IMO and from my personal experience, inconsistent and low GFLOPS are a sigh of instability. When I got my rig 99.999% stable (OC'ed rig just can't be 100% stable) I never had lower then 53 GFLOPS.
Printable View
IMO and from my personal experience, inconsistent and low GFLOPS are a sigh of instability. When I got my rig 99.999% stable (OC'ed rig just can't be 100% stable) I never had lower then 53 GFLOPS.
I have a problem with LinX in that when I overclock and it fails because of bad overclock it will not run again after I stop it, all that happens is that it shows it is running but there is no CPU usage or very little no where near 20%
The only way I can make it work again is to uninstall it then reinstall it, then it works again until it fails an overclock then I have to uninstall agian.
Any Idea's please?
I might have found the problem, I tried to download the file again and everytime I do when I try to open it Win Zip says it's corrupted.
it occurs at stock/non-OC settings also. So I don't think that's it.Quote:
Originally Posted by donmarkoni
If I know my ram is stable at certain speed should I still use a large problem size? ie, do larger problem sizes stress the CPU more?
Also I've noticed people recommend using 16 threads for i7's? What's the deal with that? Extra stress?
GFlop results have been pretty consistent with my testing so far. Increasing in a fashion one would expect as I have overclocked from stock to 4.0ghz. However I should try disabling HT. It appears our i5 brothers get more Gflops clock for clock.
Dua|ist, thanks for Linx. It is a great software.
I wonder, if you would please consider painting errored lines' background a different color in the grid. It is very difficult to detect if there are errors and how many of them. Also I think it will be cool, if you could add number of errors to status bar.
Linx is just a GUI for Linpack. You'd have to ask Intel to put error numbers in Linpack it's self.Quote:
Originally Posted by aziz
Thanks for your response and I am sorry not being clear.Quote:
Originally Posted by safan80
Linx has algorithm to detect if Linpack returns an error. It can stop on Linpack error.
I use 0.5.2, run for 8 hours without stopping on error. It's status color change from green to orange if it detects an error. When I check Linpack results, I can count errors.
Please take a look at this. Second row shows an error. I can tell because last two columns are different from the other rows' columns. It would be nice if that row is colored and counted :)
16331 16336 4 115.611 25.1205 2.521529e-010 3.350270e-002
16331 16336 4 117.778 24.6582 1.657744e+000 2.202588e+008
16331 16336 4 116.038 25.0281 2.521529e-010 3.350270e-002
16331 16336 4 116.867 24.8505 2.521529e-010 3.350270e-002
16331 16336 4 116.363 24.9582 2.521529e-010 3.350270e-002
16331 16336 4 117.197 24.7805 2.521529e-010 3.350270e-002
16331 16336 4 118.304 24.5486 2.521529e-010 3.350270e-002
16331 16336 4 116.610 24.9052 2.521529e-010 3.350270e-002
16331 16336 4 116.180 24.9975 2.521529e-010 3.350270e-002
16331 16336 4 117.611 24.6933 2.521529e-010 3.350270e-002
16331 16336 4 115.699 25.1013 2.521529e-010 3.350270e-002
I had the same problem. It was simply the CPU TM function in the bios that I had to disable.Quote:
Originally Posted by phsinc1
It's not the usual throttling/energy settings but the one which only works if the processor is at frequency >=3.6GHz and bus >=800MHz in the bios comments.
That was the first time that TM function was really triggered on a system for me (i7 920): LinX is the devil ;)
the latest version is 6.4 please update to that and retest. dl link is in the first post.Quote:
Originally Posted by aziz
Hello!Quote:
Originally Posted by LostHawk
LostHawk, what's the abbreviation to TM please?
Thanks in advance!
//subscribed.
"CPU TM Function" is the official name from Intel in most Bios.Quote:
Originally Posted by AlderaaN
It's CPU Thermal Monitor Function (TM or TM2).
You can usually find this option in the same section than Intel Virtualization/Vanderpool Tech, Execute Disable Bit, ...
Cool!Quote:
Originally Posted by LostHawk
Thanks again, LostHawk!
