Apple's A6 Processor Uses Hand Drawn ARM Cores to Boost Performance

Subject: General Tech, Processors, Mobile | September 27, 2012 - 09:26 AM |
Tagged: SoC, PowerVR, iphone, arm, apple, a6

Apple's latest smartphone was unveiled earlier this month, and just about every feature has been analyzed extensively by reviewers and expounded upon by Apple. However, the one aspect that remains a mystery is the ARM System on a Chip that is powering the iPhone 5. There has been a great deal of speculation, but the officially Apple is not talking. The company has stated that the new processor is two times faster than its predecessor, but beyond that it will be up to reviewers to figure out what makes it tick.

After the press conference PC Perspective's Josh Walrath researched what few hints there were on the new A6 processor, and determined that there was a good chance it was an ARM Cortex A15-based design. Since then some tidbits of information have come out that suggest otherwise, however. Developers for iOS disovered that the latest SDK suggest new functionality for the A6 processor, including some new instruction sets. That discovery tended credence to the A6 possibly being Cortex A15, but it did not prove that it wasn't. Following that, Anandtech posted an article that stated it was in a licensed Cortex A15 design. Rather, the A6 was a custom Apple-developed chip that would, ideally, give users the same level of performance without needing significantly more power – and without waiting for a Cortex A15 chip to be manufactured.

Finally, thanks to the work of the enthusiasts over at Chipworks, we have physical proof that, finally, reveals details about Apple's A6 SoC. By stripping away the outer protective layers, and placing the A6 die under a powerful microscope, they managed to get an 'up close and personal' look at the inside of the chip.

Apple A6 ARM SoC.jpg

Despite the near-Jersey Shore (shudder) levels of drama between Apple and Samsung over the recent trade dress and patent infringement allegations, it seems that the two companies worked together to bring Apple's custom processor to market. The researchers determined that the A6 was based on Samsung's 32nm CMOS manufacturing process. It reads APL0589B01 on the inside, which suggests that it is of Apple's own design. Once the Chipworks team sliced open the processor further, they discovered proof that Apple really did craft a custom ARM processor.

In fact, Apple has created a chip with dual ARM CPU cores and three GPU cores (PowerVR). The CPU cores support the ARMv7s instruction set, and Apple has gone with a hand drawn design. Rather than employ computer libraries to automatically lay out the logic in the processor, Apple and the engineers acquired from its purchase of PA Semi have manually drawn out the processor by hand. This chip has likely been in the works for a couple of years now, and the 96.71mm^2 sized die will offer up some notable performance improvements.

microscope.jpg

It seems like Apple has opted to go for an expensive custom chip rather than opt for a licensed Cortex A15 design. That combined with the hand drawn layout should give Apple a processor with better performance than its past designs without requiring significantly more power.

At a time when mobile SoC giant Texas Instruments is giving up on ARM chips for tablets and smartphones, and hand drawn designs are becoming increasingly rare (even AMD has given up), I have to give Apple props for going with a custom processor laid out by hand. I'm interested to see what the company is able to do with it and where they will go from here. 

Chipworks and iFixIt also took a look at the LTE modem, Wi-Fi chip, audio amplifier, and other aspects of the iPhone 5's internals, and it is definitely worth a read for the impressive imagery alone.

Source: ifixit

Ivy Bridge versus Sandy Bridge in a power consumption showdown

Subject: Processors | September 18, 2012 - 10:49 AM |
Tagged: sandy bridge, Ivy Bridge, Intel

iXBT Labs wanted to see how the two most current generations of Intel processors compare when running identical tasks.  To put the processors under maximum load they used Linpack and Furmark as well as looking at video playback.  In the case of the Furmark and Linpack+Furmark tests it might have been nice to see a power versus performance metric, as better performance on the benchmarks could make a slightly less power hungry CPU even more attractive.  However the video playback is a great example of what you can expect in the way of power draw as no one wants a faster processor to play their movie back at an increased speed, a 2 hour movie should take 2 hours to play.  That makes the second metric a little more valuable for those on battery power.  Take a quick peek at their 2 page article here.

furmark190_logo.jpg

"We measured consumed power and energy consumption of four configurations based on the same testbed and four different CPUs belonging to two platforms: Intel Core i7-2700K (Sandy Bridge) and Intel Core i7-3770K (Ivy Bridge), Intel Core i5-2400 (Sandy Bridge) and Intel Core i5-3450 (Ivy Bridge)."

Here are some more Processor articles from around the web:

Processors

Source: iXBT Labs

AMD Binning Trinity APUs With Defective GPUs as CPU-Only Athlon Processors

Subject: Processors | September 13, 2012 - 10:03 AM |
Tagged: trinity, fm2, cpu, athlon, APU, AMD A series, amd, a75

NVIDIA’s new Kepler graphics cards (such as the GTX 660 we recently reviewed) will be getting most of the PC enthusiast attention today, but there is a bit of news about AMD to talk about as well.

The Trinity APU die.

