Intel and IBM and TSMC and Samsung have all competed against one another in the area of shrinking the size of the design rules that govern their production lines for processors. Each new successively smaller generation has to be tested, piloted and put into production with big amounts of failed product along the way. And even as the point of diminishing returns comes with each new process shrink, the drive is on to continue the march to progress, smaller chips, and new partners along the way.
Monday IBM announced a partnership with UK chip developer ARM to develop 14-nm chip processing technology. The news confirms the continuation of an alliance between both parties that launched back in 2008 with an overall goal to refine SoC density, routability, manufacturability, power consumption and performance.
Interesting that IBM is striking out so far away from the current state of the art processing node for silicon chips. 22nm or there abouts is the what most producers of flash memory are targeting for their next generation product. Smaller sizes mean more chips per wafer, higher density means storage sizes go up for both flash drives and SSDs without increasing in physical size (who wants to use brick sized external SSDs right?). Too, it is interesting that ARM is the partner with IBM for their farthest target yet in chip production design rule sizes. But it appears that System-on-Chip (SoC) designers like ARM are now state of the art producers of power and waste heat optimized computing. Look at Apple’s custom A4 processor for the iPad and iPhone. That chip has lower power requirements than any other chip on the market. It is currently leading the pack for battery life in the iPad (10 hours!). So maybe it does make sense to choose ARM right now as they can benefit the most and the fastest from any shrink in the size of the wire traces used to create a microprocessor or a whole integrated system on a chip. Strength built on strength, that’s a winning combination and shows that IBM and ARM have an affinity for the lower power consumption future of cell phone and tablet computing.
But consider this also, the last article I wrote about Tilera’s product plans regarding cloud computing in a box. ARM chips could easily be the basis for much lower power, much higher density computing clouds. Imagine a GooglePlex style datacenter running ARM CPUs on cookie trays instead of commodity Intel parts. That’s a lot of CPUs and a lot less power draw, both big pluses for a Google design team working on a new data center. True, legacy software concerns might over rule a switch to lower power parts. But if the cost of electricity would offset the opportunity cost of switching to a new CPU (an having to re-compile software for the new chip) then Google would be crazy not to seize up on this.
AppleInsider calls a few strikes against hyperbole and supposition found in articles written about the Apple iPad A4 processor. Here now is a more likely accounting of what Apple’s chip design mergers and acquisitions really bought for the iPad development team.
Another report, appearing in The New York Times in February, stated that Apple, Nvidia and Qualcomm were all working to develop their own ARM-based chips before noting that “it can cost these companies about $1 billion to create a smartphone chip from scratch.” Developing an SoC based on licensed ARM designs is not “creating a chip from scratch,” and does not cost $1 billion, but the article set off a flurry of reports that said Apple has spent $1 billion on the A4.
Thankyou AppleInsider for trying to set the record straight. I doubted the veracity of the NYTimes article when I saw that $1Billion figure thrown around (seems more like the price of a Intel chip development project which is usually from scratch). And knowing now from this article here (link to PA Semi historical account), that PA Semi made a laptop version of a dual core G5 chip, leads me to believe power savings is something they would be brilliant at engineering solutions for (G5 was a heat monster, meaning electrical power use was large). P.A. Semi was going to made the G5 power efficient enough to fit into a laptop and they did it, but Apple had already migrated to Intel chips for its laptops.
Intrinsity + P.A. Semiconductor + Apple = A4. Learning that Intrinsity is an ARM developer knits a nice neat picture of a team of chip designers, QA folks and validation folks who would all team up to make the A4 a resounding success. No truer mark of accomplishment can be shown for this effort than Walt Mossberg and David Pogue stating in reviews of the iPad yesterday they both got over 10 hours of run time from their iPads. Kudos to Apple, you may not have made a unique chip but you sure as hell made a well optimized one. Score, score, score.
Following further articles published on the Apple iPad cpu, new reports are surfacing the custom CPU Apple created called the A4 may be an ARM Cortex A8 single core cpu with integrated graphics GPU and controller logic.
The custom A4 processor in the iPad is in reality a castrated Cortex A8 ARM design, say several sources.
This is truly interesting, and really shows some attempt to optimize the chips with ‘known’ working designs. Covering the first announcement of the A4 chip by Brightside of News, I tried to argue that customizing a chip by licensing a core design from ARM Holdings Inc. isn’t all that custom. Following this Ashlee Vance wrote in the NYTimes the cost of development for the A4 ‘could be’ upwards of $1Billion. And now just today MacNN/Electronista is saying Apple used the ARM A8. By this I mean the ARM Cortex A8 is a licensed core already being used in the Apple iPhone 3GS. It is a proven, known cpu core that engineers are familiar with at Apple. Given the level of familiarity, it’s a much smaller step to optimize that same CPU core for speed and integration with other functions. Like for instance the GPU or memory controllers can be tightly bound into the final CPU. Add a dose of power management and you got good performance and good battery life. It’s not cutting edge to be sure, but it is more guaranteed to work right out of the gate. That’s a bloodthirsty step in the right direction of market domination. However, the market hasn’t quite yet shown itself to be so large and self sustaining that slate devices are a sure thing in the casual/auxiliary/secondary computing device market. You may have an iPhone and you may have a laptop, bu this device is going to be purchased IN ADDITION not INSTEAD OF those two existing device markets. So anyone who can afford a third device is probably going to be the target market for iPad as opposed to creating a new platform for people that want to substitute an iPad for either the iPhone or laptop.
