mesa/src/amd/compiler/aco_instruction_selection.h
Rhys Perry 6113ee650a aco/gfx11: fix FS input loads in quad-divergent control flow
This is not ideal and it would be great to somehow make it better some
day.

fossil-db (gfx1100):
Totals from 5208 (3.86% of 135032) affected shaders:
MaxWaves: 127058 -> 126962 (-0.08%); split: +0.01%, -0.09%
Instrs: 3983440 -> 4072736 (+2.24%); split: -0.00%, +2.24%
CodeSize: 21872468 -> 22230852 (+1.64%); split: -0.00%, +1.64%
VGPRs: 206688 -> 206984 (+0.14%); split: -0.05%, +0.20%
Latency: 37447383 -> 37491197 (+0.12%); split: -0.05%, +0.17%
InvThroughput: 6421955 -> 6422348 (+0.01%); split: -0.03%, +0.03%
VClause: 71579 -> 71545 (-0.05%); split: -0.09%, +0.04%
SClause: 148289 -> 147146 (-0.77%); split: -0.84%, +0.07%
Copies: 259011 -> 258084 (-0.36%); split: -0.61%, +0.25%
Branches: 101366 -> 101314 (-0.05%); split: -0.10%, +0.05%
PreSGPRs: 223482 -> 223460 (-0.01%); split: -0.21%, +0.20%
PreVGPRs: 184448 -> 184744 (+0.16%)

Signed-off-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/19370>
2022-11-01 12:42:43 +00:00

136 lines
4.2 KiB
C++

/*
* Copyright © 2018 Valve 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.
*
*/
#ifndef ACO_INSTRUCTION_SELECTION_H
#define ACO_INSTRUCTION_SELECTION_H
#include "aco_ir.h"
#include "vulkan/radv_shader_args.h"
#include <array>
#include <unordered_map>
#include <vector>
namespace aco {
enum aco_color_output_type {
ACO_TYPE_ANY32,
ACO_TYPE_FLOAT16,
ACO_TYPE_INT16,
ACO_TYPE_UINT16,
};
struct shader_io_state {
uint8_t mask[VARYING_SLOT_MAX];
Temp temps[VARYING_SLOT_MAX * 4u];
shader_io_state()
{
memset(mask, 0, sizeof(mask));
std::fill_n(temps, VARYING_SLOT_MAX * 4u, Temp(0, RegClass::v1));
}
};
struct isel_context {
const struct aco_compiler_options* options;
const struct radv_shader_args* args;
Program* program;
nir_shader* shader;
uint32_t constant_data_offset;
Block* block;
uint32_t first_temp_id;
std::unordered_map<unsigned, std::array<Temp, NIR_MAX_VEC_COMPONENTS>> allocated_vec;
Stage stage;
struct {
bool has_branch;
struct {
unsigned header_idx;
Block* exit;
bool has_divergent_continue = false;
bool has_divergent_branch = false;
} parent_loop;
struct {
bool is_divergent = false;
} parent_if;
bool had_divergent_discard = false;
bool exec_potentially_empty_discard =
false; /* set to false when loop_nest_depth==0 && parent_if.is_divergent==false */
uint16_t exec_potentially_empty_break_depth = UINT16_MAX;
/* Set to false when loop_nest_depth==exec_potentially_empty_break_depth
* and parent_if.is_divergent==false. Called _break but it's also used for
* loop continues. */
bool exec_potentially_empty_break = false;
std::unique_ptr<unsigned[]> nir_to_aco; /* NIR block index to ACO block index */
} cf_info;
/* NIR range analysis. */
struct hash_table* range_ht;
nir_unsigned_upper_bound_config ub_config;
Temp arg_temps[AC_MAX_ARGS];
/* FS inputs */
Temp persp_centroid, linear_centroid;
/* GS inputs */
Temp gs_wave_id;
/* VS output information */
bool export_clip_dists;
unsigned num_clip_distances;
unsigned num_cull_distances;
/* tessellation information */
uint64_t tcs_temp_only_inputs;
bool tcs_in_out_eq = false;
/* Fragment color output information */
uint16_t output_color_types;
/* I/O information */
shader_io_state inputs;
shader_io_state outputs;
};
inline Temp
get_arg(isel_context* ctx, struct ac_arg arg)
{
assert(arg.used);
return ctx->arg_temps[arg.arg_index];
}
void init_context(isel_context* ctx, nir_shader* shader);
void cleanup_context(isel_context* ctx);
isel_context setup_isel_context(Program* program, unsigned shader_count,
struct nir_shader* const* shaders, ac_shader_config* config,
const struct aco_compiler_options* options,
const struct aco_shader_info* info,
const struct radv_shader_args* args,
bool is_gs_copy_shader, bool is_ps_epilog);
} // namespace aco
#endif /* ACO_INSTRUCTION_SELECTION_H */