Replies to post #26772 on Advanced Micro Devices Inc (AMD)

[wbmw]

HM, Re: The bottom line is Intel should keep IPF alive as it is making an incremental profit, but nobody will ever try to do a new architecture like this again as recooping the original investment is unlikely.

You might be right.

[chipguy]

but nobody will ever try to do a new architecture like this again as recooping the original investment is unlikely.


For general purpose computing? I fully agree. Only Intel
could have released a new ISA in 2001 after 7 years of
development and driven it to where it is now - rapidly
expanding sales and broad OEM and ISV support. The
most recent ISA before than was Alpha released in 1993,
just a little too late to the house RISC party despite all
of its technical merit.

[fastpathguru]

"The bottom line is Intel should keep IPF alive as it is making an incremental profit, but nobody will ever try to do a new architecture like this again as recooping the original investment is unlikely."

A) According to even chipguy's estimates, Itanium isn't breaking even.

B) Not all architectures have to be as expensive and demand so much R&D as Itanium. (I doubt there's much need for a new architecture regardless... It's possible that one of the embedded arch's will bridge the gap into more widespread PC use, but it's far more likely that the PC will wane in popularity in preference to smaller more specialized devices. In other words, smaller/simpler/cheaper/faster may overcome even the x86-legacy advantage/millstone.)

fpg