Speeds and Feeds

In this last wrap-up post for Speeds and Feeds, I address what may be the most important issue in the future of personal computing architecture: consistent data access across multiple platforms.

Perhaps it's my multi-platform background, but I've never demanded or expected consistency in form factors, user interfaces or even capabilities. Variety in these areas is great; it's what makes the personal computing market so big. Variety is also why I keep so many PCs and consumer electronic devices around (see photo); I like knowing I have the right tools for many different jobs.

My active gizmo collection. Back row: Apple MacBook Pro (note the discolored helicopter tape protecting the palm rests), Amazon Kindle, Sony Reader, NEC Versa LitePad Tablet PC. Front row: 4G iPod, iPhone, iPod Classic, OLPC XO-1. All of these items provide independent data storage.

(Credit: Peter N. Glaskowsky)

On the other hand, I really don't like the fact that all of these machines are, in effect, independent little islands of data storage. Sure, most of these things have sync functions to help move the relevant data among them, and syncing is fine if you only have one PC and one gizmo, but at some point it becomes a pain in the neck.

In 2000, as a columnist for Electronic Business magazine, I wrote a piece titled "Where do your data live?" In it, I lamented the proliferation of isolated data stores on the growing number of personal electronic devices.

I pointed out that the computer industry had already found a better way to manage this problem: caching. Caching technology allows data to be shared among many storage subsystems. Each datum is "owned" by exactly one storage device, and all of the stores negotiate among themselves to change ownership as needed according to how the data are used.

I proposed that we adopt a caching model instead of thinking of every gizmo as a separate storage device. Each file could carry tags that identify where the master copy of the data should reside and what other devices should have copies of each item. (This tagging can even be extended to individual records in databases such as address books.)

This approach would eliminate the need to move data around manually. Any two connected devices could figure out for themselves if any data need to be synchronized between them--and the Internet can keep all of our devices connected almost all the time. Cloud storage makes a pretty effective location for those master copies, too.

I still think this is a good idea. There are some proprietary solutions along these lines, such as the sync features of Apple's MobileMe and Microsoft's Windows Mobile Device Center, but these solutions leave much to be desired, including interoperability. I'd love to see an open standard for data sharing, including file system extensions to support the necessary tags.

A few things have changed since 2000. USB and Wi-Fi have become ubiquitous, making it much easier to connect devices together (though there's still plenty of room for improvement in that area). The storage capacity of personal electronic devices has soared; the Newton I used in 2000 has been replaced by an iPhone with over 680 times as much flash memory.

Perhaps even more importantly, it's become practical for almost any personal electronic device to access and process the vast majority of data objects we own. There aren't very many files on my laptop hard disk that can't be at least viewed on my iPhone. Most of the exceptions, things like Photoshop images and HD video files, can at least be converted to compatible formats.

These changes have made a caching strategy even more valuable. Of course, automated data movement makes effective data security even more important (see "Wrapping up Speeds and Feeds, part 4: Security").

Ideally, our devices should stop acting like separate systems at all, but rather as multiple views into one consistent set of documents. Each device can still have its own look and feel, but not its own independent storage.

I think these last five posts have suggested enough projects to keep everyone busy for a while. When that's all done, I'll explain what we need to do next!

Nothing disappoints me more about the evolution of the personal computer than the PC's lack of ubiquitous security.

There's no technical reason why PCs can't provide strong security. Improving security costs money, which provides a business reason not to do it, but the way I see it, the costs associated with insecure computing have long since eclipsed the costs of making systems more secure.

It's also true that there's always a way around any layer of protection, which is sometimes taken as another argument against improving security. As the argument goes, you have to be able to access your own data; if someone else wants access, they can always force you to get it for them.

But that's like saying that because anyone can force you to unlock your front door, you shouldn't have a lock on it.

The right answer, I think, is to seek the point at which the security of a system establishes a balance between the costs and inconveniences of providing the security and the risks of having the security violated. In my opinion, the PC is nowhere near that point.

We need several key security improvements in the personal-computing experience:

Secure storage
To my way of thinking, security starts with secure storage. I assume most of us have sensitive information on our PCs. Since PCs can be stolen or attacked while nobody's watching, we need a way to protect our information. "Storage" in this context can include hard drives, the PC's main memory, and even removable media like USB drives and DVD-ROMs.

Properly done, storage security can be almost invisible. It shouldn't take much more than entering a password to unlock the storage device; for extra security, you could be required to use some kind of security token. But once you're in, and as long as you remain physically present, your machine can operate normally.

The same weaknesses that contribute to unreliability (see my earlier post, "Wrapping up Speeds and Feeds, part 2: Reliability") make PC storage insecure. Recent history shows how vulnerable PCs are to malware. Once a malicious program is in your machine, it can find personal data in memory or on disk and send it over the Internet to the attacker. Reliable execution can be associated with secure execution, and that's a good thing too.

