Re: [dpdk-dev] [PATCH v4 0/3] add lpm support for NEON

["Kobylinski, MichalX" <michalx.kobylinski@intel.com>]

> -----Original Message-----
> From: Jerin Jacob [mailto:jerin.jacob@caviumnetworks.com]
> Sent: Tuesday, February 16, 2016 5:44 PM
> To: Kobylinski, MichalX <michalx.kobylinski@intel.com>
> Cc: dev@dpdk.org; viktorin@rehivetech.com
> Subject: Re: [dpdk-dev] [PATCH v4 0/3] add lpm support for NEON
> Importance: High
> 
> On Tue, Feb 16, 2016 at 01:27:02PM +0000, Kobylinski, MichalX wrote:
> >
> >
> > > -----Original Message-----
> > > From: dev [mailto:dev-bounces@dpdk.org] On Behalf Of Jerin Jacob
> > > Sent: Friday, February 12, 2016 1:29 PM
> > > To: dev@dpdk.org
> > > Cc: viktorin@rehivetech.com
> > > Subject: [dpdk-dev] [PATCH v4 0/3] add lpm support for NEON
> > >
> [snip]
> > >
> > > Jerin Jacob (3):
> > >   lpm: make rte_lpm_lookupx4 API definition architecture agnostic
> > >   lpm: add support for NEON
> > >   maintainers: claim responsibility for arm64 specific files of hash and
> > >     lpm
> > >
> > >  MAINTAINERS                                |   3 +
> > >  app/test/test_lpm.c                        |  21 ++--
> > >  app/test/test_xmmt_ops.h                   |  67 +++++++++++++
> > >  config/defconfig_arm-armv7a-linuxapp-gcc   |   3 -
> > >  config/defconfig_arm64-armv8a-linuxapp-gcc |   3 -
> > >  lib/librte_lpm/Makefile                    |   6 ++
> > >  lib/librte_lpm/rte_lpm.h                   |  99 ++-----------------
> > >  lib/librte_lpm/rte_lpm_neon.h              | 148
> +++++++++++++++++++++++++++++
> > >  lib/librte_lpm/rte_lpm_sse.h               | 143
> ++++++++++++++++++++++++++++
> > >  9 files changed, 386 insertions(+), 107 deletions(-)  create mode
> > > 100644 app/test/test_xmmt_ops.h  create mode 100644
> > > lib/librte_lpm/rte_lpm_neon.h create mode 100644
> > > lib/librte_lpm/rte_lpm_sse.h
> > >
> > > --
> > > 2.1.0
> >
> > Hi Jerin,
> 
> Hi Michal,
> 
> > Are you planning increase next_hop field for ARM? I extended next_hop field
> from 8 bits to 24 bits and created structure to configure LPM for x86.
> 
> Yes, I am planning to increase next_hop field for ARM as a separate patch.  Let
> this base patchset get merges.
> 
> I will make  ARM specific changes for your new feature in 'rte_lpm_lookupx4' as
> a separate patch on top of your series.
> So that in case if I want to go back to 8 bit then I can do it
> 
> Jerin

Thank you for your answer.
Do you prepare separate patch with changes for ARM architecture on the top my series?
If you want I can support you with prepare new patch.

Michal

> 
> > Please look at my patchset with proposal increase next_hop field and structure
> to configure.
> >
> > http://patchwork.dpdk.org/dev/patchwork/patch/10249/
> > http://patchwork.dpdk.org/dev/patchwork/patch/10250/
> >
> > Best Regards,
> > Michal
> >