index.mdwn

   1 # Welcome to Libre-SOC
   2 (formerly Libre-RISCV)
   3
   4 > We're building a chip. A fast chip. A safe chip. A trusted chip.
   5
   6 > A chip with lots of peripherals. And a VPU.  And a 3D GPU...
   7
   8 > Oh and here, have the [source code](http://git.libre-riscv.org)...
   9
  10 ## Tell Me More...
  11
  12 With LibreSOC, you can take complex algorithms usually intended for power
  13
  14 hungry servers with big fat GPUs, and run them on tiny devices like smartwatches,
  15
  16 cellphones, and pocket drones without changing your code at all.
  17
  18 ## Hasn't Somebody Already This?
  19
  20 To the best of our knowledge, no. The closest systems would be ARM Cortex devices
  21
  22 which currently offer mediocre GPU and OpenCL support. Often times, it is quite
  23
  24 diffcult for customers to get their hands on the drivers and install them due to
  25
  26 their locked down nature. LibreSOC is providing our own Free/Libre drivers. Easy as
  27 1, 2, 3!
  28
  29 Sounds cool? Learn more about the [why](why_a_libresoc) behind Libre-SOC
  30 and [our mission](The_Mission).
  31
  32 # Our Team
  33
  34 We are proud of our talented and diverse [team](about_us).
  35
  36 # Our sponsors
  37
  38 * [Purism](http://puri.sm) donates to us through [NLNet](nlnet)
  39   charitable gifting
  40 * [Raptor CS](http://raptorcs.com) has given us access to a powerful
  41   18-core 128 GB RAM TALOS II workstation, online.
  42
  43 # How Can I Help?
  44
  45 If you would like to fund us, see [[funding]]. We currently have some
  46 funding and always appreciate more!  If you are a Corporation or an
  47 individual you can donate tax-free to NLNet, and they can in turn gift
  48 our developers.  Contact lkcl@lkcl.net for more information.
  49
  50 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.
  51
  52 1. First, join the
  53 [mailing list](http://lists.libre-riscv.org/mailman/listinfo/libre-riscv-dev),
  54 introduce yourself (people will happily say "hello" back"). Read through
  55 [recent posts](http://lists.libre-riscv.org/pipermail/libre-riscv-dev/)
  56 and the [[charter]], and let everyone know, on the list that you're
  57 happy with it and agree to it.
  58 2. The next thing you should do is read through the [bugs
  59 list](http://bugs.libre-riscv.org) and see if there are any bugs that
  60 pique your interest.
  61 3. After that, go ahead and take a look at the
  62    [git repositories](https://git.libre-riscv.org).
  63 Try and clone a repository with
  64 ``git clone https://git.libre-riscv.org/git/repositoryname.git``
  65 4. If you plan to do HDL work, you should familiarize yourself with our
  66    [[HDL_workflow]].
  67 5. We do have funding available (see [[nlnet]]) upon completion of issues -
  68 we are also working on procuring more funding which gets the project to
  69 nanometre scale tapeout.
  70 6. After all this, if you feel that Libre-SOC is a something that
  71 you would like to contribute to, add yourself to the [current_members](about_us)
  72 page, fill in some information about yourself, and join the mailing list
  73 and say hello.
  74
  75 Also note that you can edit this wiki.  You can experiment in the [[Sandbox]].
  76
  77 ## How can I learn?
  78
  79 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.
  80
  81 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).
  82
  83 ## Needed Skills
  84
  85 Most labor is currently being applied to developing the GPU portion of
  86 the Libre-SOC.
  87
  88 The highest priority needed at the moment is a c++ engineer to work on
  89 a MESA 3D driver. This will begin life similar to SwiftShader however
  90 retaining the vectorisation and predication intrinsics as well as hardware
  91 accelerated opcodes (all of which SwiftShader lacks)
  92
  93 Medium to long-term we need HDL engineers. Particularly those familiar
  94 with nMigen or just python.  Most of the techniques being used require
  95 software engineering skills (OO design, polymorphism) than they do more
  96 traditional HDL programming skills. Basically if you have experience in 2
  97 of the following you'll do fine: python, nmigen, verilog/VHDL/gate-level
  98 design. See [[HDL_workflow]]
  99
 100 Also, individuals with experience in formal mathematical verification
 101 are quite welcome.
 102