Overclocking a Core i5 3570K
 

I've just built a new Core i5 3750K based system. It seems to be stable at 4.4GHz with vcore + 0.0v. Core temperatures while torture testing were around 60 degrees. I'm currently torture testing at 4.5GHz with vcore + 0.1v. (It wasn't stable at vcore + 0.05v.) Temperatures are up to about 75 degrees.

If its stable at 4.5GHZ at this or maybe a little higher voltage, then my plan is to pull back on the overclock - to 4.3GHz, say, then resume P-1 testing for GIMPS. I have 2 questions:

1. Will running 24/7 for years with all cores at 100% at these kinds of speeds and temperatures damage or significantly reduce the lifespan of my processor?

2. Defining "stable" to mean 24 hours of torture testing with no errors, will pulling back 200MHz from the highest stable overclock be a sufficient margin for production or should I take it even lower?

[QUOTE=Mr. P-1;327321]1. Will running 24/7 for years with all cores at 100% at these kinds of speeds and temperatures damage or significantly reduce the lifespan of my processor?[/QUOTE]Yes. Read up about electromigration. Although the precise determination of "significantly" is open to debate.[QUOTE=Mr. P-1;327321]2. Defining "stable" to mean 24 hours of torture testing with no errors, will pulling back 200MHz from the highest stable overclock be a sufficient margin for production or should I take it even lower?[/QUOTE]If it was me I would take it all the way back to stock. This has been discussed here before but in summary: You could stand to lose more work through occasional errors than you can make up for with over-clocking. But the exact trade-off point is dependant upon which type of work you intend to do. For P-1 I'm not sure where the trade-off point is but I usually use the metric of one month of runtime per work unit is the maximum work unit I commit for stock machines and reduce the time period accordingly for over-clocked machines.

Edit: Where the meaning of "work unit" is: a minimal computation sequence that must run from beginning to end before any meaningful result is obtained.

Edit2: For runs longer than one month always use ECC enabled hardware.

I disagree with retina.

1) Yes it will reduce the life of your CPU but it is unlikely to reduce it to before the point of obsolescence. I would try to keep temps < 70C if possible. You need to leave room for those very hot days.

2) I find torture tests aren't the best for determining stability. Throw in a bunch of double checks - stagger them so that your computer is tested with 0/1/2/3/4 DCs and 4/3/2/1/0 P-1 tests simultaneously and verify if your DCs match. If you can do 10-12 DCs without any mismatch I'd say you are good to go. There is no hard and fast rule but 200MHz should be sufficient.

Core i5 3[B]75[/B]0k?
Guess you mean either Core i5 3[B]57[/B]0k or Core i7 3[B]77[/B]0k :razz:.

[QUOTE=retina;327322]Yes. Read up about electromigration.[/QUOTE]

From what I can find out, the rate of EM deterioration is dependent upon three factors:

Voltage: I do not intend to overvolt at my production overclock.

Temperature: My temperatures at 4.4GHZ with my installed Frio cooler were about 3 degrees higher than at stock speed with the stock cooler. At 4.3GHZ, I would expect it to run cooler.

Frequency. My understanding is that the rate of EM deterioration varies proportionately with frequency, which I view as not reducing the life of the CPU (measured in CPU ticks), rather compressing it in terms of wallclock time.

[QUOTE=VictordeHolland;327342]Core i5 3[B]75[/B]0k?
Guess you mean either Core i5 3[B]57[/B]0k or Core i7 3[B]77[/B]0k :razz:.[/QUOTE]

Yes.

This is an example of the situation P-1 is trying to gauge.
If a cpu has an error rate of 2% at stock then the necessary work for testing 100 exponents is 204 tests in 204 time.
If you overclock your cpu by 10% and have an error rate of 5% then 210 tests are needed but they will be done in 210/1.1=190.909090... time. This is a saving of about the time of 13 tests at stock.

The trouble is determining the error rate but that would be the same with all cpus. Retina seems to be suggesting underclocking cpus to eliminate errors completely. It is amazing what error percentage it is possible to have before you are behind the production speed of stock. For the example above an error rate of 12.2% breaks even.

What speed increase are you getting Mr. P-1?

[QUOTE=garo;327328] I would try to keep temps < 70C if possible. You need to leave room for those very hot days.[/quote]

I live in Scotland. There aren't very many hot days.

That said, I do intend to monitor the temperature and keep it at about 60, reducing the overclock if necessary as the weather gets warmer.

[quote]2) I find torture tests aren't the best for determining stability.[/quote]

They're good for quickly establishing instability. But I take your point - I should prove, using doublechecks, that my system is stable at x MHz before going into production at x-200 MHz.

But before I do any of that, I'm thinking that I should test it for a week or so at stock speed. That way I will find out it I'm having any problems which are nothing to do with the overclock. For example: at 2.5MHz +0.1v, mprime has segfaulted once. Is that because of the overclock or some other problem?

I've also noticed some peculiarities in the temperature graph: it goes through occasional episodes of square-waving, when every few seconds the temperature will suddenly drop to about 45 degrees for about a second or so, before returning to the 60-70 range. The torture test doesn't fail, and the threads are still getting the usual 98-100% of processor time. So it looks to me as though it's throttling, even though it's nowhere near the temperature at which it should do this.

[QUOTE=henryzz;327351]Retina seems to be suggesting underclocking cpus to eliminate errors completely.[/QUOTE]Not at all. Underclocking will, in most cases, reduce the error rate but I doubt it can ever eliminate errors completely.

[QUOTE=henryzz;327351]This is an example of the situation P-1 is trying to gauge.
If a cpu has an error rate of 2% at stock then the necessary work for testing 100 exponents is 204 tests in 204 time.
If you overclock your cpu by 10% and have an error rate of 5% then 210 tests are needed but they will be done in 210/1.1=190.909090... time. This is a saving of about the time of 13 tests at stock.[/QUOTE]

That's true for DC assignments, where all you lose for a erroneous run is the time you spent on it. It's also true for an LL, though GIMPS may not find out about it (including the possibility of a missed prime) until the DC wave catches up.

For factorisation, (trial or P-1), the calculation is a little different. If an erroneous run fails to find a factor which it should have, the cost to the project isn't that the factorisation has to be repeated. The cost is that two unnecessary LLs get done.

