File: ao_serial.cpp

package info (click to toggle)
ispc 1.28.2-1
  • links: PTS, VCS
  • area: main
  • in suites: forky, sid
  • size: 97,620 kB
  • sloc: cpp: 77,067; python: 8,303; yacc: 3,337; lex: 1,126; ansic: 631; sh: 475; makefile: 17
file content (268 lines) | stat: -rw-r--r-- 7,339 bytes parent folder | download | duplicates (2)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
// -*- mode: c++ -*-
/*
  Copyright (c) 2010-2023, Intel Corporation

  SPDX-License-Identifier: BSD-3-Clause
*/
/*
  Based on Syoyo Fujita's aobench: http://code.google.com/p/aobench
*/

#ifdef _MSC_VER
#define _CRT_SECURE_NO_WARNINGS
#define NOMINMAX
#pragma warning(disable : 4244)
#pragma warning(disable : 4305)
#endif

#include <math.h>
#include <stdlib.h>

#ifdef _MSC_VER
static long long drand48_x = 0x1234ABCD330E;

static inline void srand48(int x) { drand48_x = x ^ (x << 16); }

static inline double drand48() {
    drand48_x = drand48_x * 0x5DEECE66D + 0xB;
    return (drand48_x & 0xFFFFFFFFFFFF) * (1.0 / 281474976710656.0);
}
#endif // _MSC_VER

#ifdef _MSC_VER
__declspec(align(16))
#endif
    struct vec {
    vec() { x = y = z = pad = 0.; }
    vec(float xx, float yy, float zz) {
        x = xx;
        y = yy;
        z = zz;
        pad = 0;
    }

    vec operator*(float f) const { return vec(x * f, y * f, z * f); }
    vec operator+(const vec &f2) const { return vec(x + f2.x, y + f2.y, z + f2.z); }
    vec operator-(const vec &f2) const { return vec(x - f2.x, y - f2.y, z - f2.z); }
    vec operator*(const vec &f2) const { return vec(x * f2.x, y * f2.y, z * f2.z); }
    float x, y, z;
    float pad;
}
#ifndef _MSC_VER
__attribute__((aligned(16)))
#endif
;
inline vec operator*(float f, const vec &v) { return vec(f * v.x, f * v.y, f * v.z); }

#define NAO_SAMPLES 8

#ifdef M_PI
#undef M_PI
#endif
#define M_PI 3.1415926535f

struct Isect {
    float t;
    vec p;
    vec n;
    int hit;
};

struct Sphere {
    vec center;
    float radius;
};

struct Plane {
    vec p;
    vec n;
};

struct Ray {
    vec org;
    vec dir;
};

static inline float dot(const vec &a, const vec &b) { return a.x * b.x + a.y * b.y + a.z * b.z; }

static inline vec vcross(const vec &v0, const vec &v1) {
    vec ret;
    ret.x = v0.y * v1.z - v0.z * v1.y;
    ret.y = v0.z * v1.x - v0.x * v1.z;
    ret.z = v0.x * v1.y - v0.y * v1.x;
    return ret;
}

static inline void vnormalize(vec &v) {
    float len2 = dot(v, v);
    float invlen = 1.f / sqrtf(len2);
    v = v * invlen;
}

static inline void ray_plane_intersect(Isect &isect, Ray &ray, Plane &plane) {
    float d = -dot(plane.p, plane.n);
    float v = dot(ray.dir, plane.n);

    if (fabsf(v) < 1.0e-17f)
        return;
    else {
        float t = -(dot(ray.org, plane.n) + d) / v;

        if ((t > 0.0) && (t < isect.t)) {
            isect.t = t;
            isect.hit = 1;
            isect.p = ray.org + ray.dir * t;
            isect.n = plane.n;
        }
    }
}

static inline void ray_sphere_intersect(Isect &isect, Ray &ray, Sphere &sphere) {
    vec rs = ray.org - sphere.center;

    float B = dot(rs, ray.dir);
    float C = dot(rs, rs) - sphere.radius * sphere.radius;
    float D = B * B - C;

    if (D > 0.) {
        float t = -B - sqrtf(D);

        if ((t > 0.0) && (t < isect.t)) {
            isect.t = t;
            isect.hit = 1;
            isect.p = ray.org + t * ray.dir;
            isect.n = isect.p - sphere.center;
            vnormalize(isect.n);
        }
    }
}

static inline void orthoBasis(vec basis[3], const vec &n) {
    basis[2] = n;
    basis[1].x = 0.0;
    basis[1].y = 0.0;
    basis[1].z = 0.0;

