mirror of
https://gitlab.kitware.com/vtk/vtk-m
synced 2024-09-19 10:35:42 +00:00
c1560e2d3f
One of the causes of the large library size and slow compile times has been
that vtkm has been creating unnecessary copies when not needed. When the
objects being copied use shared_ptr this causes a bloom in library size. I
presume this bloom is caused by the atomic increment/decrement that is
required by shared_ptr.
For testing I used the following example:
```
struct ExampleFieldWorklet : public vtkm::worklet::WorkletMapField
{
typedef void ControlSignature( FieldIn<>, FieldIn<>, FieldIn<>,
FieldOut<>, FieldOut<>, FieldOut<> );
typedef void ExecutionSignature( _1, _2, _3, _4, _5, _6 );
template<typename T, typename U, typename V>
VTKM_EXEC_EXPORT
void operator()( const vtkm::Vec< T, 3 > & vec,
const U & scalar1,
const V& scalar2,
vtkm::Vec<T, 3>& out_vec,
U& out_scalar1,
V& out_scalar2 ) const
{
out_vec = vec * scalar1;
out_scalar1 = scalar1 + scalar2;
out_scalar2 = scalar2;
}
template<typename T, typename U, typename V, typename W, typename X, typename Y>
VTKM_EXEC_EXPORT
void operator()( const T & vec,
const U & scalar1,
const V& scalar2,
W& out_vec,
X& out_scalar,
Y& ) const
{
//no-op
}
};
int main(int argc, char** argv)
{
std::vector< vtkm::Vec<vtkm::Float32, 3> > inputVec;
std::vector< vtkm::Int32 > inputScalar1;
std::vector< vtkm::Float64 > inputScalar2;
vtkm::cont::ArrayHandle< vtkm::Vec<vtkm::Float32, 3> > handleV =
vtkm::cont::make_ArrayHandle(inputVec);
vtkm::cont::ArrayHandle< vtkm::Vec<vtkm::Float32, 3> > handleS1 =
vtkm::cont::make_ArrayHandle(inputVec);
vtkm::cont::ArrayHandle< vtkm::Vec<vtkm::Float32, 3> > handleS2 =
vtkm::cont::make_ArrayHandle(inputVec);
vtkm::cont::ArrayHandle< vtkm::Vec<vtkm::Float32, 3> > handleOV;
vtkm::cont::ArrayHandle< vtkm::Vec<vtkm::Float32, 3> > handleOS1;
vtkm::cont::ArrayHandle< vtkm::Vec<vtkm::Float32, 3> > handleOS2;
std::cout << "Making 3 output DynamicArrayHandles " << std::endl;
vtkm::cont::DynamicArrayHandle out1(handleOV), out2(handleOS1), out3(handleOS2);
typedef vtkm::worklet::DispatcherMapField<ExampleFieldWorklet> DispatcherType;
std::cout << "Invoking ExampleFieldWorklet" << std::endl;
DispatcherType dispatcher;
dispatcher.Invoke(handleV, handleS1, handleS2, out1, out2, out3);
}
```
Original vtkm would generate a binary of size 4684kb and would perform 91
ArrayHandle copies or assignments. With this branch the binary size is
reduced to 2392kb and will perform 36 copies or assignments.
144 lines
4.6 KiB
C
144 lines
4.6 KiB
C
//============================================================================
|
|
// Copyright (c) Kitware, Inc.
|
|
// All rights reserved.
|
|
// See LICENSE.txt for details.
|
|
// This software is distributed WITHOUT ANY WARRANTY; without even
|
|
// the implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR
|
|
// PURPOSE. See the above copyright notice for more information.
|
|
//
|
|
// Copyright 2014 Sandia Corporation.
|
|
// Copyright 2014 UT-Battelle, LLC.
|
|
// Copyright 2014 Los Alamos National Security.
|
|
//
|
|
// Under the terms of Contract DE-AC04-94AL85000 with Sandia Corporation,
|
|
// the U.S. Government retains certain rights in this software.
|
|
//
|
|
// Under the terms of Contract DE-AC52-06NA25396 with Los Alamos National
|
|
// Laboratory (LANL), the U.S. Government retains certain rights in
|
|
// this software.
|
|
//============================================================================
|
|
$# This file uses the pyexpander macro processing utility to build the
|
|
$# FunctionInterface facilities that use a variable number of arguments.
|
|
$# Information, documentation, and downloads for pyexpander can be found at:
|
|
$#
|
|
$# http://pyexpander.sourceforge.net/
|
|
$#
|
|
$# To build the source code, execute the following (after installing
|
|
$# pyexpander, of course):
|
|
$#
|
|
$# expander.py FunctionInterfaceDetailPost.h.in > FunctionInterfaceDetailPost.h
|
|
$#
|
|
$# Ignore the following comment. It is meant for the generated file.
