deploy: 688eb0e

Author: ndgrigorian

404.html

@@ -67,5 +67,5 @@
 selecting only devices that do not support SPIR language would result in an error.</p><h3 id=targeting-other-gpus>Targeting other GPUs<a class=td-heading-self-link href=#targeting-other-gpus aria-label="Heading self-link"></a></h3><p>DPC++ supports generation of offload sections for multiple targets. For example, to compile for both SPIR and NVPTX targets (oneAPI for NVidia(R) GPUs is assumed installed):</p><div class=highlight><pre tabindex=0 style=background-color:#f8f8f8;-moz-tab-size:4;-o-tab-size:4;tab-size:4><code class=language-bash data-lang=bash><span style=display:flex><span>icpx -fsycl -Xsycl-targets<span style=color:#ce5c00;font-weight:700>=</span><span style=color:#4e9a06>&#34;nvptx64-nvidia-cuda,spir64-unknown-unknown&#34;</span> first.cpp -o first.out
 </span></span></code></pre></div><p>To compile for both SPIR and AMD GCN targets (oneAPI for AMD GPUs is assumed installed):</p><div class=highlight><pre tabindex=0 style=background-color:#f8f8f8;-moz-tab-size:4;-o-tab-size:4;tab-size:4><code class=language-bash data-lang=bash><span style=display:flex><span>icpx -fsycl -Xsycl-targets<span style=color:#ce5c00;font-weight:700>=</span><span style=color:#4e9a06>&#34;amdgcn-amd-amdhsa,spir64-unknown-unknown&#34;</span> first.cpp -o first.out
 </span></span></code></pre></div><p>It is possible to pass additional arguments to the specific SYCL target backend. For example, to target specific architecture use:</p><ul><li><code>-Xsycl-target-backend=amdgcn-amd-amdhsa --offload-arch=gfx1030</code> for AMD GPUs</li><li><code>-Xsycl-target-backend=nvptx64-nvidia-cuda --cuda-gpu-arch=sm_80</code> for NVidia GPUs</li></ul></div></main></div></div><footer class="td-footer row d-print-none"><div class=container-fluid><div class="row mx-md-2"><div class="td-footer__left col-6 col-sm-4 order-sm-1"></div><div class="td-footer__right col-6 col-sm-4 order-sm-3"><ul class=td-footer__links-list><li class=td-footer__links-item data-bs-toggle=tooltip title=GitHub aria-label=GitHub><a target=_blank rel=noopener href=https://github.com/google/docsy aria-label=GitHub><i class="fab fa-github"></i></a></li></ul></div><div class="td-footer__center col-12 col-sm-4 py-2 order-sm-2"><span class=td-footer__copyright>&copy;
-2024
+2025
 <span class=td-footer__authors>Intel Corp. All Rights Reserved</span></span><span class=td-footer__all_rights_reserved>All Rights Reserved</span></div></div></div></footer></div><link rel=stylesheet href=https://cdn.jsdelivr.net/npm/katex@0.16.10/dist/katex.min.css integrity="sha512-r2+FkHzf1u0+SQbZOoIz2RxWOIWfdEzRuYybGjzKq18jG9zaSfEy9s3+jMqG/zPtRor/q4qaUCYQpmSjTw8M+g==" crossorigin=anonymous><script defer src=https://cdn.jsdelivr.net/npm/katex@0.16.10/dist/katex.min.js integrity="sha512-INps9zQ2GUEMCQD7xiZQbGUVnqnzEvlynVy6eqcTcHN4+aQiLo9/uaQqckDpdJ8Zm3M0QBs+Pktg4pz0kEklUg==" crossorigin=anonymous></script><script defer src=https://cdn.jsdelivr.net/npm/katex@0.16.10/dist/contrib/auto-render.min.js integrity="sha512-YJVxTjqttjsU3cSvaTRqsSl0wbRgZUNF+NGGCgto/MUbIvaLdXQzGTCQu4CvyJZbZctgflVB0PXw9LLmTWm5/w==" crossorigin=anonymous onload=renderMathInElement(document.body,null)></script><script src=/portable-data-parallel-extensions-scipy-2024/js/main.min.01cb5f1282c45e535df60a2391d493bcb88881db5cb163e5a05d0280da827233.js integrity="sha256-ActfEoLEXlNd9gojkdSTvLiIgdtcsWPloF0CgNqCcjM=" crossorigin=anonymous></script><script defer src=/portable-data-parallel-extensions-scipy-2024/js/click-to-copy.min.73478a7d4807698aed7e355eb23f9890ca18fea3158604c8471746d046702bad.js integrity="sha256-c0eKfUgHaYrtfjVesj+YkMoY/qMVhgTIRxdG0EZwK60=" crossorigin=anonymous></script><script src=/portable-data-parallel-extensions-scipy-2024/js/tabpane-persist.js></script></body></html>