Thanks to a Gigabyte motherboard compatibility list that was accidentally leaked to the internet, it was revealed that Advanced Micro Devices (AMD) would be repurposing Trinity APU dies that don’t quite make the cut due to non-operative graphics cores. Instead of simply discarding the processors, AMD is going to bin the chips into at least three CPU-only Athlon-branded processors. The Athlon X4 730, X4 740, and X4 750K are the three processors that are (now) public knowledge. All three of the CPUs have TDP ratings of 65W, and the X4 750K is even unlocked – allowing for overclocking. Further, the processors are all quad core parts with a total of 4MB of L2 cache (1MB per core).

The new Athlon-branded processors will be supported by the A75 chipset and will plug into FM2-socket equipped motherboards.

The following chart details the speeds and feeds of the Athlon processors with Trinity CPU cores.

  Clockspeed TDP
Athlon X4 730 2.8GHz 65W
Athlon X4 740 3.2GHz 65W
Athlon X4 750K 3.4GHz 65W

 

Unfortunately, there is no word on pricing or availability. You can expect them to be significantly cheaper than the fully fledged Trinity processors to keep them price-competitive and in-line with the company's traditional CPU-only processors.

Would you consider rolling a Trinity-based Athlon in a budget build?

Read about the new direction of AMD as it moves to producing Vishera processors and beyond.

Source: Bit-Tech

Intel Dives in to Oil!

Subject: General Tech, Cases and Cooling, Processors, Systems, Shows and Expos | September 12, 2012 - 06:34 PM |
Tagged: mineral oil, Intel

Intel has been dunking servers in oil for the last year and found the practice to be both safe and effective. Ironically it has been almost a year since we played around with mineral oil cooling – and when we did – we did not want to upgrade or fix anything. Intel agrees.

Intel inside, slick mess outside.

Often cooling a computer with a radiant that is not air focuses on cooling a handful of specific components and leaving the rest exposed to air. Gigabyte in their recent live presentation showed how the company reduced waste heat on the motherboard as it delivers power to the CPU as the latter likely receives more cooling than the former. With mineral oil you are able to more efficiently cool the entire system by immersing it in a better coolant than air.

aquarium.jpg

This still makes Ken wake up in a cold sweat… is what we convince ourselves.

After a full year of testing servers, Intel has decided that oil immersion cooling should be utilized by more server hosts to cut costs over traditional air conditioning. In their test they used heat sinks which were designed for air and dunked them pretty much unmodified into the mineral oil dielectric. Apart from the mess of it – Intel engineers always carried cleaning cloths just in case – Intel seems to only sing praise for results of their study.

Of course Intel could not help but promote their upcoming Phi platform which you may know as the ancestor of Larabee.

Now the real question is whether Intel just wanted to shamelessly plug themselves – or whether they are looking so closely at alternative cooling solutions as a result of their upcoming Phi platform. Will we eventually see heat dissipation concerns rear their heads with the new platform? Could Intel either be sitting on or throttling Phi because they are waiting for a new heat dissipation paradigm?

Could be interesting.

Live Blog: Intel Developer Forum (IDF) 2012 Keynotes

Subject: Editorial, General Tech, Processors | September 11, 2012 - 08:52 AM |
Tagged: Intel, idf, idf 2012, keynote

The Intel Developer Forum is one of the best places in the world to get information and insight on the future of technology directly from those that creat it.  Join me as I live blog (Wi-Fi connection dependent as always!) the keynotes from all three days at http://pcper.com/live!!

logo.png

Be sure to stop by our PC Perspective Live page at 9am PT on Tuesday, Wednesday and Thursday!!

Intel Haswell CPUs to Have 10W TDP, Perfect for Mobile Devices

Subject: Processors | September 6, 2012 - 10:10 AM |
Tagged: ultrabook, Intel, haswell, cpu, 10w tdp

Intel’s next generation Haswell CPU architecture is set to lower the bar even further on power efficiency by requiring only 10W of cooling. As the company’s mainstream processor, and replacement for Ivy Bridge, it is set to launch in the first half of 2013.

Haswell will be based on a new socket called LGA 1150, and is said to feature incremental performance improvements over Ivy Bridge. Further, Haswell CPUs will include one of three tiers of GT1, GT2, or GT3 processor graphics along with the AVX2 instruction set.

What is interesting about the recent report by The Verge is that previous rumors suggested that Haswell would have higher TDP ratings than both Sandy Bridge and Ivy Bridge. Considering Ivy Bridge has several 35W desktop models, and a few 17W mobile parts, the reported 10W TDP of Haswell seems to indicate that at least the mobile editions of Haswell will actually have much lower TDPs than Ivy Bridge. (It is not clear if detkop and non ultra-low-voltage (ULV) chips will see similar TDP improvements or not.)

The 10W TDP would mean that ultrabooks and other thin-and-light laptops could use smaller heatsinks and suggests that the processors will be more power efficient resulting in battery life improvements (which are always welcome). The Verge further quoted an Intel representative in stating that "It's really the first product we're building from the ground up for ultrabook."

While the lowest-power Haswell chips won’t be powerhouses on the performance front, with the improvements over Ivy Bridge to the CPU and GPU it should still handily best the company’s Atom lineup. Such a feat would allow Haswell to secure a spot powering future Windows 8 slates and other mobile devices where Atom is currently being used.

