Processors
Intel® Processors, Tools, and Utilities
14368 Discussions

Simple instructions for freezing a Skylake Processor.

HStok
Novice
11,882 Views

The people at the community over at http://www.mersenneforum.org http://www.mersenneforum.org have found what appears to be a bug in the new Skylake architecture that can freeze any system that has a Skylake processor.

The Mersenne community are a bunch of mathematicians and other folks that use Intel processors to find record prime numbers. They have found all the record prime numbers of the last 20 years.

The main website of the community is http://www.mersenne.org http://www.mersenne.org where they keep track of all progress in searching for a new record prime number.

Owners of Skylake systems have found out that the software package that they use to hunt for prime numbers will freeze their system if they use particular settings. Since this bug is reproducible and has been confirmed on motherboards of many different suppliers and with RAM modules of different suppliers the bug seems to be tied to the processor architecture. The bug is reproducible under Windows and Linux.

This software works perfectly normal on all other Intel processors of past generations.

Steps to freeze your Skylake system:

- Download and install Prime95 for Windows on a Skylake system from the website at http://www.mersenne.org/download/ http://www.mersenne.org/download/

(If you want to familiarize yourself with the software use the readme, a background in math will be helpful, but is not needed.)

- In the menu go to 'Advanced | Test' and fill in the number 14942209 in the box labeled 'Exponent to test'

- Let the program run for some time and at some point, minutes or hours, the system will freeze.

The prime95 software does multiplications of extreme high numbers using the Fast Fourier Transformation. The implementation of these FFT's in prime95 is handcoded in assembly by George Woltman, and is the most efficient implementation available. This project runs for more than 20 years now and has always been carefully maintained. Tens of thousands of machines run this software 24 hours a day.

For optimization, different FFT sizes have been implemented in Prime95, only the FFT with length 768K freezes the Skylake.

It is my fear that like the infamous FDIV bug this issue will require a new stepping and a product recall, since this has security implications as well.

If you have a Skylake system I invite you to try out the steps above. Please post your findings here and in the mersenneforum at http://mersenneforum.org/showthread.php?t=20714 http://mersenneforum.org/showthread.php?t=20714

Regards,

34 Replies
Anonymous
Not applicable
7,071 Views

Hi Henk_NL,

I would need more information about your system configuration in order to replicate the issue. Please download and run our Intel® System Support Utility and Intel® Processor Diagnostic Tool. Send me both results.

Send me pictures (screenshots) of the errors that you are getting.

Intel® System Support Utility

https://downloadcenter.intel.com/download/25293/Intel-System-Support-Utility Download Intel® System Support Utility

Intel® Processor Diagnostic Tool (64-bit)

https://downloadcenter.intel.com/download/19792/Intel-Processor-Diagnostic-Tool-64-bit https://downloadcenter.intel.com/download/19792/Intel-Processor-Diagnostic-Tool-64-bit-

Regards,

 

Mike C
HStok
Novice
7,071 Views

Hi Mike,

The PEG/SVE/Security Center of Excellence (SeCoE), Intel Product Security Incident Response Team is also working on this issue, but feel free to join or beat them.

Fint the requested information below. As is stated in the forum at http://mersenneforum.org/showthread.php?t=20714 http://mersenneforum.org/showthread.php?t=20714 the problem is related to hyperthreading and the use of CPUsupportsFMA3. Overclocking, underclocking or just running at stock speed does not influence the outcome of the program

---------------------------

--- Testing Processor 1 ---

---------------------------

--- IPDT64 - rev 2.20.0.0.W.MP ---

--- Start Time: 12/16/2015 22:42:52---

--- Skipping Config ---

--- Reading CPU Manufacturer ---

Expected --> GenuineIntel

Detected --> GenuineIntel

Found --- Genuine Intel Processor ---

--- Temperature Test ---

Temperature Test Passed!!!

Temperature = 79 degrees C below maximum.

--- Reading Brand String ---

Detected Brand String:

Intel Core i7-6700K 4.00GHz

Brand String Test Passed!!!

--- Reading CPU Frequency ---

Expected CPU Frequency is --> 4.00

Detected CPU Frequency is --> 7.4008

CPU Frequency Test Passed!!!

Expected frequency - The highest frequency at which the tested processor was manufactured to operate

Detected frequency - The frequency at which the tested processor is currently operating

Power management modes can create marginally higher or lower detected frequency

than expected frequency. Small variations in clock frequencies are common.

--- FSB NOT Supported on this Processor ---

--- Running Base Clock test ---

Detected Base Clock --> 134

Base Clock test Pass ---

..QPI rate Test not supported..

..Skipping QPI rate Test..

