Understanding the Cell Microprocessor

by Anand Lal Shimpi on March 17, 2005 12:05 AM EST

Cell’s Dynamic Logic

Although it’s beyond the scope of this article, one of the major problems with static CMOS circuits are the p-type transistors, and the fact that for every n-type transistor, you also must use a p-type transistor.

There is an alternative known as dynamic or pseudo-NMOS logic, which gets around the problems of static CMOS while achieving the same functionality.   Let’s take a look at that static CMOS NOR gate again:

The two transistors at the top of the diagram are p-type transistors.   When either A or B are high (i.e. have a logical 1 value), then the p-type transistor gates remain open, with no current flowing.   In that case, the output of the circuit is ground, or 0 since the complementary n-type transistors at the bottom function oppositely from their p-type counterparts (e.g. current can flow when the input is high).

Thus, the NOR gate outputs a 1 only if all inputs are 0, which is exactly how a NOR gate should function.

Now, let’s take a look at a pseudo-NMOS implementation of the same NOR gate:

There are a few things to notice here.  First and foremost, the clock signal is tied to two transistors (a p-type at the top, and an n-type at the bottom) whereas there was no clock signal directly to the NOR gate in our static CMOS example.  There is a clock signal fed to the gate here.

Cell’s implementation goes one step further.  The p-type transistor at the top of the circuit and the n-type transistor at the bottom are clocked on non-overlapping phases, meaning that the two clocks aren’t high/low at the same time.

The way in which the gate here works is as follows: inputs are first applied to the logic in between the clock fed transistors.   The top transistor’s gate is closed allowing the logic transistors to charge up.  The gate is then opened and the lower transistor’s gate is closed to drain the logic transistors to ground.   The charge that remains is the output of the circuit.

What’s important about this is that since power is only consumed during two non-overlapping phases, overall power consumption is lower than static CMOS.   The downside is that clock signal routing becomes much more difficult.

The other benefit is lower transistor count.  In the example of the 2-input NOR gate, our static CMOS design used 4 transistors, while our pseudo-NMOS implementation used 4 transistors as well.   But for a 3-input NOR gate, the static CMOS implementation requires 6 transistors, while the pseudo-NMOS implementation requires 5.  The reasoning is that for a CMOS circuit, you have 1 p-type transistor for every n-type, while in a pseudo-NMOS circuit you only have two additional transistors beyond the bare minimum required to implement the logic function.   For a 100-input NOR gate (unrealistic, but a good example), a static CMOS implementation would require 200 transistors, while a pseudo-NMOS implementation would only require 102.

By making more efficient use of transistors and lowering power consumption, Cell’s pseudo-NMOS logic design enables higher clock frequencies.   The added cost is in the manufacturing and design stages:
1. As we mentioned before, clock routing becomes increasingly difficult with pseudo-NMOS designs similar to that used in Cell.   The clock trees required for Cell are probably fairly complex, but given IBM’s expertise in the field, it’s not an insurmountable problem.
2. Designing pseudo-NMOS logic isn’t easy, and there are no widely available libraries from which to pull circuit designs.   Once again, given IBM’s size and expertise, this isn’t much of an issue, but it does act as a barrier for entry of smaller chip manufacturers.
3. Manufacturing such high speed dynamic logic circuits often requires techniques like SOI, but once again, not a problem for IBM given that they have been working on SOI for quite some time now.   There’s no surprise that Cell is manufactured on a 90nm SOI process.
On the gate level, just like at the logic level, Cell is architected for high speeds and efficient use of transistors.

Understanding Gates Blueprint for a High Performance per Transistor CPU

• PhilAnd - Wednesday, October 05, 2005 - link

Thank you SO MUCH!!! I've been looking for an explanation of the cell forever and this did it perfictly!! THANK YOU!!! YOU ARE GOD!!! Reply
• philpoe - Sunday, July 31, 2005 - link

Under the high-level overview of the cell section, the PPE has 64KB L1 and 512KB L2 cache.
On the other hand, under the on-die memory controller section, we see that the XDR memory gives bandwidth of 25.6GB/sec, and the integrated memory controller "significantly reduces memory latencies".
My question then is, what good is the L1 and L2 cache doing? Given the amount of real estate those transistors take up, isn't it more economical to use the system RAM exclusively? The L2 cache takes up about the same amount of space as an SPE, not that it would help but so much to put another one on the die, but what effect on performance would getting rid of the L2 or even L1 cache have on memory with such high bandwidth?
• jiulemoigt - Saturday, March 26, 2005 - link

