Beta
×

Welcome to the Slashdot Beta site -- learn more here. Use the link in the footer or click here to return to the Classic version of Slashdot.

Thank you!

Before you choose to head back to the Classic look of the site, we'd appreciate it if you share your thoughts on the Beta; your feedback is what drives our ongoing development.

Beta is different and we value you taking the time to try it out. Please take a look at the changes we've made in Beta and  learn more about it. Thanks for reading, and for making the site better!

Cell Chip Coming To the PC Via a PCI Express Card

timothy posted about 6 years ago | from the buy-one-for-every-prisoner dept.

Upgrades 164

arcticstoat writes with an excerpt from Custom PC: "After developing a brand new CPU architecture from the ground-up, you'd expect that Toshiba, Sony and IBM would have more uses for the Cell architecture than the PlayStation 3, and Toshiba has been quick to make use of the architecture's HD video transcoding abilities in its new Qosimo laptops. However, Leadtek is now taking Toshiba's efforts a step further by putting the chip onto a PCI-E card for desktop PCs. The WinFast PxVC1100 is based on Toshiba's SpursEngine SE1000 processor, which is a cut-down version of the Cell chip. The SpursEngine chip features four SPEs (synergistic processing elements) based on 128-bit RISC cores, along with H.264 and MPEG-2 codecs, but it doesn't contain its own CPU as the chip in the PS3 does. The chip is capable of encoding and decoding H.264, MPEG-2 and MPEG-4 video streams in hardware."

cancel ×

164 comments

Sorry! There are no comments related to the filter you selected.

yo yo yo (-1, Offtopic)

Anonymous Coward | about 6 years ago | (#25240353)

frist poast

Re:yo yo yo (-1, Offtopic)

Anonymous Coward | about 6 years ago | (#25240603)

TFA:

...based on Toshiba's Toshiba's...

Can the cell chip remove echoes?

Re:yo yo yo (-1, Offtopic)

Anonymous Coward | about 6 years ago | (#25241503)

How is this "offtopic"?

It quotes TFA (now fixed) and mentions the cell processor.
Repeat after me "I will not moderate while drinking".

You may safely moderate _this_ post "overrated".
Thank you.

Re:yo yo yo (3, Insightful)

lysergic.acid (845423) | about 6 years ago | (#25241337)

Leadtek says that the card will enable both encoding and transcoding at speeds that are 'faster than real-time.'

sweet, i can finally have my PVR record programs before they actually air!

but seriously though, how much is this card going to cost? is it just for professional video processing or will there be other uses for it as well? i wouldn't mind having one of these things for a PVR/media center, except for the fact that it needs a one-slot cooler, meaning it probably runs hot and noisy.

Re:yo yo yo (5, Funny)

neokushan (932374) | about 6 years ago | (#25241553)

Lets say the PS3 retails for £300 (it's less than this, but what the hell, this is slashdot, we don't need to be accurate. Or impartial for that matter...let me start again) Lets say the shitty PS3 costs £300, which is far too bloody much, but once you take away the shitty Blu-Ray drive, the shitty Hard drive, shitty controller, shitty case, etc. the price for the shitty fully-fledged CELLs (7 of them, remember) can't be more than £100 and that's a safe overestimation, with added money for the Lube Sony will use to anally violate you with their shitty cocks. This chip has only 4 shitty cores of the shitty CELL and it's not even the full CELL, it's a shitter version of it so I'd say it's a safe bet that it SHOULD cost no more than £50-70, but since the company that makes it is so shitty, they'll probably triple that price. Cunts.

Re:yo yo yo (0)

neokushan (932374) | about 6 years ago | (#25241559)

NOTE TO THE MODERATORS: Subtle amounts of sarcasm are present within this post. Before you mod troll or flamebait, please refer to the first two lines of the post for "the joke", if you missed it.

Re:yo yo yo (-1, Redundant)

dmbasso (1052166) | about 6 years ago | (#25241653)

Someone said in another post to not drink and moderate... I liked the idea. In the same lines, I'd say "You should not drink and watch gay-snuff-porn movies and post comments". Btw, if Sony anally violated you, be happy it was a japanese company. Imagine if it was... Ubuntu!!! (I know, I know... OS not company... don't spoil my retarded joke.)

Re:yo yo yo (0)

Anonymous Coward | about 6 years ago | (#25241993)

I dunno Canonical has a slightly erotic sound. I think it would be a simple but significant anal violation.

anus penis? (0)

Anonymous Coward | about 6 years ago | (#25242157)

penis anus!

Er... supercomputers? (1, Insightful)

Samantha Wright (1324923) | about 6 years ago | (#25240357)

Just maybe? [wikipedia.org] Had anyone other than the submitter and TFAuthor not heard of this?

Re:Er... supercomputers? (1)

somersault (912633) | about 6 years ago | (#25240547)

The whole point is that this is a way to get Cell power in "Personal Computers", rather than supercomputers or games consoles.

Re:Er... supercomputers? (1)

Fred_A (10934) | about 6 years ago | (#25241607)

So we can get "cell power" and then all we have to do is write cell empowered applications !

This is so exciting, I can hardly wait ! Soon I'll be able to index my cactus seeds in no time ! (I've got almost 30)

I mean, gosh !

