What are the advantages of using FPGAs over GPGPUs? It seems like GPGPUs have the best of CPUs and GPUs combined.

  • 2
    $\begingroup$ Have you seen cuda vs fpga? Besides, I do not think that question is strictly on-topic here. There are tags, like computer-architecture, but question is more about usage. $\endgroup$ – Evil Mar 12 '18 at 0:21
  • $\begingroup$ Not sure how this is a computer science question. $\endgroup$ – Raphael Mar 15 '18 at 13:46
  • 1
    $\begingroup$ why is it not? @Raphael computer architecture and therefore components is part of computer science $\endgroup$ – Trajan Mar 15 '18 at 14:33
  • $\begingroup$ The principles of computer architecture are ontopic. The technical differences of real-world chips not so much. $\endgroup$ – Raphael Mar 15 '18 at 15:03

There are specific applications for which GPUs are useful. For example, they are useful when we want to perform same operation(use same instructions) but for many different data elements in parallel. For example, add 1K elements in parallel. Such workloads are said to have Data Parallelism.

This is not the case with FPGAs. They are highly customisable and can be made to do anything you want and not just highly data parallel operations. Hence, FPGAs offers much more freedom for designers than GPUs.

| cite | improve this answer | |

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.