I also think your error rate assumptions are implausible. The overall error rate for the project is 2%. In practice, this means most machines are error free, while a few have a much higher error-rate. Error-prone machines do not hurt the project - and might still contribute if they are sometimes error-free - if they are doing DC checks only. Error-prone machines doing factorisation are likely to harm it.

[quote]The trouble is determining the error rate but that would be the same with all cpus.[/quote]

Not necessarily. Overclocking-related errors are caused by a circuit not completing its calculation by the time its results are read at the next clock pulse. Two corresponding circuits in two cores may have fractionally different electrical properties, causing one to take slightly longer to complete its calculation than the other.

[QUOTE]What speed increase are you getting Mr. P-1?[/QUOTE]

I don't know, as I'm currently booted up non-overclocked and didn't check before. Here are my non-overclocked benchmarks:

[code]Compare your results to other computers at http://www.mersenne.org/report_benchmarks
Intel(R) Core(TM) i5-3570K CPU @ 3.40GHz
CPU speed: 3555.84 MHz, 4 cores
CPU features: Prefetch, SSE, SSE2, SSE4, AVX
L1 cache size: 32 KB
L2 cache size: 256 KB, L3 cache size: 6 MB
L1 cache line size: 64 bytes
L2 cache line size: 64 bytes
TLBS: 64
Prime95 32-bit version 27.9, RdtscTiming=1
Best time for 768K FFT length: 4.902 ms., avg: 4.934 ms.
[Mon Feb 4 19:52:51 2013]
Best time for 896K FFT length: 6.109 ms., avg: 6.177 ms.
Best time for 1024K FFT length: 6.753 ms., avg: 6.768 ms.
Best time for 1280K FFT length: 8.858 ms., avg: 8.875 ms.
Best time for 1536K FFT length: 10.625 ms., avg: 10.658 ms.
Best time for 1792K FFT length: 12.838 ms., avg: 12.862 ms.
Best time for 2048K FFT length: 14.115 ms., avg: 14.136 ms.
Best time for 2560K FFT length: 18.314 ms., avg: 18.358 ms.
Best time for 3072K FFT length: 22.194 ms., avg: 22.247 ms.
Best time for 3584K FFT length: 27.787 ms., avg: 27.809 ms.
Best time for 4096K FFT length: 30.450 ms., avg: 30.487 ms.
Best time for 5120K FFT length: 39.470 ms., avg: 39.566 ms.
Best time for 6144K FFT length: 48.028 ms., avg: 48.044 ms.
Best time for 7168K FFT length: 59.815 ms., avg: 59.862 ms.
Best time for 8192K FFT length: 67.326 ms., avg: 67.416 ms.
Timing FFTs using 2 threads.
Best time for 768K FFT length: 2.567 ms., avg: 2.591 ms.
Best time for 896K FFT length: 3.151 ms., avg: 3.175 ms.
Best time for 1024K FFT length: 3.492 ms., avg: 3.512 ms.
Best time for 1280K FFT length: 4.622 ms., avg: 4.762 ms.
Best time for 1536K FFT length: 5.479 ms., avg: 5.624 ms.
Best time for 1792K FFT length: 6.641 ms., avg: 6.657 ms.
Best time for 2048K FFT length: 7.273 ms., avg: 7.307 ms.
Best time for 2560K FFT length: 9.413 ms., avg: 9.619 ms.
Best time for 3072K FFT length: 11.416 ms., avg: 11.443 ms.
Best time for 3584K FFT length: 14.197 ms., avg: 14.229 ms.
Best time for 4096K FFT length: 15.613 ms., avg: 15.680 ms.
Best time for 5120K FFT length: 20.288 ms., avg: 20.366 ms.
Best time for 6144K FFT length: 24.626 ms., avg: 25.045 ms.
Best time for 7168K FFT length: 30.428 ms., avg: 30.546 ms.
Best time for 8192K FFT length: 34.430 ms., avg: 34.818 ms.
Timing FFTs using 3 threads.
Best time for 768K FFT length: 1.872 ms., avg: 1.896 ms.
Best time for 896K FFT length: 2.181 ms., avg: 2.205 ms.
Best time for 1024K FFT length: 2.449 ms., avg: 2.479 ms.
Best time for 1280K FFT length: 3.259 ms., avg: 3.403 ms.
Best time for 1536K FFT length: 3.861 ms., avg: 3.895 ms.
Best time for 1792K FFT length: 4.647 ms., avg: 4.697 ms.
Best time for 2048K FFT length: 5.149 ms., avg: 5.318 ms.
Best time for 2560K FFT length: 6.679 ms., avg: 6.803 ms.
Best time for 3072K FFT length: 8.107 ms., avg: 8.159 ms.
Best time for 3584K FFT length: 10.041 ms., avg: 10.513 ms.
Best time for 4096K FFT length: 11.063 ms., avg: 11.106 ms.
Best time for 5120K FFT length: 14.333 ms., avg: 14.387 ms.
Best time for 6144K FFT length: 17.335 ms., avg: 17.784 ms.
Best time for 7168K FFT length: 21.178 ms., avg: 21.542 ms.
Best time for 8192K FFT length: 24.145 ms., avg: 24.206 ms.
Timing FFTs using 4 threads.
Best time for 768K FFT length: 1.564 ms., avg: 1.600 ms.
Best time for 896K FFT length: 1.741 ms., avg: 1.791 ms.
Best time for 1024K FFT length: 2.004 ms., avg: 2.050 ms.
Best time for 1280K FFT length: 2.693 ms., avg: 2.885 ms.
Best time for 1536K FFT length: 3.273 ms., avg: 3.321 ms.
Best time for 1792K FFT length: 3.882 ms., avg: 3.946 ms.
Best time for 2048K FFT length: 4.400 ms., avg: 4.465 ms.
Best time for 2560K FFT length: 5.746 ms., avg: 5.821 ms.
Best time for 3072K FFT length: 6.901 ms., avg: 7.006 ms.
Best time for 3584K FFT length: 8.420 ms., avg: 8.531 ms.
Best time for 4096K FFT length: 9.501 ms., avg: 9.764 ms.
Best time for 5120K FFT length: 12.002 ms., avg: 12.036 ms.
Best time for 6144K FFT length: 14.494 ms., avg: 14.546 ms.
Best time for 7168K FFT length: 17.653 ms., avg: 17.715 ms.
Best time for 8192K FFT length: 19.786 ms., avg: 19.878 ms.
Best time for 61 bit trial factors: 2.630 ms.
Best time for 62 bit trial factors: 2.658 ms.
Best time for 63 bit trial factors: 4.385 ms.
Best time for 64 bit trial factors: 4.386 ms.
Best time for 65 bit trial factors: 4.373 ms.
Best time for 66 bit trial factors: 4.341 ms.
Best time for 67 bit trial factors: 4.340 ms.
Best time for 75 bit trial factors: 4.559 ms.
Best time for 76 bit trial factors: 4.557 ms.
Best time for 77 bit trial factors: 4.538 ms.[/code]

[QUOTE=Mr. P-1;327359]I don't know, as I'm currently booted up non-overclocked and didn't check before. Here are my non-overclocked benchmarks:[/QUOTE]

What's the point of OCing if you don't even bother to check if it's giving an appreciable speed increase?

