pentium G4400

[Frantisek Kluknavsky]

On 05/26/2016 07:24 PM, Torbjörn Granlund wrote:
> Frantisek Kluknavsky <fkluknav at redhat.com> writes:
> 
>   on a Pentium G4400, GMP 6.1.0 configured with --enable-fat crashes
>   because of an illegal instruction:
>   
>   
>   Program received signal SIGILL, Illegal instruction.
>   0x00007ffff7501514 in __gmpn_submul_1_coreihwl ()
>       at tmp-coreihwl_submul_1.s:165
>   165		jmp	.Llo3
>   (gdb) bt full
>   #0  0x00007ffff7501514 in __gmpn_submul_1_coreihwl ()
>       at tmp-coreihwl_submul_1.s:165
>   
>   
>   I can not reproduce it myself, it is a report from a different user.
>   
>   http://www.intel.com/content/dam/www/public/us/en/documents/specification-updates/desktop-6th-gen-core-family-spec-update.pdf
>   says there is a bug in reporting BMI support. I am not sure how exactly
>   to read the document if the bug affects G4400 and if this is the real
>   reason of the crash.
>   
>   Are you interested in working around hardware bugs?
>   
> We are, to some extent.
> 
> Please ask that someone else if a recent snapshot helps:
> 
> https://gmplib.org/download/snapshot/
> 
> And then please report back here!
> 

Hi again,

I sent packaged gmp-6.1.99-20160531 to 'the user' and he says it solves
all his crashes. Thank you very much.

Fero

-------------- next part --------------
A non-text attachment was scrubbed...
Name: signature.asc
Type: application/pgp-signature
Size: 819 bytes
Desc: OpenPGP digital signature
URL: <https://gmplib.org/list-archives/gmp-bugs/attachments/20160608/2b71426c/attachment.bin>