mirror of
https://bitbucket.org/mfeemster/fractorium.git
synced 2025-06-30 21:36:33 -04:00
--User changes
-Add new variations: bubbleT3D, crob, hexaplay3D, hexcrop, hexes, hexnix3D, loonie2, loonie3, nBlur, octapol and synth. -Allow for pre/post versions of dc_bubble, dc_cylinder and dc_linear whereas before they were omitted. -When saving a file with multiple embers in it, detect if time values are all the same and if so, start them at zero and increment by 1 for each ember. -Allow for numerous quality increases to be coalesced into one. It will pick up at the end of the current render. -Show selection highlight on variations tree in response to mouse hover. This makes it easier to see for which variation or param the current mouse wheel action will apply. -Make default temporal samples be 100, whereas before it was 1000 which was overkill. -Require the shift key to be held with delete for deleting an ember to prevent it from triggering when the user enters delete in the edit box. -This wasn't otherwise fixable without writing a lot more code. --Bug fixes -EmberGenome was crashing when generating a sequence from a source file with more than 2 embers in it. -EmberGenome was improperly handling the first frame of a merge after the last frame of the loop. -These bugs were due to a previous commit. Revert parts of that commit. -Prevent a zoom value of less than 0 when reading from xml. -Slight optimization of the crescents, and mask variations, if the compiler wasn't doing it already. -Unique file naming was broken because it was looking for _# and the default names ended with -#. -Disallow renaming of an ember in the library tree to an empty string. -Severe bug that prevented some variations from being read correctly from params generated outside this program. -Severe OpenCL randomization bug. The first x coordinates of the first points in the first kernel call of the first ember of a render since the OpenCL renderer object was created were not random and were mostly -1. -Severe bug when populating xform selection distributions that could sometimes cause a crash due to roundoff error. Fix by using double. -Limit the max number of variations in a random ember to MAX_CL_VARS, which is 8. This ensures they'll look the same on CPU and GPU. -Prevent user from saving stylesheet to default.qss, it's a special reserved filename. --Code changes -Generalize using the running sum output point inside of a variation for all cases: pre, reg and post. -Allow for array variables in variations where the address of each element is stored in m_Params. -Qualify all math functions with std:: -No longer use our own Clamp() in OpenCL, instead use the standard clamp(). -Redesign how functions are used in the variations OpenCL code. -Add tests to EmberTester to verify some of the new functionality. -Place more const and override qualifiers on functions where appropriate. -Add a global rand with a lock to be used very sparingly. -Use a map instead of a vector for bad param names in Xml parsing. -Prefix affine interpolation mode defines with "AFFINE_" to make their purpose more clear. -Allow for variations that change state during iteration by sending a separate copy of the ember to each rendering thread. -Implement this same functionality with a local struct in OpenCL. It's members are the total of all variables that need to change state within an ember. -Add Contains() function to Utils.h. -EmberRender: print names of kernels being printed with --dump_kernel option. -Clean up EmberTester to handle some of the recent changes. -Fix various casts. -Replace % 2 with & 1, even though the compiler was likely doing this already. -Add new file Variations06.h to accommodate new variations. -General cleanup.
This commit is contained in:
mfeemster
@ -787,7 +787,8 @@ string DEOpenCLKernelCreator::CreateGaussianDEKernelNoLocalCache(size_t ss)
|
||||
"\n";
|
||||
|
||||
if (doScf)
|
||||
os << " filterSelect *= scfact;\n";
|
||||
os <<
|
||||
" filterSelect *= scfact;\n";
|
||||
}
|
||||
else
|
||||
{
|
||||
@ -830,7 +831,7 @@ string DEOpenCLKernelCreator::CreateGaussianDEKernelNoLocalCache(size_t ss)
|
||||
" }\n"
|
||||
" }\n"//bucket.w != 0.
|
||||
" }\n"//In bounds.
|
||||
"\n"
|
||||
//"\n"
|
||||
//" barrier(CLK_GLOBAL_MEM_FENCE);\n"//Just to be safe.
|
||||
"}\n";
|
||||
|
||||
|
||||
@ -149,8 +149,8 @@ static const char* CalcAlphaFunctionString =
|
||||
static const char* CurveAdjustFunctionString =
|
||||
"static inline void CurveAdjust(__constant real4reals_bucket* csa, float* a, uint index)\n"
|
||||
"{\n"
|
||||
" uint tempIndex = (uint)Clamp(*a, 0.0, (float)COLORMAP_LENGTH_MINUS_1);\n"
|
||||
" uint tempIndex2 = (uint)Clamp(csa[tempIndex].m_Real4.x, 0.0, (real_t)COLORMAP_LENGTH_MINUS_1);\n"
|
||||
" uint tempIndex = (uint)clamp(*a, (float)0.0, (float)COLORMAP_LENGTH_MINUS_1);\n"
|
||||
" uint tempIndex2 = (uint)clamp((float)csa[tempIndex].m_Real4.x, (float)0.0, (float)COLORMAP_LENGTH_MINUS_1);\n"
|
||||
"\n"
|
||||
" *a = (float)round(csa[tempIndex2].m_Reals[index]);\n"
|
||||
"}\n";
|
||||
@ -194,135 +194,6 @@ static const char* RandFunctionString =
|
||||
"}\n"
|
||||
"\n";
|
||||
|
||||
/// <summary>
|
||||
/// OpenCL equivalent of the global ClampRef().
|
||||
/// </summary>
|
||||
static const char* ClampRealFunctionString =
|
||||
"inline real_t Clamp(real_t val, real_t min, real_t max)\n"
|
||||
"{\n"
|
||||
" if (val < min)\n"
|
||||
" return min;\n"
|
||||
" else if (val > max)\n"
|
||||
" return max;\n"
|
||||
" else\n"
|
||||
" return val;\n"
|
||||
"}\n"
|
||||
"\n"
|
||||
"inline void ClampRef(real_t* val, real_t min, real_t max)\n"
|
||||
"{\n"
|
||||
" if (*val < min)\n"
|
||||
" *val = min;\n"
|
||||
" else if (*val > max)\n"
|
||||
" *val = max;\n"
|
||||
"}\n"
|
||||
"\n"
|
||||
"inline real_t ClampGte(real_t val, real_t gte)\n"
|
||||
"{\n"
|
||||
" return (val < gte) ? gte : val;\n"
|
||||
"}\n"
|
||||
"\n";
|
||||
|
||||
/// <summary>
|
||||
/// OpenCL equivalent of the global LRint().
