mirror of
https://bitbucket.org/mfeemster/fractorium.git
synced 2025-06-30 21:36:33 -04:00
--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.
This commit is contained in:
@ -8,10 +8,10 @@
|
||||
/// </summary>
|
||||
/// <param name="opt">A populated EmberOptions object which specifies all program options to be used</param>
|
||||
/// <returns>True if success, else false.</returns>
|
||||
template <typename T, typename bucketT>
|
||||
template <typename T>
|
||||
bool EmberRender(EmberOptions& opt)
|
||||
{
|
||||
OpenCLWrapper wrapper;
|
||||
EmberCLns::OpenCLInfo& info(EmberCLns::OpenCLInfo::Instance());
|
||||
|
||||
std::cout.imbue(std::locale(""));
|
||||
|
||||
@ -21,7 +21,7 @@ bool EmberRender(EmberOptions& opt)
|
||||
if (opt.OpenCLInfo())
|
||||
{
|
||||
cout << "\nOpenCL Info: " << endl;
|
||||
cout << wrapper.DumpInfo();
|
||||
cout << info.DumpInfo();
|
||||
return true;
|
||||
}
|
||||
|
||||
@ -44,8 +44,9 @@ bool EmberRender(EmberOptions& opt)
|
||||
XmlToEmber<T> parser;
|
||||
EmberToXml<T> emberToXml;
|
||||
vector<QTIsaac<ISAAC_SIZE, ISAAC_INT>> randVec;
|
||||
const vector<pair<size_t, size_t>> devices = Devices(opt.Devices());
|
||||
unique_ptr<RenderProgress<T>> progress(new RenderProgress<T>());
|
||||
unique_ptr<Renderer<T, bucketT>> renderer(CreateRenderer<T, bucketT>(opt.EmberCL() ? OPENCL_RENDERER : CPU_RENDERER, opt.Platform(), opt.Device(), false, 0, emberReport));
|
||||
unique_ptr<Renderer<T, float>> renderer(CreateRenderer<T>(opt.EmberCL() ? OPENCL_RENDERER : CPU_RENDERER, devices, false, 0, emberReport));
|
||||
vector<string> errorReport = emberReport.ErrorReport();
|
||||
|
||||
if (!errorReport.empty())
|
||||
@ -86,8 +87,11 @@ bool EmberRender(EmberOptions& opt)
|
||||
|
||||
if (opt.Verbose())
|
||||
{
|
||||
cout << "Platform: " << wrapper.PlatformName(opt.Platform()) << endl;
|
||||
cout << "Device: " << wrapper.DeviceName(opt.Platform(), opt.Device()) << endl;
|
||||
for (auto& device : devices)
|
||||
{
|
||||
cout << "Platform: " << info.PlatformName(device.first) << endl;
|
||||
cout << "Device: " << info.DeviceName(device.first, device.second) << endl;
|
||||
}
|
||||
}
|
||||
|
||||
if (opt.ThreadCount() > 1)
|
||||
@ -145,7 +149,7 @@ bool EmberRender(EmberOptions& opt)
|
||||
|
||||
//Final setup steps before running.
