Tag: Texas Instruments

The Case for Intel’s Future Smartphone Success

In my many weekly conversations with industry insiders we discuss Intel’s chances in mobility markets, specifically smartphones. Few people are betting against Qualcomm and for very good reason in that they are entrenched at handset vendors and their 2012 roadmap, at least on paper, looks solid. What few are discussing is how Intel will pick up market share. My last column on Intel’s smartphone efforts outlined what Intel needs to demonstrate quickly to start gaining share and getting people to believe they can be a player. Now I want to take a look at why I believe Intel can and will pick up relevant market share over the next three years.

Intel Finally Broke the Code with Medfield

This isn’t Intel’s first time in mobility. Intel owned XScale, an ARM-based mobile processor that was in the most popular WinCE devices like the Compaq iPaq, one of the more popular Pocket PCs. XScale products even powered Blackberrys for a time as well. Intel sold the entire XScale mobile application processor business to Marvell in 2006 for $600M. This move was driven by Intel’s desire to focus on X86 designs. What followed were some failed mobile attempts with Menlo and Moorestown, two low power, Atom-branded processors that made their way into MIDs (Mobile Internet Devices). It appeared that Intel would make grand announcements with big names like LG for smartphones then nothing would happen afterward. Things are very different with Medfield. Handsets are at China Unicom in testing for Lenovo and Motorola announced their handsets would be at carriers for the summer.

Medfield is a huge step forward in design and integration for Intel. First, it combines the application processor with I/O capabilities on a single chip. This saves handset makers integration time and board space. Secondly, it is paired with the Intel XMM 6260 radio based on the Infineon Wireless Solutions (WLS) acquisition. This increases the Intel revenue BOM (Bill of Material) and also helps with handset integration. Finally, Intel has embraced the Android mobile OS in a huge way with a large developer investment and will provide optimized drivers for Medfield’s subsystems. This move is in contrast to their MeeGo OS efforts that didn’t go anywhere. Intel has even gone to the effort to emulate ARM instructions so that it can run native apps that talk directly to ARM. These apps are typically games that need to be closer to the hardware. This is a very good start for Intel, but as I tell my clients, if there are 10 steps to mobile silicon success, Intel just successfully crossed step 3.

It’s a Tough Smartphone Market

Intel made some very serious headway with Medfield, but it is a very competitive market out there. According to IDC, in Q4 2011, Apple and Samsung combined to garner almost 50% of the smartphone market. As I pointed out in my previous column, Apple already designs their A-Series processors and I don’t see that changing. I expect Samsung with the exception of the very low end to lean into their own Exynos silicon. Nokia at 12% Q4 smartphone share is tied to Windows Phone and Qualcomm at least for the short term. Struggling RIM doesn’t need another variable to worry about with their muddled operating system strategy and is currently tied to Qualcomm. Finally, HTC is rumored to tie up with NVIDIA on its Tegra platform on the high end. Who does this leave for Intel?

For Intel in the short term, with Motorola and Lenovo on-board, this leaves private label for carriers, LG, Sony, ZTE, Huawei, Kyocera, Sanyo and a very long tail of small manufacturers. The long tail will be a challenge for Medfield until Intel waterfalls the products line to be cost-competitive with lower end models. I expect Intel to start waterfalling products down in the end of 2012.

Why Intel Could Succeed

While I outlined the many challenges, Intel could very well succeed in the space longer term. First, the phone marketplace is a rapidly changing market. Not only have there been tremendous share shifts in the last two years, but feature phones are migrating to smartphone market resulting in exploding growth.

Operating systems are clear from shaking out. Microsoft will not go gently into the night with Windows Phone and will invest what it takes to be successful even if it takes another Nokia-like investment to own another platform. I also believe once Microsoft starts gaining share, they will devote resources for X86 on Windows Phone 8 or 9 platforms. They see Intel as successful with Medfield and the WINTEL alliance could be brought back from the dead. Long-term, I do not believe Samsung will be happy licensing someone else’s operating system, particularly with Apple’s integration and experience success. I expect Samsung to do one of three things, possibly two; increase investment in Bada to a point that it can compete with Android in a closed environment, embrace webOS, oe lean heavily into Tizen. Marketplaces in dynamic change are an opportunity for newcomers, even companies worth $140B like Intel.

One other important factor that hasn’t fully played out is “carrier versus handset-maker” dominance. Up until the Apple iPhone, the carriers dictated terms to the handset makers. Every carrier who has adopted the iPhone has taken a gross margin reduction. This doesn’t mean they made a bad decision; they had to carry the iPhone. That carrier margin reduction money is going to Apple and not the carriers. Carriers are strategizing how they can regain that dominance going forward and I believe Intel will part of those plans. Intel has the capability to partner with an extremely low cost manufacturer or ODM an entire solution, white label it to a carrier and provide a competitive Android experience. I expect a few key announcements this month at this year’s Mobile World Congress.