|
||||
/// </summary>
|
||||
static const char* InlineMathFunctionsString =
|
||||
"inline real_t LRint(real_t x)\n"
|
||||
"{\n"
|
||||
" intPrec temp = (x >= 0.0 ? (intPrec)(x + 0.5) : (intPrec)(x - 0.5));\n"
|
||||
" return (real_t)temp;\n"
|
||||
"}\n"
|
||||
"\n"
|
||||
"inline real_t Round(real_t r)\n"
|
||||
"{\n"
|
||||
" return (r > 0.0) ? floor(r + 0.5) : ceil(r - 0.5);\n"
|
||||
"}\n"
|
||||
"\n"
|
||||
"inline real_t Sign(real_t v)\n"
|
||||
"{\n"
|
||||
" return (v < 0.0) ? -1 : (v > 0.0) ? 1 : 0.0;\n"
|
||||
"}\n"
|
||||
"\n"
|
||||
"inline real_t SignNz(real_t v)\n"
|
||||
"{\n"
|
||||
" return (v < 0.0) ? -1.0 : 1.0;\n"
|
||||
"}\n"
|
||||
"\n"
|
||||
"inline real_t Sqr(real_t v)\n"
|
||||
"{\n"
|
||||
" return v * v;\n"
|
||||
"}\n"
|
||||
"\n"
|
||||
"inline real_t SafeSqrt(real_t x)\n"
|
||||
"{\n"
|
||||
" if (x <= 0.0)\n"
|
||||
" return 0.0;\n"
|
||||
"\n"
|
||||
" return sqrt(x);\n"
|
||||
"}\n"
|
||||
"\n"
|
||||
"inline real_t Cube(real_t v)\n"
|
||||
"{\n"
|
||||
" return v * v * v;\n"
|
||||
"}\n"
|
||||
"\n"
|
||||
"inline real_t Hypot(real_t x, real_t y)\n"
|
||||
"{\n"
|
||||
" return sqrt(SQR(x) + SQR(y));\n"
|
||||
"}\n"
|
||||
"\n"
|
||||
"inline real_t Spread(real_t x, real_t y)\n"
|
||||
"{\n"
|
||||
" return Hypot(x, y) * ((x) > 0.0 ? 1.0 : -1.0);\n"
|
||||
"}\n"
|
||||
"\n"
|
||||
"inline real_t Powq4(real_t x, real_t y)\n"
|
||||
"{\n"
|
||||
" return pow(fabs(x), y) * SignNz(x);\n"
|
||||
"}\n"
|
||||
"\n"
|
||||
"inline real_t Powq4c(real_t x, real_t y)\n"
|
||||
"{\n"
|
||||
" return y == 1.0 ? x : Powq4(x, y);\n"
|
||||
"}\n"
|
||||
"\n"
|
||||
"inline real_t Zeps(real_t x)\n"
|
||||
"{\n"
|
||||
" return x == 0.0 ? EPS : x;\n"
|
||||
"}\n"
|
||||
"\n"
|
||||
"inline real_t Lerp(real_t a, real_t b, real_t p)\n"
|
||||
"{\n"
|
||||
" return a + (b - a) * p;\n"
|
||||
"}\n"
|
||||
"\n"
|
||||
"inline real_t Fabsmod(real_t v)\n"
|
||||
"{\n"
|
||||
" real_t dummy;\n"
|
||||
"\n"
|
||||
" return modf(v, &dummy);\n"
|
||||
"}\n"
|
||||
"\n"
|
||||
"inline real_t Fosc(real_t p, real_t amp, real_t ph)\n"
|
||||
"{\n"
|
||||
" return 0.5 - cos(p * amp + ph) * 0.5;\n"
|
||||
"}\n"
|
||||
"\n"
|
||||
"inline real_t Foscn(real_t p, real_t ph)\n"
|
||||
"{\n"
|
||||
" return 0.5 - cos(p + ph) * 0.5;\n"
|
||||
"}\n"
|
||||
"\n"
|
||||
"inline real_t LogScale(real_t x)\n"
|
||||
"{\n"
|
||||
" return x == 0.0 ? 0.0 : log((fabs(x) + 1) * M_E) * SignNz(x) / M_E;\n"
|
||||
"}\n"
|
||||
"\n"
|
||||
"inline real_t LogMap(real_t x)\n"
|
||||
"{\n"
|
||||
" return x == 0.0 ? 0.0 : (M_E + log(x * M_E)) * 0.25 * SignNz(x);\n"
|
||||
"}\n"
|
||||
"\n";
|
||||
|
||||
/// <summary>
|
||||
/// OpenCL equivalent Renderer::AddToAccum().
|
||||
/// </summary>
|
||||
|
||||
@ -44,9 +44,11 @@
|
||||
#include <cstdlib>
|
||||
#include <fstream>
|
||||
#include <iostream>
|
||||
#include <set>
|
||||
#include <string>
|
||||
#include <iterator>
|
||||
#include <time.h>
|
||||
#include <unordered_map>
|
||||
|
||||
#ifdef _WIN32
|
||||
#if defined(BUILDING_EMBERCL)
|
||||
|
||||
@ -13,15 +13,6 @@
|
||||
|
||||
namespace EmberCLns
|
||||
{
|
||||
//These two must always match.
|
||||
#ifdef WIN32
|
||||
#define ALIGN __declspec(align(16))
|
||||
#else
|
||||
#define ALIGN __attribute__ ((aligned (16)))
|
||||
#endif
|
||||
|
||||
#define ALIGN_CL "((aligned (16)))"//The extra parens are necessary.
|
||||
|
||||
/// <summary>
|
||||
/// Various constants needed for rendering.
|
||||
/// </summary>
|
||||
@ -32,20 +23,23 @@ static string ConstantDefinesString(bool doublePrecision)
|
||||
if (doublePrecision)
|
||||
{
|
||||
os << "#if defined(cl_amd_fp64)\n"//AMD extension available?
|
||||
<< " #pragma OPENCL EXTENSION cl_amd_fp64 : enable\n"
|
||||
<< "#endif\n"
|
||||
<< "#if defined(cl_khr_fp64)\n"//Khronos extension available?
|
||||
<< " #pragma OPENCL EXTENSION cl_khr_fp64 : enable\n"
|
||||
<< "#endif\n"
|
||||
<< "#pragma OPENCL EXTENSION cl_khr_int64_base_atomics : enable\n"//Only supported on nVidia.
|
||||
<< "typedef long intPrec;\n"
|
||||
<< "typedef uint atomi;\n"//Same size as real_bucket_t, always 4 bytes.
|
||||
<< "typedef double real_t;\n"
|
||||
<< "typedef float real_bucket_t;\n"//Assume buckets are always float, even though iter calcs are in double.