Since you long table is just for one mode and thus does nothing to answer the question, why post it? Do the differential diagnosis, then get back to us.

I got my 3570K 2 months ago. I had it built locally by a reputable company.
They ensured me the stock Intel cooler would be fine.
But it was running 90 degrees
[B]They assured me it would be fine and in fact this chip doesn't even throttle back until 105. [/B]
However, that was too hot for me and I had wanted them to OC it to 4.2
I asked for a REAL cooler and at 4.2 my temps are now around 60.

[QUOTE=petrw1;327542]They ensured me the stock Intel cooler would be fine.[/QUOTE]

They assumed you'd only be running it during the winter. With a long extension cord and an extra long Ethernet cable. In the back yard.

Caveat emptor.

[QUOTE=ewmayer;327517]What's the point of OCing if you don't even bother to check if it's giving an appreciable speed increase?

Since you long table is just for one mode and thus does nothing to answer the question, why post it? Do the differential diagnosis, then get back to us.[/QUOTE]

That's a fair point. Ignore the previous benchmark. Other than that it wasn't overclocked, I don't know what the UEFI settings were.

Here's the benchmark at UEFI defaults, which if I understand correctly what it's telling me, means that the RAM is configured as DDR3-1333 9-9-9-24

[code]Compare your results to other computers at http://www.mersenne.org/report_benchmarks
Intel(R) Core(TM) i5-3570K CPU @ 3.40GHz
CPU speed: 3555.62 MHz, 4 cores
CPU features: Prefetch, SSE, SSE2, SSE4, AVX
L1 cache size: 32 KB
L2 cache size: 256 KB, L3 cache size: 6 MB
L1 cache line size: 64 bytes
L2 cache line size: 64 bytes
TLBS: 64
Prime95 32-bit version 27.9, RdtscTiming=1
Best time for 768K FFT length: 4.907 ms., avg: 4.923 ms.
Best time for 896K FFT length: 6.106 ms., avg: 6.170 ms.
Best time for 1024K FFT length: 6.770 ms., avg: 6.790 ms.
Best time for 1280K FFT length: 8.880 ms., avg: 8.894 ms.
Best time for 1536K FFT length: 10.660 ms., avg: 10.686 ms.
Best time for 1792K FFT length: 12.866 ms., avg: 12.883 ms.
Best time for 2048K FFT length: 14.150 ms., avg: 14.162 ms.
Best time for 2560K FFT length: 18.371 ms., avg: 18.393 ms.
Best time for 3072K FFT length: 22.250 ms., avg: 22.283 ms.
Best time for 3584K FFT length: 27.746 ms., avg: 27.771 ms.
Best time for 4096K FFT length: 30.435 ms., avg: 30.456 ms.
Best time for 5120K FFT length: 39.460 ms., avg: 39.527 ms.
Best time for 6144K FFT length: 47.982 ms., avg: 47.993 ms.
Best time for 7168K FFT length: 59.772 ms., avg: 59.823 ms.
Best time for 8192K FFT length: 67.568 ms., avg: 67.631 ms.
Timing FFTs using 2 threads.
Best time for 768K FFT length: 2.618 ms., avg: 2.638 ms.
Best time for 896K FFT length: 3.138 ms., avg: 3.218 ms.
Best time for 1024K FFT length: 3.492 ms., avg: 3.510 ms.
Best time for 1280K FFT length: 4.618 ms., avg: 4.642 ms.
Best time for 1536K FFT length: 5.499 ms., avg: 5.527 ms.
Best time for 1792K FFT length: 6.625 ms., avg: 6.650 ms.
Best time for 2048K FFT length: 7.282 ms., avg: 7.311 ms.
Best time for 2560K FFT length: 9.407 ms., avg: 9.460 ms.
Best time for 3072K FFT length: 11.414 ms., avg: 11.434 ms.
Best time for 3584K FFT length: 14.195 ms., avg: 14.239 ms.
Best time for 4096K FFT length: 15.599 ms., avg: 15.633 ms.
Best time for 5120K FFT length: 20.244 ms., avg: 20.283 ms.
Best time for 6144K FFT length: 24.580 ms., avg: 24.653 ms.
Best time for 7168K FFT length: 30.496 ms., avg: 30.509 ms.
Best time for 8192K FFT length: 34.411 ms., avg: 34.461 ms.
Timing FFTs using 3 threads.
Best time for 768K FFT length: 1.874 ms., avg: 1.894 ms.
Best time for 896K FFT length: 2.160 ms., avg: 2.201 ms.
Best time for 1024K FFT length: 2.439 ms., avg: 2.471 ms.
Best time for 1280K FFT length: 3.247 ms., avg: 3.270 ms.
Best time for 1536K FFT length: 3.858 ms., avg: 3.896 ms.
Best time for 1792K FFT length: 4.654 ms., avg: 4.683 ms.
Best time for 2048K FFT length: 5.140 ms., avg: 5.171 ms.
Best time for 2560K FFT length: 6.690 ms., avg: 6.755 ms.
Best time for 3072K FFT length: 8.096 ms., avg: 8.122 ms.
Best time for 3584K FFT length: 10.028 ms., avg: 10.079 ms.
Best time for 4096K FFT length: 11.070 ms., avg: 11.108 ms.
Best time for 5120K FFT length: 14.296 ms., avg: 14.350 ms.
Best time for 6144K FFT length: 17.325 ms., avg: 17.366 ms.
Best time for 7168K FFT length: 21.316 ms., avg: 21.392 ms.
Best time for 8192K FFT length: 24.109 ms., avg: 24.155 ms.
Timing FFTs using 4 threads.
Best time for 768K FFT length: 1.530 ms., avg: 1.583 ms.
Best time for 896K FFT length: 1.743 ms., avg: 1.798 ms.
Best time for 1024K FFT length: 1.995 ms., avg: 2.017 ms.
Best time for 1280K FFT length: 2.673 ms., avg: 2.729 ms.
Best time for 1536K FFT length: 3.249 ms., avg: 3.283 ms.
Best time for 1792K FFT length: 3.886 ms., avg: 3.932 ms.
Best time for 2048K FFT length: 4.374 ms., avg: 4.429 ms.
Best time for 2560K FFT length: 5.694 ms., avg: 5.819 ms.
Best time for 3072K FFT length: 6.965 ms., avg: 7.052 ms.
Best time for 3584K FFT length: 8.395 ms., avg: 8.481 ms.
Best time for 4096K FFT length: 9.457 ms., avg: 9.527 ms.
Best time for 5120K FFT length: 11.992 ms., avg: 12.039 ms.
Best time for 6144K FFT length: 14.470 ms., avg: 14.527 ms.
Best time for 7168K FFT length: 17.502 ms., avg: 17.552 ms.
Best time for 8192K FFT length: 19.746 ms., avg: 19.793 ms.
Best time for 61 bit trial factors: 2.636 ms.
Best time for 62 bit trial factors: 2.662 ms.
Best time for 63 bit trial factors: 4.382 ms.
Best time for 64 bit trial factors: 4.386 ms.
Best time for 65 bit trial factors: 4.369 ms.
Best time for 66 bit trial factors: 4.340 ms.
Best time for 67 bit trial factors: 4.338 ms.
Best time for 75 bit trial factors: 4.559 ms.
Best time for 76 bit trial factors: 4.557 ms.
Best time for 77 bit trial factors: 4.537 ms.[/code]

