2
$\begingroup$

A Von Neumann Architecture bottleneck is a limit on the amount of data a computer can process due to limited bandwidth between the CPU and RAM. Possible mitigations to the problem according to Wikipedia are...

  • Providing a cache between the CPU and the main memory
  • Providing separate caches or separate access paths for data and instructions
  • Using branch predictor algorithms and logic
  • Providing a limited CPU stack or other on-chip scratchpad memory to reduce memory access
  • Implementing the CPU and the memory hierarchy as a system on chip, providing greater locality of reference and thus reducing latency and increasing throughput between processor registers and main memory.

I know that increasing the number of data lanes between the CPU and RAM would help, but would increasing the system memory speed also help?

$\endgroup$
3
  • $\begingroup$ limited bandwidth do you know further processing speed related properties of memory? $\endgroup$
    – greybeard
    Mar 14, 2021 at 9:28
  • 1
    $\begingroup$ In addition to "the other obvious measure" Shashank V M's answer equates with memory speed, it mentions memory size, which has an influence on applicable data structures&algorithms. $\endgroup$
    – greybeard
    Mar 14, 2021 at 21:28
  • $\begingroup$ Obviously increasing the speed would reduce the bottleneck. But it's already as fast as we can make it. Why would we make one slower than that??? $\endgroup$
    – user253751
    Aug 13, 2021 at 16:02

1 Answer 1

2
$\begingroup$

No, increasing the memory speed won't help solve the Von Neumann architecture bottleneck. The reason is as memory size is increased the time required to access the memory contents increases. So no matter how fast the memory is, if it is large it will be slower. So faster, smaller memories called caches are used to provide the illusion of a large, fast memory to the user.

$\endgroup$

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.