AMD has updated their Blogs to include info leading up the long-awaited launch of the Bulldozer 8 core CPU - known as FX Series. There is of course lots of hype and secrecy involved in this oh-so-important launch for the Number two X86 CPU maker. 

The CPU has broken the world record for overclocking and seemed to have attracted SLI back to the AMD platform even though nVidia has left the x86 chipset market. This means the launch is imminent and could well happen as soon as next week, with several stories around the web stating the launch is going to happen on Oct 12. If so this will beat the vaunted SandyBridge E processor from the incumbent Intel.

There have rumored benchmarks appearing all over the web but most have been exposed as fake but we should expect competitive perf from the new chips as members of the overclocking record team stated. So all of you drooling for some FX-goodness have a very short time to wait.

Digitimes reports that AMD's issues with 32nm Llano parts will last until 2012 once yields are up enough to fully meet demand.

Supply of AMD's Llano APUs, affected by Globalfoundries's lower-than-expected 32nm yield rates, has been significantly limited and is unlikely to recover until the company's upcoming Trinity arrives in 2012, according to sources from motherboard players. When asked about the company's upcoming Trinity schedule, AMD Taiwan declined to comment on unannounced products.

Recently, one of AMDs Fellows and chief technologists, Chuck Moore sat down to talk about the latest architectures and why they made the choices they did. Here's some higlights from an interesting chat.

On the shared resources element of “Bulldozer,” and the implications:

 
You can look at two cores next to each other and say surely there are some aspects of those two cores we could share. If I share them, I can save power or space.
Each core in a typical system is somewhat overprovisioned for those workloads that have an extreme amount of computing. By sharing some of the subsystems, what we’re able to do is not overprovision each core, but appropriately provision each core and share some of the subsystems like the floating-point unit. In fact, when either of the CPUs in a shared “Bulldozer” environment need to use the floating point unit, they have more capability than they would have in the past.
Here’s a good analogy; if you want to have a very, very, very fast sports car but you know you’re not going to use it every day but you know you have friends that also would like to have a sports car, perhaps you alternate every other week or every other day. Therefore, each one of you gets to use the fast sports car.
So when you want that high performance, you’ve got it. When you don’t need it, you have your average car, and things go along as normal. So the sharing is a way of reducing area, reducing power, and actually dealing with this overprovisioning problem, which left alone would contribute to higher power consumption.

 

Check out the rest here.

Yes, word out of HPCWire, the web site for all things High Performance, is that several European Supers are being outfitted with the new Interlagos (codenamed Bulldozer) 6200 series chips from the number two maker of x86 chips.

Interlagos will fit into the same G34 Maranello Platform as the current 6100 flavor Opterons (codename Magny Cours) that come in 8 and 12 core versions. This is  a major milestone for the also ran as their retail serve fortunes have chnaged over the past few years, dropping form a hig of ~25% to today's low of ~7%. If AMD reached their goals, then Interlagos is sure to challenge Intel on every front, especially AVX\FMAC since Intel's FMAC implementation isn't due until the Haswell architecture.

AMD has been very mum about producing any pre-launch benchmarks and hopefully this will be a successful decision. Some of the systems due to be upgraded to Interlagos include the CSCS (Swiss National SuperComputing Center), who report the upgrade should double their output to ~400TFlops. The HeCToR (High-End Computing Terascale Resource) in the UK is also picking up the new chip which they expect will take their system up to ~827TFlops, which outs it near to the PetaScale rating, a sure boost to their research efforts.The Swiss site is also going to take advantage of the XK6 upgrade and will be installing Tesla 2090 GPUs for what is reported to be a 25PFlop system.

 

Check out the whole story here.

Howdy folks, yes as the title says AMD has released new Llano chips in the form of the triple Core A6-3500 and the CPU-only Athlon II X4 631. Both chips are the usual 32nm SOI HKMG with the A6 running at a cool 2.1GHz with a 2.4GHz Turbo function. The GPU is marked as the 6530 and has 320 SPs with a 443MHz GPU clock. As with other Llanos this chips supports up to DDR3-1866.

The Athlon model, a renewed brand previously thought to be canceled runs a little faster at a speedy 2.6GHz but with no Turbo and of course no GPU. This chip should be a hit with people who want to get a discrete card without having the HybridGraphics. Since the APU paradigm is new I would say that this a good move.

 

Check them out at Newegg and Amazon.

Amazon - A63500 , Athlon II

Newegg - A6-3500 , Athlon II