Why Intel’s Tick-Tock model had to die

The reason most cite is wrong

Intel logo 87x80  Why Intels Tick Tock model had to dieThe idea was simple, with a two year upgrade cycle for new processes, a two year cadence for new silicon architectures, and a yearly release of updated chips, Intel has fairly regular introductions to plan around. New process and new architectures both tend to have teething problems, and doing both at the same time is essentially asking for trouble. In case you can’t see where this is going, the idea behind tick-tock is to spread out your pain points so you never have two at the same time.

With that in mind, Intel’s approach was pretty basic, never introduce a new architecture on a new process, and vice versa. With new architectures such as Nehalem, Sandy Bridge, and Haswell coming every other year, and minor updates like Westmere, Ivy Bridge, and Broadwell every other year, new processes were introduced with the updates. That means you never get two big potential problems on the same chip, something that has bitten AMD very publicly several times in the past. For Intel anyway, the whole concept has worked out pretty well until recently.

[Editor's note:  This article is analysis only and will not be available for individual purchase nor available to the Curious level membership as it does not contain news.]

...

{{{Member|Professional|Student}}}
Full article access is for subscribers only, for immediate access as a subscriber login here now or subscribe if you want to read the full article now.