Open Source 3D Hardware
An anonymous submitter writes: "Open Source haven icculus.org has updated with a new project: Manticore. Different from most Open Source projects however, Manticore is hardware. It is a 3D graphics acceleration design, coded in VHDL. Although still fairly early in development, its goals are similar to those of other 3D cores, from companies like NVIDIA and ATI. The project includes an SDRAM controller for storage, and a VGA unit for display, in addition to the 3D rendering core. It is available under the Design Science License. Source, Documentation and other information available at the Manticore Homepage."
if they ditched the VGA it would be better
simply because you would not have to add all that redundant crap into the hardware
I dont care much for VGA other people do because they are lazy or cant modify their source code (-;
(even MS will be ditching VGA for longhorn)
regards
john jones
The success of open source is that it is easy for the masses to get access to the "products". This would not be the case with an open source hardware project.
Unfortuantely, I suspect this will not be successful.
...do they have to develop a 3D accellerator that is compatible with most software (OpenGL, DirectX, etc)? It seems to me that many of the design concepts in this arena are mired up in patents by giants like nVidia and ATI. For instance, doesn't nVidia have 'rights' to per-pixel vertex shader techniques?
Why bother.
I'm sure you were just being funny, but you wouldn't normally try to burn something like this onto an ASIC (application specific integrated circuit) - you'd compile the VHDL and load it into a big hoggin' FPGA (field programmable gate array).
/. is my opinion, not my employers) use FPGAs to do a lot of signal processing.
An ASIC is a chip you have MADE in a foundary - once it's fabbed, it is no more reprogrammable than any other chip. An FPGA is a collection of omni-purpose gates that are controlled by SRAM or flash - you can reprogram it to do what you want just be hitting the reset line and loading a new image into it. At work, we (obdisclaimer - what I post on
The bad thing is that an FPGA big enough for a decent accelerator would be about a $700-$1500 part.
Now, what I can see it somebody doing enough devel on this to make a viable part, then getting it burned down to an ASIC and made avaible to the community. Yeah, that worked really well with IBM/Moto's CHIRP PowerPC boards.
But what could happen is this chip could find its way into the next generation TiVo, or some other set top box. In that market, a synthesizable core that was royalty-free would RULE.
I agree with some of the other posters, though - ditch the damn VGA compatibility layer, and just make a Linux (and *BSD) kernel console driver for it, an XFree driver, and a very basic BIOS driver for it. The BIOS driver can be stupid - just enough support to set modes, and print text. The kernel driver can take over once the system boots. Don't waste silicon making the framebuffer compatible with VGA (and thus EGA (and thus CGA)) - that design is a flat-out nightmare kludge. Go for a simple, clean, legacy-free design.
And while you are at it, make sure the DMA path is secure - make sure you can program the chip so that a vertex list entry cannot corrupt system memory. I lurk on the DRI mailing list, and the lengths to which they have to go to keep the graphics chip from being an exploit are ludicuous. It slows down the DRI drivers relative to other so-called operating systems that don't concern themselves with security.
www.eFax.com are spammers
While I'm sure this is an admirable project, I'd much rather see icculus rescue me, and remove the only reason I still have a Windows filesystem: Serious Sam. It'd be nice to get AvP, too, but Serious Sam is the one that counts for me. Yeah, I know it's a volunteer effort, but I'd love to see it deliver anyway.
"The invisible and the non-existent look very much alike." -- Delos B. McKown
What we want to do is learn how a 3D core works, and get some exposure.
The reality is I want to work for NVidia or ATI, and what better way to learn the ropes than to try it yourself.
Its not for mass consumption. So far we have a working board which can plug a monitor into it and render triangles. Further along than I thought I may ever get.
Then again maybe some already large company would like to expand their scope, and bring in what will one day be a complete core.
The reality is, its a learning experience.
Jeff Mrochuk
Manticore
Well not exactly 3d, but simputer is another hardware project which is released under the modified GPL