Just the fact that Intel has managed to get its next generation mainstream CPU architecture down to 10W is impressive, and I’m looking forward to see what kinds of devices such a low power x86-64 chip will enable.

Stay tuned for more Haswell news as the Intel Developer Forum (IDF) next week should be packed with new information. Here's hoping that the desktop chips manage some (smaller) TDP improvements as well!

Source: The Verge

New Low-Cost 35W Ivy Bridge Processors Coming

Subject: Processors | September 4, 2012 - 07:46 AM |
Tagged: sandy bridge, Ivy Bridge, Intel, core i3, 35w

Back in March of this year, Intel launched a slew of third generation Core Ivy Bridge processors. At the high end sat the Core i7-3770K with 4 cores, hyperthreading, 3.5 GHz clockspeed (3.9 GHz Turbo Boost), 8 MB L3 cache, and a 77W TDP for $332. The lineup went down in features – and price – from there all the way to the Core i5-3330S. The 3330S had four cores, 6 MB of L3 cache, a 65W TDP, and a clockspeed of 2.7 GHz (3.2 GHz Turbo Boost). Further, just about every CPU that was not a K, S, or T edition came equipped with the older HD 2500 integrated processor graphics. While the list comprised 18 new processors, the lower-end Core i3 Ivy Bridge CPUs were noticeably absent.

Fortunately, FanlessTech has managed to get ahold of pricing and specifications for five of those lower cost Intel chips. The new additions to Intel's lineup include three Ivy Bridge processors and two Sandy Bridge CPUs. Specifically, we have the i3-3240T, i3-3220T, Pentium G2100T, Pentium G645T, and Pentium G550T. All of those parts have a TDP of 35W and are priced very affordably.

Model   Cores / Threads Clockspeed  L3 Cache TDP Launch Price ($USD)
i3-3240T Ivy Bridge 2/4 2.90 GHz 3MB 35W $138
i3-3220T Ivy Bridge 2/4 2.80 GHz 3MB 35W $117
Pentium G2100T Ivy Bridge 2/2 2.60 GHz 3MB 35W $75
Pentium G645T Sandy Bridge 2/2 2.50 GHz 3MB 35W $64
Pentium G550T Sandy Bridge 2/2 2.20 GHz 2MB 35W $42

 

The Core i3-3240T and i3-3220T are dual core Ivy Bridge processors build on a 22nm process, and are priced at just over $100. The cheapest Ivy Bridge CPU is actually the Pentium G2100T at $75 so the barrier to entry for Intel’s latest chips is much lower than it was a few months ago. Intel’s second generation Core architecture is still alive and kicking as well with the Pentium G645T and G550T at $64 and $42 respectively.

Two specifications are still unkown: Turbo Boost clockspeeds (if any) and which version of processor graphics these chips will feature. On the graphics front, I think HD 2500 is a safe bet but Intel may throw everyone a curve ball and pack the higher-end processor graphics into the low end units – which are arguably the (computers) that need the better GPU the most.

Granted, these lower cost processors are not going to give you near the performance of the i7-3770K that we recently reviewed, but they are still important for low power and budget desktops. Bringing the power efficiency improvements of Ivy Bridge down to under $100 is definitely a good thing.

As far as availability, you can find some of the new low TDP processors at online retailers now (such as the Core i3-3220T), but others are not for sale yet. While I do not have any exact dates, they should be available shortly.

How would you put these low TDP dual cores to work?

Source: FanlessTech

AMD Adds New AMD FX-4130 CPU, Announces New Pricing for Desktop Processors

Subject: Processors | August 27, 2012 - 10:56 AM |
Tagged: amd, am3+, fx-4130

AMD has good news for those looking to build or upgrade an AMD powered system as they are lowering their prices on processors across the board as well as adding the new four core Socket AM3+ FX-4130, with a 3.8GHz base clock and 3.9GHz in Turbo.  It is not yet for sale but is expected to retail for $112, easily affordable for most users looking for a lower cost system.

AMD Price Moves Aug 2012.png

"The value proposition for the first generation AMD A-Series APUs is also compelling: A quad-core CPU and a DirectX® 11 highly-capable gaming GPU on a single-chip with more than 500 GFLOPs of compute power, for under $100 (A8 3850). Working together, the CPU and GPU can accelerate a range of applications to outperform a stand-alone CPU in some use cases. The lower-power first generation AMD A-Series APUs are even more affordable and are receiving positive reviews for small-form factor HTPCs as well.  Price reductions across the first generation AMD A-Series APUs stack are in effect now, so please check your local retailer!"

 

Source: AMD

Intel's new HD2500 on Linux

Subject: Processors | August 20, 2012 - 01:07 PM |
Tagged: linux, Ivy Bridge, Intel, i5-3470, hd 2500

The new Ivy Bridge processors introduced a new member of Intel's graphics processor called the HD 2500, which has received less than positive reviews as the previous HD 3000 outperforms it.  However those tests were for Windows applications and games, whereas the testing at Phoronix specifically pertains to the performance under Linux.  They compare the i5-2400S, i5-2500K, i5-3470, and i7-3770K together in a series of benchmarks to not only test the performance but also their compatibility with Linux.  It seems that perhaps the performance of the HD3000 and HD2500 are much closer in Linux than they were running under Windows, though both still lose out to the HD4000.

