I am working on genetic programming , where I need to pick a function from a set of functions fs by an integer index in each node of the tree. An example demonstrating the difficulty I encountered is given below. using CUDA # a kernel function pass_func_array(x::Float32, fs) for f in fs …

[image] Shuhua: Is there any workaround to do what I want in CUDA.jl for now? You could create a trampoline function, but generally no this pattern is not supported.

CUDA kernel: how to pass an array of functions

Specific Domains GPU

maleadt February 8, 2021, 2:54pm 7

You could create a trampoline function, but generally no this pattern is not supported.

Topic		Replies	Views
Use GPU subfunction in a bigger-function? New to Julia cudanative , cuarrays	5	785	April 19, 2020
Sparse arrays and function arrays in CUDAnative.jl GPU cudanative	12	1772	July 10, 2017
Presentation on effective use of CUDAnative/CuArrays GPU	7	2410	January 3, 2019
Passing a wrapped array to a kernel GPU	2	557	May 27, 2020
Mapping functions using CuArrays GPU cuarrays	2	1942	September 9, 2020

CUDA kernel: how to pass an array of functions

Related topics