Issue with amount of shared memory used in dense opencl correlator

[kif]

/nobackup/lid02gpu11/conda3/envs/dahu/lib/python3.7/site-packages/pyopencl/cache.py:501: UserWarning: PyOpenCL compiler caching failed with an exception:
[begin exception]
Traceback (most recent call last):
  File "/nobackup/lid02gpu11/conda3/envs/dahu/lib/python3.7/site-packages/pyopencl/cache.py", line 478, in create_built_program_from_source_cached
    include_path=include_path)
  File "/nobackup/lid02gpu11/conda3/envs/dahu/lib/python3.7/site-packages/pyopencl/cache.py", line 398, in _create_built_program_from_source_cached
    prg.build(options_bytes, [devices[i] for i in to_be_built_indices])
  File "/nobackup/lid02gpu11/conda3/envs/dahu/lib/python3.7/site-packages/pyopencl/__init__.py", line 714, in program_build
    raise err
pyopencl._cl.RuntimeError: clBuildProgram failed: <unknown error -9999> - clBuildProgram failed: <unknown error -9999>

Build on <pyopencl.Device 'Tesla K20m' on 'NVIDIA CUDA' at 0x55ecb43b4d70>:

ptxas error   : Entry function 'compute_sums_dense' uses too much shared data (0x14004 bytes, 0xc000 max)