编辑“︁OpenCL”︁（章节）

=== 快速傅立葉變換 ===
一個[[快速傅立葉變換]]的式子：
<ref name=siggraph>{{cite web | url=http://s08.idav.ucdavis.edu/munshi-opencl.pdf | title=OpenCL | accessdate=2008-08-14 | publisher=SIGGRAPH2008 | date=2008-08-14 | archive-url=https://www.webcitation.org/66GmScoh5?url=http://s08.idav.ucdavis.edu/munshi-opencl.pdf | archive-date=2012-03-19 | dead-url=yes }}</ref>
<syntaxhighlight lang="c">
  // create a compute context with GPU device
  context = clCreateContextFromType(NULL, CL_DEVICE_TYPE_GPU, NULL, NULL, NULL);

  // create a command queue
  queue = clCreateCommandQueue(context, NULL, 0, NULL);

  // allocate the buffer memory objects
  memobjs[0] = clCreateBuffer(context, CL_MEM_READ_ONLY | CL_MEM_COPY_HOST_PTR, sizeof(float)*2*num_entries, srcA, NULL);
  memobjs[1] = clCreateBuffer(context, CL_MEM_READ_WRITE, sizeof(float)*2*num_entries, NULL, NULL);

  // create the compute program
  program = clCreateProgramWithSource(context, 1, &fft1D_1024_kernel_src, NULL, NULL);

  // build the compute program executable
  clBuildProgram(program, 0, NULL, NULL, NULL, NULL);

  // create the compute kernel
  kernel = clCreateKernel(program, "fft1D_1024", NULL);

  // set the args values
  clSetKernelArg(kernel, 0, sizeof(cl_mem),(void *)&memobjs[0]);
  clSetKernelArg(kernel, 1, sizeof(cl_mem),(void *)&memobjs[1]);
  clSetKernelArg(kernel, 2, sizeof(float)*(local_work_size[0]+1)*16, NULL);
  clSetKernelArg(kernel, 3, sizeof(float)*(local_work_size[0]+1)*16, NULL);

  // create N-D range object with work-item dimensions and execute kernel
  global_work_size[0] = num_entries;
  local_work_size[0] = 64;
  clEnqueueNDRangeKernel(queue, kernel, 1, NULL, global_work_size, local_work_size, 0, NULL, NULL);
</syntaxhighlight>

真正的運算：（基於Fitting FFT onto the G80 Architecture）<ref name=VolkovKazianFFTG80>{{cite web | url=http://www.cs.berkeley.edu/~kubitron/courses/cs258-S08/projects/reports/project6_report.pdf | title=Fitting FFT onto G80 Architecture | accessdate=2008-11-14 | publisher=Vasily Volkov and Brian Kazian, UC Berkeley CS258 project report | format=PDF | date=May 2008 | archive-date=2012-03-19 | archive-url=https://www.webcitation.org/66GmTA1HM?url=http://www.cs.berkeley.edu/~kubitron/courses/cs258-S08/projects/reports/project6_report.pdf | dead-url=no }}</ref>
<syntaxhighlight lang="c">
  // This kernel computes FFT of length 1024. The 1024 length FFT is decomposed into
  // calls to a radix 16 function, another radix 16 function and then a radix 4 function

  __kernel void fft1D_1024(__global float2 *in, __global float2 *out,
                          __local float *sMemx, __local float *sMemy){
    int tid = get_local_id(0);
    int blockIdx = get_group_id(0) * 1024 + tid;
    float2 data[16];

    // starting index of data to/from global memory
    in = in + blockIdx;  out = out + blockIdx;

    globalLoads(data, in, 64); // coalesced global reads
    fftRadix16Pass(data);      // in-place radix-16 pass
    twiddleFactorMul(data, tid, 1024, 0);

    // local shuffle using local memory
    localShuffle(data, sMemx, sMemy, tid, (((tid & 15)* 65) +(tid >> 4)));
    fftRadix16Pass(data);               // in-place radix-16 pass
    twiddleFactorMul(data, tid, 64, 4); // twiddle factor multiplication

    localShuffle(data, sMemx, sMemy, tid, (((tid >> 4)* 64) +(tid & 15)));

    // four radix-4 function calls
    fftRadix4Pass(data);      // radix-4 function number 1
    fftRadix4Pass(data + 4);  // radix-4 function number 2
    fftRadix4Pass(data + 8);  // radix-4 function number 3
    fftRadix4Pass(data + 12); // radix-4 function number 4

    // coalesced global writes
    globalStores(data, out, 64);
  }
</syntaxhighlight>
Apple的網站上可以發現傅立葉變換的例子<ref name=AppleOpenCLFFT>.
{{cite web | url=https://developer.apple.com/mac/library/samplecode/OpenCL_FFT/index.html | title=OpenCL on FFT | accessdate=2009-12-07 | publisher=Apple | date=16 Nov 2009 | archive-date=2009-11-30 | archive-url=https://web.archive.org/web/20091130085543/http://developer.apple.com/mac/library/samplecode/OpenCL_FFT/index.html | dead-url=no }}</ref>