尝试使用与使用TBB(线程构建块)运行时使用的相同代码(类型)。
我对OpenCL没有太多经验,但我认为大部分主要代码都是正确的。我相信这些错误都在.cl
文件中,在那里进行数学计算。
这是我在TBB中的mandelbrot代码:
这是我在OpenCL中的代码
非常感谢任何帮助。
答案 0 :(得分:1)
查看此链接。它由@ eric-bainville开发。本机和OpenCL的CPU代码都不是最佳的(它不使用SSE / AVX),但我认为GPU代码可能很好。对于CPU,您可以通过使用AVX并一次操作八个像素来加快代码速度。
答案 1 :(得分:1)
我更改了内核中的代码,运行正常。我的新内核代码如下:
// voronoi kernels
//
// local memory version
//
kernel void voronoiL(write_only image2d_t outputImage)
{
// get id of element in array
int x = get_global_id(0);
int y = get_global_id(1);
int w = get_global_size(0);
int h = get_global_size(1);
float4 result = (float4)(0.0f,0.0f,0.0f,1.0f);
float MinRe = -2.0f;
float MaxRe = 1.0f;
float MinIm = -1.5f;
float MaxIm = MinIm+(MaxRe-MinRe)*h/w;
float Re_factor = (MaxRe-MinRe)/(w-1);
float Im_factor = (MaxIm-MinIm)/(h-1);
float MaxIterations = 50;
//C imaginary
float c_im = MaxIm - y*Im_factor;
//C real
float c_re = MinRe + x*Re_factor;
//Z real
float Z_re = c_re, Z_im = c_im;
bool isInside = true;
bool col2 = false;
bool col3 = false;
int iteration =0;
for(int n=0; n<MaxIterations; n++)
{
// Z - real and imaginary
float Z_re2 = Z_re*Z_re, Z_im2 = Z_im*Z_im;
//if Z real squared plus Z imaginary squared is greater than c squared
if(Z_re2 + Z_im2 > 4)
{
if(n >= 0 && n <= (MaxIterations/2-1))
{
col2 = true;
isInside = false;
break;
}
else if(n >= MaxIterations/2 && n <= MaxIterations-1)
{
col3 = true;
isInside = false;
break;
}
}
Z_im = 2*Z_re*Z_im + c_im;
Z_re = Z_re2 - Z_im2 + c_re;
iteration++;
}
if(col2)
{
result = (float4)(iteration*0.05f,0.0f, 0.0f, 1.0f);
}
else if(col3)
{
result = (float4)(255, iteration*0.05f, iteration*0.05f, 1.0f);
}
else if(isInside)
{
result = (float4)(0.0f, 0.0f, 0.0f, 1.0f);
}
write_imagef(outputImage, (int2)(x, y), result);
}
你也可以在这里找到它:
https://docs.google.com/file/d/0B6DBARvnB__iUjNSTWJubFhUSDA/edit