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: Elmer who wrote (88131)	9/11/1999 9:07:00 PM
From: Rob Young	Read Replies (1) \| Respond to of 186894

<Any hints out there that [Merced Integer numbers suck]?> Yes.. numerous. The most reliable hint comes to us via HP PA-RISC folks. Running PA binaries in emulation mode result in about 90% native integer PA 8500 performance. Since PA 8500 does 34-35 or so integer, Merced does about 31-32 int running emulated PA-RISC binaries (translated on the fly). The one remaining question is: Just how well (efficient) does Merced emulate PA-RISC binaries? Answer: EXTREMELY well... I had a number shot my way that was surprising. I had no idea it did that good. But as a CPU architect wrote in a forum: "Looking at the base IA64 instruction set, I'd say that the IA64 is extremely similar to PA-RISC -- most of the instructions look like they were just copied over, then this bundle/predication/windows/multiway branch stuff heaped over it." Merced integer numbers sucking? Sure. No one admits it yet of course. Rob