Kévin Dietrich
bbe6d44928
This optimizes device updates (during user edits or frame changes in the viewport) by avoiding unnecessary computations. To achieve this, we use a combination of the sockets' update flags as well as some new flags passed to the various managers when tagging for an update to tell exactly what the tagging is for (e.g. shader was modified, object was removed, etc.). Besides avoiding recomputations, we also avoid resending to the devices unmodified data arrays, thus reducing bandwidth usage. For OptiX and Embree, BVH packing was also multithreaded. The performance improvements may vary depending on the used device (CPU or GPU), and the content of the scene. Simple scenes (e.g. with no adaptive subdivision or volumes) rendered using OptiX will benefit from this work the most. On average, for a variety of animated scenes, this gives a 3x speedup. Reviewed By: #cycles, brecht Maniphest Tasks: T79174 Differential Revision: https://developer.blender.org/D9555
150 lines
3.9 KiB
C++
150 lines
3.9 KiB
C++
/*
|
|
* Copyright 2011-2013 Blender Foundation
|
|
*
|
|
* Licensed under the Apache License, Version 2.0 (the "License");
|
|
* you may not use this file except in compliance with the License.
|
|
* You may obtain a copy of the License at
|
|
*
|
|
* http://www.apache.org/licenses/LICENSE-2.0
|
|
*
|
|
* Unless required by applicable law or agreed to in writing, software
|
|
* distributed under the License is distributed on an "AS IS" BASIS,
|
|
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
* See the License for the specific language governing permissions and
|
|
* limitations under the License.
|
|
*/
|
|
|
|
#include "render/particles.h"
|
|
#include "device/device.h"
|
|
#include "render/scene.h"
|
|
#include "render/stats.h"
|
|
|
|
#include "util/util_foreach.h"
|
|
#include "util/util_hash.h"
|
|
#include "util/util_logging.h"
|
|
#include "util/util_map.h"
|
|
#include "util/util_progress.h"
|
|
#include "util/util_vector.h"
|
|
|
|
CCL_NAMESPACE_BEGIN
|
|
|
|
/* Particle System */
|
|
|
|
NODE_DEFINE(ParticleSystem)
|
|
{
|
|
NodeType *type = NodeType::add("particle_system", create);
|
|
return type;
|
|
}
|
|
|
|
ParticleSystem::ParticleSystem() : Node(node_type)
|
|
{
|
|
}
|
|
|
|
ParticleSystem::~ParticleSystem()
|
|
{
|
|
}
|
|
|
|
void ParticleSystem::tag_update(Scene *scene)
|
|
{
|
|
scene->particle_system_manager->tag_update(scene);
|
|
}
|
|
|
|
/* Particle System Manager */
|
|
|
|
ParticleSystemManager::ParticleSystemManager()
|
|
{
|
|
need_update_ = true;
|
|
}
|
|
|
|
ParticleSystemManager::~ParticleSystemManager()
|
|
{
|
|
}
|
|
|
|
void ParticleSystemManager::device_update_particles(Device *,
|
|
DeviceScene *dscene,
|
|
Scene *scene,
|
|
Progress &progress)
|
|
{
|
|
/* count particles.
|
|
* adds one dummy particle at the beginning to avoid invalid lookups,
|
|
* in case a shader uses particle info without actual particle data. */
|
|
int num_particles = 1;
|
|
for (size_t j = 0; j < scene->particle_systems.size(); j++)
|
|
num_particles += scene->particle_systems[j]->particles.size();
|
|
|
|
KernelParticle *kparticles = dscene->particles.alloc(num_particles);
|
|
|
|
/* dummy particle */
|
|
memset(kparticles, 0, sizeof(KernelParticle));
|
|
|
|
int i = 1;
|
|
for (size_t j = 0; j < scene->particle_systems.size(); j++) {
|
|
ParticleSystem *psys = scene->particle_systems[j];
|
|
|
|
for (size_t k = 0; k < psys->particles.size(); k++) {
|
|
/* pack in texture */
|
|
Particle &pa = psys->particles[k];
|
|
|
|
kparticles[i].index = pa.index;
|
|
kparticles[i].age = pa.age;
|
|
kparticles[i].lifetime = pa.lifetime;
|
|
kparticles[i].size = pa.size;
|
|
kparticles[i].rotation = pa.rotation;
|
|
kparticles[i].location = float3_to_float4(pa.location);
|
|
kparticles[i].velocity = float3_to_float4(pa.velocity);
|
|
kparticles[i].angular_velocity = float3_to_float4(pa.angular_velocity);
|
|
|
|
i++;
|
|
|
|
if (progress.get_cancel())
|
|
return;
|
|
}
|
|
}
|
|
|
|
dscene->particles.copy_to_device();
|
|
}
|
|
|
|
void ParticleSystemManager::device_update(Device *device,
|
|
DeviceScene *dscene,
|
|
Scene *scene,
|
|
Progress &progress)
|
|
{
|
|
if (!need_update())
|
|
return;
|
|
|
|
scoped_callback_timer timer([scene](double time) {
|
|
if (scene->update_stats) {
|
|
scene->update_stats->particles.times.add_entry({"device_update", time});
|
|
}
|
|
});
|
|
|
|
VLOG(1) << "Total " << scene->particle_systems.size() << " particle systems.";
|
|
|
|
device_free(device, dscene);
|
|
|
|
progress.set_status("Updating Particle Systems", "Copying Particles to device");
|
|
device_update_particles(device, dscene, scene, progress);
|
|
|
|
if (progress.get_cancel())
|
|
return;
|
|
|
|
need_update_ = false;
|
|
}
|
|
|
|
void ParticleSystemManager::device_free(Device *, DeviceScene *dscene)
|
|
{
|
|
dscene->particles.free();
|
|
}
|
|
|
|
void ParticleSystemManager::tag_update(Scene * /*scene*/)
|
|
{
|
|
need_update_ = true;
|
|
}
|
|
|
|
bool ParticleSystemManager::need_update() const
|
|
{
|
|
return need_update_;
|
|
}
|
|
|
|
CCL_NAMESPACE_END
|