<div dir="auto"><span style="font-family:sans-serif;font-size:12.8px">I have a few questions on the environment.</span><div style="font-family:sans-serif;font-size:12.8px" dir="auto"><br></div><div style="font-family:sans-serif;font-size:12.8px" dir="auto">riscv-tools repository has a version of Spike. Is the same one contained in the libre-riscv repository a fork of that one? I noticed it does have the libre-riscv repository version has a description stating it is an augmented version but I just want to be sure. </div><div style="font-family:sans-serif;font-size:12.8px" dir="auto"><br></div><div style="font-family:sans-serif;font-size:12.8px" dir="auto">What you asked me to document is the process of creating a development environment that one can use to compile and then run a sample program using the simulator correct? The instructions on the page detail vaguely how to set it up but not how to verify the installation or compile/run any programs which I am guessing is the missing documentation that needs to be done.</div><div style="font-family:sans-serif;font-size:12.8px" dir="auto"><br></div><div style="font-family:sans-serif;font-size:12.8px" dir="auto">Also are the unit tests that need work regarding the Spike simulator or another component of the project? If it is the Spike sim unit tests need work is it the tests in the riscv-tools repository or the libre-riscv repository?</div><div style="font-family:sans-serif;font-size:12.8px" dir="auto"><br></div><div style="font-family:sans-serif;font-size:12.8px" dir="auto">Thanks for your time!</div><div style="color:rgb(136,136,136);font-family:sans-serif;font-size:12.8px" dir="auto"><div><br></div><div>- Daniel</div></div></div><br><div class="gmail_quote"><div dir="ltr">On Fri, Oct 5, 2018, 10:09 PM lkcl <<a href="mailto:lkcl@libre-riscv.org">lkcl@libre-riscv.org</a>> wrote:<br></div><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">On Sat, Oct 6, 2018 at 5:49 AM Daniel Benusovich<br>
<<a href="mailto:flyingmonkeys1996@gmail.com" target="_blank" rel="noreferrer">flyingmonkeys1996@gmail.com</a>> wrote:<br>
<br>
> I am Daniel Benusovich and a newcomer to the RISC-V and Open<br>
> Source world in general and was hoping you could use some help in one way or another.<br>
<br>
much appreciated. yes!<br>
<br>
> I saw your post asking for help with development for the Vulkan<br>
> 3D GPU project and while I do not have any experience in this<br>
> area I would love to help out and get my foot in the door<br>
> contributing to RISC-V development. I have experience working<br>
> in C, C++, Java, VHDL and some assembly though I am happy<br>
> to learn any languages and tools that are used for this project specifically.<br>
<br>
that's fantastic.<br>
<br>
> Let me know what needs to be done and I will get right on it.<br>
<br>
thanks daniel.<br>
<br>
ok, so the preliminary roadmap is here:<br>
<a href="https://libre-riscv.org/3d_gpu/roadmap/" rel="noreferrer noreferrer" target="_blank">https://libre-riscv.org/3d_gpu/roadmap/</a><br>
<br>
and there are currently two parallel tracks: i'm working at the<br>
beginning of a chain of dependencies, implementing SV (a<br>
hardware-level parallelism API for RISCV, which is best described as a<br>
"hardware-level macro-expansion system" that effectively applies a<br>
for-loop to *scalar* assembly instructions) and starting with the<br>
simulator, spike:<br>
<br>
<a href="https://git.libre-riscv.org/?p=riscv-isa-sim.git;a=shortlog;h=refs/heads/sv" rel="noreferrer noreferrer" target="_blank">https://git.libre-riscv.org/?p=riscv-isa-sim.git;a=shortlog;h=refs/heads/sv</a><br>
<a href="https://git.libre-riscv.org/?p=riscv-tests.git;a=shortlog;h=refs/heads/sv" rel="noreferrer noreferrer" target="_blank">https://git.libre-riscv.org/?p=riscv-tests.git;a=shortlog;h=refs/heads/sv</a><br>
<br>
the second track is jacob's domain, he's focussing on the vulkan3d<br>
software-renderer, where, once that's done, we will be able to begin<br>
doing benchmarks, and, based on those benchmarks (following the<br>
techniques pioneered by jeff bush from the nyuzi project), actually<br>
design custom RISC-V instructions and a microarchitecture that will<br>
bring the speed up and power consumption down to match an entry-level<br>
embedded GPU such as MALI400, Vivante GC800 and so on.<br>
<br>
in terms of "numbers" that's around 5 GFLOPS, 100 MPixels/sec and i<br>
believe something like 30 MTriangles/sec which are extremely modest<br>
and perfectly reasonably achievable: the tricky bit is doing so in<br>
well under 1 Watt @ 28nm.<br>
<br>
anyway that is a long way ahead: the most immediately useful thing<br>
would be to replicate and document the build environment for spike-sv<br>
and the unit tests. this is slightly tricky as it's based on<br>
riscv-tools which is not being properly maintained. i set up a build<br>
environment over a year ago and haven't dared update it since, just in<br>
case it breaks.<br>
<br>
i started a page here:<br>
<a href="https://libre-riscv.org/3d_gpu/spike_sv/" rel="noreferrer noreferrer" target="_blank">https://libre-riscv.org/3d_gpu/spike_sv/</a><br>
<br>
the unit tests themselves also need a bit of work, as i have made some<br>
mistakes, plus more tests are also needed.<br>
<br>
lots of things: even just asking questions helps.<br>
<br>
thanks daniel,<br>
<br>
l.<br>
</blockquote></div>