Hardware can create security holes, too. The IEEE 1394 peripheral interface (also known as FireWire and i.Link) is a notorious weakness. It can provide unlimited access to system memory and, indirectly, all connected storage devices, even those configured with full-disk encryption.

Strong process and object isolation--the same techniques I recommended to improve reliability--can help improve storage security, too. These methods apply directly to memory security, and by extension, to mass storage.

Secure communication
Because most of the data on our PCs arrives there from somewhere else, communications security is also important. I remember being disappointed in the late 1980s that emerging Internet e-mail standards did not allow for secure e-mail, but I assumed that this omission would be quickly rectified.

When Phil Zimmerman's Pretty Good Privacy arrived a few years later, I figured it was only a matter of time before all Internet e-mail was encrypted by default.

But some of the critical technology, notably the RSA public-key cryptography algorithm, was patented and not really available at consumer-friendly price points. When the RSA patent was released to the public domain in 2000, I figured the end of insecure e-mail was finally in sight.

But here we are, eight years later, still waiting.

It wouldn't take much for someone to introduce a mainstream e-mail service that is secure by default. Apple, for example, could provide almost invisible security for MobileMe e-mail using nothing more than the existing open standards created for that purpose. Any e-mail provider could do the same thing. What are they waiting for?

In fact, there's no longer any technical or commercial barrier to cryptographic protection of all of our Internet communications. Every Web server could provide HTTPS support in preference to standard HTTP, but very few allow this. Almost every insecure Internet protocol has a secure alternative, but most of these are not well-supported.

This lack of security is quite serious and quite expensive. Many credit card theft rings have intercepted card numbers being transmitted over Wi-Fi networks. Many individuals have fallen victim to identity theft because someone intercepted their traffic on public Wi-Fi networks.

There are ways for individuals to protect their Internet communications. One is to use VPN (virtual private network) software, which is built into most PC operating systems these days. Until consumer ISPs provide VPN endpoints for their customers to use when away from home, however, this option is mostly limited to business users. Also, a VPN only protects traffic between you and the other end of the VPN connection; from there to whatever Web sites or other services you access, your connections are not covered by the VPN.

Secure identification
Many sites on the Internet require some form of log-in before giving access to personal information. This process is separate from the communication method itself.

HTTPS, for example, doesn't require any kind of user identification; it just protects a single session. VPNs protect the link from the user's machine to some remote site, but in themselves don't usually give access to systems at that site.

Ideally, the remote system should be convinced who the user is, the user should be convinced what system is being accessed, and the whole process should be strongly secured by open industry standards.

Alas, that isn't how it works.

Most Web sites use their own authentication systems, requiring users to keep track of a separate set of log-in credentials for every secure site they visit. Although there are a few open standards for this purpose such as OpenID, they are nowhere near universal.

Few Web sites provide any way for the user to authenticate the site itself. The Extended Validation Certificates offered by some certificate authorities help a lot, though they are relatively expensive and not easy to get. Modern Web browsers recognize these certificates and turn the address bar green to indicate that the site certificate matches the displayed address.

These certificates still don't provide a direct negotiation between the user and the server based on some previous agreement, however, so there are still some risks involved, such as users mistyping domain names and getting a site masquerading as the one they intended to reach, or having the server taken over by malware.

While it's entirely appropriate for many servers to know exactly who their users are, I also think there are times when users should be entitled to some privacy. Just as there are multiple levels of identification, there should be multiple levels of anonymity.

The details of this option can get a little tricky. I think it ought to be possible to have a Web site for government oversight, for example, where whistleblowers can participate with almost complete anonymity. Of course, such a site could become a magnet for libel, and that wouldn't be useful.

A more practical kind of anonymity is already practiced by many Web sites, where user credentials are accepted uncritically but access logs can still be used to track down the IP addresses of users who violate the site's terms of service (or the law). This is fine, as far as it goes, but it isn't really secure anonymity. It can be fairly easy to associate an IP address with a name depending on the user's other online habits.

There are anonymizing services available online that can act as go-betweens to protect against this kind of investigation, but these services can also provide cover for libel, and again, that isn't very useful.

I think there's room for a new open standard to anonymize Internet communications in a way that is secure against casual investigations yet fully accountable if abused.

Security is a big topic, of course, and I've really just scratched the surface here. (Not to mention the risk of oversimplifying some important issues.) Suffice it to say that there's plenty of room to make personal computing far more secure, and that this improvement is, in my opinion, long overdue.

As I continue to wind down Speeds and Feeds, I picked ruggedness as the topic for part 3.

In part 2 of this wrap-up series, I on Tuesday discussed reliability, suggesting that an increasing portion of the transistor budget in personal computers should be used to avoid, detect, and recover from hardware, software, and data errors.

Ruggedness, the ability of a PC to survive adverse physical conditions, complements reliability by further increasing the practical availability of a PC to do useful work.

