The commercial version of MKL lets you redistribute the library. There isn't much else really but I guess that means you can't redistribute the headers and documentation. I guess Intel is not much concerned about possible piracy by research institutes. In fact, I don't understand why Intel isn't giving the MKL away for free, they are in the hardware business after all. Probably not enough competition from AMD
I'm not quite clear if that binary distribution would be compatible with the GPL. I take it its a "borderline case". See http://www.gnu.org/licenses/gpl-faq.html#GPLAndPlugins: ---------------------------------------------------- If a program released under the GPL uses plug-ins, what are the requirements for the licenses of a plug-in? (#GPLAndPlugins) It depends on how the program invokes its plug-ins. If the program uses fork and exec to invoke plug-ins, then the plug-ins are separate programs, so the license for the main program makes no requirements for them. If the program dynamically links plug-ins, and they make function calls to each other and share data structures, we believe they form a single program, which must be treated as an extension of both the main program and the plug-ins. This means the plug-ins must be released under the GPL or a GPL-compatible free software license, and that the terms of the GPL must be followed when those plug-ins are distributed. If the program dynamically links plug-ins, but the communication between them is limited to invoking the ‘main’ function of the plug-in with some options and waiting for it to return, that is a borderline case. ---------------------------------------------------- In any case it would be nice to have access to MKL even if only to make sure that you can link to it in the privacy of your own home. On Tuesday, December 25, 2012 7:38:48 AM UTC, jason wrote: > > On 12/23/12 11:37 AM, Volker Braun wrote: > > On a related note, does anybody know MAGMA (not the number theory > > system, silly). The BLAS implementation, aka Matrix Algebra on GPU and > > Multicore Architectures: http://icl.cs.utk.edu/magma/ > > > > I've been keeping an eye on MAGMA and PLASMA. > > Also, the other day, Ralph Gommers announced on the scipy list [1] that > Intel was offering free MKL licenses for building/testing scientific > python software (specifically, stuff listed at > http://numfocus.org/projects-2/projects/). In a later message [2], he > said Intel would be pleased if they offered binaries for download that > were built against MKL. I assume this means the end-user would still > have to have an MKL license; if so, it doesn't completely resolve the > ATLAS/OpenBLAS issue in this thread. However, as long as we are talking > about switching BLAS implementations, it might be interesting to also > look at what it would take to build against MKL. If there is interest, > we might try asking Intel about the same sort of deal for distributing > Sage binaries built against MKL. > > Thanks, > > Jason > > > [1] > http://thread.gmane.org/gmane.comp.python.numeric.general/52372/focus=52455 > > [2] > http://thread.gmane.org/gmane.comp.python.numeric.general/52372/focus=52455 > > > > -- You received this message because you are subscribed to the Google Groups "sage-devel" group. To post to this group, send email to sage-devel@googlegroups.com. To unsubscribe from this group, send email to sage-devel+unsubscr...@googlegroups.com. Visit this group at http://groups.google.com/group/sage-devel?hl=en.
