1 /*
2  * Copyright (C) 2018-2019 Alyssa Rosenzweig <alyssa@rosenzweig.io>
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 FROM,
20  * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
21  * SOFTWARE.
22  */
23 
24 #ifndef __BIFROST_PUBLIC_H_
25 #define __BIFROST_PUBLIC_H_
26 
27 #include "compiler/nir/nir.h"
28 #include "util/u_dynarray.h"
29 #include "panfrost/util/pan_ir.h"
30 
31 void
32 bifrost_compile_shader_nir(nir_shader *nir,
33                            const struct panfrost_compile_inputs *inputs,
34                            struct util_dynarray *binary,
35                            struct pan_shader_info *info);
36 
37 static const nir_shader_compiler_options bifrost_nir_options = {
38         .lower_scmp = true,
39         .lower_flrp16 = true,
40         .lower_flrp32 = true,
41         .lower_flrp64 = true,
42         .lower_ffract = true,
43         .lower_fmod = true,
44         .lower_fdiv = true,
45         .lower_isign = true,
46         .lower_find_lsb = true,
47         .lower_ifind_msb = true,
48         .lower_fdph = true,
49         .lower_fsqrt = true,
50 
51         .lower_wpos_pntc = true,
52         .lower_fsign = true,
53 
54         .lower_bitfield_insert_to_shifts = true,
55         .lower_bitfield_extract_to_shifts = true,
56         .lower_extract_byte = true,
57         .lower_extract_word = true,
58         .lower_insert_byte = true,
59         .lower_insert_word = true,
60         .lower_rotate = true,
61 
62         .lower_pack_half_2x16 = true,
63         .lower_pack_unorm_2x16 = true,
64         .lower_pack_snorm_2x16 = true,
65         .lower_pack_unorm_4x8 = true,
66         .lower_pack_snorm_4x8 = true,
67         .lower_unpack_half_2x16 = true,
68         .lower_unpack_unorm_2x16 = true,
69         .lower_unpack_snorm_2x16 = true,
70         .lower_unpack_unorm_4x8 = true,
71         .lower_unpack_snorm_4x8 = true,
72         .lower_pack_split = true,
73 
74         .lower_doubles_options = nir_lower_dmod,
75         /* TODO: Don't lower supported 64-bit operations */
76         .lower_int64_options = ~0,
77         /* TODO: Use IMULD on v7 */
78         .lower_mul_high = true,
79         .lower_uadd_carry = true,
80 
81         .has_fsub = true,
82         .has_isub = true,
83         .vectorize_io = true,
84         .vectorize_vec2_16bit = true,
85         .fuse_ffma16 = true,
86         .fuse_ffma32 = true,
87         .fuse_ffma64 = true,
88         .use_interpolated_input_intrinsics = true,
89 
90         .lower_uniforms_to_ubo = true,
91 
92         .has_cs_global_id = true,
93         .vertex_id_zero_based = true,
94         .lower_cs_local_index_from_id = true,
95         .max_unroll_iterations = 32,
96         .force_indirect_unrolling = (nir_var_shader_in | nir_var_shader_out | nir_var_function_temp),
97 };
98 
99 #endif
100