|
||||
<< "typedef double4 real4;\n"
|
||||
<< "typedef float4 real4_bucket;\n"//And here too.
|
||||
<< "#define EPS (DBL_EPSILON)\n"
|
||||
;
|
||||
" #pragma OPENCL EXTENSION cl_amd_fp64 : enable\n"
|
||||
"#endif\n"
|
||||
"#if defined(cl_khr_fp64)\n"//Khronos extension available?
|
||||
" #pragma OPENCL EXTENSION cl_khr_fp64 : enable\n"
|
||||
"#endif\n"
|
||||
"#pragma OPENCL EXTENSION cl_khr_int64_base_atomics : enable\n"//Only supported on nVidia.
|
||||
"typedef long intPrec;\n"
|
||||
"typedef uint atomi;\n"//Same size as real_bucket_t, always 4 bytes.
|
||||
"typedef double real_t;\n"
|
||||
"typedef float real_bucket_t;\n"//Assume buckets are always float, even though iter calcs are in double.
|
||||
"typedef double2 real2;\n"
|
||||
"typedef double4 real4;\n"
|
||||
"typedef float4 real4_bucket;\n"//And here too.
|
||||
"#define EPS (DBL_EPSILON)\n"
|
||||
"#define TLOW (DBL_MIN)\n"
|
||||
"#define TMAX (DBL_MAX)\n"
|
||||
;
|
||||
}
|
||||
else
|
||||
{
|
||||
@ -53,9 +47,12 @@ static string ConstantDefinesString(bool doublePrecision)
|
||||
"typedef uint atomi;\n"
|
||||
"typedef float real_t;\n"
|
||||
"typedef float real_bucket_t;\n"
|
||||
"typedef float2 real2;\n"
|
||||
"typedef float4 real4;\n"
|
||||
"typedef float4 real4_bucket;\n"
|
||||
"#define EPS (FLT_EPSILON)\n"
|
||||
"#define TLOW (FLT_MIN)\n"
|
||||
"#define TMAX (FLT_MAX)\n"
|
||||
;
|
||||
}
|
||||
|
||||
|
||||
@ -186,7 +186,6 @@ string FinalAccumOpenCLKernelCreator::CreateFinalAccumKernelString(bool earlyCli
|
||||
|
||||
os <<
|
||||
ConstantDefinesString(m_DoublePrecision) <<
|
||||
ClampRealFunctionString <<
|
||||
UnionCLStructString <<
|
||||
RgbToHsvFunctionString <<
|
||||
HsvToRgbFunctionString <<
|
||||
@ -484,7 +483,6 @@ string FinalAccumOpenCLKernelCreator::CreateGammaCorrectionKernelString(bool alp
|
||||
|
||||
os <<
|
||||
ConstantDefinesString(m_DoublePrecision) <<
|
||||
ClampRealFunctionString <<
|
||||
UnionCLStructString <<
|
||||
RgbToHsvFunctionString <<
|
||||
HsvToRgbFunctionString <<
|
||||
|
||||
151
Source/EmberCL/FunctionMapper.cpp
Normal file
151
Source/EmberCL/FunctionMapper.cpp
Normal file
@ -0,0 +1,151 @@
|
||||
#include "EmberCLPch.h"
|
||||
#include "FunctionMapper.h"
|
||||
|
||||
namespace EmberCLns
|
||||
{
|
||||
std::unordered_map<string, string> FunctionMapper::m_GlobalMap;
|
||||
|
||||
FunctionMapper::FunctionMapper()
|
||||
{
|
||||
if (m_GlobalMap.empty())
|
||||
{
|
||||
m_GlobalMap["LRint"] =
|
||||
"inline real_t LRint(real_t x)\n"
|
||||
"{\n"
|
||||
" intPrec temp = (x >= 0.0 ? (intPrec)(x + 0.5) : (intPrec)(x - 0.5));\n"
|
||||
" return (real_t)temp;\n"
|
||||
"}\n";
|
||||
|
||||
m_GlobalMap["Round"] =
|
||||
"inline real_t Round(real_t r)\n"
|
||||
"{\n"
|
||||
" return (r > 0.0) ? floor(r + 0.5) : ceil(r - 0.5);\n"
|
||||
"}\n";
|
||||
|
||||
m_GlobalMap["Sign"] =
|
||||
"inline real_t Sign(real_t v)\n"
|
||||
"{\n"
|
||||
" return (v < 0.0) ? -1 : (v > 0.0) ? 1 : 0.0;\n"
|
||||
"}\n";
|
||||
|
||||
m_GlobalMap["SignNz"] =
|
||||
"inline real_t SignNz(real_t v)\n"
|
||||
"{\n"
|
||||
" return (v < 0.0) ? -1.0 : 1.0;\n"
|
||||
"}\n";
|
||||
|
||||
m_GlobalMap["Sqr"] =
|
||||
"inline real_t Sqr(real_t v)\n"
|
||||
"{\n"
|
||||
" return v * v;\n"
|
||||
"}\n";
|
||||
|
||||
m_GlobalMap["SafeSqrt"] =
|
||||
"inline real_t SafeSqrt(real_t x)\n"
|
||||
"{\n"
|
||||
" if (x <= 0.0)\n"
|
||||
" return 0.0;\n"
|
||||
"\n"
|
||||
" return sqrt(x);\n"
|
||||
"}\n";
|
||||
|
||||
m_GlobalMap["Cube"] =
|
||||
"inline real_t Cube(real_t v)\n"
|
||||
"{\n"
|
||||
" return v * v * v;\n"
|
||||
"}\n";
|
||||
|
||||
m_GlobalMap["Hypot"] =
|
||||
"inline real_t Hypot(real_t x, real_t y)\n"
|
||||
"{\n"
|
||||
" return sqrt(SQR(x) + SQR(y));\n"
|
||||
"}\n";
|
||||
|
||||
m_GlobalMap["Spread"] =
|
||||
"inline real_t Spread(real_t x, real_t y)\n"
|
||||
"{\n"
|
||||
" return Hypot(x, y) * ((x) > 0.0 ? 1.0 : -1.0);\n"
|
||||
"}\n";
|
||||
|
||||
m_GlobalMap["Powq4"] =
|
||||
"inline real_t Powq4(real_t x, real_t y)\n"
|
||||
"{\n"
|
||||
" return pow(fabs(x), y) * SignNz(x);\n"
|
||||
"}\n";
|
||||
|
||||
m_GlobalMap["Powq4c"] =
|
||||
"inline real_t Powq4c(real_t x, real_t y)\n"
|
||||
"{\n"
|
||||
" return y == 1.0 ? x : Powq4(x, y);\n"
|
||||
"}\n";
|
||||
|
||||
m_GlobalMap["Zeps"] =
|
||||
"inline real_t Zeps(real_t x)\n"
|
||||
"{\n"
|
||||
" return x == 0.0 ? EPS : x;\n"
|
||||
"}\n";
|
||||
|
||||
m_GlobalMap["Lerp"] =
|
||||
"inline real_t Lerp(real_t a, real_t b, real_t p)\n"
|
||||
"{\n"
|
||||
" return a + (b - a) * p;\n"
|
||||
"}\n";
|
||||
|
||||
m_GlobalMap["Fabsmod"] =
|
||||
"inline real_t Fabsmod(real_t v)\n"
|
||||
"{\n"
|
||||
" real_t dummy;\n"
|
||||
"\n"
|
||||
" return modf(v, &dummy);\n"
|
||||
"}\n";
|
||||
|
||||
m_GlobalMap["Fosc"] =
|
||||
"inline real_t Fosc(real_t p, real_t amp, real_t ph)\n"
|
||||
"{\n"
|
||||
" return 0.5 - cos(p * amp + ph) * 0.5;\n"
