https://github.com/evstigneevnm/gpu_container

https://github.com/evstigneevnm/gpu_container

Last synced: 25 days ago
JSON representation

• Host: GitHub
• URL: https://github.com/evstigneevnm/gpu_container
• Owner: evstigneevnm
• License: gpl-3.0
• Created: 2021-08-03T07:02:04.000Z (over 3 years ago)
• Default Branch: main
• Last Pushed: 2022-05-08T13:55:26.000Z (almost 3 years ago)
• Last Synced: 2024-11-15T15:45:31.078Z (3 months ago)
• Language: C++
• Size: 27.3 KB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# gpu_container

A simple class that implements an adaptive container for a GPU storage using CUDA.

Can be used analogous to the std::vector, contains the following methods:

- init(size of a single data type)

- push_back(type val_)

- shrink_to_fit()

- get_size()

- capacity()

- type data()  <- access to internal part of the container.

                  

Constructor takes two optional parameters:

- container(int muliplyer_ = 2, int init_steps_ = 100)

muliplyer_ - adjusts the internal storage if the data doesnot fit for the next push_back()

init_steps_ - amount of data that is initially reserved in the internal storage.             

# index_table

Added quasi-dynamically adjustable indexing table for GPU, see dynamic_index_table_gpu.h and test_dynamic_table_gpu.cu