Intel Corporation (INTC) Message Board

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)

INTC 43.47

+8.6%

3:59 PM EST

Public Reply Prvt Reply Mark as Last Read File

Previous 10 Next 10 Previous Next

To: fp_scientist who wrote (114508)	10/19/2000 10:02:33 AM
From: jcholewa	Read Replies (1) of 186894

Re: spec2000 and Pentium 4 performance > Absolutely true. Most of the codes in SPECfp require plenty of memory and it is up to the compiler to decide how to > access the data. The higher the bandwidth, the better execution you get. > I am curious about what OS (W or Linux?) and compiler(s) where used in this P4 specfp benchmark .... It's Pentium 4, not Merced, so there isn't too much of an uncertainty on this one. My bets would be that it's NT5 with VTUNE5. The memory bandwidth should help specfp quite unbelievably, but the really neat thing might be the hardware prefetching capability, which it seems might slightly increase average bandwidth (by filling available idle times with memory accesses), and will certainly and very strongly decrease average memory latency. Like I said before, though, it's possible that VTUNE5 makes minimal or no use of the double precision SIMD in Willamette.     -JC PS: It'll still not be too impressive in specint2000. :P

Report TOU Violation

Share This Post

Public Reply Prvt Reply Mark as Last Read File

Previous 10 Next 10 Previous Next