<?xml version="1.0" encoding="UTF-8"?>
<rss xmlns:content="http://purl.org/rss/1.0/modules/content/" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" xmlns:taxo="http://purl.org/rss/1.0/modules/taxonomy/" version="2.0">
  <channel>
    <title>topic Hi Irina in Intel® oneAPI Math Kernel Library</title>
    <link>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/dfeast-scsrev-problem/m-p/1100036#M23826</link>
    <description>&lt;P&gt;Hi Irina&lt;BR /&gt;
	Linking with ILP64 as Gennady mentioned was a good tip but I had another problem which I just found out.&lt;BR /&gt;
	when I was preparing my pointer arrays for FEAST I was initiallizing like this&lt;/P&gt;

&lt;P&gt;double&amp;nbsp;&amp;nbsp;&amp;nbsp; *&amp;nbsp;&amp;nbsp; E =&amp;nbsp; (double*)malloc(N*sizeof(double)) ;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp; /* Eigenvalues */&lt;BR /&gt;
	double&amp;nbsp;&amp;nbsp;&amp;nbsp; *&amp;nbsp;&amp;nbsp; X =&amp;nbsp; (double*)malloc(N*N*sizeof(double));&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp; /* Eigenvectors */&lt;BR /&gt;
	double&amp;nbsp;&amp;nbsp;&amp;nbsp; *&amp;nbsp; res = (double*)malloc(N*sizeof(double)) ;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp; /* Residual */&lt;/P&gt;

&lt;P&gt;which is devil, because when you go for very big matrices you will face memory issues.&lt;BR /&gt;
	Some one can replace this N by M which is the number of eigenvalues(for sure approximately,because nobody knows exactly in advance) you want to calculate in corresponding interval.&lt;BR /&gt;
	Now my code is working fine.&lt;BR /&gt;
	Best,&lt;BR /&gt;
	Sina&lt;/P&gt;</description>
    <pubDate>Thu, 23 Jun 2016 08:26:36 GMT</pubDate>
    <dc:creator>Sina_S_</dc:creator>
    <dc:date>2016-06-23T08:26:36Z</dc:date>
    <item>
      <title>dfeast_scsrev problem</title>
      <link>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/dfeast-scsrev-problem/m-p/1100030#M23820</link>
      <description>&lt;P&gt;Hi Everybody&lt;BR /&gt;
	I have a problem regarding eigenvalue calculations for my system with dfeast_scsrev&lt;BR /&gt;
	as you know this function supposed to solve standard eigenvalue problem for sparse matrices.&lt;BR /&gt;
	My code was working fine previously but since I changed to bigger system(65536x65536) I have a segmentation fault. when I run my code with gdb I will see that the memory issue is regarding function mkl_feast_dfeast_srci () which I do not call it in my program.&lt;/P&gt;

&lt;P&gt;Program received signal SIGSEGV, Segmentation fault.&lt;BR /&gt;
	0x00007ffff54aa08a in mkl_feast_dfeast_srci () from /opt/apps/intel/2016-2/compilers_and_libraries_2016.2.181/linux/mkl/lib/intel64/libmkl_core.so&lt;/P&gt;

&lt;P&gt;this function belongs to Reverse Communication Interface which I am not using directly. Does any of you have any experience?&lt;BR /&gt;
	Thank you in advance.&lt;BR /&gt;
	Regards,&lt;/P&gt;</description>
      <pubDate>Fri, 17 Jun 2016 09:42:53 GMT</pubDate>
      <guid>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/dfeast-scsrev-problem/m-p/1100030#M23820</guid>
      <dc:creator>Sina_S_</dc:creator>
      <dc:date>2016-06-17T09:42:53Z</dc:date>
    </item>
    <item>
      <title>Sina, please try to link with</title>
      <link>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/dfeast-scsrev-problem/m-p/1100031#M23821</link>
      <description>&lt;P&gt;Sina, please try to link with ILP64 library and check how it will work. Pls see in MKL User's Guide how to compile and link this case.&lt;/P&gt;</description>
      <pubDate>Fri, 17 Jun 2016 11:21:11 GMT</pubDate>
      <guid>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/dfeast-scsrev-problem/m-p/1100031#M23821</guid>
      <dc:creator>Gennady_F_Intel</dc:creator>
      <dc:date>2016-06-17T11:21:11Z</dc:date>
    </item>
    <item>
      <title>thanks gennady,</title>
      <link>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/dfeast-scsrev-problem/m-p/1100032#M23822</link>
      <description>&lt;P&gt;thanks gennady,&lt;/P&gt;

&lt;P&gt;I was simply running my code with this command&lt;/P&gt;

&lt;P&gt;icpc -O3&amp;nbsp; -mkl -std=c++11 main.cpp -o CSR_Network&lt;BR /&gt;
	and i also tried with&lt;/P&gt;

&lt;P&gt;icpc -O3 -ILP64 -mkl -std=c++11 main.cpp -o CSR_Network&lt;BR /&gt;
	but still i have the same problem.&lt;/P&gt;

&lt;P&gt;&amp;nbsp;&lt;/P&gt;