I've tried using LinX 0.6.4. The first time I run it after installation it works without problem.
If I close it and then open it again, it doesn't do anything. I click "start", and the "Elapsed" counter starts counting, but the CPU remains idle and the program is not using any RAM. This happens whatever amount of RAM I tell it to use.
My CPU is core i7-860.
Any idea what is the problem?
Thanks.
I try to run LinX on my new setup. I have 6gb Ram with no swap file. If i choose max mem, around 4950mb, i get an error not enough memory or something. So i have to manually choose the 4096mb setting. Is this normal? How can i run with max mem?
You have to enable your swap file again, otherwise you're going to have the problems you described. The system has a full memory usage so when there is a lack of memory the swap file is like a memory on the disk and it serves the needs of the os in order to work properly. If you don't want to enable the swap file then use less memory, but I suggest you enable swap file again for the testing purposes and then disable it again, is what I did in order to use the max memory on my system when I used Linx.
Thanks for the reply xpatar, thats what i had in mind. Anyway atm i run my tests with 4900mb with no problem.
Makedonia apo pou eise akribws? Egw menw perea/thessaloniki.
File mou, ehoume xanamilisi sto parelthon, apo Katerini ime, almost 20 meters:yepp:
Nai swsta twra pou to les exoume xanamilisei :) Swsta ti eine h katerinh, 20 min :)
nai re paidia alla me to linx ti paizei stamathse sta 13 tests enw to eixa valei na treksei 20 k mou elege test complited no errors eleos....allo na sou pei error k allo auto:rofl:
You should report that to Dua|ist, maybe a bug of the program.
I thought this was an English thread... press 2 for espanol.. press 3 for pig latin... press 4 for ...
Indeed guys. Have nothing against native languages at all, but it'd be great to see the English variant of the phrase somewhere as well. :)
UNSTABLE_HERO reported that even though he had chosen 20 runs from Linx, it stopped at the 13nth run reporting that the program finished without any errors.Quote:
Originally Posted by Dua|ist
Can we consider it as a bug of the program or some setting fix.
Press 4 for ...Greek, it was Greek:rofl:
as xpatar says...13 of 20 test complited an finished no errors:cool:i have the feeling that sometimes linx reports false errors especialy when running it and trying to open any program like hwmonitor or media player...i used linpack from occt for 3 hours then occt(cpu / small fft) for 3 hours and sometimes linx give me errors in an minute or runs fine for hours with the same settings of course!i have an i7 system if that helps :)
Did you consider that it stresses your system more then any other program, so it fails for that reason? ;)
it stresses a lot but i dont find it so normal crashing after 2 minutes and when i give a second run with everything unchanged it finishes test with no errors after 4 hours,of course an error is random and can happen!so if u pass 4 hours linx u run it again because you are not sure....!or maybe finishing at 13 of 20 tests and reports that test finished with no errors is an error?yesterday i uzipped it again because the prog was getting crazy and didnt stress the cpu correct!5000mb 20 runs and i had only 59c...while with occt and prime cpu hits 70s!now after deleting the old file and unzipped it again everything is ok i hit 74c:up:
Did you try running the program from drive C:\ ? Does this make any difference?
i keep getting the "not enough memory" error. What does that mean?
I started using LinX to test my system (Q9550@3.6). The starnge thing I noticed is that while using version 0.63 the Gflops were consistant around 50 and the temps reported during the test were around 65c, with version 0.64 my Gglops are very inconsistent and stay around 30-35 and the temps are 10C lower around 55c.
Nothing has changed on the system, in fact I can run 5 cycles with 0.63 and get max temps and Gflops, then run 5 cycles with 0.64 and get 34Gflops and 10c lower temps.
Has anything changed in the latest version that could cause this discrepancy?
Either you're not using the swap file or you're asking for too much! ;)Quote:
Originally Posted by McLaren__F1
Switching back, thanks for the heads up.Quote:
Originally Posted by MaxOC
Can anybody else confirm the issue with version 0.6.4?