PH_linux_3740.jpg

"Since the launch of Intel's Ivy Bridge processors earlier this year there have been many benchmarks of the Intel Core i7 3770K with its integrated HD 4000 graphics and then more recently have been Linux testing of the Intel Core i7 3517UE from the CompuLab Intense-PC and Intel Core i7-3615QM as found on the Apple Retina MacBook Pro. The newest Intel Ivy Bridge chip to play with at Phoronix is the Intel Core i5 3470, which bears an Intel HD 2500 graphics core. In this article are benchmarks of the Intel HD 2500 Ivy Bridge graphics with the open-source Intel Linux graphics driver stack."

Here are some more Processor articles from around the web:

Processors

Source: Phoronix

PC Perspective Hardware Workshop 2012 @ Quakecon 2012 in Dallas, TX

Subject: Editorial, General Tech, Graphics Cards, Motherboards, Cases and Cooling, Processors, Memory, Systems, Storage, Mobile, Shows and Expos | August 9, 2012 - 07:30 PM |
Tagged: video, workshop, streaming, quakecon, prizes, live, giveaways

It is that time of year again: another installment of the PC Perspective Hardware Workshop!  Once again we will be presenting on the main stage at Quakecon 2012 being held in Dallas, TX August 2-5th.  

workshop_logo.png

Main Stage - Quakecon 2012

Saturday, August 4th, 2pm CT

Our thanks go out to the organizers of Quakecon for allowing us and our partners to put together a show that we are proud of every year.  We love giving back to the community of enthusiasts and gamers that drive us to do what we do!  Get ready for 2 hours of prizes, games and raffles and the chances are pretty good that you'll take something out with you - really, they are pretty good!

Our thanks for this year's workshop logo goes to John Pastor!!

Our primary partners at the event are those that threw in for our ability to host the workshop at Quakecon and for the hundreds of shirts we have ready to toss out!  Our thanks to NVIDIA, MSI Computer and Corsair!!

 

nvidia_logo_small.png

msi_logo_small.png

corsair_logo_small.png

Live Streaming

If you can't make it to the workshop - don't worry!  You can still watch the workshop live on our page right here as we stream it over one of several online services.  Just remember this URL: http://pcper.com/workshop and you will find your way!

Case Mod Competition

Along with the Hardware Workshop, PC Perspective is working with Modders Inc on the annual case mod contest!  There are two categories for the competition: "Scratch Built" and "In the Box" that will allow those that build their computer enclosures from the ground up to compete separately from those that heavily modify their existing cases and systems.

For more details, be sure to check out the on going thread at the Modders Inc Forums!

Prize List (will continue to grow!)

Continue reading to see the list of prizes for the workshop!!!

Source: PCPer

Gigabyte Unveils GA-H77N-WIFI Mini-ITX Motherboard

Subject: General Tech, Graphics Cards, Motherboards, Cases and Cooling, Processors, Chipsets, Memory, Displays | August 7, 2012 - 07:07 AM |
Tagged: Z77, motherboard, mini-itx, Intel, gigabyte, ga-h77n-wifi

During a European roadshow, Gigabyte showed off a new Mini-ITX form factor motherboard for the first time. Called the GA-H77N-WIFI, the motherboard is well suited for home theater and home server tasks. Based on the H77 chipset, it is compatible with the latest Intel Core i3 (coming soon), i5, and i7 "Ivy Bridge" processors. The board goes for an all-black PCB with minimal heatsinks on the VRMs, and the form factor is the same size as the motherboard that Ryan recently used in his Mini-ITX HTPC build.

ga_h77n_wifi.jpg

The GA-H77N-WIFI features a LGA 1155 processor socket, two DDR3 DIMM slots, PCI Express slot, two SATA 3Gbps ports, two SATA 6Gbps ports, and an internal USB 3.0 header. There are also two Realtek Ethernet controller chips and a Realtek audio chip.

Rear IO on the Mini-ITX motherboard includes:
  • 1 PS/2 port
  • 2 USB 3.0 ports
  • 2 HDMI ports
  • 1 DVI port
  • 2 Antenna connectors (WIFI)
  • 4 USB 2.0 ports
  • 2 Gigabit Ethernet ports
  • 1 Optical S/PDIF port
  • 5 Analog audio jacks

The dual Gigabit Ethernet ports are interesting. It could easily be loaded with open source routing software and turned into router/firewall/Wi-Fi access point. To really take advantage of the Ivy Bridge support, you could put together a nice media server and HTPC recording/streaming box (using something like SiliconDust's HDHomeRun networked tuners or Ceton's USB tuner since this board is very scarce in the way of PCI-E slots). What would you do with this Mini-ITX Gigabyte board?

Unfortunately, there is no word yet on pricing or availability, but the motherboard is likely coming soon. You can find more information on the motherboard over at tonymacx86, who managed to snag get some photos of the board.

Source: Tony Mac X86

Ivy Bridge-E after Haswell: I think I've gone cross-eyed

Subject: General Tech, Processors | August 5, 2012 - 11:12 PM |
Tagged: Ivy Bridge-E, Intel

According to VR-Zone, an Intel roadmap has surfaced which outlines the upper end of the company’s CPU product line through the end of 3rd Quarter 2013. The most interesting albeit also most confusing entry is the launch of Ivy Bridge-E processors in the quarter after the Haswell mainstream parts.

