Commit bd85d8db authored by THIBAULT Samuel's avatar THIBAULT Samuel
Browse files

Restore some changes

parent 979e95c5
Pipeline #152266 passed with stages
in 1 minute and 6 seconds
......@@ -74,7 +74,7 @@ connections.</p>
<h4>StarPU</h4>
<p>The StarPU source code can be downloaded from
<a href="/files">the StarPU website</a>, make sure to get
<a href="https://starpu.gitlabpages.inria.fr/">the StarPU website</a>, make sure to get
the latest release, that is 0.9.1. The build process is using the usual GNU style:</p>
<tt><pre>
......
......@@ -73,7 +73,7 @@ connections.</p>
<h4>StarPU</h4>
<p>The StarPU source code can be downloaded from
<a href="/files">the StarPU website</a>, make sure to get
<a href="https://starpu.gitlabpages.inria.fr/">the StarPU website</a>, make sure to get
the latest release, that is 0.9.1. The build process is using the usual GNU style:</p>
<tt><pre>
......
......@@ -75,7 +75,7 @@ connections.</p>
<h4>StarPU</h4>
<p>The StarPU source code can be downloaded from
<a href="/files">the StarPU website</a>, make sure to get
<a href="https://starpu.gitlabpages.inria.fr/">the StarPU website</a>, make sure to get
the latest release, that is 1.1.0rc1. The build process is using the usual GNU style:</p>
<tt><pre>
......
......@@ -249,7 +249,7 @@ STARPU_NCPUS=0 STARPU_NCUDA=0 vector_scal_task_insert
You can set the environment variable STARPU_WORKER_STATS to 1 when
running your application to see the number of tasks executed by each
device. You can see the whole list of environment
variables <a href="http://runtime.bordeaux.inria.fr/StarPU/doc/html/ExecutionConfigurationThroughEnvironmentVariables.html">here</a>.
variables <a href="/files/doc/html/ExecutionConfigurationThroughEnvironmentVariables.html">here</a>.
</p>
<tt><pre>
......@@ -419,9 +419,9 @@ have been easily ported to StarPU by simply using <tt>starpu_insert_task</tt>.
<p>
Take the vector example again, and add partitioning support to it, using the
matrix-matrix multiplication as an example. Here we will use the
<a href="http://runtime.bordeaux.inria.fr/StarPU/doc/html/group__API__Data__Partition.html#ga212189d3b83dfa4e225609b5f2bf8461"><tt>starpu_vector_filter_block()</tt></a> filter function. You can see the list of
<a href="/files/doc/html/group__API__Data__Partition.html#ga212189d3b83dfa4e225609b5f2bf8461"><tt>starpu_vector_filter_block()</tt></a> filter function. You can see the list of
predefined filters provided by
StarPU <a href="http://runtime.bordeaux.inria.fr/StarPU/doc/html/starpu__data__filters_8h.html">here</a>.
StarPU <a href="/files/doc/html/starpu__data__filters_8h.html">here</a>.
Try to run it with various numbers of tasks.
</p>
</div>
......@@ -433,7 +433,7 @@ Try to run it with various numbers of tasks.
<p>
This is based on StarPU's documentation
<a href="http://runtime.bordeaux.inria.fr/StarPU/doc/html/HowToOptimizePerformanceWithStarPU.html">optimization
<a href="/files/doc/html/HowToOptimizePerformanceWithStarPU.html">optimization
chapter</a>
</p>
......@@ -443,14 +443,14 @@ This is based on StarPU's documentation
<p>
We have explained how StarPU can overlap computation and data transfers
thanks to DMAs. This is however only possible when CUDA has control over the
application buffers. The application should thus use <a href="http://runtime.bordeaux.inria.fr/StarPU/doc/html/group__API__Standard__Memory__Library.html#ga49603eaea3b05e8ced9ba1bd873070c3"><tt>starpu_malloc()</tt></a>
application buffers. The application should thus use <a href="/files/doc/html/group__API__Standard__Memory__Library.html#ga49603eaea3b05e8ced9ba1bd873070c3"><tt>starpu_malloc()</tt></a>
when allocating its buffer, to permit asynchronous DMAs from and to
it.
</p>
<p>
Take the vector example again, and fix the allocation, to make it use
<a href="http://runtime.bordeaux.inria.fr/StarPU/doc/html/group__API__Standard__Memory__Library.html#ga49603eaea3b05e8ced9ba1bd873070c3"><tt>starpu_malloc()</tt></a>.
<a href="/files/doc/html/group__API__Standard__Memory__Library.html#ga49603eaea3b05e8ced9ba1bd873070c3"><tt>starpu_malloc()</tt></a>.
