RE: kernel 2.4.9-34 ia64 bugfix list?
Daniel Kidger <[email protected]> Thu, 13 Jun 2002 13:49:35 +0100
| Newsgroups | gmane.linux.redhat.ia64.general |
|---|---|
| Message-ID | <010C86D15E4D1247B9A5DD312B7F5AA74D2DD9@stegosaurus.bristol.quadrics.com> |
>For the floating point assist fault, take a look at this document. It >shouldn't be a problem. >http://h21007.www2.hp.com/dspp/tech/tech_TechDocumentDetailPage_IDX/1,1701, 165,00.html yes - but note that you get "floating point assist faults" when for example your application code has the odd underflow. A side-effect is that messages get written to the console and even /var/log/messages (caused just by normal round-off in a scientific application!). The result is the code goes slowly - in one case of ours the code run 13 times slower than it should. If you set the flush-to-zero flag in the FPU, it runs at full speed again. You can do this either by an assember call or options like -ftz to the intel itanium compilers. Yours, Daniel. -------------------------------------------------------------- Dr. Dan Kidger, Quadrics Ltd. [email protected] One Bridewell St., Bristol, BS1 2AA, UK 0117 915 5505 ----------------------- www.quadrics.com -------------------- -----Original Message----- From: FISHER,JOE (HP-Loveland,ex1) [mailto:[email protected]] Sent: 12 June 2002 19:40 To: '[email protected]' Subject: RE: kernel 2.4.9-34 ia64 bugfix list? -----Original Message----- From: Rob Myers [mailto:[email protected]] Sent: Wednesday, June 12, 2002 12:14 PM To: [email protected] Subject: kernel 2.4.9-34 ia64 bugfix list? hello- i'm currently running Linux 2.4.9-31smp on my redhat7.1 ia64 box. i was looking into upgrading to redhat's 2.4.9-34 kernel, but i cannot seem to find a list of ia64 bugs that are fixed by it. does anyone know of such a list? i'm currently having random oopses and mapped out banks of memory with this machine so i dont want to stray from a supported redhat configuration. also, i get lots of error messages about floating point assist faults. for example: fdtd(21172): floating-point assist fault at ip 40000000000686e1 what are the ramifications of this "fault"? thanks for any pointers, rob. _______________________________________________ ia64-list mailing list [email protected] https://listman.redhat.com/mailman/listinfo/ia64-list _______________________________________________ ia64-list mailing list [email protected] https://listman.redhat.com/mailman/listinfo/ia64-list