boost/libs/compute/doc/html/boost_compute/faq.html
2021-10-05 21:37:46 +02:00

284 lines
17 KiB
HTML
Raw Permalink Blame History

This file contains invisible Unicode characters

This file contains invisible Unicode characters that are indistinguishable to humans but may be processed differently by a computer. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

<html>
<head>
<meta http-equiv="Content-Type" content="text/html; charset=UTF-8">
<title>Frequently Asked Questions</title>
<link rel="stylesheet" href="../../../../../doc/src/boostbook.css" type="text/css">
<meta name="generator" content="DocBook XSL Stylesheets V1.79.1">
<link rel="home" href="../index.html" title="Chapter 1. Boost.Compute">
<link rel="up" href="../index.html" title="Chapter 1. Boost.Compute">
<link rel="prev" href="performance.html" title="Performance">
</head>
<body bgcolor="white" text="black" link="#0000FF" vlink="#840084" alink="#0000FF">
<table cellpadding="2" width="100%"><tr>
<td valign="top"><img alt="Boost C++ Libraries" width="277" height="86" src="../../../../../boost.png"></td>
<td align="center"><a href="../../../../../index.html">Home</a></td>
<td align="center"><a href="../../../../../libs/libraries.htm">Libraries</a></td>
<td align="center"><a href="http://www.boost.org/users/people.html">People</a></td>
<td align="center"><a href="http://www.boost.org/users/faq.html">FAQ</a></td>
<td align="center"><a href="../../../../../more/index.htm">More</a></td>
</tr></table>
<hr>
<div class="spirit-nav">
<a accesskey="p" href="performance.html"><img src="../../../../../doc/src/images/prev.png" alt="Prev"></a><a accesskey="u" href="../index.html"><img src="../../../../../doc/src/images/up.png" alt="Up"></a><a accesskey="h" href="../index.html"><img src="../../../../../doc/src/images/home.png" alt="Home"></a>
</div>
<div class="section">
<div class="titlepage"><div><div><h2 class="title" style="clear: both">
<a name="boost_compute.faq"></a><a class="link" href="faq.html" title="Frequently Asked Questions">Frequently Asked Questions</a>
</h2></div></div></div>
<h4>
<a name="boost_compute.faq.h0"></a>
<span class="phrase"><a name="boost_compute.faq.how_do_i_report_a_bug__issue__or_feature_request_"></a></span><a class="link" href="faq.html#boost_compute.faq.how_do_i_report_a_bug__issue__or_feature_request_">How
do I report a bug, issue, or feature request?</a>
</h4>
<p>
Please submit an issue on the GitHub issue tracker at <a href="https://github.com/boostorg/compute/issues" target="_top">https://github.com/boostorg/compute/issues</a>.
</p>
<h4>
<a name="boost_compute.faq.h1"></a>
<span class="phrase"><a name="boost_compute.faq.where_can_i_find_more_documentation_"></a></span><a class="link" href="faq.html#boost_compute.faq.where_can_i_find_more_documentation_">Where can
I find more documentation?</a>
</h4>
<div class="itemizedlist"><ul class="itemizedlist" style="list-style-type: disc; ">
<li class="listitem">
The main documentation is here: <a href="http://boostorg.github.io/compute/" target="_top">http://boostorg.github.io/compute/</a>
</li>
<li class="listitem">
The README is here: <a href="https://github.com/boostorg/compute/blob/master/README.md" target="_top">https://github.com/boostorg/compute/blob/master/README.md</a>
</li>
<li class="listitem">
The wiki is here: <a href="https://github.com/boostorg/compute/wiki" target="_top">https://github.com/boostorg/compute/wiki</a>
</li>
<li class="listitem">
The contributor guide is here: <a href="https://github.com/boostorg/compute/blob/master/CONTRIBUTING.md" target="_top">https://github.com/boostorg/compute/blob/master/CONTRIBUTING.md</a>
</li>
<li class="listitem">
The reference is here: <a href="http://boostorg.github.io/compute/compute/reference.html" target="_top">http://boostorg.github.io/compute/compute/reference.html</a>
</li>
</ul></div>
<h4>
<a name="boost_compute.faq.h2"></a>
<span class="phrase"><a name="boost_compute.faq.where_is_the_best_place_to_ask_questions_about_the_library_"></a></span><a class="link" href="faq.html#boost_compute.faq.where_is_the_best_place_to_ask_questions_about_the_library_">Where
is the best place to ask questions about the library?</a>
</h4>
<p>
The mailing list at <a href="https://groups.google.com/forum/#!forum/boost-compute" target="_top">https://groups.google.com/forum/#!forum/boost-compute</a>.