Re:Er... supercomputers? (1)

aliquis (678370) | about 6 years ago | (#25243249)

Yeah, I can't understand why anyone would want a crippled Cell. I really doubt they are all that superawesome powerful in the PS3 so why would I want something less powerful in my computer?
Also the price will probably be to expensive compared to what you get for the money.

For general computing shouldn't say an Intel Q9550 be a much better choice? Or if I'd really wanted something this specialized why not get whatever Nvidia-card and use their CUDA-stuff?

Where is the market for this card? Sure it may be sad for Toshiba that their Cell-partnership went the way of HD-DVD but.. tough luck.

Re:Er... supercomputers? (1)

aliquis (678370) | about 6 years ago | (#25243257)

(I thought it was obvious so I never said it but also modern graphic cards already do HD-video decoding so this is useless there to, just get a decent graphics card.)

Re:Er... supercomputers? (2, Informative)

Nursie (632944) | about 6 years ago | (#25240923)

Yeah, and there's that whole "Roadrunner" thing, fastest supercomputer in the world. And IBM sell Cell bladeservers...

Re:Er... supercomputers? (3, Funny)

mrsteveman1 (1010381) | about 6 years ago | (#25241087)

meep meep?

haha (-1, Troll)

Anonymous Coward | about 6 years ago | (#25240359)

whats up penis tickler?

Re:haha (-1, Offtopic)

nawcom (941663) | about 6 years ago | (#25240413)

Your penis, obviously.

Re:haha (0)

Anonymous Coward | about 6 years ago | (#25242739)

No if his penis was up he wouldn't be posting on /. he be trawling for poofter cock.

mythtv apps (4, Interesting)

pak9rabid (1011935) | about 6 years ago | (#25240383)

this + mythtv = interesting possibilities

Re:mythtv apps (0)

Anonymous Coward | about 6 years ago | (#25240491)

Don't hold your breath for proper Linux support while this is still useful. That is while this is still state of the art, not last years gadget.

Chances are you can get 8+ core Intel/AMD CPU for half the price before support for this is mature enough to be useful. Sigh.

Re:mythtv apps (3, Insightful)

Walpurgiss (723989) | about 6 years ago | (#25240505)

As op, it would have to be cheaper than the parts in your computer it negates for it to be worthwhile, and even then, linux support is unlikely. If it was cheap enough to make 1080p x264 decoding not require an ati or nvidia graphics card and a modern processor, it would be good. But my quadcore and onboard nForce video is able to do it, so unless this card + like a celeron could do it, it isn't worthwhile

Re:mythtv apps (5, Informative)

batkiwi (137781) | about 6 years ago | (#25240635)

Most modern CPUs cannot decode 1080p blu-rays in linux. The video card has nothing to do with it, as there is no support in any linux driver for GPU assisted decoding of anything apart from mpeg2, and even that is shoddy. ffmpeg works well with two threads on dual core, but quad cores isn't buying much right now.

Low bitrate 1080p rips on the net are not the same quality nor difficulty.

Yes, a dual/quad core super-fast intel setup can do it (and the mythtv list has a big thread right now about what it takes for full blu-ray rips) but right now those machines are expensive and loud.

This card could be perfect for people making HTPCs who want a low power and QUIET computer to watch on their TV using myth/etc.

Re:mythtv apps (1)

corerunner (971136) | about 6 years ago | (#25240689)

Would you be able to decrease rip/encoding time by installing two or more of these cards?

Re:mythtv apps (1)

danwat1234 (942579) | about 6 years ago | (#25241539)

LOL, reminds me of the fake seti@home PCI cards (not actually manufactured) that supposedly decrease work unit completion times, especially if more than one is hooked up.

Re:mythtv apps (1)

Kjella (173770) | about 6 years ago | (#25241027)

Most modern CPUs cannot decode 1080p blu-rays in linux. The video card has nothing to do with it, as there is no support in any linux driver (...) This card could be perfect for people making HTPCs who want a low power and QUIET computer to watch on their TV using myth/etc.

So what made you think Linux would be any better supported on this card? By the way, it looks like UVD2 is coming to Linux with the ATI drivers soon (since they're usually late, before Christmas at least).

Re:mythtv apps (1)

batkiwi (137781) | about 6 years ago | (#25241671)

I think linux would be better supported because of the current support of linux for the cell processor.

Re:mythtv apps (1)

Walpurgiss (723989) | about 6 years ago | (#25241247)

Spot on about the bitrate disparity between BD rips on the net and a full lossless rip. I'm sure any software decoding solution in linux would die a horrible death trying to decode it watchably.

I went without a video card at all just to avoid the noise issue, knowing I'm unlikely to get any full bitrate or blu-ray rips or even close.

Now if this thing could decode full bd rips real-time, and was cheaper than a video card, it would be intriguing. Though again, linux drivers would be neccessary. FTA though, it has a 1 slot cooler on it, so it might be equally loud as a dedicated PCI-Expressx16 slot video card.

Re:mythtv apps (1)

aliquis (678370) | about 6 years ago | (#25243287)

Yesterday I read on a forum that the PS3 had problems decoding DivX and such (various and whatever format, in up to HD resolutions I guess) videos when used as a media player, but still it can play BluRay videos and such so it much have decent decoders for the codecs used for BluRay atleast.