I have had this same thing happen, but it is not blue at the top where is says you finished without error, it is in red, and windows reports the program has stopped responding, which is normally a sign you aren't using enough vcore.Quote:
Originally Posted by xpatar
I use LinX as a starting point for testing stability to give an idea if it is close. Sometimes it will pass, then fail with same settings a day later, I think is has to due with the conditions when you were testing, such as ambient temps, or other programs being open possibly. Prime blend will do the same thing, can pass it several times at the same settings then fail at random. None of these programs are 100% consistent IMO.
It simply means that your overclock was on the edge of stability. Drop ~200Mhz (and for the sake of stability decrease other values as well such as RAM mhz, possibly bclk etc.) and you will pass all your tests many times any day :)
so i'm curious, does this work on amd rigs.. and if it does, is 10 passes or 5 passes enough to test just general stability in the quest to find a max oc?? i'm a bit nubish on the oc'ing, currently got my p2 965 c3 at 4.1Ghz 1.55v and it passes 10 passes and i'm wondering if i need to run more, and what settings should i use?
here are the system specs
asus m4a79t deluxe
2x2gb ddr3 1600 cl9 g.skill 1.5v
phenom 2 965c3 4.1Ghz 20.5x200 1.55v
4xg.skill 64gig ssd in raid 0 + 1 wd 1 tb storage drive.
bfg es 800 psu
You need at least 20, max memory.
thanx for the reply, i'm getting a bluescreen crash about 5 tests in, in orthos linpack and p95-24 hour run small fft and blend on two different occasions i get no errors, but linx fails almost 4 minutes in, is this the settings or is this my computer, i always though 24 hour run of p95 or a orthos linpack was enough, this just bluescreens me?
What are your temperature in p95 small fft and linpack? If the temps are at the limit with p95, linpack will push them over the edge and cause instability.Quote:
Originally Posted by exodusprime1337
it was blue to me:yepp: btw i think occts linpack is more reliable and i have same max cpu temps as with linx!i7 @ 74c(22 room) with both progs under load!Quote:
Originally Posted by OC Nub
from changelog:
LinX 0.6.4
- added an option to run tests for a specified period of time. Use the drop-down list to set minutes or times to run tests
- small UI redesign/enhancements
- graph windows now correctly save their positions on program close
- fixed a somewhat rare bug leading to false LinX errors when CPU usage was high----------( i think )----------------------------------->(MAYBE NOT FIXED 100%)
- added new command-line options, fixed found bugs in older ones (run LinX.exe -help to view the list of command-line options)
- added seconds to filenames to prevent overwriting
i barly edge over 44 in linpack, and linx is no higher, maybe a bit lower, the room is at 65f/18c or so but it doesn't go high, in fact i don't think i'v ever hit 50 on this chip... Problem is, that doesn't equatte to anything more than 4.0Ghz, can't get anywhere near 4.1, was hoping to but it isn't happening.Quote:
Originally Posted by MaxOC
Wow! nice temps. Sometimes OC hits a wall regardless of the temperatures, anyway, 4.0ghz is still not bad ;)Quote:
Originally Posted by exodusprime1337
I have the same issue on occasions too. I'll start up, run the test, and when I normally hit the 70's, it goes down to low 60's. Gflops also drop from 61 down to anywhere between 35 and 55 when it doesn't run properly. Task manager shows nothing else using the CPU and this is on a fresh w7 64-bit install. C1E and EIST are also off.Quote:
Originally Posted by MaxOC
So would anyone agree that 0.6.3 is likely to be better for now? (in our cases)
Dang, times have changed. Prime95 is officially out for me, and LinX is in. Stable in Prime for 30 minutes. LinX gives 5C higher temps than small FFTs, and it BSOD the system after only 1 minute.
Спасибо за интерфейс.
linx doesn't appear to be working for me. i downloaded the latest version. fired it up, and... nothing. it doesn't ever seem to initiate the tests. realtemp is reporting no load on my cpu. temps aren't going up. there's no output. what gives?
itb works fine, btw.
Don't throw prime just yet...Quote:
Originally Posted by IvanAndreevich
Testing with large FFTs will reveal QPI volt problems. However small FFTs are inadequate for I7's. A Linpack based program is better.
