Understanding the Cell Microprocessor

Manufacturing, Die Size and Clock Speed

Intel's superiority in manufacturing is responsible for the majority of their technological advances in microprocessors over the past decade, and it's often argued that there isn't a company around that could come close to matching Intel's manufacturing abilities - with the exception of IBM.

The Cell prototype boasts some pretty major manufacturing specs:

- 90nm SOI manufacturing process
- 221 mm² die area
- 234M transistors
- > 4GHz observed clock speed

When it was first announced, the chip sounded massive, but its specifications compare extremely well to Intel's upcoming Pentium D processor; let's take a look at its vitals:

Intel Pentium D Processor

- 90nm strained silicon manufacturing process
- 206 mm² die area
- 230M transistors
- 2.8GHz - 3.2GHz clock speed

With a slightly larger chip and a few million transistors more, Cell is supposed to be able to run at a minimum of 25% higher clock frequency than Intel's forthcoming Pentium D.   We'll let that sit in for a moment...

Dynamic Logic

At first glance, a 90nm SOI Cell running at between 3 - 5GHz looks extremely impressive.   After all, the fastest 90nm CPU IBM currently produces runs at 2.5GHz, not to mention that even Intel, the king of clock speed, can't mass produce anything faster than 3.8GHz on their 90nm process.   But let's dig a little deeper.

The Pentium 4 has two ALUs that run at twice its internal clock speed - so in the case of a Pentium 4 660, that means that two of the more frequently used execution units operate at 7.2GHz - on a 90nm process.   So, it's possible to get circuits to run at higher clock speeds, even in the 3 - 5GHz range, on current 90nm processes - it just takes a little bit of creative logic design.

It's been confirmed that Cell is using some sort of dynamic logic as opposed to static CMOS in order to control transistor counts and improve operating frequencies.   Intel uses a number of specialized logic techniques in their double-pumped ALUs to reach their 7GHz+ operating frequencies, and Intel has discussed techniques that are similar to the dynamic logic used in Cell.

The diagram on the right of a "sleep transistor" should look very familiar by the end of this article

To understand how dynamic works, you have to understand how the transistors are implemented on a chip.

Transistors and You

Just about any AnandTech reader who has followed our CPU articles has heard us count transistors before, but understanding how transistors work is quite critical to understanding how IBM can talk about 3 - 5GHz clock speeds for Cell.

We'll spare you the details about how transistors are made and the physics behind them in an attempt to keep this section as brief, but as informative, as possible.   It's quite common to refer to a transistor as a "switch" much like a light switch, so how does a transistor function like a switch?   Below, we have a representation of a p-type transistor:

There are three points labeled on the transistor: the drain (D), gate (G), and source (S).   In a microprocessor, you generally have the source connected to Vcc (think of Vcc as a line carrying the CPU's core voltage), and the drain connected to ground - often times indirectly (e.g. 10 transistors will be connected in series, with the top-most source connecting to Vcc and the bottom-most drain connecting to ground).

The input to the gate of the p-type transistor is what makes it function as a switch.   If you apply the right voltage to the gate, thus making it a logical "1" or high, current doesn't flow in the transistor.   If you don't apply any voltage to the gate, current can flow.   Just like a light switch, flip it one way and the light turns on; flip it another and you're in the dark.

There's another type of transistor that we'll be talking about here: the n-type transistor:

The three points on the transistor are the same, but the drain and source switch places.   The functionality of the n-type transistor is different as well.  Here, if you apply the appropriate voltage to the gate, a current will flow; if you apply no voltage, no current will flow through the transistor.

CMOS circuits work by using pairs of n- and p-type transistors (that's where the Complementary element of CMOS comes from).   CMOS circuits are by far the most predominant in modern day microprocessors, but as you will soon see, that doesn't mean that they are without flaws.