PR with opt params

  if(CUDA_FIRST_TARGET GREATER_EQUAL 120)
    set(CUDA_TARGET BLACKWELL)
  elseif(CUDA_FIRST_TARGET GREATER_EQUAL 90)
    set(CUDA_TARGET HOPPER)
  elseif(CUDA_FIRST_TARGET GREATER_EQUAL 89)
    set(CUDA_TARGET ADA)
  elseif(CUDA_FIRST_TARGET GREATER_EQUAL 80) # was 86 before
    set(CUDA_TARGET AMPERE)
  elseif(CUDA_FIRST_TARGET GREATER_EQUAL 75)
    set(CUDA_TARGET TURING)
  elseif(CUDA_FIRST_TARGET GREATER_EQUAL 60)
    set(CUDA_TARGET PASCAL)
  elseif(CUDA_FIRST_TARGET GREATER_EQUAL 30)
    set(CUDA_TARGET KEPLER)
  elseif(CUDA_FIRST_TARGET GREATER_EQUAL 20)
    set(CUDA_TARGET FERMI)
  else()
    set(CUDA_TARGET TESLA)
  endif()

Best parameters comparison - Nvidia

Kernels in single stream steps

Kernels in multi stream steps

Next steps