Raytracer::Raytracer(): texture(0)
{
prepareTargetBuffer(128,128);
std::shared_ptr<Clump3d> clump(new Clump3d);
//
// Cube
//
std::shared_ptr<MeshGeometry3d> geom1(new MeshGeometry3d());
cube(geom1->getMesh());
geom1->meshChanged();
geom1->setColor(GAL::P4d(1.0, 0.0, 0.0, 1.0));
std::shared_ptr<MeshGeometry3d> geom5(new MeshGeometry3d());
cube(geom5->getMesh());
geom5->meshChanged();
geom5->setColor(GAL::P4d(0.0, 0.7, 1.0, 1.0));
//
// Manifold
//
std::shared_ptr<MeshGeometry<Vertex3d> > geom3(new MeshGeometry<Vertex3d>());
manifold(geom3->getMesh());
geom3->meshChanged();
geom3->setColor(GAL::P4d(1.0, 1.0, 0.0, 1.0));
//
// Sphere
//
std::shared_ptr<SphereGeometry3d> geom2(new SphereGeometry3d(0.5));
geom2->setColor(GAL::P4d(0.0, 1.0, 1.0, 1.0));
std::shared_ptr<SphereGeometry3d> geom4(new SphereGeometry3d(0.25));
geom4->setColor(GAL::P4d(1.0, 0.8, 0.0, 1.0));
clump->addGeometry(geom1);
clump->addGeometry(geom2);
clump->addGeometry(geom3);
clump->addGeometry(geom4);
clump->addGeometry(geom5);
geom1->setTranslation(GAL::P3d(-1,-1,0));
geom2->setTranslation(GAL::P3d(0,1,0));
geom3->setTranslation(GAL::P3d(1,0.5,0));
geom3->setLocalTransform(GAL::EulerRotationX(90.0), 0);
geom4->setTranslation(GAL::P3d(1.2,1,0.8));
geom5->setTranslation(GAL::P3d(0,1,-3));
geom5->setLocalTransform(GAL::EulerRotationY(10.0), 0);
scene.addClump(clump);
std::shared_ptr<Light3d> light1(new Light3d());
light1->setPosition(GAL::P3d(1,4,-1));
light1->setDiffuseColor(GAL::P3d(0.7, 0.7, 0.7));
light1->setSpecularColor(GAL::P3d(1.0, 1.0, 1.0));
light1->setShadow(true);
light1->setSoftShadowWidth(0.05);
scene.addLight(light1);
std::shared_ptr<Light3d> light2(new Light3d());
light2->setPosition(GAL::P3d(-1,4,3));
light2->setDiffuseColor(GAL::P3d(0.7, 0.7, 0.7));
light2->setSpecularColor(GAL::P3d(1.0, 1.0, 1.0));
light2->setShadow(true);
light2->setSoftShadowWidth(0.05);
scene.addLight(light2);
camera.setFrustum(-1, 1, -1, 1, -1, -100);
camera.setTranslation(GAL::P3d(1,2,3));
camera.setLocalTransform(GAL::EulerRotationX(30.0) * GAL::EulerRotationY(15.0), 0);
camera.setFSAA(true);
camera.setRecursionDepth(3);
}
int main(int argc, char *argv[])
{
int step, ie, iside, i, j, k;
double mflops, tmax, nelt_tot = 0.0;
char Class;
logical ifmortar = false, verified;
double t2, trecs[t_last+1];
char *t_names[t_last+1];
//--------------------------------------------------------------------
// Initialize NUMA control
//--------------------------------------------------------------------
numa_initialize_env(NUMA_MIGRATE_EXISTING);
//---------------------------------------------------------------------
// Read input file (if it exists), else take
// defaults from parameters
//---------------------------------------------------------------------
FILE *fp;
if ((fp = fopen("timer.flag", "r")) != NULL) {
timeron = true;
t_names[t_total] = "total";
t_names[t_init] = "init";
t_names[t_convect] = "convect";
t_names[t_transfb_c] = "transfb_c";
t_names[t_diffusion] = "diffusion";
t_names[t_transf] = "transf";
t_names[t_transfb] = "transfb";
t_names[t_adaptation] = "adaptation";
t_names[t_transf2] = "transf+b";
t_names[t_add2] = "add2";
fclose(fp);
} else {
timeron = false;
}
printf("\n\n NAS Parallel Benchmarks (NPB3.3-OMP-C) - UA Benchmark\n\n");
if ((fp = fopen("inputua.data", "r")) != NULL) {
int result;
printf(" Reading from input file inputua.data\n");
result = fscanf(fp, "%d", &fre);
while (fgetc(fp) != '\n');
result = fscanf(fp, "%d", &niter);
while (fgetc(fp) != '\n');
result = fscanf(fp, "%d", &nmxh);
while (fgetc(fp) != '\n');
result = fscanf(fp, "%lf", &alpha);
Class = 'U';
fclose(fp);
} else {
printf(" No input file inputua.data. Using compiled defaults\n");
fre = FRE_DEFAULT;
niter = NITER_DEFAULT;
nmxh = NMXH_DEFAULT;
alpha = ALPHA_DEFAULT;
Class = CLASS_DEFAULT;
}
dlmin = pow(0.5, REFINE_MAX);
dtime = 0.04*dlmin;
printf(" Levels of refinement: %8d\n", REFINE_MAX);
printf(" Adaptation frequency: %8d\n", fre);