Of course, we cannot forget about Intel’s technology. According to tests run at Anandtech, Intel’s Medfield is competitive in power at 32nm LP so you must assume that it only gets better at Intel’s 22nm 3DTri–Gatetechnology. Intel will roll Atom into 22nm in 2013 and 14nm in 2014. This is all the while in 2012 TSMC is at best case at 28nm and GLOBALFOUNDRIES and Samsung is at 32nm.

I define success as the ability to reach a relevant level of profitable business that supports the desired brand goals. For Intel, this doesn’t need to be 80% like they have in the PC market, but needs to be a profitable 20%.

What this Means for Intel, Qualcomm, Texas Instruments, and NVIDIA

Over a period of three years, Intel will start to take market share from Qualcomm, Texas Instruments and NVIDIA, albeit very small in 2012. As Intel integrates wireless, moves to 14nm, and waterfalls their offerings to lower price point smartphones, this makes much more competitive to handset makers and carriers. I expect Huawei, ZTE, or a major carrier to go big with Intel in 2013 which will make a huge difference. One thing to remember about Intel; unlike others in the marketplace, Intel also captures the manufacturing margin TSMC and GLOBALFOUNDRIES makes and the design margin ARM earns. While Intel has a long way to go in proving themselves, they have the start they never had before at a time to take advantage of the mammoth growth in smartphones. Never count Intel out of any market, no matter how many times they have tried and failed.

What Intel Must Demonstrate in Smartphones (and soon)

Intel made a big splash at CES 2012 with the announcement that Motorola and Lenovo committed to Intel’s Medfield clip_image002smartphone solution. This came on the heels of a disappointing break-up between Intel and Nokia as well as a lack of previous traction with LG. While Intel has come farther than they have ever come before with one of their X86 SOCs, they still have a long way to go to claim smartphone victory. Of course Intel knows this and is working diligently and sparing no expense. The biggest challenge Intel faces is attacking a market where the incumbent, ARM ecosystem partners Qualcomm, NVIDIA, and Texas Instruments have almost 100% market share. To start gaining share in smartphones, Intel must demonstrate many things in the near future.

More Design Wins with Key Players

The Motorola announcement was impressive in that Moto has a respected name in smartphones, but they won’t carry Intel that far alone. Lenovo is an even smaller player and while very successful in PCs, hasn’t been able to secure a lot of smartphone market share even in their home country, China. Intel knows they need a few more partners to start chipping away at market share and I expect them to announce at least one at this year’s Mobile World Congress.

One of the challenges is that many of the top players are already locked-in in one way or another, Intel has some negative history with, or has rapidly declining share. Apple already has their own A-Series SOC, Samsung has Exynos SOC, and Nokia rebuffed Intel last year and is clearly locked into ARM and Microsoft for the time being. RIM as a partner is a shaky proposition and HTC is an aggressive player but is recently dropping share. That leaves lower smartphone market share holders LG, Sony, Sharp, NEC and ZTE in the short term.

Longer term, I don’t expect Apple or Samsung to get out of the SOC business because they have been successful with their own strategies. I cannot see Nokia or Microsoft motivated to drive a change or provide dual support for X86 until Windows 9. RIM is in a free-fall with no bottom in sight. Intel is forced to take the long-term approach as they are with Lenovo by developing smaller smartphone players to become larger ones. ZTE certainly is a good long term prospect as is Huawei. If Intel can leverage their PC franchise with them I could see them being successful.

Relevant, Differentiated, and Demonstrable Usage Models

In fighting any incumbent, the new entrant must provide something well above and beyond what the incumbent offers to incent a change in behavior. I am assuming that Intel won’t lead in low price or lowest development cost, so they must offer handset makers or the carriers a way to make more money or get consumers to demand an Intel-based smartphone. Regardless of which variable Intel wants to push, they must devise relevant, differentiated and demonstrable usage models that ARM cannot.

By relevant I mean that it must be fixing a known pain point or creating a real “wow” feature consumers never asked for, but is so cool it cannot be passed up. One pain point example is battery life. Battery life is simply not good enough on smartphones when used many times daily. If this weren’t true, car chargers and battery backs wouldn’t be so popular. Wireless display is useful and cool but not differentiated in that Apple can enable this via AirPlay. Demonstrable means that it must be demonstrated at the store, an ad, or on-line on a web site. If something isn’t demonstrable then it may as well not exist.

I would like to see Intel invest heavily in modularity, or the ability to best turn the smartphone into a PC through wireless display and wireless input. Yes, this is dangerous short-term in that if Intel does a great job at it then they could eat into their PC processor franchise. But, this is the innovator’s dilemma, and a leader must sacrifice something today to get something tomorrow. I could envision an Intel-based emerging region smartphone that enables PC functionality. ARM cannot offer this well today but will be able to in the future with their A15 and beyond-based silicon. Intel should jump on the modularity opportunity while it lasts.

One other opportunity here is for Intel to leverage their end-to-end experience from the X86-based Intel smartphone to the X86-based data center. If Intel can demonstrate something incredible in the end-to-end experience with something like security or a super-fast virtualized desktop, this could be incredibly impactful. One thing that will be with us for at least another 5 years is bandwidth limitation.

