LinX - A simple Linpack interface

[WaterFlex]

pcnazz
Very nice rig and clock

[Unrealer]

Im trying to use all the available memory with Linx but i only have aroung 1Gb free ! And i installed 6Gb...

[SimpleTECH]

Try increasing VTT.

Or it could be that one of your sticks is dead or perhaps DIMM slots is dead.

[Salamndar]

Im trying to use all the available memory with Linx but i only have aroung 1Gb free ! And i installed 6Gb...

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

[phsinc1]

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

check for bent pins or the cooler could be making much force on the mobo socket backplate or the memory slots are bad

[Salamndar]

check for bent pins or the cooler could be making much force on the mobo socket backplate or the memory slots are bad

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 !

[CryptiK]

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.

[Unrealer]

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 !

I also fixed the problem, i loaded the default values @ bios, reoverclock, and now i get around 5Gb free

[ryant]

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 for cpu and ram

I use both but linx finds the errors wayyyyy faster..

[ryant]

Guys question is it normal for linx to drop load every 3 minutes and then goes back up to 100% load ? thanks

[tool_462]

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"

[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.. and i have all turbos off and speedtep straight 21 multi

[Boulard83]

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.

[donmarkoni]

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...

[D1C30N]

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.

Try a cheaky little "right click run as admin"

[Lome]

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.. and i have all turbos off and speedtep straight 21 multi

this is normal and your temps under linpack will be higher than lolprime95, unles your getting throttled wich could be the case again lol.

[Csybe]

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... I have to run it as admin on Win7.

[LarsMarkelson]

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.

[ryant]

this is normal and your temps under linpack will be higher than lolprime95, unles your getting throttled wich could be the case again lol.

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 thanks

[jcool]

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.

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.

[jcool]

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.

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.

[LarsMarkelson]

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.

Cool, thanks for the info!

[AlleyViper]

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.

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.

[cabbspapp]

Running 0.6.4 without issue in Windows 7 64. Holy crap, it makes my q9550 run 5 degrees Celsius hotter than Prime95!

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.

[donmarkoni]

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).
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.