Message boards :
Number crunching :
Countermeasures for Increased CPU Time
Posted 23 May 2019 by Ken_g6
The reason for this is that each task requires all of the prime numbers in an ever-growing range to be calculated, and this calculation can only be performed by the CPU.
This is interesting. I looked into a prime sieve on GPU once, but never got anywhere. However, I have seen at least one implementation of a prime sieve on a GPU: mfaktc by Oliver Weihe. This is the CUDA version: https://mersenneforum.org/showthread.php?t=12827 There's also an OpenCL version, mfakto, but I'm not 100% sure it has the GPU sieve: https://mersenneforum.org/showthread.php?t=15646
Edit: I should point out that these programs do not work on Amicable Numbers. But they could be useful to the developers.
©2024 Sergei Chernykh