|
||||
"}\n";
|
||||
|
||||
m_GlobalMap["Foscn"] =
|
||||
"inline real_t Foscn(real_t p, real_t ph)\n"
|
||||
"{\n"
|
||||
" return 0.5 - cos(p + ph) * 0.5;\n"
|
||||
"}\n";
|
||||
|
||||
m_GlobalMap["LogScale"] =
|
||||
"inline real_t LogScale(real_t x)\n"
|
||||
"{\n"
|
||||
" return x == 0.0 ? 0.0 : log((fabs(x) + 1) * M_E) * SignNz(x) / M_E;\n"
|
||||
"}\n";
|
||||
|
||||
m_GlobalMap["LogMap"] =
|
||||
"inline real_t LogMap(real_t x)\n"
|
||||
"{\n"
|
||||
" return x == 0.0 ? 0.0 : (M_E + log(x * M_E)) * 0.25 * SignNz(x);\n"
|
||||
"}\n";
|
||||
|
||||
m_GlobalMap["ClampGte"] =
|
||||
"inline real_t ClampGte(real_t val, real_t gte)\n"
|
||||
"{\n"
|
||||
" return (val < gte) ? gte : val;\n"
|
||||
"}\n";
|
||||
|
||||
m_GlobalMap["Swap"] =
|
||||
"inline void Swap(real_t* val1, real_t* val2)\n"
|
||||
"{\n"
|
||||
" real_t tmp = *val1;\n"
|
||||
" *val1 = *val2;\n"
|
||||
" *val2 = tmp;\n"
|
||||
"}\n";
|
||||
}
|
||||
}
|
||||
|
||||
const string* FunctionMapper::GetGlobalFunc(const string& func)
|
||||
{
|
||||
auto& text = m_GlobalMap.find(func);
|
||||
|
||||
if (text != m_GlobalMap.end())
|
||||
return &text->second;
|
||||
else
|
||||
return nullptr;
|
||||
}
|
||||
}
|
||||
21
Source/EmberCL/FunctionMapper.h
Normal file
21
Source/EmberCL/FunctionMapper.h
Normal file
@ -0,0 +1,21 @@
|
||||
#pragma once
|
||||
|
||||
#include "EmberCLPch.h"
|
||||
|
||||
namespace EmberCLns
|
||||
{
|
||||
/// <summary>
|
||||
/// Functionality to map OpenCL function names to their full function body program strings.
|
||||
/// This is used to ensure only the functions that are needed by a program are included once
|
||||
/// in the program string.
|
||||
/// </summary>
|
||||
class EMBERCL_API FunctionMapper
|
||||
{
|
||||
public:
|
||||
FunctionMapper();
|
||||
static const string* GetGlobalFunc(const string& func);
|
||||
|
||||
private:
|
||||
static std::unordered_map<string, string> m_GlobalMap;
|
||||
};
|
||||
}
|
||||
@ -2,7 +2,6 @@
|
||||
#include "IterOpenCLKernelCreator.h"
|
||||
|
||||
//#define STRAIGHT_RAND 1
|
||||
#define USE_CASE 1
|
||||
|
||||
namespace EmberCLns
|
||||
{
|
||||
@ -39,16 +38,20 @@ template <typename T> const string& IterOpenCLKernelCreator<T>::IterEntryPoint()
|
||||
/// <param name="doAccum">Debugging parameter to include or omit accumulating to the histogram. Default: true.</param>
|
||||
/// <returns>The kernel string</returns>
|
||||
template <typename T>
|
||||
string IterOpenCLKernelCreator<T>::CreateIterKernelString(Ember<T>& ember, string& parVarDefines, bool lockAccum, bool doAccum)
|
||||
string IterOpenCLKernelCreator<T>::CreateIterKernelString(const Ember<T>& ember, string& parVarDefines, bool lockAccum, bool doAccum)
|
||||
{
|
||||
bool doublePrecision = typeid(T) == typeid(double);
|
||||
size_t i, v, varIndex, varCount, totalXformCount = ember.TotalXformCount();
|
||||
ostringstream kernelIterBody, xformFuncs, os;
|
||||
vector<Variation<T>*> variations;
|
||||
|
||||
xformFuncs << "\n" << parVarDefines << endl;
|
||||
xformFuncs << VariationStateString(ember);
|
||||
xformFuncs << parVarDefines << endl;
|
||||
ember.GetPresentVariations(variations);
|
||||
for (auto var : variations) if (var) xformFuncs << var->OpenCLFuncsString();
|
||||
|
||||
for (auto var : variations)
|
||||
if (var)
|
||||
xformFuncs << var->OpenCLFuncsString();
|
||||
|
||||
for (i = 0; i < totalXformCount; i++)
|
||||
{
|
||||
@ -62,7 +65,7 @@ string IterOpenCLKernelCreator<T>::CreateIterKernelString(Ember<T>& ember, strin
|
||||
|
||||
v = varIndex = varCount = 0;
|
||||
xformFuncs <<
|
||||
"void Xform" << i << "(__constant XformCL* xform, __constant real_t* parVars, Point* inPoint, Point* outPoint, uint2* mwc)\n" <<
|
||||
"void Xform" << i << "(__constant XformCL* xform, __constant real_t* parVars, Point* inPoint, Point* outPoint, uint2* mwc, VariationState* varState)\n" <<
|
||||
"{\n"
|
||||
" real_t transX, transY, transZ;\n"
|
||||
" real4 vIn, vOut = 0.0;\n";
|
||||
@ -215,8 +218,7 @@ string IterOpenCLKernelCreator<T>::CreateIterKernelString(Ember<T>& ember, strin
|
||||
|
||||
os <<
|
||||
ConstantDefinesString(doublePrecision) <<
|
||||
InlineMathFunctionsString <<
|
||||
ClampRealFunctionString <<
|
||||
GlobalFunctionsString(ember) <<
|
||||
RandFunctionString <<
|
||||
PointCLStructString <<
|
||||
XformCLStructString <<
|
||||
@ -237,12 +239,13 @@ string IterOpenCLKernelCreator<T>::CreateIterKernelString(Ember<T>& ember, strin
|
||||
" __constant EmberCL* ember,\n"
|
||||
" __constant XformCL* xforms,\n"
|
||||
" __constant real_t* parVars,\n"
|
||||
" __global uchar* xformDistributions,\n"//Using uchar is quicker than uint. Can't be constant because the size can be too large to fit when using xaos.//FINALOPT
|
||||
" __global uchar* xformDistributions,\n"//Using uchar is quicker than uint. Can't be constant because the size can be too large to fit when using xaos.
