From ojw23@cam.ac.uk Sun Mar  4 18:59:38 2001
Date: Wed, 28 Feb 2001 19:02:18 -0000
From: Oli Wade <ojw23@cam.ac.uk>
To: Ole W. Saastad <ole@scali.no>
Cc: beowulf@beowulf.org
Subject: Re: Athlon vs. PIII

    [ The following text is in the "iso-8859-1" character set. ]
    [ Your display is set for the "US-ASCII" character set.  ]
    [ Some characters may be displayed incorrectly. ]

Yes it is a Duron. The 'model' is the key; see
http://www.sandpile.org/ia32/cpuid.htm for full CPUID details.

For K7:
---
1 0.25 m
2 0.18 m
3 0.18 m with 64 KB on-die L2 cache
4 0.18 m with 256 KB on-die L2 cache
---

1 & 2 are the original slot A Athlons. 3 = Duron (Spitfire), 4 = new Athlon
(Thunderbird), both (mostly) socket A.

Remember too that the L2 cache is exclusive.


      Oli



----- Original Message -----
From: "Cameron Harr" <charr@lnxi.com>
To: "Ole W. Saastad" <ole@scali.no>
Cc: <beowulf@beowulf.org>
Sent: Wednesday, February 21, 2001 4:32 PM
Subject: Re: Athlon vs. PIII


> I have a 1GHz Athlon and this is what it says:
>
> processor : 0
> vendor_id : AuthenticAMD
> cpu family : 6
> model : 4
> model name : AMD Athlon(tm) Processor
> stepping : 2
> cpu MHz : 1009.001
> cache size : 256 KB
> fdiv_bug : no
> hlt_bug : no
> f00f_bug : no
> coma_bug : no
> fpu : yes
> fpu_exception : yes
> cpuid level : 1
> wp : yes
> flags : fpu vme de pse tsc msr pae mce cx8 sep mtrr pge mca cmov pat
> pse36 mmx fxsr syscall mmxext 3dnowext 3dnow
> bogomips : 2011.95
>
>
> "Ole W. Saastad" wrote:
> >
> > Athlon vs. PIII again.
> >
> > It might be that /proc/cpuinfo is wrong about Athlon/Duron:
> > As suggested in several mails the processor could be a
> > Duron and not an Athlon after all. If this is the case the price
> > performance of Duron vs. PIII is very high.
> >
> > This is what /proc/cpuinfo prints:
> >
> > : ole@pc-10:ole; cat /proc/cpuinfo
> > processor       : 0
> > vendor_id       : AuthenticAMD
> > cpu family      : 6
> > model           : 3
> > model name      : AMD Athlon(tm) Processor
> > stepping        : 1
> > cpu MHz         : 807.203
> > cache size      : 64 KB
> > fdiv_bug        : no
> > hlt_bug         : no
> > sep_bug         : no
> > f00f_bug        : no
> > coma_bug        : no
> > fpu             : yes
> > fpu_exception   : yes
> > cpuid level     : 1
> > wp              : yes
> > flags           : fpu vme de pse tsc msr 6 mce cx8 sep mtrr pge 14 cmov
fcmov 17
> > psn 22 mmx 24 30 3dnow
> > bogomips        : 1608.91
> >
> > If this is true there is probably a bug in either the kernel or the cpu
> > chip.
> > I did not open the box to look inside to physically check the chip
> > myself.
> >
> > As for the pgf77 flags the suggested flags like prefetch are not a part
> > of
> > the 3.1 version of the compiler. No doubt that prefecth is yielding
> > higher
> > performance.
> >
> > Ole W Saastad
>
> --
> Cameron Harr
> Applications Engineer
> Linux NetworX Inc.
> http://www.linuxnetworx.com



_______________________________________________
Beowulf mailing list, Beowulf@beowulf.org
To change your subscription (digest mode or unsubscribe) visit http://www.beowulf.org/mailman/listinfo/beowulf
