mirror of
https://bitbucket.org/mfeemster/fractorium.git
synced 2025-07-17 05:34:50 -04:00
--Bug fixes
-Fix crash when using Lanczos2 filter with color curves due to negative numbers. Fix by passing abs() of first argument to pow() in Renderer::GammaCorrection(). -Fix crash in hexes with SP. Rounding error caused out of bounds index.
This commit is contained in:
mfeemster
@ -12,22 +12,17 @@ FinalAccumOpenCLKernelCreator::FinalAccumOpenCLKernelCreator(bool doublePrecisio
|
||||
m_DoublePrecision = doublePrecision;
|
||||
m_GammaCorrectionWithAlphaCalcEntryPoint = "GammaCorrectionWithAlphaCalcKernel";
|
||||
m_GammaCorrectionWithoutAlphaCalcEntryPoint = "GammaCorrectionWithoutAlphaCalcKernel";
|
||||
|
||||
m_GammaCorrectionWithAlphaCalcKernel = CreateGammaCorrectionKernelString(true);
|
||||
m_GammaCorrectionWithoutAlphaCalcKernel = CreateGammaCorrectionKernelString(false);
|
||||
|
||||
m_FinalAccumEarlyClipEntryPoint = "FinalAccumEarlyClipKernel";
|
||||
m_FinalAccumEarlyClipWithAlphaCalcWithAlphaAccumEntryPoint = "FinalAccumEarlyClipWithAlphaCalcWithAlphaAccumKernel";
|
||||
m_FinalAccumEarlyClipWithoutAlphaCalcWithAlphaAccumEntryPoint = "FinalAccumEarlyClipWithoutAlphaCalcWithAlphaAccumKernel";
|
||||
|
||||
m_FinalAccumEarlyClipKernel = CreateFinalAccumKernelString(true, false, false);
|
||||
m_FinalAccumEarlyClipWithAlphaCalcWithAlphaAccumKernel = CreateFinalAccumKernelString(true, true, true);
|
||||
m_FinalAccumEarlyClipWithoutAlphaCalcWithAlphaAccumKernel = CreateFinalAccumKernelString(true, false, true);
|
||||
|
||||
m_FinalAccumLateClipEntryPoint = "FinalAccumLateClipKernel";
|
||||
m_FinalAccumLateClipWithAlphaCalcWithAlphaAccumEntryPoint = "FinalAccumLateClipWithAlphaCalcWithAlphaAccumKernel";
|
||||
m_FinalAccumLateClipWithoutAlphaCalcWithAlphaAccumEntryPoint = "FinalAccumLateClipWithoutAlphaCalcWithAlphaAccumKernel";
|
||||
|
||||
m_FinalAccumLateClipKernel = CreateFinalAccumKernelString(false, false, false);
|
||||
m_FinalAccumLateClipWithAlphaCalcWithAlphaAccumKernel = CreateFinalAccumKernelString(false, true, true);
|
||||
m_FinalAccumLateClipWithoutAlphaCalcWithAlphaAccumKernel = CreateFinalAccumKernelString(false, false, true);
|
||||
@ -183,15 +178,14 @@ string FinalAccumOpenCLKernelCreator::CreateFinalAccumKernelString(bool earlyCli
|
||||
{
|
||||
ostringstream os;
|
||||
string channels = alphaAccum ? "4" : "3";
|
||||
|
||||
os <<
|
||||
ConstantDefinesString(m_DoublePrecision) <<
|
||||
UnionCLStructString <<
|
||||
RgbToHsvFunctionString <<
|
||||
HsvToRgbFunctionString <<
|
||||
CalcAlphaFunctionString <<
|
||||
CurveAdjustFunctionString <<
|
||||
SpatialFilterCLStructString;
|
||||
ConstantDefinesString(m_DoublePrecision) <<
|
||||
UnionCLStructString <<
|
||||
RgbToHsvFunctionString <<
|
||||
HsvToRgbFunctionString <<
|
||||
CalcAlphaFunctionString <<
|
||||
CurveAdjustFunctionString <<
|
||||
SpatialFilterCLStructString;
|
||||
|
||||
if (earlyClip)
|
||||
{
|
||||
@ -207,8 +201,8 @@ string FinalAccumOpenCLKernelCreator::CreateFinalAccumKernelString(bool earlyCli
|
||||
else
|
||||
{
|
||||
os <<
|
||||
CreateCalcNewRgbFunctionString(false) <<
|
||||
CreateGammaCorrectionFunctionString(false, alphaCalc, alphaAccum, true);
|
||||
CreateCalcNewRgbFunctionString(false) <<
|
||||
CreateGammaCorrectionFunctionString(false, alphaCalc, alphaAccum, true);
|
||||
|
||||
if (!alphaCalc && !alphaAccum)//Rgb output, the most common case.
