Mark Roulo (nothanks.delete@this.xxx.com) on January 8, 2015 6:37 pm wrote:
> juanrga (nospam.delete@this.juanrga.com) on January 7, 2015 6:03 am wrote:
> > I recall Aaron asking me why I believed that mixing VLIW with
> > RA was a good idea. Funny, because we know now that
> > Denver is an in-order VLIW+RA core that outperforms wide OoO cores such as Cyclone or Haswell.
>
> Have you not noticed that nVidia did not select the fastest 15W Haswell CPU they could?
>
> The 2955U Celeron is a 15W TDP part with no hyperthreading, a clockspeed
> of 1.4 GHz and 2 MB of L3 cache. Turbo-boost is disabled.
>
> The 4650U is *also* a 15W TDP Haswell part, but it has a base frequency
> of 1.7 GHz, 4 MB of L3 cache and will turbo to 3.3 GHz.

I am not inside their heads, but I guess that one being a $132 chip whereas the other being a $454 chip played some role.

Have care with turbo frequencies. In Anand review the 4650U had difficulties achieving the 3.3GHz on ST and in MT Anand saw "occasional bursts up to 2.9GHz".

http://www.anandtech.com/show/7113/2013-macbook-air-core-i5-4250u-vs-core-i7-4650u/3

> Eyeballing the nVidia chart, the Denver (@ 2.5GHz?) beat the 2955U by about 10% on SpecInt2000. My guess is
> that a 4650U would beat the Denver chip by close to 2:1. When you lose by 2:1, you aren't "outperforming".

Denver beats it at much less than half the power consumption, die area, and price.

E.g. a single Haswell core on 22nm occupies more die space than two Denver cores on 28nm.

All that is a win in my book.

> If you want to do a technical comparison between Denver and Haswell, you really
> do have to pick the fastest relevant Haswell part, not the slowest.
>

If I was to do a technical comparison I would avoid Haswell because cannot produce the required level of performance with same power consumption and die space constraints that Denver engineers had to satisfy. I would chose an Atom chip and normalize for the node advantage (22FF vs 28PL). The result would be about the same.