fractorium/Source/Ember/RendererBase.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

235 lines
7.8 KiB
C++

#pragma once
#include "Utils.h"
#include "Ember.h"
#include "DensityFilter.h"
/// <summary>
/// RendererBase, RenderCallback and EmberStats classes.
/// </summary>
namespace EmberNs
{
/// <summary>
/// Function pointers present a major restriction when dealing
/// with member functions, and that is they can only point to
/// static ones. So instead of a straight function pointer, use
/// a callback class with a single virtual callback
/// member function.
/// Template argument expected to be float or double.
/// </summary>
class EMBER_API RenderCallback
{
public:
/// <summary>
/// Virtual destructor to ensure anything declared in derived classes gets cleaned up.
/// </summary>
virtual ~RenderCallback() { }
/// <summary>
/// Empty progress function to be implemented in derived classes to take action on progress updates.
/// </summary>
/// <param name="ember">The ember currently being rendered</param>
/// <param name="foo">An extra dummy parameter</param>
/// <param name="fraction">The progress fraction from 0-100</param>
/// <param name="stage">The stage of iteration. 1 is iterating, 2 is density filtering, 2 is final accumulation.</param>
/// <param name="etaMs">The estimated milliseconds to completion of the current stage</param>
/// <returns>Override should return 0 if an abort is requested, else 1 to continue rendering</returns>
virtual int ProgressFunc(Ember<float>& ember, void* foo, double fraction, int stage, double etaMs) { return 0; }
virtual int ProgressFunc(Ember<double>& ember, void* foo, double fraction, int stage, double etaMs) { return 0; }
};
/// <summary>
/// Render statistics for the number of iterations ran,
/// number of bad values calculated during iteration, and
/// the total time for the entire render from the start of
/// iteration to the end of final accumulation.
/// </summary>
class EMBER_API EmberStats
{
public:
/// <summary>
/// Constructor which sets all values to 0.
/// </summary>
EmberStats()
{
Clear();
}
void Clear()
{
m_Iters = 0;
m_Badvals = 0;
m_IterMs = 0;
m_RenderMs = 0;
}
EmberStats& operator += (const EmberStats& stats)
{
m_Iters += stats.m_Iters;
m_Badvals += stats.m_Badvals;
m_IterMs += stats.m_IterMs;
m_RenderMs += stats.m_RenderMs;
return *this;
}
size_t m_Iters, m_Badvals;
double m_IterMs, m_RenderMs;
};
/// <summary>
/// The types of available renderers.
/// Add more in the future as different rendering methods are experimented with.
/// Possible values might be: CPU+OpenGL, Particle, Inverse.
/// </summary>
enum eRendererType { CPU_RENDERER, OPENCL_RENDERER };
/// <summary>
/// A base class with virtual functions to allow both templating and polymorphism to work together.
/// Derived classes will implement all of these functions.
/// Note that functions which return a decimal number use the most precise type, double.
/// </summary>
class EMBER_API RendererBase : public EmberReport
{
//using EmberReport::m_ErrorReport;
public:
RendererBase();
virtual ~RendererBase() { }
//Non-virtual processing functions.
void ChangeVal(std::function<void(void)> func, eProcessAction action);
size_t HistMemoryRequired(size_t strips);
pair<size_t, size_t> MemoryRequired(size_t strips, bool includeFinal, bool threadedWrite);
vector<QTIsaac<ISAAC_SIZE, ISAAC_INT>> RandVec();
bool PrepFinalAccumVector(vector<byte>& pixels);
//Virtual processing functions.
virtual bool Ok() const;
virtual size_t MemoryAvailable();
virtual void SetEmber(Ember<float>& ember, eProcessAction action = FULL_RENDER) { }
virtual void SetEmber(vector<Ember<float>>& embers) { }
virtual void SetEmber(Ember<double>& ember, eProcessAction action = FULL_RENDER) { }
virtual void SetEmber(vector<Ember<double>>& embers) { }
virtual bool RandVec(vector<QTIsaac<ISAAC_SIZE, ISAAC_INT>>& randVec);
//Abstract processing functions.