|
||||
os << "__kernel void " << m_FinalAccumLateClipEntryPoint << "(\n";
|
||||
@ -221,53 +215,53 @@ string FinalAccumOpenCLKernelCreator::CreateFinalAccumKernelString(bool earlyCli
|
||||
}
|
||||
|
||||
os <<
|
||||
" const __global real4reals_bucket* accumulator,\n"
|
||||
" __write_only image2d_t pixels,\n"
|
||||
" __constant SpatialFilterCL* spatialFilter,\n"
|
||||
" __constant real_bucket_t* filterCoefs,\n"
|
||||
" __constant real4reals_bucket* csa,\n"
|
||||
" const uint doCurves,\n"
|
||||
" const real_bucket_t alphaBase,\n"
|
||||
" const real_bucket_t alphaScale\n"
|
||||
"\t)\n"
|
||||
"{\n"
|
||||
"\n"
|
||||
" if ((GLOBAL_ID_Y >= spatialFilter->m_FinalRasH) || (GLOBAL_ID_X >= spatialFilter->m_FinalRasW))\n"
|
||||
" return;\n"
|
||||
"\n"
|
||||
" uint accumX = spatialFilter->m_DensityFilterOffset + (GLOBAL_ID_X * spatialFilter->m_Supersample);\n"
|
||||
" uint accumY = spatialFilter->m_DensityFilterOffset + (GLOBAL_ID_Y * spatialFilter->m_Supersample);\n"
|
||||
" int2 finalCoord;\n"
|
||||
" finalCoord.x = GLOBAL_ID_X;\n"
|
||||
" finalCoord.y = (int)((spatialFilter->m_YAxisUp == 1) ? ((spatialFilter->m_FinalRasH - GLOBAL_ID_Y) - 1) : GLOBAL_ID_Y);\n"
|
||||
" float4floats finalColor;\n"
|
||||
" int ii, jj;\n"
|
||||
" uint filterKRowIndex;\n"
|
||||
" const __global real4reals_bucket* accumBucket;\n"
|
||||
" real4reals_bucket newBucket;\n"
|
||||
" newBucket.m_Real4 = 0;\n"
|
||||
"\n"
|
||||
" for (jj = 0; jj < spatialFilter->m_FilterWidth; jj++)\n"
|
||||
" {\n"
|
||||
" filterKRowIndex = jj * spatialFilter->m_FilterWidth;\n"
|
||||
"\n"
|
||||
" for (ii = 0; ii < spatialFilter->m_FilterWidth; ii++)\n"
|
||||
" {\n"
|
||||
" real_bucket_t k = filterCoefs[ii + filterKRowIndex];\n"
|
||||
"\n"
|
||||
" accumBucket = accumulator + (accumX + ii) + ((accumY + jj) * spatialFilter->m_SuperRasW);\n"
|
||||
" newBucket.m_Real4 += (k * accumBucket->m_Real4);\n"
|
||||
" }\n"
|
||||
" }\n"
|
||||
"\n";
|
||||
" const __global real4reals_bucket* accumulator,\n"
|
||||
" __write_only image2d_t pixels,\n"
|
||||
" __constant SpatialFilterCL* spatialFilter,\n"
|
||||
" __constant real_bucket_t* filterCoefs,\n"
|
||||
" __constant real4reals_bucket* csa,\n"
|
||||
" const uint doCurves,\n"
|
||||
" const real_bucket_t alphaBase,\n"
|
||||
" const real_bucket_t alphaScale\n"
|
||||
"\t)\n"
|
||||
"{\n"
|
||||
"\n"
|
||||
" if ((GLOBAL_ID_Y >= spatialFilter->m_FinalRasH) || (GLOBAL_ID_X >= spatialFilter->m_FinalRasW))\n"
|
||||
" return;\n"
|
||||
"\n"
|
||||
" uint accumX = spatialFilter->m_DensityFilterOffset + (GLOBAL_ID_X * spatialFilter->m_Supersample);\n"
|
||||