Does anyone know why that is? Just shitty software from Sony? I assume they should be able to upgrade it to decent performance if they tried?

Re:mythtv apps (3, Insightful)

lysergic.acid (845423) | about 6 years ago | (#25241409)

This card could be perfect for people making HTPCs who want a low power and QUIET computer to watch on their TV using myth/etc.

i was imagining how cool it'd be to have one of these + VIA EPIA/Eden micro-ATX (what's the smallest form factor that supports PCI-E?) for a HTPC/DVR. that is until i read that the card comes with a one-slot cooler. that would suggest that the processor runs pretty hot, and the slot cooler would probably make a good deal of noise.

Re:mythtv apps (1)

aliquis (678370) | about 6 years ago | (#25243301)

This won't help for this card, but it would help if you got a regular graphics card instead:
http://www.arctic-cooling.com/vga2.php?idx=147 [arctic-cooling.com]

They have other solutions as well.

Re:mythtv apps (1)

aliquis (678370) | about 6 years ago | (#25243351)

Oh, and btw, there exist Micro-ATX-motherboards with HD3200 or HD3300 built-in, those may be good enough for HD-video. Lots of nForce chipset motherboards to. Sure they are socket 775 so for Intel cpus instead of Via but there exist silent cooling solutions for those to. And I guess you could lower the voltage and clock aswell.

Re:mythtv apps (1)

Jorophose (1062218) | about 6 years ago | (#25241723)

I was thinking something along those lines, using it to speed up decodes on Linux. The problem is, when would support come, assuming support is necessary?

There's all sorts of ARM CPUs that can do h.264 (OSD2 is supposed to ship with one, but only for SDTV/EDTV, beagleboard does 720p but I'm not too sure what formats). The problem there is that they don't do HD.

Should this work really well under Linux, I could easily see VIA boards fitting dual PCIE (or seeing this card for a different bus, or using a riser). VIA Nano 1GHz would use 5W or less depending on the model; should be more than enough for all your background tasks. Offload the video onto the PCIE card, and even with a PicoPSU-120 you should have more than enough power. Stick in an HD4450 or something similar on another PCIEx16 slot, and now you can game too.

Re:mythtv apps (0)

Anonymous Coward | about 6 years ago | (#25242975)

It could go in an mythtv backend and transcode all your stuff. Perhaps you have mpeg2 or a analog signal and you want to save in h.264, so you save disk space.
I have an appletv, which is only able to decode mpeg2 in the nvidia cpu (because the driver is limited), so if I have h.264 content I could transcode it to mpeg2.

Transcoding in real time, or faster, is very cpu intensive, so offloading to Cell power could be nice.

Re:mythtv apps (1)

aliquis (678370) | about 6 years ago | (#25243271)

This is already 2005s years gadget or something like that. The Cell is not state of the art now.

Re:mythtv apps (0, Flamebait)

Anonymous Coward | about 6 years ago | (#25240761)

No it wont... because I'll bet you $1000 they will NOT create linux drivers or open up all the specs so that a linux driver could be written.

so we will get that card working in about 5 years after it's pretty much abandonded and someone reverse engineered it. Like the Hollywood+ cards back in the late 90's.

This card would make media center pc's and Linux XBMC awesome as well as letting myth play back HD recording nicely without having to throw insane amounts of processor at the job like you have to currently.

How about everyone contact leadtech and demand they open all the specs without a stupid NDA asap so that a linux driver can be made.

Nahh, that will never happen. The guys at leadtech are asshats.

Re:mythtv apps (1)

TooMuchToDo (882796) | about 6 years ago | (#25242231)

Doesn't the Folding@Home project have a client that runs on the PS3? Doesn't that client use the Cell system to churn through work at a much faster pace than a regular CPU? If they can access the processor, I'm sure this will be accessible.

Re:mythtv apps (1)

TooMuchToDo (882796) | about 6 years ago | (#25242289)

To add to my comment:

http://folding.stanford.edu/English/FAQ-PS3 [stanford.edu]

How does the PS3 client's visualization compare to other FAH clients?

The PS3 client supports advanced visualization features. While the Cell microprocessor does most of the calculation processing of the simulation, the graphic chip of the PLAYSTATION 3 system (the RSX) displays the actual folding process in real-time using new technologies such as HDR and ISO surface rendering. It is possible to navigate the 3D space of the molecule using the interactive controller of the PS3, allowing us to look at the protein from different angles in real-time.

Re:mythtv apps (1)

rtechie (244489) | about 6 years ago | (#25240875)

As many have said, this isn't cost-effective for the hobbyist (assuming there is proper Linux support, which is unlikely) unless he's encoding shitloads of video i.e. he as at least 4 HD streams he's encoding. This is more for content providers making dedicated encoding boxes.

Re:mythtv apps (1)

davolfman (1245316) | about 6 years ago | (#25242475)

Wasn't part of the news that both WinDVD and PowerDVD would potentially support this? That would certainly help for lightweight Windows HTPC's especially given that the card is a half-height and only needs a PCIe x1.