So apparently the lack of high-performance CPU competition unhooked Intel’s tick-tock-clock.

The latest Intel CPU product roadmap outlines the company’s expected product schedule through to the end of Q3 2013. The roadmap from last quarter revealed that Intel’s next architecture, Haswell, would be released in the second quarter of 2013 with only Sandy Bridge-E SKUs to satisfy the enthusiasts who want the fastest processors and the most available RAM slots. It was unclear what would eventually replace SBE as the enthusiast part and what Intel expects for their future release cycles.

2a.png

I can Haswell-E’zburger?

(Photo Credit: VR-Zone)

Latest rumors continue to assert that Sandy Bridge-E X79 chipset-based motherboards will be able to support Ivy Bridge-E with a BIOS update.

The downside: personally, not a big fan of upgrading CPUs frequently.

In the past I have never kept a motherboard and replaced a CPU. While I have gone through the annoyance of applying thermal paste – and guessing where Arctic Cooling stains will appear over the next 2 weeks – I tend to even just use the default thermal tape which comes with the stock coolers. I am not just cheap or lazy either; I simply tend to not feel a jump in performance unless I allow three to five years between CPU product cycles to pass by.

But that obviously does not reflect all enthusiasts.

But how far behind on the enthusiast architectures will Intel allow themselves to get? Certainly someone with my taste in CPU upgrades should not wait 8-10 years to upgrade our processors if this doubling of time-between-releases continues?

What do you think is the future of Intel’s release cycle? Is this a one-time blip trying to make Ivy Bridge scale up or do you expect that Intel will start releasing progressively more infrequently on the upper end?

Source: VR-Zone

AMD Hires Veteran CPU Architect in Jim Keller

Subject: Processors | August 1, 2012 - 05:38 AM |
Tagged: x86-64, x86, MIPS, Jim Keller, arm, amd, Alpha

There has been quite a bit of news lately from AMD, and very little of it good.  What has perhaps dominated the headlines throughout this past year was the amount of veteran AMD employees who have decided (or were pushed) to seek employment elsewhere.  Not much has been said from these departing employees, but Rory Read certainly started things off with a bang by laying off some 10% of the company just months into his tenure.

Now we finally have some good news in terms of employment.  AMD has hired a pretty big name in the industry.  Not just a big name, but a person who was one of the primary leads on two of AMD’s most successful architectures to date.  Jim Keller is coming back to AMD, and at a time where it seems AMD needs some veteran leadership who is very in touch with not just the industry, but CPU architecture design.

Jim was a veteran of DEC and worked on some of the fastest Alpha processors of the time.  Much could be written about DEC and how they let what could have been one of the most important and profitable architectures in computing history sit essentially on the back burner while they focused on seemingly dinosaur age computing.  After the Alpha was sold off and DEC sold away, Jim found his way to AMD and played a very important role at that company.

amd_logo.gif

The first product was helping to launch the K7, and worked primarily with system engineering.  The vast majority of design work for the K7 was finished by the time he signed on, but he apparently worked quite a bit on integrating it into the new socket architecture that was derived from the DEC Alpha.  Where Jim really earned his keep was in co-authoring the x86-64 specification and being lead architect on the AMD K8 series of processors.  While he left in 1999, the mark he left on AMD is essentially indelible.

After AMD he joined Sibyte (Broadcom) and was lead architect on a series of MIPS processors used in networking devices.  This lasted until 2003 and he again left the company seemingly more prosperous than when he began.

PA-Semi was the next stop and he worked again primarily on networking specific SOCs utilizing the PowerPC architecture.  So far, by counting fingers, Jim has worked on five major ISAs (Alpha, x86, x86-64, MIPS, and PowerPC).  These chips were able to power networking devices with 10 Gb throughput.  PA-Semi was then purchased by Apple in 2007/2008.

At Apple Jim was now Director of Platform Architecture and worked with yet another major ISA; ARM.  Jim worked to develop several major and successful products with the A4 and A5 processors that have powered the latest iPhone and iPad products from the Cupertino giant.  To say that this individual has had his fingers in some very important pies is an understatement.

Jim now rejoins AMD as CVP and Chief Architect of CPU Cores.  He will report directly to Mark Papermaster.  His primary job is to improve execution efficiency and consistency, as well as implement next generation features into future CPU cores which will keep AMD competitive with not only Intel, but other rising competitors in the low power space.  This is finally some good news for AMD as they are actually adding talent rather than losing it.  While Jim may not be able to turn the company around overnight, he does look to be an important piece of the puzzle with a huge amount of experience and knowhow with multiple CPU ISA.  If there is anyone that can tackle the challenges in front of AMD in the face of a changing world, this might be the guy.  So far he has had a positive impact in every stop he has made, and perhaps this could prove to be the pinnacle of his career.  Or it could be where his career goes to die.  It is hard to say, but I do think that AMD made a good hire with Jim.

Source: AMD

Dango Durango -- Next-Gen Xbox developer kit in the wild.