printf(" Time steps: %8d dt: %15.6E\n", niter, dtime);
printf(" CG iterations: %8d\n", nmxh);
printf(" Heat source radius: %8.4f\n", alpha);
printf(" Number of available threads: %8d\n", omp_get_max_threads());
printf("\n");
top_constants();
for (i = 1; i <= t_last; i++) {
timer_clear(i);
}
if (timeron) timer_start(t_init);
// set up initial mesh (single element) and solution (all zero)
create_initial_grid();
r_init_omp((double *)ta1, ntot, 0.0);
nr_init_omp((int *)sje, 4*6*nelt, -1);
init_locks();
// compute tables of coefficients and weights
coef();
geom1();
// compute the discrete laplacian operators
setdef();
// prepare for the preconditioner
setpcmo_pre();
// refine initial mesh and do some preliminary work
time = 0.0;
mortar();
prepwork();
adaptation(&ifmortar, 0);
if (timeron) timer_stop(t_init);
timer_clear(1);
time = 0.0;
for (step = 0; step <= niter; step++) {
if (step == 1) {
// reset the solution and start the timer, keep track of total no elms
r_init((double *)ta1, ntot, 0.0);
time = 0.0;
nelt_tot = 0.0;
for (i = 1; i <= t_last; i++) {
if (i != t_init) timer_clear(i);
}
timer_start(1);
}
// advance the convection step
convect(ifmortar);
if (timeron) timer_start(t_transf2);
// prepare the intital guess for cg
transf(tmort, (double *)ta1);
// compute residual for diffusion term based on intital guess
// compute the left hand side of equation, lapacian t
#pragma omp parallel default(shared) private(ie,k,j,i)
{
#pragma omp for
for (ie = 0; ie < nelt; ie++) {
laplacian(ta2[ie], ta1[ie], size_e[ie]);
}
// compute the residual
#pragma omp for
for (ie = 0; ie < nelt; ie++) {
for (k = 0; k < LX1; k++) {
for (j = 0; j < LX1; j++) {
for (i = 0; i < LX1; i++) {
trhs[ie][k][j][i] = trhs[ie][k][j][i] - ta2[ie][k][j][i];
}
}
}
}
} //end parallel
// get the residual on mortar
transfb(rmor, (double *)trhs);
if (timeron) timer_stop(t_transf2);
// apply boundary condition: zero out the residual on domain boundaries
// apply boundary conidtion to trhs
#pragma omp parallel for default(shared) private(ie,iside)
for (ie = 0; ie < nelt; ie++) {
for (iside = 0; iside < NSIDES; iside++) {
if (cbc[ie][iside] == 0) {
facev(trhs[ie], iside, 0.0);
}
}
}
// apply boundary condition to rmor
col2(rmor, tmmor, nmor);
// call the conjugate gradient iterative solver
diffusion(ifmortar);
// add convection and diffusion
if (timeron) timer_start(t_add2);
add2((double *)ta1, (double *)t, ntot);
if (timeron) timer_stop(t_add2);
// perform mesh adaptation
time = time + dtime;
if ((step != 0) && (step/fre*fre == step)) {
if (step != niter) {
adaptation(&ifmortar, step);
}
} else {
ifmortar = false;
}
nelt_tot = nelt_tot + (double)(nelt);
}
timer_stop(1);
tmax = timer_read(1);
verify(&Class, &verified);
// compute millions of collocation points advanced per second.
// diffusion: nmxh advancements, convection: 1 advancement
mflops = nelt_tot*(double)(LX1*LX1*LX1*(nmxh+1))/(tmax*1.e6);
print_results("UA", Class, REFINE_MAX, 0, 0, niter,
tmax, mflops, " coll. point advanced",
verified, NPBVERSION, COMPILETIME, CS1, CS2, CS3, CS4, CS5,
CS6, "(none)");
//---------------------------------------------------------------------
// More timers
//---------------------------------------------------------------------
if (timeron) {
for (i = 1; i <= t_last; i++) {
trecs[i] = timer_read(i);
}
if (tmax == 0.0) tmax = 1.0;
printf(" SECTION Time (secs)\n");
for (i = 1; i <= t_last; i++) {
printf(" %-10s:%9.3f (%6.2f%%)\n",
t_names[i], trecs[i], trecs[i]*100./tmax);
if (i == t_transfb_c) {
t2 = trecs[t_convect] - trecs[t_transfb_c];
printf(" --> %11s:%9.3f (%6.2f%%)\n",
"sub-convect", t2, t2*100./tmax);
} else if (i == t_transfb) {
t2 = trecs[t_diffusion] - trecs[t_transf] - trecs[t_transfb];
printf(" --> %11s:%9.3f (%6.2f%%)\n",
"sub-diffuse", t2, t2*100./tmax);
}
}
}
//--------------------------------------------------------------------
// Teardown NUMA control
//--------------------------------------------------------------------
numa_shutdown();
return 0;
}