I think I can already do that (1, Informative)

Corpuscavernosa (996139) | about 6 years ago | (#25240421)

The chip is capable of encoding and decoding H.264, MPEG-2 and MPEG-4 video streams in hardware.

Don't video cards do that? or does this thing just sorta add juice to your system?

I WANT THIS TO BE AWESOME but I'm just a bit underwhelmed.

Re:I think I can already do that (3, Informative)

batkiwi (137781) | about 6 years ago | (#25240649)

-in linux, no. only mpeg2 decoding
-in any OS, not really. There is a brand new ENCODER for h.264, but reviews show it to be crap and limited

Windows does have full GPU decoding of h.264 with modern nvidia (not sure about ATI, but it is likely), but that's it.

Re:I think I can already do that (1)

Hal_Porter (817932) | about 6 years ago | (#25243253)

-in linux, no. only mpeg2 decoding
-in any OS, not really. There is a brand new ENCODER for h.264, but reviews show it to be crap and limited

Windows does have full GPU decoding of h.264 with modern nvidia (not sure about ATI, but it is likely), but that's it.

Wouldn't it be better for Linux to get h.264 decoding working on GPUs rather than work on this card which will probably end up being low volume and thus high cost?

Re:I think I can already do that (1)

squiggleslash (241428) | about 6 years ago | (#25240867)

Is the author aware that H.264 is one of two video encoding standards that fall under the umbrella of "MPEG4"? (H.264 is MPEG 4 Part 10, with the other being Part 2, and I can't honestly remember what it's called. DivX is built off of it, but it's otherwise generally considered kinda irrelevant these days.)

Re:I think I can already do that (1)

lysergic.acid (845423) | about 6 years ago | (#25241567)

XviD and DivX are the two most popular video codecs used on the internet, both of which are MPEG-4 Part 2 encodings. i would hardly consider it irrelevant. XviD in particular is useful because it provides high-quality video compression under a GNU license and is supported on all platforms. H.264 is a patented codec, so despite there being open source implementations, it's still excluded from certain FOSS products.

the author probably wanted to specifically mention H.264 because it's a very well-known encoding that is used in popular consumer products like the Video iPod, iPhone, PSP, etc.

frankly, out of the specifically mentioned encodings, MPEG-2 is the most out of date and would be completely irrelevant if it weren't used in DVDs. no one uses MPEG-2 encoding for either downloadable content or ripped movies. it doesn't offer good compression ratios (for reasonable video quality). even digital TV broadcasts are quickly switching to the higher quality MPEG-4 AVC.

Re:I think I can already do that (2, Informative)

doctor_no (214917) | about 6 years ago | (#25241017)

Its not meant for playback of a single video like the GFX cards do, or watch a DVD or Blu-ray, its designed for content creation and distribution. In an early demo, the Cell did 48 simultaneous Mpeg2 streams in real-time.

http://gizmodo.com/gadgets/home-entertainment/playstation/cell-processor-demos-mpeg2-x-48-100853.php [gizmodo.com]

 

Re:I think I can already do that (1)

evilviper (135110) | about 6 years ago | (#25242089)

Don't video cards do that?

No. Video cards don't do any encoding.

Two things (2, Interesting)

iamwhoiamtoday (1177507) | about 6 years ago | (#25240445)

#1: Is there going to be a Mac Version? I would love to put this in my Apple Tower, I have 3 PCI-E x16 slots sitting around doing nothing. #2: When is this actually going to come out? I mean, I keep reading things on "fantastic pieces of tech" and they either never come out, or they come out everyone forgets about them. Anyone know what this should retail for, or if software can even take advantage of it yet?

Re:Two things (2, Interesting)

somersault (912633) | about 6 years ago | (#25240589)

Any PCIe card is a 'mac version' just as much as it is a 'PC version' - perhaps you mean will there be drivers or a developer API for the Mac - the good thing is that a lot of Linux geeks will be wanting this (probably good for University research projects), and if there is Linux support then basically you will already have OSX support.

The interesting question is, what are you planning to do with it that you can't already do fast enough with a multicore CPU, GPU or physics type add in card? Or do you just want this because it's there? I'm not meaning to criticize especially, I tend to waste a lot of money on gadgets myself..

Re:Two things (1)

iamwhoiamtoday (1177507) | about 6 years ago | (#25240709)

Mainly because I enjoy trying out the latest tech. I have too many computers utilizing many advances in technology, and I'm always trying to find a way to either expand their capacity, or just to check out cool new things. (and yet I don't have an iPhone... go figure)

Re:Two things (1)

somersault (912633) | about 6 years ago | (#25240835)

That's probably because iPhones aren't really advanced. I had a 3G touchscreen smartphone (HTC TyTN) about a year and a half before the first gen iPhone even hit the streets.. I have always liked Macs since I was a kid (we had a Mac Classic which I used to play games on, write up my homework on, and I even did a bit of coding on it), but iPods and iPhones don't interest me too much. I doubt you'd be able to do anything useful with a Cell PCIe card unless you are heavily into scientific research, cryptography, games development or something like that tbh.

Unless this thing is cheaper than a graphics card and your system can't handle HD graphics streams then it will remain pointless even for most geeks.