Nice, a consistently 12h prime blend stable setting wouldn't complete a 20 pass test, failing always near middle after 5 tries. A small NB bump solved it, testing exact amount of memory for multiple passes.
On the other hand, a setting that will pass whatever linpack I throw at it or prime, once failed me under Linx at a time I was stress testing my PC and closed Winamp and Firefox. It seems like closing both programs triggered it's failure. I report same temps for OCCT, linx and interburntest's linpack.
Thank you guys for all your input. It is appreciated.
I feel sorry for all those bugs and inconsistencies. In fact, I'm still surprised there's so many of you out there using this tool.
The thing is, communicating with a foreign process, and especially such a specific one as Linpack (which sometimes acts weird by itself, but in no way I mean here to accuse it of my own glitches), is tough. The sensitiveness to specific system configurations doesn't aid in solving the issues too.
Having said that, I can only suggest those having issues to try some previous versions (that's actually why they're listed, solving one issue without introducing another one is still a feat I have to learn ;) ) if you still want to give LinX a go. And I think it's time for me to stop adding features and focus on solving errors.
You're welcome. I was always curious whether someone with such nickname as yours could know Russian. Figure, my assumptions were correct. :)Quote:
Originally Posted by IvanAndreevich
New this week my first ever Intel platform and love it so far . JoeBar brought this to my attention and OC Nub threw up the down load . My clocks were 6 hours p95 stable but I gave this a try and like it a lot . Thanks again JoeBar & OC-Nub . :up: http://i470.photobucket.com/albums/rr63/pcnazz/save.jpghttp://i470.photobucket.com/albums/r...zz/4630Mhz.jpg Turbo Enable 24/7 , purchased 2000 GT CL8 Dominators today !
For me is the other way around. I was stable for 25 loops (max gflops) but Prime 95 would fail within 3 to 5 hours every time.Quote:
Originally Posted by IvanAndreevich
I think Linpack is good to test quickly for major stability issues, but for fine tuning long term stability, Prime95 is still the way to go.
pcnazz
Very nice rig and clock :up:
Im trying to use all the available memory with Linx but i only have aroung 1Gb free ! :shrug: And i installed 6Gb...
http://i770.photobucket.com/albums/x...nreal/1-13.png
http://i770.photobucket.com/albums/x...nreal/2-14.png
Try increasing VTT.
Or it could be that one of your sticks is dead or perhaps DIMM slots is dead. :(
I have the same exact problem ! I don;t know what's wrong, Memtest gave me no errors, VTT is already increased, dunno what to do next :shrug:Quote:
Originally Posted by Unrealer
check for bent pins or the cooler could be making much force on the mobo socket backplate or the memory slots are badQuote:
Originally Posted by Salamndar
I made a Clear CMOS and it solved the issue, I'm reoverclocking now, increasing Bclk in a much smaller amount and so far so good !Quote:
Originally Posted by phsinc1
Try removing the CPU, checking all pins are good, clean the pads on the CPU with isopropyl alcohol and remount it. If you have good contact, could be a Vtt / vdimm issue.
I also fixed the problem, i loaded the default values @ bios, reoverclock, and now i get around 5Gb free :clap::shrug:Quote:
Originally Posted by Salamndar
Love this program especially the sound when it doesnt pass test :) and also that it does not boot you off windows it will warn you and stop loading...memtest 1.4 pass 5hrs and i was geting blue screens in windows but this program let me know that my timing were too low in only 4minutes ::) no more lue screens
I think in my experience with prime 95 and linx if it passes 1hr you are fully stable ...
1hr for prime small ftt for cpu load
1hr linx and ready to go :):D for cpu and ram
I use both but linx finds the errors wayyyyy faster..
Guys question is it normal for linx to drop load every 3 minutes and then goes back up to 100% load ? thanks
Yeah, you'll see it will do that as many times as you choose "Run" ;)Quote:
Originally Posted by ryant
ok got it but isnt that making the cpu stress and temps rest a little :)?
prime 95 is 100% load untill you stop it and linx load goes down every 3 minutes weird..:shrug: and i have all turbos off and speedtep straight 21 multi
AT some point of overclocking my P6TD just dont use my 3 dimms instead of not booting.
