fractorium/Source/Ember/Curves.h
mfeemster 018ba26b5f --User changes
-Add support for multiple GPU devices.
  --These options are present in the command line and in Fractorium.
 -Change scheme of specifying devices from platform,device to just total device index.
  --Single number on the command line.
  --Change from combo boxes for device selection to a table of all devices in Fractorium.
 -Temporal samples defaults to 100 instead of 1000 which was needless overkill.

--Bug fixes
 -EmberAnimate, EmberRender, FractoriumSettings, FinalRenderDialog: Fix wrong order of arguments to Clamp() when assigning thread priority.
 -VariationsDC.h: Fix NVidia OpenCL compilation error in DCTriangleVariation.
 -FractoriumXformsColor.cpp: Checking for null pixmap pointer is not enough, must also check if the underlying buffer is null via call to QPixmap::isNull().

--Code changes
 -Ember.h: Add case for FLAME_MOTION_NONE and default in ApplyFlameMotion().
 -EmberMotion.h: Call base constructor.
 -EmberPch.h: #pragma once only on Windows.
 -EmberToXml.h:
  --Handle different types of exceptions.
  --Add default cases to ToString().
 -Isaac.h: Remove unused variable in constructor.
 -Point.h: Call base constructor in Color().
 -Renderer.h/cpp:
  --Add bool to Alloc() to only allocate memory for the histogram. Needed for multi-GPU.
  --Make CoordMap() return a const ref, not a pointer.
 -SheepTools.h:
  --Use 64-bit types like the rest of the code already does.
  --Fix some comment misspellings.
 -Timing.h: Make BeginTime(), EndTime(), ElapsedTime() and Format() be const functions.
 -Utils.h:
  --Add new functions Equal() and Split().
  --Handle more exception types in ReadFile().
  --Get rid of most legacy blending of C and C++ argument parsing.
 -XmlToEmber.h:
  --Get rid of most legacy blending of C and C++ code from flam3.
  --Remove some unused variables.
 -EmberAnimate:
  --Support multi-GPU processing that alternates full frames between devices.
  --Use OpenCLInfo instead of OpenCLWrapper for --openclinfo option.
  --Remove bucketT template parameter, and hard code float in its place.
  --If a render fails, exit since there is no point in continuing an animation with a missing frame.
  --Pass variables to threaded save better, which most likely fixes a very subtle bug that existed before.
  --Remove some unused variables.
 -EmberGenome, EmberRender:
  --Support multi-GPU processing that alternates full frames between devices.
  --Use OpenCLInfo instead of OpenCLWrapper for --openclinfo option.
  --Remove bucketT template parameter, and hard code float in its place.
 -EmberRender:
  --Support multi-GPU processing that alternates full frames between devices.
  --Use OpenCLInfo instead of OpenCLWrapper for --openclinfo option.
  --Remove bucketT template parameter, and hard code float in its place.
  --Only print values when not rendering with OpenCL, since they're always 0 in that case.
 -EmberCLPch.h:
  --#pragma once only on Windows.
  --#include <atomic>.
 -IterOpenCLKernelCreator.h: Add new kernel for summing two histograms. This is needed for multi-GPU.
 -OpenCLWrapper.h:
  --Move all OpenCL info related code into its own class OpenCLInfo.
  --Add members to cache the values of global memory size and max allocation size.
 -RendererCL.h/cpp:
  --Redesign to accomodate multi-GPU.
  --Constructor now takes a vector of devices.
  --Remove DumpErrorReport() function, it's handled in the base.
  --ClearBuffer(), ReadPoints(), WritePoints(), ReadHist() and WriteHist() now optionally take a device index as a parameter.
  --MakeDmap() override and m_DmapCL member removed because it no longer applies since the histogram is always float since the last commit.
  --Add new function SumDeviceHist() to sum histograms from two devices by first copying to a temporary on the host, then a temporary on the device, then summing.
  --m_Calls member removed, as it's now per-device.
  --OpenCLWrapper removed.
  --m_Seeds member is now a vector of vector of seeds, to accomodate a separate and different array of seeds for each device.
  --Added member m_Devices, a vector of unique_ptr of RendererCLDevice.
