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
|
/*
* Copyright © 2018 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.
*/
#include "brw_nir.h"
#include "compiler/nir/nir_builder.h"
static nir_op
get_conversion_op(nir_alu_type src_type,
unsigned src_bit_size,
nir_alu_type dst_type,
unsigned dst_bit_size,
nir_rounding_mode rounding_mode)
{
nir_alu_type src_full_type = (nir_alu_type) (src_type | src_bit_size);
nir_alu_type dst_full_type = (nir_alu_type) (dst_type | dst_bit_size);
return nir_type_conversion_op(src_full_type, dst_full_type, rounding_mode);
}
static nir_rounding_mode
get_opcode_rounding_mode(nir_op op)
{
switch (op) {
case nir_op_f2f16_rtz:
return nir_rounding_mode_rtz;
case nir_op_f2f16_rtne:
return nir_rounding_mode_rtne;
default:
return nir_rounding_mode_undef;
}
}
static void
split_conversion(nir_builder *b, nir_alu_instr *alu, nir_op op1, nir_op op2)
{
b->cursor = nir_before_instr(&alu->instr);
assert(alu->dest.write_mask == 1);
nir_ssa_def *src = nir_ssa_for_alu_src(b, alu, 0);
nir_ssa_def *tmp = nir_build_alu(b, op1, src, NULL, NULL, NULL);
nir_ssa_def *res = nir_build_alu(b, op2, tmp, NULL, NULL, NULL);
nir_ssa_def_rewrite_uses(&alu->dest.dest.ssa, nir_src_for_ssa(res));
nir_instr_remove(&alu->instr);
}
static bool
lower_instr(nir_builder *b, nir_alu_instr *alu)
{
unsigned src_bit_size = nir_src_bit_size(alu->src[0].src);
nir_alu_type src_type = nir_op_infos[alu->op].input_types[0];
nir_alu_type src_full_type = (nir_alu_type) (src_type | src_bit_size);
unsigned dst_bit_size = nir_dest_bit_size(alu->dest.dest);
nir_alu_type dst_full_type = nir_op_infos[alu->op].output_type;
nir_alu_type dst_type = nir_alu_type_get_base_type(dst_full_type);
/* BDW PRM, vol02, Command Reference Instructions, mov - MOVE:
*
* "There is no direct conversion from HF to DF or DF to HF.
* Use two instructions and F (Float) as an intermediate type.
*
* There is no direct conversion from HF to Q/UQ or Q/UQ to HF.
* Use two instructions and F (Float) or a word integer type
* or a DWord integer type as an intermediate type."
*
* It is important that the intermediate conversion happens through a
* 32-bit float type so we don't lose range when we convert from
* a 64-bit integer.
*/
if ((src_full_type == nir_type_float16 && dst_bit_size == 64) ||
(src_bit_size == 64 && dst_full_type == nir_type_float16)) {
nir_op op1 = get_conversion_op(src_type, src_bit_size,
nir_type_float, 32,
nir_rounding_mode_undef);
nir_op op2 = get_conversion_op(nir_type_float, 32,
dst_type, dst_bit_size,
get_opcode_rounding_mode(alu->op));
split_conversion(b, alu, op1, op2);
return true;
}
/* SKL PRM, vol 02a, Command Reference: Instructions, Move:
*
* "There is no direct conversion from B/UB to DF or DF to B/UB. Use
* two instructions and a word or DWord intermediate type."
*
* "There is no direct conversion from B/UB to Q/UQ or Q/UQ to B/UB.
* Use two instructions and a word or DWord intermediate integer
* type."
*
* It is important that we use a 32-bit integer matching the sign of the
* destination as the intermediate type so we avoid any chance of rtne
* rounding happening before the conversion to integer (which is expected
* to round towards zero) in double to byte conversions.
*/
if ((src_bit_size == 8 && dst_bit_size == 64) ||
(src_bit_size == 64 && dst_bit_size == 8)) {
nir_op op1 = get_conversion_op(src_type, src_bit_size, dst_type, 32,
nir_rounding_mode_undef);
nir_op op2 = get_conversion_op(dst_type, 32, dst_type, dst_bit_size,
nir_rounding_mode_undef);
split_conversion(b, alu, op1, op2);
return true;
}
return false;
}
static bool
lower_impl(nir_function_impl *impl)
{
nir_builder b;
nir_builder_init(&b, impl);
bool progress = false;
nir_foreach_block(block, impl) {
nir_foreach_instr_safe(instr, block) {
if (instr->type != nir_instr_type_alu)
continue;
nir_alu_instr *alu = nir_instr_as_alu(instr);
assert(alu->dest.dest.is_ssa);
if (!nir_op_infos[alu->op].is_conversion)
continue;
progress = lower_instr(&b, alu) || progress;
}
}
if (progress) {
nir_metadata_preserve(impl, nir_metadata_block_index |
nir_metadata_dominance);
} else {
nir_metadata_preserve(impl, nir_metadata_all);
}
return progress;
}
bool
brw_nir_lower_conversions(nir_shader *shader)
{
bool progress = false;
nir_foreach_function(function, shader) {
if (function->impl)
progress |= lower_impl(function->impl);
}
return progress;
}
|