</p>
<h4>
<a name="boost_compute.faq.h3"></a>
<span class="phrase"><a name="boost_compute.faq.what_compute_devices__e_g__gpus__are_supported_"></a></span><a class="link" href="faq.html#boost_compute.faq.what_compute_devices__e_g__gpus__are_supported_">What
compute devices (e.g. GPUs) are supported?</a>
</h4>
<p>
Any device which implements the OpenCL standard is supported. This includes
GPUs from NVIDIA, AMD, and Intel as well as CPUs from AMD and Intel and other
accelerator cards such as the Xeon Phi.
</p>
<h4>
<a name="boost_compute.faq.h4"></a>
<span class="phrase"><a name="boost_compute.faq.can_you_compare_boost_compute_to_other_gpgpu_libraries_such_as_thrust__bolt_and_vexcl_"></a></span><a class="link" href="faq.html#boost_compute.faq.can_you_compare_boost_compute_to_other_gpgpu_libraries_such_as_thrust__bolt_and_vexcl_">Can
you compare Boost.Compute to other GPGPU libraries such as Thrust, Bolt and
VexCL?</a>
</h4>
<p>
Thrust implements a C++ STL-like API for GPUs and CPUs. It is built with multiple
backends. NVIDIA GPUs use the CUDA backend and multi-core CPUs can use the
Intel TBB or OpenMP backends. However, thrust will not work with AMD graphics
cards or other lesser-known accelerators. I feel Boost.Compute is superior
in that it uses the vendor-neutral OpenCL library to achieve portability across
all types of compute devices.
</p>
<p>
Bolt is an AMD specific C++ wrapper around the OpenCL API which extends the
C99-based OpenCL language to support C++ features (most notably templates).
It is similar to NVIDIA's Thrust library and shares the same failure, lack
of portability.
</p>
<p>
VexCL is an expression-template based linear-algebra library for OpenCL. The
aims and scope are a bit different from the Boost Compute library. VexCL is
closer in nature to the Eigen library while Boost.Compute is closer to the
C++ standard library. I don't feel that Boost.Compute really fills the same
role as VexCL. In fact, the recent versions of VexCL allow to use Boost.Compute
as one of the backends, which makes the interaction between the two libraries
a breeze.
</p>
<p>
Also see this StackOverflow question: <a href="http://stackoverflow.com/questions/20154179/differences-between-vexcl-thrust-and-boost-compute" target="_top">http://stackoverflow.com/questions/20154179/differences-between-vexcl-thrust-and-boost-compute</a>
</p>
<h4>
<a name="boost_compute.faq.h5"></a>
<span class="phrase"><a name="boost_compute.faq.why_not_write_just_write_a_new_opencl_back_end_for_thrust_"></a></span><a class="link" href="faq.html#boost_compute.faq.why_not_write_just_write_a_new_opencl_back_end_for_thrust_">Why
not write just write a new OpenCL back-end for Thrust?</a>
</h4>
<p>
It would not be possible to provide the same API that Thrust expects for OpenCL.
The fundamental reason is that functions/functors passed to Thrust algorithms
are actual compiled C++ functions whereas for Boost.Compute these form expression
objects which are then translated into C99 code which is then compiled for
OpenCL.
</p>
<h4>
<a name="boost_compute.faq.h6"></a>
<span class="phrase"><a name="boost_compute.faq.why_not_target_cuda_and_or_support_multiple_back_ends_"></a></span><a class="link" href="faq.html#boost_compute.faq.why_not_target_cuda_and_or_support_multiple_back_ends_">Why
not target CUDA and/or support multiple back-ends?</a>
</h4>
<p>
CUDA and OpenCL are two very different technologies. OpenCL works by compiling
C99 code at run-time to generate kernel objects which can then be executed
on the GPU. CUDA, on the other hand, works by compiling its kernels using a
special compiler (nvcc) which then produces binaries which can executed on
the GPU.
</p>
<p>
OpenCL already has multiple implementations which allow it to be used on a
variety of platforms (e.g. NVIDIA GPUs, Intel CPUs, etc.). I feel that adding
another abstraction level within Boost.Compute would only complicate and bloat
the library.