 -EmberCommon.h
  --Added Devices() function to convert from a vector of device indices to a vector of platform,device indices.
  --Changed CreateRenderer() to accept a vector of devices to create a single RendererCL which will split work across multiple devices.
  --Added CreateRenderers() function to accept a vector of devices to create multiple RendererCL, each which will render on a single device.
  --Add more comments to some existing functions.
 -EmberCommonPch.h: #pragma once only on Windows.
 -EmberOptions.h:
  --Remove --platform option, it's just sequential device number now with the --device option.
  --Make --out be OPT_USE_RENDER instead of OPT_RENDER_ANIM since it's an error condition when animating. It makes no sense to write all frames to a single image.
  --Add Devices() function to parse comma separated --device option string and return a vector of device indices.
  --Make int and uint types be 64-bit, so intmax_t and size_t.
  --Make better use of macros.
 -JpegUtils.h: Make string parameters to WriteJpeg() and WritePng() be const ref.
 -All project files: Turn off buffer security check option in Visual Studio (/Gs-)
 -deployment.pri: Remove the line OTHER_FILES +=, it's pointless and was causing problems.
 -Ember.pro, EmberCL.pro: Add CONFIG += plugin, otherwise it wouldn't link.
 -EmberCL.pro: Add new files for multi-GPU support.
 -build_all.sh: use -j4 and QMAKE=${QMAKE:/usr/bin/qmake}
 -shared_settings.pri:
  -Add version string.
  -Remove old DESTDIR definitions.
  -Add the following lines or else nothing would build:
   CONFIG(release, debug|release) {
    CONFIG += warn_off
    DESTDIR = ../../../Bin/release
   }

   CONFIG(debug, debug|release) {
    DESTDIR = ../../../Bin/debug
   }

   QMAKE_POST_LINK += $$quote(cp --update ../../../Data/flam3-palettes.xml $${DESTDIR}$$escape_expand(\n\t))
   LIBS += -L/usr/lib -lpthread
 -AboutDialog.ui: Another futile attempt to make it look correct on Linux.
 -FinalRenderDialog.h/cpp:
  --Add support for multi-GPU.
  --Change from combo boxes for device selection to a table of all devices.
  --Ensure device selection makes sense.
  --Remove "FinalRender" prefix of various function names, it's implied given the context.
 -FinalRenderEmberController.h/cpp:
  --Add support for multi-GPU.
  --Change m_FinishedImageCount to be atomic.
  --Move CancelRender() from the base to FinalRenderEmberController<T>.
  --Refactor RenderComplete() to omit any progress related functionality or image saving since it can be potentially ran in a thread.
  --Consolidate setting various renderer fields into SyncGuiToRenderer().
 -Fractorium.cpp: Allow for resizing of the options dialog to show the entire device table.
 -FractoriumCommon.h: Add various functions to handle a table showing the available OpenCL devices on the system.
 -FractoriumEmberController.h/cpp: Remove m_FinalImageIndex, it's no longer needed.
 -FractoriumRender.cpp: Scale the interactive sub batch count and quality by the number of devices used.
 -FractoriumSettings.h/cpp:
  --Temporal samples defaults to 100 instead of 1000 which was needless overkill.
  --Add multi-GPU support, remove old device,platform pair.
 -FractoriumToolbar.cpp: Disable OpenCL toolbar button if there are no devices present on the system.
 -FractoriumOptionsDialog.h/cpp:
  --Add support for multi-GPU.
  --Consolidate more assignments in DataToGui().
  --Enable/disable CPU/OpenCL items in response to OpenCL checkbox event.
 -Misc: Convert almost everything to size_t for unsigned, intmax_t for signed.
2015-09-12 18:33:45 -07:00

285 lines
7.4 KiB
C++

#pragma once
#include "Utils.h"
#include "Isaac.h"
/// <summary>
/// Curves class.
/// </summary>
namespace EmberNs
{
/// <summary>
/// The Bezier curves used to adjust the colors during final accumulation.
/// This functionality was gotten directly from Apophysis.
/// </summary>
template <typename T>
class EMBER_API Curves
{
public:
/// <summary>
/// Constructor which sets the curve and weight values to their defaults.
