mersenneforum.org  

Go Back   mersenneforum.org > Great Internet Mersenne Prime Search > PrimeNet > GPU to 72

Reply
 
Thread Tools
Old 2011-12-02, 16:41   #1
bcp19
 
bcp19's Avatar
 
Oct 2011

7×97 Posts
Default GPU TF vs DC/LL data

It seems obvious that there will be several factors involved when comparing GPU's; memory, clock, shaders, bus, etc. I broke it down to total exponents per day per GPU rather than say 1 @ 24 min + 1 @ 57 min, 2 @ 34 min, etc, for simplicity.

This is the rough capabilities of my 3:
Code:
Exp/day:
        GTS 450 GTX 560 GTX 560Ti
DC ^69  42      78      84
LL ^70  33      60      64
LL ^71  17      30      32
LL ^72  8.8     15      16
^69-72  4.9     8.5     9
Days/LL or DC:
        2500    2400    Q740    Core 2 Quad     GTS 450 GTX 560 GTX 560Ti
45M exp 0.033   0.030   0.059   0.054           0.029   0.014   0.013
Days    17.2    15.6    30.7    28.1            15.1    7.3     6.7
27M exp 0.017   0.016   0.035   0.031           0.0146  0.0071  0.0067
Days    5.3     5       10.9    9.7             4.5     2.2     2.1
CUDALuc ^68-69TF vs DC  ^69-70 vs LL    ^70-71 vs LL    ^71-72 vs LL    ^69-72 vs LL
560 Ti  ~176 to 1       ~429 to 1       ~214 to 1       ~107 to 1       ~60 to 1
560     ~172 to 1       ~438 to 1       ~219 to 1       ~110 to 1       ~62 to 1
450     ~189 to 1       ~498 to 1       ~257 to 1       ~133 to 1       ~74 to 1
The 450 has 512M memory as compared to 1GB in the 560/560Ti which is probably why it is less efficient at doing DC/LL when compared to TF. I also don't know how many factors per bit level are found, which is why I broke them down to 3 separate as well as including the 3 combined.
bcp19 is offline   Reply With Quote
Reply

Thread Tools


Similar Threads
Thread Thread Starter Forum Replies Last Post
NFS filtering in the era of big data jasonp Msieve 36 2018-05-07 19:55
Corrupted data? Oops! Information & Answers 2 2013-10-22 03:48
Data available? Prime95 LMH > 100M 10 2007-06-22 23:55
Conflicting data? ATH Data 4 2006-02-27 13:53
Have I submitted bad data? (Or, well, about to anyway) Nazo Software 5 2005-08-06 05:44

All times are UTC. The time now is 03:18.

Fri Jul 10 03:18:09 UTC 2020 up 107 days, 51 mins, 0 users, load averages: 2.00, 2.23, 2.17

Powered by vBulletin® Version 3.8.11
Copyright ©2000 - 2020, Jelsoft Enterprises Ltd.

This forum has received and complied with 0 (zero) government requests for information.

Permission is granted to copy, distribute and/or modify this document under the terms of the GNU Free Documentation License, Version 1.2 or any later version published by the Free Software Foundation.
A copy of the license is included in the FAQ.