<?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 Re: memory increasing problem calling pardiso! in Intel® oneAPI Math Kernel Library</title>
    <link>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/memory-increasing-problem-calling-pardiso/m-p/905371#M11593</link>
    <description>Thank you for your reply! &lt;BR /&gt;&lt;BR /&gt;Sorry,I forgot that. I use MKL 10.0.1.015. Does this version have a bug as you have said? And which version should I use? Thanks!&lt;BR /&gt;</description>
    <pubDate>Wed, 27 Aug 2008 02:52:58 GMT</pubDate>
    <dc:creator>liubing84</dc:creator>
    <dc:date>2008-08-27T02:52:58Z</dc:date>
    <item>
      <title>memory increasing problem calling pardiso!</title>
      <link>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/memory-increasing-problem-calling-pardiso/m-p/905369#M11591</link>
      <description>Hi, &lt;BR /&gt;here is the exact description of my problem: In loops(up to more than 2,000,000),i need to call MKL Pardiso to calculate Ax=b, but when running my program, i find the memory is increasing all the time till the program has to stop. &lt;BR /&gt;&lt;BR /&gt;Incidentally, i use MKL IA-32, static MKL, three libraries: libguide.lib mkl_c.lib mkl_solver.lib are linked. &lt;BR /&gt;&lt;BR /&gt;The following subroutine is called in loops: &lt;BR /&gt;subroutine Solver_MF2(N,A,B)&lt;BR /&gt; IMPLICIT NONE&lt;BR /&gt; integer(kinD=4)::N&lt;BR /&gt; real(kind=8),dimension(N,N)::A&lt;BR /&gt; real(kind=8),dimension(N)::B&lt;BR /&gt; real(kind=8),dimension(N)::X&lt;BR /&gt; &lt;BR /&gt; INTEGER*8 pt(64)&lt;BR /&gt; INTEGER maxfct, mnum, mtype, phase, nrhs, error, msglvl&lt;BR /&gt; INTEGER iparm(64)&lt;BR /&gt; integer,dimension(N+1)::ia&lt;BR /&gt; integer,allocatable::ja(:)&lt;BR /&gt; REAL*8,ALLOCATABLE::A_A(:)&lt;BR /&gt; &lt;BR /&gt; INTEGER I,j,K,IDUM&lt;BR /&gt; REAL*8 waltime1, waltime2, ddum&lt;BR /&gt; &lt;BR /&gt; DATA nrhs /1/, maxfct /1/, mnum /1/&lt;BR /&gt; K=0&lt;BR /&gt; do j=1,N&lt;BR /&gt; DO i=1,N&lt;BR /&gt; IF (A(I,J).NE.0.0) THEN&lt;BR /&gt; K=K+1&lt;BR /&gt; END IF &lt;BR /&gt; END DO &lt;BR /&gt; end do&lt;BR /&gt; &lt;BR /&gt; ALLOCATE(A_A(K));ALLOCATE(JA(K))&lt;BR /&gt; A_A=0.0;JA=0;K=0;i=1  &lt;BR /&gt; K=0;i=1&lt;BR /&gt; IA(I)=1&lt;BR /&gt; do i=1,N&lt;BR /&gt; DO J=1,N&lt;BR /&gt; IF(A(I,J).NE.0.0) THEN &lt;BR /&gt; K=K+1&lt;BR /&gt; A_A(K)=A(I,J)&lt;BR /&gt; JA(K)=J&lt;BR /&gt; END IF &lt;BR /&gt; END DO &lt;BR /&gt; IA(I+1)=K+1&lt;BR /&gt; end do &lt;BR /&gt;&lt;BR /&gt; mtype=11 !real unsymmetric&lt;BR /&gt; call pardisoinit(pt,mtype,iparm)&lt;BR /&gt; iparm(3)=2 ! number of processors&lt;BR /&gt;&lt;BR /&gt; phase = 11 ! only reordering and symbolic factorization &lt;BR /&gt; msglvl=0 !do not print &lt;BR /&gt; CALL pardiso (pt, maxfct, mnum, mtype, phase, N, A_A, ia, ja,idum, nrhs, iparm, msglvl, ddum, ddum, error) &lt;BR /&gt; &lt;BR /&gt; phase = 22 ! only factorization &lt;BR /&gt; CALL pardiso (pt, maxfct, mnum, mtype, phase, n, A_A, ia, ja, idum, nrhs, iparm, msglvl, ddum, ddum, error) &lt;BR /&gt;&lt;BR /&gt; iparm(8) = 2 ! max numbers of iterative refinement steps  &lt;BR /&gt;  phase = 33 ! only factorization &lt;BR /&gt; CALL pardiso (pt, maxfct, mnum, mtype, phase, n, A_A, ia, ja, idum, nrhs, iparm, msglvl, b
, x, error) &lt;BR /&gt;&lt;BR /&gt; phase = -1 ! release internal memory &lt;BR /&gt; CALL pardiso (pt, maxfct, mnum, mtype, phase, n, ddum, idum, idum,idum, nrhs, iparm, msglvl, ddum, ddum, error) &lt;BR /&gt; CALL MKL_FreeBuffers()&lt;BR /&gt; DEALLOCATE(A_A);DEALLOCATE(JA) &lt;BR /&gt;end &lt;BR /&gt;&lt;BR /&gt; &lt;BR /&gt;&lt;BR /&gt;</description>
      <pubDate>Tue, 12 Aug 2008 10:07:23 GMT</pubDate>
      <guid>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/memory-increasing-problem-calling-pardiso/m-p/905369#M11591</guid>
      <dc:creator>liubing84</dc:creator>
      <dc:date>2008-08-12T10:07:23Z</dc:date>
    </item>
    <item>
      <title>Re: memory increasing problem calling pardiso!</title>