Carrier Excitement

Outside of Apple, the carriers are the gatekeepers. Consumers must go through them to get the wireless plans, the phones, and most importantly, the wireless subsidy. Apple’s market entry strategy with AT&T on the iPhone was a strategic masterpiece in how to get into a market and change the rules over time. Apple drove so much consumer demand for iPhones that the carriers were begging Apple to carry the iPhone, the exact opposite of the previous decade.

Intel must get carriers excited in the new usage models, bring them a new stream of revenue they feel they are being cut out from, or lower their costs. Intel doesn’t bring them revenue from content side but could I can imagine Intel enabling telcos to get a piece of classic retailer’s PC action once “family plans” become a reality. While telco-distributed PCs weren’t a big success in the past, this was due primarily from the absence of family data plans. I can also imagine Intel helping telcos lower the costs of their massive data centers with Xeon-based servers. Finally, if Intel could shift traffic on the already oversold “wire” by shifting processing done in the cloud and onto their SOCs, this would be very good in a bandwidth-constrained environment.

Competitive Handset Power

At CES, Intel showed some very impressive battery life figures for Medfield handsets:

• 6 hour HD video playback

• 5 hours 3G browsing

• 45 hour audio playback

• 8 hour 3G talk time

• 14 day standby

This was measured on Intel’s own reference platform which is somewhat representative of how OEMs handsets will perform. What will be very telling will be how Medfield performs on a Tier 1 handset maker, Motorola when they launch in Q3 2012. There is no reason to think the Moto handset won’t get as impressive battery life figures, but Intel could gain even more credibility by releasing those figures as available.

When Will We Know When/If Intel’s Smartphone Effort is a Success?

Intel has slowly but surely made inroads into the smartphone market. Medfield is impressive but competing with and taking share from an incumbent with 99%+ market share is a daunting task. The easy answer to measure Intel progress is by market share alone but that’s lazy. I believe that Intel smartphone efforts should first be measured by handset carrier alliances, the number of handset wins, the handset quality and the new end usage models their SOCs and software can enable. As these efforts lead to potential share gain does it make sense to start measuring and scrutinizing share.

Windows 8 Desktop on ARM Decision Driven by Phones and Consoles

There has been a lot written about the possibility of Microsoft not supporting the Windows 8 Desktop environment on the ARM architecture. If true, this could impact Microsoft, ARM and ARM’s licensees and Texas Instruments, NVIDIA, and Qualcomm are in the best position to challenge the high end of the ARM stack and are publicly supported by Microsoft.  One question that hasn’t been explored is, why would Microsoft even consider something like this? It’s actually quite simple and makes a lot of sense the position they’re in; it’s all about risk-return and the future of phones and living room consoles.

The Threat to Microsoft

The real short and mid term threat isn’t from Macs stealing significant Windows share from Microsoft, it’s all about the Apple iPad and iOS.  It could also be a little about Android, but so far, Android has only seen tablet success in platforms that are little risk to a PC, like the Amazon Kindle Fire.  Market-wise, the short term threat is about consumer, too, not business.  Businesses work in terms of years, not months. The reality is that while long term, the phone could disrupt the business PC, short term it won’t impact where Microsoft makes their profits today. Businesses, short term, won’t buy three devices for their employees and therefore tablets will most likely get squeezed there.  Business employees first need a PC, then a smart phone, and maybe a few a tablet.  There could be exceptions, of course, primarily in verticals like healthcare, retail and transportation.

What About Convertibles?

One wild-card are business convertibles.  Windows 8 has the best chance here given Microsoft’s ownership on business and if you assume Intel or AMD can deliver custom SOCs with low enough power envelopes, thermal solutions and proper packaging for thin designs.  Thinking here is that if business wants a convertible, they’ll also want Windows 8 Desktop and more than likely backward compatibility, something only X86 can provide.  So net-net, Microsoft is covered here if Intel and AMD can deliver.

Focus is Consumer and Metro Apps

So the focus for Microsoft then is clearly consumer tablets, and Microsoft needs a ton of developers writing high quality, Metro apps to compete in the space.  Metro is clearly the primary Windows 8 tablet interface and Desktop is secondary, as it’s an app.  Developers don’t have money or time to burn so most likely they will have to choose between writing a Metro app or rewriting or recompiling their desktop to work with ARM and X86 (Intel and AMD) desktop. It’s not just about development; it’s as expensive for devs to test and validate, too.  Many cases it’s more expensive to test and validate than it is to actually develop the app.  Strategically, it then could make sense for Microsoft to push development of the Metro apps and possibly by eliminating the Desktop on ARM option, makes the dev’s decision easier.

Strategically, It’s About Phones and the Living Room in the Endimage

Windows 8, Windows Phone 7, and XBOX development environments are currently related but not identical.  I would expect down the road we will see an environment that for most apps that don’t need to closely touch the hardware, you write once and deploy onto a Microsoft phone, tablet, PC and XBOX.  The unifier here is Metro, so getting developers on Metro is vitally important.

If Microsoft needed to improve the chances developers will swarm to Metro and do it by taking a risk by limiting variables, let’s say by eliminating ARM desktop support, it makes perfect sense.