guozhou

#include "stdafx.h"
#include "Tree.h"
#include <libmorton/morton.h>

Tree::Tree() // sharing face, edge, vertex
	:order{ { 0, 1, 2, 4, 3, 5, 6, 7 },{ 1, 0, 3, 5, 2, 4, 7, 6 },
	{ 2, 0, 3, 6, 1, 4, 7, 5 },{ 3, 1, 2, 7, 0, 5, 6, 4 },
	{ 4, 0, 5, 6, 1, 2, 7, 3 },{ 5, 1, 4, 7, 0, 3, 6, 2 },
	{ 6, 2, 4, 7, 0, 3, 5, 1 },{ 7, 3, 5, 6, 1, 2, 4, 0 } }
{

guozhou

#include <iostream>
#include <cstdlib>
#include <cassert>
#include <vector>

#include <wstp.h>
#include <glm/glm.hpp>
#include <glm/gtc/type_ptr.hpp>

#define DEQUE_SIZE 7

guozhou

#include <iostream>
#include <cuda_runtime.h>
#include <device_launch_parameters.h>

// GTS450 sm_21
#define NUM_SM 4 // no. of streaming multiprocessors
#define NUM_WARP_PER_SM 48 // maximum no. of resident warps per SM
#define NUM_BLOCK_PER_SM 8 // maximum no. of resident blocks per SM
#define NUM_BLOCK NUM_SM * NUM_BLOCK_PER_SM
#define NUM_WARP_PER_BLOCK NUM_WARP_PER_SM / NUM_BLOCK_PER_SM