Releases: tedliosu/cuda_mergesort_ytl
Releases · tedliosu/cuda_mergesort_ytl
Initial Windows CLI Program Release
This release includes two CUDA Windows executables:
main.exe
: Linear buffer version of the programmain_circ_buff.exe
: Circular buffer version of the program
You are encouraged to run both executables to compare their performance differences.
Requirements
- An NVIDIA GPU with a compute capability of 5.0 or greater.
- To check your GPU's compute capability, visit NVIDIA's CUDA GPUs page.
- Latest NVIDIA GPU drivers installed.
- CUDA Toolkit is NOT required to run these programs.
How to Run
- Open a PowerShell terminal.
- Navigate to the directory where you downloaded the executables.
- Run the desired program:
- For the linear buffer version:
.\main.exe
- For the circular buffer version:
.\main_circ_buff.exe
- For the linear buffer version:
- Follow the on-screen instructions once the program starts.
Note
On an RTX 3050 Laptop GPU with 4 GiB of VRAM, the maximum array size is approximately 190000000 before the input is rejected due to memory constraints.