Skipping QPI rate Test

--- Running Floating Point test ---

Million Floating Points per Second, MFLOPS --> 561.6

Floating Point Test Pass ---

--- Running Prime Number Generation Test ---

Operation Per Second--> 8.63953e+006

Prime Number Generation Test Pass ---

--- Reading Cache Size ---

- Detected L1 Data Cache Size --> 4 x 32

- Detected L1 Inst Cache Size --> 4 x 32

- Detected L2 Cache Size --> 1024

- Detected L3 Cache Size --> 8192

Cache Size Test Passed!!!

--- Determining MMX - SSE capabilities ---

--- CPU FEATURES DETECTION FOR ---

--- MMX SSE ---

MMX - MMX Supported --> Yes

SSE - SSE Supported --> Yes

SSE2 - SSE2 Supported --> Yes

SSE3 - SSE3 Supported --> Yes

SSSE3 - SSSE3 Supported --> Yes

SSE4.1 - SSE4.1 Supported --> Yes

SSE4.2 - SSE4.2 Supported --> Yes

--- MMX SSE - capabilities check complete ---

MMX Test Result --- PASS

SSE Test Result --- PASS

SSE2 Test Result --- PASS

SSE3 Test Result --- PASS

SSSE3 Test Result --- PASS

SSE4.1 Test Result --- PASS

SSE4.2 Test Result --- PASS

MMX SSE Testing Passed !!

--- Determining AVX AES PCLMULQDQ capabilities ---

--- CPU FEATURES DETECTION FOR ---

--- AVX/AES/PCLMULQDQ ---

AVX - Advanced Vector Extensions Supported --> Yes

AVX OS Support - AVX Operating System Supported --> Yes

AES - Advanced Encryption Standard Supported --> Yes

PCLMULQDQ - Polys Carry-Less Multiply Supported --> Yes

--- AVX AES PCLMULQDQ capabilities check complete ---

AVX Compare Test Result --- PASS

AES Test Result --- PASS

PCLMULQDQ Test Result --- PASS

AVX AES PCLMULQDQ Testing Passed !!

--- Reading Memory Size ---

Detected Memory Size is --> 32.00GB

--- Integrated Memory Controller Stress Test ---

--- Integrated Memory Controller Stress Test Pass!!! ---

Integrated Memory Controller Test Pass!!!

..Platform Controller Hub Test not supported curent chipset..

..Skipping Platform Controller Hub Test..

Skipping Platform Controller Hub Test

--- Querying for Intel(R) Integrated Graphics Device (IGD) ---

..Detected 8086 as Vendor ID on Device 2 on Intel(R) processor..

..Intel(R) Integrated Graphics Device Presence Detection Passed..

..2D Graphics Visual Display Passed..

..Graphics Visual Display Passed..

..Rotating Display Passed..

--- CPU Load ---

--- Load Level = 8

CPU Load Passed!!!

--- Temperature Test ---

Temperature Test Passed!!!

Temperature = 71 degrees C below maximum.

--- Test End Time: 12/16/2015 22:46:51---

System Information

------------------

Processor Name: Intel(R) Core(TM) i7-6700K CPU @ 4.00GHz

Processor Information: Intel64 Family 6 Model 94 Stepping 3

Number of Physical Cores: 4

Number of Logical Cores: 8

Installed System Memory: 32 GB

Operating System: Microsoft Windows 7 Professional 64-Bit

Graphics Information: Intel(R) HD Graphics 530

System Product: Z170 OC FORMULA

System BIOS: P1.70

HStok
Novice
7,071 Views
0 Kudos
HStok
Novice
7,071 Views

When I registered here as a member, only the second attempt got me an email to my address that I had to use to confirm the validity of my account. More people from the Mersenneforum have tried to join but failed, because they did not receive a confirmation link in their email box. On behalf of future user 'ATH' I post this clarification on how to obtain the freezing of the Skylake system:

In order to replicate the error make sure hyperthreading is enabled on a Skylake 6700K.

Download Prime95 version 27.9, as the error seems to occur more frequently here:

ftp://mersenne.org/gimps/p95v279.win64.zip ftp://mersenne.org/gimps/p95v279.win64.zip

The error also occurs in the newest version 28.7:

ftp://mersenne.org/gimps/p95v287.win64.zip ftp://mersenne.org/gimps/p95v287.win64.zip

but if you try this you need to create a file called "local.txt" in the directory with the line:

CpuSupportsFMA3=0

because version 28.7 uses AVX2/FMA3 by default and the error seems to occur only with AVX.

Start Prime95.exe and choose "Options" - "Torture test", and fill out the popup box like this:

http://www.bilder-hochladen.net/files/hb0a-9y-635a.jpeg http://www.bilder-hochladen.net/files/hb0a-9y-635a.jpeg

except change the bottom one "Time to run each FFT size (in minutes)" to like 120min or more, however long you want to run the test.

In summary the error occurs only with HT on and all 8 virtual threads running tests and only with AVX. The error is currently only experienced with 768 FFT (Fast Fourier transform) size in Prime95.

0 Kudos
CHals
Novice
7,071 Views

To put on the table, signing up to this forum involves jumping through a few hoops.

