Is it possible to solve CUDA memory fragmentation issue?

Question

I'm trying to allocate some memory but sometimes get error "out of memory". cudaMemGetInfo says that available more memory that I need. So, problem in memory fragmentation. Is it possible to fix this problem? Is it possible to place elements in memory not one by one and fragment to few peaces that I can place in memory?

Ealdorman

Answer 1

If you get "out of memory" because of memory fragmentation, then there is some error in the way that you work with memory!! You are responsible for fragmenting that memory, consider a redesign of your program and for example use a pool of memory to avoid too much new/delete to avoid fragmenting memory

Lacrimatory

Is exist library that implements memory pool to CUDA? – Ealdorman

Sorry for late answer, take a look at libhoard. I don't remember the site but googling libhoard will help you. – Lacrimatory

I found this library but I found nothing about using it for CUDA device memory allocation. – Ealdorman