</p>
<h4>
<a name="boost_compute.faq.h7"></a>
<span class="phrase"><a name="boost_compute.faq.is_it_possible_to_use_ordinary_c___functions_functors_or_c__11__lambdas_with_boost_compute_"></a></span><a class="link" href="faq.html#boost_compute.faq.is_it_possible_to_use_ordinary_c___functions_functors_or_c__11__lambdas_with_boost_compute_">Is
it possible to use ordinary C++ functions/functors or C++11 lambdas with Boost.Compute?</a>
</h4>
<p>
Unfortunately no. OpenCL relies on having C99 source code available at run-time
in order to execute code on the GPU. Thus compiled C++ functions or C++11 lambdas
cannot simply be passed to the OpenCL environment to be executed on the GPU.
</p>
<p>
This is the reason why I wrote the Boost.Compute lambda library. Basically
it takes C++ lambda expressions (e.g. _1 * sqrt(_1) + 4) and transforms them
into C99 source code fragments (e.g. “input[i] * sqrt(input[i]) + 4)”)
which are then passed to the Boost.Compute STL-style algorithms for execution.
While not perfect, it allows the user to write code closer to C++ that still
can be executed through OpenCL.
</p>
<p>
Also check out the BOOST_COMPUTE_FUNCTION() macro which allows OpenCL functions
to be defined inline with C++ code. An example can be found in the monte_carlo
example code.
</p>
<h4>
<a name="boost_compute.faq.h8"></a>
<span class="phrase"><a name="boost_compute.faq.what_is_the_command_queue_argument_that_appears_in_all_of_the_algorithms_"></a></span><a class="link" href="faq.html#boost_compute.faq.what_is_the_command_queue_argument_that_appears_in_all_of_the_algorithms_">What
is the command_queue argument that appears in all of the algorithms?</a>
</h4>
<p>
Command queues specify the context and device for the algorithm's execution.
For all of the standard algorithms the command_queue parameter is optional.
If not provided, a default command_queue will be created for the default GPU
device and the algorithm will be executed there.
</p>
<h4>
<a name="boost_compute.faq.h9"></a>
<span class="phrase"><a name="boost_compute.faq.how_can_i_print_out_the_contents_of_a_buffer_vector_on_the_gpu_"></a></span><a class="link" href="faq.html#boost_compute.faq.how_can_i_print_out_the_contents_of_a_buffer_vector_on_the_gpu_">How
can I print out the contents of a buffer/vector on the GPU?</a>
</h4>
<p>
This can be accompilshed easily using the generic boost::compute::copy() algorithm
along with std::ostream_iterator&lt;T&gt;. For example:
</p>
<p>
</p>
<pre class="programlisting"><span class="identifier">std</span><span class="special">::</span><span class="identifier">cout</span> <span class="special">&lt;&lt;</span> <span class="string">"vector: [ "</span><span class="special">;</span>
<span class="identifier">boost</span><span class="special">::</span><span class="identifier">compute</span><span class="special">::</span><span class="identifier">copy</span><span class="special">(</span>
<span class="identifier">vector</span><span class="special">.</span><span class="identifier">begin</span><span class="special">(),</span> <span class="identifier">vector</span><span class="special">.</span><span class="identifier">end</span><span class="special">(),</span>
<span class="identifier">std</span><span class="special">::</span><span class="identifier">ostream_iterator</span><span class="special">&lt;</span><span class="keyword">int</span><span class="special">&gt;(</span><span class="identifier">std</span><span class="special">::</span><span class="identifier">cout</span><span class="special">,</span> <span class="string">", "</span><span class="special">),</span>
<span class="identifier">queue</span>
<span class="special">);</span>
<span class="identifier">std</span><span class="special">::</span><span class="identifier">cout</span> <span class="special">&lt;&lt;</span> <span class="string">"]"</span> <span class="special">&lt;&lt;</span> <span class="identifier">std</span><span class="special">::</span><span class="identifier">endl</span><span class="special">;</span>
</pre>
<p>
</p>
<h4>
<a name="boost_compute.faq.h10"></a>
<span class="phrase"><a name="boost_compute.faq.does_boost_compute_support_zero_copy_memory_"></a></span><a class="link" href="faq.html#boost_compute.faq.does_boost_compute_support_zero_copy_memory_">Does
Boost.Compute support zero-copy memory?</a>
</h4>
<p>
Zero-copy memory allows OpenCL kernels to directly operate on regions of host
memory (if supported by the platform).