Oh #59 it's funnier than that the PPE does all the work the modern CPU does with logic, and the easy stuff is done by the extra procs... but that means the messy {think calc equations} can not be done by the extra proc so if your game requires more abstract equations vs simple math {the math understadning simple math} say AI vs drawing boxes adn cubes, your machine will be dependant of the smaller proc, and the pipeline length is a game of balence prediction vs speed meaning that if you can predict a full pipeline it is much faster if the pipe is longer the vs you miss with the prediction at some point in the pipe and everthing after that point is lost so the longer the pipe is after the miss is a loss. So a shorter pipe is not nessacry better as there are tasks the P4 excells at because it has the huge pipe and the longer the pipe the high you can scale the proc speed, which is why intel chose such a huge pipe knowing the misses would hurt but at the time people still wanted every mhz possible. AMD has a 14 stage pipe because they use decent prediction but better register use, as well as fast pathing, but the biggest reason x86 is fast is because as long as it works theres reams of code out there to reach the sun a new system will require human hours to clean up so that is can take all the short cuts that x86 already does. So if the dev's are laughing now it is becasue the know it going to be very unfriendly to code for and are frustrated that the hardware which has years of effort going into it's design is not being designed to be easier to code for and to do the hardwork for us instead of the doing all the easy work faster which doesn't help us and making the hardwork harder! and in some cases run slower because it was cheaper. I understand how much money M\$ lost, which was passed on to nvidia, so for them they won't get away with that this time so they will have to make it cheaper this time around. Reply
• AndyKH - Thursday, March 24, 2005 - link

#55
Regarding the interview from GameSpot:
He (the guy who is very upset with having to program for in-order cores) states that code will run very crappy on these new cores. Well... I don't know exactly how many pipeline stages the new cores have, but they will without a doubt have a LOT less stages than modern out-of-order core. If you also spend a great amount of design effort to make sure the branch target is calculated very early in the pipeline and couple that with a high clock frequency, you might not even need to fetch your bag of kleenexes to dry your eyes.

Of course, I don't know how long the pipeline in a Cell PPE or in the Xenon's cores is, but everything points to a very short one. Also I don't know how early the branch target is calculated, but I bet it's pretty early.

As an end remark I might add that "computer engineers are not stupid people". In the interview, the guy make it sound like it will be impossible to run gameplay code on the new console CPUs..... I personally don't think that IBM and Sonys engineers will design a CPU with such a little amount of care.

Regards
Andreas
• TheGee - Monday, March 21, 2005 - link

Transputer anyone? The computer on a chip that could be massively parralleled? Difficult to program but this cell is not such a great leap in ideas but with the corporate weight may succeed where others have failed and break the x86 limitations put on PCs. If the busses are big enough it would be nice to be able to plug in extra CPUs on a card or such like to upgrade or speed up a system without to much difficulty as long as the software is not CPU limited. But as before it's best not to hold your breath! Reply
• Slaimus - Sunday, March 20, 2005 - link

PS1 was easy to program, so that took off. Sony made PS2 very hard to program if you want to use its vector units efficiently, but since the game developers are already on board, they had to live with it. And sony will dump the same heap onto developers again with the PS3.

With this kind of complexity, I have a feeling that middleware companies will thrive. Game developers want to create content more than write assembly code, so a few middleware companies will probably supply the libraries while everyone else licenses them. Of course Microsoft has a head start since DirectX already exists and is included in the devkit, but then again, the xbox2 is not as massively parallel.
• stephenbrooks - Sunday, March 20, 2005 - link

Ah sod multiple cores. I always preferred playing Tetris anyhow. Reply
• knitecrow - Friday, March 18, 2005 - link

GAME DEVELOPER @ GDC RANT ON NEXT GEN CONSOLES
http://www.gamespot.com/news/2005/03/18/news_61204...

All right, here we go. "How Sony and Microsoft are about to screw your game design." These are games in the good old days. We didn't exactly have the best physique, but we were at least a balanced individual, you walk out on the beach, and you were like, you know, pathetic. But you know, you looked like a normal person. These are games today. We've been working really hard--I mean, you can maybe make the argument that this is the game--these are games today. I gotta little more work on that left arm to do, it's going to be as big as our graphics arm soon. This is kind of lame. We really want to be this guy don't we?

Unknown Speaker: No!

