Added Polynomial Smoother infos

This commit is contained in:
2024-11-18 10:03:21 +01:00
parent 82de529c54
commit 70fb39ae55
38 changed files with 4595 additions and 6181 deletions
+26 -20
View File
@@ -33,8 +33,7 @@ class="cmr-12">The code discussed here shows how to set up a program exploiting
<span
class="cmr-12">capabilities of PSBLAS and AMG4PSBLAS. The code example is available in the</span>
<span
class="cmr-12">source distribution directory </span><span class="obeylines-h"><span class="verb"><span
class="cmtt-12">amg4psblas/examples/gpu</span></span></span><span
class="cmr-12">source distribution directory </span><span class="obeylines-h"><code class="verb">amg4psblas/examples/gpu</code></span><span
class="cmr-12">.</span>
<!--l. 431--><p class="indent" > <span
class="cmr-12">First of all, we need to include the appropriate modules and declare some auxiliary</span>
@@ -52,7 +51,7 @@ class="cmr-12">variables:</span>
<div class="center"
>
<!--l. 452--><p class="noindent" >
<div class="minipage"><pre class="verbatim" id="verbatim-10">
<div class="minipage"><pre class="verbatim" id="verbatim-11">
program&#x00A0;amg_dexample_gpu
&#x00A0;&#x00A0;use&#x00A0;psb_base_mod
&#x00A0;&#x00A0;use&#x00A0;amg_prec_mod
@@ -67,9 +66,10 @@ program&#x00A0;amg_dexample_gpu
&#x00A0;&#x00A0;type(psb_d_hlg_sparse_mat)&#x00A0;::&#x00A0;agmold
&#x00A0;&#x00A0;type(psb_d_vect_gpu)&#x00A0;&#x00A0;&#x00A0;&#x00A0;&#x00A0;&#x00A0;&#x00A0;::&#x00A0;vgmold
&#x00A0;&#x00A0;type(psb_i_vect_gpu)&#x00A0;&#x00A0;&#x00A0;&#x00A0;&#x00A0;&#x00A0;&#x00A0;::&#x00A0;igmold
&#x00A0;
</pre>
<!--l. 471--><p class="nopar" ></div></div>
<!--l. 471--><p class="nopar" > </div></div>
<br /> <div class="caption"
><span class="id">Listing 5: </span><span
class="content">setup of a GPU-enabled test program part one.</span></div><!--tex4ht:label?: x16-15001r5 -->
@@ -78,8 +78,7 @@ class="content">setup of a GPU-enabled test program part one.</span></div><!--te
</div><hr class="endfloat" />
<!--l. 478--><p class="indent" > <span
class="cmr-12">In this particular example we are choosing to employ a </span><span class="obeylines-h"><span class="verb"><span
class="cmtt-12">HLG</span></span></span> <span
class="cmr-12">In this particular example we are choosing to employ a </span><span class="obeylines-h"><code class="verb">HLG</code></span> <span
class="cmr-12">data structure for</span>
<span
class="cmr-12">sparse matrices on GPUs; for more information please refer to the PSBLAS-EXT users&#8217;</span>
@@ -103,7 +102,7 @@ class="cmr-12">guides).</span>
<div class="center"
>
<!--l. 501--><p class="noindent" >
<div class="minipage"><pre class="verbatim" id="verbatim-11">
<div class="minipage"><pre class="verbatim" id="verbatim-12">
&#x00A0;&#x00A0;call&#x00A0;psb_init(ctxt)
&#x00A0;&#x00A0;call&#x00A0;psb_info(ctxt,iam,np)
&#x00A0;&#x00A0;!
@@ -114,9 +113,10 @@ class="cmr-12">guides).</span>
&#x00A0;&#x00A0;......