As with efficiency in power management (part 1's topic), this is an area where PCs can learn a lot from cell phones. I expect my cell phone to continue operating normally unless it's physically damaged--and I expect that it will not be damaged even by fairly rough handling.

PCs, by comparison, are pretty fragile. I know that if I drop my laptop, even if it falls only a few feet to a carpeted floor, there's a good chance it will be damaged. The LCD could crack, the case could bend, the hard disk could crash, the battery latch could break. In fact, I've managed to do all of these things to one or more of the 15-plus laptops I've owned and used since 1984.

Not all laptops need to be rugged; for example, some laptops are used as small-footprint desktop computers and rarely moved at all, so ruggedness would be an unnecessary expense.

There are many situations, however, where greater ruggedness is obviously valuable: laptops for students (even in a classroom), field photographers, mechanics, factory workers, the military, and so on.

Some companies already make rugged systems for these applications, but demand for such systems is low, and they require a lot of additional engineering. The combination of small quantities and extra design work leads to very high prices; it isn't unusual to see rugged laptops with the features of a typical low-cost notebook selling for $4,000 or more.

There have been very few standard mass-market personal computers with any real degree of ruggedization. In the old days of 8-bit microcomputers, some consumer-oriented systems such as the popular Atari 400 and Commodore 64 were fairly robust due to heavy plastic cases designed to survive casual home use, but these weren't portable machines.

In the mid-1990s, Dell's Latitude line earned the favor of serious road warriors in part due to a high degree of ruggedness, if only in comparison with other mainstream laptops. Sometimes these Latitude models were the only survivors of annual notebook torture tests run by PC Computing magazine.

Panasonic's Toughbook line took over later in that decade as the first truly rugged notebooks. (I have a Toughbook 25 myself; alas, it's dead.) It's easy to see how these machines differ from ordinary notebooks: heavy magnesium casings with stiffening ribs to resist twisting, shock-mounted hard disks, water- and dust-resistant connectors, and so on. They aren't suitable for most people, though.

Three trends are bringing rugged systems closer to the mainstream today.

First, portable PCs are becoming increasingly more integrated into our daily lives. As power efficiency improves to the point that we can run them all day, portable machines will be even more important to us. But if these devices aren't rugged, we won't really be able take them with us as often as we'd like.

A simplified view of a small ruggedized notebook that I designed in 2005.

(Credit: Peter N. Glaskowsky)

Second, the components themselves are getting smaller, lighter, and in some cases more rugged. It's possible to buy a decent dual-core CPU that doesn't need a huge heat sink. Solid-state disk drives are a huge step forward; and with 128GB of capacity requiring only 32 flash chips, they can be much smaller than traditional hard disks. Smaller, lighter components are easier to support and protect.

Third, materials science is making a lot of progress. The glass used in LCDs is much better today than it was a decade ago--better able to absorb shock and flex a little when needed. (It's actually a little scary just how flexible the displays of some super-thin notebooks are.) New chassis materials such as milled aluminum and CFRP (carbon-fiber reinforced plastic) can produce very strong machines, though in most consumer systems they're used to reduce weight instead. In the near future, carbon nanotube-reinforced materials will become available in commercial quantities; while expensive, they will be very strong.

These new materials can be used in new ways to make very rugged machines that don't have to cost dramatically more than existing systems.

In 2005, as a practical exercise, I designed a small notebook with a milled titanium case and a novel mechanical design that provided exceptional stiffness. With a fixed battery and few external connectors (another improvement enabled by new technology), it would have provided Toughbook-like ruggedness in a very small and convenient package.

That design didn't go anywhere, but there are plenty of designers out there. I expect that someone will develop something similar before too long.

The current Netbook craze is directing a lot of attention to ruggedness as a design goal. These machines are small, light, and obviously portable, but they tend to be cheaply made and more fragile than many consumers would like. Adapting these designs to more rugged enclosures would add significant cost, but I think there's a good market for such machines.

Personal computers have become much more reliable over the last 10 years or so, mostly due to the introduction of advanced operating systems with memory protection and hardware abstraction. The hardware itself has gotten better too; uncorrectable random errors are rare in PCs and extraordinarily rare in server-class systems.

These and other improvements have largely eliminated machine crashes. Blue-screen errors on Windows and kernel panics in Linux and Mac OS X still occur, but much more rarely.

Error-reporting services have become common, helping software developers figure out what went wrong. Most large developers now issue regular patches to fix newly discovered bugs, making systems more reliable between major releases.

All this progress is wonderful, of course, but our PCs still aren't reliable in the way that other consumer products are reliable. Machine crashes are still possible, and any bug can bring down an individual application.

Automobiles, for example, can fail in many ways, but they are still much more reliable than PCs. The risks associated with vehicle failures have been greatly reduced by decades of design refinements. Would you feel safe if PC technology controlled the steering and brakes in your car? Conversely, wouldn't you be more confident in your PC if you knew it was as reliable as your vehicle?

