#include <stdio.h>
#include <stdlib.h>

/* align_size has to be a power of two !! */
void *aligned_malloc(size_t size, size_t align_size) {

	char *ptr,*ptr2,*aligned_ptr;
	int align_mask = align_size - 1;

	ptr=(char *)malloc(size + align_size + sizeof(int));
	if(ptr==NULL) return(NULL);

	ptr2 = ptr + sizeof(int);
	aligned_ptr = ptr2 + (align_size - ((size_t)ptr2 & align_mask));


	ptr2 = aligned_ptr - sizeof(int);
	*((int *)ptr2)=(int)(aligned_ptr - ptr);

	return(aligned_ptr);
}

void aligned_free(void *ptr) {

	int *ptr2=(int *)ptr - 1;
	ptr -= *ptr2;
	free(ptr);
}

int main( void )
{
	// declare the type of data pointer that
	// we want to allocate...
	char* pData = 0;

	pData = aligned_malloc( 64, 4 ); // let's get 64 bytes aligned on a 4-byte boundry

	if( pData != NULL )
	{
		; // do something with our allocated memory

		// free it...
		aligned_free( pData );
		pData = 0;
	}

	return 0;
}