|
||||
" __constant CarToRasCL* carToRas,\n"
|
||||
" __global real4reals_bucket* histogram,\n"
|
||||
" uint histSize,\n"
|
||||
" __read_only image2d_t palette,\n"
|
||||
" __global Point* points\n"
|
||||
//" uint startRender\n"
|
||||
"\t)\n"
|
||||
"{\n"
|
||||
" bool fuse, ok;\n"
|
||||
@ -261,8 +264,9 @@ string IterOpenCLKernelCreator<T>::CreateIterKernelString(Ember<T>& ember, strin
|
||||
" CLK_ADDRESS_CLAMP_TO_EDGE |\n"//Clamp to edge
|
||||
" CLK_FILTER_NEAREST;\n"//Don't interpolate
|
||||
" uint threadXY = (THREAD_ID_X + THREAD_ID_Y);\n"
|
||||
" uint threadXDivRows = (THREAD_ID_X / (NTHREADS / THREADS_PER_WARP));\n"
|
||||
" uint threadXDivRows = (THREAD_ID_X / NWARPS);\n"
|
||||
" uint threadsMinus1 = NTHREADS - 1;\n"
|
||||
" VariationState varState;\n"
|
||||
;
|
||||
|
||||
os <<
|
||||
@ -278,6 +282,9 @@ string IterOpenCLKernelCreator<T>::CreateIterKernelString(Ember<T>& ember, strin
|
||||
" {\n"
|
||||
" fuse = true;\n"
|
||||
" itersToDo = fuseCount;\n"
|
||||
//Calling MwcNextNeg1Pos1() twice is deliberate. The first call to mwc is not very random since it just does
|
||||
//an xor. So it must be called twice to get it in a good random state.
|
||||
" firstPoint.m_X = MwcNextNeg1Pos1(&mwc);\n"
|
||||
" firstPoint.m_X = MwcNextNeg1Pos1(&mwc);\n"
|
||||
" firstPoint.m_Y = MwcNextNeg1Pos1(&mwc);\n"
|
||||
" firstPoint.m_Z = 0.0;\n"
|
||||
@ -290,7 +297,13 @@ string IterOpenCLKernelCreator<T>::CreateIterKernelString(Ember<T>& ember, strin
|
||||
" itersToDo = iterCount;\n"
|
||||
" firstPoint = points[pointsIndex];\n"
|
||||
" }\n"
|
||||
"\n";
|
||||
"\n"
|
||||
;
|
||||
|
||||
auto varStateString = VariationStateInitString(ember);
|
||||
|
||||
if (!varStateString.empty())
|
||||
os << varStateString << "\n\n";
|
||||
|
||||
//This is done once initially here and then again after each swap-sync in the main loop.
|
||||
//This along with the randomness that the point shuffle provides gives sufficient randomness
|
||||
@ -336,7 +349,6 @@ string IterOpenCLKernelCreator<T>::CreateIterKernelString(Ember<T>& ember, strin
|
||||
|
||||
for (i = 0; i < ember.XformCount(); i++)
|
||||
{
|
||||
#ifdef USE_CASE
|
||||
if (i == 0)
|
||||
{
|
||||
os <<
|
||||
@ -347,7 +359,7 @@ string IterOpenCLKernelCreator<T>::CreateIterKernelString(Ember<T>& ember, strin
|
||||
os <<
|
||||
" case " << i << ":\n"
|
||||
" {\n" <<
|
||||
" Xform" << i << "(&(xforms[" << i << "]), parVars, &firstPoint, &secondPoint, &mwc);\n" <<
|
||||
" Xform" << i << "(&(xforms[" << i << "]), parVars, &firstPoint, &secondPoint, &mwc, &varState);\n" <<
|
||||
" break;\n"
|
||||
" }\n";
|
||||
|
||||
@ -356,19 +368,6 @@ string IterOpenCLKernelCreator<T>::CreateIterKernelString(Ember<T>& ember, strin
|
||||
os <<
|
||||
" }\n";
|
||||
}
|
||||
#else
|
||||
if (i == 0)
|
||||
os <<
|
||||
" if (secondPoint.m_LastXfUsed == " << i << ")\n";
|
||||
else
|
||||
os <<
|
||||
" else if (secondPoint.m_LastXfUsed == " << i << ")\n";
|
||||
|
||||
os <<
|
||||
" {\n" <<
|
||||
" Xform" << i << "(&(xforms[" << i << "]), parVars, &firstPoint, &secondPoint, &mwc);\n" <<
|
||||
" }\n";
|
||||
#endif
|
||||
}
|
||||
|
||||
os <<
|
||||
@ -438,7 +437,7 @@ string IterOpenCLKernelCreator<T>::CreateIterKernelString(Ember<T>& ember, strin
|
||||
" if ((xforms[" << finalIndex << "].m_Opacity == 1) || (MwcNext01(&mwc) < xforms[" << finalIndex << "].m_Opacity))\n"
|
||||
" {\n"
|
||||
" tempPoint.m_LastXfUsed = secondPoint.m_LastXfUsed;\n"
|
||||
" Xform" << finalIndex << "(&(xforms[" << finalIndex << "]), parVars, &secondPoint, &tempPoint, &mwc);\n"
|
||||
" Xform" << finalIndex << "(&(xforms[" << finalIndex << "]), parVars, &secondPoint, &tempPoint, &mwc, &varState);\n"
|
||||
" secondPoint = tempPoint;\n"
|
||||
" }\n"
|
||||
"\n";
|
||||
@ -543,6 +542,50 @@ string IterOpenCLKernelCreator<T>::CreateIterKernelString(Ember<T>& ember, strin
|
||||
return os.str();
|
||||
}
|
||||
|
||||
/// <summary>
|
||||
/// Return a string containing all of the global functions needed by the passed in ember.
