1 <div class="jumbotron">
2 <h1 class="display-4">Welcome to Libre-SOC</h1>
4 <p>We're building a chip. A fast chip. A safe chip. A trusted chip.</p>
6 <p>A chip with lots of peripherals. And a VPU. And a 3D GPU...</p>
8 <p>Oh and here, have the <a href="http://git.libre-riscv.org">source code</a>...</p>
12 <h2 class="display-4">Why should I care?</h2>
14 With LibreSOC, you can take complex algorithms usually intended for power
16 hungry servers with big fat GPUs, and run them on tiny devices like smartwatches,
18 cellphones, and pocket drones without changing your code at all.
21 <h2 class="display-4">Hasn't Somebody Already Done This?</h2>
23 To the best of our knowledge, no. The closest systems would be ARM Cortex devices
25 which currently offer mediocre GPU and OpenCL support. Often times, it is quite
27 diffcult for customers to get their hands on the drivers and install them due to
29 their locked down nature. LibreSOC is providing our own Free/Libre drivers. Easy as
33 <a class="btn btn-primary btn-lg" href="https://libre-soc.org/why_a_libresoc/" role="button">Learn more</a>
39 We are proud of our talented and diverse [team](about_us).
43 * [Purism](http://puri.sm) donates to us through [NLNet](nlnet)
45 * [Raptor CS](http://raptorcs.com) has given us access to a powerful
46 18-core 128 GB RAM TALOS II workstation, online.
50 If you would like to fund us, see [[funding]]. We currently have some
51 funding and always appreciate more! If you are a Corporation or an
52 individual you can donate tax-free to NLNet, and they can in turn gift
53 our developers. Contact lkcl@lkcl.net for more information.
55 If you want to write code with us, keep reading. If you want to *learn* so that you can write code with us, see below. If there is anything else, just get in touch on the list, there is plenty to do.
58 [mailing list](http://lists.libre-riscv.org/mailman/listinfo/libre-riscv-dev),
59 introduce yourself (people will happily say "hello" back"). Read through
60 [recent posts](http://lists.libre-riscv.org/pipermail/libre-riscv-dev/)
61 and the [[charter]], and let everyone know, on the list that you're
62 happy with it and agree to it.
63 2. The next thing you should do is read through the [bugs
64 list](http://bugs.libre-riscv.org) and see if there are any bugs that
66 3. After that, go ahead and take a look at the
67 [git repositories](https://git.libre-riscv.org).
68 Try and clone a repository with
69 ``git clone https://git.libre-riscv.org/git/repositoryname.git``
70 4. If you plan to do HDL work, you should familiarize yourself with our
72 5. We do have funding available (see [[nlnet]]) upon completion of issues -
73 we are also working on procuring more funding which gets the project to
74 nanometre scale tapeout.
75 6. After all this, if you feel that Libre-SOC is a something that
76 you would like to contribute to, add yourself to the [current_members](about_us)
77 page, fill in some information about yourself, and join the mailing list
80 Also note that you can edit this wiki. You can experiment in the [[Sandbox]].
84 The whole purpose of this project is to be a learning environment as well as an actual business. If you want to learn how to do ASIC design, with a view to contributing or starting your own ASIC business, start here: [[3d_gpu/tutorial]]. Yes, really: do not let anyone tell you that you can't learn this stuff too.
86 Along the way, if you find any [[resources]] or links that you found particularly helpful, please add them to that page so that other people can also benefit (and you have a place to remember them, too).
90 Most labor is currently being applied to developing the GPU portion of
93 The highest priority needed at the moment is a c++ engineer to work on
94 a MESA 3D driver. This will begin life similar to SwiftShader however
95 retaining the vectorisation and predication intrinsics as well as hardware
96 accelerated opcodes (all of which SwiftShader lacks)
98 Medium to long-term we need HDL engineers. Particularly those familiar
99 with nMigen or just python. Most of the techniques being used require
100 software engineering skills (OO design, polymorphism) than they do more
101 traditional HDL programming skills. Basically if you have experience in 2
102 of the following you'll do fine: python, nmigen, verilog/VHDL/gate-level
103 design. See [[HDL_workflow]]
105 Also, individuals with experience in formal mathematical verification