Subject: General Tech, Graphics Cards, Processors, Systems | July 31, 2012 - 05:35 PM |
Tagged:

Eurogamer and Digital Foundry believe that a next-generation Xbox developer kit somehow got into the hands of an internet user looking to fence it for $10,000. If the rumors are true, a few interesting features are included in the kit: an Intel CPU and an NVIDIA graphics processor.

A little PC perspective on console gaming news…

If the source and people who corroborate it are telling the truth: somehow Microsoft lost control of a single developer’s kit for their upcoming Xbox platform. Much like their Cupertino frenemies who lost an iPhone 4 in a bar which was taken and sold for $5000 to a tech blog, the current owner of the Durango devkit is looking for a buyer for a mere $10000. It is unlikely he found it on a bar stool.

Durango0.jpg.jpg

One further level of irony, the Xbox 360 alpha devkit were repurposed Apple Mac Pros.

Image source: DaE as per its own in-image caption.

Alpha developer kits will change substantially externally but often do give clues to what to expect internally.

The first Xbox 360 software demonstrations were performed on slightly altered Apple Mac Pros. At that time, Apple was built on a foundation of PowerPC by IBM while the original Xbox ran Intel hardware. As it turned out, the Xbox 360 was based on the PowerPC architecture.

Durango2.jpg.jpg

Huh, looks like a PC.

The leaked developer kit for the next Xbox is said to be running X86 hardware and an NVIDIA graphics processor. 8GB of RAM is said to be present on the leaked kit albeit that only suggests that the next Xbox will have less than 8GB of RAM. With as cheap as RAM is these days -- a great concern for PC gamers would be that Microsoft would load the console to the brim with memory and remove the main technical advantage of our platform. Our PCs will still have that advantage once our gamers stop being scared of 64-bit compatibility issues. As a side note, those specifications are fairly identical to the equally nebulous specs rumored for Valve’s Steam Box demo kit.

The big story is the return to x86 and NVIDIA.

AMD is not fully ruled out of the equation if they manage to provide Microsoft with a bid they cannot refuse. Of course practically speaking AMD only has an iceball’s chance in Hell of have a CPU presence in the upcoming Xbox – upgraded from snowball. More likely than not Intel will pick up the torch that IBM kept warm for them with their superior manufacturing.

PC gamers might want to pay close attention from this point on…

Contrast the switch for Xbox from PowerPC to X86 with the recent commentary from Gabe Newell and Rob Pardo of Blizzard. As Mike Capps has allured to – prior to the launch of Unreal Tournament 3 – Epic is concerned about the console mindset coming to the PC. It is entirely possible that Microsoft could be positioning the Xbox platform closer to the PC. Perhaps there are plans for cross-compatibility in exchange for closing the platform around certification and licensing fees?

Moving the Xbox platform closer to the PC in hardware specifications could renew their attempts to close the platform as has failed with their Games for Windows Live initiative. What makes the PC platform great is the lack of oversight about what can be created for it and the ridiculous time span for compatibility for what has been produced for it.

It might be no coincidence that the two companies who are complaining about Windows 8 are the two companies who design their games to be sold and supported for decades after launch.

And if the worst does happen, PC gaming has been a stable platform despite repetitive claims of its death – but could the user base be stable enough to handle a shift to Linux? I doubt that most would even understand the implications of proprietary platforms on art to even consider it. What about Adobe and the other software and hardware tool companies who have yet to even consider Linux as a viable platform?

The dark tunnel might have just gotten longer.

Source: Eurogamer

ARM, TSMC to Produce 64-bit Processors With 3D Transistors

Subject: Processors | July 24, 2012 - 09:07 AM |
Tagged: TSMC, ARMv8, arm, 64-bit, 3d transistors, 20nm

 

Yesterday ARM announced a multi-year partnership with fab TSMC to produce sub-20nm processors that utilize 3D FinFET transistors. The collaboration and data sharing between the two companies will allow the fabless ARM SoC company the ability to produce physical processors based on its designs and will allow TSMC a platform to further its process nodes and FinFET transistor technology. The first TSMC-produced processors will be based on the ARMv8 architecture and will be 64-bit compatible.

ARMv8.jpg

The addition of 3D transistors will allow the ARM processors to be even more power efficient and suitable for both mobile devices. Alternatively, it could allow for higher clockspeeds at the same TDP ratings as current chips. The other big news is that the chips will be moving to a 64-bit compatible design, which is huge considering ARM processors have traditionally been 32-bit. By moving to 64-bit, ARM is positioning itself for server and workstation adoption, especially with the recent ARM-compatible Windows 8 build due to be released soon. Granted, ARM SoCs have a long way to go before taking market share from Intel and AMD in the desktop and server markets in a big way but it is slowly but surely becoming more competitive with the x86-64 giants.

TSMC’s R&D Vice President Cliff Hou stated that the collaboration between ARM and TSMC will allow TSMC to optimize its FinFET process to target “high speed, low voltage and low leakage.” ARM further qualified that the partnership would give ARM early access to the 3D transistor FinFET process that could help create advanced SoC designs and ramp up volume production.