" uint accumY = spatialFilter->m_DensityFilterOffset + (GLOBAL_ID_Y * spatialFilter->m_Supersample);\n"
|
||||
" int2 finalCoord;\n"
|
||||
" finalCoord.x = GLOBAL_ID_X;\n"
|
||||
" finalCoord.y = (int)((spatialFilter->m_YAxisUp == 1) ? ((spatialFilter->m_FinalRasH - GLOBAL_ID_Y) - 1) : GLOBAL_ID_Y);\n"
|
||||
" float4floats finalColor;\n"
|
||||
" int ii, jj;\n"
|
||||
" uint filterKRowIndex;\n"
|
||||
" const __global real4reals_bucket* accumBucket;\n"
|
||||
" real4reals_bucket newBucket;\n"
|
||||
" newBucket.m_Real4 = 0;\n"
|
||||
"\n"
|
||||
" for (jj = 0; jj < spatialFilter->m_FilterWidth; jj++)\n"
|
||||
" {\n"
|
||||
" filterKRowIndex = jj * spatialFilter->m_FilterWidth;\n"
|
||||
"\n"
|
||||
" for (ii = 0; ii < spatialFilter->m_FilterWidth; ii++)\n"
|
||||
" {\n"
|
||||
" real_bucket_t k = filterCoefs[ii + filterKRowIndex];\n"
|
||||
"\n"
|
||||
" accumBucket = accumulator + (accumX + ii) + ((accumY + jj) * spatialFilter->m_SuperRasW);\n"
|
||||
" newBucket.m_Real4 += (k * accumBucket->m_Real4);\n"
|
||||
" }\n"
|
||||
" }\n"
|
||||
"\n";
|
||||
|
||||
//Not supporting 2 bytes per channel on the GPU. If the user wants it, run on the CPU.
|
||||
if (earlyClip)//If early clip, simply assign values directly to the temp float4 since they've been gamma corrected already, then write it straight to the output image below.
|
||||
{
|
||||
os <<
|
||||
" finalColor.m_Float4.x = (float)newBucket.m_Real4.x;\n"//CPU side clamps, skip here because write_imagef() does the clamping for us.
|
||||
" finalColor.m_Float4.y = (float)newBucket.m_Real4.y;\n"
|
||||
" finalColor.m_Float4.z = (float)newBucket.m_Real4.z;\n";
|
||||
" finalColor.m_Float4.x = (float)newBucket.m_Real4.x;\n"//CPU side clamps, skip here because write_imagef() does the clamping for us.
|
||||
" finalColor.m_Float4.y = (float)newBucket.m_Real4.y;\n"
|
||||
" finalColor.m_Float4.z = (float)newBucket.m_Real4.z;\n";
|
||||
|
||||
if (alphaAccum)
|
||||
{
|
||||
@ -283,37 +277,36 @@ string FinalAccumOpenCLKernelCreator::CreateFinalAccumKernelString(bool earlyCli
|
||||
if (m_DoublePrecision)
|
||||
{
|
||||
os <<
|
||||
" real4reals_bucket realFinal;\n"
|
||||
"\n"
|
||||
" GammaCorrectionFloats(&newBucket, &(spatialFilter->m_Background[0]), spatialFilter->m_Gamma, spatialFilter->m_LinRange, spatialFilter->m_Vibrancy, spatialFilter->m_HighlightPower, alphaBase, alphaScale, &(realFinal.m_Reals[0]));\n"
|
||||
" finalColor.m_Float4.x = (float)realFinal.m_Real4.x;\n"
|
||||
" finalColor.m_Float4.y = (float)realFinal.m_Real4.y;\n"
|
||||
" finalColor.m_Float4.z = (float)realFinal.m_Real4.z;\n"
|
||||
" finalColor.m_Float4.w = (float)realFinal.m_Real4.w;\n"
|
||||
;
|
||||