I fall to 4gigs as soon as i push to hard without loosening the timing.
One faulty stick of ram. I say it's faulty cause "if it doesn't overclock - it's broken", as someone said... :yepp:Quote:
Originally Posted by Boulard83
Try a cheaky little "right click run as admin"Quote:
Originally Posted by namurt
this is normal and your temps under linpack will be higher than lolprime95, unles your getting throttled wich could be the case again lol.Quote:
Originally Posted by ryant
Hi,
I have LinX 0.6.4 and after I had a session with default settings, the next time I start the program it does not do anything when I press start, just counting the time, but does not put load on the CPU at all. If I press stop, nothing happens, either. I tried looking around the settings, deleted the ini file, but the only way I found working is to reinstall the program after every use... What do I do wrong?
EDIT: solved... :D I have to run it as admin on Win7.
Sorry this may have been asked before but does anyone know why hyper-threading lowers GFlops score? This is on my i7 920 system... non HT scores are significantly higher than HT On at the same clock speeds.
it might be but with prime it doesnt throtle since linx lowers my blck to 4.2ghz from 4.5ghz on load i guess i go by prime because my oc is not @ 4.2 ....Please fix this bug thanksQuote:
Originally Posted by Lome
Because Intels linpack routine is about the only app out there that fully utilises all capabilities of the CPU. SMT was designed to boost performance for poorly coded/optimised (but multithreaded) applications, but when the CPU faces something as efficient as linpack, Hyperthreading actually backfires. Still causes your CPU to heat up more, so I'd leave it on for testing if you normally run with HT enbabled.Quote:
Originally Posted by LarsMarkelson
Not a faulty stick, just a bad combination of dram & uncore speed as well as VTT and Vdimm voltages. Try keeping uncore at 2xDram for starters, and play with VTT (on Asus boards it's probably called something like QPI voltage, lol) and Vdimm.Quote:
Originally Posted by Boulard83
Cool, thanks for the info! :up:Quote:
Originally Posted by jcool
Hi, I tried to run this program on my old single core 754 under w7 x86 (w/ 2x512MB ram), but when using small memory amounts like 16-32MB the program seems to produce errors.
It will start without giving output for about 20s, and then all of the sudden, either a lot of computations appear with different times/gflops, or it errors out with invalid values on time/gflops GUI columns.
Just for comparison sake, on another popular linpack gui results will appear as they are calculated without errors taking about 7s for 20x 16MB.
http://i48.tinypic.com/122ks53.pngQuote:
Intel(R) LINPACK 32-bit data - LinX 0.6.4
Current date/time: Sat Feb 27 21:27:01 2010
CPU frequency: 2.604 GHz
Number of CPUs: 1
Number of threads: 1
Parameters are set to:
Number of tests : 1
Number of equations to solve (problem size) : 1354
Leading dimension of array : 1368
Number of trials to run : 20
Data alignment value (in Kbytes) : 4
Maximum memory requested that can be used = 14849632, at the size = 1354
============= Timing linear equation system solver =================
Size LDA Align. Time(s) GFlops Residual Residual(norm)
1354 1368 4 0.853 1.9454 2.177591e-012 4.079813e-002
1354 1368 4 0.782 2.1217 2.177591e-012 4.079813e-002
1354 1368 4 0.834
Edit: I've just tested on my PhII 4x and it doesn't exhibit the same problem. Computation output is immediately displayed.
I'm just reporting this, because it might uncover any bug that could cause false positives on other systems.
Running 0.6.4 without issue in Windows 7 64. Holy crap, it makes my q9550 run 5 degrees Celsius hotter than Prime95! :shocked:
Edit: Noticed something. Using it right after booting results in a lower problem size. After letting it run for a bit, closing LinX and re-running it again sets it to a higher problem size, which gives me the increase in load temps, higher GFlop count, and higher memory usage.
