Penultimate Reality

There’s no doubt: the megahertz race is over. Both Intel and AMD, in more recent research and development, have been focusing not on improving the raw speed of the processor, but simply on improving the performance. This change in focus has resulted in several dual and quad-core processors being put to the market in the past couple of years. The trend began with features like hyper-threading that Intel introduced several years ago. Now, this trend looks to be taking a giant step forward.

Intel unveiled Polaris on Sunday, a chip that apparently makes use of no less than eighty cores to do its work. Eighty-core chips are still several years away from the consumer marketplace, which is probably a good thing. The number does indeed sound fantastic, and I can imagine many a person got a little starry-eyed with visions of amazing performance upon hearing the news. Nonetheless, there are some issues that I can see to overcome before these types of massively parallel chips can revolutionize computing.

The biggest issue is simply that today’s software is designed to run on a serial architecture. Most people multi-task to some degree, which helps somewhat, but today’s machines are so fast that there are diminishing returns with extra cores. Personally, I seem to have about one to three processes ready to go at any given time, not including BOINC, which essentially just grabs up any unused processor time. While playing a resource-intensive game or similar workload, that number may rise. What this really means is that I’m not in a position to effectively utilize more than two to four cores.

The question of the day is thus whether or not it is possible to take traditionally serial algorithms used by numerous programs and rewrite or transform them (in the compiler, for instance) to optimize them for massively parallel architectures. If this doesn’t turn out to be feasible, or even if it does, it still remains that applications must be written and optimized to work in parallel, instead of serially.

Personally, my biggest concern is the overhead the necessary thread-safety would incur. But maybe I’m just a dinosaur who’s remembering the problems of traditional multi-threading. In either case, I can’t wait to see what awaits us in the near future.

I recently received a new watch as a gift, and as part of the recent month, had done some research on the features available on modern watches, especially those produced by Casio. Some features, like temperature sensors, have been around for a few years. But there are a plethora of features that are a bit more recent.

Perhaps the most useful is that many such watches are capable of synchronizing themselves each day using a radio signal. Other ones use solar energy to recharge the battery, enhancing battery life to over ten years, in some cases. If that’s not enough, there are a wide variety of sensors like compasses, temperature sensors, barometers, altimeters, and even depth meters for the divers out there.

I suspect it won’t be long before we not only have watches that tell time, but allow you to control it as well, among other things, like doing your laundry, cooking your meals, and walking your dog.

Slashdot is reporting today that drive manufacturers are beginning to augment their hard drives with flash memory. This will first be used as a cache, but later, they’ll be releasing solid-state only drives (in smaller form factors for notebooks, it seems). Performance-wise, it seems that they can’t match the streaming performance of today’s drives, but that random-access performance is quite fast, and in the interview, Samsung’s Don Barnetson indicated that this is the real bottleneck for I/O performance. We’ll have to see just how this develops in the coming months, with many benchmarks sure to arrive on the scene.

Where I really want to go with this discussion, however, is the future of storage. One thing that has always bothered me about hard disk drives is the moving parts. Where there are moving parts, there is a potential for disaster, with hard drive crashes being seemingly inevitable, though I do generally get 5-10 years out of my drives before failure. One move from here is to solid-state electronics, which is where Samsung (and perhaps others) are going. Another potential move is to CD-like storage. A few months back, there was a lot of discussion about holographic versatile disc, which if it doesn’t become vaporware, seems to almost certainly define the market for portable storage.

Honestly, I’d prefer a portable storage format that’s crash-resistant, reliable, easy-to-use, and fairly small, so I can carry it on my keychain or something. (CD-like discs don’t quite fit that requirement, which is why I’m thinking more on the lines of a little holographic cube.) That way, wherever I go, I can bring my operating system, files, and so on with me. But I suppose that’s still somewhat in the future, isn’t it?

What ideas do you have for future storage mechanisms? What kind of features are important, and what isn’t so important? Will fixed storage (like hard drives) remain important, or will we move toward an all-portable medium?

The market for portable music players (perhaps more often referred to simply as MP3 players) is certainly strong at the moment. Apple’s iPod certainly gets most of the press, and as far as I know, is still the most popular player on the market. Microsoft’s made a late entry into the game, with its Zune offering, with limited success. That said, there are several other companies producing good players. If you’re buying one for yourself, or if you’re buying one as a gift for someone else, there are a few things you should consider, beyond the marketing hype.

(more…)