    if ((n.x < 0.6f) && (n.x > -0.6f)) {
        basis[1].x = 1.0;
    } else if ((n.y < 0.6f) && (n.y > -0.6f)) {
        basis[1].y = 1.0;
    } else if ((n.z < 0.6f) && (n.z > -0.6f)) {
        basis[1].z = 1.0;
    } else {
        basis[1].x = 1.0;
    }

    basis[0] = vcross(basis[1], basis[2]);
    vnormalize(basis[0]);

    basis[1] = vcross(basis[2], basis[0]);
    vnormalize(basis[1]);
}

static float ambient_occlusion(Isect &isect, Plane &plane, Sphere spheres[3]) {
    float eps = 0.0001f;
    vec p, n;
    vec basis[3];
    float occlusion = 0.0;

    p = isect.p + eps * isect.n;

    orthoBasis(basis, isect.n);

    static const int ntheta = NAO_SAMPLES;
    static const int nphi = NAO_SAMPLES;
    for (int j = 0; j < ntheta; j++) {
        for (int i = 0; i < nphi; i++) {
            Ray ray;
            Isect occIsect;

            float theta = sqrtf(drand48());
            float phi = 2.0f * M_PI * drand48();
            float x = cosf(phi) * theta;
            float y = sinf(phi) * theta;
            float z = sqrtf(1.0f - theta * theta);

            // local . global
            float rx = x * basis[0].x + y * basis[1].x + z * basis[2].x;
            float ry = x * basis[0].y + y * basis[1].y + z * basis[2].y;
            float rz = x * basis[0].z + y * basis[1].z + z * basis[2].z;

            ray.org = p;
            ray.dir.x = rx;
            ray.dir.y = ry;
            ray.dir.z = rz;

            occIsect.t = 1.0e+17f;
            occIsect.hit = 0;

            for (int snum = 0; snum < 3; ++snum)
                ray_sphere_intersect(occIsect, ray, spheres[snum]);
            ray_plane_intersect(occIsect, ray, plane);

            if (occIsect.hit)
                occlusion += 1.f;
        }
    }

    occlusion = (ntheta * nphi - occlusion) / (float)(ntheta * nphi);
    return occlusion;
}

/* Compute the image for the scanlines from [y0,y1), for an overall image
   of width w and height h.
 */
static void ao_scanlines(int y0, int y1, int w, int h, int nsubsamples, float image[]) {
    static Plane plane = {vec(0.0f, -0.5f, 0.0f), vec(0.f, 1.f, 0.f)};
    static Sphere spheres[3] = {
        {vec(-2.0f, 0.0f, -3.5f), 0.5f}, {vec(-0.5f, 0.0f, -3.0f), 0.5f}, {vec(1.0f, 0.0f, -2.2f), 0.5f}};

    srand48(y0);

    for (int y = y0; y < y1; ++y) {
        for (int x = 0; x < w; ++x) {
            int offset = 3 * (y * w + x);
            for (int u = 0; u < nsubsamples; ++u) {
                for (int v = 0; v < nsubsamples; ++v) {
                    float px = (x + (u / (float)nsubsamples) - (w / 2.0f)) / (w / 2.0f);
                    float py = -(y + (v / (float)nsubsamples) - (h / 2.0f)) / (h / 2.0f);

                    // Scale NDC based on width/height ratio, supporting non-square image output
                    px *= (float)w / (float)h;

                    float ret = 0.f;
                    Ray ray;
                    Isect isect;

                    ray.org = vec(0.f, 0.f, 0.f);

                    ray.dir.x = px;
                    ray.dir.y = py;
                    ray.dir.z = -1.0f;
                    vnormalize(ray.dir);

                    isect.t = 1.0e+17f;
                    isect.hit = 0;

                    for (int snum = 0; snum < 3; ++snum)
                        ray_sphere_intersect(isect, ray, spheres[snum]);
                    ray_plane_intersect(isect, ray, plane);

                    if (isect.hit)
                        ret = ambient_occlusion(isect, plane, spheres);

                    // Update image for AO for this ray
                    image[offset + 0] += ret;
                    image[offset + 1] += ret;
                    image[offset + 2] += ret;
                }
            }
            // Normalize image pixels by number of samples taken per pixel
            image[offset + 0] /= nsubsamples * nsubsamples;
            image[offset + 1] /= nsubsamples * nsubsamples;
            image[offset + 2] /= nsubsamples * nsubsamples;
        }
    }
}

void ao_serial(int w, int h, int nsubsamples, float image[]) { ao_scanlines(0, h, w, h, nsubsamples, image); }