<html><head><meta http-equiv="Content-Type" content="text/html; charset=UTF-8"></head><body><div><font face="sans-serif">Hi, BTW, with Roland's help I did get things installed and running on Stampede2. Good luck! Joel Giedt </font></div><div><br></div><div><br></div><div><br></div><div id="composer_signature"><meta http-equiv="Content-Type" content="text/html; charset=UTF-8"><div style="font-size:85%;color:#575757">Sent from my Samsung Galaxy S8</div></div><div><br></div><div style="font-size:100%;color:#000000"><!-- originalMessage --><div>-------- Original message --------</div><div>From: 林家暉 <r06222015@ntu.edu.tw> </div><div>Date: 12/22/17 11:28 PM (GMT-05:00) </div><div>To: rhaas@ncsa.illinois.edu, Joel Giedt <giedtj@rpi.edu>, 'Roland Haas' <roland.haas@physics.gatech.edu> </div><div>Cc: users@einsteintoolkit.org </div><div>Subject: RE: [Users] questions about compilation </div><div><br></div></div>Dear Roland and Joel,<br>Thanks for your kindly reply.<br>I can use two other machines from my supervisor . They are the following:<br><br>1.NAOJ CfCA XC30 ,which is located in Tokyo ,Japan<br>https://www.nao.ac.jp/en/project/cfca.html<br><br>2.YITP XC40 ,which is located in Kyoto ,Japan <br>http://www2.yukawa.kyoto-u.ac.jp/~computer.room/cgi-bin/yitpinfo-web.cgi<br><br>Both of them are Cray machines , I think I will try NAOJ CfCA XC30 first and start with bluewaters-gnu files as you suggested.<br><br>If possible,please inform me if there is any updated progress on edison.<br>Thank you .<br>Best regards,<br>Chia Hui<br>________________________________________<br>從: Roland Haas [rhaas@illinois.edu]<br>寄件日期: 2017年12月23日 上午 01:37<br>至: Joel Giedt; 'Roland Haas'; 林家暉<br>副本: rhaas@ncsa.illinois.edu; users@einsteintoolkit.org<br>主旨: RE: [Users] questions about compilation<br><br>Hello Joel,<br><br>ohoh. Sorry to hear that you had so much trouble on stampede2. I think I have a set of working files for both its knl and skx partitions yet they may be only in the master or maybe even a separate (rhaas/stampede2) branch of simfactory.<br><br>Usually it is best to use a tested system yes. Also good is if the system has a fast queue turnaround time.<br><br>Yours,<br>Roland<br><br>On December 22, 2017 12:15:52 PM EST, Joel Giedt <giedtj@rpi.edu> wrote:<br>>Hi, I struggled for days trying to get ET installed on Stampede2 (no<br>>problems on Stampede1, so some issue about the different environment,<br>>which<br>>is supposed to be KNL oriented). It worked 100% with very little<br>>intervention on my part for Bridges, compiling in about an hour. On<br>>Stampede2, after some suggestions from various people I managed to get<br>>all<br>>the object files and libraries built for all the thorns, but then it<br>>didn't<br>>like a couple of the arguments being passed to ld, which are hard to<br>>fix<br>>because it's not at all obvious how to modify the make-cycle. I could<br>>go<br>>into all the details of snags I hit for anyone who is interested.<br>>Anyways,<br>>as Roland suggests, trying a different resource might be a very good<br>>idea<br>>because the process seems rather sensitive the local environment.<br>>--Joel<br>><br>>-----Original Message-----<br>>From: users-bounces@einsteintoolkit.org<br>>[mailto:users-bounces@einsteintoolkit.org] On Behalf Of Roland Haas<br>>Sent: Friday, December 22, 2017 12:05 PM<br>>To: 林家暉 <r06222015@ntu.edu.tw><br>>Cc: rhaas@ncsa.illinois.edu; users@einsteintoolkit.org<br>>Subject: Re: [Users] questions about compilation<br>><br>>Hello Chia Hui,<br>><br>>sorry for the long delay, I got caught up with Christmas preparations.<br>><br>>> It also took several hours for me to compile the code which should be<br>><br>>> down in 20 min. Did the similar situation occur when Edison is tested<br>><br>>> last time ?<br>>No I do not think that it took so long to compile on edison before. I<br>>am<br>>tempted to see if using the gnu compiler would be any faster. This is<br>>right<br>>now so painfully slow as to render the system almost unusable.<br>>it also does not help if one tries to compile in /dev/shm or from<br>>within an<br>>interactive job so the "usual" remedies for slow compilation do not<br>>apply.<br>><br>>> Actually there are two other clusters I can use. But they are not<br>>> supported by Einstein toolkit . I have tried to compile the code on<br>>> them but failed since the required information for a new cluster is<br>>> quite detailed and I cannot find all of them. Will you suggest me to<br>>> shift to another cluster which is unsupported ?<br>>If you want to use a different cluster then I would try and start from<br>>the<br>>files for a similar, working one. Eg for Cray machines the<br>>bluewaters-gnu<br>>files are a good starting point or maybe the cori ones (it being a<br>>newer<br>>cray).<br>><br>>We have a wiki page:<br>><br>>https://docs.einsteintoolkit.org/et-docs/Configuring_a_new_machine<br>><br>>that describes the procedure and would be happy to help out on the<br>>mailing<br>>list (or on the system if one of us has an account there).<br>><br>>Yours,<br>>Roland<br>><br>>--<br>>My email is as private as my paper mail. I therefore support encrypting<br>>and<br>>signing email messages. Get my PGP key from http://keys.gnupg.net.<br><br>--<br>Sent from my Android device with K-9 Mail. Please excuse my brevity.<br></body></html>