blender/intern/cycles/util/util_task.cpp
Brecht Van Lommel 07b2241fb1 Cycles: merging features from tomato branch.
=== BVH build time optimizations ===

* BVH building was multithreaded. Not all building is multithreaded, packing
  and the initial bounding/splitting is still single threaded, but recursive
  splitting is, which was the main bottleneck.

* Object splitting now uses binning rather than sorting of all elements, using
  code from the Embree raytracer from Intel.
  http://software.intel.com/en-us/articles/embree-photo-realistic-ray-tracing-kernels/

* Other small changes to avoid allocations, pack memory more tightly, avoid
  some unnecessary operations, ...

These optimizations do not work yet when Spatial Splits are enabled, for that
more work is needed. There's also other optimizations still needed, in
particular for the case of many low poly objects, the packing step and node
memory allocation.

BVH raytracing time should remain about the same, but BVH build time should be
significantly reduced, test here show speedup of about 5x to 10x on a dual core
and 5x to 25x on an 8-core machine, depending on the scene.

=== Threads ===

Centralized task scheduler for multithreading, which is basically the
CPU device threading code wrapped into something reusable.

Basic idea is that there is a single TaskScheduler that keeps a pool of threads,
one for each core. Other places in the code can then create a TaskPool that they
can drop Tasks in to be executed by the scheduler, and wait for them to complete
or cancel them early.

=== Normal ====

Added a Normal output to the texture coordinate node. This currently
gives the object space normal, which is the same under object animation.

In the future this might become a "generated" normal so it's also stable for
deforming objects, but for now it's already useful for non-deforming objects.

=== Render Layers ===

Per render layer Samples control, leaving it to 0 will use the common scene
setting.

Environment pass will now render environment even if film is set to transparent.

Exclude Layers" added. Scene layers (all object that influence the render,
directly or indirectly) are shared between all render layers. However sometimes
it's useful to leave out some object influence for a particular render layer.
That's what this option allows you to do.

=== Filter Glossy ===

When using a value higher than 0.0, this will blur glossy reflections after
blurry bounces, to reduce noise at the cost of accuracy. 1.0 is a good
starting value to tweak.

Some light paths have a low probability of being found while contributing much
light to the pixel. As a result these light paths will be found in some pixels
and not in others, causing fireflies. An example of such a difficult path might
be a small light that is causing a small specular highlight on a sharp glossy
material, which we are seeing through a rough glossy material. With path tracing
it is difficult to find the specular highlight, but if we increase the roughness
on the material the highlight gets bigger and softer, and so easier to find.

Often this blurring will be hardly noticeable, because we are seeing it through
a blurry material anyway, but there are also cases where this will lead to a
loss of detail in lighting.
2012-04-28 08:53:59 +00:00

224 lines
4.2 KiB
C++

/*
* Copyright 2011, Blender Foundation.
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License
* as published by the Free Software Foundation; either version 2
* of the License, or (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software Foundation,
* Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
*/
#include "util_debug.h"
#include "util_foreach.h"
#include "util_system.h"
#include "util_task.h"
CCL_NAMESPACE_BEGIN
/* Task Pool */
TaskPool::TaskPool(const TaskRunFunction& run_)
{
num = 0;
num_done = 0;
do_cancel = false;
run = run_;
}
TaskPool::~TaskPool()
{
stop();
}
void TaskPool::push(Task *task, bool front)
{
TaskScheduler::Entry entry;
entry.task = task;
entry.pool = this;
TaskScheduler::push(entry, front);
}
void TaskPool::wait()
{
thread_scoped_lock lock(done_mutex);
while(num_done != num)
done_cond.wait(lock);
}
void TaskPool::cancel()
{
TaskScheduler::clear(this);
do_cancel = true;
wait();
do_cancel = false;
}
void TaskPool::stop()
{
TaskScheduler::clear(this);
assert(num_done == num);
}
bool TaskPool::cancelled()
{
return do_cancel;
}
void TaskPool::done_increase(int done)
{
done_mutex.lock();
num_done += done;
done_mutex.unlock();
assert(num_done <= num);
done_cond.notify_all();
}
/* Task Scheduler */
thread_mutex TaskScheduler::mutex;
int TaskScheduler::users = 0;
vector<thread*> TaskScheduler::threads;
volatile bool TaskScheduler::do_exit = false;
list<TaskScheduler::Entry> TaskScheduler::queue;
thread_mutex TaskScheduler::queue_mutex;
thread_condition_variable TaskScheduler::queue_cond;
void TaskScheduler::init(int num_threads)
{
thread_scoped_lock lock(mutex);
/* multiple cycles instances can use this task scheduler, sharing the same
threads, so we keep track of the number of users. */
if(users == 0) {
do_exit = false;
/* launch threads that will be waiting for work */
if(num_threads == 0)
num_threads = system_cpu_thread_count();
threads.resize(num_threads);
for(size_t i = 0; i < threads.size(); i++)
threads[i] = new thread(function_bind(&TaskScheduler::thread_run, i));
}
users++;
}
void TaskScheduler::exit()
{
thread_scoped_lock lock(mutex);
users--;
if(users == 0) {
/* stop all waiting threads */
do_exit = true;
TaskScheduler::queue_cond.notify_all();
/* delete threads */
foreach(thread *t, threads) {
t->join();
delete t;
}
threads.clear();
}
}
bool TaskScheduler::thread_wait_pop(Entry& entry)
{
thread_scoped_lock lock(queue_mutex);
while(queue.empty() && !do_exit)
queue_cond.wait(lock);
if(queue.empty()) {
assert(do_exit);
return false;
}
entry = queue.front();
queue.pop_front();
return true;
}
void TaskScheduler::thread_run(int thread_id)
{
Entry entry;
/* todo: test affinity/denormal mask */
/* keep popping off tasks */
while(thread_wait_pop(entry)) {
/* run task */
entry.pool->run(entry.task, thread_id);
/* delete task */
delete entry.task;
/* notify pool task was done */
entry.pool->done_increase(1);
}
}
void TaskScheduler::push(Entry& entry, bool front)
{
/* add entry to queue */
TaskScheduler::queue_mutex.lock();
if(front)
TaskScheduler::queue.push_front(entry);
else
TaskScheduler::queue.push_back(entry);
entry.pool->num++;
TaskScheduler::queue_mutex.unlock();
TaskScheduler::queue_cond.notify_one();
}
void TaskScheduler::clear(TaskPool *pool)
{
thread_scoped_lock lock(TaskScheduler::queue_mutex);
/* erase all tasks from this pool from the queue */
list<TaskScheduler::Entry>::iterator it = TaskScheduler::queue.begin();
int done = 0;
while(it != TaskScheduler::queue.end()) {
TaskScheduler::Entry& entry = *it;
if(entry.pool == pool) {
done++;
delete entry.task;
it = TaskScheduler::queue.erase(it);
}
else
it++;
}
/* notify done */
pool->done_increase(done);
}
CCL_NAMESPACE_END