I think this is a very positive move for ARM, and it should allow them to make much larger inroads into the higher-end computing markets and see higher adoption beyond mobile devices. On the other hand, it is going to depend on TSMC to keep up and get the process down. Considering the issues with creating enough 28nm silicon to meet demand for AMD and NVIDIA’s latest graphics cards, a sub-20nm process may be asking a lot. Here’s hoping that it’s a successful venture for both companies, however.

You can find more information in the full press release.

Source: Maximum PC

AMD Blames Lackluster Earnings on Weak Economy

Subject: Processors | July 20, 2012 - 08:21 AM |
Tagged: quarterly earnings, loss, APU, amd

AMD recently released its Q2 2012 earnings (as did Intel), and things are continuing to look bleak for the number two x86-64 processor company. The company stated that the lower than expected numbers were the result of a weak economy and during a time of the year when people are not buying computers. The may be some truth to that as the second quarter is in the post-Christmas holiday season lul and before the big back-to-school retail push. On the economy front, it’s harder for me to say but without going political or armchair economist on you, the market seems better than it has been but is really still recovering–At least from a consumer perspective.

AMD reported revenue of $1.41 billion in the second quarter of 2012, which does not seem terrible, but when compared to Intel’s $13.5 billion Q2 revenue, and the fact that AMD’s numbers represent an 11-percent lower value than last quarter and 10-percent decrease versus Q2 2011, it’s easy to say that things are not looking good for the company.

According to Paul Lilly over at MaximumPC, when breaking AMD’s numbers down by business segment it gets even worse. Its Computing Solutions business fell 13-percent versus the previous quarter and Q2 2011. On the other hand, the company has the ever-so-slightly better news that the graphics card division stayed the same versus last year and was down 5-percent versus last quarter. The company was quoted as stating that the respective revenue drops were due to lower desktop sales in China and Europe and a “seasonally down quarter.”

PC Perspective’s Josh Walrath recently wrote up an editorial (note: pre-earnings call) that talks about AMDs new plan to focus on APUs, take on less risk, and push out new products faster. As a future-looking article, it talks about the impact of the company’s upcoming VIshera and Kaveri processors as well as AMD’s increased focus on heterogeneous system architectures. It remains to be seen if that new path for company will help them to make money or if it will hurt them. AMD cautions that Q3 2012 may not see increased revenue, but here’s hoping that they will be able to pull together for a strong Q4 and sell chips during the big holiday shopping season.

I for one am excited about the prospects of Kaveri and believe that HSA could work and is what AMD needs to focus on as it is one advantage that they have over NVIDIA and Intel – NVIDIA does not have an x86-64 license and Intel’s processor graphics leave room for improvement, to put it mildly. AMD may not have the best CPU cores, but it’s not an inherently bad design and where they are moving with the full convergence of the CPU and GPU is much farther ahead of the other big players.

Read more about AMD's Q2 2012 earnings (transcript).

Source: Maximum PC

AMD Social Media Reviewers Wanted - 2000 AMD APUs Available Free!

Subject: General Tech, Processors | July 12, 2012 - 12:51 PM |
Tagged: amd, llano, APU, comiccon

If you are in the San Diego area today or tomorrow, you should make it a point to stop by Belo San Diego (http://www.belosandiego.com/ 438 E Street), a night club near the convention area, to visit with the AMD and the Geek and Sundry group.

day.jpg

Felicia Day, most popular for her role in the web-series The Guild, will be part of the on going event between 10am and 2am both today (the 12th) and tomorrow sponsored by AMD.  She is excited to be there - just look!

If you stop by the Belo nightclub during those hours you can take home a FREE AMD A8-3870K APU (with accompanying motherboard) if you agree to use your social media outlets (Twitter and Facebook) to tell your friends about the experience.  You will in fact become an AMD Social Media Reviewer!

Sorry, if you aren't in the San Diego area, you are out of luck on this promotion.  This is just another reason why attending ComicCon is so enticing!

Source: AMD

Can a 12-Core ARM Cluster hit critical mass?

Subject: Processors | June 26, 2012 - 02:08 PM |
Tagged: arm, cortex-a9, e-350, i7-3770k, z530, Ivy Bridge, atom, Zacate

Taking a half dozen PandaBoard ESes from Texas Instruments that have a 1.2GHz dual-core ARM Cortex-A9 processor onboard, Phoronix built a 12-core ARM machine to test out against AMD's E-350 APU as well as Intel's Atom Z530 and a Core i7 3770K.  Before you you make the assumption that the ARM's will be totally outclassed by any of these processors, Phoronix is testing performance per Watt and the ARM system uses a total of 31W when fully stressed and idles below 20W, which gives ARM a big lead on power consumption. 

Phoronix tested out these four systems and the results were rather surprising as it seems Intel's Ivy Bridge is a serious threat to ARM.  Not only did it provide more total processing power, its performance per Watt tended to beat ARM and more importantly to many, it is cheaper to build an i7-3770K system than it is to set up a 12-core ARM server.  The next generation of ARM chips have some serious competition.

Phoronix12ARM.jpg

"Last week I shared my plans to build a low-cost, 12-core, 30-watt ARMv7 cluster running Ubuntu Linux. The ARM cluster that is built around the PandaBoard ES development boards is now online and producing results... Quite surprising results actually for a low-power Cortex-A9 compute cluster. Results include performance-per-Watt comparisons to Intel Atom and Ivy Bridge processors along with AMD's Fusion APU."

