Thanks for the info Steve,
I guess I have to look for someone in Norway that builds such things.
(there would be huge shipping costs and probably issues with the customs as well)
Looking forward to your results :)
Printable View
Thanks for the info Steve,
I guess I have to look for someone in Norway that builds such things.
(there would be huge shipping costs and probably issues with the customs as well)
Looking forward to your results :)
:up: Time to see some 5GHz+ stable runs.Quote:
Originally Posted by SteveRo
Once you have your cascade - what - 5.5-6 linx stable on 32nm?Quote:
Originally Posted by lowfat
SteveRo and Mike, i'm a bit curious here, what is your PCmark Vantage HDD score? And could you post SS of the HDD sub-test?
Also, Mike, what storage setup are you using now?
I am hoping I can run F@H @ 5GHz 24/7. But this is w/ a i7 920. Since VMWare only supports 8 threads there is no use for me to buy a 980x.Quote:
Originally Posted by SteveRo
this is nuts!Quote:
I am hoping I can run F@H @ 5GHz 24/7.
do u think it would manage to last even a year..?
I think so. I have a damn good chip. It ran @ 4.8GHz w/ only 1.3375V (24/7 full load of course). This was with a very poor single stage.Quote:
Originally Posted by onex
I think I should be able to do 5GHz and still keep it under 1.45V.
nice challenge going on there fellas :up:
Good morning,Quote:
Originally Posted by GullLars
Mike posted a score here, not sure if this is his fastest though.
Huge HDD score - 138077 - http://service.futuremark.com/compare?pcmv=302906
My best - trying to beat lowfat's ioxtreme and losing - 74868 - http://service.futuremark.com/compare?pcmv=285729
All the subtest scores for both are available at the above locations.
But Mike is not saying what storage he is using :D Classic :)Quote:
Originally Posted by SteveRo
You are still above him in my books. 138k is very obviously non legit/cached/whatever (non sustainable), especially considering it can not be ran on dynamic raid.Quote:
Originally Posted by SteveRo
The 1GB++/s bandwidth (if legit) means the only possibility is an LSI card and none of them are capable of that score.
pure conjecture here - but what about a bootable texas systems or intel pcie direct connect prototype or an areca 1880 4GB preproduction. Mike - can you say?Quote:
Originally Posted by One_Hertz
Hmmm... I've seen 74.000 in HDD score from 3R0 x25-V off ICH10R with 16KB stripe...
In our Norwegian SSD benchmark thread, we have the following PCmark Vantage HDD score listings above 100K points:
Anvil with 120.596 from 4R0 X25-M G1 off ICH10R.
Anvil with 120.374, 3R0 X25-M G1 off ICH10R.
Nizzen with 112.441 from 7R0 OCZ Vertex off Areca 1680ix.
Ourasi with 110.935 from 2R0 x25-E off ICH10R.
Anvil with 104.231 from 2R0 X25-M G2 160GB off ICH10R.
Perhaps 3-4 x25-E off ICH10R could give 130K+?
We should hope Areca makes their 18xx series with a more powerfull controller than LSI put in their 92xx series, since LSI 92xx can "only" do 80-90K IOPS on integrated RAID-0.
yes but were those results on bootable arrays? or with each device configured as individual arrays via ich10r? those scores look very much like ddr3 cache numbers....
Bootable arrays as in standard RAID-0 using the ICH in my case, but not running as boot drives.
yes so they wouldnt be able to run a real vantage benchmark then if they were configured as smaller arrays that were non-boot.
Anvil, the question is, what stripe size did you use for those arrays, and was WriteBack cache on?
Also, have you tried putting 8 (or all your) Intel SSDs (80/160GB) on your LSI 9260 and running PCmark vantage on that? Could be interresting, now that you can get 80-90K IOPS after new firmware.
Now, that is a good question, it's all hidden in the Norwegian thread :)
I haven't tried running Vantage on anything but ICH, I might give it a try though.
I'm a bit p****d at OCZ at the moment, they've announced that the Vertex 2 Pro wil be released shortly.
(so much for their words on the LE being exclusive)
gullars the 8R0 vertex on 9260 is tenth place vantage,
and 8R0 c300 is fourth (mbreslin)
would be interesting to see 8R0 intels!
the remarks i was making involving ddr3 cache refers to a trick used around pcm05 quite a bit to leverage the amount of system ram (ddr3) that is given to arrays on the ICH10r. it will produce uber results akin to those mentioned. it is just a matter of getting more assigned to a particular arrray. but that should not be able to be ran on a full vantage run, which is why you wont see the HDD test numbers equate to performance in the real benchmark. with numbers like those above^^^those guys should all be in the pcmark hall of fame. easily.
i have bigger results with 8R0 9211 than SteveRo. im using 0Mb of cache and SteveRo use 4Gigs and im still faster than him... Im using 8 cores instead of 6 but im slower..
The thing with pcmark Vantage is how do u setup ur pc. Using a 5Ghz cpu may not be faster than a 4.2-4.4Ghz .. Pc's are like cars maybe Mike has found his golden peak point that works for him. And yeah each pc handles different so maybe this is way his not speaking about his setup. In past records SteveRo used 12R0 acards but mike used only 3 ... Everyone here has a record but those records are not with more than 5 disk.. have u ever thought that? A pc is a pc there is nomatter how fast it can go.. the operator makes the laps not the autopilot!
+1 to mikes record not for being no1 but for show me that records doesnt match with bugets ;)
Yes, Tilt, concur with all you said - the 1231 cache makes up for it's other shortcomings (not being pcie 2.0, limited throughput, ...)
The PCM vantage gods seem to like areca controllers and it seems to be more than the controller cache.
its not about ARECA's or LSI's.. Even with that where is the C300 performance?Quote:
Originally Posted by SteveRo
Why do i kill C300 for fun even without cache..????? i score more with my drives than with c300's?? Anvil scored more even with 4.... You r looking in the wrong place to get back to top1 the 1rst place is not where the PCIE v2 or v3 is....
But how the pc works..how it responce... how to setit up currectly.
It doesnt matter what ur driving but it matters how u r driving it ;)
Now according to ur post PCIE has nothing to do with PCmarkV
and how do i know that??? just look the ICHxR performance... Limited to 750M/s top.. now with the areca even u r using 1 drive even 12 u will get the same results.. ALL READ IN CACHE :clap: :clap:
DDR3 cache ramdrive numbers are 250k+ I know because I tested :)Quote:
Originally Posted by Computurd
yes, ramdrive numbers are. but that is not the way it is being used , but i am sure you are aware of that. it is NOT being used as a ramdrive.
Anvil maybe you could give some quick breakdown of any settings/tweaks you do in w7 to get the most out of your array? tilt now and then spits out a tweak or 2 but I don't have the time to check a million things 1 by 1. (yes I know settings for intels won't necessarily work great for my c300s but it will show me I'm on the right track)Quote:
Originally Posted by Anvil
Mike giving a rundown of his would be amazing clearly he knows how to tweak!
Either of you not wanting to share your secrets is understandable too :) Just thought I would ask.