[laughter]

Chris Hecker: OK, he was the best guy I could find in like, three seconds in the WiFi network out in the lobby. All right. But how do we get there? Well, I'm going to take a little diversion here. I'm a programmer, so, I have two technical slides, really one technical slide. And that's about it. All right, ready? So there are two kinds of code in a game basically. There's gameplay code and engine code. Engine code, like graphics and physics, takes really giant data structures of homogenous data. I mean, it's all the same, like a lot of vertices are all a big matrix, or whatever, but usually floating point data structures these days. And you have a single small, relatively small hour that grinds away on that. This code is like, wow, it has a lot of math in it, it has to be optimized for super scalar, blah, blah, blah. It's just not actually that hard to write, right? It's pretty well defined what this code does.

The second kind of code we have is AI and gameplay code. Lots of little exceptions. Even if you're doing a simulation-y kind of game, there's tons of tunable parameters, [it's got a lot of interactions], it's a mess. I mean, this code--you look at the gameplay code in the game, and it's crap. Compared to like, my elegant physics simulator or whatever. But this is a code that actually makes the game feel different. This is the kind of code we want to be easy to write and so we can do more experimental stuff. Here is the terrifying realization about the next generation of consoles. I'm about to break about a zillion NDAs, but I didn't sign any NDAs so that's totally cool!

I'm actually a pretty good programmer and mathematician but my real talent is getting people to tell me stuff that they're not supposed to tell me. There we go. Gameplay code will get slower and harder to write on the next generation of consoles. Why is this? Here's our technical slide. Modern CPUs, like the Intel Pentium 4, blah, blah, blah, Pentium [indiscernible] or laptop, whatever is in your desktop, and all the modern power PCs, use what's called 'out of order' execution. Basically, out of order execution is there to make really crappy code run fast.

So, they basically--when out of order execution came out on the P6, the Pentium 6 [indiscernible] the Pentium 5, the original Pentium and the one after that. The Pentium Pro I think they called it, it basically annoyed a whole bunch of low level ASCII coders, because now all of a sudden, like, the crappiest-ass C code, that like, Joe junior programmer could write, is running as fast as their Assembly, and there's nothing they can do about it. Because the CPU behind their back, is like, reordering that guy's crappy ass C code, to run really well and utilize all the parts of the processor. While this annoyed a whole bunch of people in Scandinavia, it actually…

[laughter]

And this is a great change in the bad old days of 'in order execution,' where you had to be an Assembly language wizard to actually get your CPU to do anything. You were always stalling in the cache, you needed to like--it was crazy. It was a lot of fun to write that code. It wasn't exactly the most productive way of doing experimental programming.

The Xenon and the cell are both in order chips. What does this mean? The reason they did this, is it's cheaper for them to do this. They can drop a lot of core--you know--one out of order core is about the size of three to four in order cores. So, they can make a lot of in order cores and drop them on a chip, and keep the power down, and sell it for cheap--what does this do to our code?

Well, it makes--it's totally fine for grinding like, symmetric algorithms out of floating point numbers, but for lots of 'if' statements in directions, it totally sucks. How do we quantify 'totally sucks?' "Rumors" which happen to be from people who are actually working on these chips, is that straight line gameplay code runs at 1/3 to 1/10 the speed at the same clock rate on an in order core as an out of order core.

This means that your new fancy 2 plus gigahertz CPU, and its Xenon, is going to run code as slow or slower than the 733 megahertz CPU in the Xbox 1. The PS3 will be even worse.

This sucks!

[laughter]

There's absolutely nothing you can do about this. Well, you can actually hope that Nintendo uses an out of order core, because they're claiming that they're going to try and make it easy to develop for--except for Nintendo basically totally flailed this generation. So maybe they'll do something next generation. Who knows? You can think about having batchable design simulation-y systems, but like, I'm a huge proponent of simulation in gameplay, but even simulation in gameplay takes kind of messy systems under the hood. And this makes your gameplay harder to write.

You want to just write the gameplay. You don't want to have to like, spend 6 years of a super hardcore engine programmer's time to figure out how to make your gameplay run super scalars. You could do PC games. They are still out of order cores, but a lot of people don't think that's an option nowadays.
• Houdani - Friday, March 18, 2005 - link

I think I missed something fundamental.

Can the SPEs be addressed directly by software, or do they have to be fed all of their instructions by the PPE?

If they DO have to be fed be the PPE, I fail to see how the PPE can possibly feed them enough to keep them all working concurrently.

Someone throw me a bone here.