You can't reasonably test for this yourself in any way. Even if you sample 1M chips uniformly across wafers, fabs, etc., a new stepping, could be a simple 1-layer fix, could completely change time and invalidate all of your testing, you'd have to test another 1M sampled uniformly
-
-
This is a nice soundbite that I guess could sound good to someone who doesn't understand hardware at all but doesn't address anything I said.
-
Then help me understand, I test 10 Transmeta chips, and find all of them start miscalculating branches when some unit is heated with some odd instruction sequence. Should I add Transmeta to the whitelist? I would say no, but it sounds like you're saying, that means nothing.
- 27 more replies
New conversation -
-
-
I don't know, I'm explaining that making sure something works seems prudent. if I test some samples and all of them fail, should I still enable it? It seems obvious the answer is no, what are you arguing?
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.