</p>
</div>
......@@ -648,7 +648,7 @@ For any questions regarding StarPU, please contact the StarPU developers mailing
<h2>More Performance Optimizations</h2>
<p>
The StarPU
documentation <a href="http://runtime.bordeaux.inria.fr/StarPU/doc/html/PerformanceFeedback.html">performance
documentation <a href="/files/doc/html/PerformanceFeedback.html">performance
feedback chapter</a> provides more optimization tips for further
reading after this tutorial.
</p>
......
......@@ -287,7 +287,7 @@ STARPU_NCPUS=0 STARPU_NCUDA=0 vector_scal_task_insert
You can set the environment variable STARPU_WORKER_STATS to 1 when
running your application to see the number of tasks executed by each
device. You can see the whole list of environment
variables <a href="http://runtime.bordeaux.inria.fr/StarPU/doc/html/ExecutionConfigurationThroughEnvironmentVariables.html">here</a>.
variables <a href="/files/doc/html/ExecutionConfigurationThroughEnvironmentVariables.html">here</a>.
</p>
<tt>
......@@ -463,9 +463,9 @@ have been easily ported to StarPU by simply using <tt>starpu_insert_task</tt>.
<p>
Take the vector example again, and add partitioning support to it, using the
matrix-matrix multiplication as an example. Here we will use the
<a href="http://runtime.bordeaux.inria.fr/StarPU/doc/html/group__API__Data__Partition.html#ga212189d3b83dfa4e225609b5f2bf8461"><tt>starpu_vector_filter_block()</tt></a> filter function. You can see the list of
<a href="/files/doc/html/group__API__Data__Partition.html#ga212189d3b83dfa4e225609b5f2bf8461"><tt>starpu_vector_filter_block()</tt></a> filter function. You can see the list of
predefined filters provided by
StarPU <a href="http://runtime.bordeaux.inria.fr/StarPU/doc/html/starpu__data__filters_8h.html">here</a>.
StarPU <a href="/files/doc/html/starpu__data__filters_8h.html">here</a>.
Try to run it with various numbers of tasks.
</p>
</div>
......@@ -477,7 +477,7 @@ Try to run it with various numbers of tasks.
<p>
This is based on StarPU's documentation
<a href="http://runtime.bordeaux.inria.fr/StarPU/doc/html/HowToOptimizePerformanceWithStarPU.html">optimization
<a href="/files/doc/html/HowToOptimizePerformanceWithStarPU.html">optimization
chapter</a>
</p>
......@@ -487,14 +487,14 @@ This is based on StarPU's documentation
<p>
We have explained how StarPU can overlap computation and data transfers
thanks to DMAs. This is however only possible when CUDA has control over the
application buffers. The application should thus use <a href="http://runtime.bordeaux.inria.fr/StarPU/doc/html/group__API__Standard__Memory__Library.html#ga49603eaea3b05e8ced9ba1bd873070c3"><tt>starpu_malloc()</tt></a>
application buffers. The application should thus use <a href="/files/doc/html/group__API__Standard__Memory__Library.html#ga49603eaea3b05e8ced9ba1bd873070c3"><tt>starpu_malloc()</tt></a>
when allocating its buffer, to permit asynchronous DMAs from and to
it.
</p>
<p>
Take the vector example again, and fix the allocation, to make it use
<a href="http://runtime.bordeaux.inria.fr/StarPU/doc/html/group__API__Standard__Memory__Library.html#ga49603eaea3b05e8ced9ba1bd873070c3"><tt>starpu_malloc()</tt></a>.
<a href="/files/doc/html/group__API__Standard__Memory__Library.html#ga49603eaea3b05e8ced9ba1bd873070c3"><tt>starpu_malloc()</tt></a>.
</p>
</div>
......@@ -698,7 +698,7 @@ For any questions regarding StarPU, please contact the StarPU developers mailing
<h2>More Performance Optimizations</h2>
<p>
The StarPU
documentation <a href="http://runtime.bordeaux.inria.fr/StarPU/doc/html/PerformanceFeedback.html">performance
documentation <a href="/files/doc/html/PerformanceFeedback.html">performance
feedback chapter</a> provides more optimization tips for further
reading after this tutorial.
</p>
......
......@@ -85,7 +85,7 @@ the platform using the following command.
</p>
<tt><pre>
$ wget http://starpu.gforge.inria.fr/tutorials/2019-11-HPNS-Inria/material.tgz
$ wget https://starpu.gitlabpages.inria.fr/tutorials/2019-11-HPNS-Inria/material.tgz
</pre></tt>
</div>
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment