eigen/test/dynalloc.cpp
Benoit Jacob fd831d5a12 * implement handmade aligned malloc, fast but always wastes 16 bytes of memory.
only used as fallback for now, needs benchmarking.
  also notice that some malloc() impls do waste memory to keep track of alignment
  and other stuff (check msdn's page on malloc).
* expand test_dynalloc to cover low level aligned alloc funcs. Remove the old
  #ifdef EIGEN_VECTORIZE...
* rewrite the logic choosing an aligned alloc, some new stuff:
  * malloc() already aligned on freebsd and windows x64 (plus apple already)
  * _mm_malloc() used only if EIGEN_VECTORIZE
  * posix_memalign: correct detection according to man page (not necessarily
    linux specific), don't attempt to declare it if the platform didn't declare it
    (there had to be a reason why it didn't declare it, right?)
2009-01-09 14:56:44 +00:00

157 lines
4.3 KiB
C++

// This file is part of Eigen, a lightweight C++ template library
// for linear algebra. Eigen itself is part of the KDE project.
//
// Copyright (C) 2008 Gael Guennebaud <g.gael@free.fr>
//
// Eigen is free software; you can redistribute it and/or
// modify it under the terms of the GNU Lesser General Public
// License as published by the Free Software Foundation; either
// version 3 of the License, or (at your option) any later version.
//
// Alternatively, you can redistribute it and/or
// modify it under the terms of the GNU General Public License as
// published by the Free Software Foundation; either version 2 of
// the License, or (at your option) any later version.
//
// Eigen is distributed in the hope that it will be useful, but WITHOUT ANY
// WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS
// FOR A PARTICULAR PURPOSE. See the GNU Lesser General Public License or the
// GNU General Public License for more details.
//
// You should have received a copy of the GNU Lesser General Public
// License and a copy of the GNU General Public License along with
// Eigen. If not, see <http://www.gnu.org/licenses/>.
#include "main.h"
void check_handmade_aligned_malloc()
{
for(int i = 1; i < 1000; i++)
{
char *p = (char*)ei_handmade_aligned_malloc(i);
VERIFY(size_t(p)%16==0);
// if the buffer is wrongly allocated this will give a bad write --> check with valgrind
for(int j = 0; j < i; j++) p[j]=0;
ei_handmade_aligned_free(p);
}
}
void check_aligned_malloc()
{
for(int i = 1; i < 1000; i++)
{
char *p = (char*)ei_aligned_malloc(i);
VERIFY(size_t(p)%16==0);
// if the buffer is wrongly allocated this will give a bad write --> check with valgrind
for(int j = 0; j < i; j++) p[j]=0;
ei_aligned_free(p);
}
}
void check_aligned_new()
{
for(int i = 1; i < 1000; i++)
{
float *p = ei_aligned_new<float>(i);
VERIFY(size_t(p)%16==0);
// if the buffer is wrongly allocated this will give a bad write --> check with valgrind
for(int j = 0; j < i; j++) p[j]=0;
ei_aligned_delete(p,i);
}
}
void check_aligned_stack_alloc()
{
for(int i = 1; i < 1000; i++)
{
float *p = ei_aligned_stack_new(float,i);
VERIFY(size_t(p)%16==0);
// if the buffer is wrongly allocated this will give a bad write --> check with valgrind
for(int j = 0; j < i; j++) p[j]=0;
ei_aligned_stack_delete(float,p,i);
}
}
// test compilation with both a struct and a class...
struct MyStruct
{
EIGEN_MAKE_ALIGNED_OPERATOR_NEW
char dummychar;
Vector4f avec;
};
class MyClassA
{
public:
EIGEN_MAKE_ALIGNED_OPERATOR_NEW
char dummychar;
Vector4f avec;
};
template<typename T> void check_dynaligned()
{
T* obj = new T;
VERIFY(size_t(obj)%16==0);
delete obj;
}
void test_dynalloc()
{
// low level dynamic memory allocation
CALL_SUBTEST(check_handmade_aligned_malloc());
CALL_SUBTEST(check_aligned_malloc());
CALL_SUBTEST(check_aligned_new());
CALL_SUBTEST(check_aligned_stack_alloc());
for (int i=0; i<g_repeat*100; ++i)
{
CALL_SUBTEST( check_dynaligned<Vector4f>() );
CALL_SUBTEST( check_dynaligned<Vector2d>() );
CALL_SUBTEST( check_dynaligned<Matrix4f>() );
CALL_SUBTEST( check_dynaligned<Vector4d>() );
CALL_SUBTEST( check_dynaligned<Vector4i>() );
}
// check static allocation, who knows ?
{
MyStruct foo0; VERIFY(size_t(foo0.avec.data())%16==0);
MyClassA fooA; VERIFY(size_t(fooA.avec.data())%16==0);
}
// dynamic allocation, single object
for (int i=0; i<g_repeat*100; ++i)
{
MyStruct *foo0 = new MyStruct(); VERIFY(size_t(foo0->avec.data())%16==0);
MyClassA *fooA = new MyClassA(); VERIFY(size_t(fooA->avec.data())%16==0);
delete foo0;
delete fooA;
}
// dynamic allocation, array
const int N = 10;
for (int i=0; i<g_repeat*100; ++i)
{
MyStruct *foo0 = new MyStruct[N]; VERIFY(size_t(foo0->avec.data())%16==0);
MyClassA *fooA = new MyClassA[N]; VERIFY(size_t(fooA->avec.data())%16==0);
delete[] foo0;
delete[] fooA;
}
// std::vector
for (int i=0; i<g_repeat*100; ++i)
{
std::vector<Vector4f, ei_new_allocator<Vector4f> > vecs(N);
for (int j=0; j<N; ++j)
{
VERIFY(size_t(vecs[j].data())%16==0);
}
std::vector<MyStruct,ei_new_allocator<MyStruct> > foos(N);
for (int j=0; j<N; ++j)
{
VERIFY(size_t(foos[j].avec.data())%16==0);
}
}
}