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: Scumbria who wrote (78165)	4/9/1999 1:38:00 AM
From: Paul Engel	Read Replies (2) \| Respond to of 186894

SCUM bria - Re: "VLIW is easier to design, and requires less logic in the critical path- but it carries the burden that the software must schedule it's own delays." You are missing half of the IA64 picture. The IA64 EPIC architecture provides some excellent features for overcoming memory latencies with predication and speculative execution. The HALF that you are missing is the Software COMPILER program that is generating specific IA64 compilers to directly address, among other topics, data dependencies. The compiler will spot dependencies, allowing a LOAD from a register prior to a preceding, possibly conflicting data store operation to the same register. The IA64 architecture will then detect any subsequent fault, if it occurs, and re-issue the instructions to be executed with the "proper" data in the registers. The "BIG PICTURE" is that the Merced/IA64 is not just a chunk of silicon but an Integrated System of Software Compilers and EPIC hardware that work TOGETHER to optimize throughput of the system. You need to get a better understanding of the "SYSTEM" involved - you are clearly underestimating the magnitude of this project. Paul