|
||||
/// </summary>
|
||||
/// <param name="ember">The ember to create the global function strings from</param>
|
||||
/// <returns>String of all global function names and bodies</returns>
|
||||
template <typename T>
|
||||
string IterOpenCLKernelCreator<T>::GlobalFunctionsString(const Ember<T>& ember)
|
||||
{
|
||||
size_t i, j, xformCount = ember.TotalXformCount();
|
||||
vector<string> funcNames;//Can't use a set here because they sort and we must preserve the insertion order due to nested function calls.
|
||||
ostringstream os;
|
||||
static string zeps = "Zeps";
|
||||
|
||||
for (i = 0; i < xformCount; i++)
|
||||
{
|
||||
if (auto xform = ember.GetTotalXform(i))
|
||||
{
|
||||
size_t varCount = xform->TotalVariationCount();
|
||||
|
||||
if (xform->NeedPrecalcAngles())
|
||||
if (!Contains(funcNames, zeps))
|
||||
funcNames.push_back(zeps);
|
||||
|
||||
for (j = 0; j < varCount; j++)
|
||||
{
|
||||
if (auto var = xform->GetVariation(j))
|
||||
{
|
||||
auto names = var->OpenCLGlobalFuncNames();
|
||||
|
||||
for (auto& name : names)
|
||||
if (!Contains(funcNames, name))
|
||||
funcNames.push_back(name);
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
for (auto& funcName : funcNames)
|
||||
if(auto text = m_FunctionMapper.GetGlobalFunc(funcName))
|
||||
os << *text << endl;
|
||||
|
||||
return os.str();
|
||||
}
|
||||
|
||||
/// <summary>
|
||||
/// Create an OpenCL string of #defines and a corresponding host side vector for parametric variation values.
|
||||
/// Parametric variations present a special problem in the iteration code.
|
||||
@ -571,9 +614,9 @@ string IterOpenCLKernelCreator<T>::CreateIterKernelString(Ember<T>& ember, strin
|
||||
/// #define CURL_C2_2 3
|
||||
/// #define BLOB_LOW_3 4
|
||||
/// #define BLOB_HIGH_3 5
|
||||
/// #define BLOB_WAVES_ 6
|
||||
/// #define BLOB_WAVES_3 6
|
||||
///
|
||||
/// The variations the use these #defines by first looking up the index of the
|
||||
/// The variations use these #defines by first looking up the index of the
|
||||
/// xform they belong to in the parent ember and generating the OpenCL string based on that
|
||||
/// in their overridden OpenCLString() functions.
|
||||
/// Template argument expected to be float or double.
|
||||
@ -583,10 +626,9 @@ string IterOpenCLKernelCreator<T>::CreateIterKernelString(Ember<T>& ember, strin
|
||||
/// <param name="doVals">True if the vector should be populated, else false. Default: true.</param>
|
||||
/// <param name="doString">True if the string should be populated, else false. Default: true.</param>
|
||||
template <typename T>
|
||||
void IterOpenCLKernelCreator<T>::ParVarIndexDefines(Ember<T>& ember, pair<string, vector<T>>& params, bool doVals, bool doString)
|
||||
void IterOpenCLKernelCreator<T>::ParVarIndexDefines(const Ember<T>& ember, pair<string, vector<T>>& params, bool doVals, bool doString)
|
||||
{
|
||||
size_t i, j, k, size = 0, xformCount = ember.TotalXformCount();
|
||||
Xform<T>* xform;
|
||||
ostringstream os;
|
||||
|
||||
if (doVals)
|
||||
@ -594,23 +636,26 @@ void IterOpenCLKernelCreator<T>::ParVarIndexDefines(Ember<T>& ember, pair<string
|
||||
|
||||
for (i = 0; i < xformCount; i++)
|
||||
{
|
||||
if ((xform = ember.GetTotalXform(i)))
|
||||
if (auto xform = ember.GetTotalXform(i))
|
||||
{
|
||||
size_t varCount = xform->TotalVariationCount();
|
||||
|
||||
for (j = 0; j < varCount; j++)
|
||||
{
|
||||
if (ParametricVariation<T>* parVar = dynamic_cast<ParametricVariation<T>*>(xform->GetVariation(j)))
|
||||
if (auto parVar = dynamic_cast<ParametricVariation<T>*>(xform->GetVariation(j)))
|
||||
{
|
||||
for (k = 0; k < parVar->ParamCount(); k++)
|
||||
{
|
||||
if (doString)
|
||||
os << "#define " << ToUpper(parVar->Params()[k].Name()) << "_" << i << " " << size << endl;//Uniquely identify this param in this variation in this xform.
|
||||
if (!parVar->Params()[k].IsState())
|
||||
{
|
||||
if (doString)
|
||||
os << "#define " << ToUpper(parVar->Params()[k].Name()) << "_" << i << " " << size << endl;//Uniquely identify this param in this variation in this xform.
|
||||
|
||||
if (doVals)
|
||||
params.second.push_back(parVar->Params()[k].ParamVal());
|
||||
if (doVals)
|
||||
params.second.push_back(parVar->Params()[k].ParamVal());
|
||||
|
||||
size++;
|
||||
size++;
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
@ -624,6 +669,69 @@ void IterOpenCLKernelCreator<T>::ParVarIndexDefines(Ember<T>& ember, pair<string
|
||||
}
|
||||
}
|
||||
|
||||
/// <summary>
|
||||
/// Create the string needed for the struct whose values will change between each iteration.
|
||||
/// This is only needed for variations whose state changes.
|
||||
/// If none are present, the struct will be empty.
|
||||
/// </summary>
|
||||
/// <param name="ember">The ember to generate the variation state struct string for</param>
|
||||
/// <returns>The variation state struct string</returns>
|
||||
template <typename T>
|
||||
string IterOpenCLKernelCreator<T>::VariationStateString(const Ember<T>& ember)
|
||||
{
|
||||
ostringstream os;
|
||||
|
||||
os << "typedef struct __attribute__ " ALIGN_CL " _VariationState\n{";
|
||||
|
||||
for (size_t i = 0; i < ember.TotalXformCount(); i++)
|
||||
{
|
||||
if (auto xform = ember.GetTotalXform(i))
|
||||
{
|
||||
for (size_t j = 0; j < xform->TotalVariationCount(); j++)
|
||||
{
|
||||
if (auto var = xform->GetVariation(j))
|
||||
{
|
||||
os << var->StateOpenCLString();
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
os << "\n} VariationState;\n\n";
|
||||
|
||||
return os.str();
|
||||
}
|
||||
|
||||
/// <summary>
|
||||
/// Create the string needed for the initial state of the struct whose values will change between each iteration.
