--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.

Source/EmberTester/EmberTester.cpp

@@ -714,7 +714,7 @@ bool TestParVars()
 			names.reserve(parVar->ParamCount());
 			addresses.reserve(parVar->ParamCount());
 
-			for (uint j = 0; j < parVar->ParamCount(); j++)
+			for (size_t j = 0; j < parVar->ParamCount(); j++)
 			{
 				if (std::find(names.begin(), names.end(), params[j].Name()) != names.end())
 				{
@@ -1449,13 +1449,13 @@ void TestVarsSimilar()
 
 				if (parVar)
 				{
-					for (uint v = 0; v < parVar->ParamCount(); v++)
+					for (size_t v = 0; v < parVar->ParamCount(); v++)
 						parVar->SetParamVal(v, (T)iter);
 				}
 
 				if (parVarComp)
 				{
-					for (uint v = 0; v < parVarComp->ParamCount(); v++)
+					for (size_t v = 0; v < parVarComp->ParamCount(); v++)
 						parVarComp->SetParamVal(v, (T)iter);
 				}
 
@@ -1878,6 +1878,46 @@ double RandD(QTIsaac<ISAAC_SIZE, ISAAC_INT>& rand)
 //	double points[4];
 //};
 
+void TestThreadedKernel()
+{
+	OpenCLWrapper wrapper1, wrapper2;
+
+	if (wrapper1.Init(1, 0) && wrapper2.Init(2, 0))
+	{
+		string k = ConstantDefinesString(false) + "\n__kernel void Kern()\n"
+			"{\n"
+			"	int gid = GLOBAL_ID_X + GLOBAL_ID_Y;\n"
+			"}\n"
+			"\n";
+
+		if (wrapper1.AddProgram("prog1", k, "Kern", false) &&
+			wrapper2.AddProgram("prog1", k, "Kern", false))
+		{
+			cout << "Builds ok, now run..." << endl;
+
+			std::thread th1([&]()
+			{
+				if (wrapper1.RunKernel(0, 256, 16, 1, 16, 16, 1))
+				{
+					cout << "Successful run inside thread 1..." << endl;
+				}
+			});
+
+			std::thread th2([&]()
+			{
+				if (wrapper2.RunKernel(0, 256, 16, 1, 16, 16, 1))
+				{
+					cout << "Successful run inside thread 2..." << endl;
+				}
+			});
+
+			th1.join();
+			th2.join();
+			cout << "Successful join of kernel thread..." << endl;
+		}
+	}
+}
+
 int _tmain(int argc, _TCHAR* argv[])
 {
 	//int i;
@@ -1885,12 +1925,14 @@ int _tmain(int argc, _TCHAR* argv[])
 	QTIsaac<ISAAC_SIZE, ISAAC_INT> rand(1, 2, 3);
 	mt19937 meow(1729);
 
-	PaletteList<float> palf;
+	TestThreadedKernel();
+
+	/*PaletteList<float> palf;
 	Palette<float>* pal = palf.GetRandomPalette();
 
 	cout << pal->Size() << endl;
 
-	/*double d = 1;
+	double d = 1;
 
 	for (int i = 0; i < 10; i++)
 	{