Did you see the article about the Pandora console? Now that is IMO a geek toy worth blowing some cash on (and thankfully I was on the mailing list so I got an order in before the site was slashdotted) :)

Re:Two things (1)

lysergic.acid (845423) | about 6 years ago | (#25241815)

Did you see the article about the Pandora console? Now that is IMO a geek toy worth blowing some cash on (and thankfully I was on the mailing list so I got an order in before the site was slashdotted) :)

i couldn't agree with you more. personally, i love my PSP to death. it's the only gaming system i have, and i use it all the time to read e-books, listen to audiobooks, or play PSX games. once you get CFW on it, there's no other handheld out there that can compare as a general portable entertainment device. however, the Pandora is looking to change that.

as a novice C++ programmer, i really wanted to develop my own homebrew apps for the PSP, but the lack of real documentation and closed nature of the platform presents a daunting obstacle. so when i heard about Pandora, it got me really excited. a powerful open source handheld whose manufacturer embraced & encouraged homebrew? how could any real geek not be psyched by this news? the Pandora is a tinkerer's dream.

the people complaining about how Pandora isn't newsworthy because it can't compete with the PSP/DS just don't get it. yea, the PSP/DS have a lot more games and publisher support, but that's not the point. the Pandora isn't competing for the mainstream gaming market. between the PSP and the DS, Sony and Nintendo have the bases covered. but the Pandora is aimed at a niche market who up until now have had to content themselves with voiding the warranty on their PSP/DS.

compared to many other articles posted on /., the average computer geek probably has a lot more use for the Pandora than any of the supercomputers, super batteries, Cell-powered PCI Express cards, or other specialized hardware that the average geek may read about simply as a passing interest in its novelty.

Re:Two things (2, Insightful)

christurkel (520220) | about 6 years ago | (#25241603)

and if there is Linux support then basically you will already have OSX support.
You've never tried to write a Mac OS X driver, have you? If so, you'd know you couldn't be more wrong. OS X uses a totally different different architecture; they are not even close. OS X uses I/O Kit. Not even FreeBSD is close.

Re:Two things (1)

Trelane (16124) | about 6 years ago | (#25242293)

what are you planning to do with it that you can't already do fast enough with a multicore CPU, GPU or physics type add in card?

If it's cheap enough, it's an affordable Cell processor to play^H^H^h^Hprototype with. :)

Re:Two things (1)

Hal_Porter (817932) | about 6 years ago | (#25243267)

The interesting question is, what are you planning to do with it that you can't already do fast enough with a multicore CPU, GPU or physics type add in card? Or do you just want this because it's there? I'm not meaning to criticize especially, I tend to waste a lot of money on gadgets myself..

We should replace -1 Flamebait with -1 Passive Aggressive

Re:Two things (0)

Anonymous Coward | about 6 years ago | (#25242001)

Why would you want to use a piece of hardware that wasn't bless by The Jobs?

Why bother? (4, Insightful)

HateBreeder (656491) | about 6 years ago | (#25240453)

This spurs engine sounds just like an extra GPU...

Why not just go with CUDA or some other GP-GPU platform and avoid the hassle?

I know nVidia and AMD/ATI are doing H.264 decoding in hardware using their GPUs... I'm sure you can get software for encoders too.

Re:Why bother? (5, Informative)

stonecypher (118140) | about 6 years ago | (#25240509)

CUDA is a matrix processor. This is a serial processor. CUDA isn't really applicable to general purpose tasks. This is. CUDA gets its power by running the same function over an array of inputs to generate an array of outputs.

Different beasts.

But then the question is (2, Insightful)

Sycraft-fu (314770) | about 6 years ago | (#25241719)

What does it have over a normal multi-core processor, like say a Core 2 Quad?

The problem I've been seeing with the Cell both in terms of how it performs in the PS3 and the researchers tinkering with it at work (I work for a university) is that it doesn't really seem to have something that it is great at. A lot of the tasks people tout for it are highly parallel tasks, like Folding@Home. Ok, wonderful, except a GeForce crushes it. A GTX 280 using the CUDA client is much faster than a Cell. Ok so, not for tasks like that. You say it is more applicable to general purpose tasks. Fine, but we've got that already. Intel's Core and AMD's Athlon processors are some amazing general purpose processors for some amazing prices. From what I've seen, at regular CPU tasks, it can't keep up (in the PS3's case, the CPU core that has to dispatch everything to the cells gets swamped). So then what is the market?

You'll note that here one of the things listed is H.264 encode/decode. Well that IS something that GPUs do and quite well. The decode functions ship with newer drivers. As for encoding, there's a program called Badaboom that uses the GPU to do the encoding. So thus far a lot of the things I've seen the Cell marketed for (video, physics) are things GPUs with CUDA kick ass at.

The real question isn't what can this card do, it is what can it do better and/or cheaper than either a CPU or GPU? Doesn't matter if it can do everything that they can do, if it is turning complete it can pretty much by definition. What matters it can it do it for either less dollars or in less time (or better yet, both)?

Also in the video domain it has to compete with ASICs. I don't know about H.264 but there are very cheap MPEG-2/4 codecs. Each chip does 4 realtime encodes and decodes, and they aren't pricey. Computer based CCTV systems use them all the time.

