1 /*
2  * Copyright 2012 Advanced Micro Devices, Inc.
3  *
4  * Permission is hereby granted, free of charge, to any person obtaining a
5  * copy of this software and associated documentation files (the "Software"),
6  * to deal in the Software without restriction, including without limitation
7  * the rights to use, copy, modify, merge, publish, distribute, sublicense,
8  * and/or sell copies of the Software, and to permit persons to whom the
9  * Software is furnished to do so, subject to the following conditions:
10  *
11  * The above copyright notice and this permission notice (including the next
12  * paragraph) shall be included in all copies or substantial portions of the
13  * Software.
14  *
15  * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
16  * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
17  * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
18  * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
19  * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
20  * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
21  * IN THE SOFTWARE.
22  */
23 
24 #ifndef AC_SHADER_UTIL_H
25 #define AC_SHADER_UTIL_H
26 
27 #include "ac_binary.h"
28 #include "amd_family.h"
29 #include "compiler/nir/nir.h"
30 #include "compiler/shader_enums.h"
31 
32 #include <stdbool.h>
33 #include <stdint.h>
34 
35 #ifdef __cplusplus
36 extern "C" {
37 #endif
38 
39 enum ac_image_dim
40 {
41    ac_image_1d,
42    ac_image_2d,
43    ac_image_3d,
44    ac_image_cube, // includes cube arrays
45    ac_image_1darray,
46    ac_image_2darray,
47    ac_image_2dmsaa,
48    ac_image_2darraymsaa,
49 };
50 
51 struct ac_data_format_info {
52    uint8_t element_size;
53    uint8_t num_channels;
54    uint8_t chan_byte_size;
55    uint8_t chan_format;
56 };
57 
58 struct ac_spi_color_formats {
59    unsigned normal : 8;
60    unsigned alpha : 8;
61    unsigned blend : 8;
62    unsigned blend_alpha : 8;
63 };
64 
65 /* For ac_build_fetch_format.
66  *
67  * Note: FLOAT must be 0 (used for convenience of encoding in radeonsi).
68  */
69 enum ac_fetch_format
70 {
71    AC_FETCH_FORMAT_FLOAT = 0,
72    AC_FETCH_FORMAT_FIXED,
73    AC_FETCH_FORMAT_UNORM,
74    AC_FETCH_FORMAT_SNORM,
75    AC_FETCH_FORMAT_USCALED,
76    AC_FETCH_FORMAT_SSCALED,
77    AC_FETCH_FORMAT_UINT,
78    AC_FETCH_FORMAT_SINT,
79    AC_FETCH_FORMAT_NONE,
80 };
81 
82 unsigned ac_get_spi_shader_z_format(bool writes_z, bool writes_stencil, bool writes_samplemask);
83 
84 unsigned ac_get_cb_shader_mask(unsigned spi_shader_col_format);
85 
86 uint32_t ac_vgt_gs_mode(unsigned gs_max_vert_out, enum chip_class chip_class);
87 
88 unsigned ac_get_tbuffer_format(enum chip_class chip_class, unsigned dfmt, unsigned nfmt);
89 
90 const struct ac_data_format_info *ac_get_data_format_info(unsigned dfmt);
91 
92 enum ac_image_dim ac_get_sampler_dim(enum chip_class chip_class, enum glsl_sampler_dim dim,
93                                      bool is_array);
94 
95 enum ac_image_dim ac_get_image_dim(enum chip_class chip_class, enum glsl_sampler_dim sdim,
96                                    bool is_array);
97 
98 unsigned ac_get_fs_input_vgpr_cnt(const struct ac_shader_config *config,
99                                   signed char *face_vgpr_index, signed char *ancillary_vgpr_index);
100 
101 void ac_choose_spi_color_formats(unsigned format, unsigned swap, unsigned ntype,
102                                  bool is_depth, bool use_rbplus,
103                                  struct ac_spi_color_formats *formats);
104 
105 void ac_compute_late_alloc(const struct radeon_info *info, bool ngg, bool ngg_culling,
106                            bool uses_scratch, unsigned *late_alloc_wave64, unsigned *cu_mask);
107 
108 unsigned ac_compute_cs_workgroup_size(uint16_t sizes[3], bool variable, unsigned max);
109 
110 unsigned ac_compute_lshs_workgroup_size(enum chip_class chip_class, gl_shader_stage stage,
111                                         unsigned tess_num_patches,
112                                         unsigned tess_patch_in_vtx,
113                                         unsigned tess_patch_out_vtx);
114 
115 unsigned ac_compute_esgs_workgroup_size(enum chip_class chip_class, unsigned wave_size,
116                                         unsigned es_verts, unsigned gs_inst_prims);
117 
118 unsigned ac_compute_ngg_workgroup_size(unsigned es_verts, unsigned gs_inst_prims,
119                                        unsigned max_vtx_out, unsigned prim_amp_factor);
120 
121 #ifdef __cplusplus
122 }
123 #endif
124 
125 #endif
126