I would be very interested on the data set (and exact command) you used that exhibited a 25% speed up. Because our tests showed little to no improvement in run time when using the -march=core-avx2 during compiling.
-Zeke > Oh PS, AVX gives about 25% speed up compared to SSE. Would it be useful > for me to send the data that it segfaults on? > > -----Original Message----- > From: freesurfer-boun...@nmr.mgh.harvard.edu > [mailto:freesurfer-boun...@nmr.mgh.harvard.edu] On Behalf Of Z K > Sent: Tuesday, 23 June 2015 1:50 AM > To: Freesurfer support list > Subject: Re: [Freesurfer] Segmentation fault in mris_fix_topology when > compiling with gcc 4.8 + AVX2 > > Thank you for this information. > > -Zeke > > On 06/22/2015 02:22 AM, Chris Adamson wrote: >> Everyone, >> >> I know this is a fairly specific issue but nonetheless. >> >> If you compile Freesurfer 5.3.0 with the option -march=core-avx2 with >> gcc 4.8 it can cause mris_fix_topology to segfault at >> utils/mrisurf.c:64770 mrisCopyDefectPatch >> >> gcc 4.9 also does the same thing. >> >> If you still use AVX but disable AVX2, i.e. use -march=core-avx-i then >> it does not segfault. >> >> Just something to keep in mind. >> >> *Dr **Chris Adamson >> *Research Officer, Developmental Imaging, *Murdoch Childrens Research >> Institute *Murdoch Childrens Research Institute Royal Children's >> Hospital Flemington Road, Parkville, Victoria 3052, Australia >> www.mcri.edu.au <http://www.mcri.edu.au/> >> >> E chris.adam...@mcri.edu.au >> T 03 9936 6780 >> >> >> ______________________________________________________________________ >> This email has been scanned by the Symantec Email Security.cloud >> service. >> For more information please visit http://www.symanteccloud.com >> ______________________________________________________________________ >> >> >> _______________________________________________ >> Freesurfer mailing list >> Freesurfer@nmr.mgh.harvard.edu >> https://mail.nmr.mgh.harvard.edu/mailman/listinfo/freesurfer >> > _______________________________________________ > Freesurfer mailing list > Freesurfer@nmr.mgh.harvard.edu > https://mail.nmr.mgh.harvard.edu/mailman/listinfo/freesurfer > > > The information in this e-mail is intended only for the person to whom it > is addressed. If you believe this e-mail was sent to you in error and the > e-mail contains patient information, please contact the Partners > Compliance HelpLine at http://www.partners.org/complianceline . If the > e-mail was sent to you in error but does not contain patient information, > please contact the sender and properly dispose of the e-mail. > > ______________________________________________________________________ > This email has been scanned by the Symantec Email Security.cloud service. > For more information please visit http://www.symanteccloud.com > > If you have any questions, please contact MCRI IT Servicedesk for further > assistance. > ______________________________________________________________________ > > ______________________________________________________________________ > This email has been scanned by the Symantec Email Security.cloud service. > For more information please visit http://www.symanteccloud.com > ______________________________________________________________________ > > _______________________________________________ > Freesurfer mailing list > Freesurfer@nmr.mgh.harvard.edu > https://mail.nmr.mgh.harvard.edu/mailman/listinfo/freesurfer > > > _______________________________________________ Freesurfer mailing list Freesurfer@nmr.mgh.harvard.edu https://mail.nmr.mgh.harvard.edu/mailman/listinfo/freesurfer