As above, except with the RAM configured to it's XMP profile: DDR3-2400 10-12-12-31

[code]Compare your results to other computers at http://www.mersenne.org/report_benchmarks
Intel(R) Core(TM) i5-3570K CPU @ 3.40GHz
CPU speed: 3555.84 MHz, 4 cores
CPU features: Prefetch, SSE, SSE2, SSE4, AVX
L1 cache size: 32 KB
L2 cache size: 256 KB, L3 cache size: 6 MB
L1 cache line size: 64 bytes
L2 cache line size: 64 bytes
TLBS: 64
Prime95 32-bit version 27.9, RdtscTiming=1
Best time for 768K FFT length: 4.912 ms., avg: 4.925 ms.
Best time for 896K FFT length: 6.107 ms., avg: 6.159 ms.
Best time for 1024K FFT length: 6.743 ms., avg: 6.760 ms.
Best time for 1280K FFT length: 8.858 ms., avg: 8.874 ms.
Best time for 1536K FFT length: 10.625 ms., avg: 10.639 ms.
Best time for 1792K FFT length: 12.830 ms., avg: 12.850 ms.
Best time for 2048K FFT length: 14.119 ms., avg: 14.139 ms.
Best time for 2560K FFT length: 18.311 ms., avg: 18.340 ms.
Best time for 3072K FFT length: 22.191 ms., avg: 22.217 ms.
Best time for 3584K FFT length: 27.762 ms., avg: 27.802 ms.
Best time for 4096K FFT length: 30.441 ms., avg: 30.470 ms.
Best time for 5120K FFT length: 39.437 ms., avg: 39.488 ms.
Best time for 6144K FFT length: 47.994 ms., avg: 48.006 ms.
Best time for 7168K FFT length: 59.786 ms., avg: 59.852 ms.
Best time for 8192K FFT length: 67.364 ms., avg: 67.415 ms.
Timing FFTs using 2 threads.
Best time for 768K FFT length: 2.587 ms., avg: 2.616 ms.
Best time for 896K FFT length: 3.140 ms., avg: 3.215 ms.
Best time for 1024K FFT length: 3.487 ms., avg: 3.515 ms.
Best time for 1280K FFT length: 4.609 ms., avg: 4.621 ms.
Best time for 1536K FFT length: 5.475 ms., avg: 5.500 ms.
Best time for 1792K FFT length: 6.620 ms., avg: 6.646 ms.
Best time for 2048K FFT length: 7.264 ms., avg: 7.315 ms.
Best time for 2560K FFT length: 9.413 ms., avg: 9.453 ms.
Best time for 3072K FFT length: 11.389 ms., avg: 11.402 ms.
Best time for 3584K FFT length: 14.228 ms., avg: 14.308 ms.
Best time for 4096K FFT length: 15.621 ms., avg: 15.649 ms.
Best time for 5120K FFT length: 20.269 ms., avg: 20.318 ms.
Best time for 6144K FFT length: 24.637 ms., avg: 24.753 ms.
Best time for 7168K FFT length: 30.494 ms., avg: 30.560 ms.
Best time for 8192K FFT length: 34.430 ms., avg: 34.547 ms.
Timing FFTs using 3 threads.
Best time for 768K FFT length: 1.867 ms., avg: 1.900 ms.
Best time for 896K FFT length: 2.156 ms., avg: 2.204 ms.
Best time for 1024K FFT length: 2.432 ms., avg: 2.455 ms.
Best time for 1280K FFT length: 3.242 ms., avg: 3.314 ms.
Best time for 1536K FFT length: 3.874 ms., avg: 3.920 ms.
Best time for 1792K FFT length: 4.624 ms., avg: 4.680 ms.
Best time for 2048K FFT length: 5.125 ms., avg: 5.171 ms.
Best time for 2560K FFT length: 6.709 ms., avg: 6.837 ms.
Best time for 3072K FFT length: 8.122 ms., avg: 8.158 ms.
Best time for 3584K FFT length: 10.055 ms., avg: 10.095 ms.
Best time for 4096K FFT length: 11.093 ms., avg: 11.134 ms.
Best time for 5120K FFT length: 14.302 ms., avg: 14.393 ms.
Best time for 6144K FFT length: 17.320 ms., avg: 17.412 ms.
Best time for 7168K FFT length: 21.225 ms., avg: 21.327 ms.
Best time for 8192K FFT length: 24.003 ms., avg: 24.050 ms.
Timing FFTs using 4 threads.
Best time for 768K FFT length: 1.521 ms., avg: 1.569 ms.
Best time for 896K FFT length: 1.724 ms., avg: 1.777 ms.
Best time for 1024K FFT length: 1.998 ms., avg: 2.030 ms.
Best time for 1280K FFT length: 2.686 ms., avg: 2.747 ms.
Best time for 1536K FFT length: 3.257 ms., avg: 3.284 ms.
Best time for 1792K FFT length: 3.887 ms., avg: 3.952 ms.
Best time for 2048K FFT length: 4.386 ms., avg: 4.430 ms.
Best time for 2560K FFT length: 5.757 ms., avg: 5.852 ms.
Best time for 3072K FFT length: 6.940 ms., avg: 7.006 ms.
Best time for 3584K FFT length: 8.494 ms., avg: 8.576 ms.
Best time for 4096K FFT length: 9.466 ms., avg: 9.570 ms.
Best time for 5120K FFT length: 12.004 ms., avg: 12.088 ms.
Best time for 6144K FFT length: 14.448 ms., avg: 14.505 ms.
Best time for 7168K FFT length: 17.473 ms., avg: 17.540 ms.
Best time for 8192K FFT length: 19.737 ms., avg: 19.791 ms.
Best time for 61 bit trial factors: 2.516 ms.
Best time for 62 bit trial factors: 2.659 ms.
Best time for 63 bit trial factors: 4.381 ms.
Best time for 64 bit trial factors: 4.385 ms.
Best time for 65 bit trial factors: 4.373 ms.
Best time for 66 bit trial factors: 4.336 ms.
Best time for 67 bit trial factors: 4.341 ms.
Best time for 75 bit trial factors: 4.561 ms.
Best time for 76 bit trial factors: 4.558 ms.
Best time for 77 bit trial factors: 4.541 ms.[/code]