docs/first-app/index.html

@@ -10,5 +10,5 @@
 <a href="https://github.com/google/docsy-example/new/main/content/en/docs?filename=change-me.md&amp;value=---%0Atitle%3A+%22Long+Page+Title%22%0AlinkTitle%3A+%22Short+Nav+Title%22%0Aweight%3A+100%0Adescription%3A+%3E-%0A+++++Page+description+for+heading+and+indexes.%0A---%0A%0A%23%23+Heading%0A%0AEdit+this+template+to+create+your+new+page.%0A%0A%2A+Give+it+a+good+name%2C+ending+in+%60.md%60+-+e.g.+%60getting-started.md%60%0A%2A+Edit+the+%22front+matter%22+section+at+the+top+of+the+page+%28weight+controls+how+its+ordered+amongst+other+pages+in+the+same+directory%3B+lowest+number+first%29.%0A%2A+Add+a+good+commit+message+at+the+bottom+of+the+page+%28%3C80+characters%3B+use+the+extended+description+field+for+more+detail%29.%0A%2A+Create+a+new+branch+so+you+can+preview+your+new+file+and+request+a+review+via+Pull+Request.%0A" class="td-page-meta--child td-page-meta__child" target=_blank rel=noopener><i class="fa-solid fa-pen-to-square fa-fw"></i> Create child page</a>
 <a href="https://github.com/google/docsy-example/issues/new?title=SciPy%202024%20poster%20content" class="td-page-meta--issue td-page-meta__issue" target=_blank rel=noopener><i class="fa-solid fa-list-check fa-fw"></i> Create documentation issue</a>
 <a href=https://github.com/google/docsy/issues/new class="td-page-meta--project td-page-meta__project-issue" target=_blank rel=noopener><i class="fa-solid fa-list-check fa-fw"></i> Create project issue</a></div><div class=td-toc><nav id=TableOfContents><ul><li><a href=#portable-data-parallel-extensions-with-oneapi>Portable Data-Parallel Extensions with oneAPI</a></li></ul></nav></div></aside><main class="col-12 col-md-9 col-xl-8 ps-md-5" role=main><nav aria-label=breadcrumb class="td-breadcrumbs td-breadcrumbs__single"><ol class=breadcrumb><li class="breadcrumb-item active" aria-current=page>Details</li></ol></nav><div class=td-content><h1>SciPy 2024 poster content</h1><header class=article-meta></header><h2 id=portable-data-parallel-extensions-with-oneapi>Portable Data-Parallel Extensions with oneAPI<a class=td-heading-self-link href=#portable-data-parallel-extensions-with-oneapi aria-label="Heading self-link"></a></h2><p>by <a href=https://github.com/ndgrigorian>Nikita Grigorian</a> and <a href=https://github.com/oleksandr-pavlyk>Oleksandr Pavlyk</a></p><p>This poster is intended to introduce writing portable data-parallel Python extensions using oneAPI.</p><p>We present several examples, starting with the basics of initializing a USM (unified shared memory) array, then a KDE (kernel density estimation) with pure DPC++/Sycl, then a KDE Python extension, and finally how to write a portable Python extension which uses oneMKL.</p><p>The examples can be found <a href=https://github.com/IntelPython/example-portable-data-parallel-extensions>here</a>.