/// </summary>
Curves(bool init = false)
{
if (init)
Init();
else
Clear();
}
/// <summary>
/// Default copy constructor.
/// </summary>
/// <param name="curves">The Curves object to copy</param>
Curves(const Curves<T>& curves)
{
Curves<T>::operator=<T>(curves);
}
/// <summary>
/// Copy constructor to copy a Curves object of type U.
/// Special case that must be here in the header because it has
/// a second template parameter.
/// </summary>
/// <param name="curves">The Curves object to copy</param>
template <typename U>
Curves(const Curves<U>& curves)
{
Curves<T>::operator=<U>(curves);
}
/// <summary>
/// Default assignment operator.
/// </summary>
/// <param name="curves">The Curves object to copy</param>
Curves<T>& operator = (const Curves<T>& curves)
{
if (this != &curves)
Curves<T>::operator=<T>(curves);
return *this;
}
/// <summary>
/// Assignment operator to assign a Curves object of type U.
/// </summary>
/// <param name="curves">The Curves object to copy</param>
/// <returns>Reference to updated self</returns>
template <typename U>
Curves<T>& operator = (const Curves<U>& curves)
{
for (size_t i = 0; i < 4; i++)
{
m_Points[i][0].x = T(curves.m_Points[i][0].x); m_Points[i][0].y = T(curves.m_Points[i][0].y); m_Weights[i].x = T(curves.m_Weights[i].x);
m_Points[i][1].x = T(curves.m_Points[i][1].x); m_Points[i][1].y = T(curves.m_Points[i][1].y); m_Weights[i].y = T(curves.m_Weights[i].y);
m_Points[i][2].x = T(curves.m_Points[i][2].x); m_Points[i][2].y = T(curves.m_Points[i][2].y); m_Weights[i].z = T(curves.m_Weights[i].z);
m_Points[i][3].x = T(curves.m_Points[i][3].x); m_Points[i][3].y = T(curves.m_Points[i][3].y); m_Weights[i].w = T(curves.m_Weights[i].w);
}
return *this;
}
/// <summary>
/// Unary addition operator to add a Curves<T> object to this one.
/// </summary>
/// <param name="curves">The Curves object to add</param>
/// <returns>Reference to updated self</returns>
Curves<T>& operator += (const Curves<T>& curves)
{
for (size_t i = 0; i < 4; i++)
{
m_Points[i][0] += curves.m_Points[i][0];
m_Points[i][1] += curves.m_Points[i][1];
m_Points[i][2] += curves.m_Points[i][2];
m_Points[i][3] += curves.m_Points[i][3];
m_Weights[i] += curves.m_Weights[i];
}
return *this;
}
/// <summary>
/// Unary multiplication operator to multiply this object by another Curves<T> object.
/// </summary>
/// <param name="curves">The Curves object to multiply this one by</param>
/// <returns>Reference to updated self</returns>
Curves<T>& operator *= (const Curves<T>& curves)
{
for (size_t i = 0; i < 4; i++)
{
m_Points[i][0] *= curves.m_Points[i][0];
m_Points[i][1] *= curves.m_Points[i][1];
m_Points[i][2] *= curves.m_Points[i][2];
m_Points[i][3] *= curves.m_Points[i][3];
m_Weights[i] *= curves.m_Weights[i];
}
return *this;
}
/// <summary>
/// Unary multiplication operator to multiply this object by a scalar of type T.
/// </summary>
/// <param name="t">The scalar to multiply this object by</param>
/// <returns>Reference to updated self</returns>
Curves<T>& operator *= (const T& t)
{
for (size_t i = 0; i < 4; i++)
{
m_Points[i][0] *= t;
m_Points[i][1] *= t;
m_Points[i][2] *= t;
m_Points[i][3] *= t;
m_Weights[i] *= t;
}
return *this;
}
/// <summary>
/// Set the curve and weight values to their default state.
/// </summary>
void Init()
{
for (size_t i = 0; i < 4; i++)
{
m_Points[i][0] = v2T(0);//0,0 -> 0,0 -> 1,1 -> 1,1.
m_Points[i][1] = v2T(0);
m_Points[i][2] = v2T(1);
m_Points[i][3] = v2T(1);
m_Weights[i] = v4T(1);
}
}
/// <summary>
/// Set the curve and weight values to an empty state.
