SI
SI
discoversearch

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: milo_morai who wrote (60257)10/25/2001 4:11:12 PM
From: Win SmithRead Replies (2) | Respond to of 275872
 
I found the leakage about McKinley, it was at realworltech, not aceshardware.

Name: Nathan Brookwood (nathan@insight64.com) 10/19/01

At IDF, Intel said "Based on early measurements, today’s Itanium processor binaries expected at 1.7x on McKinley." This translates to 644 on SPECint2000, given the 379 result for the HP rx46100 posted at SPEC.org.

Virtually all this performance gain comes from the faster caches and improved clock speed of McKinley, since the Merced binaries cannot take advantage of the increased number of execution units, reduced pairing restrictions on instruction issue, or shorter instruction latencies in the McKinley core. Intel estimates that with recompilation to exploit its improved microarchitecture, a 1 GHz McKinley will come in at 2X Merced's SPECint score, or approximately 758. This still doesn't trump the Power4's 783 on SPECint2000_base, but it's not all that far off, either.
realworldtech.com



To: milo_morai who wrote (60257)10/25/2001 4:20:47 PM
From: TenchusatsuRead Replies (1) | Respond to of 275872
 
Milo, <Hammer brings allot to the table otherwise you wouldn't be here posting so much..>

Do not use me as a contrarian indicator. You'll probably make no more money than if you took me at my word. <G>

Tenchusatsu