Ex-AMD Engineer Explains Bulldozer Fiasco: Lack of Fine Tuning
Automated Design = 20% Bigger, 20% Slower
Automated Design = 20% Bigger, 20% Slower
So if BD was largely a synthesized design, why was it delayed so much?
So if BD was largely a synthesized design, why was it delayed so much?
And IMHO, for a high frequency design, automated vs hand design penalty is much higher than 20%...
I actually saw this quite a long time ago.
I've heard this story before. I have nothing against x-bit passing this of as "news" since BD failure is a hot item now, but Cliff Maier mentioned this quite some time ago already.
So it's actually the other way around if I remember correctly. Cliff left before BD was anywhere near completion, but he said (in so many words) that BD will be a flop due to reliance on automated tools. 20% bigger, 20% slower.
Most people dismissed him as your average disgruntled employee, yadda yadda yadda.
Now that Bulldozer flopped epically, he now gets his much deserved vindication.
I actually created a thread about this for feedback and satiate my curiosity.I actually saw this quite a long time ago.
And no one will be held accountable. The idiot that made the decision will probably get a bonus and promotion.
Sounds about right. Hopefully the lesson has been learned.
I seem to remember having an indepth discussion with CTho when this originally came out, where he was saying that current tools have shown that they are usually more efficient compared to hand designs, and are also usually more compact.
The management decided there should be such cross-engineering [between AMD and ATI teams within the company] ,which meant we had to stop hand-crafting our CPU designs and switch to an SoC design style.
I'm surprised no one mentioned this:
LOL, management. As if they know any better.
AMD went straight downhill after Jerry left. When you get people like Hector Ruiz (more like Hector Ruinz), I can't say I'm not surprised how they're turning out. In fact, it won't be news to me if they get bought soon.
http://www.forbes.com/sites/ericsavitz/2011/10/13/amd-now-verging-on-irrelvancy-analyst-says/
Don't forget that Hector Ruinz now works at Global foundries ...
he wasn't exactly "fired"
GloFo had six (6) 32nm wafers, AMD could have 6 wafers worth of Llanos or 6 wafers worth of bulldozer, or a mixture of the two.
Llano launch needed 7-8 wafers worth of chips, so they allocated to Llano at the expense of bulldozer.
(substitute 6 wfrs for 2,000 or so, the point still stands, early node ramps suck when it comes to supporting volume launches of new products)
Hector resigned over the insider trading scandal.
I'm talking about this >>> Ex AMD designer: Bulldozer to disappoint at XtremeSystems. This was last year.I actually created a thread about this for feedback and satiate my curiosity.