</p><div class=section-index><hr class=panel-line><div class=entry><h5><a href=/portable-data-parallel-extensions-scipy-2024/docs/oneapi/>About oneAPI</a></h5><p>A brief overview of oneAPI and the programming model</p></div><div class=entry><h5><a href=/portable-data-parallel-extensions-scipy-2024/docs/first-app/>First DPC++ app</a></h5><p>A SYCL and DPC++ &ldquo;Hello, World!&rdquo; example.</p></div><div class=entry><h5><a href=/portable-data-parallel-extensions-scipy-2024/docs/kde-cpp/>KDE DPC++ example</a></h5><p>KDE (kernel density estimation) example using SYCL and DPC++.</p></div><div class=entry><h5><a href=/portable-data-parallel-extensions-scipy-2024/docs/kde-python/>KDE Python extension</a></h5><p>KDE (kernel density estimation) Python extension example.</p></div><div class=entry><h5><a href=/portable-data-parallel-extensions-scipy-2024/docs/onemkl/>oneMKL Python extension</a></h5><p>A Python extension written using oneMKL interfaces.</p></div></div></div></main></div></div><footer class="td-footer row d-print-none"><div class=container-fluid><div class="row mx-md-2"><div class="td-footer__left col-6 col-sm-4 order-sm-1"></div><div class="td-footer__right col-6 col-sm-4 order-sm-3"><ul class=td-footer__links-list><li class=td-footer__links-item data-bs-toggle=tooltip title=GitHub aria-label=GitHub><a target=_blank rel=noopener href=https://github.com/google/docsy aria-label=GitHub><i class="fab fa-github"></i></a></li></ul></div><div class="td-footer__center col-12 col-sm-4 py-2 order-sm-2"><span class=td-footer__copyright>&copy;
-2024
+2025
 <span class=td-footer__authors>Intel Corp. All Rights Reserved</span></span><span class=td-footer__all_rights_reserved>All Rights Reserved</span></div></div></div></footer></div><link rel=stylesheet href=https://cdn.jsdelivr.net/npm/katex@0.16.10/dist/katex.min.css integrity="sha512-r2+FkHzf1u0+SQbZOoIz2RxWOIWfdEzRuYybGjzKq18jG9zaSfEy9s3+jMqG/zPtRor/q4qaUCYQpmSjTw8M+g==" crossorigin=anonymous><script defer src=https://cdn.jsdelivr.net/npm/katex@0.16.10/dist/katex.min.js integrity="sha512-INps9zQ2GUEMCQD7xiZQbGUVnqnzEvlynVy6eqcTcHN4+aQiLo9/uaQqckDpdJ8Zm3M0QBs+Pktg4pz0kEklUg==" crossorigin=anonymous></script><script defer src=https://cdn.jsdelivr.net/npm/katex@0.16.10/dist/contrib/auto-render.min.js integrity="sha512-YJVxTjqttjsU3cSvaTRqsSl0wbRgZUNF+NGGCgto/MUbIvaLdXQzGTCQu4CvyJZbZctgflVB0PXw9LLmTWm5/w==" crossorigin=anonymous onload=renderMathInElement(document.body,null)></script><script src=/portable-data-parallel-extensions-scipy-2024/js/main.min.01cb5f1282c45e535df60a2391d493bcb88881db5cb163e5a05d0280da827233.js integrity="sha256-ActfEoLEXlNd9gojkdSTvLiIgdtcsWPloF0CgNqCcjM=" crossorigin=anonymous></script><script defer src=/portable-data-parallel-extensions-scipy-2024/js/click-to-copy.min.73478a7d4807698aed7e355eb23f9890ca18fea3158604c8471746d046702bad.js integrity="sha256-c0eKfUgHaYrtfjVesj+YkMoY/qMVhgTIRxdG0EZwK60=" crossorigin=anonymous></script><script src=/portable-data-parallel-extensions-scipy-2024/js/tabpane-persist.js></script></body></html>