&#x00A0;&#x00A0;t1&#x00A0;=&#x00A0;psb_wtime()
&#x00A0;&#x00A0;call&#x00A0;prec%smoothers_build(a,desc_a,info,&#x00A0;amold=agmold,&#x00A0;vmold=vgmold,&#x00A0;imold=igmold)
&#x00A0;
</pre>
<!--l. 516--><p class="nopar" ></div></div>
<!--l. 516--><p class="nopar" > </div></div>
<br /> <div class="caption"
><span class="id">Listing 6: </span><span
class="content">setup of a GPU-enabled test program part two.</span></div><!--tex4ht:label?: x16-15002r6 -->
@@ -144,11 +144,12 @@ class="cmr-12">GPU environment</span>
<div class="center"
>
<!--l. 557--><p class="noindent" >
<div class="minipage"><pre class="verbatim" id="verbatim-12">
<div class="minipage"><pre class="verbatim" id="verbatim-13">
&#x00A0;&#x00A0;call&#x00A0;desc_a%cnv(mold=igmold)
&#x00A0;&#x00A0;call&#x00A0;a%cscnv(info,mold=agmold)
&#x00A0;&#x00A0;call&#x00A0;psb_geasb(x,desc_a,info,mold=vgmold)
&#x00A0;&#x00A0;call&#x00A0;psb_geasb(b,desc_a,info,mold=vgmold)
&#x00A0;&#x00A0;!
&#x00A0;&#x00A0;!&#x00A0;iterative&#x00A0;method&#x00A0;parameters
&#x00A0;&#x00A0;!
@@ -161,13 +162,15 @@ class="cmr-12">GPU environment</span>
&#x00A0;&#x00A0;call&#x00A0;prec%deallocate_wrk(info)
&#x00A0;&#x00A0;call&#x00A0;psb_barrier(ctxt)
&#x00A0;&#x00A0;tslv&#x00A0;=&#x00A0;psb_wtime()&#x00A0;-&#x00A0;t1
&#x00A0;&#x00A0;......
&#x00A0;&#x00A0;call&#x00A0;psb_gpu_exit()
&#x00A0;&#x00A0;call&#x00A0;psb_exit(ctxt)
&#x00A0;&#x00A0;stop
&#x00A0;
</pre>
<!--l. 584--><p class="nopar" ></div></div>
<!--l. 584--><p class="nopar" > </div></div>
<br /> <div class="caption"
><span class="id">Listing 7: </span><span
class="content">setup of a GPU-enabled test program part three.</span></div><!--tex4ht:label?: x16-15003r7 -->
@@ -182,21 +185,21 @@ class="cmr-12">GPU, i.e. methods that do NOT employ triangular system solve kern
<span
class="cmr-12">satisfy this constraint include:</span>
<ul class="itemize1">
<li class="itemize"><span class="obeylines-h"><span class="verb"><span
class="cmtt-12">JACOBI</span></span></span>
<li class="itemize">
<!--l. 596--><p class="noindent" ><span class="obeylines-h"><code class="verb">JACOBI</code></span>
</li>
<li class="itemize"><span class="obeylines-h"><span class="verb"><span
class="cmtt-12">BJAC</span></span></span> <span
<li class="itemize">
<!--l. 597--><p class="noindent" ><span class="obeylines-h"><code class="verb">BJAC</code></span> <span
class="cmr-12">with the following methods on the local blocks:</span>
<ul class="itemize2">
<li class="itemize"><span class="obeylines-h"><span class="verb"><span
class="cmtt-12">INVK</span></span></span>
<li class="itemize">
<!--l. 599--><p class="noindent" ><span class="obeylines-h"><code class="verb">INVK</code></span>
</li>
<li class="itemize"><span class="obeylines-h"><span class="verb"><span
class="cmtt-12">INVT</span></span></span>
<li class="itemize">
<!--l. 600--><p class="noindent" ><span class="obeylines-h"><code class="verb">INVT</code></span>
</li>
<li class="itemize"><span class="obeylines-h"><span class="verb"><span
class="cmtt-12">AINV</span></span></span></li></ul>
<li class="itemize">
<!--l. 601--><p class="noindent" ><span class="obeylines-h"><code class="verb">AINV</code></span></li></ul>
</li></ul>
<!--l. 604--><p class="noindent" ><span
class="cmr-12">and their </span><span
@@ -209,6 +212,9 @@ class="cmr-12">variants.</span>
<!--l. 1--><div class="crosslinks"><p class="noindent"><span
class="cmr-12">[</span><a
href="userhtmlsu6.html" ><span