It's because of W7. It still does some things after boot, but eventually releases 200-250MB more of RAM and settles at 900-950MB (from 6GB).Quote:
Originally Posted by cabbspapp
I don't mean this as a flaw of W7. I'm using W7x64 on my old Opty170/NF4 too and it works great. It drops from 600-700MB to 200-300MB when LinX is ran. I run and stop LinX 2-3 times just for Win to release memory and then run it with desired RAM amount.
hi! just got a new rig today.
was wondering how much memory and loops i had to set linx to manage a stable OC.
in my previous rig (EP45-UD3R + Q9550) i used 20 passes and 3.5 as stability criteria; would the same apply to my core i7 rig?
thanks in advance!
Hey, I tried to use this version of linx for stability testing and I think there's a bug in it. No matter what I do it encounters an error just after 3 minutes of running while two other IBT programs can complete the task successfully. I'm using win7 pro x64 btw.
More memory - the better. 20 passes is more then enough IMO. I personally use just 5 passes with 5GB of RAM. Then I use my rig for what it's meant (folding, gaming...) and see if its stable. :rolleyes:Quote:
Originally Posted by vodka3dg
Usual answer is: unstable OC (no offence meant). I find LinX most stressing of all stressing application as many OC'ers will concur. Of course it is not the only needed for stability testing (prime, hyper pi, etc...)Quote:
Originally Posted by Red Maw
I downloaded linx and installed it, set it as described and when i hit start the counter starts counting, but none of the cores are loaded?
ok, the zipped version that is just extracted runs just fine, but the setup one doesn't it will load the app but doesnt load the cores. but anyway, my problem is
once it stops at an error, how do you find out what the error was? mine stopped upon error after 52m 16s on run #14 i was averaging 52.3 Gflops on a i7 920
running at 3.9, im trying my dambdest to get over 4.0
No offense taken, but my point was that no matter what this version of linpack fails at ~3min (iirc) independent of OC. My system has no trouble passing either of the other two linpack versions I have, just this one.Quote:
Originally Posted by donmarkoni
here is the link or w/e to the SS of the installer version of linx running but not loading any cores at all. the .rar version works fine for me tho.
http://i582.photobucket.com/albums/s...nxscreenie.png
Well, LinX is just a GUI and uses Intel's linpack modules, but it could be a bug showing only with your specific HW/SW used... :shrug:Quote:
Originally Posted by Red Maw
BTW, try raising VTT a notch, usually works for me when I get error after 1st loop.
Using version 0.6.4 I think theres a bug when another app is running while testing, such as WMP or browsing the net. When watching a movie while testing it tends to fail within 1 hour regardless of settings, when just running LinX alone it went for over 170 runs all memory (4850 MB) compared to less than 20 runs when watching a movie or browsing the net with the exact same settings, temps, and memory use.
Are you able to duplicate this using Intel Burn Test?Quote:
Originally Posted by GigaByte
Yes, when both apps were in their earlier stages I didn't have that issue. Even happened once at stock, IBT seems to finish several seconds faster than LinX at the same memory useage, don't really know why.Quote:
Originally Posted by Delirious
same problem here...Quote:
Originally Posted by jstanthr
I'll try the zip now
edit:
also the zipped version doesn't do anything :(
no one knows how to fix this?
Linx doesn't work for everyone, not sure why. I use the linpack version/gui by AgentGod since it has worked every time on all my systems, just search on XS or google and you should find it.
This needs an update to show correct Gflops for 980X
for the 980x It is possible to edit the program with the new Linpack from intell and get correct ~Gflops at a 25000 problem size but for me anyway trying to run at 37000 problem size it will still give lower temps and way lower Gflops for me running the 6.4 when I ran at 25000 problem size I was getting ~50Gflops andtemps of 60C and at problem size of 37000 I was getting 80-83Gflops and 70C temps after replacing the linpack with the intell version it was the exact oppisite at a 25000 problem size I would get 80-82Glops and 70Ctemps and at 37000 problem size I get 50Gflops and 60C temps so still not sure intell has got the linpack correct for 980X series
I just succeeded in running IntelBurnTest!
The trick was to execute it with admin rights.
Not sure if I did that with Linx.
In noticed that in between each run, it pauses for a moment (few secs) and the CPU cools down
Is this normal?
edit:
just tried Linx out again... It works if you run it as administrator... Seems like an easy fix for the next version to automate this...