Can you rely on your system to display this 370-megapixel image?

(Credit: European Southern Observatory (ESO))

PCs are also fragile in response to change. I know I'm always a little nervous the first time I install a new device driver or run a new application. Even without software changes, opening an unusually large image can induce some trepidation. Consider this 370-megapixel image of the Lagoon Nebula available from the European Southern Observatory Web site; how confident are you that all of your image-viewing programs would survive the attempt to open it?

And worst of all, PCs are fragile in response to attack. The kinds of problems that are sometimes created accidentally by software bugs are relatively easy to create on purpose.

Minimizing the frequency and consequences of these problems would require tremendous effort from everyone in the industry. Almost every bit of PC hardware and software would have to change. One part of the solution is an extension of the same techniques that make today's PCs more reliable than older models: more hardware-based isolation of one function from another.

The minimal isolation of today's systems is very convenient for software developers, making it easier to write code and achieve high levels of performance. More isolation means more complexity and more overhead, but it improves reliability.

Developers are taking the first steps in this direction already, for example, with the process isolation features of the Microsoft Internet Explorer 8 and Google Chrome browsers. But there's much more that can be done.

Another way to improve reliability is to verify that data and addresses are consistent in range and format with the original intent of the software developer before they are used by the program. Making these checks in software can help; the incidence of failures related to accidental and deliberate buffer-overflow conditions has been dramatically reduced in this way. There's plenty of room for new hardware to help in this process too.

There's also work to be done in making it easier to recover from failures, since true hardware failures are inevitable. This is another area where some high-end systems are way ahead of the PC. Fault-tolerant machine architectures have been around for a long time in the aerospace industry, for example.

Historically, fault tolerance has never been practical on the PC because PCs always had only one of each critical subsystem: one processor, one bank of memory, one display channel. Today, PC processors and graphics chips have multiple cores and multiple memory interfaces, creating the potential for redundant operation where it's most needed.

Recoverability also implies backups--not just of the contents of disk drives, but even of the live data in memory through checkpointing. And disk backups can be improved too, by making the backup process an integral part of all disk I/O. Modern file systems use journaling to increase reliability; this technique can be extended to allow recovering from errors long after they occur.

There will be a heavy price to be paid in complexity and performance for all of these techniques, but the currency for this payment is transistors, and Moore's Law gives us more of those in every new process generation. We need to consider how we want to allocate these transistors. Over time, I believe reliability should account for an increasing portion of them.

After 19 months of consulting--in Silicon Valley, we prefer that term to "unemployment"--I've accepted a job.

Once I start, I'll have to stop blogging. But while I'm still independent, I'd like to wrap up here by offering a short series of articles addressing several key topics in the area of personal computing.

Today, the topic is energy efficiency.

Energy efficiency has become a major selling point of today's personal computers, especially laptops, because power consumption determines battery life.

Unfortunately, laptops are being optimized for energy efficiency in a way that isn't fully consistent with the needs of laptop users.

Advances in process technology and CPU design have greatly improved the power efficiency of modern microprocessors when they're running. This improvement is most visible at the highest performance levels.

Over the last few years, dual-core laptop processors have gone from maximum speeds of roughly 2.4GHz to 3.0GHz without consuming any more power. The newest quad-core chips provide much more aggregate performance in a similar power envelope.

This improvement in operating efficiency is great for gaming, mobile video editing, and a few other applications. But it's not very meaningful for most consumers.

What the rest of us need is non-operating efficiency, the ability of the laptop to consume very little power when it isn't doing much because that's what our laptops are usually doing.

We need laptops that can do nothing--more efficiently.

I've been looking at the newest crop of ultra low-power laptops. Based on published benchmark data, they consume an average of 8W to 10W of power when doing essentially nothing (what we call "idle power"). Even the best of them consumes about 6W of power at all times, getting 10 hours of battery life from a 60WH battery. Maybe 2W of that is spent keeping the display on. The other 4W to 8W is just wasted by the CPU and other motherboard circuitry.

When your laptop isn't doing much--for example, when you're typing in your word processor--it's using only slightly more CPU performance than your cell phone is when you're texting. Your cell phone consumes very little power to do this meager amount of work, usually no more than 0.25W or so for the CPU and its support chips. The corresponding elements of your laptop, however, may consume 50 times as much power under similar conditions.

Some of this difference is inevitable; your laptop has wider data buses, more and faster RAM, and so on. Nevertheless, your laptop motherboard could be designed to idle along on 1W or so.

That would give you a total system-level power consumption of around 3W--half the power of today's most energy-efficient laptops and about one-quarter the power of an average machine. Because there's a relationship between peak CPU speed and idle power, today's fastest laptops consume 20W or more at idle. With more energy-aware designs, these systems could see even greater proportional reductions.

