Messages in this thread | | | Date | Fri, 15 May 1998 10:06:08 -0700 (PDT) | From | Joel Jaeggli <> | Subject | Re: How to compile a Pentium II |
| |
On Fri, 15 May 1998, Alex Buell wrote:
> H. Peter Anvin wrote: > > > Actually, the PII has an external L2 cache running at 2:1 clock > > vs. the core; the PPro has an internal L2 cache at 1:1 (faster). > > So the PII is a marketing con-trick then? I've been told the PPro is far > better. <g>
You have a couple of different issues at play here...
cpu clock speed l2 cache size and clock speed main memory clock speed size and bus width and timing (depends on chipset)
If you take my pentium pro linux box: 200 mhz ppro 256k l2 cache at 200mhz 440fx chipset and 64mb of edo running at 66mhz
versus my windows box: 233mhz pii 512k l2 cache at 120mhz 440fx and 64mb of edo running at 66mhz
versus the machine I just built for someone: 400mhz pii 512k l2 cache at 200mhz 440bx motherboard with 128mb of 7ns samsung sdram at 100mhz
The 233mhz pii is almost always just slightly faster that the ppro. the 400mhz pii will outpeform the ppro and has about double the usable memory bandwidth as a result of moving the memory timing from 60ns to less than 10 and increasing the bus speed by 1/2. In most things it's at least half again as fast, although in quake it's about double.
Until the pii xeon ships and the 450nx chipset is available you can't have more than 2 pii's in an smp machine. this is an issue because with the 450gx chipset you can have 4-6 ppro's on a board (see: alr revolution 6x6), but again the memory bandwidth is limited compared to the of lx and bx based boards, so there are some inherent trade-offs.
Off hand, for your personal workstation I'd say a pii would be better, at least I enjoy it more, mostly it comes down to whatever has the right mix of performance and cost for your application and pii's are pretty cheap...
joelja
> -- > Cheers, > Alex. > > Watch out, the NSA are everywhere. Your computer must be watched! > > /\_/\ Legalise cannabis now! > ( o.o ) Smoke some cannabis today! > > ^ < Peace, Love, Unity and Respect to all. > > - > To unsubscribe from this list: send the line "unsubscribe linux-kernel" in > the body of a message to majordomo@vger.rutgers.edu >
-------------------------------------------------------------------------- Joel Jaeggli joelja@darkwing.uoregon.edu Academic User Services consult@gladstone.uoregon.edu PGP Key Fingerprint: 1DE9 8FCA 51FB 4195 B42A 9C32 A30D 121E -------------------------------------------------------------------------- It is clear that the arm of criticism cannot replace the criticism of arms. Karl Marx -- Introduction to the critique of Hegel's Philosophy of the right, 1843.
- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.rutgers.edu
| |