-4

My question was, What makes brute force attack faster? Is it a bigger RAM, larger storage or a faster processor... because I saw a video of a man who put 7 GTX 1080's in parallel and it hacked a lot of passwords in less than a second using a dictionary.

closed as too broad by Steffen Ullrich, S.L. Barth, Tobi Nary, WhiteWinterWolf, Bacon Brad Aug 3 '17 at 16:24

Please edit the question to limit it to a specific problem with enough detail to identify an adequate answer. Avoid asking multiple distinct questions at once. See the How to Ask page for help clarifying this question. If this question can be reworded to fit the rules in the help center, please edit the question.

  • 3
    All of this, depending on what the current limitation is. – Steffen Ullrich Aug 3 '17 at 9:32
  • Will having a larger storage result in faster brute force attacks? Or a faster RAM will make the.... In short, what will make the computer try more hashes or keys/sec – Verschit Aug 3 '17 at 9:37
  • Again: all of this depending on what the current limitations are. RAM and CPU can help a lot if the process is bound on RAM or CPU speed (which it usually is). Adding more CPU will only help if the process scales to multiple CPU. GPU will help if the process makes use of it (many but not all do) etc. – Steffen Ullrich Aug 3 '17 at 9:40
  • 2
    What kind of brute force attack? – Jan Doggen Aug 3 '17 at 10:06
  • Basically, some hashing algorithm can be implemented faster against a GPU, because GPU has a different architecture of a classic CPU, to allow more parrellel computing when possible. Which is why they used one in your example, however is really depends of the algorithm, for instance, using GPU for BCrypt is meaningless. – Walfrat Aug 3 '17 at 10:40
2

It depends on the hashing algorithm which was used to hash the passwords.

  • There are algorithms which can be implemented well on GPUs or on specialized hardware (like FPGAs).
  • There are algorithms which mostly use operations which aren't very fast on GPUs so that they are bound by CPU speed.
  • There are algorithms which generate large amounts of data in their immediate stages, so if you want to parallelize them, you need a lot of RAM (system ram or video ram, depending on whether you use CPU or GPU).

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