" real4reals_bucket realFinal;\n"
|
||||
"\n"
|
||||
" GammaCorrectionFloats(&newBucket, &(spatialFilter->m_Background[0]), spatialFilter->m_Gamma, spatialFilter->m_LinRange, spatialFilter->m_Vibrancy, spatialFilter->m_HighlightPower, alphaBase, alphaScale, &(realFinal.m_Reals[0]));\n"
|
||||
" finalColor.m_Float4.x = (float)realFinal.m_Real4.x;\n"
|
||||
" finalColor.m_Float4.y = (float)realFinal.m_Real4.y;\n"
|
||||
" finalColor.m_Float4.z = (float)realFinal.m_Real4.z;\n"
|
||||
" finalColor.m_Float4.w = (float)realFinal.m_Real4.w;\n"
|
||||
;
|
||||
}
|
||||
else
|
||||
{
|
||||
os <<
|
||||
" GammaCorrectionFloats(&newBucket, &(spatialFilter->m_Background[0]), spatialFilter->m_Gamma, spatialFilter->m_LinRange, spatialFilter->m_Vibrancy, spatialFilter->m_HighlightPower, alphaBase, alphaScale, &(finalColor.m_Floats[0]));\n";
|
||||
" GammaCorrectionFloats(&newBucket, &(spatialFilter->m_Background[0]), spatialFilter->m_Gamma, spatialFilter->m_LinRange, spatialFilter->m_Vibrancy, spatialFilter->m_HighlightPower, alphaBase, alphaScale, &(finalColor.m_Floats[0]));\n";
|
||||
}
|
||||
}
|
||||
|
||||
os <<
|
||||
"\n"
|
||||
" if (doCurves)\n"
|
||||
" {\n"
|
||||
" CurveAdjust(csa, &(finalColor.m_Floats[0]), 1);\n"
|
||||
" CurveAdjust(csa, &(finalColor.m_Floats[1]), 2);\n"
|
||||
" CurveAdjust(csa, &(finalColor.m_Floats[2]), 3);\n"
|
||||
" }\n"
|
||||
"\n"
|
||||
" finalColor.m_Float4 /= 255.0f;\n"
|
||||
" write_imagef(pixels, finalCoord, finalColor.m_Float4);\n"//Use write_imagef instead of write_imageui because only the former works when sharing with an OpenGL texture.
|
||||
" barrier(CLK_GLOBAL_MEM_FENCE);\n"//Required, or else page tearing will occur during interactive rendering.
|
||||
"}\n"
|
||||
;
|
||||
|
||||
"\n"
|
||||
" if (doCurves)\n"
|
||||
" {\n"
|
||||
" CurveAdjust(csa, &(finalColor.m_Floats[0]), 1);\n"
|
||||
" CurveAdjust(csa, &(finalColor.m_Floats[1]), 2);\n"
|
||||
" CurveAdjust(csa, &(finalColor.m_Floats[2]), 3);\n"
|
||||
" }\n"
|
||||
"\n"
|
||||
" finalColor.m_Float4 /= 255.0f;\n"
|
||||
" write_imagef(pixels, finalCoord, finalColor.m_Float4);\n"//Use write_imagef instead of write_imageui because only the former works when sharing with an OpenGL texture.
|
||||
" barrier(CLK_GLOBAL_MEM_FENCE);\n"//Required, or else page tearing will occur during interactive rendering.
|
||||
"}\n"
|
||||
;
|
||||
return os.str();
|
||||
}
|
||||
|
||||
@ -332,54 +325,52 @@ string FinalAccumOpenCLKernelCreator::CreateGammaCorrectionFunctionString(bool g
|
||||
string dataType;
|
||||
string unionMember;
|
||||
dataType = "real_bucket_t";
|
||||
|
||||
//Use real_t for all cases, early clip and final accum.
