Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Open-Source Graphics Processor

kickstarter.com

Post reply on HN
Print view View original

61–70 of 78 posts

Re: Open-Source Graphics Processor

#61

Post by Narishma »

agumonkey wrote: post #54
pjc50 wrote: post #51

Earlier quoted context omitted.

If you want a large set of general purpose RISC cores, check out Tilera and Netronome. The Raspberry Pi GPU is actually very powerful, but not in ways that help you with CSS/DOM; I don't think there's much work been done to accelerate layout in 3D accelerators other than at the very basic level of glyph rendering and image uncompression.

Actually the rpi case is fueling my desire. I know that the VideoCore part of the SoC is very potent but it's encapsulated beneath too many layers (especially considering the goal of the rpi, I would love to have simple access to all the gpu).

You can start here: https://github.com/hermanhermitage/videocoreiv/wiki/VideoCor...

Re: Open-Source Graphics Processor

#62

Post by agumonkey »

Narishma wrote: post #61
agumonkey wrote: post #54

Earlier quoted context omitted.

Actually the rpi case is fueling my desire. I know that the VideoCore part of the SoC is very potent but it's encapsulated beneath too many layers (especially considering the goal of the rpi, I would love to have simple access to all the gpu).

You can start here: https://github.com/hermanhermitage/videocoreiv/wiki/VideoCor...

One word: thanks.

Re: Open-Source Graphics Processor

#63

Post by pjc50 »

zackmorris wrote: post #58

As someone who has done a fair amount of OpenGL programming, I can honestly say that it's becoming a convoluted spec. It's no longer elegant or something that should be aspired to IMHO, YMMV. The principles are generally sound, just not the implementation or API. I would rather see an FPGA being used as a general purpose DSP with the ability to run shader code in software, perhaps inside a runtime written with Go or…

Or you could buy a 72 core processor: http://www.tilera.com/products/processors/TILE-Gx_Family

(it's not as powerful as it sounds; memory bandwidth ends up being a major constraint, and programming all those cores effectively is hard in itself)

Re: Open-Source Graphics Processor

#66

Post by neurotech1 »

ChuckMcM wrote: post #60
pjc50 wrote: post #24

As someone with a chip design background: - prices seem reasonable for doing this as a commercial project - badly written intro that assumes far too much - seems to be based on 2000-era technology - not actually delivering hardware, so very limited practical use - the community that demands open hardware on principle is a lot smaller than they think, so this probably won't get funded But we're not used to kickstartin…

Agreed, this is both too little and too much in the same Kickstarter. So there is a pretty nice FPGA + Dual ARM9 chip, the Zyng7020 which is used in the Parallela and the Zedboard[1]. This has a pretty decent amount of FPGA fabric, and it could use an open source frame buffer to go along with the core. One of the hugely annoying things about Xilinx parts is that their design flow is insanely over complex. That said,…

I have a Parallella from another KickStarter, with a Zynq-7020 included. It would be interesting to use the Epiphany-16 co-processor as well to evaluate GPU concepts and code.

[1] http://www.kickstarter.com/projects/adapteva/parallella-a-su...

Re: Open-Source Graphics Processor

#67

Post by justincormack »

simias wrote: post #43
justincormack wrote: post #27

I wish people wouldn't use the LGPL for "hardware" without a legal opinion from the FSF. I mean what is "linking" for verilog code? - it does not fit the model. The intentions are fine but the mechanisms need work.

I don't know that the FSF has to say but I can easily imagine what the LGPL would mean in the context of hardware IPs: if you modify the core of the IP in any way you have to share the code. However the rest of the hardware that interacts through the documented interface or ports of the IP (that would be the "linked" part) is not subject to the license. Modern ASICs are built around blocks connected by a system bus s…

As I said, the intentions are clear but the license is inappropriate. Licenses, especially GPL style ones need to get the details right. What if you change the interfaces, how does that affect it, or if you change the process. can you draw the line where you like. And thats an LGPL style license. I have come across people using the GPL, what is the boundary of that system. The LGPL has all sorts of provisions specific to basically C libraries.

Re: Open-Source Graphics Processor

#68

Post by zackmorris »

pjc50 wrote: post #63
zackmorris wrote: post #58

As someone who has done a fair amount of OpenGL programming, I can honestly say that it's becoming a convoluted spec. It's no longer elegant or something that should be aspired to IMHO, YMMV. The principles are generally sound, just not the implementation or API. I would rather see an FPGA being used as a general purpose DSP with the ability to run shader code in software, perhaps inside a runtime written with Go or…

Or you could buy a 72 core processor: http://www.tilera.com/products/processors/TILE-Gx_Family (it's not as powerful as it sounds; memory bandwidth ends up being a major constraint, and programming all those cores effectively is hard in itself)

Ya I was excited about the Xeon Phi too:

http://www.intel.com/content/www/us/en/processors/xeon/xeon-...

I just don't know if anything from Intel will be cost-effective because it's going to be over-engineered to not compete with existing products.

For example caching is largely useless with something like Go that is sending copies of data around. I don't know if it's possible to use copy-on-write with so many cores.

It's just a hunch but I think multiprocessing in the future is going to use something like content addressable storage and not worry so much about a complex router or interconnect. Only the most naive algorithms will probably win out, so basically chop the screen up into a bunch of 16x16 squares and send them to each processor.

Also I think it will be really awesome to be free of middleware and be able to run physics or AI directly. I've even thought about trying to write something to emulate a bunch of cores on my computer so I can at least play with the algorithms until affordable hardware arrives.

Post reply on HN