CL_INVALID_KERNEL_NAME error after edit a function

I’m working to improve the perfomance of a 2D FFT on images . After a benchmark ; I regconize the transpose function is the reason make the program slow , so I replace it with a more optimized one .

But after that ; I received a return code of all the functions which work fine before

CL_INVALID_KERNEL_NAME

. Except the transpose function and

clSetKernelArg 

in the host code ; I don’t change anything else . So I’m out of idea. Hope you guys help me out :slight_smile:

Here is the kernel file

The transpose function before :

__kernel void transpose(__global float2 *dst, __global float2* src, int n)
{    
      unsigned int xgid = get_global_id(0);
      unsigned int ygid = get_global_id(1);

      unsigned int iid = ygid * n + xgid;
      unsigned int oid = xgid * n + ygid;

      dst[oid] = src[iid];
}

and the new one :

#define BLOCK_DIM 16

__kernel void   transpose(
             __global float2* dataout, 
             __global float2* datain, 
             int width, int height)

// width = N (signal length) 
// height = batch_size (number of signals in a batch)

{
// read the matrix tile into shared memory

__local float2 block[BLOCK_DIM * (BLOCK_DIM + 1)] 
   unsigned int xIndex = get_global_id(0);
   unsigned int yIndex = get_global_id(1);

    if((xIndex < width) && (yIndex < height))
    {
            unsigned int index_in = yIndex * width + xIndex;
                       int Idin = get_local_id(1)*(BLOCK_DIM+1)+get_local_id(0);
                       block[Idin]=  datain[index_in];
    }

barrier(CLK_LOCAL_MEM_FENCE);

// write the transposed matrix tile to global memory

             xIndex = get_group_id(1) * BLOCK_DIM + get_local_id(0);
             yIndex = get_group_id(0) * BLOCK_DIM + get_local_id(1);

    if((xIndex < height) && (yIndex < width))
    {
        unsigned int index_out = yIndex * height + xIndex;
        int Idout = get_local_id(0)*(BLOCK_DIM+1)+get_local_id(1);
                dataout[index_out] = block[Idout];
    }

}

Here is the log file . Seems normal with me . Is anthing wrong ?

expected a "]"
      __local float2 block[BLOCK_DIM * (BLOCK_DIM + 1)] ;
                           ^

     line 110: error:
              expected a ")"
      __local float2 block[BLOCK_DIM * (BLOCK_DIM + 1)] ;
                                        ^

     line 110: error: operand
              of "*" must be a pointer
      __local float2 block[BLOCK_DIM * (BLOCK_DIM + 1)] ;

error:
          expected a ";"
          int Idout = get_local_id(0)*(BLOCK_DIM+1)+get_local_id(1);
                                                  ^

Seems linke he does not like your define. do you get any errors when compiling your code? hace you tried buildoption -Werror to make shure there are no warnings? Looks fine for me, but i downt know if threre is something worng in the define. I dont need them at the moment.

Greetings
clint3112

You could also check the Binary. The defined value should be in there i think