|
||||
os << "void GammaCorrectionFloats(" << (globalBucket ? "__global " : "") << "real4reals_bucket* bucket, __constant real_bucket_t* background, real_bucket_t g, real_bucket_t linRange, real_bucket_t vibrancy, real_bucket_t highlightPower, real_bucket_t alphaBase, real_bucket_t alphaScale, " << (finalOut ? "" : "__global") << " real_bucket_t* correctedChannels)\n";
|
||||
|
||||
os
|
||||
<< "{\n"
|
||||
<< " real_bucket_t alpha, ls, tmp, a;\n"
|
||||
<< " real4reals_bucket newRgb;\n"
|
||||
<< "\n"
|
||||
<< " if (bucket->m_Reals[3] <= 0)\n"
|
||||
<< " {\n"
|
||||
<< " alpha = 0;\n"
|
||||
<< " ls = 0;\n"
|
||||
<< " }\n"
|
||||
<< " else\n"
|
||||
<< " {\n"
|
||||
<< " tmp = bucket->m_Reals[3];\n"
|
||||
<< " alpha = CalcAlpha(tmp, g, linRange);\n"
|
||||
<< " ls = vibrancy * 256.0 * alpha / tmp;\n"
|
||||
<< " alpha = clamp(alpha, (real_bucket_t)0.0, (real_bucket_t)1.0);\n"
|
||||
<< " }\n"
|
||||
<< "\n"
|
||||
<< " CalcNewRgb(bucket, ls, highlightPower, &newRgb);\n"
|
||||
<< "\n"
|
||||
<< " for (uint rgbi = 0; rgbi < 3; rgbi++)\n"
|
||||
<< " {\n"
|
||||
<< " a = newRgb.m_Reals[rgbi] + ((1.0 - vibrancy) * 256.0 * pow(bucket->m_Reals[rgbi], g));\n"
|
||||
<< "\n";
|
||||
<< "{\n"
|
||||
<< " real_bucket_t alpha, ls, tmp, a;\n"
|
||||
<< " real4reals_bucket newRgb;\n"
|
||||
<< "\n"
|
||||
<< " if (bucket->m_Reals[3] <= 0)\n"
|
||||
<< " {\n"
|
||||
<< " alpha = 0;\n"
|
||||
<< " ls = 0;\n"
|
||||
<< " }\n"
|
||||
<< " else\n"
|
||||
<< " {\n"
|
||||
<< " tmp = bucket->m_Reals[3];\n"
|
||||
<< " alpha = CalcAlpha(tmp, g, linRange);\n"
|
||||
<< " ls = vibrancy * 256.0 * alpha / tmp;\n"
|
||||
<< " alpha = clamp(alpha, (real_bucket_t)0.0, (real_bucket_t)1.0);\n"
|
||||
<< " }\n"
|
||||
<< "\n"
|
||||
<< " CalcNewRgb(bucket, ls, highlightPower, &newRgb);\n"
|
||||
<< "\n"
|
||||
<< " for (uint rgbi = 0; rgbi < 3; rgbi++)\n"
|
||||
<< " {\n"
|
||||
<< " a = newRgb.m_Reals[rgbi] + ((1.0 - vibrancy) * 256.0 * pow(fabs(bucket->m_Reals[rgbi]), g));\n"
|
||||
<< "\n";
|
||||
|
||||
if (!alphaCalc)
|
||||
{
|
||||
os <<
|
||||
" a += ((1.0 - alpha) * background[rgbi]);\n";
|
||||
" a += ((1.0 - alpha) * background[rgbi]);\n";
|
||||
}
|
||||
else
|
||||
{
|
||||
os
|
||||
<< " if (alpha > 0)\n"
|
||||
<< " a /= alpha;\n"
|
||||
<< " else\n"
|
||||
<< " a = 0;\n";
|
||||
<< " if (alpha > 0)\n"
|
||||
<< " a /= alpha;\n"
|
||||
<< " else\n"
|
||||
<< " a = 0;\n";
|
||||
}
|
||||
|
||||
os <<
|
||||
"\n"
|
||||
" correctedChannels[rgbi] = (" << dataType << ")clamp(a, (real_bucket_t)0.0, (real_bucket_t)255.0);\n"
|
||||
" }\n"
|
||||
"\n";
|
||||
"\n"
|
||||
" correctedChannels[rgbi] = (" << dataType << ")clamp(a, (real_bucket_t)0.0, (real_bucket_t)255.0);\n"
|
||||
" }\n"
|
||||
"\n";
|
||||
|
||||
//The CPU code has 3 cases for assigning alpha:
|
||||
//[3] = alpha.//Early clip.