</p>
<p>
Boost.Compute supports zero-copy memory in multiple ways. The low-level interface
is provided by allocating <code class="computeroutput">buffer</code>
objects with the <code class="computeroutput"><span class="identifier">CL_MEM_USE_HOST_PTR</span></code>
flag. The high-level interface is provided by the <code class="computeroutput"><a class="link" href="../boost/compute/mapped_view.html" title="Class template mapped_view">mapped_view&lt;T&gt;</a></code>
class which provides a std::vector-like interface to a region of host-memory
and can be used directly with all of the Boost.Compute algorithms.
</p>
<h4>
<a name="boost_compute.faq.h11"></a>
<span class="phrase"><a name="boost_compute.faq.is_boost_compute_thread_safe_"></a></span><a class="link" href="faq.html#boost_compute.faq.is_boost_compute_thread_safe_">Is
Boost.Compute thread-safe?</a>
</h4>
<p>
The low-level Boost.Compute APIs offer the same thread-safety guarantees as
the underyling OpenCL library implementation. However, the high-level APIs
make use of a few global static objects for features such as automatic program
caching which makes them not thread-safe by default.
</p>
<p>
To compile Boost.Compute in thread-safe mode define <code class="computeroutput"><span class="identifier">BOOST_COMPUTE_THREAD_SAFE</span></code>
before including any of the Boost.Compute headers. By default this will require
linking your application/library with the Boost.Thread library.
</p>
<h4>
<a name="boost_compute.faq.h12"></a>
<span class="phrase"><a name="boost_compute.faq.what_applications_libraries_use_boost_compute_"></a></span><a class="link" href="faq.html#boost_compute.faq.what_applications_libraries_use_boost_compute_">What
applications/libraries use Boost.Compute?</a>
</h4>
<p>
Boost.Compute is used by a number of open-source libraries and applications
including:
</p>
<div class="itemizedlist"><ul class="itemizedlist" style="list-style-type: disc; ">
<li class="listitem">
ArrayFire (<a href="http://arrayfire.com" target="_top">http://arrayfire.com</a>)
</li>
<li class="listitem">
Ceemple (<a href="http://www.ceemple.com" target="_top">http://www.ceemple.com</a>)
</li>
<li class="listitem">
Odeint (<a href="http://headmyshoulder.github.io/odeint-v2" target="_top">http://headmyshoulder.github.io/odeint-v2</a>)
</li>
<li class="listitem">
VexCL (<a href="https://github.com/ddemidov/vexcl" target="_top">https://github.com/ddemidov/vexcl</a>)
</li>
</ul></div>
<p>
If you use Boost.Compute in your project and would like it to be listed here
please send an email to Kyle Lutz (kyle.r.lutz@gmail.com).
</p>
<h4>
<a name="boost_compute.faq.h13"></a>
<span class="phrase"><a name="boost_compute.faq.how_can_i_contribute_"></a></span><a class="link" href="faq.html#boost_compute.faq.how_can_i_contribute_">How
can I contribute?</a>
</h4>
<p>
We are actively seeking additional C++ developers with experience in GPGPU
and parallel-computing.
</p>
<p>
Please send an email to Kyle Lutz (kyle.r.lutz@gmail.com) for more information.
</p>
<p>
Also see the <a href="https://github.com/boostorg/compute/blob/master/CONTRIBUTING.md" target="_top">contributor
guide</a> and check out the list of issues at: <a href="https://github.com/boostorg/compute/issues" target="_top">https://github.com/boostorg/compute/issues</a>.
</p>
</div>
<table xmlns:rev="http://www.cs.rpi.edu/~gregod/boost/tools/doc/revision" width="100%"><tr>
<td align="left"></td>
<td align="right"><div class="copyright-footer">Copyright © 2013, 2014 Kyle Lutz<p>
Distributed under the Boost Software License, Version 1.0. (See accompanying
file LICENSE_1_0.txt or copy at <a href="http://www.boost.org/LICENSE_1_0.txt" target="_top">http://www.boost.org/LICENSE_1_0.txt</a>)
</p>
</div></td>
</tr></table>
<hr>
<div class="spirit-nav">
<a accesskey="p" href="performance.html"><img src="../../../../../doc/src/images/prev.png" alt="Prev"></a><a accesskey="u" href="../index.html"><img src="../../../../../doc/src/images/up.png" alt="Up"></a><a accesskey="h" href="../index.html"><img src="../../../../../doc/src/images/home.png" alt="Home"></a>
</div>
</body>
</html>