docs/index.html

@@ -86,5 +86,5 @@
 in <a href=https://github.com/IntelPython/example-portable-data-parallel-extensions/blob/main/steps/kernel_density_estimation_cpp/kde.hpp><code>"steps/kernel_density_estimation_cpp/kde.hpp"</code></a>.</p><p>These implementations are called from C++ application <a href=https://github.com/IntelPython/example-portable-data-parallel-extensions/blob/main/steps/kernel_density_estimation_cpp/app.cpp><code>"steps/kernel_density_estimation_cpp/app.cpp"</code></a>, which
 samples data uniformly distributed over unit cuboid, and estimates the density using Kernel Density Estimation
 and spherically symmetric multivariate Gaussian probability density function as the kernel.</p><p>The application can be built using <code>CMake</code>, or <code>Meson</code>, please refer to <a href=https://github.com/IntelPython/example-portable-data-parallel-extensions/blob/main/steps/kernel_density_estimation_cpp/README.md>README</a> document in that folder.</p></div></main></div></div><footer class="td-footer row d-print-none"><div class=container-fluid><div class="row mx-md-2"><div class="td-footer__left col-6 col-sm-4 order-sm-1"></div><div class="td-footer__right col-6 col-sm-4 order-sm-3"><ul class=td-footer__links-list><li class=td-footer__links-item data-bs-toggle=tooltip title=GitHub aria-label=GitHub><a target=_blank rel=noopener href=https://github.com/google/docsy aria-label=GitHub><i class="fab fa-github"></i></a></li></ul></div><div class="td-footer__center col-12 col-sm-4 py-2 order-sm-2"><span class=td-footer__copyright>&copy;
-2024
+2025
 <span class=td-footer__authors>Intel Corp. All Rights Reserved</span></span><span class=td-footer__all_rights_reserved>All Rights Reserved</span></div></div></div></footer></div><link rel=stylesheet href=https://cdn.jsdelivr.net/npm/katex@0.16.10/dist/katex.min.css integrity="sha512-r2+FkHzf1u0+SQbZOoIz2RxWOIWfdEzRuYybGjzKq18jG9zaSfEy9s3+jMqG/zPtRor/q4qaUCYQpmSjTw8M+g==" crossorigin=anonymous><script defer src=https://cdn.jsdelivr.net/npm/katex@0.16.10/dist/katex.min.js integrity="sha512-INps9zQ2GUEMCQD7xiZQbGUVnqnzEvlynVy6eqcTcHN4+aQiLo9/uaQqckDpdJ8Zm3M0QBs+Pktg4pz0kEklUg==" crossorigin=anonymous></script><script defer src=https://cdn.jsdelivr.net/npm/katex@0.16.10/dist/contrib/auto-render.min.js integrity="sha512-YJVxTjqttjsU3cSvaTRqsSl0wbRgZUNF+NGGCgto/MUbIvaLdXQzGTCQu4CvyJZbZctgflVB0PXw9LLmTWm5/w==" crossorigin=anonymous onload=renderMathInElement(document.body,null)></script><script src=/portable-data-parallel-extensions-scipy-2024/js/main.min.01cb5f1282c45e535df60a2391d493bcb88881db5cb163e5a05d0280da827233.js integrity="sha256-ActfEoLEXlNd9gojkdSTvLiIgdtcsWPloF0CgNqCcjM=" crossorigin=anonymous></script><script defer src=/portable-data-parallel-extensions-scipy-2024/js/click-to-copy.min.73478a7d4807698aed7e355eb23f9890ca18fea3158604c8471746d046702bad.js integrity="sha256-c0eKfUgHaYrtfjVesj+YkMoY/qMVhgTIRxdG0EZwK60=" crossorigin=anonymous></script><script src=/portable-data-parallel-extensions-scipy-2024/js/tabpane-persist.js></script></body></html>

