Hi Vipin,
> -----Original Message----- > From: Varghese, Vipin > Sent: Thursday, December 6, 2018 2:26 PM > To: Lu, Wenzhuo <wenzhuo...@intel.com>; dev@dpdk.org > Subject: RE: [dpdk-dev] [PATCH v2 19/20] doc: add ICE description and > update release note > > snipped > > > > > Thanks Wenzhuo > > > > > > > > > > snipped > > > > > > > > > > > > > > Do we support Traffic Manager and Inline Crypto? If not, can > > > > > > > we add this also to limitations? > > > > > > The style is only listed supported features here. I don't > > > > > > think we'll list everything not supported as limitation. > > > > > Thanks for the correction in format, hence the suggested action > > > > > item is update limitation section to state what is not supported. > > > > > > > > > > > The same below. > > > > > > > > > > > > > > > > > > > > > +FW version = Y > > > > > > > > +Module EEPROM dump = Y > > > > > > > > +Multiprocess aware = Y > > > > > > > > +BSD nic_uio = Y > > > > > > > > +Linux UIO = Y > > > > > > > > +Linux VFIO = Y > > > > > > > > +x86-32 = Y > > > > > > > > +x86-64 = Y > > > > > > > > > > > > > > Is cross compile for ARM and PPC disabled since it uses > > > > > > > Intel specific > > > ISA? > > > > > > > Should this be added to limitations? > > > > > Is powerpc and arm cross build with non avx and sse ISA supported? > > > > > If no, will default '.config' has 'ICE_PMD=n'? > > > > Yes, it should be. Currently at least all the Intel NICs set 'y' here. > > > > If any problem, we should handle it as bug. > > > So my understanding from 'yes' is ICE_DSI PMD is having minimum > > > scalar functions which is cross build successful for ARM and > > > powerpc. Hence you are leaving it as '=y' like other NIC. > > > > > > If above is true, why is arm and PowerPC not added to your > documentation? > > It's a good question. If you check the history, you'll find the arm > > and powerpc support is updated by the arm and powerpc maintainers. It > > means ideally we believe it supports these platforms, but we don't > > have any of these platform to confirm that. > Perfect, please add the right team members in 'to' so they can update the > same. Good suggestion. I'll cc them when sending the new version. But we cannot expect there's a quick update because ice is a new device. > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > Snipped > > > > > > > > > > > > > > > + > > > > > > > > +Config File Options > > > > > > > > +~~~~~~~~~~~~~~~~~~~ > > > > > > > > + > > > > > > > > +The following options can be modified in the ``config`` file. > > > > > > > > +Please note that enabling debugging options may affect > > > > > > > > +system > > > > > > > performance. > > > > > > > > > > > > > > Do we see real performance variance? If yes, can we > > > > > > > highlight this in info section? > > > > > > IMH, we could get different numbers because of different scenarios. > > > > > > It's only a reminder to not enable debug. > > > > > Thanks, but then wording should 'Note: enabling debug option for > > > > > ICE will have difference in performance. Hence recommendation is > > > > > not to enable unless for debugging the ICE PMD.' > > > > > > > > > > > > > > > > > > > > snipped
