topic Basic Code of Using MKL FFT on MIC in IntelĀ® oneAPI Math Kernel Library
https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/Basic-Code-of-Using-MKL-FFT-on-MIC/m-p/1019980#M19675
<PRE class="brush:cpp;"> </PRE>
<P>Hello,</P>
<P>In our local cluster we have a bunch of MIC's, which are (almost) never esed. I would like to give it the try, but I have no experience iwth the MKL library or MIC. My programs are very simple and they are based on FFT:</P>
<P>I have an iterative process in which the smae update procedure is applied to the previous data:</P>
<PRE class="brush:cpp;">// initialize data rho[lx]
for(t=0;t<tmax;t++)
{
// first step in real space is local
for(i=0;i<lx;i++)
{
nt(i)=rho<I>*rho<I>*rho<I>;
}
//forward FFT rho->rhok
//forward FFT nt-> ntk
//update in k space
for(i=0;i<lx/2+1;i++)
{
newrhok(i)=filter1(i)*rhok(i)+filter2(i)*ntk(i); // complex multiplication
}
//inverse FFT newrhok->newrho
</I></I></I></PRE>
<P>So my problem is how to ues MKL FFT's on MIC's and how minimize the transfers between cpu and MIC.</P>
<P>I hope this is the right forum and many thanks in advance</P>
<P>Cristian</P>
<P> </P>Thu, 11 Dec 2014 12:06:42 GMTCristian_Vasile_A_2014-12-11T12:06:42ZBasic Code of Using MKL FFT on MIC
https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/Basic-Code-of-Using-MKL-FFT-on-MIC/m-p/1019980#M19675
<PRE class="brush:cpp;"> </PRE>
<P>Hello,</P>
<P>In our local cluster we have a bunch of MIC's, which are (almost) never esed. I would like to give it the try, but I have no experience iwth the MKL library or MIC. My programs are very simple and they are based on FFT:</P>
<P>I have an iterative process in which the smae update procedure is applied to the previous data:</P>
<PRE class="brush:cpp;">// initialize data rho[lx]
for(t=0;t<tmax;t++)
{
// first step in real space is local
for(i=0;i<lx;i++)
{
nt(i)=rho<I>*rho<I>*rho<I>;
}
//forward FFT rho->rhok
//forward FFT nt-> ntk
//update in k space
for(i=0;i<lx/2+1;i++)
{
newrhok(i)=filter1(i)*rhok(i)+filter2(i)*ntk(i); // complex multiplication
}
//inverse FFT newrhok->newrho
</I></I></I></PRE>
<P>So my problem is how to ues MKL FFT's on MIC's and how minimize the transfers between cpu and MIC.</P>
<P>I hope this is the right forum and many thanks in advance</P>
<P>Cristian</P>
<P> </P>Thu, 11 Dec 2014 12:06:42 GMThttps://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/Basic-Code-of-Using-MKL-FFT-on-MIC/m-p/1019980#M19675Cristian_Vasile_A_2014-12-11T12:06:42ZCristian,
https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/Basic-Code-of-Using-MKL-FFT-on-MIC/m-p/1019981#M19676
<P>Cristian,</P>
<P>The best way to to learn how to use MKL for Xeon Phi - to look at the examples which were prepared special for such sort of questions.</P>
<P>in particular for FFT - you can find such example into "<mkl_root>\examples\mic_offload\dftc\" </P>
<P>--Gennady</P>Fri, 12 Dec 2014 08:29:44 GMThttps://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/Basic-Code-of-Using-MKL-FFT-on-MIC/m-p/1019981#M19676Gennady_F_Intel2014-12-12T08:29:44ZQuote:Gennady Fedorov (Intel)
https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/Basic-Code-of-Using-MKL-FFT-on-MIC/m-p/1019982#M19677
<P></P><BLOCKQUOTE>Gennady Fedorov (Intel) wrote:<BR /><P></P>
<P>Cristian,</P>
<P>The best way to to learn how to use MKL for Xeon Phi - to look at the examples which were prepared special for such sort of questions.</P>
<P>in particular for FFT - you can find such example into "<mkl_root>\examples\mic_offload\dftc\" </P>
<P>--Gennady</P>
<P></P></BLOCKQUOTE><P></P>
<P> </P>
<P>Hello,</P>
<P> </P>
<P>Thank you for your reply. I will check the examples on our cluster.</P>Fri, 12 Dec 2014 14:34:00 GMThttps://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/Basic-Code-of-Using-MKL-FFT-on-MIC/m-p/1019982#M19677Cristian_Vasile_A_2014-12-12T14:34:00Z