fractorium/Source/Ember/Timing.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

224 lines
6.3 KiB
C++

#pragma once
#include "EmberDefines.h"
/// <summary>
/// Timing and CriticalSection classes.
/// </summary>
namespace EmberNs
{
/// <summary>
/// Since the algorithm is so computationally intensive, timing and benchmarking are an integral portion
/// of both the development process and the execution results. This class provides an easy way to time
/// things by simply calling its Tic() and Toc() member functions. It also assists with formatting the
/// elapsed time as a string.
/// </summary>
class EMBER_API Timing
{
public:
/// <summary>
/// Constructor that takes an optional precision argument which specifies how many digits after the decimal place should be printed for seconds.
/// As a convenience, the Tic() function is called automatically.
/// </summary>
/// <param name="precision">The precision of the seconds field of the elapsed time. Default: 2.</param>
Timing(int precision = 2)
{
m_Precision = precision;
Init();
Tic();
}
/// <summary>
/// Set the begin time.
/// </summary>
/// <returns>The begin time cast to a double</returns>
double Tic()
{
m_BeginTime = Clock::now();
return BeginTime();
}
/// <summary>
/// Set the end time and optionally output a string showing the elapsed time.
/// </summary>
/// <param name="str">The string to output. Default: nullptr.</param>
/// <param name="fullString">If true, output the string verbatim, else output the text " processing time: " in between str and the formatted time.</param>
/// <returns>The elapsed time in milliseconds as a double</returns>
double Toc(const char* str = nullptr, bool fullString = false)
{
m_EndTime = Clock::now();
double ms = ElapsedTime();
if (str != nullptr)
{
cout << string(str) << (fullString ? "" : " processing time: ") << Format(ms) << endl;
}
return ms;
}
/// <summary>
/// Return the begin time as a double.
/// </summary>
/// <returns></returns>
double BeginTime() const { return static_cast<double>(m_BeginTime.time_since_epoch().count()); }
/// <summary>
/// Return the end time as a double.
/// </summary>
/// <returns></returns>
double EndTime() const { return static_cast<double>(m_EndTime.time_since_epoch().count()); }
/// <summary>
/// Return the elapsed time in milliseconds.
/// </summary>
/// <returns>The elapsed time in milliseconds as a double</returns>
double ElapsedTime() const
{
duration<double> elapsed = duration_cast<milliseconds, Clock::rep, Clock::period>(m_EndTime - m_BeginTime);
return elapsed.count() * 1000.0;
}
/// <summary>
/// Formats a specified milliseconds value as a string.
/// This uses some intelligence to determine what to return depending on how much time has elapsed.
/// Days, hours and minutes are only included if 1 or more of them has elapsed. Seconds are always
/// included as a decimal value with the precision the user specified in the constructor.
/// </summary>
/// <param name="ms">The ms</param>
/// <returns>The formatted string</returns>
string Format(double ms) const
{
stringstream ss;
double x = ms / 1000;
double secs = fmod(x, 60);
x /= 60;
double mins = fmod(x, 60);
x /= 60;
double hours = fmod(x, 24);
x /= 24;
double days = x;
if (days >= 1)
ss << static_cast<int>(days) << "d ";
if (hours >= 1)
ss << static_cast<int>(hours) << "h ";
if (mins >= 1)
ss << static_cast<int>(mins) << "m ";
ss << std::fixed << std::setprecision(m_Precision) << secs << "s";
return ss.str();
}
/// <summary>
/// Return the number of cores in the system.
/// </summary>
/// <returns>The number of cores in the system</returns>
static uint ProcessorCount()
{
Init();
return m_ProcessorCount;
}
private:
/// <summary>
/// Query and store the performance info of the system.
/// Since it will never change it only needs to be queried once.
/// This is achieved by keeping static state and performance variables.
/// </summary>
static void Init()
{
if (!m_TimingInit)
{
m_ProcessorCount = thread::hardware_concurrency();
m_TimingInit = true;
}
}
int m_Precision;//How many digits after the decimal place to print for seconds.
time_point<Clock> m_BeginTime;//The start of the timing, set with Tic().
time_point<Clock> m_EndTime;//The end of the timing, set with Toc().
static bool m_TimingInit;//Whether the performance info has bee queried.
static uint m_ProcessorCount;//The number of cores on the system, set in Init().
};
/// <summary>
/// Cross platform critical section class which can be used for thread locking.
/// </summary>
class EMBER_API CriticalSection
{
public:
#ifdef _WIN32
/// <summary>
/// Constructor which initialized the underlying CRITICAL_SECTION object.
/// </summary>
CriticalSection() { InitializeCriticalSection(&m_CriticalSection); }
/// <summary>
/// Constructor which initialized the underlying CRITICAL_SECTION object
/// with the specified spin count value.
/// </summary>
/// <param name="spinCount">The spin count.</param>
CriticalSection(DWORD spinCount) { InitializeCriticalSectionAndSpinCount(&m_CriticalSection, spinCount); }
/// <summary>
/// Deletes the underlying CRITICAL_SECTION object.
/// </summary>
~CriticalSection() { DeleteCriticalSection(&m_CriticalSection); }
/// <summary>
/// Lock the critical section.
/// </summary>
void Enter() { EnterCriticalSection(&m_CriticalSection); }
/// <summary>
/// Unlock the critical section.
/// </summary>
void Leave() { LeaveCriticalSection(&m_CriticalSection); }
private:
CRITICAL_SECTION m_CriticalSection;//The Windows specific critical section object.
#else
/// <summary>
/// Constructor which initialized the underlying pthread_mutex_t object.
/// </summary>
CriticalSection()
{
pthread_mutexattr_t attr;
pthread_mutexattr_init(&attr);
pthread_mutexattr_settype(&attr, PTHREAD_MUTEX_NORMAL);
pthread_mutex_init(&m_CriticalSection, &attr);
pthread_mutexattr_destroy(&attr);
}
/// <summary>
/// Deletes the underlying pthread_mutex_t object.
/// </summary>
~CriticalSection() { pthread_mutex_destroy(&m_CriticalSection); }
/// <summary>
/// Lock the critical section.
/// </summary>
void Enter() { pthread_mutex_lock(&m_CriticalSection); }
/// <summary>
/// Unlock the critical section.
/// </summary>
void Leave() { pthread_mutex_unlock(&m_CriticalSection); }
private:
pthread_mutex_t m_CriticalSection;//The *nix/pthread specific critical section object.
#endif
};
}