• We’re currently investigating an issue related to the forum theme and styling that is impacting page layout and visual formatting. The problem has been identified, and we are actively working on a resolution. There is no impact to user data or functionality, this is strictly a front-end display issue. We’ll post an update once the fix has been deployed. Thanks for your patience while we get this sorted.

New ECCP client

Page 2 - Seeking answers? Join the AnandTech community: where nearly half-a-million members share solutions and discuss the latest tech.
kinda new to eccp so be nice
first off, there are optimized clients?! i didn't know that, running eccp on a T'bird so is there a certain client i should have? currently im running the one with a gui from the guys website at nd.edu

secondly, the zip in the fixed link only contains the eccp exe. do i just copy over my existing exe and leave everything else intact?
 
audiophan,

I would rename the ND executable so that if you need to go back, you don't have to redownload it. Then you can just copy the new client to your eccp109 directory and you should be all set.
 
I have a P4. The iteration reports that this new client is giving me have to be wrong. Have to be. I am getting 50,000,000,000 iterations REPORTED, with wild variations. Like I said, this has to be a bug. Anyone else got a P4 and getting real results?
 
is yer client a tad bit offscreeN? i had it running half off screen and the #'s were really high or zero.. try moving hte app around a bit
 
Oh, its now back into reliable numbers. I'm guessing the P4 on SDRAM (dont ask me why, I'm still pissed about having it shoved down my throat) sucks at ECCP as I'm getting around 300K now. Its better (before it was about 250K). Did I set it up wrong, or what?
 


<< i doubt it.. p4's really suck at eccp... >>



Thats what I figured. [sarcasm]But just you wait until the SSE2 optimized client comes out![/sarcasm]
 
MereMortal - "I compiled a Linux CL client based on the new asm code."
So MM, it seems as though I can simply grab the asm code and merge it into my modified Linux ECCp C code, were all changes kept within the asm code?
 
Man, this new client is great. Many, many thanks to the folks that produced it!!!

I'm getting around 150,000 more iterations/second than before on my PIII 1Ghz machine. Now its up to 520,000 its/sec approx.

Will try it on my athlon 1Ghz when i get home.

 
RC,

The only differences I could find (at least for the Linux client) between Ken's source and Chris's 130-3 source were:

asm (I used AT&T)
Makefile - to link in new asm files
eccp109/iteradd.c
include/eccp109_asm.h


There were also differences in Ken's eccp109/eccp109.c concerning the calculation of it/sec, but they didn't work for me, so I went back to Chris's way of doing it.


 
You must log in or register to reply here.

TRENDING THREADS

Back
Top