Several people who have valuable information and want to share on this matter have had difficulty joining.

Please see http://mersenneforum.org/showthread.php?t=20714 http://mersenneforum.org/showthread.php?t=20714 for more details.

Kindest regards.

Anonymous
Not applicable
7,071 Views

Hi Henk_NL,

I am going to work on this, I will let you the results.

Regards,

Mike C

0 Kudos
MScri2
Beginner
7,071 Views

I can reproduce this issue as well. In addition to that, I and others over at this thread: http://www.tomshardware.com/forum/id-2830772/skylake-build-randomly-freezing-crashing.html http://www.tomshardware.com/forum/id-2830772/skylake-build-randomly-freezing-crashing.html have been battling an issue for months now, where the system completely hangs when idle. Anywhere from a few hours being idle, to several days. We've tried RMA'ing every piece of hardware except the CPU, and tried every setting possible, including running RAM at the default 2133MHz, but so far nothing has resolved the issue. There is some underlying platform issue here.

0 Kudos
Anonymous
Not applicable
7,071 Views

Hi Henk_NL,

I noted you are using running the processor at 7.4008MHz. The base frequency of the Intel® Core™ i7-6700K is 4.0MHz. Are you getting the same results using the stock settings of the processor and using memories of 2133MHz at 1.25V.

Regards,

 

Mike C
0 Kudos
TLier
Beginner
7,071 Views
0 Kudos
HStok
Novice
7,071 Views

The results that I posted were not mine but one of the other people who stumbled upon this and posted their results in the mersenne forum.

Indeed, the results obtained are the same regardless of systems having been overclocked or not, or even are underclocked. The fatal combination seems to be:

- Skylake AND

- hyperthreading AND

- CpuSupportsFMA3=0. (only needed if you use the latest version of prime95, since previous version stem from before the introduction use FMA3 anyway)

There are people contemplating writing a piece of software based on prime95 that will simplify freezing the Skylake based on just a few instructions. Very scary indeed and further analysis of the downloadable code is required

0 Kudos
Anonymous
Not applicable
7,071 Views

Hi Henk_NL,

Thank you for your feedback, our engineer department is working on your case now.

Regards,

 

Mike C
0 Kudos
HStok
Novice
7,071 Views

Hi,

See http://www.mersenneforum.org/showthread.php?t=20714&page=19 768k Skylake Problem/Bug - Page 19 - mersenneforum.org

These two things might be related. Anyway it certainly brings back the memories of the FDIV bug.

I saw the bug report I filed was categorized as 'performance issue'. It may soon seriously affect the performance of the Intel stock price on the stocks exchange, but I guess such an option does not exist in the drop down menu.

0 Kudos
HStok
Novice
7,071 Views

Then of course it may as well be two separate issues as well.

0 Kudos
CHals
Novice
7,071 Views

Hi Mike.C. from Intel.

I do hope your engineering department is working this.

You might want to get your public and investor relations departments on this really soon now....

0 Kudos
idata
Employee
7,071 Views

Hello All,

Intel has identified an issue that potentially affects the 6th Gen Intel® Core™ family of products. This issue only occurs under certain complex workload conditions, like those that may be encountered when running applications like Prime95. In those cases, the processor may hang or cause unpredictable system behavior. Intel has identified and released a fix and is working with external business partners to get the fix deployed through BIOS.

CHals
Novice
7,071 Views

Excellent Mr. Solano. Thank you for the update.

If you could share, what MCU, CSME and/or BIOS version numbers should testers watch out for?

Please trust that those who were able to reproduce this bug will want to upgrade, and then do many more tests to ensure this has actually been fixed.

Cesar_B_Intel
Employee
7,071 Views

Hello Chris_Halsall,

Please allow some time for Intel engineers to provide you with an update on your requested information.

Regards

Caesar B_Intel.

0 Kudos
HStok
Novice
7,071 Views

This is great news to hear. I had already started working on a simple test case, so that the error would show up in a predicatable way. It will take a few more days to complete, and I might do it just as an exercise. I will not publish the details however before the update is out.

0 Kudos
Cesar_B_Intel
Employee
7,071 Views

Hello Henk_NL,

Thank you for letting us know about your tests.

Please let us know of your findings.

Regards,

Caesar B_Intel.

0 Kudos
CHals
Novice
5,722 Views

Hello Cesar Badilla

Certainly we will "allow some time" for a response. But is there any chance you could provide an estimate as to how long we should expect to wait? After all, if you (read: Intel) have a fix which is now being rolled out, you should have at least a new MCU.

Please do also note that while it was Prime95 (and _very_ observant testers) which found this bug, there are many who use compute for scientific (and financial et al) purposes which might also exhibit "certain complex workload conditions".

It would be a shame if a lot of previous computing had to be redone, just to make sure the results were correct....

0 Kudos
Reply