5 for – 2 against reasons about using CUDA Parallel Programming

5 For

  1. Affordable: Nvidia’s Graphic Cards can be combined to build a super computer. 
  2. Easier parallel coding: Since Nvidia inserts an abstraction level, parallel thread programming burden of the programmers is diminished.
  3. Forward code compatibility: Previously mentioned abstraction level also enables to source code to be used for future hardware versions without modification. But modifications will make code performance better.
  4. Extensible architecture: The designed model can be used for different levels of architecture, by adding or subtracting units of GPUs.
  5. C / C++ syntax

2 Against

  1. CUDA is strict to Nvidia solutions.
  2. CUDA is not mature yet.