Intel (INTC)

[wbmw]

Interesting AMD 65nm Process Variation Analysis

I was looking through AMD's thermal design guide, and found some interesting results:

http://www.amd.com/us-en/assets/content_type/white_papers_and_tech_docs/33954.pdf

If you look at the IDD current of their C1 states, you get an idea of the leakage at various voltages. I looked at their current CZ (F3 stepping, 90nm) and their DD (G0 stepping, 65nm) parts at the max P-state (1.2-1.3V for 65W TDP parts and 1.3-1.35V for 89W TDP parts) and min P-state (1.1V for all products).

I pay special attention to their 3800+ part, which was their downbinned part for 90nm (therefore, highest leakage), and their higher bin parts, which presumably require binning for low leakage in order to fit in the power envelopes. Note that with the new price cuts, AMD's new 90nm downbin is a 4200+ part, which is not listed in this already outdated thermal guide. For 65nm, their downbinned part was the 3600+ part. Today, it is 4000+. Note that you can see the part name in the ID Tag.

 
 ID Tag           Process     IDDC1@HighV      IDDC1@LowV 
 ADO3800IAA5CZ      90nm     23.4A @ 1.25V     7.6A @ 1.1V 
 ADO5000IAA5CZ      90nm     14.8A @ 1.25V     4.8A @ 1.1V 
   
 ADA5000IAA5CZ      90nm     24.8A @ 1.35V     5.7A @ 1.1V 
 ADA5600IAA6CZ      90nm     21.5A @ 1.35V     5.0A @ 1.1V 
   
 ADO3600IAA5DD      65nm     32.2A @ 1.30V    11.2A @ 1.1V 
 ADO4000IAA5DD      65nm     26.5A @ 1.325V    7.8A @ 1.1V 
 ADO4400IAA5DD      65nm     24.1A @ 1.325V    7.1A @ 1.1V 
 ADO4800IAA5DD      65nm     17.9A @ 1.35V     4.6A @ 1.1V 
 ADO5000IAA5DD      65nm     16.6A @ 1.35V     4.4A @ 1.1V

I looks to me like AMD splits 65nm parts into three buckets: let's call them low, medium, and high leakage.

1. The low leakage parts are used for the 4800+ and 5000+ products. They are lower leakage than AMD's best 90nm parts. This is good news. They draw about 8% less current at 1.1V, and about 23-28% less current at 1.35V.

2. The medium leakage parts are used for the 4000+ and 4400+ products. They are somewhat as high in leakage than AMD's leakiest parts on 90nm, and definitely leakier than their 90nm median parts. The 4000+ part, for example, draws more current at 1.1V than AMD's downbinned 3800+ part on 90nm. At 1.325V, they are drawing more current than AMD's high end 90nm parts at 1.35V. This is certainly not good news, and suggest that the median of AMD's 65nm process leakage is worse off than at 90nm.

3. The high leakage parts are downbinned to the 3600+ chip. Although this part has been removed from the current lineup, it's not clear whether they are still producing these and selling them as 4000+ parts, or whether their process has improved. At any rate, these parts are insanely leaky. A 1.1V, they are drawing almost 50% more current than AMD's worst 90nm part. And good thing AMD restricted the voltage to 1.3V, because even at this voltage, the leakage towers over the entire 90nm product line.

I think these results are pretty interesting, and may explain why AMD has not been able to ramp 65nm. The leakage is killing them, and only their lowest leaking parts are able to hit 2.6GHz at 1.35V, and still maintain a reasonable power envelope.

Also, I found something interesting in one of the other AMD datasheets I was looking at. Ever wonder why AMD's Brisbane chips do so much better in idle power dissipation tests done by reviews...? It's because they enabled a new mobile sleep state on it.

http://www.amd.com/us-en/assets/content_type/white_papers_and_tech_docs/32559.pdf

Check out Table 64 on page 278. Previously, desktop chips supported no better than C1 Halt state. Starting with G-step (Brisbane), they now support C3.

Interesting that AMD has needed to start enabling mobile sleep states on their desktop parts. Intel's mobile parts support all the way down to C4E, while their desktop parts only support C1E. C4E flushes the cache and goes to a lower voltage than regular C4. C1E is also lower voltage than regular C1. Note that Brisbane also supports C1E and can hit lower idle power in that state. AMD doesn't state the voltage of that state, so I didn't bother listing it in the above tables. At any rate, their C1 is still at 1.1V, which is nice, because it lines up with current 90nm parts.

Anyway, I thought people would find this interesting.

P.S. (to Chipguy) I posted your other response on SI. Let's see if Petz responds.