&lt;P&gt;&amp;nbsp;&lt;/P&gt;</description>
      <pubDate>Fri, 17 Jun 2016 13:50:50 GMT</pubDate>
      <guid>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/dfeast-scsrev-problem/m-p/1100032#M23822</guid>
      <dc:creator>Sina_S_</dc:creator>
      <dc:date>2016-06-17T13:50:50Z</dc:date>
    </item>
    <item>
      <title>have you read the User's</title>
      <link>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/dfeast-scsrev-problem/m-p/1100033#M23823</link>
      <description>&lt;P&gt;have you read the User's Guide to see how compile ILP64 example? pls have a look at, for example, this page&amp;nbsp;https://software.intel.com/en-us/node/528524. pls pay attenntion you need add additional compler's option and changed the linking line &amp;nbsp;&amp;nbsp;&lt;/P&gt;</description>
      <pubDate>Fri, 17 Jun 2016 15:57:36 GMT</pubDate>
      <guid>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/dfeast-scsrev-problem/m-p/1100033#M23823</guid>
      <dc:creator>Gennady_F_Intel</dc:creator>
      <dc:date>2016-06-17T15:57:36Z</dc:date>
    </item>
    <item>
      <title>Hi again</title>
      <link>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/dfeast-scsrev-problem/m-p/1100034#M23824</link>
      <description>&lt;P&gt;Hi again&lt;BR /&gt;
	Thanks for your information.&lt;BR /&gt;
	from intel mkl link line advisor I learned how to link with ILP64.&lt;BR /&gt;
	&lt;A href="https://software.intel.com/en-us/articles/intel-mkl-link-line-advisor" target="_blank"&gt;https://software.intel.com/en-us/articles/intel-mkl-link-line-advisor&lt;/A&gt;&lt;BR /&gt;
	this time the segmentation fault is like this&lt;/P&gt;

&lt;P&gt;Program received signal SIGSEGV, Segmentation fault.&lt;BR /&gt;
	0x000000000040f23a in __intel_avx_rep_memset ().&lt;BR /&gt;
	Best,&lt;BR /&gt;
	&amp;nbsp;&lt;/P&gt;</description>
      <pubDate>Tue, 21 Jun 2016 07:43:06 GMT</pubDate>
      <guid>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/dfeast-scsrev-problem/m-p/1100034#M23824</guid>
      <dc:creator>Sina_S_</dc:creator>
      <dc:date>2016-06-21T07:43:06Z</dc:date>
    </item>
    <item>
      <title>Hi Sina,</title>
      <link>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/dfeast-scsrev-problem/m-p/1100035#M23825</link>
      <description>&lt;P&gt;Hi Sina,&lt;/P&gt;

&lt;P&gt;dfeast_scsrev calls rci interface internally, so that's expected.&lt;/P&gt;

&lt;P&gt;Could you please&amp;nbsp;sent me a small reproducer on how you set feast parameters and call dfeast_scsrev? Is your matrix 1-based?&lt;/P&gt;

&lt;P&gt;Best regards,&lt;/P&gt;

&lt;P&gt;Irina&lt;/P&gt;</description>
      <pubDate>Thu, 23 Jun 2016 08:00:50 GMT</pubDate>
      <guid>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/dfeast-scsrev-problem/m-p/1100035#M23825</guid>
      <dc:creator>Irina_S_Intel</dc:creator>
      <dc:date>2016-06-23T08:00:50Z</dc:date>
    </item>
    <item>
      <title>Hi Irina</title>
      <link>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/dfeast-scsrev-problem/m-p/1100036#M23826</link>
      <description>&lt;P&gt;Hi Irina&lt;BR /&gt;
	Linking with ILP64 as Gennady mentioned was a good tip but I had another problem which I just found out.&lt;BR /&gt;
	when I was preparing my pointer arrays for FEAST I was initiallizing like this&lt;/P&gt;

&lt;P&gt;double&amp;nbsp;&amp;nbsp;&amp;nbsp; *&amp;nbsp;&amp;nbsp; E =&amp;nbsp; (double*)malloc(N*sizeof(double)) ;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp; /* Eigenvalues */&lt;BR /&gt;
	double&amp;nbsp;&amp;nbsp;&amp;nbsp; *&amp;nbsp;&amp;nbsp; X =&amp;nbsp; (double*)malloc(N*N*sizeof(double));&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp; /* Eigenvectors */&lt;BR /&gt;
	double&amp;nbsp;&amp;nbsp;&amp;nbsp; *&amp;nbsp; res = (double*)malloc(N*sizeof(double)) ;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp; /* Residual */&lt;/P&gt;

&lt;P&gt;which is devil, because when you go for very big matrices you will face memory issues.&lt;BR /&gt;
	Some one can replace this N by M which is the number of eigenvalues(for sure approximately,because nobody knows exactly in advance) you want to calculate in corresponding interval.&lt;BR /&gt;
	Now my code is working fine.&lt;BR /&gt;
	Best,&lt;BR /&gt;
	Sina&lt;/P&gt;</description>
      <pubDate>Thu, 23 Jun 2016 08:26:36 GMT</pubDate>
      <guid>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/dfeast-scsrev-problem/m-p/1100036#M23826</guid>
      <dc:creator>Sina_S_</dc:creator>
      <dc:date>2016-06-23T08:26:36Z</dc:date>
    </item>
  </channel>
</rss>