What’s the point of licensing computer chip designs from another company if it costs about the 1/3 the price of building it yourself? That seems like a rhetorical question, but I always assumed that people who licensed technology from ARM holdings were aiming to save tons of money compared to fabricating the chips themselves. So how does the Apple iPad A4 cpu figure into this? Well it’s a custom CPU, but according to NYTimes creating a new cpu is serious business.
In bypassing a traditional chip maker like Intel and creating its own custom ARM-based processor for the iPad, Apple has likely incurred an investment of about $1 billion, a new report suggests.
After reading the NYTimes article linked to within this article I can only conclude it’s a very generalized statement that it costs $1Billion to create a custom chip. The exact quote from the NYTimes article author Ashlee Vance is: “Even without the direct investment of a factory, it can cost these companies about $1 billion to create a smartphone chip from scratch.”
Given that is one third the full price of building a chip fabrication plant, why so expensive? What is the breakdown of those costs. Apple did invest money in PA Semiconductor to get some chip building expertise (they primarily designed chips that were fabricated at overseas contract manufacturing plants). Given Qualcomm has created the Snapdragon CPU using similar cpu cores from ARM Holdings Inc., they must have $1Billion to throw around too? Qualcomm was once dominant in the cell phone market licensing its CDMA technology to the likes of Verizon. But it’s financial success is nothing like the old days. So how does Qualcomm come up with $1Billion to develop the Snapdragon CPU for smartphones? Does that seem possible?
Qualcomm and Apple are licensing the biggest building blocks and core intellectual property from ARM, all they need to do is route and place and verify the design. Where does the $1Billion figure come into it? Is it the engineers? Is it the masks for exposing the silicon wafers? I argue now as I did in my first posting about the Apple A4 chip, the chip is an adaptation of intellectual property, a license to a CPU design provided by ARM. It’s not literally created from ‘scratch’ starting with no base design or using completely new proprietary intellectual property from Apple. This is why I am confused. Maybe ‘from scratch’ means different things to different people.
“iPad is powered by our own custom silicon. We have an incredible group that does custom silicon at Apple,” company co-founder Steve Jobs said during Wednesday’s keynote. “We have a chip called A4, which is our most advanced chip we’ve ever done that powers the iPad. It’s got the processor, the graphics, the I/O, the memory controller — everything in this one chip, and it screams.”
Getting back to Apple A4, Steve Jobs incorrectly addressed Apple A4 as a CPU. We’re not sure was this to keep the mainstream press enthused, but A4 is not a CPU. Or we should say, it’s not just a CPU. Nor did PA Semi/Apple had anything to do with the creation of the CPU component.
Interesting info on the Apple A4 System on Chip which is being used by the recently announced Ipad tablet computer. The world of mobile, low power processors is dominated by the designs of ARM Holdings Inc. Similarly ARM is providing the graphics processor intellectual property too. So in the commodity CPU/GPU and System on Chip (SoC) market ARM is the only way to go. You buy the license you layout the chip with all the core components you license and shop that around to a chip foundry. Samsung has a lot of expertise fabricating these chips made to order using the ARM designs. But Apparently another competitor Global Foundries is shrinking its design rules (meaning lower power and higher clock speeds) and may become the foundry of choice. Unfortunately outfits like iFixit can only figure out what chips and components go into an electronics device. They cannot reverse engineer the components going into the A4, and certainly anyone else would probably be sued by Apple if they did spill the beans on the A4’s exact layout and components. But because everyone is working from the same set of Lego Blocks for the CPUs and GPUs and forming them into full Systems on a Chip, some similarities are going to occur.
One thing pointed out in this article is the broad adoption of the same clockspeed for all these ARM derived SoCs. 1Ghz is the clock speed across the board despite differences in manufacturers and devices. The reason being everyone is using the same ARM cpu cores and they are designed to run optimally at the 1Ghz clock rate. So the more things change (meaning faster and faster time to market for more earth shaking designs) the more they stay the same (people adopt commodity CPU designs and become more similar in performance). It will take a big investment for Apple and PA Semiconductor to really TRULY differentiate themselves with a unique and different and proprietary CPU of any type. They just don’t have the time, though they may have the money. So when Jobs tells you something is exclusive to Apple, that may be true for industrial design. But for CPU/GPU/SoC, … Don’t Believe the Hype surround the Apple A4.
NYTimes weighs in on the Apple A4 chip and what it means for the iPad maintaining its competitive advantage. NYTimes gives Samsung more credit than Apple because they manufacture the chip. What they will not speculate on or guess at is ARM Holdings Inc. sale of licenses to it’s Cortex A-9 to Apple. They do hint that the nVidia Tegra CPU is going to compete directly against Apple’s iPad using the A4. However, as Steve Jobs has pointed out more than once, “Great Products Ship”. And anyone else in the market who has licensed the Cortex A-9 from ARM had better get going. You got 60 days or 90 days depending on your sales/marketing projections to compete directly with the iPad.