AMD Licenses Z-RAM Technology

ZuperDee writes "It appears AMD has licensed Z-RAM technology from Innovative Silicon for possible use in future processors. According to the article, this could lead to caches about 5 times denser than the SRAM that is normally used right now. C|Net says they will probably make the announcement on Monday."

Comments

Apple should have considered?

[Saven Marek]

Another reason Apple's alliance with Intel wasn't such a good idea. Should have gone AMD, Steve.

Re:Apple should have considered?

[jcr]

Should have gone AMD, Steve.

Apple's already been down the road of choosing the apparently spiffier processor from a vendor that wasn't able to deliver in quantity. If AMD becomes the better processor choice in the future, then I'm sure Apple will switch again.

-jcr

Re:Apple should have considered?

[turgid]

As many like to point out, Intel often shows a "Not Invented Here" attitude.

Quite. The crossbar switch came and went (1990's RISC workstations, appeared in the AMD Athlon) and intel's still using a 1970's bus for it's "high-end" pentium processors.

Now we have point-to-point interconnects (1990's supercomputers NUMA architecture) called Hypertransport and intel's still flogging the 1970's bus on the pentium.

Look at how pentium doesn't scale in SMP systems. Itanic is a different matter, but you can buy several equivalently-fast Opterons for a single itanic, which only performs on numerical workloads.

Someone needs to administer the clue bat at intel before it's too late.

Re:factorial benchmark

[80 85 83 83 89 33]

here is my list (so far) of factorial times for "100,000!"

look at the XPs running at 2.0GHZ and notice how it is frequency dependant

P4 3.2GHz
81 seconds

athlon XP 3200+ (2.2GHz socket A, barton)
81 seconds

P4 3.0GHz (laptop)
90 seconds

athlon XP 3200+ (2.0GHz 939 venice)
91 seconds

athlon XP 2400+ (2.0GHz)
93 seconds

athlon XP 2100+
106 seconds

athlon XP 2000+ (1.67GHz)
121 seconds

athlon mobile XP 1800+ (1.52GHz)
122 seconds

celeron 2.7 GHz (northwood core)
130 seconds

celeron 1.4GHz (tualatin)
205 seconds

celeron 800MHz (win98)
333 seconds (5min 33sec)

celeron 800MHz (XP pro)
373 seconds

PIII 800 (XP pro)
474 seconds

PIII 450MHz (underclocked coppermine)
490 seconds

PII 333MHz
686 seconds

PII 300MHz
760 SECONDS

P 166MHz
2417 seconds

Re:Details

[Savantissimo]

That should mean about 25 bits per square micron in a 65um process or 3.25 megabytes of memory per square millimeter. Pretty cool.

Re:Read much, do you?

[semaj]

It's not the same software.

When you change the insides, nobody notices

Newer versions of "Calc" were completely written behind the scenes to provide more accuracy (essentially infinite accuracy on simple arithmetic, explained above) while the interface remained the same. So the comparison is flawed.

Only caches?

[jcr]

Any reason why this couldn't also lead to much higher density for system RAM?

-jcr

Re:In 2 years

[Jesus_666]

You forgot "3. The wrong tool for the job". The Cell is not quite the best architecture for your usual application with just one or two threads and it's highly unlikely that everyone will rewrite their software to make use of a half dozen threads (thus killing performnce on systems not running a Cell or SMP).

I agree for different reasons.

[Andy Dodd]

To get into a console, you can't win if you fall into categories 1 or 2. If the Cell were that expensive or underperforming, people wouldn't be putting it into consoles.

Now, there is one thing about the Cell you missed - It's a special-purpose processor designed for raw floating point performance. 8 of the cores can only do basic streaming floating point (although they do it EXTREMELY fast), the remaining CPU is a VERY stripped down PPC.

So for a gaming system or DSP, the Cell will kick ass. For general purpose computing, it's going to suck.

there's a lot of assumption there...

[YesIAmAScript]

Note that if ZRAM works, it would let AMD put something like 4X as much cache on their chips in the same die area. This indeed would be quite a competitive advantage.

But why do people assume this will work? There's a couple companies trying to do this stuff (T-RAM is another) and none have succeeded yet.

It has proven to be difficult to get this kind of technology working in production chips. The main difficulty is that process control becomes very very important. Your yields drop through the floor.

Additionally, note that any 1T transistor technology is inherently a stored charge device (like EPROM, EEPROM or flash memory but different). The problem is that transistors on chips are getting so small that they have less than 100 electrons in the gate of a transistor. So your insulating ability becomes very important. Your chip is designed for electron mobility that electrons can flow around a fairly long loop (the instruction execution path) 1 million times in 1 millisecond. And now you have to make sure that 100 electrons sitting in one place don't leak out in that same time.

It's a challenge. It might be possible. I don't see any particular reason to think that AMD is going to be the one to do it though. Intel are wizards at process technology, as evidenced by their movement to 65nm before AMD. They don't happen to use SOI though, that's about the only advantage AMD has in this situation that I can see.

Anyway, I do like AMD (I'm typing this post on one), but them licensing some unproven technology from a 3rd party is no kind of condemnation of Intel or Apple's choice of Intel.

Re:Details

[darkmeridian]

Finally, a technology patent that does some good! A small company innovated a new technology and licensed it to a big company that will bring it to market. Everybody wins! How rare is this?

Re:Details

[Short Circuit]

More often than "A small company patents something, and sues big company for failing to pay for using it."

The two are often related.