|
||||
/// This is only needed for variations whose state changes.
|
||||
/// If none are present, the returned init string will be empty.
|
||||
/// This will be called at the beginning of each kernel.
|
||||
/// </summary>
|
||||
/// <param name="ember">The ember to generate the variation state struct init string for</param>
|
||||
/// <returns>The variation state struct init string</returns>
|
||||
template <typename T>
|
||||
string IterOpenCLKernelCreator<T>::VariationStateInitString(const Ember<T>& ember)
|
||||
{
|
||||
ostringstream os;
|
||||
|
||||
for (size_t i = 0; i < ember.TotalXformCount(); i++)
|
||||
{
|
||||
if (auto xform = ember.GetTotalXform(i))
|
||||
{
|
||||
for (size_t j = 0; j < xform->TotalVariationCount(); j++)
|
||||
{
|
||||
if (auto var = xform->GetVariation(j))
|
||||
{
|
||||
os << var->StateInitOpenCLString();
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
return os.str();
|
||||
}
|
||||
|
||||
/// <summary>
|
||||
/// Determine whether the two embers passed in differ enough
|
||||
/// to require a rebuild of the iteration code.
|
||||
@ -641,7 +749,7 @@ void IterOpenCLKernelCreator<T>::ParVarIndexDefines(Ember<T>& ember, pair<string
|
||||
/// <param name="ember2">The second ember to compare</param>
|
||||
/// <returns>True if a rebuild is required, else false</returns>
|
||||
template <typename T>
|
||||
bool IterOpenCLKernelCreator<T>::IsBuildRequired(Ember<T>& ember1, Ember<T>& ember2)
|
||||
bool IterOpenCLKernelCreator<T>::IsBuildRequired(const Ember<T>& ember1, const Ember<T>& ember2)
|
||||
{
|
||||
size_t i, j, xformCount = ember1.TotalXformCount();
|
||||
|
||||
@ -688,7 +796,7 @@ bool IterOpenCLKernelCreator<T>::IsBuildRequired(Ember<T>& ember1, Ember<T>& emb
|
||||
/// </summary>
|
||||
/// <returns>The kernel string</returns>
|
||||
template <typename T>
|
||||
string IterOpenCLKernelCreator<T>::CreateZeroizeKernelString()
|
||||
string IterOpenCLKernelCreator<T>::CreateZeroizeKernelString() const
|
||||
{
|
||||
ostringstream os;
|
||||
|
||||
@ -707,8 +815,16 @@ string IterOpenCLKernelCreator<T>::CreateZeroizeKernelString()
|
||||
return os.str();
|
||||
}
|
||||
|
||||
/// <summary>
|
||||
/// Create the histogram summing kernel string.
|
||||
/// This is used when running with multiple GPUs. It takes
|
||||
/// two histograms present on a single device, source and dest,
|
||||
/// and adds the values of source to dest.
|
||||
/// It optionally sets all values of source to zero.
|
||||
/// </summary>
|
||||
/// <returns>The kernel string</returns>
|
||||
template <typename T>
|
||||
string IterOpenCLKernelCreator<T>::CreateSumHistKernelString()
|
||||
string IterOpenCLKernelCreator<T>::CreateSumHistKernelString() const
|
||||
{
|
||||
ostringstream os;
|
||||
|
||||
@ -739,7 +855,7 @@ string IterOpenCLKernelCreator<T>::CreateSumHistKernelString()
|
||||
/// <param name="ember">The ember to create the projection string for</param>
|
||||
/// <returns>The kernel string</returns>
|
||||
template <typename T>
|
||||
string IterOpenCLKernelCreator<T>::CreateProjectionString(Ember<T>& ember)
|
||||
string IterOpenCLKernelCreator<T>::CreateProjectionString(const Ember<T>& ember) const
|
||||
{
|
||||
size_t projBits = ember.ProjBits();
|
||||
ostringstream os;
|
||||
|
||||
@ -3,6 +3,7 @@
|
||||
#include "EmberCLPch.h"
|
||||
#include "EmberCLStructs.h"
|
||||
#include "EmberCLFunctions.h"
|
||||
#include "FunctionMapper.h"
|
||||
|
||||
/// <summary>
|
||||
/// IterOpenCLKernelCreator class.
|
||||
@ -29,20 +30,24 @@ public:
|
||||
const string& SumHistKernel() const;
|
||||
const string& SumHistEntryPoint() const;
|
||||
const string& IterEntryPoint() const;
|
||||
string CreateIterKernelString(Ember<T>& ember, string& parVarDefines, bool lockAccum = false, bool doAccum = true);
|
||||
static void ParVarIndexDefines(Ember<T>& ember, pair<string, vector<T>>& params, bool doVals = true, bool doString = true);
|
||||
static bool IsBuildRequired(Ember<T>& ember1, Ember<T>& ember2);
|
||||
string CreateIterKernelString(const Ember<T>& ember, string& parVarDefines, bool lockAccum = false, bool doAccum = true);
|
||||
string GlobalFunctionsString(const Ember<T>& ember);
|
||||
static void ParVarIndexDefines(const Ember<T>& ember, pair<string, vector<T>>& params, bool doVals = true, bool doString = true);
|
||||
static string VariationStateString(const Ember<T>& ember);
|
||||
static string VariationStateInitString(const Ember<T>& ember);
|
||||
static bool IsBuildRequired(const Ember<T>& ember1, const Ember<T>& ember2);
|
||||
|
||||
private:
|
||||
string CreateZeroizeKernelString();
|
||||
string CreateSumHistKernelString();
|
||||
string CreateProjectionString(Ember<T>& ember);
|
||||
string CreateZeroizeKernelString() const;
|
||||
string CreateSumHistKernelString() const;
|
||||
string CreateProjectionString(const Ember<T>& ember) const;
|
||||
|
||||
string m_IterEntryPoint;
|
||||
string m_ZeroizeKernel;
|
||||
string m_ZeroizeEntryPoint;
|
||||
string m_SumHistKernel;
|
||||
string m_SumHistEntryPoint;
|
||||
FunctionMapper m_FunctionMapper;
|
||||
};
|
||||
|
||||
#ifdef OPEN_CL_TEST_AREA
|
||||
|
||||
@ -354,7 +354,7 @@ bool RendererCL<T, bucketT>::WritePoints(size_t device, vector<PointCL<T>>& vec)
|
||||
|
||||
#ifdef TEST_CL
|
||||
template <typename T, typename bucketT>
|
||||
bool RendererCL<T, bucketT>::WriteRandomPoints()
|
||||
bool RendererCL<T, bucketT>::WriteRandomPoints(size_t device)
|
||||
{
|
||||
size_t size = IterGridKernelCount();
|
||||
vector<PointCL<T>> vec(size);
|
||||
@ -368,7 +368,7 @@ bool RendererCL<T, bucketT>::WriteRandomPoints()
|
||||
vec[i].m_LastXfUsed = 0;
|
||||
}
|
||||
|
||||
return WritePoints(vec);
|
||||
return WritePoints(device, vec);
|
||||
}
|
||||
#endif
|
||||
|
||||
@ -613,6 +613,8 @@ vector<string> RendererCL<T, bucketT>::ErrorReport()
|
||||
/// <summary>
|
||||
/// Set the vector of random contexts on every device.