Comment is too long. I'll post the overclocked benchmarks separately

Overclocked to 4.2MHz DDR3-1333

[code][Mon Feb 4 23:02:04 2013]
Compare your results to other computers at http://www.mersenne.org/report_benchmarks
Intel(R) Core(TM) i5-3570K CPU @ 3.40GHz
CPU speed: 4148.23 MHz, 4 cores
CPU features: Prefetch, SSE, SSE2, SSE4, AVX
L1 cache size: 32 KB
L2 cache size: 256 KB, L3 cache size: 6 MB
L1 cache line size: 64 bytes
L2 cache line size: 64 bytes
TLBS: 64
Prime95 32-bit version 27.9, RdtscTiming=1
Best time for 768K FFT length: 4.251 ms., avg: 4.280 ms.
Best time for 896K FFT length: 5.281 ms., avg: 5.325 ms.
Best time for 1024K FFT length: 5.868 ms., avg: 5.896 ms.
Best time for 1280K FFT length: 7.692 ms., avg: 7.711 ms.
Best time for 1536K FFT length: 9.243 ms., avg: 9.394 ms.
Best time for 1792K FFT length: 11.145 ms., avg: 11.197 ms.
Best time for 2048K FFT length: 12.292 ms., avg: 12.327 ms.
Best time for 2560K FFT length: 15.936 ms., avg: 15.977 ms.
Best time for 3072K FFT length: 19.350 ms., avg: 19.448 ms.
Best time for 3584K FFT length: 24.108 ms., avg: 24.197 ms.
Best time for 4096K FFT length: 26.477 ms., avg: 26.493 ms.
Best time for 5120K FFT length: 34.313 ms., avg: 34.461 ms.
Best time for 6144K FFT length: 41.704 ms., avg: 41.717 ms.
Best time for 7168K FFT length: 52.009 ms., avg: 52.204 ms.
Best time for 8192K FFT length: 58.487 ms., avg: 58.694 ms.
Timing FFTs using 2 threads.
Best time for 768K FFT length: 2.290 ms., avg: 2.317 ms.
Best time for 896K FFT length: 2.731 ms., avg: 2.791 ms.
Best time for 1024K FFT length: 3.052 ms., avg: 3.090 ms.
Best time for 1280K FFT length: 4.023 ms., avg: 4.048 ms.
Best time for 1536K FFT length: 4.788 ms., avg: 4.831 ms.
Best time for 1792K FFT length: 5.778 ms., avg: 5.821 ms.
Best time for 2048K FFT length: 6.396 ms., avg: 6.426 ms.
Best time for 2560K FFT length: 8.257 ms., avg: 8.274 ms.
Best time for 3072K FFT length: 10.028 ms., avg: 10.065 ms.
Best time for 3584K FFT length: 12.472 ms., avg: 12.521 ms.
Best time for 4096K FFT length: 13.687 ms., avg: 13.737 ms.
Best time for 5120K FFT length: 17.792 ms., avg: 17.861 ms.
Best time for 6144K FFT length: 21.578 ms., avg: 21.615 ms.
Best time for 7168K FFT length: 26.648 ms., avg: 26.676 ms.
Best time for 8192K FFT length: 30.141 ms., avg: 30.170 ms.
Timing FFTs using 3 threads.
Best time for 768K FFT length: 1.676 ms., avg: 1.709 ms.
Best time for 896K FFT length: 1.894 ms., avg: 1.945 ms.
Best time for 1024K FFT length: 2.170 ms., avg: 2.206 ms.
Best time for 1280K FFT length: 2.914 ms., avg: 2.937 ms.
Best time for 1536K FFT length: 3.483 ms., avg: 3.515 ms.
Best time for 1792K FFT length: 4.155 ms., avg: 4.197 ms.
Best time for 2048K FFT length: 4.662 ms., avg: 4.684 ms.
Best time for 2560K FFT length: 6.103 ms., avg: 6.179 ms.
Best time for 3072K FFT length: 7.307 ms., avg: 7.447 ms.
Best time for 3584K FFT length: 9.062 ms., avg: 9.134 ms.
Best time for 4096K FFT length: 9.971 ms., avg: 10.159 ms.
Best time for 5120K FFT length: 12.935 ms., avg: 12.969 ms.
Best time for 6144K FFT length: 15.611 ms., avg: 15.709 ms.
Best time for 7168K FFT length: 19.020 ms., avg: 19.099 ms.
Best time for 8192K FFT length: 21.643 ms., avg: 21.699 ms.
Timing FFTs using 4 threads.
Best time for 768K FFT length: 1.391 ms., avg: 1.435 ms.
Best time for 896K FFT length: 1.591 ms., avg: 1.639 ms.
Best time for 1024K FFT length: 1.864 ms., avg: 1.909 ms.
Best time for 1280K FFT length: 2.523 ms., avg: 2.560 ms.
Best time for 1536K FFT length: 3.104 ms., avg: 3.148 ms.
Best time for 1792K FFT length: 3.696 ms., avg: 3.733 ms.
Best time for 2048K FFT length: 4.228 ms., avg: 4.254 ms.
Best time for 2560K FFT length: 5.492 ms., avg: 5.579 ms.
Best time for 3072K FFT length: 6.590 ms., avg: 6.664 ms.
Best time for 3584K FFT length: 8.015 ms., avg: 8.071 ms.
Best time for 4096K FFT length: 9.052 ms., avg: 9.101 ms.
Best time for 5120K FFT length: 11.319 ms., avg: 11.392 ms.
Best time for 6144K FFT length: 13.594 ms., avg: 13.647 ms.
Best time for 7168K FFT length: 16.478 ms., avg: 16.639 ms.
Best time for 8192K FFT length: 18.430 ms., avg: 18.500 ms.
Best time for 61 bit trial factors: 2.269 ms.
Best time for 62 bit trial factors: 2.278 ms.
Best time for 63 bit trial factors: 3.755 ms.
Best time for 64 bit trial factors: 3.758 ms.
Best time for 65 bit trial factors: 3.746 ms.
Best time for 66 bit trial factors: 3.720 ms.
Best time for 67 bit trial factors: 3.721 ms.
Best time for 75 bit trial factors: 3.908 ms.
Best time for 76 bit trial factors: 3.906 ms.
Best time for 77 bit trial factors: 3.889 ms.[/code]

