Slashdot Mirror

A hundred million PCs are getting sold this year without SATA support ....

Just because you don't have SATA doesn't mean you can't add it. You're going to spend $280(approx) for a SSD, spend $600-1000 to populate it with memory, and about $50-200 for battery packs and perhaps a UPS, but you wouldn't also spend just $32 to add a couple Serial ATA ports ???

Serial ATA makes a lot of sense for a many reasons, the main one being that it's simply faster than parallel ATA. Today, SATA is 150 Mbytes/sec... only slightly faster than the fastest parallel ATA at 133 Mbytes/sec. But in designing a high speed SSD, I'm certainly not going to skimp and I'll definately use a SATA PHY chip that supports 300 Mbytes/sec, or the planned 600 Mbytes/sec if a PHY chip is available, or a pin-compatible version is planned. I'm also planning on primarily designing around reconfigurable FPGA-based hardware, which reduces a lot of the risk and development costs, and might allow me to populate the boards with faster PHY chips as they become available.

With 300 Mbyte/sec SATA and the plans for 600 Mbyte/sec down the road, AND many gigabytes of DDR DRAM media that can actually have sustained I/O at those speeds with virtually zero latency, parallel ATA is looking like quite a dinosaur. Of course, future motherboards will need PCI-X or some other faster bus to transfer these amazing speeds... but all that is coming soon.

Anyway, the main point is that you can pretty painlessly add SATA ports to your existing PC with an inexpensive card. And lots of inexpensive adaptors are available to retrofit "legacy" parallel ATA drives to SATA (which will likely be needed if motherboards start phasing out parallel ATA connectors... which is expected soon since all the new semiconductor processes don't provide 5 volt tolerant I/O pins anymore).

STMicroelectronics Sets World Record for Silicon Light Emission

(Score:-1, Overrated)

So I just signed up for a project next year using PDAs and biomentrics from ST Microelectronics. Anyone used their fingerpring reco kit? Is it any good?

The Imaging and Display Division of ST Microelectronics (formerly VLSI Vision Ltd) makes the chipset for the CPiA-based webcam as well as the upcoming CPiA2 chipset.

I'm not sure about the original CPiA project, but with the CPiA2 chipset Linux driver ST Micro provided the intial driver source (ported from their Windows driver), and they have a staff developer on the open-source team. Of course the CPiA2 code is still a work in progress.

Good example. Kyro is a rev of the tile-based PowerVR technology. (I mentioned them as scanline based on memories of their earliest, earliest stuff but they've clearly been doing tile-based stuff for years now.) If it had ever shown up as faster than NVidia/ATI by an interesting amount, I'd consider it a possible landscape-altering innovation. But they haven't even matched them AFAIK. So they have to charge less for the card in an attempt to make it "faster than comparably priced cards" as even the most flattering reviews linked to by this Kyro website indicate. Which is nice but hardly a compelling technological breakthrough.

Besides what I mentioned earlier, another basic downside is this: a tile based renderer makes sense if there is a lot of 'overdraw' where a given pixel on the screen is redrawn multiple times for each object between eye's viewpoint and the horizon. Then the bandwidth savings of tile-based approaches payoff. But most FPS game and flight simulators have pretty low overdraw as part of the basic tuning process for more conventional architectures. I recall one of the Quakes having average overdraw per pixel of about 1.25, since BSP trees ensured that you only drew the nearest walls, and only a few pixels on average would be drawn multiple times (the portion of the screen filled by bad guys or in-room objects). In such a case, getting tile-based speedups above 25% (and that itself is a best best case) takes some other advantage besides the back-end memory bandwidth one.

--LP

I don't believe there's a flavour of Apple ][ that can decode MP3 streams real-time in software. However, an Apple ][ should be able to easily run a GUI (and now IDE filesystem), and just send the resulting raw MP3 bitstream to to an inexpensive outboard decoder chip. (Some buffering for constant data rate may also be required).

FWIW, if anyone wants to take the leap, the standard homebrew decoder chips used today seem to be one of these...
Micronas MAS3509F Compressed-Audio Decoder
SGS Thompson STA013 MP3 Decoder
The Micronas chip is newer and doesn't require an external DAC.

For a player that fits into the world envisioned by Thomson & Fraunhofer IIS-A, it's really not that expensive to make a cool MP3 player...
<shameless plug>
...like this one that I've been working on lately.
</shameless plug>

These chips aren't upgradable, at least in any meaningful way. Some commercial players are based on DSP chips, but generally the power consumption is high, so they don't tend to run from batteries. The empeg is a good example, though I believe it uses a strongarm chip instead of a dedicated DSP. The creative nomad jukebox (still vapor) is another example, where they only get 3-4 hours from high capacity NiMH batteries.

There are an aweful lot of hardware players running from batteries that use these existing chips that only decode MP3. Perhaps the download software could convert vorbis to mp3 during the download? Of course, if a nice low-power vorbis decoder chip existed, maybe one could make a player that only used vorbis (longer play time) and convert mp3 to vorbis during the download. The use may end up using vorbis and not even know it.

Well, to avoid making a truely shameless plug (only a bit shameless?), I'll avoid posting a link.... if you really want to see it, follow the link to my site above in the user info. The player is still more or less vapor, but maybe in a couple weeks circuit boards will actually be available.