--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:
mfeemster
2015-09-12 18:33:45 -07:00
parent a4aae06b02
commit 018ba26b5f
85 changed files with 3869 additions and 2517 deletions

View File

@ -213,13 +213,19 @@ static bool ReadFile(const char* filename, string& buf, bool nullTerminate = tru
fclose(f);
}
}
catch (...)
catch (const std::exception& e)
{
if (f != nullptr)
fclose(f);
cout << "Error: Reading file " << filename << " failed: " << e.what() << endl;
b = false;
}
catch (...)
{
cout << "Error: Reading file " << filename << " failed." << endl;
b = false;
}
if (f != nullptr)
fclose(f);
return b;
}
@ -270,7 +276,7 @@ static void CopyVec(vector<T>& dest, const vector<U>& source, std::function<void
template <typename T>
static void ClearVec(vector<T*>& vec, bool arrayDelete = false)
{
for (uint i = 0; i < vec.size(); i++)
for (size_t i = 0; i < vec.size(); i++)
{
if (vec[i] != nullptr)
{
@ -286,6 +292,32 @@ static void ClearVec(vector<T*>& vec, bool arrayDelete = false)
vec.clear();
}
/// <summary>
/// Determine whether all elements in two containers are equal.
/// </summary>
/// <param name="c1">The first collection to compare</param>
/// <param name="c2">The second collection to compare</param>
/// <returns>True if the sizes and all elements in both collections are equal, else false.</returns>
template <typename T>
static bool Equal(const T& c1, const T& c2)
{
bool equal = c1.size() == c2.size();
if (equal)
{
for (auto it1 = c1.begin(), it2 = c2.begin(); it1 != c1.end(); ++it1, ++it2)
{
if (*it1 != *it2)
{
equal = false;
break;
}
}
}
return equal;
}
/// <summary>
/// Thin wrapper around passing a vector to memset() to relieve
/// the caller of having to pass the size.
@ -305,15 +337,15 @@ static inline void Memset(vector<T>& vec, int val = 0)
/// <param name="x">The value to return the floor of</param>
/// <returns>The floored value</returns>
template <typename T>
static inline int Floor(T val)
static inline intmax_t Floor(T val)
{
if (val >= 0)
{
return static_cast<int>(val);
return static_cast<intmax_t>(val);
}
else
{
int i = static_cast<int>(val);//Truncate.
intmax_t i = static_cast<intmax_t>(val);//Truncate.
return i - (i > val);//Convert trunc to floor.
}
}
@ -862,25 +894,9 @@ static string GetPath(const string& filename)
/// <returns>The value of the specified environment variable if found, else default</returns>
template <typename T>
static inline T Arg(char* name, T def)
{
T t;
return t;
}
/// <summary>
/// Template specialization for Arg<>() with a type of int.
/// </summary>
/// <param name="name">The name of the environment variable to query</param>
/// <param name="def">The default value to return if the environment variable was not present</param>
/// <returns>The value of the specified environment variable if found, else default</returns>
template <>
#ifdef _WIN32
static
#endif
int Arg<int>(char* name, int def)
{
char* ch;
int returnVal;
T returnVal;
#ifdef WIN32
size_t len;
errno_t err = _dupenv_s(&ch, &len, name);
@ -892,7 +908,17 @@ int Arg<int>(char* name, int def)
if (err || !ch)
returnVal = def;
else
returnVal = atoi(ch);
{
T tempVal;
istringstream istr(ch);
istr >> tempVal;
if (!istr.bad() && !istr.fail())
returnVal = tempVal;
else
returnVal = def;
}
#ifdef WIN32
free(ch);
@ -900,21 +926,6 @@ int Arg<int>(char* name, int def)
return returnVal;
}
/// <summary>
/// Template specialization for Arg<>() with a type of uint.
/// </summary>
/// <param name="name">The name of the environment variable to query</param>
/// <param name="def">The default value to return if the environment variable was not present</param>
/// <returns>The value of the specified environment variable if found, else default</returns>
template <>
#ifdef _WIN32
static
#endif
uint Arg<uint>(char* name, uint def)
{
return Arg<int>(name, static_cast<int>(def));
}
/// <summary>
/// Template specialization for Arg<>() with a type of bool.
/// </summary>
@ -930,39 +941,6 @@ bool Arg<bool>(char* name, bool def)
return (Arg<int>(name, -999) != -999) ? true : def;
}
/// <summary>
/// Template specialization for Arg<>() with a type of double.
/// </summary>
/// <param name="name">The name of the environment variable to query</param>
/// <param name="def">The default value to return if the environment variable was not present</param>
/// <returns>The value of the specified environment variable if found, else default</returns>
template <>
#ifdef _WIN32
static
#endif
double Arg<double>(char* name, double def)
{
char* ch;
double returnVal;
#ifdef WIN32
size_t len;
errno_t err = _dupenv_s(&ch, &len, name);
#else
int err = 1;
ch = getenv(name);
#endif
if (err || !ch)
returnVal = def;
else
returnVal = atof(ch);
#ifdef WIN32
free(ch);
#endif
return returnVal;
}
/// <summary>
/// Template specialization for Arg<>() with a type of string.
/// </summary>
@ -1031,6 +1009,24 @@ static uint FindAndReplace(T& source, const T& find, const T& replace)
return replaceCount;
}
/// <summary>
/// Split a string into tokens and place them in a vector.
/// </summary>
/// <param name="str">The string to split</param>
/// <param name="del">The delimiter to split the string on</param>
/// <returns>The split strings, each as an element in a vector.</returns>
static vector<string> Split(const string& str, char del)
{
string tok;
vector<string> vec;
stringstream ss(str);
while (getline(ss, tok, del))
vec.push_back(tok);
return vec;
}
/// <summary>
/// Return a character pointer to a version string composed of the EMBER_OS and EMBER_VERSION values.
/// </summary>