4.2MHz DDR3-2400

[code][Mon Feb 4 22:51:57 2013]
Compare your results to other computers at http://www.mersenne.org/report_benchmarks
Intel(R) Core(TM) i5-3570K CPU @ 3.40GHz
CPU speed: 3555.70 MHz, 4 cores
CPU features: Prefetch, SSE, SSE2, SSE4, AVX
L1 cache size: 32 KB
L2 cache size: 256 KB, L3 cache size: 6 MB
L1 cache line size: 64 bytes
L2 cache line size: 64 bytes
TLBS: 64
Prime95 32-bit version 27.9, RdtscTiming=1
Best time for 768K FFT length: 4.904 ms., avg: 4.924 ms.
Best time for 896K FFT length: 6.236 ms., avg: 6.270 ms.
Best time for 1024K FFT length: 6.745 ms., avg: 6.772 ms.
Best time for 1280K FFT length: 8.857 ms., avg: 8.881 ms.
Best time for 1536K FFT length: 10.617 ms., avg: 10.645 ms.
Best time for 1792K FFT length: 12.843 ms., avg: 12.854 ms.
Best time for 2048K FFT length: 14.107 ms., avg: 14.143 ms.
Best time for 2560K FFT length: 18.321 ms., avg: 18.336 ms.
Best time for 3072K FFT length: 22.189 ms., avg: 22.225 ms.
Best time for 3584K FFT length: 27.728 ms., avg: 27.766 ms.
Best time for 4096K FFT length: 30.427 ms., avg: 30.446 ms.
Best time for 5120K FFT length: 39.471 ms., avg: 39.544 ms.
Best time for 6144K FFT length: 47.990 ms., avg: 48.002 ms.
Best time for 7168K FFT length: 59.842 ms., avg: 59.850 ms.
Best time for 8192K FFT length: 67.388 ms., avg: 67.434 ms.
Timing FFTs using 2 threads.
Best time for 768K FFT length: 2.559 ms., avg: 2.594 ms.
Best time for 896K FFT length: 3.135 ms., avg: 3.163 ms.
Best time for 1024K FFT length: 3.485 ms., avg: 3.520 ms.
Best time for 1280K FFT length: 4.609 ms., avg: 4.635 ms.
Best time for 1536K FFT length: 5.452 ms., avg: 5.483 ms.
Best time for 1792K FFT length: 6.586 ms., avg: 6.626 ms.
Best time for 2048K FFT length: 7.281 ms., avg: 7.309 ms.
Best time for 2560K FFT length: 9.392 ms., avg: 9.409 ms.
Best time for 3072K FFT length: 11.395 ms., avg: 11.467 ms.
Best time for 3584K FFT length: 14.199 ms., avg: 14.223 ms.
Best time for 4096K FFT length: 15.589 ms., avg: 15.686 ms.
Best time for 5120K FFT length: 20.299 ms., avg: 20.399 ms.
Best time for 6144K FFT length: 24.562 ms., avg: 24.637 ms.
Best time for 7168K FFT length: 30.487 ms., avg: 30.548 ms.
Best time for 8192K FFT length: 34.428 ms., avg: 34.502 ms.
Timing FFTs using 3 threads.
Best time for 768K FFT length: 1.876 ms., avg: 1.904 ms.
Best time for 896K FFT length: 2.186 ms., avg: 2.211 ms.
Best time for 1024K FFT length: 2.424 ms., avg: 2.447 ms.
Best time for 1280K FFT length: 3.249 ms., avg: 3.270 ms.
Best time for 1536K FFT length: 3.855 ms., avg: 3.884 ms.
Best time for 1792K FFT length: 4.686 ms., avg: 4.723 ms.
Best time for 2048K FFT length: 5.163 ms., avg: 5.197 ms.
Best time for 2560K FFT length: 6.712 ms., avg: 6.794 ms.
Best time for 3072K FFT length: 8.138 ms., avg: 8.193 ms.
Best time for 3584K FFT length: 10.037 ms., avg: 10.086 ms.
Best time for 4096K FFT length: 11.069 ms., avg: 11.120 ms.
Best time for 5120K FFT length: 14.305 ms., avg: 14.358 ms.
Best time for 6144K FFT length: 17.278 ms., avg: 17.341 ms.
Best time for 7168K FFT length: 21.281 ms., avg: 21.332 ms.
Best time for 8192K FFT length: 24.067 ms., avg: 24.161 ms.
Timing FFTs using 4 threads.
Best time for 768K FFT length: 1.526 ms., avg: 1.604 ms.
Best time for 896K FFT length: 1.724 ms., avg: 1.766 ms.
Best time for 1024K FFT length: 2.000 ms., avg: 2.026 ms.
Best time for 1280K FFT length: 2.688 ms., avg: 2.725 ms.
Best time for 1536K FFT length: 3.248 ms., avg: 3.310 ms.
Best time for 1792K FFT length: 3.861 ms., avg: 3.947 ms.
Best time for 2048K FFT length: 4.377 ms., avg: 4.439 ms.
Best time for 2560K FFT length: 5.732 ms., avg: 5.844 ms.
Best time for 3072K FFT length: 6.937 ms., avg: 7.027 ms.
Best time for 3584K FFT length: 8.367 ms., avg: 8.460 ms.
Best time for 4096K FFT length: 9.497 ms., avg: 9.542 ms.
Best time for 5120K FFT length: 11.988 ms., avg: 12.062 ms.
Best time for 6144K FFT length: 14.427 ms., avg: 14.502 ms.
Best time for 7168K FFT length: 17.489 ms., avg: 17.547 ms.
Best time for 8192K FFT length: 19.733 ms., avg: 19.795 ms.
Best time for 61 bit trial factors: 2.530 ms.
Best time for 62 bit trial factors: 2.661 ms.
Best time for 63 bit trial factors: 4.381 ms.
Best time for 64 bit trial factors: 4.388 ms.
Best time for 65 bit trial factors: 4.370 ms.
Best time for 66 bit trial factors: 4.341 ms.
Best time for 67 bit trial factors: 4.338 ms.
Best time for 75 bit trial factors: 4.559 ms.
Best time for 76 bit trial factors: 4.556 ms.
Best time for 77 bit trial factors: 4.539 ms.[/code]