Re:Why bother? (0)

Anonymous Coward | about 6 years ago | (#25241917)

Yes, but video decoding, gathering from discussions I've had, can actaully be a mix of both. The simplest form of decoding is largely parallel (i.e. CUDA is great for this). However, when you start doing noise filtering and other forms of post-processing, I imagine there's a lot of serial work to be done as well.

Am I right?

Re:Why bother? (1)

neocrono (619254) | about 6 years ago | (#25242563)

Cell may be more applicable to general purpose tasks than GPGPU, yes, but I recall hearing from several Playstation 3 developers that the synergistic processing elements, or "SPEs"--the only part of the Cell architecture that this board includes--are agonizingly difficult to program for because of the incredibly small amount of local memory available to them. I want to say it's 256 KB?

Given 4 SPEs, that's a total of a megabyte of memory, shared 4 ways. I'd say these add-in cards are arguably even more limiting than a graphics card.

Re:Why bother? (1)

snikulin (889460) | about 6 years ago | (#25240669)

We've been there with audio already. And with "full" modems. And with printing PCL/PS engines (remoted on big printers). As soon as CPU could handle it, the add-on cards will almost disappear (except for hi- and pro- end applications). I think multi-core CPUs will start to achieve that level in 2009. Essentially, they do it already but for the hi-$$$$.

Re:Why bother? (2, Interesting)

tonytnnt (1335443) | about 6 years ago | (#25240789)

Hardware encoding acceleration h.264 isn't easy to do on GPUs as I recall. Your source video file isn't really meant to be worked in parallel, so a serial approach (like this) should work better. At least from what I've been reading/told, which is mostly related to transcoding rather than pure encoding. Someone else might be able to enlighten us more (hopefully a dev from x264 maybe?)

Re:Why bother? (1)

i.of.the.storm (907783) | about 6 years ago | (#25240863)

AMD has something called the Avivo video encoder which supposedly makes encoding videos really fast and uses very little CPU. Unfortunately, I have an AMD card that is just the wrong type and doesn't have the UVD chip so I can't test it out myself, but the Radeon HD 2600 and all 3x00 and 4x00 GPUs have it. Not sure why they left it out on the 2900s, ugh. I guess the 2900s already generate more heat than almost anything else, so one more chip might be too much.

Re:Why bother? (0)

Anonymous Coward | about 6 years ago | (#25241165)

IIRC, they only have the encoder available for a small number of cards from a few generations ago. They don't support it on the newer cards. Decoding acceleration, yes. But not encoding acceleration.

Yes, but... (2, Informative)

lowlymarine (1172723) | about 6 years ago | (#25240497)

...can it play Crysis?

Because if not, seeing as modern graphics cards [wikipedia.org] all feature hardware MPEG, I'm kind of underwhelmed by this announcement.

Re:Yes, but... (3, Insightful)

SoapBox17 (1020345) | about 6 years ago | (#25240629)

Most feature hardware DEcoding (such as those you linked to). Few feature hardware ENcoding, as TFA does.

Re:Yes, but... (0)

Anonymous Coward | about 6 years ago | (#25241035)

Few feature hardware ENcoding,

I believe my Radeon AIW card did. I used to use the card for real-time capture/upscaling/encoding to high bitrate MPEG-2 via S-Video at 640x480. After that, I would transcode to 1MBps DivX 5, and hour long episodes came out to roughly 450 MB.

No, you couldn't fit two on a CD, and DVD's weren't mainstream yet, but despite the fact that I couldn't release immediately after airing, people would wait until the next day to grab my caps because they just looked so much better.

Years later, before the show hit DVD and torrent sites sprung up, I found them again all over the net, bundled in torrents with all the previous seasons from other groups.

I was such a dedicated pirate in high school... Didn't get me laid, though.

Does it run ... ? (4, Interesting)

sergstesh (929586) | about 6 years ago | (#25240597)

The mandatory "does it run Linux ?" boils down to "do they provide enough documentation to write drivers for it ?".

I RTFA, but I didn't find an answer in it.

Hopefully so, unless they really hate Linux. (3, Informative)

Anonymous Coward | about 6 years ago | (#25241125)

Probably. We already have enough information about the CELL processor on its own to make use of it under Linux; this card is just taking a cut-down CELL and tacking a PCIe bus on it.

Unless they purposefully fucked the register table to prevent it, it's probably just a matter of finding the correct PCIe offsets to access known registers/segments on the CELL. While it's possible they could "sabotage" it to prevent the first-day-out-of-the-box Linux driver, chips modified this way usually have to go under more steps of formal validation again (beyond that of just throwing a PCIe controller on, and sheering a few SPUs off), so most companies won't do it.

Before we get too confident, though, there is a history of this kind of intentional fucking. Conexant acquired some video IP from a defunct company Brooktree, the BT8x8 model, which worked fabulously under Linux, which they re-released with virtually unchanged functionality, but with a completely revamped address table. Brooktree was more friendly and released the specs for its chips to the public, so the Linux driver was fantastic. Since Conexant would not release the new specs without an NDA (and is generally is Linux's bane when it comes to hardware), it took months to get the new driver back to the shape that the old one was in (and IIRC, it was only after someone stepped forward and went under the NDA to do so).

