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: L. Adam Latham who wrote (164823)	5/2/2002 8:26:47 PM
From: combjelly	Respond to of 186894

"but I do recall that a JVM (IBM's I think, possibly others) was specifically tuned for Itanium." Could be. But it is hard to see what aspect of IA-64 would benefit an interpreter like a JVM. The data stream is not real predictable, so the static analysis of the compilers isn't all tha helpful. True, the register set is pretty large, but that is something that doesn't yield all that much for an architecture that is stack based, like a JVM. You have to spill the registers at unpredictacble points, which is an Itanium weakness. I dunno, I don't see where Itanium is a good JVM machine. The P4 would be better...

To: L. Adam Latham who wrote (164823)	5/2/2002 9:49:16 PM
From: kapkan4u	Read Replies (2) \| Respond to of 186894

<Recollections of my Intel work details fade away with each passing day, but I do recall that a JVM (IBM's I think, possibly others) was specifically tuned for Itanium.> Itanium code can't be JIT compiled well. Heck it can't even be JID (Just in Days) compiled well. So the quote above is as absurd as it gets. Granted you don't pretend to understand the issues. I happen to know that Itanic's inability to support JIT and .NET framework efficiently was one of the primary motivations behind MS's push into x86-64. Kap