Sot it's significantly faster overclocked, but only if the RAM is set to DDR3-1333, unless I've made a mistake somehow.

The "overclocked" 2400 isn't actually overclocked.

edit: an increase of 7% at 3072K FFT length

[QUOTE=Mr. P-1;327590]So it's significantly faster overclocked, but only if the RAM is set to DDR3-1333, unless I've made a mistake somehow.[/QUOTE]

Thanks. Interestingly, the OC speedup for 4-thread appears to be close to 0.

[QUOTE=ewmayer;327612]Thanks. Interestingly, the OC speedup for 4-thread appears to be close to 0.[/QUOTE]

I hadn't even looked at the 4-thread results. My use case will be four separate workers doing P-1 using 2560K or larger FFTs, so that's what I looked at.

[QUOTE=Mr. P-1;327321]
1. Will running 24/7 for years with all cores at 100% at these kinds of speeds and temperatures damage or significantly reduce the lifespan of my processor?
[/QUOTE]
My i7 620M has been running between 95 and 105 C for the last 2 1/2 years, usually at least 12 hours a day. As I often forgot to take out the batteries, the second set of them is nearing end-of-life. Apart from that, no break-downs.

It can go well for quite some time ...

[QUOTE=Bdot;328381]My i7 620M has been running between 95 and 105 C for the last 2 1/2 years, usually at least 12 hours a day. As I often forgot to take out the batteries, the second set of them is nearing end-of-life. Apart from that, no break-downs.

It can go well for quite some time ...[/QUOTE]

It has been discussed elsewhere in the forum, but my i7-920 runs about 85C 24/7 and has been for several years. I may be shortening the lifespan of the chip but it will be obsolete by the time real damage is done. my i5-3570k runs btwn 70 and 80 C on the stock intel cooler.

OK, seems like I misunderstood what the UEFI was telling me about my RAM speed. I had assumed that with the RAM frequency set to "auto", it would be 1333, because that was the number it showed next to the setting.

I've just tried explicitly setting the RAM frequency to 1333 with the UEFI otherwise in its default configuration. Here are my benchmarks:

[code][Sun Feb 17 11:58:40 2013]
Compare your results to other computers at http://www.mersenne.org/report_benchmarks
Intel(R) Core(TM) i5-3570K CPU @ 3.40GHz
CPU speed: 3556.71 MHz, 4 cores
CPU features: Prefetch, SSE, SSE2, SSE4, AVX
L1 cache size: 32 KB
L2 cache size: 256 KB, L3 cache size: 6 MB
L1 cache line size: 64 bytes
L2 cache line size: 64 bytes
TLBS: 64
Prime95 64-bit version 27.9, RdtscTiming=1
Best time for 768K FFT length: 4.445 ms., avg: 4.478 ms.
Best time for 896K FFT length: 5.446 ms., avg: 5.472 ms.
Best time for 1024K FFT length: 6.060 ms., avg: 6.119 ms.
Best time for 1280K FFT length: 7.728 ms., avg: 7.744 ms.
Best time for 1536K FFT length: 9.509 ms., avg: 9.541 ms.
Best time for 1792K FFT length: 11.357 ms., avg: 11.375 ms.
Best time for 2048K FFT length: 12.689 ms., avg: 12.701 ms.
Best time for 2560K FFT length: 16.087 ms., avg: 16.109 ms.
Best time for 3072K FFT length: 20.037 ms., avg: 20.077 ms.
Best time for 3584K FFT length: 24.339 ms., avg: 24.364 ms.
Best time for 4096K FFT length: 27.206 ms., avg: 27.225 ms.
Best time for 5120K FFT length: 35.312 ms., avg: 35.338 ms.
Best time for 6144K FFT length: 42.442 ms., avg: 42.468 ms.
Best time for 7168K FFT length: 51.318 ms., avg: 51.345 ms.
Best time for 8192K FFT length: 59.488 ms., avg: 59.521 ms.
Timing FFTs using 2 threads.
Best time for 768K FFT length: 2.366 ms., avg: 2.382 ms.
Best time for 896K FFT length: 2.789 ms., avg: 2.813 ms.
Best time for 1024K FFT length: 3.148 ms., avg: 3.170 ms.
Best time for 1280K FFT length: 4.050 ms., avg: 4.068 ms.
Best time for 1536K FFT length: 4.916 ms., avg: 4.956 ms.
Best time for 1792K FFT length: 5.881 ms., avg: 5.913 ms.
Best time for 2048K FFT length: 6.571 ms., avg: 6.627 ms.
Best time for 2560K FFT length: 8.348 ms., avg: 8.425 ms.
Best time for 3072K FFT length: 10.374 ms., avg: 10.418 ms.
Best time for 3584K FFT length: 12.506 ms., avg: 12.536 ms.
Best time for 4096K FFT length: 14.009 ms., avg: 14.072 ms.
Best time for 5120K FFT length: 18.185 ms., avg: 18.202 ms.
Best time for 6144K FFT length: 21.847 ms., avg: 21.892 ms.
Best time for 7168K FFT length: 26.304 ms., avg: 26.342 ms.
Best time for 8192K FFT length: 30.656 ms., avg: 30.703 ms.
Timing FFTs using 3 threads.
Best time for 768K FFT length: 1.644 ms., avg: 1.661 ms.
Best time for 896K FFT length: 1.953 ms., avg: 1.982 ms.
Best time for 1024K FFT length: 2.222 ms., avg: 2.256 ms.
Best time for 1280K FFT length: 2.906 ms., avg: 2.936 ms.
Best time for 1536K FFT length: 3.552 ms., avg: 3.604 ms.
Best time for 1792K FFT length: 4.252 ms., avg: 4.298 ms.
Best time for 2048K FFT length: 4.771 ms., avg: 4.813 ms.
Best time for 2560K FFT length: 6.136 ms., avg: 6.221 ms.
Best time for 3072K FFT length: 7.478 ms., avg: 7.543 ms.
Best time for 3584K FFT length: 9.175 ms., avg: 9.251 ms.
Best time for 4096K FFT length: 10.330 ms., avg: 10.371 ms.
Best time for 5120K FFT length: 13.268 ms., avg: 13.348 ms.
Best time for 6144K FFT length: 15.913 ms., avg: 16.012 ms.
Best time for 7168K FFT length: 18.873 ms., avg: 18.921 ms.
Best time for 8192K FFT length: 21.820 ms., avg: 21.886 ms.
Timing FFTs using 4 threads.
Best time for 768K FFT length: 1.312 ms., avg: 1.335 ms.
Best time for 896K FFT length: 1.617 ms., avg: 1.639 ms.
Best time for 1024K FFT length: 1.898 ms., avg: 1.920 ms.
Best time for 1280K FFT length: 2.533 ms., avg: 2.570 ms.
Best time for 1536K FFT length: 3.145 ms., avg: 3.186 ms.
Best time for 1792K FFT length: 3.752 ms., avg: 3.804 ms.
Best time for 2048K FFT length: 4.290 ms., avg: 4.330 ms.
Best time for 2560K FFT length: 5.541 ms., avg: 5.608 ms.
Best time for 3072K FFT length: 6.691 ms., avg: 6.743 ms.
Best time for 3584K FFT length: 8.082 ms., avg: 8.167 ms.
Best time for 4096K FFT length: 9.217 ms., avg: 9.269 ms.
Best time for 5120K FFT length: 11.735 ms., avg: 11.782 ms.
Best time for 6144K FFT length: 14.091 ms., avg: 14.163 ms.
Best time for 7168K FFT length: 16.496 ms., avg: 16.577 ms.
Best time for 8192K FFT length: 18.689 ms., avg: 18.806 ms.
Best time for 61 bit trial factors: 1.961 ms.
Best time for 62 bit trial factors: 2.016 ms.
Best time for 63 bit trial factors: 2.276 ms.
Best time for 64 bit trial factors: 2.306 ms.
Best time for 65 bit trial factors: 2.730 ms.
Best time for 66 bit trial factors: 3.165 ms.
Best time for 67 bit trial factors: 3.138 ms.
Best time for 75 bit trial factors: 3.054 ms.
Best time for 76 bit trial factors: 3.047 ms.
Best time for 77 bit trial factors: 3.047 ms.[/code]

This is significantly faster than the "auto" RAM setting, which was identical to the "2400" setting. The obvious conclusion is that "auto" means "2400"

The other thing to notice is that there is essentially no gain in speed by running at 4.2MHz. The only thing that makes a difference is the RAM setting: "1333" is faster than the "2400".

I'm putting the alleged frequencies in quotes, because in truth, I have no way of knowing what speed the memory is being run at. One hypothesis is that the memory is running at the same speed on both settings, and the performance improvement of "1333" over "2400" is due to the former's tighter latency settings. I don't have time to test this right now, but I will do later, and report back.

In the mean time, if anyone has any other ideas about what might be happening, I would appreciate the input.

[QUOTE=Mr. P-1;329866]In the mean time, if anyone has any other ideas about what might be happening, I would appreciate the input.[/QUOTE]

Your "4.2MHz DDR3-2400" run was actually a 3.5 GHz run as it was already [URL="http://www.mersenneforum.org/showpost.php?p=327591&postcount=16"]stated above:[/URL]

[QUOTE=Mr. P-1;329866]
4.2MHz DDR3-2400

[Mon Feb 4 22:51:57 2013]
Compare your results to other computers at [URL]http://www.mersenne.org/report_benchmarks[/URL]
Intel(R) Core(TM) i5-3570K CPU @ 3.40GHz
CPU speed: 3555.70 MHz, 4 cores
[/QUOTE]

You can use [URL]http://www.cpuid.com/softwares/cpu-z.html[/URL] to find out what speed your memory is running at.

[QUOTE=garo;329878]You can use [URL]http://www.cpuid.com/softwares/cpu-z.html[/URL] to find out what speed your memory is running at.[/QUOTE]

This appears to be Windows only. I only have Linux.

[QUOTE=Ralf Recker;329868]Your "4.2MHz DDR3-2400" run was actually a 3.5 GHz run as it was already [URL="http://www.mersenneforum.org/showpost.php?p=327591&postcount=16"]stated above:[/URL][/QUOTE]

Sorry I missed that.

I'm sure that, when I set the multiplier to 42 (or higher), I really was overclocking - my temperatures (and instability) indicated as much. Perhaps I mixed up which benchmark was which.

I'm still struggling to find time. When I do, I'll redo all the benchmarks.

[QUOTE=Mr. P-1;330092]This appears to be Windows only. I only have Linux.[/QUOTE]
[URL]http://diznix.com/2012/01/07/linux-equivalent-of-cpu-z/[/URL] ?

[QUOTE=science_man_88;330114][URL]http://diznix.com/2012/01/07/linux-equivalent-of-cpu-z/[/URL] ?[/QUOTE]

Thanks. Turns out I already have dmidecode installed. When I have the time to return to this, I'll play around with it.