Calling EnqueuTask multiple times is not working.

I am running one program on my server with 32GB RAM. We have requirement to do matrix multiplication of 64x64x256 image with filter of the same size (64x64x256). Problem is that we have 2614600 such filter and image and filter pixel values are in float.

// Command queue
fc_queue = clCreateCommandQueue(context, device, CL_QUEUE_PROFILING_ENABLE, &status); 
checkError(status, "Failed to create command queue");
FC_input_buf = clCreateBuffer(context, CL_MEM_READ_ONLY, 64x64x256 * sizeof(float), NULL, &status); 
checkError(status, "Failed to create buffer for input image");
FC_output_buf = clCreateBuffer(context, CL_MEM_READ_ONLY, 1024 * sizeof(float), NULL, &status); 
checkError(status, "Failed to create buffer for input image");
status = clEnqueueWriteBuffer(fc_queue, FC_input_buf, CL_TRUE, 0, 64x64x256 * sizeof(float), input_image, 0, NULL, NULL); 
checkError(status, "Failed to transfer input.");
for(unsigned int ff=0; ff< 2614600; ff++){ //// Number of filters ////   // Buffer
   FC_weight_buf = clCreateBuffer(context, CL_MEM_READ_ONLY, 64x64x256 * sizeof(float), NULL, &status); 
   checkError(status, "Failed to create buffer for FC_weights");
   // NOTE we have taken FC_weights common for each iteration in this pseudo code. In original, it will be some offset of fc_weights based on iteration number. But size with the same for each iteration.
   status = clEnqueueWriteBuffer(fc_queue, FC_weight_buf, CL_TRUE, 0, 64x64x256*sizeof(float), FC_weights, 0, NULL, NULL); 
   checkError(status, "Failed to transfer weights");
   unsigned argi = 0;
   status = clSetKernelArg(fc_kernal, argi++, sizeof(cl_mem), &FC_input_buf); checkError(status, "Failed to set argument %d", argi - 1);
   status = clSetKernelArg(fc_kernal, argi++, sizeof(cl_mem), &FC_weight_buf); checkError(status, "Failed to set argument %d", argi - 1);
   status = clSetKernelArg(fc_kernal, argi++, sizeof(cl_mem), &FC_output_buf); checkError(status, "Failed to set argument %d", argi - 1);
        
   cl_event kernel_event = NULL;
   status = clEnqueueTask(fc_queue, fc_kernal, 0, NULL, &kernel_event);  checkError(status, "Failed to launch kernel");
   // NOTE we have to wait until this kernel finish its execution. We can also use NDRange kernal here. I am getting the same problem in NDrange kernal also.
   clWaitForEvents(1, &kernel_event);
   clReleaseMemObject(FC_weight_buf);
   FC_weight_buf = NULL;
}
clReleaseMemObject(FC_input_buf);
clReleaseMemObject(FC_output_buf);
clReleaseCommandQueue(fc_queue);