In other words, adopting more aggressive methods for reducing idle power could easily double battery life across the board, and some systems would see much bigger improvements.

This is not merely a quantitative improvement. Consider what happens when your laptop can comfortably operate for 20 hours with the display on, or 60 hours with the display off.

For one thing, it never has to go to sleep. Your cell phone never really goes to sleep, and that's a great part of its value. Your laptop can have this same cell phone operating model.

Closing the lid should turn off the display, but the machine should keep running. It can stay connected to the Internet over Wi-Fi or 3G, periodically download your new e-mail messages, watch that eBay auction, and do whatever else you need it to do...all the time. Just plug it in to recharge while you're asleep. (If the laptop is in your briefcase, it'll have to slow down a lot to keep from consuming too much power, but that's easily managed.)

When you're ready to start using the machine actively again, it shouldn't take any longer to turn the display on again than it does to physically open the lid. Think "always on," not "instant on."

All of this is possible with today's technology, but nobody's doing it. I think one of the reasons we don't see this usage model is that laptop buyers don't know to ask for it. Incremental improvements produce adequate sales figures with each new laptop generation, and everyone figures that's good enough.

But mark my words: the first full-function laptop that works like a cell phone--always running, always connected, always ready--is going to hit the market like a sledgehammer. Everything else is going to seem obsolete overnight.

While we're all familiar with the steady increase in the number of cores in mainstream PC and server processors, the corresponding progress in the embedded-processor market has been anything but steady.

With mainstream PC microprocessors standardizing on four-core designs such as Intel's Core i7 and leading-edge server chips ranging from 8 to 16 cores, single-core chips are no longer competitive. For embedded systems, however, one core may still be the right answer; if more are needed, the choices range up into the hundreds.

The Tilera Tile-Gx100 combines 100 independent 64-bit integer processor cores and cryptographic accelerators with memory, network, and PCI Express interfaces.

(Credit: Tilera Corporation)

The latest announcement in the many-core embedded processor market is Tilera's Tile-Gx family, which combines 16 to 100 64-bit integer processor cores with cryptographic accelerators and off-chip interfaces for memory, networking, and PCI Express. I met with Tilera before last week's announcement to discuss the technical and business issues related to the Tile-Gx.

The technical details
San Jose, Calif.-based Tilera is eager to set itself apart from the many other chip companies competing in its target markets. Unlike most embedded processors with high core counts, for example, Tilera's design allows its cores to operate truly independently, even to the extent of running different operating systems if needed. More commonly, groups of tiles will be combined to run a single task that is part of a larger workload. In this way, one chip can operate like a cluster of multiprocessor systems.

Between this distinction and the fact that cores in the Tile-Gx family are a full 64 bits wide, Tilera claims the Tile-Gx100 is the "world's first 100-core processor." I think that's just a little too broad a claim, personally, since companies such as Clearspeed and Xelerated have previously made similar claims for their chips. Even more significantly, the Tile-Gx100 doesn't exist yet. It won't be a real product until early 2011, according to Tilera's current schedule.

Tile-Gx processors aren't something most CNET readers will ever knowingly use, though these chips will likely, eventually, help carry traffic over the public Internet and through larger corporate networks. But they do provide an excellent example of the issues facing PC processor vendors as core counts continue to grow.

Consider the Tile-Gx100 block diagram shown above. It's easy to imagine that this chip can get a lot of work done. Every core can run up to three instructions per cycle at up to 1.5GHz. It has dedicated hardware accelerators for cryptography and network packet processing. The network interfaces can implement up to eight 10Gb Ethernet ports. The chip also has four DDR3 memory interfaces; to reduce DRAM accesses, every core has 320KB of local cache memory. (The total amount of cache memory in the Tile-Gx100, about 32MB, matches that of IBM's Power7 processor, which has only eight cores.)

The need for balance
It's not so easy to keep all these resources busy, however. The more complicated a chip gets, generally speaking, the more difficult it becomes to make full use of its resources. This is what we often call the balance between hardware and software.

Tilera will offer four products in the Tile-Gx family with 16, 36, 64, and 100 cores and corresponding differences in memory and networking support. This range of products helps meet the needs of different applications, but each product still needs a particular balance of application requirements for maximum efficiency.

So here lies Tilera's great challenge--finding software applications that need a large amount of CPU performance and that also:

1. Are highly parallel, so they can keep many cores busy.
2. Don't need much (if any) floating-point math, since the Tile-Gx doesn't do that.
3. Can benefit from cryptographic acceleration.
4. Consume large amounts of network bandwidth.

Tilera wants customers to think of its chips as "general-purpose" processors, but as this list shows, they're better for some purposes than for others. As PC processors reach higher core counts and integrate more functionality, they too will become more sensitive to application requirements. Integration eventually reaches a point where additional complexity adds no practical value. And the closer PC processor vendors approach that limit, the more difficult it will become to sell their latest, greatest, most complicated chips.