virtual bool CreateDEFilter(bool& newAlloc) = 0;
virtual bool CreateSpatialFilter(bool& newAlloc) = 0;
virtual bool CreateTemporalFilter(bool& newAlloc) = 0;
virtual void ComputeBounds() = 0;
virtual void ComputeQuality() = 0;
virtual void ComputeCamera() = 0;
virtual eRenderStatus Run(vector<byte>& finalImage, double time = 0, size_t subBatchCountOverride = 0, bool forceOutput = false, size_t finalOffset = 0) = 0;
virtual EmberImageComments ImageComments(const EmberStats& stats, size_t printEditDepth = 0, bool intPalette = false, bool hexPalette = true) = 0;
virtual DensityFilterBase* GetDensityFilter() = 0;
//Non-virtual renderer properties, getters only.
size_t SuperRasW() const;
size_t SuperRasH() const;
size_t SuperSize() const;
size_t FinalRowSize() const;
size_t FinalDimensions() const;
size_t FinalBufferSize() const;
size_t PixelSize() const;
size_t GutterWidth() const;
size_t DensityFilterOffset() const;
size_t TotalIterCount(size_t strips) const;
size_t ItersPerTemporalSample() const;
eProcessState ProcessState() const;
eProcessAction ProcessAction() const;
EmberStats Stats() const;
//Non-virtual render getters and setters.
bool LockAccum() const;
void LockAccum(bool lockAccum);
bool EarlyClip() const;
void EarlyClip(bool earlyClip);
bool YAxisUp() const;
void YAxisUp(bool yup);
bool InsertPalette() const;
void InsertPalette(bool insertPalette);
bool ReclaimOnResize() const;
void ReclaimOnResize(bool reclaimOnResize);
bool Transparency() const;
void Transparency(bool transparency);
void Callback(RenderCallback* callback);
void ThreadCount(size_t threads, const char* seedString = nullptr);
size_t BytesPerChannel() const;
void BytesPerChannel(size_t bytesPerChannel);
size_t NumChannels() const;
eThreadPriority Priority() const;
void Priority(eThreadPriority priority);
eInteractiveFilter InteractiveFilter() const;
void InteractiveFilter(eInteractiveFilter filter);
//Virtual render properties, getters and setters.
virtual void NumChannels(size_t numChannels);
virtual size_t ThreadCount() const;
virtual eRendererType RendererType() const;
//Abstract render properties, getters only.
virtual size_t TemporalSamples() const = 0;
virtual size_t HistBucketSize() const = 0;
virtual size_t FinalRasW() const = 0;
virtual size_t FinalRasH() const = 0;
virtual size_t SubBatchSize() const = 0;
virtual size_t FuseCount() const = 0;
virtual double ScaledQuality() const = 0;
virtual double LowerLeftX(bool gutter = true) const = 0;
virtual double LowerLeftY(bool gutter = true) const = 0;
virtual double UpperRightX(bool gutter = true) const = 0;
virtual double UpperRightY(bool gutter = true) const = 0;
//Non-virtual threading control.
void Reset();
void EnterRender();
void LeaveRender();
void EnterFinalAccum();
void LeaveFinalAccum();
void EnterResize();
void LeaveResize();
void Abort();
bool Aborted();
bool InRender();
bool InFinalAccum();
void* m_ProgressParameter;
protected:
bool m_EarlyClip;
bool m_YAxisUp;
bool m_Transparency;
bool m_LockAccum;
bool m_InRender;
bool m_InFinalAccum;
bool m_InsertPalette;
bool m_ReclaimOnResize;
bool m_CurvesSet;
volatile bool m_Abort;
size_t m_SuperRasW;
size_t m_SuperRasH;
size_t m_SuperSize;
size_t m_GutterWidth;
size_t m_DensityFilterOffset;
size_t m_NumChannels;
size_t m_BytesPerChannel;
size_t m_ThreadsToUse;
size_t m_VibGamCount;
size_t m_LastTemporalSample;
size_t m_LastIter;
double m_LastIterPercent;
eThreadPriority m_Priority;
eProcessAction m_ProcessAction;
eProcessState m_ProcessState;
eInteractiveFilter m_InteractiveFilter;
EmberStats m_Stats;
RenderCallback* m_Callback;
vector<size_t> m_SubBatch;
vector<size_t> m_BadVals;
vector<QTIsaac<ISAAC_SIZE, ISAAC_INT>> m_Rand;
auto_ptr<tbb::task_group> m_TaskGroup;
CriticalSection m_RenderingCs, m_AccumCs, m_FinalAccumCs, m_ResizeCs;
Timing m_RenderTimer, m_IterTimer, m_ProgressTimer;
};
}