|
||||
@ -393,13 +384,12 @@ string FinalAccumOpenCLKernelCreator::CreateGammaCorrectionFunctionString(bool g
|
||||
if (alphaAccum)
|
||||
{
|
||||
os
|
||||
<< " correctedChannels[3] = (" << dataType << ")(alphaBase + (alpha * alphaScale));\n";
|
||||
<< " correctedChannels[3] = (" << dataType << ")(alphaBase + (alpha * alphaScale));\n";
|
||||
}
|
||||
|
||||
os <<
|
||||
"}\n"
|
||||
"\n";
|
||||
|
||||
"}\n"
|
||||
"\n";
|
||||
return os.str();
|
||||
}
|
||||
|
||||
@ -411,63 +401,61 @@ string FinalAccumOpenCLKernelCreator::CreateGammaCorrectionFunctionString(bool g
|
||||
string FinalAccumOpenCLKernelCreator::CreateCalcNewRgbFunctionString(bool globalBucket)
|
||||
{
|
||||
ostringstream os;
|
||||
|
||||
os <<
|
||||
"static void CalcNewRgb(" << (globalBucket ? "__global " : "") << "real4reals_bucket* oldRgb, real_bucket_t ls, real_bucket_t highPow, real4reals_bucket* newRgb)\n"
|
||||
"{\n"
|
||||
" int rgbi;\n"
|
||||
" real_bucket_t newls, lsratio;\n"
|
||||
" real4reals_bucket newHsv;\n"
|
||||
" real_bucket_t maxa, maxc;\n"
|
||||
" real_bucket_t adjhlp;\n"
|
||||
"\n"
|
||||
" if (ls == 0 || (oldRgb->m_Real4.x == 0 && oldRgb->m_Real4.y == 0 && oldRgb->m_Real4.z == 0))\n"//Can't do a vector compare to zero.
|
||||
" {\n"
|
||||
" newRgb->m_Real4 = 0;\n"
|
||||
" return;\n"
|
||||
" }\n"
|
||||
"\n"
|
||||
//Identify the most saturated channel.
|
||||
" maxc = max(max(oldRgb->m_Reals[0], oldRgb->m_Reals[1]), oldRgb->m_Reals[2]);\n"
|
||||
" maxa = ls * maxc;\n"
|
||||
"\n"
|
||||
//If a channel is saturated and highlight power is non-negative
|
||||
//modify the color to prevent hue shift.
|
||||
" if (maxa > 255 && highPow >= 0)\n"
|
||||
" {\n"
|
||||
" newls = 255.0 / maxc;\n"
|
||||
" lsratio = pow(newls / ls, highPow);\n"
|
||||
"\n"
|
||||
//Calculate the max-value color (ranged 0 - 1).
|
||||
" for (rgbi = 0; rgbi < 3; rgbi++)\n"
|
||||
" newRgb->m_Reals[rgbi] = newls * oldRgb->m_Reals[rgbi] / 255.0;\n"
|
||||
"\n"
|
||||
//Reduce saturation by the lsratio.
|
||||
" RgbToHsv(&(newRgb->m_Real4), &(newHsv.m_Real4));\n"
|
||||
" newHsv.m_Real4.y *= lsratio;\n"
|
||||
" HsvToRgb(&(newHsv.m_Real4), &(newRgb->m_Real4));\n"
|
||||
"\n"
|
||||
" for (rgbi = 0; rgbi < 3; rgbi++)\n"//Unrolling and vectorizing makes no difference.
|
||||
" newRgb->m_Reals[rgbi] *= 255.0;\n"
|
||||
" }\n"
|
||||
" else\n"
|
||||
" {\n"
|
||||
" newls = 255.0 / maxc;\n"
|
||||
" adjhlp = -highPow;\n"
|
||||
"\n"
|
||||
" if (adjhlp > 1)\n"
|
||||
" adjhlp = 1;\n"
|
||||
"\n"
|
||||
" if (maxa <= 255)\n"
|
||||
" adjhlp = 1;\n"
|
||||
"\n"
|
||||
//Calculate the max-value color (ranged 0 - 1) interpolated with the old behavior.
