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 : Advanced Micro Devices - Moderated (AMD) -- Ignore unavailable to you. Want to Upgrade?

To: hmaly who wrote (68770)	1/24/2002 2:46:21 PM
From: milan0	Read Replies (1) \| Respond to of 275872

from theinquirer.net Clawhammer - more speculation here Samples at CeBIT? By Mike Magee, 24/01/2002 09:45:18 BST AN ENTERPRISING reader of the INQ has contacted the owner of the Czech site which published a SPECint chart and has asked him some pertinent questions about the up-and-coming AMD microprocessor. See Clawhammer performance projected. The Czech owner of the site that published the AMD figures told our reader the figures came from AMD's Fred Weber, who has a senior development role for Hammer technology. He asked whether Clawhammer was sampling and the Web owner said he believed it was sampling in both silicon on insulator (SOI) and on a .13 micron process, with AMD set to show off samples of the chip at the up and coming CeBIT 2002 trade fair. He also thinks that Clawhammer will be up for sale before December of this year and that it will integrate Hypertransport, and memory in its north bridge, with only the AGP controller being off the core. This last is well known, however our reader points out that chipset roadmaps from Via, SIS and ALI all indicate they will produce north bridges for Hammer too. Perhaps the onboard Clawhammer north bridge will be disable so that the three chipset manufacturers can get a look in, he speculates. µ

To: hmaly who wrote (68770)	1/24/2002 3:08:22 PM
From: Ali Chen	Read Replies (1) \| Respond to of 275872

"Don't you mean to say that even if the CPU increases by 2x, Sysmark won't increase by that much because sysmark tests the response time of the whole system." Yes, you are correct. We can see this kind of "flat" behavior on many applications, Quake for example. However, I must apologize for including hard drives in my list, and maybe polygons were a stretch too, which may create some confusion (unless you read the "increase in system clock" as the "clock in every peripheral", including disk r.p.m and MR-head clocking as well ). In some cases it is much more efficient to overclock the whole system while dropping the CPU multipler (to stay within CPU operating limit), e.g. Xilinx FPGA development software. - Ali