View Single Post
Old 2021-09-25, 20:38   #6
kriesel
 
kriesel's Avatar
 
"TF79LL86GIMPS96gpu17"
Mar 2017
US midwest

10111001011002 Posts
Default

Good.
One thing in favor of V7.x P-1 is superior error detection.
1) It saves powers of 3 produced during PRP/GEC, for use in generating the P-1 stage 1 power of 3. Generation of those individual powers if it errors will get flagged by a GEC.
2) It uses Jacobi check on the P-1 computations.

An extremely long P-1 run might be better on V7.2-53 for that error detection despite a small speed disadvantage.

https://mersenneforum.org/showpost.p...30&postcount=2
https://mersenneforum.org/showpost.p...2&postcount=82
Jacobi check on P-1 is something I had identified as possible by early 2019, and R. Gerbicz reviewed. It's not as productive as for LL, since unlike for the LL sequence, it's not known which value is correct, that must be computed.

Last fiddled with by kriesel on 2021-09-25 at 20:40
kriesel is online now   Reply With Quote