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
236
237
238
239
240
|
/*
* Copyright © 2010 Intel Corporation
*
* 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:
* Eric Anholt <eric@anholt.net>
*
*/
/* DO NOT EDIT mesa_codegen.h. It is a generated file produced
* from mesa_codegen.brg and will be overwritten.
*/
#include <stdint.h>
#include <stdlib.h>
#include <string.h>
#include <assert.h>
#include <stdio.h>
/* Everything before the first %% is pasted at the start of the
* mesa_codegen.h header file.
*/
#include "ir_to_mesa.h"
#define MBTREE_TYPE struct mbtree
%%
# The list of terminals is the set of things that ir_to_mesa.cpp will
# generate in its trees.
%term assign
%term reference_vec4
%term exp_vec4
%term exp2_vec4
%term log_vec4
%term log2_vec4
%term add_vec4_vec4
%term sub_vec4_vec4
%term mul_vec4_vec4
%term div_vec4_vec4
%term slt_vec4_vec4
%term sgt_vec4_vec4
%term sle_vec4_vec4
%term sge_vec4_vec4
%term seq_vec4_vec4
%term sne_vec4_vec4
%term dp4_vec4_vec4
%term dp3_vec4_vec4
%term dp2_vec4_vec4
%term sqrt_vec4
%term rsq_vec4
%term swizzle_vec4
%term trunc_vec4
# Each tree will produce stmt. Currently, the only production for
# stmt is from an assign rule -- every statement tree from
# ir_to_mesa.cpp assigns a result to a register.
%start stmt
# Now comes all the rules for code generation. Each rule is of the
# general form
#
# produced: term(term, term) cost
# {
# code_run_when_we_choose_this_rule();
# }
#
# where choosing this rule means we turn term(term, term) into
# produced at the cost of "cost". We measure "cost" in approximate
# instruction count. The BURG should then more or less minimize the
# number of instructions.
# A reference of a variable is just a vec4 register location,
# so it can be used as an argument for pretty much anything.
vec4: reference_vec4 0
# Here's the rule everyone will hit: Moving the result of an
# expression into a variable-dereference register location.
#
# Note that this is likely a gratuitous move. We could make variants
# of each of the following rules, e.g:
#
# vec4: add_vec4_vec4(vec4, vec4) 1
# {
# emit(ADD, tree, tree->left, tree->right);
# }
#
# becoming
#
# vec4: assign(vec4_vec4, add_vec4_vec4(vec4, vec4) 1
# {
# emit(ADD, tree->left, tree->right->left, tree->right->right);
# }
#
# But it seems like a lot of extra typing and duped code, when we
# probably want copy propagation and dead code after codegen anyway,
# which would clean these up.
stmt: assign(vec4, vec4) 1
{
ir_to_mesa_emit_op1_full(tree, OPCODE_MOV,
tree->left->dst_reg,
tree->right->src_reg);
}
# Perform a swizzle by composing our swizzle with the swizzle
# required to get at the src reg.
vec4: swizzle_vec4(vec4) 1
{
ir_to_mesa_src_reg reg = tree->left->src_reg;
int swiz[4];
int i;
for (i = 0; i < 4; i++) {
swiz[i] = GET_SWZ(tree->src_reg.swizzle, i);
if (swiz[i] >= SWIZZLE_X && swiz[i] <= SWIZZLE_Y) {
swiz[i] = GET_SWZ(tree->left->src_reg.swizzle, swiz[i]);
}
}
reg.swizzle = MAKE_SWIZZLE4(swiz[0], swiz[1], swiz[2], swiz[3]);
ir_to_mesa_emit_op1_full(tree, OPCODE_MOV,
tree->dst_reg,
reg);
}
vec4: add_vec4_vec4(vec4, vec4) 1 { ir_to_mesa_emit_op2(tree, OPCODE_ADD); }
vec4: sub_vec4_vec4(vec4, vec4) 1 { ir_to_mesa_emit_op2(tree, OPCODE_SUB); }
vec4: mul_vec4_vec4(vec4, vec4) 1 { ir_to_mesa_emit_op2(tree, OPCODE_MUL); }
vec4: dp4_vec4_vec4(vec4, vec4) 1
{
ir_to_mesa_emit_op2(tree, OPCODE_DP4);
tree->src_reg.swizzle = SWIZZLE_XXXX;
}
vec4: dp3_vec4_vec4(vec4, vec4) 1
{
ir_to_mesa_emit_op2(tree, OPCODE_DP3);
tree->src_reg.swizzle = SWIZZLE_XXXX;
}
vec4: dp2_vec4_vec4(vec4, vec4) 1
{
ir_to_mesa_emit_op2(tree, OPCODE_DP2);
tree->src_reg.swizzle = SWIZZLE_XXXX;
}
vec4: div_vec4_vec4(vec4, vec4) 1
{
ir_to_mesa_emit_scalar_op1(tree, OPCODE_RCP,
tree->dst_reg,
tree->right->src_reg);
ir_to_mesa_emit_op2_full(tree, OPCODE_MUL,
tree->dst_reg,
tree->src_reg,
tree->left->src_reg);
}
vec4: slt_vec4_vec4(vec4, vec4) 1 { ir_to_mesa_emit_op2(tree, OPCODE_SLT); }
vec4: sgt_vec4_vec4(vec4, vec4) 1 { ir_to_mesa_emit_op2(tree, OPCODE_SGT); }
vec4: sle_vec4_vec4(vec4, vec4) 1 { ir_to_mesa_emit_op2(tree, OPCODE_SLE); }
vec4: sge_vec4_vec4(vec4, vec4) 1 { ir_to_mesa_emit_op2(tree, OPCODE_SGE); }
vec4: sne_vec4_vec4(vec4, vec4) 1 { ir_to_mesa_emit_op2(tree, OPCODE_SNE); }
vec4: seq_vec4_vec4(vec4, vec4) 1 { ir_to_mesa_emit_op2(tree, OPCODE_SEQ); }
vec4: sqrt_vec4(vec4) 1
{
ir_to_mesa_emit_scalar_op1(tree, OPCODE_RSQ,
tree->dst_reg,
tree->left->src_reg);
ir_to_mesa_emit_op1_full(tree, OPCODE_RCP,
tree->dst_reg,
tree->src_reg);
}
vec4: rsq_vec4(vec4) 1
{
ir_to_mesa_emit_scalar_op1(tree, OPCODE_RSQ,
tree->dst_reg,
tree->left->src_reg);
}
vec4: exp_vec4(vec4) 1
{
ir_to_mesa_emit_scalar_op1(tree, OPCODE_EXP,
tree->dst_reg,
tree->left->src_reg);
}
vec4: exp2_vec4(vec4) 1
{
ir_to_mesa_emit_scalar_op1(tree, OPCODE_EX2,
tree->dst_reg,
tree->left->src_reg);
}
vec4: log_vec4(vec4) 1
{
ir_to_mesa_emit_scalar_op1(tree, OPCODE_LOG,
tree->dst_reg,
tree->left->src_reg);
}
vec4: log2_vec4(vec4) 1
{
ir_to_mesa_emit_scalar_op1(tree, OPCODE_LG2,
tree->dst_reg,
tree->left->src_reg);
}
vec4: trunc_vec4(vec4) 1
{
ir_to_mesa_emit_scalar_op1(tree, OPCODE_TRUNC,
tree->dst_reg,
tree->left->src_reg);
}
%%
|