I hope I have room for another card! (2, Funny)

ProppaT (557551) | about 6 years ago | (#25240621)

::checks case::
Ooh, awesome! I have one more PCI-E slot left, right next to my PhysX accelerator! Where do I pre-order?

I can see a use for it.... (3, Insightful)

snicho99 (984884) | about 6 years ago | (#25240705)

Decoding .264 isn't really such a big deal. The ability to do low-cost multi-pass 1080 h.264 encoding at greater than real-time is something that would be EXTREMELY welcome for my company. We're a video post production house and we burn *LOTS* of CPU cycles encoding video for delivery to clients. A sub $500 card that greatly streamlined that process would be VERY welcome. Especially if it's something you could do as a background process that effectively didn't interfere with the operation of the edit suite.

Re:I can see a use for it.... (2, Interesting)

fuzzyfuzzyfungus (1223518) | about 6 years ago | (#25240973)

Just hope that they expose the card's power in a nice way. Documentation and/or SDK so that your in-house geek and/or the next version of $EDIT_SUITE can silently harness the power of the coprocessor? Instant win.

Attempting to integrate Leadtek l33tripZ SE (Now with the crushing power of the "buggy, ill-defined, good enough for consumers" h.246 profile in hardware! Totally Vista compatible(32 bit systems only, when run as administrator during waxing moon)) into a professional workflow? World of pain.

So, yeah, do linux geeks, I mean... yourself a favor and tell Leadtek that your outfit will totally buy them by the crate if documentation is good. ;)

Need more info (1)

getnate (518090) | about 6 years ago | (#25240791)

The article doesn't specify which H.264 profiles and levels the card will encode and decode. Don't get too excited yet.

50/50. (4, Interesting)

fuzzyfuzzyfungus (1223518) | about 6 years ago | (#25240793)

The fate of this device hinges pretty much exclusively on the quality of its software and documentation. If all you get is some gaudy half-broken-and-all-ugly fixed purpose video encode decode app(in the fine tradition of graphics card shovelware, remember the bad old days when the card vendor was responsible for the driver?) then this thing is dead in the water. A few will sell to Netflix pirates looking to rip and encode 3 times as much video as they could ever watch, instead of just twice as much; but that'll be about it.

If it has good general purpose support(I'd really prefer that this mean "good documentation" and properlinux support; but I suspect a proprietary sdk would do alright as well) then it could be a killer in certain lower end computing scenarios. Since the cell is produced in nontrivial bulk, and this thing is only about 1/2 the complexity of a full cell(does that mean that this card is "spursengine on the half-cell?) it should be cheap, cheap, cheap compared to FPGA boards or custom ASICs for such purposes as the cell architecture is useful.

I hope the do the right thing, and get rewarded(and I hope so, surely somebody looking to sell computational hardware would see the virtues of making it as useful as possible for as many customers as possible?); but if they don't, I suspect that they'd be lucky to do as well as physX, and will probably do worse.

Re:50/50. (1)

not already in use (972294) | about 6 years ago | (#25241411)

I'm sure Sony has the best dev tools for the thing, will be interesting if they release them in some form or another.

About damned time! (0, Redundant)

cmacb (547347) | about 6 years ago | (#25240869)

About damned time!

Shit man... (3, Funny)

alexborges (313924) | about 6 years ago | (#25240921)

I want to be a synergistic procesing element!

Doesnt everyone?

Only pci-e x1 and 128meg of ram? ati, nv cards hav (2, Insightful)

Joe The Dragon (967727) | about 6 years ago | (#25240955)

Only pci-e x1 and 128meg of ram? ati, nv cards have more ram at a lower cost with a pci-e x16 link.

The x1 link will slow this down. HTX is even better then pci-e for a add in cpu.

I don't care if there's a PCI card for it but... (1)

LedIris (1331589) | about 6 years ago | (#25241013)

...I am not leaving without my elephant(motherboard).

Already been done (1)

phil_ps (1164071) | about 6 years ago | (#25241083)

Mercury Computers offers a $7000 PCI Express card that has an _Original_ Cell BE chip. It takes up some much power and is so finicky that you basically have to buy the recommended computer to put the card in or it won't work.

See also, Mercury Computers (1)

LotsOfPhil (982823) | about 6 years ago | (#25241151)

Mercury Computers has had a card with a cell on it for quite some time. It is, I believe, very expensive (~$10k?).
Link to the card. [mc.com]

How Not to Build a Multicore Processor (2, Insightful)

Louis Savain (65843) | about 6 years ago | (#25241263)

The Cell is a perfect example of how not to design and build a multicore processor. It's a powerful processor but it's a pain in the ass to program. The worst thing that a multicore designer can do is build a processor before the programming model is designed and tested and all the chinks ironed out. But Sony and IBM are not alone. Intel is making the same mistake with Larrabee. AMD is soon to follow suit with its Fusion hybrid. It's enough to make a grown man cry. The truth should be clear to everyone by now. Heterogeneous processors are not the way to go simply because there is no easy software model that makes them easy to program. GPUs are not the answer either because they lack universality. As Tim Sweeny said recently [arstechnica.com] , what is needed is a homogeneous processor. It will do wonders for productivity. Homogeneity and universality is what is called for. The Cell is anything but.