docs/kde-cpp/index.html

@@ -75,5 +75,5 @@
 </span></span><span style=display:flex><span>kde_ext<span style=color:#ce5c00;font-weight:700>[</span><span style=color:#000>mode</span><span style=color:#ce5c00;font-weight:700>=</span>2<span style=color:#ce5c00;font-weight:700>]</span> 0.02815118699800223 seconds
 </span></span><span style=display:flex><span>kde_numpy 0.7227164240321144 seconds
 </span></span></code></pre></div><p>This sample run was obtained on a laptop with 11th Gen Intel(R) Core(TM) i7-1185G7 CPU @ 3.00GHz, 32 GB of RAM, and the integrated Intel(R) Iris(R) Xe GPU, with stock NumPy 1.26.4, and development build of dpctl 0.17 built with oneAPI DPC++ 2024.1.0.</p></div></main></div></div><footer class="td-footer row d-print-none"><div class=container-fluid><div class="row mx-md-2"><div class="td-footer__left col-6 col-sm-4 order-sm-1"></div><div class="td-footer__right col-6 col-sm-4 order-sm-3"><ul class=td-footer__links-list><li class=td-footer__links-item data-bs-toggle=tooltip title=GitHub aria-label=GitHub><a target=_blank rel=noopener href=https://github.com/google/docsy aria-label=GitHub><i class="fab fa-github"></i></a></li></ul></div><div class="td-footer__center col-12 col-sm-4 py-2 order-sm-2"><span class=td-footer__copyright>&copy;
-2024
+2025
 <span class=td-footer__authors>Intel Corp. All Rights Reserved</span></span><span class=td-footer__all_rights_reserved>All Rights Reserved</span></div></div></div></footer></div><link rel=stylesheet href=https://cdn.jsdelivr.net/npm/katex@0.16.10/dist/katex.min.css integrity="sha512-r2+FkHzf1u0+SQbZOoIz2RxWOIWfdEzRuYybGjzKq18jG9zaSfEy9s3+jMqG/zPtRor/q4qaUCYQpmSjTw8M+g==" crossorigin=anonymous><script defer src=https://cdn.jsdelivr.net/npm/katex@0.16.10/dist/katex.min.js integrity="sha512-INps9zQ2GUEMCQD7xiZQbGUVnqnzEvlynVy6eqcTcHN4+aQiLo9/uaQqckDpdJ8Zm3M0QBs+Pktg4pz0kEklUg==" crossorigin=anonymous></script><script defer src=https://cdn.jsdelivr.net/npm/katex@0.16.10/dist/contrib/auto-render.min.js integrity="sha512-YJVxTjqttjsU3cSvaTRqsSl0wbRgZUNF+NGGCgto/MUbIvaLdXQzGTCQu4CvyJZbZctgflVB0PXw9LLmTWm5/w==" crossorigin=anonymous onload=renderMathInElement(document.body,null)></script><script src=/portable-data-parallel-extensions-scipy-2024/js/main.min.01cb5f1282c45e535df60a2391d493bcb88881db5cb163e5a05d0280da827233.js integrity="sha256-ActfEoLEXlNd9gojkdSTvLiIgdtcsWPloF0CgNqCcjM=" crossorigin=anonymous></script><script defer src=/portable-data-parallel-extensions-scipy-2024/js/click-to-copy.min.73478a7d4807698aed7e355eb23f9890ca18fea3158604c8471746d046702bad.js integrity="sha256-c0eKfUgHaYrtfjVesj+YkMoY/qMVhgTIRxdG0EZwK60=" crossorigin=anonymous></script><script src=/portable-data-parallel-extensions-scipy-2024/js/tabpane-persist.js></script></body></html>

