Tag: SOC

Integration Gives iPhone an Unbeatable Advantage

A6 ,chip image (Apple)There was only one real surprise when iFixit.com did its by-now ritual teardown of the new iPhone 5. The phone sports a 1440 milliamp-hour battery just a hair bigger than the battery in the  iPhone 4S. Yet despite going to a bigger display, boosting processor performance, and using faster but more power-hungry LTE wireless, the new phone seems to deliver about the same battery life as its predecessor. And instead of having to go to a bigger battery, Apple was able to use improvements in case and display design to reduce the iPhone’s thickness and weight markedly.

This is the result of obsessive engineering, not magic. Apple uses its control over every aspect of the iPhone’s design, from the silicon to the software, to fine-tune a device that squeezes maximum performance from minimal resources. This gives Apple an enormous advantage over all competitors save Research In Motion (whose severe problems are the result of its inability to read and respond to the changing market for BlackBerry, not its engineering.)

 In his detailed examination of the iPhone 5, the redoubtable Anand Lal Shimpi found compelling evidence that the iPhone 5’s A6 system-on-chip uses custom, Apple-designed ARM processor cores. In previous A-series SOCs, Apple had customized Samsung ARM designs, mostly by pruning circuitry that the iPhone and iPad didn’t need. No USB ports or SD card slots, no need to have controllers for unused devices (its then nature of chips the even unused circuits increase the power draw, not by much but significantly in a design where every microwatt counts.) With the A6, Apple takes the customization a step further, achieving complete control over the heart of this system.

With a fully customized SOC, Apple could then fine-tune the software to wring out every microgram of performance while minimizing power consumption. Even the compiler used to generate  iOS code can be tweaked to optimize apps’ power consumption and performance. The tradeoffs between battery size and run time are still there–even Apple cannot escape the laws of physics–but the terms of trade are improved dramatically.

There’s no way Android can match this. Google has to write code that can support a wide variety of SOCs, including those from NVIDIA, Qualcomm, Texas Instruments, and Samsung. Android devices use several graphics systems and provide support for assorted peripherals. Code designed to run on heterogeneous systems will never be as efficient as Apple’s singleminded approach. Things are somewhat better in the Windows Phone 8 world, where the initial offerings all use a Qualcomm Snapdragon SOC. We’ll see how that afffects battery life and performance when the phones ship.

Quad Core Smartphones: What it Will Take to Become Relevant

hedgeThere has been a lot of industry discussion on multi-core smartphones in the past year, and the dialog has increased with NVIDIA’s launch of Tegra 3, a quad core SOC targeted to phones and tablets. The big question lingering with all of these implementations particularly with phones is, what will end users do with all those general purpose compute units that provide significant incremental benefit? In the end, it’s all about the improved experience that’s relevant, unique, demonstrable, and easily marketable.

Multi-Core Background

Before we talk usage models, we first have to get grounded on some of the technology basics. First, whether it’s a multi-core server, PC, tablet or phone, many these things must exist to fully take advantage of more than one general purpose computing core in any platform:

  • operating system that efficiently supports multiple cores, multitasking across cores, and mullti-threaded apps
  • applications that efficiently take advantage of multiple cores
  • intelligent energy efficiency tradeoffs

Once those elements get into place, you have an environment where multiple cores can be leveraged. The next step is to optimize the platform for energy efficiency. All of the hardware and software platform elements, even down to transistors, must be optimized for low power when you need it and high performance when you need it. The Tegra 3 utilizes a fifth core, which NVIDIA says initiates when extremely low power state is required.

Assuming all the criteria above are met, then it comes down to what an end user can actually do with a phone with four cores.

Modularity Could Be the Key

Quad core phones could potentially add value in “modular” usage environments. While there have been a lot of attempts at driving widespread modularity, most haven’t been a big hit. I personally participated on the Device Bay Consortium when I was at Compaq, along with Intel and Microsoft. It didn’t end up materializing into anything, but the concept at the time from an end user perspective was solid.

Today and beyond, smartphone modularity is quite different than Device Bay’s “modules”. The smartphone concept is simple; use a high powered smartphone which can then extend to different physical environments. These environments span entertainment to productivity. Here are just a few of today’s examples of modularity in use today:

These are all forms of today’s modularity with different levels of interest, penetration, and adoption.

So what could quad core potentially add to the mix? Here are some potential improved usages:

  • Modular video and photo editing. These apps have historically always been multithreaded and could leverage a clamshell “dock” similar to the Lapdock or Multimedia Dock.
  • Modular multi-tab web browsing. Active browser tabs require a lot of performance and overhead. Just use Chrome PC browser and check your performance monitor. iOS5 actually halts the tab when moving to another tab forcing the user to reload the tab.
  • Modular games that heavily utilize a general purpose processor. Caveat here is that most of the games leverage the GPU a lot more than a general purpose CPU. It all depends on how the game is written, extent of AI use, UI complexity, where physics are done, and how the resources are programmed.
  • Modular natural user interface. While plugged in and “docked” at the desk or living room, the smartphone could power interfaces like improved voice control and “air” gestures. This may sound like science fiction, but the XBOX 360 is doing it today with Kinect.
  • Multitasking: Given enough memory and memory bandwidth, more cores typically means better multitasking.

Will It Be Relevant?

Many things need to materialize before anyone can deem a quad core smartphone a good idea or just a marketing idea for advanced users. First, smartphones actually need to ship with quad cores and a modular-capable OS. The HTC Edge is rumored to be the first. Then apps and usage models outlined above need to be tested by users and with benchmarks. Users will have to first “get” the modularity concept and notice an experiential difference. Moving from standard phone to modular experience must be seamless, something that Android 4.0 has the potential to deliver. Finally, some segments of users like enthusiasts will need to see the benchmarks to be swayed to pay more over a dual core phone.

There is a lot of proving to do on quad core smartphones before relevance can be established with any market segment beyond enthusiasts. Enthusiast will always want the biggest and baddest spec phone on the block but marketing to different segments, even if it provides an improved experience, will be a challenge.