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 : Silicon Graphics, Inc. (SGI) -- Ignore unavailable to you. Want to Upgrade?

To: Patrick Gainer who wrote (3288)	10/29/1997 11:42:00 AM
From: nesha	Read Replies (2) \| Respond to of 14451

> - the R12K is basically a clocked up R10k with a few > microarchitecture changes. If true, this puts SPECint95 > figures around 12-15. With recently released 7.2 compilers SPECint95 for 195Mhz R10k is 11.4. I don't exactly know what the performance of R12k will be, but its SPECint95 numbers will certainly exceed your estimate.

To: Patrick Gainer who wrote (3288)	10/30/1997 1:07:00 PM
From: Alexis Cousein	Respond to of 14451

>- the R12K is basically a clocked up R10k with a few > microarchitecture changes. If true, this puts SPECint95 > figures around 12-15. DEC's 21264 is intended to ship > with SPECint95 figures around 40, in the same time frame. DEC's current 'chip' SPECfp FUD numbers place the current Alpha where? And what are the published SPECfp numbers for systems? You'll find a nice factor already there. As for SPECint95, -not commenting about your projections for R12K- it fits in cache almost entirely nowadays, and that's why all these new snazzy future chips are starting to have figures skyrocketing. Don't expect that to correlate to Oracle or anything; don't expect the SPECint98 ratio between the 21164 and the 21264 (even assuming their nice 'perfect system in a cloud' for chip numbers, let alone in systems) to be the same either. We all know what a Pentium-II gives you as the multiplier if you use an '86 benchmark for 8086 processors at 4.77 MHz as the reference. Do your apps run faster by that factor nowadays?