Replies to post #4363 on Advanced Micro Devices Inc (AMD)

[spokeshave]

chipguy: Re: All non-trivial chips have bugs..

True. However, the more trivial bugs are reported in the Errata, not in a press release. The fact that this bug has made the newswires is bad, regardless of the seriousness.

It is curious that it escaped escaped detection for so long, the silicon has been around for more than two years.

If there were millions of Itanium 2s out there, I would agree that this is likely a very rare occurrence. However, considering how few Itanics there are, this could be a potentially wide-spread recall.

Then again, it could be a "no, never-mind" like the recent 3.0 P4 release.

[Haddock]

BTW, it seems like a test coverage issue more than anything

Sounds like a missing speed path in the test coverage, since the problem is not present at 800MHz. In fact it sounds rather like the P3-1.13GHz problem.

Perhaps the test coverage gating process for
release to manufacturing at Intel needs to be revisited.

Speed bin tests would be a separate set of tests from the release-to-manufacturing tests, surely?