Also Linx pauzes and cools down between each run btw...
For Ci7 980X here is how to update your LinX:
http://www.evga.com/forums/tm.aspx?m=333894
Hello Everyone,
So yesterday I joined the ranks of all the folks that have shiny new Gulftown 6 core CPU's. One of the first things I noticed when trying to overclock is that LinX was behaving just downright weird. The GFlops were way off and it was just hit or miss getting it to work correctly at times. So this prompted me to search for a solution rather than to wait for a new version of LinX.
So one thing that's a known is that LinX is really just a GUI frontend for LinPack, so that's where I started to look. And to my surprise I found a newer version of LinPack on Intel's site. So this post will tell you how to use this to make LinX work the way it should on your Gulftown CPU.
1. Make sure you have the latest version of LinX (0.6.4 as of this posting)
2. Go to software.intel.com/en-us/articles/intel-math-kernel-library-linpack-download/ and download the windows package for LinPack
3. Open the zip file and throw the folder inside on your desktop for ease of access
4. Go into that folder, then the benchmarks folder, then the linpack folder
5. In that folder you will see linpack_xeon32.exe and linpack_xeon64.exe. These are the files that we need.
6. Now open up another explorer window with the folder that you have LinX installed in.
7. Take the new linpack exe's and drop them in the LinX folder, allowing it to overwrite the old exe's.
8. Now run LinX and observe that it runs properly and also displays the proper GFlops that we should be seeing with these CPU's
Word of warning though, this version of Linpack loads your CPU correctly once again so expect it to run your CPU hotter than Prime95 does, so all of you should keep an eye on your temps while using this.
It's little bit better, but it's still not correct is it?
New Linpack added
http://i42.tinypic.com/2rfppmo.png
Compare with SiSandra Gflops (Clicky) 75 vs 130
http://i44.tinypic.com/o608qp.jpg
Of course I realize they are different programs, but shouldn't Glfops be a universal thing or at least very close?
Thanks for the tip by the way!
IMO, should be right. I never took Sandra seriously.Quote:
Originally Posted by Lsdmeasap
Comparing yours 74GFLOPS @ Core 4200 / UnCore 3360 / QPI 3696 / RAM 1680
against mine 54GFLOPS @ Core 4200 / UnCore 3600 / QPI 3600 / RAM 1600
looks right. With 50% more Cores you could have 81GFLOPS, but the difference comes from slower UnCore speed & higher RAM timings.
First loop or two is always quite a bit lower than the rest too, I would suspect you would be closer to donmarkoni's 81Gflop estimate.
So Sandra is wrong? Shouldn't Glfops all be the same, I guess maybe not since we just showed how different linpack versions change them.Quote:
Originally Posted by donmarkoni
I suppose it is normal then, I just read online that 980X should be 100 or so at default speeds I think, maybe overclocked was meant? Either way though that would still mean LinX is still off a bit
also remember that with hyper threading and Linx, you will get more G flops with out HT, but Sandra the opposite, if my lil memory is working this morning. :cool:
Ya, I did notice that about LinX, but didn't know Sandra was the opposite.
Wonder why the differ so much?
Hello Dua|ist,
Thank you very much for this software, most useful!
Would like to seek your advice please regarding the following setup:
I'm currently testing a Core i7-860 CPU (4 Physical + 4 "Virtual"/Hyper-Threading Cores) with:
- 4GBs of RAM
- Operating system Windows 7 32-bit.
This is how I currently test my system's available memory with your software:
1. Run a session of LinX, set it to 32-bit, 4 Cores and test 1700MB of RAM.
2. Run a second session of LinX from the same directory as I ran the first one, set it to 32-bit, 4 Cores and test the remaining available memory (minus 20-40MBs)
Question 1 :
Should I change the Cores setting for each session to just 2, so each session will actually use 2 Physical + 2 Virtual cores?
Question 2:
Should I run both LinX sessions from the same directory, or create a separate directory with its own settings for each session?
Thank you very much in advance for your answer!
Best regards,
Samuel