<div dir="ltr"><div><div>Hi,<br></div>I would like to softfloat for GSOC. Is anyone working on it?<br></div>Thank you!! :)<br></div><div class="gmail_extra"><br><div class="gmail_quote">On Tue, Mar 24, 2015 at 12:16 AM, Kenneth Graunke <span dir="ltr"><<a href="mailto:kenneth@whitecape.org" target="_blank">kenneth@whitecape.org</a>></span> wrote:<br><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex"><span class="">On Monday, March 23, 2015 05:02:51 PM Aaron Watry wrote:<br>
> On a related note,<br>
><br>
> Has anyone ported shader-db over to working on R600/RadeonSI/<anything<br>
> non-intel>? I've been meaning to take a look at the NIR->TGSI pass and see<br>
> if there's an easy way to hook it up to the radeon drivers, but I wanted to<br>
> be able to get shader-db up and running on that hardware first so that we<br>
> could get some before/after numbers (I'm assuming that R600 w/o SB will be<br>
> the main radeon driver that benefits, but I'd love to be proven wrong).<br>
><br>
> --Aaron<br>
<br>
</span>It shouldn't be hard to get working.<br>
<br>
The shader-db runner doesn't actually draw anything, so you need to<br>
precompile assembly code at glLinkProgram time, making some assumptions<br>
about the GL state that will be used. We manage to guess correctly<br>
most of the time on modern Intel hardware.<br>
<br>
Beyond that, you just need to have the driver emit a few messages via<br>
KHR_debug:<br>
<br>
static GLuint msg_id = 0;<br>
_mesa_gl_debug(ctx, &msg_id,<br>
MESA_DEBUG_SOURCE_SHADER_COMPILER,<br>
MESA_DEBUG_TYPE_OTHER,<br>
MESA_DEBUG_SEVERITY_NOTIFICATION,<br>
"%s shader: %d",<br>
type_of_shader, /* "FS", "VS" and the like */<br>
num_instructions);<br>
<br>
That should be all you need for the original shader-db which most of<br>
the Intel folks use (git://<a href="http://anongit.freedesktop.org/mesa/shader-db" target="_blank">anongit.freedesktop.org/mesa/shader-db</a>).<br>
<br>
Eric has a new reboot of the project that uses apitraces of files rather<br>
than Piglit shader_test files. The Broadcom vc4 apparently has so much<br>
non-orthagonal state that it's impractical to guess the state during a<br>
precompile, so he wanted to use the actual state from the trace.<br>
<br>
Everyone else has kept using the original version because it's *much*<br>
faster - on my Haswell, it only takes about 2-3 minutes to process<br>
~24,000 shaders from ~290 applications.<br>
<br>
I assume Radeon and Nouveau can probably guess most state correctly,<br>
so using the original shader-db would make more sense. Freedreno<br>
might have to use Eric's apitrace based solution.<br>
<br>_______________________________________________<br>
mesa-dev mailing list<br>
<a href="mailto:mesa-dev@lists.freedesktop.org">mesa-dev@lists.freedesktop.org</a><br>
<a href="http://lists.freedesktop.org/mailman/listinfo/mesa-dev" target="_blank">http://lists.freedesktop.org/mailman/listinfo/mesa-dev</a><br>
<br></blockquote></div><br><br clear="all"><br>-- <br><div class="gmail_signature"><div dir="ltr"><div><div><font style="font-family:trebuchet ms,sans-serif">Regards,<br></font></div><font style="font-family:trebuchet ms,sans-serif"><b style="background-color:rgb(255,255,255);color:rgb(0,0,153)">Aditya Atluri,<br></b></font></div><div><font style="font-family:trebuchet ms,sans-serif"><b style="background-color:rgb(255,255,255);color:rgb(0,0,153)">USA.<br></b></font></div><font style="font-family:trebuchet ms,sans-serif"><b style="background-color:rgb(255,255,255);color:rgb(0,0,153)"></b><span style="background-color:rgb(255,255,255);color:rgb(0,0,153)"></span></font><br></div></div>
</div>