13 Comments

Summary:

New details have emerged which suggest chip maker Palo Alto Semiconductor (PA Semi) might not be the hive mind behind the iPad’s “A4” processor as was widely expected. In case you missed it, the A4 is the diminutive custom silicon that lies at the heart of […]

a4_thumb

New details have emerged which suggest chip maker Palo Alto Semiconductor (PA Semi) might not be the hive mind behind the iPad’s “A4” processor as was widely expected.

In case you missed it, the A4 is the diminutive custom silicon that lies at the heart of Apple’s new iPad. It’s the wee beasty that has the raw power to make Magic Move work so smoothly in the upcoming Keynote app, while providing the intelligence to manage energy efficiently enough to squeeze 10 hours of actual use out of the iPad between charges. Oh, and it runs at 1Ghz and is fuelled by unicorn tears, or something.

Anyone with an iPhone (and everyone who has ever relied on laptops to do a days work) knows that there’s usually a big difference between a mobile device’s advertised and actual battery life. So, unless Steve Jobs is lying through his teeth, how exactly does the iPad’s A4 processor manage to deliver its number-crunching goods over such a long period of time?

Certainly Apple’s developments in battery design help a lot, but it’s thought that the real magic happens in the custom-designed processor itself. Venturebeat.com’s Paul Boutin has been investigating the A4, and pushing chip engineers for answers. In an article published on the weekend, he offers the following (possible) explanation;

Apple has invested heavily in OpenCL and LLVM, which are technologies to distribute work across multiple CPUs and multiple GPUs. In this Apple is different than other mobile devices: other vendors want video decoding and 3D games at a good rate, but often leave the GPU mostly idle.

Apple is looking to drive a lot of work through the GPU all the time, as part of any application. For Apple, it makes sense to put a lot of GPU cores in the chip. It even makes sense to put in so much GPU that the chip would overheat, but throttle back the ARM clock speed to leave more thermal envelope for the GPUs to run.

Ah, right then. Magic. Got it.

Terribly Clever

This all sounds plausible, and makes Apple’s 2008 purchase of PA Semi (a snap at only $278 million) seem like a terribly clever move. And since we have yet to see a new custom brain in any iPhone, the iPad offered the most likely candidate as the first recipient of the chip maker’s special silicon.

Only, it’s not. Boutin adds the following;

A very trusted source tells me: PA Semi didn’t do the A4. It was the existing VLSI team. Apple has made custom chips for years like the Northbridges for G4 and G5.

So, if the iPad didn’t get the PA Semi treatment as we originally thought, what’s going on? $278 million is an awful lot of money (even for a company with billions in the bank), and I’d have thought we’d start seeing the results of that purchase by now.

If we haven’t yet seen the full might and majesty of PA Semi’s magic in Apple’s mobile offerings, that might all change soon. After all, we’re just months away from the anticipated 4th generation iPhone…

Back to Front

Maybe I’ve got this all back to front? Was the acquisition of PA Semi — like the more recent acquisition of music streaming service Lala — not so much about Apple getting its hands on new technology, but more about securing the mad skillz of new engineers? If that’s the case, the iPad may be the fruits of that acquisition after all.

Either way, if the next generation iPhone inherits any of the genetic characteristics of its iPad big brother, what might we expect from Apple’s next smartphone? A blistering-fast processor, perhaps, light-years ahead of the best competing handset? Insanely long battery life, perhaps two or three days between charges?

One thing is for sure; last month Steve Jobs very deliberately redefined Apple as a mobile devices company. In the last few years, the company has aggressively enhanced the processing performance and battery life of all its products, from MacBooks to iPods to iPhones and now, of course, the iPad. A breakthrough advancement in one device ultimately migrates across product lines into another, until we’re left with an ecosystem of devices that offer unrivalled power and interoperability. It’s those refinements that have helped sell MacBooks at record levels in spite of a global recession, and allowed the iPhone to steal valuable market share from well-entrenched competitors.

So with all these remarkable advancements in battery life, power management, custom silicon and hardware/software interoperability in mind, ask yourself – what can we expect to see in the next iPhone? Looking at the iPad’s A4 processor as a guide, I’m beginning to think it’ll be the most significant iPhone revision Apple has ever made. And we don’t have very long to wait before we’ll know for sure.

You’re subscribed! If you like, you can update your settings

  1. “how exactly does the iPad’s A4 processor manage to deliver its number-crunching goods over such a long period of time?”

    No multi-tasking.

    I can’t imagine that processor being that amazing. Intels 1.6Ghz pintrail atom nets me a realistic 12 hours of web surfing and thats having to run windows 7 the entire time. I really don’t understand why Apple keeps flaunting typical battery life as something revolutionary. My macbook and my lenovo get the same 7 hour battery life, yet Apple claimed its macbook battery was revolutionary…

  2. I’ll go ahead and throw cold water on this, just because there are several microprocessor design firms with valuations over a quarter of a billion dollars, and absolutely none of them have come up with a miraculous new chip so revolutionary that everything else before it becomes garbage. El Jobso himself has said it. Even if there is such a shop, someone at Intel/Freescale/AMD/Qualcomm et al would pay more than Apple to buy or license anything that might be an existential threat to their core business. Intel released Itanium and bought Alpha from HP just to kill any competition for their new product.

  3. “$278 million is an awful lot of money (even for a company with billions in the bank)”

    If my math is not out of whack, this is like saying I have $50 bucks (50 billion in the bank) on me and I just spent $0.28 cents (278 million) on a candy bar? Seems pretty cheap to me. If for no other reason than to keep them competing against their own iPhone chips.

  4. to understand why Apple got into chips with PA Semi you need to look at the mobile platform play they are creating. The A4 goes hand in hand with what they are trying to sustain – a controlled, “closed” platform and ecosystem.

    wrote a bunch here – http://stevecheney.posterous.com/apple-the-platform-company

  5. Go to anandtech.com and read Anand Lal Shimpi’s two articles on MBP vs Windows laptop battery life tests. He posits that Mac OS X is significantly more efficient than Windows Vista, and that the MBP’s rated battery life is spot-on.

    http://www.anandtech.com/mac/showdoc.aspx?i=3582
    http://www.anandtech.com/mac/showdoc.aspx?i=3580&p=4

  6. I believe the Tegra 2 chip is also supposed to be totally insane when it comes to fast processing and still giving long battery life. Notion Ink’s tablet with the Pixel Qi display is supposed to give 20 to 30 hours use in a package that’s smaller than the iPad. I think most of the gains are being made by the revolutionary display which uses next to no power. However, the Tegra 2 chip in other products has been said to be very thrifty in using power.

    I’m hoping Apple/PA Semi will come up with some miracle chip to give them an edge over the competition, but Apple still has an advantage of building a particular chip that matches each device perfectly to get a tightly integrated package with the best traits possible for consumers.

  7. Stop hyping the next iPhone so that everyone gets disappointed when it doesn’t do backflips and cook you breakfast.

    1. Waaaa! No backflips? :o(

  8. Rumors continue to swirl around the A4. For a more thoughtful dissection of the A4, see my blog at

    http://markstechchat.blogspot.com/.

    Mark Hibben

  9. iPad E-Books Have No Part in Adobe’s Story – jkOnTheRun Thursday, February 18, 2010

    [...] few organizations that wants to control the hardware and the software for the entire experience. The development of the iPad’s A4 CPU exemplifies that more than any other recent example. Why be dependent on [...]

  10. iPad e-Books Have No Part in Adobe's Story Thursday, February 18, 2010

    [...] the software for the entire experience, as exemplified by the development of the iPad’s A4 CPU. why be dependent on [...]

Comments have been disabled for this post