48 Core Vega 2 in the Making

TobyKY76 writes to tell us The Inquirer is reporting that upstart Azul Systems is planning to integrate 48 cores on their next generation chip. From the article: "The first-generation Vega processor it designed has 24 cores but the firm expects to double that level of integration in systems generally available next year with the Vega 2, built on TSMC's 90nm process and squeezing in 812 million transistors. The progress means that Azul's Compute Appliances will offer up to 768-way symmetric multiprocessing."

48 cores is a nice start, but....

[Raul654]

I know of a certain project [wikipedia.org] that's working to put over a million cores into a system (160 into a single chip), and it should be finished and available off-the-shelf within a year or so.

Re:Are they x86 compatible?

[LLuthor]

They are not x86 compatible. They are RISC like chips with an instruction set optimized for for running VM based applications like Java and .NET.

That said, its still very impressive to get that many cores working together, though not as impressive as x86.

The wiki link says 80 not 160 - read

[joe545]

"Each 64-bit Cyclops64 chip (processor) will run at 500 megahertz and contain 80 cores." While it may have two threads per core, that is not what you claimed. You stated "...that's working to put over a million cores into a system (160 into a single chip)". 160 threads per chip, yes, but not 160 cores.

Re:I don't know much about CPU internals but

[AKAImBatman]

It would seem to me, that a CPU's workload is roughly limited by the number of transistors it has multiplied by it's MHz speed.

The number of transistors can go up for a variety of reasons. Chief among them is designs that utilize complex performance enhancements. To name a few:

• Superscalar processing
• Branch prediction
• Hyperthreading
• Out of order instructions
• Pipelining

The secondary source of transistor usage is coprocessors like Floating Point Units and SIMD Units.

The latest craze in processor design is to simplify the microprocessor back down to the most basic level. From there, the processors are ramped up through shear numbers of parallel pipelines (i.e. threads) and cores as opposed to ramping up the individual CPU horsepower. These multi-core chips typically share coprocessors among a pipelines or cores, and may even have entire cores dedictated to specific tasks like SIMD. As a result, a properly designed program will be able to execute within a very short period of time, thanks to the parallel nature of the multi-core architecture.

Now the only problem is in finding these "properly written programs".

Neat stuff.

[SoupIsGood Food]

I'm not as impressed by the sillicon as I am by their product... it's a platform-agnostic application accellerator, designed to make Java apps (or any other VM app) optimized for multithreading go like stink. It does for processing power what a storage server does for disk space. Plug it into the network, and go... all it does is run a gajillion threads for the VM living on your general purpose servers. Each core probably isn't very powerful (altho they are 64bit RISC designs), but if you're in dire need of cramming as many lightweight transactions through as possible, lots and lots of little optimized processors are going to be more help than one or two big, fat general-purpose Opterons.

It's a very neat concept, and the careful wording ("virtual machine accellerator") indicates that they aren't tied to just Java... Azul's Compute Pool could be something future Parrot-lovers can use to sneak LAMP into places where Java rules all.

They're using some serious sillicon know-how to fuel an innovative and original product... gives me hope we aren't doomed to a wintel-only world, after all.

Re:OK, but...

[DarthStrydre]

You meant that in jest... but this is the kind of parallelization required to run such things as Ray-traced applications or games in realtime (or at least jerky realtime - which is much better than several seconds watching each frame draw).

Refer to:
http://graphics.cs.uni-sb.de/~sidapohl/egoshooter/ [uni-sb.de]

and for a screenshot with multiple reflection:
http://graphics.cs.uni-sb.de/~sidapohl/egoshooter/ screenshots/mutlipleReflectiveSpheres.JPG [uni-sb.de]

Re:Memory interface

[CliffClick]

The box is a flat SMP - if a core misses in L2 it's the same cost to any piece of memory (or remote L2).

The cores are our own design, not MIPs, not ARM, etc. Simple, short in-order pipeline, decent caches (not huge) caches.

Power consumption is very low compared to the equivalent stack of P4 blades or other main-frame solution.

The first-gen box (368 cores) is about 2700 watts in an 11U rack mount.
Next-gen box isn't much bigger, nor draws very much more power (a little more of both I belive).

It Runs Java not X86 Code!!!

[TheNarrator]

Have any onf you people visted Azul's website? This is not an Intel compatible machine.
It is going to only run a Java Virtual Machine so anything written in Java will run on it.
Windows will not run on it. I took some operating system courses in college and the intel
architecture is a huge mess of hideousness of backwards compatibility that luckily only operating system implementers have to deal with. By only running Java these guys get to sidestep the whole mess and focus
on massively optimizing the hardware architecture for running java code.

http://www.azulsystems.com/products/nap.html [azulsystems.com]

Re:Azul longevity

[HaydnH]

How can pointing out there's a current Sun Lawsuit with these guys be a troll? TFA even mentions the Sun lawyers:

"The scalability is showing is attracting big-name early adopters, including Credit Suisse - and even enough to have Sun Microsystems lawyers hammering at the door, alleging intellectual property infringements."

Basically Sun are saying that Azul are infringing on Sun's patents and have illegaly obtained Suns trade secrets. Sun have tried to take part ownership of the Azul and charge ongoing license fee's. Azul have given Sun a chance to look at their documents etc to prove that they haven't infringed on the patents, but Sun haven't taken them up on the offer - I believe Azul are trying to sue Sun also as they believe they're just trying to distract their companies resources.

Personally I wouldn't like to pin my hopes on a chip that has so much politics going on behind the scenes - I'd rather wait until all of this is sorted.

Re:Much Ado About Not a Damn Thing!

[Anonymous Coward]

> They did not last long because Java compiled into x86 machine language actually ran faster than Java executed directly by a Java processor.

this is NOT (repeat repeat repeat) a *JAVA* chip.

its a general purpose RISC chip that has hardware support for many common java functions, such as GC and locking.