Lets put your CPU into REAL test! Intel Linpack 64bit

[Cronos]

It may be useful to explain a bit more how Linpack works and is optimized for given platform. The benchmark is distributed as source code, and can be compiled and ran on any platform, including non -x86, like IBM Power G5, Cell, Intel IA64 (Itanium) so on. The code uses calls to specific mathematical library of functions, called BLAS (Basic Linear Algebra Subprograms), which contains most frequently used operations with matrices and vectors. This BLAS library is heavily platform -optimized and distributed by each CPU vendor.

For example, Intel has MKL for their x86 and Itanium CPUs,
AMD has ACML. There are also non-vendor versions which
have optimizations for different CPUs (Goto BLAS, Atlas).

Then Linpack exe file is compiled from source, it is linked with some specific version of BLAS, thus achieving high optimization level for this specific CPU.

The above Intel Linpack is compiled and linked with some BLAS version. The BLAS used to link with 32bit version is very general and should run even on older Intel CPUs, 64bit version is linked with latest version of MKL, which is very heavily optimized for latest Intel CPUs. Hence the large difference both in performance and load on Core2.

The BLAS libraries are frequently linked with application which require high performance, for example mathematical packets like Mathematica, Maple, Mathcad , some encoders/decoders, distributed projects like Folding&Home and so on.

If Linpack fails, all these applications may also fail, though it may take (significantly) more time, and may go largely unnoticed, as most CPU errors do not lead to any abnormal termination.

[arfett]

Every computer I've ever built I have overclocked. Every single computer would blue screen me randomly or when running certain programs if I was not at least 8 hours prime stable. It might be weekly, bi-weekly, monthly, but it would happen. I always do a minimum of 8 hours prime 95 on small fft and blend and nowdays I go for 12 hours before I call it quits or else I know at some point I'll get a blue screen or random program crash.

The stress on the board is at least as bad as cranking the volts and doing 10min 32M Pi passes and 10s 1M Pi passes for several minutes, if not worse.

Can't tell you how many times a 5 hour prime stable computer has crashed on me while playing UT2004 that was 32M Pi "stable". Even for general use you must prime or do some sort of stress testing if you want to be assured no errors/crashing. If it works for you then that's cool, but if you're overclocking and you didn't stress it then you're not stable in my opinion and at some point I'd imagine it will get you.

[dogsx2]

Every computer I've ever built I have overclocked. Every single computer would blue screen me randomly or when running certain programs if I was not at least 8 hours prime stable. It might be weekly, bi-weekly, monthly, but it would happen. I always do a minimum of 8 hours prime 95 on small fft and blend and nowdays I go for 12 hours before I call it quits or else I know at some point I'll get a blue screen or random program crash.


Can't tell you how many times a 5 hour prime stable computer has crashed on me while playing UT2004 that was 32M Pi "stable". Even for general use you must prime or do some sort of stress testing if you want to be assured no errors/crashing. If it works for you then that's cool, but if you're overclocking and you didn't stress it then you're not stable in my opinion and at some point I'd imagine it will get you.

Sorry to hear your bad luck with building computers.

[arfett]

Sorry to hear your bad luck with building computers.

Not bad luck, just overclocking too much. Drop the mhz down a bit and get a 8-12 hour run of prime and stable with no blue screens for a year. I've primed this q6600 with small fft and blend for 12 hours (in addition to some Pi 32M runs) and I can basically guarantee you I will never have a blue screen unless it's some crappy vista driver problem.

[-n7-]

Thanx for explaining how to configure this properly.

I'd already grabbed it thanx to reading your posts about this from before, but didn't know how to set its parameters.

[sofarfrome]

Every computer I've ever built I have overclocked. Every single computer would blue screen me randomly or when running certain programs if I was not at least 8 hours prime stable. It might be weekly, bi-weekly, monthly, but it would happen. I always do a minimum of 8 hours prime 95 on small fft and blend and nowdays I go for 12 hours before I call it quits or else I know at some point I'll get a blue screen or random program crash.


Can't tell you how many times a 5 hour prime stable computer has crashed on me while playing UT2004 that was 32M Pi "stable". Even for general use you must prime or do some sort of stress testing if you want to be assured no errors/crashing. If it works for you then that's cool, but if you're overclocking and you didn't stress it then you're not stable in my opinion and at some point I'd imagine it will get you.

