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.

Technology Stocks : Intel Corporation (INTC) -- Ignore unavailable to you. Want to Upgrade?

To: Charles R who wrote (89616)	10/6/1999 7:55:00 PM
From: Elmer	Respond to of 186894

Re: "The miss penalty in CuMine will increase as core speeds ramp because of the lower hit rates due to smaller cache. So, expect the comparisons to get more in favor of Athlon as speeds ramp up. " Exactly 180 degrees backwards Charles. Intel's will scale better than Athlon because of the lower latency, higher bandwidth large on-die cache, getting larger in the future. Re: "Athlon doesn't even have a on die cache, yet....." And their presentations show large off-die L2s for next year. Intel will not stop at 256K on-die L2s. EP

To: Charles R who wrote (89616)	10/6/1999 7:59:00 PM
From: Process Boy	Read Replies (2) \| Respond to of 186894

Charles - <Athlon Pro 700: Specint - 37; Specfp - 42> Please clarify what configuration and what bus and when do you expect AMD to post these mumbers. <The miss penalty in CuMine will increase as core speeds ramp because of the lower hit rates due to smaller cache. So, expect the comparisons to get more in favor of Athlon as speeds ramp up.> ?? <And, of course, we haven't factored in the potential MHz advantage.> What potential MHz advantage? I don't believe there will be a significant, if any, MHz advantage for K7. Coppermine will scale. PB

To: Charles R who wrote (89616)	10/7/1999 12:27:00 AM
From: Haim Barad	Read Replies (1) \| Respond to of 186894

Message #89617 from Charles R at Oct 6 1999 7:47PM PB, <It looks like Coppermine will compete quite well with a "seventh generation core". I wonder what Willamette will do? > I am not sure what you and Paul are talking about. From Kash's post on the AMD thread, looks like Tench is confirming JC's rumored CuMine spec numbers. If that is true, here is what you have: CuMine 600: Specint - 29; Specfp - 25 Athlon Pro 700: Specint - 37; Specfp - 42 The miss penalty in CuMine will increase as core speeds ramp because of the lower hit rates due to smaller cache. So, expect the comparisons to get more in favor of Athlon as speeds ramp up. Athlon doesn't even have a on die cache, yet..... And, of course, we haven't factored in the potential MHz advantage. Chuck Let me get this right... Now that AMD folks are seeing (even though not officially announced scores) what CuMine is potentially scoring... now the benchmarks don't mean anything! After all... something better (larger full speed cache, more compiler optimizations, etc) is "just around the corner" "... who cares about SPEC now... we'll stay ahead in MHz!" back to the ol' song... Haim