Here are some more Processor articles from around the web:

Processors

 

Source: Phoronix

Intel Introduces Xeon Phi: Larrabee Unleashed

Subject: Processors | June 19, 2012 - 08:46 AM |
Tagged: Xeon Phi, xeon e5, nvidia, larrabee, knights corner, Intel, HPC, gpgpu, amd

Intel does not respond well when asked about Larabee.  Though Intel has received a lot of bad press from the gaming community about what they were trying to do, that does not necessarily mean that Intel was wrong about how they set up the architecture.  The problem with Larrabee was that it was being considered as a consumer level product with an eye for breaking into the HPC/GPGPU market.  For the consumer level, Larrabee would have been a disaster.  Intel simply would not have been able to compete with AMD and NVIDIA for gamers’ hearts.
 
The problem with Larrabee and the consumer space was a matter of focus, process decisions, and die size.  Larrabee is unique in that it is almost fully programmable and features really only one fixed function unit.  In this case, that fixed function unit was all about texturing.    Everything else relied upon the large array of x86 processors and their attached vector units.  This turns out to be very inefficient when it comes to rendering games, which is the majority of work for the consumer market in graphics cards.  While no outlet was able to get a hold of a Larrabee sample and run benchmarks on it, the general feeling was that Intel would easily be a generation behind in performance.  When considering how large the die size would have to be to even get to that point, it was simply not economical for Intel to produce these cards.
 
phi_01.jpg
 
Xeon Phi is essentially an advanced part based on the original Larrabee architecture.
 
This is not to say that Larrabee does not have a place in the industry.  The actual design lends itself very nicely towards HPC applications.  With each chip hosting many x86 processors with powerful vector units attached, these products can provide tremendous performance in HPC applications which can leverage these particular units.  Because Intel utilized x86 processors instead of the more homogenous designs that AMD and NVIDIA use (lots of stream units doing vector and scalar, but no x86 units or a more traditional networking fabric to connect them).  This does give Intel a leg up on the competition when it comes to programming.  While GPGPU applications are working with products like OpenCL, C++ AMP, and NVIDIA’s CUDA, Intel is able to rely on many current programming languages which can utilize x86.  With the addition of wide vector units on each x86 core, it is relatively simple to make adjustments to utilize these new features as compared to porting something over to OpenCL.
 
So this leads us to the Intel Xeon Phi.  This is the first commercially available product based on an updated version of the Larrabee technology.  The exact code name is Knights Corner.  This is a new MIC (many integrated cores) product based on Intel’s latest 22 nm Tri-Gate process technology.  The details are scarce on how many cores this product actually contains, but it looks to be more than 50 of a very basic “Pentium” style core;  essentially low die space, in-order, and all connected by a robust networking fabric that allows fast data transfer between the memory interface, PCI-E interface, and the cores.
 
intelphi.jpg
 
Each Xeon Phi promises more than 1 TFLOP of performance (as measured by Linpack).  When combined with the new Xeon E5 series of processors, these products can provide a huge amount of computing power.  Furthermore, with the addition of the Cray interconnect technology that Intel acquired this year, clusters of these systems could provide for some of the fastest supercomputers on the market.  While it will take until the end of this year at least to integrate these products into a massive cluster, it will happen and Intel expects these products to be at the forefront of driving performance from the Petascale to the Exascale.
 
phi_02.jpg
 
These are the building blocks that Intel hopes to utilize to corner the HPC market.  Providing powerful CPUs and dozens if not hundreds of MIC units per cluster, the potential computer power should bring us to the Exascale that much sooner.
 
Time will of course tell if Intel will be successful with Xeon Phi and Knights Corner.  The idea behind this product seems sound, and the addition of powerful vector units being attached to simple x86 cores should make the software migration to massively parallel computing just a wee bit easier than what we are seeing now with GPU based products from AMD and NVIDIA.  The areas that those other manufacturers have advantages over Intel are that of many years of work with educational institutions (research), software developers (gaming, GPGPU, and HPC), and industry standards groups (Khronos).  Xeon Phi has a ways to go before being fully embraced by these other organizations, and its future is certainly not set in stone.  We have yet to see 3rd party groups get a hold of these products and put them to the test.  While Intel CPUs are certainly class leading, we still do not know of the full potential of these MIC products as compared to what is currently available in the market.
 

The one positive thing for Intel’s competitors is that it seems their enthusiasm for massively parallel computing is justified.  Intel just entered that ring with a unique architecture that will certainly help push high performance computing more towards true heterogeneous computing. 

Source: Intel

Live Blog: AMD Fusion Developer Summit 2012 (AFDS)

Subject: Graphics Cards, Processors, Shows and Expos | June 14, 2012 - 08:46 AM |
Tagged: live blog, arm, APU, amd, AFDS

afdslogo.png

Day 3 - Thursday, June 14th

We are here at AFDS 2012 for the day 3 keynotes - join us as find out what else AMD has in store.  

If you are looking for Tuesday or Wednesday keynotes and information on the announcement of the HSA Foundation, you can find it below, after the break!