<html>
<head>
<meta content="text/html; charset=UTF-8" http-equiv="Content-Type">
</head>
<body bgcolor="#FFFFFF" text="#000000">
I was hoping you would come to the collaborative, joint solution.
I've been waiting for Clang to have a settled OpenCL implementation
to start working on OpenCL.<br>
<br>
Dealing with 3 parallel projects would be just that, a pain in the
rear.<br>
<br>
- Marc<br>
<br>
On 10/20/2011 03:45 AM, Ralf Karrenberg wrote:
<blockquote cite="mid:4E9FFBBB.6020804@gmx.de" type="cite">
<pre wrap="">Hi Carlos,
On 10/20/11 9:54 AM, Carlos Sánchez de La Lama wrote:
</pre>
<blockquote type="cite">
<blockquote type="cite">
<pre wrap="">The project started as a use-case for our "Whole-Function Vectorization"
library, which allows to transform a function to compute the same as W
executions of the original code by using SIMD instructions (W = 4 for
SSE/AltiVec, 8 for AVX).
</pre>
</blockquote>
<pre wrap="">
Quite interesting. We were planning to add "vectorization" to our passes
also, but if I understood the paper correctly your approach uses full
speculation, which is all right for SIMD architectures but might not be
so for multi-issue processors.
</pre>
</blockquote>
<pre wrap="">
I don't know what you mean with "speculation" here, but other than that
you are right: for best performance, we explicitly target machines with
SIMD instruction sets.
</pre>
<blockquote type="cite">
<blockquote type="cite">
<pre wrap="">In contrast to Clover and pocl, we aimed at maximum performance before
full support of the API (which simply requires more manpower than one
PhD student).
</pre>
</blockquote>
<pre wrap="">
That is wrong, at least for pocl. We do not (by far) support the whole
API, the main new point on pocl is the LLVM passes to statically create
the different work items in a workgroup, and the barrier handling. Our
kernel runtime library is currently in fact fairly small, including just
a little more then the implementation-dependent functions. We are
considering merging efforts with liblcl in that point.
</pre>
</blockquote>
<pre wrap="">
Please excuse me for getting that wrong.
I think we should really stick our heads together (also including Denis
Steckelmacher who implemented Clover) and somehow combine all our efforts.
Otherwise, we will probably just all solve the same problems in
parallel. Additionally, no user will gain anything if he has to decide
between multiple, half-baked solutions.
Best,
Ralf
</pre>
<blockquote type="cite">
<blockquote type="cite">
<pre wrap="">Am 19.10.2011 17:38, schrieb Hal Finkel:
</pre>
<blockquote type="cite">
<pre wrap="">Do we have a list of these open-source LLVM-based OpenCL projects
somewhere? Off the top of my head, we have:
libclc: <a class="moz-txt-link-freetext" href="http://www.pcc.me.uk/~peter/libclc/">http://www.pcc.me.uk/~peter/libclc/</a>
pocl: <a class="moz-txt-link-freetext" href="https://launchpad.net/pocl">https://launchpad.net/pocl</a>
clover: <a class="moz-txt-link-freetext" href="http://cgit.freedesktop.org/~steckdenis/clover/">http://cgit.freedesktop.org/~steckdenis/clover/</a>
(I think that all of these have BSD- or MIT-style licenses).
Are there any others?
-Hal
On Wed, 2011-10-19 at 14:47 +0100, Peter Collingbourne wrote:
</pre>
<blockquote type="cite">
<pre wrap="">Hi,
This is to announce the availability of libclc, an open source, BSD
licensed implementation of the library requirements of the OpenCL C
programming language, as specified by the OpenCL 1.1 Specification.
libclc is intended to be used with Clang's OpenCL frontend.
libclc website: <a class="moz-txt-link-freetext" href="http://www.pcc.me.uk/~peter/libclc/">http://www.pcc.me.uk/~peter/libclc/</a>
libclc is designed to be portable and extensible. To this end,
it provides generic implementations of most library requirements,
allowing the target to override the generic implementation at the
granularity of individual functions.
libclc currently only supports the PTX target, but support for more
targets is welcome.
How does this project relate to the recently announced Portable OpenCL
(POCL) project? Unlike POCL, this project is not intended to provide
an OpenCL host library (i.e. the OpenCL Platform Layer and OpenCL
Runtime specified in sections 4-5 of the OpenCL specification).
Instead, it provides only the requirements for the OpenCL C
Programming Language (section 6 et seq). It is intended to be used
with an existing host library implementation, and comply with its
ABI requirements.
An example of such a host library is NVIDIA's OpenCL host library
for PTX -- the intention is to at some point provide a mechanism
for using the NVIDIA implementation of OpenCL with Clang, libclc
and LLVM's PTX backend instead of NVIDIA's own OpenCL compiler.
Another example would be POCL's host library, and the POCL developers
have expressed an interest in using libclc as their OpenCL C library
instead of developing their own.
I will hope to find time over the next few weeks to add libclc support
to the Clang driver. The intention is that compiling OpenCL C programs
to PTX would be as easy as (something like this):
clang -target ptx32 -S file.cl
such that the driver would automatically locate the libclc headers,
add them to the include path and pre-include the main header file.
(The libclc support will of course be optional, and a -cl-stdlib=
flag will be provided to allow for switching between OpenCL standard
library implementations.)
Thanks,
</pre>
</blockquote>
<pre wrap="">
</pre>
</blockquote>
<pre wrap="">_______________________________________________
LLVM Developers mailing list
<a class="moz-txt-link-abbreviated" href="mailto:LLVMdev@cs.uiuc.edu">LLVMdev@cs.uiuc.edu</a> <a class="moz-txt-link-rfc2396E" href="mailto:LLVMdev@cs.uiuc.edu"><mailto:LLVMdev@cs.uiuc.edu></a> <a class="moz-txt-link-freetext" href="http://llvm.cs.uiuc.edu">http://llvm.cs.uiuc.edu</a>
<a class="moz-txt-link-freetext" href="http://lists.cs.uiuc.edu/mailman/listinfo/llvmdev">http://lists.cs.uiuc.edu/mailman/listinfo/llvmdev</a>
</pre>
</blockquote>
<pre wrap="">
</pre>
</blockquote>
<pre wrap="">_______________________________________________
LLVM Developers mailing list
<a class="moz-txt-link-abbreviated" href="mailto:LLVMdev@cs.uiuc.edu">LLVMdev@cs.uiuc.edu</a> <a class="moz-txt-link-freetext" href="http://llvm.cs.uiuc.edu">http://llvm.cs.uiuc.edu</a>
<a class="moz-txt-link-freetext" href="http://lists.cs.uiuc.edu/mailman/listinfo/llvmdev">http://lists.cs.uiuc.edu/mailman/listinfo/llvmdev</a>
</pre>
</blockquote>
<br>
<div class="moz-signature">-- <br>
Marc J. Driftmeyer<br>
Email :: <a href="mailto:mjd@reanimality.com">mjd@reanimality.com</a><br>
Web :: <a href="http://www.reanimality.com">http://www.reanimality.com</a><br>
Cell :: (509) 435-5212
</div>
</body>
</html>