docs/kde-python/index.html

@@ -9,5 +9,5 @@
 </span></span><span style=display:flex><span><span style=color:#ce5c00;font-weight:700>[</span>opencl:cpu:1<span style=color:#ce5c00;font-weight:700>]</span> Intel<span style=color:#ce5c00;font-weight:700>(</span>R<span style=color:#ce5c00;font-weight:700>)</span> OpenCL, 12th Gen Intel<span style=color:#ce5c00;font-weight:700>(</span>R<span style=color:#ce5c00;font-weight:700>)</span> Core<span style=color:#ce5c00;font-weight:700>(</span>TM<span style=color:#ce5c00;font-weight:700>)</span> i9-12900 OpenCL 3.0 <span style=color:#ce5c00;font-weight:700>(</span>Build 0<span style=color:#ce5c00;font-weight:700>)</span> <span style=color:#ce5c00;font-weight:700>[</span>2024.17.3.0.08_160000<span style=color:#ce5c00;font-weight:700>]</span>
 </span></span><span style=display:flex><span><span style=color:#ce5c00;font-weight:700>[</span>ext_oneapi_cuda:gpu:0<span style=color:#ce5c00;font-weight:700>]</span> NVIDIA CUDA BACKEND, NVIDIA GeForce GT <span style=color:#0000cf;font-weight:700>1030</span> 6.1 <span style=color:#ce5c00;font-weight:700>[</span>CUDA 12.2<span style=color:#ce5c00;font-weight:700>]</span>
 </span></span></code></pre></div><p>A list of SYCL projects can be found on <a href=https://sycl.tech/projects>https://sycl.tech/projects</a></p></div></main></div></div><footer class="td-footer row d-print-none"><div class=container-fluid><div class="row mx-md-2"><div class="td-footer__left col-6 col-sm-4 order-sm-1"></div><div class="td-footer__right col-6 col-sm-4 order-sm-3"><ul class=td-footer__links-list><li class=td-footer__links-item data-bs-toggle=tooltip title=GitHub aria-label=GitHub><a target=_blank rel=noopener href=https://github.com/google/docsy aria-label=GitHub><i class="fab fa-github"></i></a></li></ul></div><div class="td-footer__center col-12 col-sm-4 py-2 order-sm-2"><span class=td-footer__copyright>&copy;
-2024
+2025
 <span class=td-footer__authors>Intel Corp. All Rights Reserved</span></span><span class=td-footer__all_rights_reserved>All Rights Reserved</span></div></div></div></footer></div><link rel=stylesheet href=https://cdn.jsdelivr.net/npm/katex@0.16.10/dist/katex.min.css integrity="sha512-r2+FkHzf1u0+SQbZOoIz2RxWOIWfdEzRuYybGjzKq18jG9zaSfEy9s3+jMqG/zPtRor/q4qaUCYQpmSjTw8M+g==" crossorigin=anonymous><script defer src=https://cdn.jsdelivr.net/npm/katex@0.16.10/dist/katex.min.js integrity="sha512-INps9zQ2GUEMCQD7xiZQbGUVnqnzEvlynVy6eqcTcHN4+aQiLo9/uaQqckDpdJ8Zm3M0QBs+Pktg4pz0kEklUg==" crossorigin=anonymous></script><script defer src=https://cdn.jsdelivr.net/npm/katex@0.16.10/dist/contrib/auto-render.min.js integrity="sha512-YJVxTjqttjsU3cSvaTRqsSl0wbRgZUNF+NGGCgto/MUbIvaLdXQzGTCQu4CvyJZbZctgflVB0PXw9LLmTWm5/w==" crossorigin=anonymous onload=renderMathInElement(document.body,null)></script><script src=/portable-data-parallel-extensions-scipy-2024/js/main.min.01cb5f1282c45e535df60a2391d493bcb88881db5cb163e5a05d0280da827233.js integrity="sha256-ActfEoLEXlNd9gojkdSTvLiIgdtcsWPloF0CgNqCcjM=" crossorigin=anonymous></script><script defer src=/portable-data-parallel-extensions-scipy-2024/js/click-to-copy.min.73478a7d4807698aed7e355eb23f9890ca18fea3158604c8471746d046702bad.js integrity="sha256-c0eKfUgHaYrtfjVesj+YkMoY/qMVhgTIRxdG0EZwK60=" crossorigin=anonymous></script><script src=/portable-data-parallel-extensions-scipy-2024/js/tabpane-persist.js></script></body></html>