/// </summary>
void Clear()
{
memset(&m_Points, 0, sizeof(m_Points));
memset(&m_Weights, 0, sizeof(m_Weights));
}
/// <summary>
/// Whether any points are not the default.
/// </summary>
/// <returns>True if any point has been set to a value other than the default, else false.</returns>
bool CurvesSet()
{
bool set = false;
for (size_t i = 0; i < 4; i++)
{
if ((m_Points[i][0] != v2T(0)) ||
(m_Points[i][1] != v2T(0)) ||
(m_Points[i][2] != v2T(1)) ||
(m_Points[i][3] != v2T(1)))
{
set = true;
break;
}
}
return set;
}
/// <summary>
/// Wrapper around calling BezierSolve() on each of the 4 weight and point vectors.
/// </summary>
/// <param name="t">The position to apply</param>
/// <returns>vec4<T> that contains the y component of the solution for each vector in each component</returns>
v4T BezierFunc(const T& t)
{
v4T result;
v2T solution(0, 0);
BezierSolve(t, m_Points[0], &m_Weights[0], solution); result.x = solution.y;
BezierSolve(t, m_Points[1], &m_Weights[1], solution); result.y = solution.y;
BezierSolve(t, m_Points[2], &m_Weights[2], solution); result.z = solution.y;
BezierSolve(t, m_Points[3], &m_Weights[3], solution); result.w = solution.y;
return result;
}
private:
/// <summary>
/// Solve the given point and weight vectors for the given position and store
/// the output in the solution vec2 passed in.
/// </summary>
/// <param name="t">The position to apply</param>
/// <param name="src">A pointer to an array of 4 vec2</param>
/// <param name="w">A pointer to an array of 4 weights</param>
/// <param name="solution">The vec2 to store the solution in</param>
void BezierSolve(const T& t, v2T* src, v4T* w, v2T& solution)
{
T s, s2, s3, t2, t3, nom_x, nom_y, denom;
s = 1 - t;
s2 = s * s;
s3 = s * s * s;
t2 = t * t;
t3 = t * t * t;
nom_x = (w->x * s3 * src->x) + (w->y * s2 * 3 * t * src[1].x) + (w->z * s * 3 * t2 * src[2].x) + (w->w * t3 * src[3].x);
nom_y = (w->x * s3 * src->y) + (w->y * s2 * 3 * t * src[1].y) + (w->z * s * 3 * t2 * src[2].y) + (w->w * t3 * src[3].y);
denom = (w->x * s3) + (w->y * s2 * 3 * t) + (w->z * s * 3 * t2) + (w->w * t3);
if (std::isnan(nom_x) || std::isnan(nom_y) || std::isnan(denom) || denom == 0)
return;
solution.x = nom_x / denom;
solution.y = nom_y / denom;
}
public:
v2T m_Points[4][4];
v4T m_Weights[4];
};
//Must declare this outside of the class to provide for both orders of parameters.
/// <summary>
/// Multiplication operator to multiply a Curves<T> object by a scalar of type T.
/// </summary>
/// <param name="curves">The curves object to multiply</param>
/// <param name="t">The scalar to multiply curves by by</param>
/// <returns>Copy of new Curves<T></returns>
template<typename T>
Curves<T> operator * (const Curves<T>& curves, const T& t)
{
Curves<T> c(curves);
for (size_t i = 0; i < 4; i++)
{
c.m_Points[i][0] *= t;
c.m_Points[i][1] *= t;
c.m_Points[i][2] *= t;
c.m_Points[i][3] *= t;
c.m_Weights[i] *= t;
}
return c;
}
/// <summary>
/// Multiplication operator for reverse order.
/// </summary>
/// <param name="t">The scalar to multiply curves by by</param>
/// <param name="curves">The curves object to multiply</param>
/// <returns>Copy of new Curves<T></returns>
template<typename T>
Curves<T> operator * (const T& t, const Curves<T>& curves)
{
return curves * t;
}
}