|
||||
/// Call the base, and reset the seeds vector.
|
||||
/// Used on the command line when the user wants a specific set of seeds to start with to
|
||||
/// produce an exact result. Mostly for debugging.
|
||||
/// </summary>
|
||||
/// <param name="randVec">The vector of random contexts to assign</param>
|
||||
/// <returns>True if the size of the vector matched the number of threads used for rendering and writing seeds to OpenCL succeeded, else false.</returns>
|
||||
@ -707,9 +709,10 @@ bool RendererCL<T, bucketT>::ResetBuckets(bool resetHist, bool resetAccum)
|
||||
/// <summary>
|
||||
/// Perform log scale density filtering on the primary device.
|
||||
/// </summary>
|
||||
/// <param name="forceOutput">Whether this output was forced due to an interactive render</param>
|
||||
/// <returns>True if success and not aborted, else false.</returns>
|
||||
template <typename T, typename bucketT>
|
||||
eRenderStatus RendererCL<T, bucketT>::LogScaleDensityFilter()
|
||||
eRenderStatus RendererCL<T, bucketT>::LogScaleDensityFilter(bool forceOutput)
|
||||
{
|
||||
return RunLogScaleFilter();
|
||||
}
|
||||
@ -804,10 +807,10 @@ EmberStats RendererCL<T, bucketT>::Iterate(size_t iterCount, size_t temporalSamp
|
||||
{
|
||||
auto& wrapper = device->m_Wrapper;
|
||||
|
||||
if (b && !(b = wrapper.WriteBuffer (m_EmberBufferName, reinterpret_cast<void*>(&m_EmberCL), sizeof(m_EmberCL)))) { this->m_ErrorReport.push_back(loc); }
|
||||
if (b && !(b = wrapper.WriteBuffer (m_XformsBufferName, reinterpret_cast<void*>(m_XformsCL.data()), sizeof(m_XformsCL[0]) * m_XformsCL.size()))) { this->m_ErrorReport.push_back(loc); }
|
||||
if (b && !(b = wrapper.AddAndWriteBuffer(m_DistBufferName, reinterpret_cast<void*>(const_cast<byte*>(XformDistributions())), XformDistributionsSize()))) { this->m_ErrorReport.push_back(loc); }//Will be resized for xaos.
|
||||
if (b && !(b = wrapper.WriteBuffer (m_CarToRasBufferName, reinterpret_cast<void*>(&m_CarToRasCL), sizeof(m_CarToRasCL)))) { this->m_ErrorReport.push_back(loc); }
|
||||
if (b && !(b = wrapper.WriteBuffer (m_EmberBufferName, reinterpret_cast<void*>(&m_EmberCL), sizeof(m_EmberCL)))) { this->m_ErrorReport.push_back(loc); }
|
||||
if (b && !(b = wrapper.WriteBuffer (m_XformsBufferName, reinterpret_cast<void*>(m_XformsCL.data()), sizeof(m_XformsCL[0]) * m_XformsCL.size()))) { this->m_ErrorReport.push_back(loc); }
|
||||
if (b && !(b = wrapper.AddAndWriteBuffer(m_DistBufferName, reinterpret_cast<void*>(const_cast<byte*>(XformDistributions())), XformDistributionsSize()))) { this->m_ErrorReport.push_back(loc); }//Will be resized for xaos.
|
||||
if (b && !(b = wrapper.WriteBuffer (m_CarToRasBufferName, reinterpret_cast<void*>(&m_CarToRasCL), sizeof(m_CarToRasCL)))) { this->m_ErrorReport.push_back(loc); }
|
||||
|
||||
if (b && !(b = wrapper.AddAndWriteImage("Palette", CL_MEM_READ_ONLY, m_PaletteFormat, m_Dmap.m_Entries.size(), 1, 0, m_Dmap.m_Entries.data()))) { this->m_ErrorReport.push_back(loc); }
|
||||
|
||||
@ -966,7 +969,7 @@ bool RendererCL<T, bucketT>::RunIter(size_t iterCount, size_t temporalSample, si
|
||||
{
|
||||
cl_uint argIndex = 0;
|
||||
#ifdef TEST_CL
|
||||
fuse = 0;
|
||||
uint fuse = 0;
|
||||
#else
|
||||
uint fuse = uint((m_Devices[dev]->m_Calls % fuseFreq) == 0u ? FuseCount() : 0u);
|
||||
#endif
|
||||
|
||||
@ -129,7 +129,7 @@ public:
|
||||
bool ClearAccum();
|
||||
bool WritePoints(size_t device, vector<PointCL<T>>& vec);
|
||||
#ifdef TEST_CL
|
||||
bool WriteRandomPoints();
|
||||
bool WriteRandomPoints(size_t device);
|
||||
#endif
|
||||
const string& IterKernel() const;
|
||||
const string& DEKernel() const;
|
||||
@ -159,7 +159,7 @@ protected:
|
||||
//Protected virtual functions overridden from Renderer.
|
||||
virtual bool Alloc(bool histOnly = false) override;
|
||||
virtual bool ResetBuckets(bool resetHist = true, bool resetAccum = true) override;
|
||||
virtual eRenderStatus LogScaleDensityFilter() override;
|
||||
virtual eRenderStatus LogScaleDensityFilter(bool forceOutput = false) override;
|
||||
virtual eRenderStatus GaussianDensityFilter() override;
|
||||
virtual eRenderStatus AccumulatorToFinalImage(byte* pixels, size_t finalOffset) override;
|
||||
virtual EmberStats Iterate(size_t iterCount, size_t temporalSample) override;
|
||||
|
||||
Reference in New Issue
Block a user