<html>
<head>
<meta http-equiv="Content-Type" content="text/html; charset=utf-8">
</head>
<body text="#000000" bgcolor="#FFFFFF">
<br>
<blockquote type="cite"
cite="mid:CAM+GqJaa6MANawyxv7+ScJZe0pOZAa6-eiBkcTz+4=CW51mDFQ@mail.gmail.com">
<div dir="ltr">
<div class="gmail_extra">
<div class="gmail_quote">
<div>I'd suggest that you check out the
recently-open-sourced OpenCL conformance test suite [0] or
my slightly-more-linux-build-friendly fork [1] and give it
a run on top of mesa/clover. It'll give you a good list of
things to work on.<br>
</div>
</div>
</div>
</div>
</blockquote>
Thanks, I took a quick look. Yeah, shame they didn't put in a proper
build system or provide a doc stating what the tests are or a main
app that runs them all in a correct order and outputs a report.<br>
<br>
<blockquote type="cite"
cite="mid:CAM+GqJaa6MANawyxv7+ScJZe0pOZAa6-eiBkcTz+4=CW51mDFQ@mail.gmail.com">
<div dir="ltr">
<div class="gmail_extra">
<div class="gmail_quote">
<div><br>
</div>
<div>I ran the integer_ops sub-tests last night, and besides
the missing CL 1.2 popcount() function, that entire
sub-suite succeeds. Feel free to attempt to implement that
built-in function in the libclc[2] library to get your
feet wet.<br>
<br>
</div>
</div>
</div>
</div>
</blockquote>
<blockquote type="cite"
cite="mid:CAM+GqJaa6MANawyxv7+ScJZe0pOZAa6-eiBkcTz+4=CW51mDFQ@mail.gmail.com">
<div dir="ltr">
<div class="gmail_extra">
<div class="gmail_quote">
<div>There are also issues with buffer copies (using
host-pointers, copySubRect), and there are a subset of the
floating-point math built-ins which are either missing or
fail some test scenarios. Some atomic operations seem to
be incorrect, and that's about as far as I've managed to
get so far in looking at the results. I'm sure plenty of
other things need work/polish. Note that many of these
things are gpu-independent and can be implemented either
in the clover state-tracker, or in the generic
(non-GPU-specific) portion of libclc.<br>
<br>
</div>
<div>I've been looking into implementing the
clCreateCommandQueueWithProperties API function as well,
since there seem to be a bunch of CL programs that just
blindly assume the API function exists for all platforms
when using the ocl-icd loader, and segfault as a result.<br>
<br>
</div>
<div>One big missing piece is image support. It's an
optional feature of OpenCL, but there are a good number of
programs used by a certain benchmarking site that depend
on it.<br>
</div>
<br>
</div>
</div>
</div>
</blockquote>
Phoronix?<br>
<br>
Yeah, it's on the todo list to see if I can get anywhere with it. My
immediate aim is to get Blender cycles with opensubdiv working, so
that's gonna need a lot of work with images.<br>
<br>
Thanks,<br>
Luke.<br>
<br>
</body>
</html>