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: Paul Engel who wrote (112809)	10/9/2000 3:33:47 AM
From: Joseph Pareti	Read Replies (1) \| Respond to of 186894

>Just what in the IA64 architecture causes pointer manipulation to be an impediment what i heard is this : IA-64 may be very good at regular patterns such as matrix operations for which the compiler can make best use of the underlying architecture ( the LINPACK benchmark might reflect this). In OLTP however (and I admit, this is a foreign territory for me) the workload is quite different and hence hard to be properly accounted for AT COMPILE TIME. Out-of-order processors (such as Pentium, PA-RISC, 21264 and higher) can mask latency penalties from memory accesses by issuing load instructions in advance (instructions ordering rearranged on the fly, this cannot be accomplished by ILP). Again, any input from you (and from the thread) would be welcome.