Hi, I’m building up a Monte Carlo code in CUDA that, as intermediate steps, needs to perform sums of several thousand Floats. The fact is that the numbers are produced by a function V(r,dip) where r is vector of floats and dip is a parameter. The details of the function are irrelevant as I just wor…

Sum is very slow (and I can't figure out why)

Ferran_Mazzanti January 3, 2021, 7:58pm 3

Thanks, that makes sense…
…but then my measured times are about the same as what I get on CPU and no CUDA (more or less 7ms), and I thought that would be much faster

Topic		Replies	Views
What is the optimal way of updating CuArray? GPU cudanative	7	1542	July 5, 2018
Timing square function in CUDA GPU	4	1705	December 11, 2018
Performance regression with GPUArrays subset sum GPU	9	745	December 9, 2020
Help Debugging GPU Performance Issue GPU gpu , debug , cuarrays	5	939	July 1, 2020
Compare julia sum to a cpp implementation - julia is extremely slow?! Performance question	35	1882	October 7, 2019

Sum is very slow (and I can't figure out why)

Related topics