Silicon Investor (SI) -- The First Internet Community

STOCKTALK

We've detected that you're using an ad content blocking browser plug-in or feature. Ads provide a critical source of revenue to the continued operation of Silicon Investor. We ask that you disable ad blocking while on Silicon Investor in the best interests of our community. If you are not using an ad blocker but are still receiving this message, make sure your browser's tracking protection is set to the 'standard' level.

Politics : Formerly About Advanced Micro Devices -- Ignore unavailable to you. Want to Upgrade?

To: Elmer who wrote (69784)	8/24/1999 10:51:00 PM
From: kash johal	Read Replies (1) \| Respond to of 1573925

Elmer, Re:"Kash, I think that there is a great deal of confusion over that statement. It is unclear as to what was meant. Did it mean that Merced running HP binaries @440MHz was 90% of the 440MHz HP machine? Did they mean the Merced binaries on Merced running at 440MHz were 90% of HP binaries on HP hardware or Merced binaries at full frequency?" I agree with you that the statement was confusing and the gentleman who made it probably regrets it. Having said all that the general tone of this individual was CLEARLY negative with regards to Merced's performance- despite anyway you wish to FUD it. Same as AMD Athlons SPEC scores that you incessantly harped on for months making groundless allegations. Now they are up - you have shut up about them. I am looking forward to your comments on the Cumine SPEC scores when they happen to come out. Regards, Kash

To: Elmer who wrote (69784)	8/24/1999 11:07:00 PM
From: Steven Ivanyi	Read Replies (1) \| Respond to of 1573925

<<Re: "Frankly the poor performance of Merced at 90% of current HP technology shocked everybody. And remember this assumes that the chips meet target speeds - something that is not guranteed (just look at cumine flap)." Kash, I think that there is a great deal of confusion over that statement. It is unclear as to what was meant. Did it mean that Merced running HP binaries @440MHz was 90% of the 440MHz HP machine? Did they mean the Merced binaries on Merced running at 440MHz were 90% of HP binaries on HP hardware or Merced binaries at full frequency?>> Please explain the above. Can't understand it at all. References please. Steven

To: Elmer who wrote (69784)	8/25/1999 2:47:00 AM
From: Petz	Read Replies (1) \| Respond to of 1573925

EP, RE:<I think that there is a great deal of confusion over that statement. It is unclear as to what was meant. Did it mean that Merced running HP binaries @440MHz was 90% of the 440MHz HP machine? Did they mean the Merced binaries on Merced running at 440MHz were 90% of HP binaries on HP hardware or Merced binaries at full frequency?> I think you are being a little naive and hoping for silver linings in black clouds. First, on clock frequency, why on earth would HP compare a processor they helped develop, at a frequency which it will never run? Does it make any sense at all to use a clock frequency in a benchmark that the CPU will never see? Gimme a break. Second, the conversion to IA64 will be done for McKinley anyway and will certainly be faster than IA32 mode. If they have a Merced compiler (and they do!), they can compile SPECint and SPECfp and run it without a full OS developed for Merced. I don't believe the Merced has a special mode for running PA-RISC code, like the (slow) mode it has for running IA32 code. Whether I'm right on that or not, HP has no reason not to use the fastest operating mode and to run at the expected maximum frequency that will work. The only leg you have to stand on is compiler improvements over the next 9-12 months. Petz