|
||||
" for (rgbi = 0; rgbi < 3; rgbi++)\n"//Unrolling, caching and vectorizing makes no difference.
|
||||
" newRgb->m_Reals[rgbi] = ((1.0 - adjhlp) * newls + adjhlp * ls) * oldRgb->m_Reals[rgbi];\n"
|
||||
" }\n"
|
||||
"}\n"
|
||||
"\n";
|
||||
|
||||
"static void CalcNewRgb(" << (globalBucket ? "__global " : "") << "real4reals_bucket* oldRgb, real_bucket_t ls, real_bucket_t highPow, real4reals_bucket* newRgb)\n"
|
||||
"{\n"
|
||||
" int rgbi;\n"
|
||||
" real_bucket_t newls, lsratio;\n"
|
||||
" real4reals_bucket newHsv;\n"
|
||||
" real_bucket_t maxa, maxc;\n"
|
||||
" real_bucket_t adjhlp;\n"
|
||||
"\n"
|
||||
" if (ls == 0 || (oldRgb->m_Real4.x == 0 && oldRgb->m_Real4.y == 0 && oldRgb->m_Real4.z == 0))\n"//Can't do a vector compare to zero.
|
||||
" {\n"
|
||||
" newRgb->m_Real4 = 0;\n"
|
||||
" return;\n"
|
||||
" }\n"
|
||||
"\n"
|
||||
//Identify the most saturated channel.
|
||||
" maxc = max(max(oldRgb->m_Reals[0], oldRgb->m_Reals[1]), oldRgb->m_Reals[2]);\n"
|
||||
" maxa = ls * maxc;\n"
|
||||
"\n"
|
||||
//If a channel is saturated and highlight power is non-negative
|
||||
//modify the color to prevent hue shift.
|
||||
" if (maxa > 255 && highPow >= 0)\n"
|
||||
" {\n"
|
||||
" newls = 255.0 / maxc;\n"
|
||||
" lsratio = pow(newls / ls, highPow);\n"
|
||||
"\n"
|
||||
//Calculate the max-value color (ranged 0 - 1).
|
||||
" for (rgbi = 0; rgbi < 3; rgbi++)\n"
|
||||
" newRgb->m_Reals[rgbi] = newls * oldRgb->m_Reals[rgbi] / 255.0;\n"
|
||||
"\n"
|
||||
//Reduce saturation by the lsratio.
|
||||
" RgbToHsv(&(newRgb->m_Real4), &(newHsv.m_Real4));\n"
|
||||
" newHsv.m_Real4.y *= lsratio;\n"
|
||||
" HsvToRgb(&(newHsv.m_Real4), &(newRgb->m_Real4));\n"
|
||||
"\n"
|
||||
" for (rgbi = 0; rgbi < 3; rgbi++)\n"//Unrolling and vectorizing makes no difference.
|
||||
" newRgb->m_Reals[rgbi] *= 255.0;\n"
|
||||
" }\n"
|
||||
" else\n"
|
||||
" {\n"
|
||||
" newls = 255.0 / maxc;\n"
|
||||
" adjhlp = -highPow;\n"
|
||||
"\n"
|
||||
" if (adjhlp > 1)\n"
|
||||
" adjhlp = 1;\n"
|
||||
"\n"
|
||||
" if (maxa <= 255)\n"
|
||||
" adjhlp = 1;\n"
|
||||
"\n"
|
||||
//Calculate the max-value color (ranged 0 - 1) interpolated with the old behavior.
|
||||
" for (rgbi = 0; rgbi < 3; rgbi++)\n"//Unrolling, caching and vectorizing makes no difference.