Network processing is the most natural fit for Tilera's capabilities, particularly high-level services like virus scanning as I discussed in September (see "Insatiable demand for mobile data challenges industry"). Internet service providers rarely provide such services for PC users, since PCs can do their own scanning--but mobile phones and other Internet appliances often can't, so these services are seeing increasing demand.

The networking market, unfortunately, is not large enough to support a company like Tilera. Although there is a lot of networking equipment sold each year, each company in the business has its own ideas about how this processing should be done. A single chip design could never capture the majority of this potential demand.

Further, the larger equipment vendors often have policies in place against relying too heavily on individual suppliers, especially small start-ups. They will commonly design different products using different chip-level technology so that the failure of a single supplier--or the purchase of a supplier by a competing equipment vendor--will have only a limited effect on their bottom line.

New business opportunities
Tilera is working to develop new markets for its current TilePro and future Tile-Gx parts. The most significant of these new markets is cloud computing, which may favor solutions like Tilera's that offer higher performance per watt.

That's the metric Tilera touts most heavily for the Tile-Gx, promising 10 times the performance per watt of Intel's Westmere-EP, a six-core 32nm processor that Intel will begin shipping in 2010, which is aimed at high-efficiency servers. (Incidentally, I commend Tilera for making this comparison; Westmere-EP is exactly what they'll be competing against. Too often, chip companies will try to make themselves look better by comparing next year's products with last year's competition.)

Although 10x is a critical multiplier in this business (see my post "The factor factor"), such an advantage doesn't necessarily guarantee success. Tilera has done everything it can to minimize the difficulties associated with software development by adopting industry-standard development tools such as GCC and Eclipse, but its Tile chips still can't run Windows and it just can't match the developer relationships that companies like Advanced Micro Devices and Intel have established.

Fortunately, Tilera is small and relatively efficient for a chip company. Last month, Tilera announced that Quanta Computer invested $10 million in the company based on Quanta's interest in cloud computing. Tilera said it has enough funding to reach cash-flow breakeven in 2011, assuming the Tile-Gx reaches market and achieves the kind of success Tilera predicts.

I remain skeptical, but hopeful. I think there's no question that in the long run, there will be plenty of demand for complex, many-core processors like Tilera's. But will Tilera still be around by that time? And in the long run, once this demand develops, larger companies such as Intel will have their own offerings.

Can Tilera carve out a market niche that it can defend against such strong competition? I just don't know, but I'm always glad to see people trying new ideas.

It's been years since the concept of a digital convergence was seriously debated. Today, it's rare to see a single-function electronic device.

Digital still cameras can record video, and camcorders can take still photos. Even cheap cell phones include cameras. There are Web browsers in cell phones, cameras, televisions, and digital picture frames. In fact, it seems like it's only a matter of time before everything with a battery or power cord will be connected to the Internet.

So it's a little startling to see a new gizmo that does nothing but display text, especially when that text comes from a preprogrammed memory card...and it's extraordinary when the text came from the Internet in the first place.

Openmoko's WikiReader is a standalone Wikipedia browser with a touch screen and the complete text of Wikipedia on a memory card.

(Credit: Peter N. Glaskowsky)

I was initially incredulous when I heard about WikiReader, a $99 device from Openmoko designed solely for the purpose of reading Wikipedia articles. How useful could such a thing really be, I wondered.

The device, which was released about two weeks ago, displays the text only. The user interface couldn't be much simpler. Pushing the power button boots the device in less than two seconds. There's a search button for looking up individual articles, a history button for recalling previously viewed articles, and a button to open a random article from the collection. A parental-control feature allows blocking mature content (imperfectly, as I quickly learned).

And that's about it. It doesn't display images, references, discussion pages, or links to outside Web sites. (The latter point is reasonable enough because the device can't access the Internet anyway.) In fact, all 3 million Wikipedia articles viewable on WikiReader ship on a memory card in the device.

The content on the card is just a snapshot of the active Wikipedia database, complete with whatever errors or vandalism may have been present at the moment each article was copied. But overall, it's still an impressive amount of useful information. (Openmoko will offer quarterly updates that can be downloaded for free, or delivered on new memory cards twice per year for an annual cost of $29.)

Not long ago, distributing Wikipedia this way would have been impractical. Even today, an 8GB Micro SD card is a sub-$15 item in wholesale channels, which is a big chunk of the $99 retail price. Saving money here, however, would have compromised the usefulness of the device. (On the unit I tested, 4.18GB out of 7.4GB was actually used; perhaps some foreign-language versions of Wikipedia could fit on smaller, cheaper cards.)

The other elements of WikiReader show similar trade-offs. In an e-mail exchange, Openmoko President Sean Moss-Pultz told me that the Wikireader design began with the chips commonly used for electronic dictionaries--for example, Epson's S1C33E07 microcontroller. But whereas such devices usually have small screens and physical keyboards, allowing them to hit very low price points (e.g., this $21 device from Royal), Openmoko chose to go with a larger screen that displays about 13 lines of proportionally spaced text--roughly 40 characters per line, 80 words at a time.