|
||||
os.imbue(std::locale(""));
|
||||
padding = uint(log10((double)embers.size())) + 1;
|
||||
padding = uint(log10(double(embers.size()))) + 1;
|
||||
renderer->EarlyClip(opt.EarlyClip());
|
||||
renderer->YAxisUp(opt.YAxisUp());
|
||||
renderer->LockAccum(opt.LockAccum());
|
||||
@ -154,7 +158,7 @@ bool EmberRender(EmberOptions& opt)
|
||||
renderer->Transparency(opt.Transparency());
|
||||
renderer->NumChannels(channels);
|
||||
renderer->BytesPerChannel(opt.BitsPerChannel() / 8);
|
||||
renderer->Priority((eThreadPriority)Clamp<int>((int)eThreadPriority::LOWEST, (int)eThreadPriority::HIGHEST, opt.Priority()));
|
||||
renderer->Priority(eThreadPriority(Clamp<int>(int(opt.Priority()), int(eThreadPriority::LOWEST), int(eThreadPriority::HIGHEST))));
|
||||
renderer->Callback(opt.DoProgress() ? progress.get() : nullptr);
|
||||
|
||||
for (i = 0; i < embers.size(); i++)
|
||||
@ -276,7 +280,7 @@ bool EmberRender(EmberOptions& opt)
|
||||
os << comments.m_NumIters << " / " << iterCount << " (" << std::fixed << std::setprecision(2) << ((double(stats.m_Iters) / double(iterCount)) * 100) << "%)";
|
||||
|
||||
VerbosePrint("\nIters ran/requested: " + os.str());
|
||||
VerbosePrint("Bad values: " << stats.m_Badvals);
|
||||
if (!opt.EmberCL()) VerbosePrint("Bad values: " << stats.m_Badvals);
|
||||
VerbosePrint("Render time: " + t.Format(stats.m_RenderMs));
|
||||
VerbosePrint("Pure iter time: " + t.Format(stats.m_IterMs));
|
||||
VerbosePrint("Iters/sec: " << size_t(stats.m_Iters / (stats.m_IterMs / 1000.0)) << endl);
|
||||
@ -291,7 +295,7 @@ bool EmberRender(EmberOptions& opt)
|
||||
if (opt.Format() == "png")
|
||||
writeSuccess = WritePng(filename.c_str(), finalImagep, finalEmber.m_FinalRasW, finalEmber.m_FinalRasH, opt.BitsPerChannel() / 8, opt.PngComments(), comments, opt.Id(), opt.Url(), opt.Nick());
|
||||
else if (opt.Format() == "jpg")
|
||||
writeSuccess = WriteJpeg(filename.c_str(), finalImagep, finalEmber.m_FinalRasW, finalEmber.m_FinalRasH, opt.JpegQuality(), opt.JpegComments(), comments, opt.Id(), opt.Url(), opt.Nick());
|
||||
writeSuccess = WriteJpeg(filename.c_str(), finalImagep, finalEmber.m_FinalRasW, finalEmber.m_FinalRasH, int(opt.JpegQuality()), opt.JpegComments(), comments, opt.Id(), opt.Url(), opt.Nick());
|
||||
else if (opt.Format() == "ppm")
|
||||
writeSuccess = WritePpm(filename.c_str(), finalImagep, finalEmber.m_FinalRasW, finalEmber.m_FinalRasH);
|
||||
else if (opt.Format() == "bmp")
|
||||
@ -303,7 +307,7 @@ bool EmberRender(EmberOptions& opt)
|
||||
|
||||
if (opt.EmberCL() && opt.DumpKernel())
|
||||
{
|
||||
if (auto rendererCL = dynamic_cast<RendererCL<T, bucketT>*>(renderer.get()))
|
||||
if (auto rendererCL = dynamic_cast<RendererCL<T, float>*>(renderer.get()))
|
||||
{
|
||||
cout << "Iteration kernel: \n" <<
|
||||
rendererCL->IterKernel() << "\n\n" <<
|
||||
@ -315,8 +319,7 @@ bool EmberRender(EmberOptions& opt)
|
||||
VerbosePrint("Done.");
|
||||
}
|
||||
|
||||
if (opt.Verbose())
|
||||
t.Toc("\nTotal time: ", true);
|
||||
t.Toc("\nFinished in: ", true);
|
||||
|
||||
return true;
|
||||
}
|
||||
@ -347,18 +350,18 @@ int _tmain(int argc, _TCHAR* argv[])
|
||||
#ifdef DO_DOUBLE
|
||||
if (opt.Bits() == 64)
|
||||
{
|
||||
b = EmberRender<double, float>(opt);
|
||||
b = EmberRender<double>(opt);
|
||||
}
|
||||
else
|
||||
#endif
|
||||
if (opt.Bits() == 33)
|
||||
{
|
||||
b = EmberRender<float, float>(opt);
|
||||
b = EmberRender<float>(opt);
|
||||
}
|
||||
else if (opt.Bits() == 32)
|
||||
{
|
||||
cout << "Bits 32/int histogram no longer supported. Using bits == 33 (float)." << endl;
|
||||
b = EmberRender<float, float>(opt);
|
||||
b = EmberRender<float>(opt);
|
||||
}
|
||||
}
|
||||
|
||||
|
Reference in New Issue
Block a user