|
||||
" newRgb->m_Reals[rgbi] = ((1.0 - adjhlp) * newls + adjhlp * ls) * oldRgb->m_Reals[rgbi];\n"
|
||||
" }\n"
|
||||
"}\n"
|
||||
"\n";
|
||||
return os.str();
|
||||
}
|
||||
|
||||
@ -480,34 +468,31 @@ string FinalAccumOpenCLKernelCreator::CreateGammaCorrectionKernelString(bool alp
|
||||
{
|
||||
ostringstream os;
|
||||
string dataType;
|
||||
|
||||
os <<
|
||||
ConstantDefinesString(m_DoublePrecision) <<
|
||||
UnionCLStructString <<
|
||||
RgbToHsvFunctionString <<
|
||||
HsvToRgbFunctionString <<
|
||||
CalcAlphaFunctionString <<
|
||||
CreateCalcNewRgbFunctionString(true) <<
|
||||
SpatialFilterCLStructString <<
|
||||
CreateGammaCorrectionFunctionString(true, alphaCalc, true, false);//Will only be used with float in this case, early clip. Will always alpha accum.
|
||||
|
||||
os << "__kernel void " << (alphaCalc ? m_GammaCorrectionWithAlphaCalcEntryPoint : m_GammaCorrectionWithoutAlphaCalcEntryPoint) << "(\n" <<
|
||||
" __global real4reals_bucket* accumulator,\n"
|
||||
" __constant SpatialFilterCL* spatialFilter\n"
|
||||
")\n"
|
||||
"{\n"
|
||||
" int testGutter = 0;\n"
|
||||
"\n"
|
||||
" if (GLOBAL_ID_Y >= (spatialFilter->m_SuperRasH - testGutter) || GLOBAL_ID_X >= (spatialFilter->m_SuperRasW - testGutter))\n"
|
||||
" return;\n"
|
||||
"\n"
|
||||
" uint superIndex = (GLOBAL_ID_Y * spatialFilter->m_SuperRasW) + GLOBAL_ID_X;\n"
|
||||
" __global real4reals_bucket* bucket = accumulator + superIndex;\n"
|
||||
//Pass in an alphaBase and alphaScale of 0, 1 which means to just directly assign the computed alpha value.
|
||||
" GammaCorrectionFloats(bucket, &(spatialFilter->m_Background[0]), spatialFilter->m_Gamma, spatialFilter->m_LinRange, spatialFilter->m_Vibrancy, spatialFilter->m_HighlightPower, 0.0, 1.0, &(bucket->m_Reals[0]));\n"
|
||||
"}\n"
|
||||
;
|
||||
|
||||
ConstantDefinesString(m_DoublePrecision) <<
|
||||
UnionCLStructString <<
|
||||
RgbToHsvFunctionString <<
|
||||
HsvToRgbFunctionString <<
|
||||
CalcAlphaFunctionString <<
|
||||
CreateCalcNewRgbFunctionString(true) <<
|
||||
SpatialFilterCLStructString <<
|
||||
CreateGammaCorrectionFunctionString(true, alphaCalc, true, false);//Will only be used with float in this case, early clip. Will always alpha accum.
|
||||
os << "__kernel void " << (alphaCalc ? m_GammaCorrectionWithAlphaCalcEntryPoint : m_GammaCorrectionWithoutAlphaCalcEntryPoint) << "(\n" <<
|
||||
" __global real4reals_bucket* accumulator,\n"
|
||||
" __constant SpatialFilterCL* spatialFilter\n"
|
||||
")\n"
|
||||
"{\n"
|
||||
" int testGutter = 0;\n"
|
||||
"\n"
|
||||
" if (GLOBAL_ID_Y >= (spatialFilter->m_SuperRasH - testGutter) || GLOBAL_ID_X >= (spatialFilter->m_SuperRasW - testGutter))\n"
|
||||
" return;\n"
|
||||
"\n"
|
||||
" uint superIndex = (GLOBAL_ID_Y * spatialFilter->m_SuperRasW) + GLOBAL_ID_X;\n"
|
||||
" __global real4reals_bucket* bucket = accumulator + superIndex;\n"
|
||||
//Pass in an alphaBase and alphaScale of 0, 1 which means to just directly assign the computed alpha value.
|
||||
" GammaCorrectionFloats(bucket, &(spatialFilter->m_Background[0]), spatialFilter->m_Gamma, spatialFilter->m_LinRange, spatialFilter->m_Vibrancy, spatialFilter->m_HighlightPower, 0.0, 1.0, &(bucket->m_Reals[0]));\n"
|
||||
"}\n"
|
||||
;
|
||||
return os.str();
|
||||
}
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user