https://github.com/cpplawyer/cudavector

Vector Datastructure for Nvidia Cuda Devices. Optimized all memory is allocated on Cuda Device for optimal use. Usable in device code maintainer of cudacpp Library
https://github.com/cpplawyer/cudavector

Last synced: 11 months ago
JSON representation

Vector Datastructure for Nvidia Cuda Devices. Optimized all memory is allocated on Cuda Device for optimal use. Usable in device code maintainer of cudacpp Library

• Host: GitHub
• URL: https://github.com/cpplawyer/cudavector
• Owner: cppLawyer
• License: gpl-3.0
• Created: 2022-06-06T10:48:50.000Z (over 3 years ago)
• Default Branch: main
• Last Pushed: 2022-06-12T21:52:42.000Z (over 3 years ago)
• Last Synced: 2025-01-14T01:10:38.139Z (about 1 year ago)
• Language: Cuda
• Homepage:
• Size: 21.5 KB
• Stars: 0
• Watchers: 1
• Forks: 1
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

          
# cudaVector

- Vector Datastructure for Nvidia Cuda Devices.

- Optimized all memory is allocated on Cuda Device for optimal use.

- Usable in device code

- maintainer of cudacpp Library

EXAMPLE:

```

#include "cuda_runtime.h"

#include "device_launch_parameters.h"

#include 

#include "cudaVector.cuh"

__global__ void do_something() {

    cudacpp::cudaVector var;

    var.push_back(1);

    var.push_back(2);

    var.push_back(3);

    var.push_back(4);

    var.push_back(5);

    var.erase(var.begin() + 3, var.end() - 1);

    printf("%i\n\n\n", var.size());

    for (uint_fast64_t i = 0; i < var.size(); ++i)

      printf("%i\n", var[i]);

    var.insert(var.begin(), 99);

    printf("%i\n", var.at(0));

    printf("%i\n", var.at(3));

}

int main()

{

    do_something << < 1, 1 >> > ();

    return 0;

}

```