM_MAX_INPUTS 16 * 4
#define RADEON_LLVM_MAX_OUTPUTS 16 * 4
#define RADEON_LLVM_MAX_BRANCH_DEPTH 16
#define RADEON_LLVM_MAX_LOOP_DEPTH 16
#define RADEON_LLVM_MAX_SYSTEM_VALUES 4
struct radeon_llvm_branch {
LLVMBasicBlockRef endif_block;
LLVMBasicBlockRef if_block;
LLVMBasicBlockRef else_block;
unsigned has_else;
};
struct radeon_llvm_loop {
LLVMBasicBlockRef loop_block;
LLVMBasicBlockRef endloop_block;
};
struct radeon_llvm_context {
struct lp_build_tgsi_soa_context soa;
unsigned chip_class;
unsigned type;
unsigned face_input;
unsigned two_side;
struct r600_shader_io * r600_inputs;
/*=== Front end configuration ===*/
/* Special Intrinsics */
/** Write to an output register: float store_output(float, i32) */
const char * store_output_intr;
/** Swizzle a vector value: <4 x float> swizzle(<4 x float>, i32)
* The swizzle is an unsigned integer that encodes a TGSI_SWIZZLE_* value
* in 2-bits.
* Swizzle{0-1} = X Channel
* Swizzle{2-3} = Y Channel
* Swizzle{4-5} = Z Channel
* Swizzle{6-7} = W Channel
*/
const char * swizzle_intr;
/* Instructions that are not described by any of the TGSI opcodes. */
/** 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 radeon_llvm_context *,
unsigned input_index,
const struct tgsi_full_declaration *decl);
void (*load_system_value)(struct radeon_llvm_context *,
unsigned index,
const struct tgsi_full_declaration *decl);
/** User data to use with the callbacks */
void * userdata;
/** 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.
*/
LLVMValueRef inputs[RADEON_LLVM_MAX_INPUTS];
LLVMValueRef outputs[RADEON_LLVM_MAX_OUTPUTS][TGSI_NUM_CHANNELS];
unsigned output_reg_count;
LLVMValueRef system_values[RADEON_LLVM_MAX_SYSTEM_VALUES];
unsigned reserved_reg_count;
/*=== Private Members ===*/
struct radeon_llvm_branch branch[RADEON_LLVM_MAX_BRANCH_DEPTH];
struct radeon_llvm_loop loop[RADEON_LLVM_MAX_LOOP_DEPTH];
unsigned branch_depth;
unsigned loop_depth;
LLVMValueRef main_fn;
struct gallivm_state gallivm;
};
static inline LLVMValueRef bitcast(
struct lp_build_tgsi_context * bld_base,
enum tgsi_opcode_type type,
LLVMValueRef value
)
{
LLVMBuilderRef builder = bld_base->base.gallivm->builder;
LLVMContextRef ctx = bld_base->base.gallivm->context;
LLVMTypeRef dst_type;
switch (type) {
case TGSI_TYPE_UNSIGNED:
case TGSI_TYPE_SIGNED:
dst_type = LLVMInt32TypeInContext(ctx);
break;
case TGSI_TYPE_UNTYPED:
case TGSI_TYPE_FLOAT:
dst_type = LLVMFloatTypeInContext(ctx);
break;
default:
dst_type = 0;
break;
}
if (dst_type)
return LLVMBuildBitCast(builder, value, dst_type, "");
else
return value;
}
void radeon_llvm_context_init(struct radeon_llvm_context * ctx);
void radeon_llvm_dispose(struct radeon_llvm_context * ctx);
inline static struct radeon_llvm_context * radeon_llvm_context(
struct lp_build_tgsi_context * bld_base)
{
return (struct radeon_llvm_context*)bld_base;
}
unsigned radeon_llvm_reg_index_soa(unsigned index, unsigned chan);
void radeon_llvm_finalize_module(struct radeon_llvm_context * ctx);
LLVMValueRef
build_intrinsic(LLVMBuilderRef builder,
const char *name,
LLVMTypeRef ret_type,
LLVMValueRef *args,
unsigned num_args,
LLVMAttribute attr);
void
build_tgsi_intrinsic_nomem(
const struct lp_build_tgsi_action * action,
struct lp_build_tgsi_context * bld_base,
struct lp_build_emit_data * emit_data);
#endif /* RADEON_LLVM_H */
|