dynamic-parallelism

I am trying to use dynamic parallelism to improve an algorithm I have in CUDA. In my original CUDA solution, every thread computes a number that is common for each block. What I want to do is to first launch a coarse (or low resolution) kernel, where threads compute the common value just once (like if every thread represents one block). Then each thread creates a small grid of 1 block (16x16 threads), and launches a child kernel for it passing the common value. In theory it should be faster because one is saving many redundant operations. But in practice, the solution works very slow, I don't

I'm trying to compile a dynamic parallelism example on CUDA and when i try to compile it gives and error saying, kernel launch from __device__ or __global__ functions requires separate compilation modes Later found that I have to set the --relocatable-device-code flag to true . But, is there a flag to set in order to make the set relocatable-device-code to true in Nsight Eclipse? If you are not using makefile project, you could change the options passed to nvcc of a Nsight project at the following position, starting from the menu. Project - Properties - Build - Settings - Tool Settings - NVCC