Files
mesa/src/compiler/glsl/ir_expression_flattening.cpp
Marek Olšák dfe45d1b67 glsl: switch ir_instruction to linear_ctx to eliminate malloc overhead
Compiling my shader-db with the gallium noop driver is 3.6% faster now.

malloc calls from ralloc+linear_alloc are reduced by 34% when compiling
Heaven shaders with the gallium noop driver. That's due to a shift of
malloc calls from ralloc to linear_alloc.

Acked-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
Acked-by: Timothy Arceri <tarceri@itsqueeze.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/36539>
2025-08-04 02:07:00 +00:00

82 lines
2.6 KiB
C++

/*
* Copyright © 2010 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.
*/
/**
* \file ir_expression_flattening.cpp
*
* Takes the leaves of expression trees and makes them dereferences of
* assignments of the leaves to temporaries, according to a predicate.
*
* This is used for breaking down matrix operations, where it's easier to
* create a temporary and work on each of its vector components individually.
*/
#include "ir.h"
#include "ir_rvalue_visitor.h"
#include "ir_expression_flattening.h"
class ir_expression_flattening_visitor : public ir_rvalue_visitor {
public:
ir_expression_flattening_visitor(bool (*predicate)(ir_instruction *ir))
{
this->predicate = predicate;
}
virtual ~ir_expression_flattening_visitor()
{
/* empty */
}
void handle_rvalue(ir_rvalue **rvalue);
bool (*predicate)(ir_instruction *ir);
};
void
do_expression_flattening(ir_exec_list *instructions,
bool (*predicate)(ir_instruction *ir))
{
ir_expression_flattening_visitor v(predicate);
visit_list_elements(&v, instructions);
}
void
ir_expression_flattening_visitor::handle_rvalue(ir_rvalue **rvalue)
{
ir_variable *var;
ir_assignment *assign;
ir_rvalue *ir = *rvalue;
if (!ir || !this->predicate(ir))
return;
linear_ctx *linalloc = ir->node_linalloc;
var = new(linalloc) ir_variable(ir->type, "flattening_tmp", ir_var_temporary);
base_ir->insert_before(var);
assign = new(linalloc) ir_assignment(new(linalloc) ir_dereference_variable(var), ir);
base_ir->insert_before(assign);
*rvalue = new(linalloc) ir_dereference_variable(var);
}