Date: Sun, 10 Oct 1999 17:05:44 -0500 (CDT) From: Kevin Day <toasty@dragondata.com> To: phk@critter.freebsd.dk (Poul-Henning Kamp) Cc: dg@root.com, dgilbert@velocet.ca (David Gilbert), freebsd-bugs@FreeBSD.ORG Subject: Re: kern/14141: 3.3-RELEASE crashing often Message-ID: <199910102205.RAA38775@celery.dragondata.com> In-Reply-To: <16423.939585645@critter.freebsd.dk> from "Poul-Henning Kamp" at Oct 10, 1999 10:00:45 PM
next in thread | previous in thread | raw e-mail | index | archive | help
> >> Then I thought about it... and fpp itself should not become NULL in > >> this case... it's being incremented from some valid pointer value. > >> > >> Ideas? > > > > Smells like a hardware problem. I had a lot of problems with AMD chips > >when I did reliability testing with them. One of the problems turned out > >to be a real bug in the chip (it only worked reliably with 32MB or less of > >RAM). They are also very sensitive to heat...you might verify that the heat > >sink is properly installed and that the fan is working. > > I can sign on that petition, I have a K6-2 where which hangs when > it tried to do FP. Works fine with the FP emulator forced on. > That's pretty odd, for a while in the embedded product I'm working on we were using AMD chips, and they worked really well. CPU: AMD-K6(tm) 3D processor (337.19-MHz 586-class CPU) Origin = "AuthenticAMD" Id = 0x580 Stepping = 0 Features=0x8001bf<FPU,VME,DE,PSE,TSC,MSR,MCE,CX8,MMX> AMD Features=0x80000800<SYSCALL,3DNow!> Granted this isn't a k6-2, we had about 20 systems with K6's running, doing heavy FP, and didn't have a single lockup. If you've really found a flaw in the chip, I'm positive AMD would like to hear about it. Kevin To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-bugs" in the body of the message
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?199910102205.RAA38775>