Further, WikiReader has a capacitive touch screen, enabling the use of a virtual on-screen keyboard rather than a separate physical keyboard. The touchscreen--equipped with a tempered glass face that resists scratches better than plastic--also handles touch-drag scrolling and selecting links to other Wikipedia pages. As a result, WikiReader is smaller than most electronic dictionaries, but has a larger screen and is easier to use. (Click for more details on the WikiReader hardware platform.)

WikiReader is also more expensive than most electronic dictionaries, but again, the higher price was essential if WikiReader was to accomplish its mission. That mission is simple to express: make Wikipedia accessible to anyone, anywhere, any time. At $99, this device may not be affordable by everyone in the world. On the other hand, it's a lot more affordable than even the least expensive laptops, including the original "$100 laptop" from the One Laptop Per Child Foundation, which is still priced at $199 two years after it first went on sale.

Although the comparison is hardly fair, it's still relevant since the number of parents and schools in the world that can afford a $99 WikiReader is a lot larger than the number that can afford a laptop plus the necessary supporting infrastructure such as an Internet connection and power source. (By comparison, Openmoko says that two AAA alkaline batteries--cheap and widely available--will run the WikiReader for up to a year, and that's the only recurring cost to keep the unit operating.)

I expect the cost of manufacturing WikiReader will come down slowly over time, and the product itself may become more valuable as third-party developers begin to work with the WikiReader's open-source software. Openmoko began as an open-source cell phone project, and while WikiReader has nothing in common with that earlier work, the company still has some visibility in the open-source developer community.

WikiReader isn't quite easy enough for a cat to use.

(Credit: Peter N. Glaskowsky)

The WikiReader software load is very simple. There's no OS, not even Linux; just one application to run the Wikipedia browser, for example. All of the software, along with the compressed Wikipedia database, is provided on the Micro SD card. There are some diagnostic programs, and there's even a simple four-function calculator "Easter egg" that comes up in response to a History-Power button combination.

The lack of a full OS is a matter of necessity, but this is the kind of necessity from which virtue is created. The near-instant boot time and ultra-low power consumption couldn't be matched with any flavor of Linux. Software development isn't as easy as it would be for a Linux PC application, but then, the device is simple, so it wouldn't be too difficult to develop new functionality for the WikiReader hardware. I'd like to see the usual combination of dictionary, thesaurus, and language translation found in many other devices, along with a more-advanced calculator.

In the meantime, WikiReader does the one thing it was meant to do, and I think that's good enough.

(My thanks to Pat Meier-Johnson of Pat Meier Associates for bringing WikiReader to my attention. Also, thanks to Openmoko for providing a review unit and answering my questions.)

I'm very impressed by the Nook, Barnes & Noble's new e-book reader. It's clear B&N has studied Sony's Reader and Amazon's Kindle very carefully.

The Nook has almost all of the major features of both product lines, plus a few more, with few competitive disadvantages. B&N has also followed Amazon's lead on support services. The Nook has a very good online e-book store as well as applications to support e-book reading on Macs, Windows machines, and smartphones.

(Credit: Barnes & Noble)

The Nook doesn't ship until the end of November, but here's what I found most significant from the announcement and the pages at nook.com:

Industrial design
I think the Nook is attractive and well-designed. It looks better than the Kindle 2, but not as good as Sony's Reader Touch Edition, which offers a larger screen in a smaller form factor. Also, Sony's forthcoming Reader Daily Edition is only slightly larger than the Nook, but offers a much larger screen.

Secondary color display
This feature surprised me. It seems expensive and insufficiently functional for what must be a significant added cost. The low resolution of this display (480 x 144, according to a CNET blog post) means it won't be useful for much beyond the basic user-interface features B&N has already described: book covers, menus, and a keyboard for note-taking. (Although I should note for the record that while B&N says "Its full-color touchscreen encourages you to bookmark, add notes, and highlight passages," I haven't found a photo on the company Web site depicting the virtual keyboard shown in some of the pre-release images. Perhaps that's one of the features still under development.)

By comparison, the secondary color screen built into the Alex e-book reader from Spring Design, shown in another recent CNET story, is large enough to be useful. Unfortunately, it's also large enough to be very much in the way, leading to an awkward device. Spring Design and B&N need to make up their minds-- are they making e-book readers or something else?

I've been thinking about buying a new gizmo, and it turns out I'm not the only one in the family having these thoughts.

My sister sent me an e-mail over the weekend:

I need a 3G card for my laptop and I'm going to get it from Verizon. What should I ask for? I just don't want them to try to sell me more or less than I need.

Coincidentally, I've been looking into the latest options for mobile broadband access for a couple of months now, ever since the two-year contract ran out on the Option GT Max 3.6 Express I bought in 2007.