|
|
// **** DO NOT EDIT THIS FILE!!! ****
|
|
// This file is automatically generated by FunctionInterfaceDetailPost.h.in
|
|
|
|
#ifndef vtk_m_internal_FunctionInterfaceDetailPost_h
|
|
#define vtk_m_internal_FunctionInterfaceDetailPost_h
|
|
|
|
#if !defined(vtk_m_internal_FunctionInterface_h) && !defined(VTKM_TEST_HEADER_BUILD)
|
|
#error FunctionInterfaceDetailPre.h must be included from FunctionInterface.h
|
|
#endif
|
|
|
|
#include <vtkm/internal/FunctionInterface.h>
|
|
|
|
$# This needs to match the max_parameters in FunctionInterfaceDetailPre.h.in
|
|
$py(max_parameters=10)\
|
|
#if VTKM_MAX_FUNCTION_PARAMETERS != $(max_parameters)
|
|
#error Mismatch of maximum parameters between FunctionInterfaceDatailPre.h.in and FunctionInterfaceDetailPost.h.in
|
|
#endif
|
|
|
|
$# Python commands used in template expansion.
|
|
$py(
|
|
def comma_if(flag):
|
|
if flag:
|
|
return ','
|
|
else:
|
|
return '';
|
|
|
|
def ptype(num, name=""):
|
|
if num == 0:
|
|
return '%sR' % name
|
|
else:
|
|
return '%sP%d' % (name, num)
|
|
|
|
def template_params(num_params, start=0, name=''):
|
|
if num_params < start:
|
|
return ''
|
|
result = 'typename %s' % ptype(start, name)
|
|
for param in xrange(start+1, num_params+1):
|
|
result += ',\n typename %s' % ptype(param, name)
|
|
return result
|
|
|
|
def signature(num_params, name=''):
|
|
result = '%s(' % ptype(0, name)
|
|
if num_params > 0:
|
|
result += ptype(1, name)
|
|
for param in xrange(2, num_params+1):
|
|
result += ',%s' % ptype(param, name)
|
|
result += ')'
|
|
return result
|
|
)\
|
|
$#
|
|
$extend(comma_if, ptype, template_params, signature)\
|
|
|
|
namespace vtkm {
|
|
namespace internal {
|
|
|
|
namespace detail {
|
|
|
|
//============================================================================
|
|
|
|
$for(num_params in xrange(0, max_parameters+1))\
|
|
template<typename Transform,
|
|
$template_params(num_params)>
|
|
struct FunctionInterfaceStaticTransformType<$signature(num_params), Transform> {
|
|
typedef $ptype(0)(type)(
|
|
$for(param_index in xrange(1, num_params+1))\
|
|
typename Transform::template ReturnType<$ptype(param_index),$(param_index)>::type$comma_if(param_index<num_params)
|
|
$endfor\
|
|
);
|
|
};
|
|
|
|
$endfor\
|
|
|
|
} // namespace detail
|
|
|
|
//============================================================================
|
|
|
|
$for(num_params in xrange(0, max_parameters+1))\
|
|
/// \brief Create a \c FunctionInterface
|
|
///
|
|
/// \c make_FunctionInterface is a function that takes a variable number of
|
|
/// arguments and returns a \c FunctionInterface object containing these
|
|
/// objects. Since the return type for the function signature is not specified,
|
|
/// you must always specify it as a template parameter
|
|
///
|
|
/// \code{.cpp}
|
|
/// vtkm::internal::FunctionInterface<void(int,double,char)> functionInterface =
|
|
/// vtkm::internal::make_FunctionInterface<void>(1, 2.5, 'a');
|
|
/// \endcode
|
|
///
|
|
VTKM_SUPPRESS_EXEC_WARNINGS
|
|
template<$template_params(num_params)>
|
|
VTKM_EXEC_CONT_EXPORT
|
|
FunctionInterface<$signature(num_params)>
|
|
make_FunctionInterface(
|
|
$for(param_index in xrange(1,num_params+1))\
|
|
const $ptype(param_index)& p$(param_index)$comma_if(param_index<num_params)
|
|
$endfor\
|
|
)
|
|
{
|
|
FunctionInterface<$signature(num_params)> fi;
|
|
$for(param_index in xrange(1,num_params+1))\
|
|
fi.template SetParameter<$(param_index)>(p$(param_index));
|
|
$endfor\
|
|
return fi;
|
|
}
|
|
|
|
$endfor\
|
|
|
|
}
|
|
} // namespace vtkm::internal
|
|
|
|
#endif //vtk_m_internal_FunctionInterfaceDetailPost_h
|