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
|
/*
* Copyright (C) 2013 Rob Clark <robclark@freedesktop.org>
*
* 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:
* Rob Clark <robclark@freedesktop.org>
*/
#ifndef IR3_COMPILER_H_
#define IR3_COMPILER_H_
#include "ir3_shader.h"
struct ir3_ra_reg_set;
struct ir3_compiler {
struct fd_device *dev;
uint32_t gpu_id;
struct ir3_ra_reg_set *set;
uint32_t shader_count;
/*
* Configuration options for things that are handled differently on
* different generations:
*/
/* a4xx (and later) drops SP_FS_FLAT_SHAD_MODE_REG_* for flat-interpolate
* so we need to use ldlv.u32 to load the varying directly:
*/
bool flat_bypass;
/* on a3xx, we need to add one to # of array levels:
*/
bool levels_add_one;
/* on a3xx, we need to scale up integer coords for isaml based
* on LoD:
*/
bool unminify_coords;
/* on a3xx do txf_ms w/ isaml and scaled coords: */
bool txf_ms_with_isaml;
/* on a4xx, for array textures we need to add 0.5 to the array
* index coordinate:
*/
bool array_index_add_half;
/* on a6xx, rewrite samgp to sequence of samgq0-3 in vertex shaders:
*/
bool samgq_workaround;
};
struct ir3_compiler * ir3_compiler_create(struct fd_device *dev, uint32_t gpu_id);
int ir3_compile_shader_nir(struct ir3_compiler *compiler,
struct ir3_shader_variant *so);
/* gpu pointer size in units of 32bit registers/slots */
static inline
unsigned ir3_pointer_size(struct ir3_compiler *compiler)
{
return (compiler->gpu_id >= 500) ? 2 : 1;
}
enum ir3_shader_debug {
IR3_DBG_SHADER_VS = 0x01,
IR3_DBG_SHADER_FS = 0x02,
IR3_DBG_SHADER_CS = 0x04,
IR3_DBG_DISASM = 0x08,
IR3_DBG_OPTMSGS = 0x10,
IR3_DBG_FORCES2EN = 0x20,
IR3_DBG_NOUBOOPT = 0x40,
};
extern enum ir3_shader_debug ir3_shader_debug;
static inline bool
shader_debug_enabled(gl_shader_stage type)
{
switch (type) {
case MESA_SHADER_VERTEX: return !!(ir3_shader_debug & IR3_DBG_SHADER_VS);
case MESA_SHADER_FRAGMENT: return !!(ir3_shader_debug & IR3_DBG_SHADER_FS);
case MESA_SHADER_COMPUTE: return !!(ir3_shader_debug & IR3_DBG_SHADER_CS);
default:
debug_assert(0);
return false;
}
}
#endif /* IR3_COMPILER_H_ */
|
