2 * Copyright © 2014 Intel Corporation
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:
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
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
24 * Jason Ekstrand (jason@jlekstrand.net)
31 * Implements a simple pass that lowers vecN instructions to a series of
32 * moves with partial writes.
36 lower_vec_to_movs_block(nir_block
*block
, void *mem_ctx
)
38 nir_foreach_instr_safe(block
, instr
) {
39 if (instr
->type
!= nir_instr_type_alu
)
42 nir_alu_instr
*vec
= (nir_alu_instr
*)instr
;
50 continue; /* The loop */
53 for (unsigned i
= 0, src_idx
= 0; i
< 4; i
++) {
54 if (!(vec
->dest
.write_mask
& (1 << i
)))
57 assert(src_idx
< nir_op_infos
[vec
->op
].num_inputs
);
59 nir_alu_instr
*mov
= nir_alu_instr_create(mem_ctx
, nir_op_imov
);
60 mov
->src
[0].src
= nir_src_copy(vec
->src
[src_idx
].src
, mem_ctx
);
61 mov
->src
[0].negate
= vec
->src
[src_idx
].negate
;
62 mov
->src
[0].abs
= vec
->src
[src_idx
].abs
;
64 /* We only care about the one swizzle */
65 mov
->src
[0].swizzle
[i
] = vec
->src
[src_idx
].swizzle
[0];
67 mov
->dest
.dest
= nir_dest_copy(vec
->dest
.dest
, mem_ctx
);
68 mov
->dest
.saturate
= vec
->dest
.saturate
;
69 mov
->dest
.write_mask
= (1u << i
);
71 nir_instr_insert_before(&vec
->instr
, &mov
->instr
);
76 nir_instr_remove(&vec
->instr
);
84 nir_lower_vec_to_movs_impl(nir_function_impl
*impl
)
86 nir_foreach_block(impl
, lower_vec_to_movs_block
, ralloc_parent(impl
));
90 nir_lower_vec_to_movs(nir_shader
*shader
)
92 nir_foreach_overload(shader
, overload
) {
94 nir_lower_vec_to_movs_impl(overload
->impl
);