In my opinion, both the CPU and the GPU are doomed [blogspot.com] for the simple reason that they are not universal. There is only one type of parallel processor core that can handle anything you can throw at it and that's a pure MIMD vector core. None of the multicore vendors have one none are planning to build one. Why? Because they don't have the right programming model. Unless they see the error of their ways, some other organization will do the right thing and rocket past them. They won't know what hit them until it's too late. The writing is on the wall.

Re:How Not to Build a Multicore Processor (0)

Anonymous Coward | about 6 years ago | (#25241483)

The worst thing that a multicore designer can do is build a processor before the programming model is designed and tested and all the chinks ironed out.

What do the Chinese have to do with it?

Re:How Not to Build a Multicore Processor (2, Interesting)

91degrees (207121) | about 6 years ago | (#25243203)

I wouldn't be so sure. Dedicated hardware is typically a lot cheaper than a general purpose CPU unless the tasks you want to do are extremely general. GPUs work very well with a simpler SIMD approach, and this can be extended to raytracing. It's an approach that works well for a lot of big number crunching tasks.

For more general purpose work, MIMD is useful. I have to wonder why Cell didn't take more cues from the Transputer. From what I've read, The Cell seems to be based on the idea of running multiple threads in parallel and having one core handle each thread. Always seemed rather inefficient. Seems that a better idea would be to package up the processes into a number of very short tasks, and assign each task to the next free core. This will, of course, require a totally different software architecture.

API support (0)

Anonymous Coward | about 6 years ago | (#25241399)

Can I run nVidia Aegia or Intel Havok games with this? I assume no way and this isn't for general users, this is only for the HPC crowd?

knIgga (-1, Redundant)

Anonymous Coward | about 6 years ago | (#25241489)

stand anymogre, [goat.cx]

Amiga 4.0? (0)

Anonymous Coward | about 6 years ago | (#25241565)

But what about the possibility of (maybe) being able to run Amiga 4.0 on it?

What we need is a daughterboard that we can run Unix or Amigas on. Then we're talking some fun possibilities...

Sounds like a basic hardware encoder (1)

DJRumpy (1345787) | about 6 years ago | (#25241687)

Well, maybe not basic. Essentially it will take the load off the cpu for the guts of h.264 encoding. Many capture cards use this technology to allow for faster and higher quality real-time encoding. This is actually a good thing for video hobbyists.

Purpose? (1)

Nodamnnicknamesavial (1095665) | about 6 years ago | (#25241717)

Is this any more or less efficient than offloading these same tasks to the GPU? I thought the whole point of GPU offloading was that you have this powerhouse chip in your PC already, making further upgrades or additions to handle video unnecessary?

Chip production yield was _that_ poor? (1)

White Flame (1074973) | about 6 years ago | (#25241789)

IIRC, the PS3 offers 7 SPEs, so they can increase their yield by letting those with one blown/bad SPE still ship, reserving the full 8-working SPE units to more expensive applications. So the chips in these cards are so bad that they have up to 4 dead SPEs and a dead PPE as well?

I wouldn't think that there'd be enough of a market segment to create a separate, more limited version of this chip just for applications like this. This have got to be their mitigation strategy for incredibly low yield.

Re:Chip production yield was _that_ poor? (2, Insightful)

Wesley Felter (138342) | about 6 years ago | (#25242287)

SpursEngine is not a partial good Cell; it's a different chip.

those who cannot remember the past (0)

Anonymous Coward | about 6 years ago | (#25241797)

Oh awesome, a computer of a different architecture inside my own computer!

This will be precisely as useful as the SunPCI card for all those Ultra5s and Ultra10s. And probably adopted just as widely.

I can't wait to get them out of a box of junk at a yard sale for $10 because no one knows what they are.

PS3 Emulator? (1)

thenewguy001 (1290738) | about 6 years ago | (#25242017)

Hmm, would this would make it much easier to develop a PS3 emulator for PCs?

Re:PS3 Emulator? (1)

Wesley Felter (138342) | about 6 years ago | (#25242297)

SpursEngine has 1/4th the performance of Cell; you do the math.

Re:PS3 Emulator? (1)

stpk4 (906462) | about 6 years ago | (#25242589)

so we need 4 cards then?

di3k (-1, Redundant)

Anonymous Coward | about 6 years ago | (#25242127)

are The important

How is this new? (4, Informative)

rockypg (787998) | about 6 years ago | (#25242237)

Mercury had a PCI-e cell expansion card [mc.com] for over a year now.

Unlike the leadtek one, the mercury version has the full version of the cell processor, with 8SPEs. Dont think it comes with any prebuilt codecs though.

Open Graphics Project (1)

Ivlis (1234144) | about 6 years ago | (#25242331)

Has the Cell processor been considered as a GPU for the Open Graphics Project?

Is this really needed? (1)

blahplusplus (757119) | about 6 years ago | (#25242521)

I remember when Creative and a few other companies had media decoder/encoader boards packaged with DVDROMS when they first came out, seems like a step back IMHO.

Load More Comments
Slashdot Login

Need an Account?

Forgot your password?