I had a rig (an E6600 at 3.71GHz) that passed prime95 for 8+ hours while looping 3DMark03 in the back ground that would crash after 10 minutes of UT2004. Even though I passed all acceptable stability tests I still needed a little more vcore to keep it stable when running UT2004. I am done killing my boards. 1 hour OCCT or P95 while looping a 3DMark program and it is off to some folding or gaming for the real test. Anyone that runs 24hours+ of P95 or Orthos to gain confidence in the OC is shortening the life of the board and other components and nothing more. What task does a PC perform that utilizes 100% CPU resources?

[cantankerous]

I had a rig (an E6600 at 3.71GHz) that passed prime95 for 8+ hours while looping 3DMark03 in the back ground that would crash after 10 minutes of UT2004. Even though I passed all acceptable stability tests I still needed a little more vcore to keep it stable when running UT2004. I am done killing my boards. 1 hour OCCT or P95 while looping a 3DMark program and it is off to some folding or gaming for the real test. Anyone that runs 24hours+ of P95 or Orthos to gain confidence in the OC is shortening the life of the board and other components and nothing more. What task does a PC perform that utilizes 100% CPU resources?

Gulp. Is this 100% accurate? I understand while stress testing you are obviously putting the system under stress (duh), but are motherboards/ram/cpu that fragile that I should be worried about them giving up the ghost from putting them under extreme pressure? I am worried now as I have HOT ambient temps of 30c, and have ran my system for weeks at 35+h straight runs under prime95/OCCT etc. Temps were quite high across the board for those long hours. Though I have not noticed any issues from using my system, I am worried I may have done some damage after reading the above statement.

[STEvil]

Gulp. Is this 100% accurate? I understand while stress testing you are obviously putting the system under stress (duh), but are motherboards/ram/cpu that fragile that I should be worried about them giving up the ghost from putting them under extreme pressure? I am worried now as I have HOT ambient temps of 30c, and have ran my system for weeks at 35+h straight runs under prime95/OCCT etc. Temps were quite high across the board for those long hours. Though I have not noticed any issues from using my system, I am worried I may have done some damage after reading the above statement.

No, he's just been burned by buying crap components and expecting too much from them.

[rge]

The reason I was irritated after hearing it stated that Linpack 64 was "very sensitive" at detecting memory and cpu instability, is I did not find that to be true.

problem: BSOD's and reboots after 1-3 hours of orthos large FFT's and seemingly random stops, reboots in small ffts.

Linpack 64, runs of 50 to 100 trials of problem size 10000, which takes 1.3 to 3 hours, never an error of any kind, all residual norms same.

Memtest tells me the problem in 2 minutes. RAM is bad, and unstable at any settings.

I dont think I would call Linpack a sensitive test for memory, when 1.3hrs plus shows no error, and memtest tells me in 2 minutes.

[GOZR]

To me a real machine overclocked is not some benchy numbers ..

It's a machine that can run 24/7 as well as it's stock speed with 4 GB/ 2 GB minimum ram liquid or air cooled and running Simulation like FSX or others games or heavy calculation softwares with out crashing..

The rest is just pictures in the wall or tests to maximum possible strengh harware to know teh limit and finally make a machine stable not 10 seconds ..

[dinos22]

The reason I was irritated after hearing it stated that Linpack 64 was "very sensitive" at detecting memory and cpu instability, is I did not find that to be true.

problem: BSOD's and reboots after 1-3 hours of orthos large FFT's and seemingly random stops, reboots in small ffts.

Linpack 64, runs of 50 to 100 trials of problem size 10000, which takes 1.3 to 3 hours, never an error of any kind, all residual norms same.

Memtest tells me the problem in 2 minutes. RAM is bad, and unstable at any settings.

I dont think I would call Linpack a sensitive test for memory, when 1.3hrs plus shows no error, and memtest tells me in 2 minutes.

i always run superpi as well in windows

Spi is not fullproof but you can't trust any of these programs as per your example either

best stability test really is some simple orthos/spi stuff and then user trial.....if you use it for a month and no issues with whatever you use it for that's a stable machine right there heh

[Cronos]

I dont think I would call Linpack a sensitive test for memory, when 1.3hrs plus shows no error, and memtest tells me in 2 minutes.

You tested half of the memory with Linpack 32bit.
Try bigger problem size and run Linpack 64bit.

Linpack is not a substitute for memtest86+ anyway. You always should test your memory with memtest for at least 10+ complete passes.

There is something not right in your way of thinking....

[cantankerous]

No, he's just been burned by buying crap components and expecting too much from them.

I sure hope this is the case. I would like to think the parts in my sig are of good quality and that they could in fact hold up to the many long weeks of extreme temps I was submitting them too. I hate dead parts, not a fun time to deal with them.