Here's an expanded version of my reply e-mail:

There are four basic kinds of 3G wireless modems: USB dongles, PC Card and ExpressCard devices, portable 3G/Wi-Fi access points, and cell phones with wireless "tethering."

USB modems are the most popular type and usually the least expensive. They plug in like a thumb drive, and they're easy to deal with. But I don't like them because they can stick out pretty far, which makes them awkward and a bit fragile. The larger ones don't work at all with USB jacks that are too close to other ports. Also, the cheapest ones can have relatively poor reception.

If your laptop has a plug-in card slot, it's either for PC Cards or the more recent ExpressCard type. Your user manual will tell you. Verizon offers one of each. They don't stick out so far, which makes them a little more rugged while in use, though you should still remove them before putting away the laptop. I find them more convenient than the USB type.

The Novatel MiFi 2372 connects up to five Wi-Fi devices to 3G mobile broadband networks.

(Credit: Novatel Wireless)

A portable access point is worth considering if you have more than one gizmo to connect to the Internet while you're traveling. For most North American users there's only one such device available, the Novatel MiFi.

Sprint and Verizon offer the MiFi 2200, which provides typical download speeds from 400Kbps to 1.4Mbps (Verizon's estimate; actual speeds vary widely).

Novatel also makes the MiFi 2372, which works on AT&T, T-Mobile, and pretty much any international phone network. This is the one I want, but as far as I can tell AT&T and T-Mobile don't offer discounted pricing on this gizmo yet. If purchased directly from a mail-order supplier, it's very expensive--well over $300.

Whichever version you get, the MiFi is a standalone gadget a little smaller than an iPhone. It has its own battery and recharges with a small wall adapter or by connecting it to your laptop (which makes it work like a USB wireless modem). It connects to the cellular data network and creates its own little Wi-Fi hot spot that can be used by up to five systems at once--like your laptop and an iPod Touch.

I don't have one of these myself, but friends do, and it looks like the most convenient way to get online while traveling.

As an aside, I should mention that one of the earliest mobile broadband/Wi-Fi gizmos was developed by a friend of mine, Tor Amundson. He called it the Stompbox, and wrote about it for Make magazine. More information is available on one of his sites, Stompboxnetworks.com.

Earlier this year, Tor told me about an interesting alternative to the MiFi. Cradlepoint makes gizmos that are functionally equivalent to the MiFi, except they work with a user-provided USB or ExpressCard modem. While this approach is noteworthy, I think the MiFi is generally a better solution for most users.

The last option is to get a 3G-compatible cell phone that supports "tethering"--that is, using the cellphone itself as a modem. This can work pretty well, though I had a lot of trouble tethering the Cingular 8525 phone I had before I got the Option card.

The major downside of tethering is that you may not be able to talk on the phone while using the Internet. Apparently AT&T and T-Mobile 3G phones are more likely to support simultaneous operation than those on Verizon or Sprint. I regard this limitation as unacceptable, though you might feel differently. The upsides are that tethering can be somewhat cheaper than getting a separate 3G modem because there's only one contract, and there's nothing else to carry around.

(The iPhone still doesn't allow tethering.)

The most important thing to keep in mind, no matter how you get online, is that mobile Internet usage is quite strictly limited by all carriers. Verizon's $40/month service provides only 250 MB/month of data transfer, and that can run out very quickly. Even the $60 service's 5GB limit can be exceeded in mere days if you spend too much time on YouTube or some other video streaming service.

If you go over your plan limit, per-megabyte charges are really painful. According to Verizon, the 5GB overage rate is 5 cents/MB and the 250MB overage rate is 10 cents/MB. In other words, a single HD video on YouTube could easily cost you a few dollars to watch once you're over the limit.

For comparison purposes, AT&T's overage fees are $10/100MB for its $40/month plan and 49 cents/MB for the $60/month plan. The latter rate is the cell phone equivalent of the death penalty, since hardly anyone is going to go only a few megabytes over the 5GB allotment. A careless user could easily incur hundreds of dollars in overage fees in a single month.

So whatever you buy, be careful how you use it. And if you share your connection (using a MiFi, or via Internet Connection Sharing in Windows), make sure your friends stay away from Hulu.

Another thing to consider is whether you need international access. If you intend to travel a lot, you can get a wireless modem that will work in most foreign countries. Be sure to ask about the countries that matter to you; Japan and South Korea, in particular, have very specific requirements. What Verizon calls "Global Ready" modems are somewhat more expensive to buy, but again, be warned: international roaming can be *very* expensive. (In the U.S., the charges are the same as for any other 3G modem.)

In my opinion, the best way to get Internet access while traveling internationally is to find cheap or free Wi-Fi hot spots and skip the mobile broadband. This approach is less convenient, but there's no risk of coming home to a very expensive bill from your cell phone company.