      <link>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/memory-increasing-problem-calling-pardiso/m-p/905370#M11592</link>
      <description>&lt;P&gt;Hi,&lt;P&gt;&lt;/P&gt;&lt;/P&gt;
&lt;P&gt;Thank You for your question. The problemconcerning memory leakage in PARDISO is known.You didn't mention the MKL version butwe think thatit should be MKL 10.0 or MKL 10.1 Beta.This bughas been fixed recently and changes will be integrated innearest MKLbuilds.&lt;P&gt;&lt;/P&gt;&lt;/P&gt;
&lt;P&gt;With best regards,&lt;P&gt;&lt;/P&gt;&lt;/P&gt;
&lt;P&gt;Sergey&lt;/P&gt;</description>
      <pubDate>Fri, 22 Aug 2008 02:04:23 GMT</pubDate>
      <guid>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/memory-increasing-problem-calling-pardiso/m-p/905370#M11592</guid>
      <dc:creator>Sergey_P_Intel2</dc:creator>
      <dc:date>2008-08-22T02:04:23Z</dc:date>
    </item>
    <item>
      <title>Re: memory increasing problem calling pardiso!</title>
      <link>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/memory-increasing-problem-calling-pardiso/m-p/905371#M11593</link>
      <description>Thank you for your reply! &lt;BR /&gt;&lt;BR /&gt;Sorry,I forgot that. I use MKL 10.0.1.015. Does this version have a bug as you have said? And which version should I use? Thanks!&lt;BR /&gt;</description>
      <pubDate>Wed, 27 Aug 2008 02:52:58 GMT</pubDate>
      <guid>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/memory-increasing-problem-calling-pardiso/m-p/905371#M11593</guid>
      <dc:creator>liubing84</dc:creator>
      <dc:date>2008-08-27T02:52:58Z</dc:date>
    </item>
    <item>
      <title>Re: memory increasing problem calling pardiso!</title>
      <link>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/memory-increasing-problem-calling-pardiso/m-p/905372#M11594</link>
      <description>&lt;P&gt;&lt;SPAN&gt;Hi, I have to add 2 remarks: &lt;SPAN&gt;&lt;/SPAN&gt;&lt;P&gt;&lt;/P&gt;&lt;/SPAN&gt;&lt;/P&gt;
&lt;P&gt;&lt;SPAN&gt;1. Yes, the version you are using contains this error. The latest version MKL 10.0 Update 4 contains some fixes but not completely. This version is available from Intel Registration Center right now. We are planning to fix this problem completely in the next version MKL 10.1 Gold. We cannot provide the exact release date but it will be somewhere around November this year.&lt;P&gt;&lt;/P&gt;&lt;/SPAN&gt;&lt;/P&gt;
&lt;P&gt;&lt;SPAN&gt;2. you pointed that you are linking only &lt;/SPAN&gt;&lt;SPAN&gt;&lt;FONT face="Verdana"&gt;&lt;SPAN&gt;&lt;/SPAN&gt;three libraries: libguide.lib mkl_c.lib mkl_solver.lib.&lt;P&gt;&lt;/P&gt;&lt;/FONT&gt;&lt;/SPAN&gt;&lt;/P&gt;
&lt;P&gt;&lt;SPAN&gt;&lt;FONT face="Verdana"&gt;We are strongly recommend for Linking Pardiso the following libraies ( win32):&lt;P&gt;&lt;/P&gt;&lt;/FONT&gt;&lt;/SPAN&gt;&lt;/P&gt;
&lt;P&gt;&lt;SPAN&gt;mkl_solver.lib mkl_intel_c.lib mkl_intel_thread.lib mkl_core.lib libguide40.lib&lt;/SPAN&gt;&lt;P&gt;&lt;/P&gt;&lt;/P&gt;
&lt;P class="MsoNormal"&gt;&lt;FONT size="2"&gt;&lt;FONT face="Verdana"&gt;more details about linking exapmples and so on you can find in Userguide ( see chapter 5, for example ).&lt;P&gt;&lt;/P&gt;&lt;/FONT&gt;&lt;/FONT&gt;&lt;/P&gt;
&lt;P class="MsoNormal"&gt;&lt;P&gt;&lt;FONT face="Verdana" size="2"&gt;&lt;/FONT&gt;&lt;/P&gt;&lt;/P&gt;
&lt;P class="MsoNormal"&gt;&lt;FONT size="2"&gt;&lt;FONT face="Verdana"&gt;I hope it helps.&lt;P&gt;&lt;/P&gt;&lt;/FONT&gt;&lt;/FONT&gt;&lt;/P&gt;
&lt;P class="MsoNormal"&gt;&lt;FONT size="2"&gt;&lt;FONT face="Verdana"&gt;Regards, Gennady&lt;P&gt;&lt;/P&gt;&lt;/FONT&gt;&lt;/FONT&gt;&lt;/P&gt;</description>
      <pubDate>Wed, 03 Sep 2008 13:10:29 GMT</pubDate>
      <guid>https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/memory-increasing-problem-calling-pardiso/m-p/905372#M11594</guid>
      <dc:creator>Gennady_F_Intel</dc:creator>
      <dc:date>2008-09-03T13:10:29Z</dc:date>
    </item>
  </channel>
</rss>

