> The patchset introuduces IPv6 optimized MFEX profiles > with AVX512 which can deliver upto 20% to 30% gain in > performance over the existing scalar data-path. > > Hashing Optimization are also included which can further > improve performance by approximately 10%. > > The patch also removes the magic numbers for MF bits, packet offsets > and packet lenghts.
Thanks for the patch series Amber & Harry. Have been testing this the last few days and it looks good to me. I've applied the series to master with a few modifications (I removed the entry from NEWS as we didn't add an entry for the IPv4 optimizations that were merged previously, so I think it makes sense to do the same thing here, also fixed a few typos in commit messages). Thanks Ian > > --- > v11: > - Rebase on top of AVX512 runtime ISA check patch. > v10: > - Reabse onto Cian Partial AVX512 build patch. > v9: > - Fix Ubsan un-alinged memory load. > v8: > - Rename packet offsets defines to aling with packet struct. > v7: > - Remove magic numbers from AVX512 Profiles. > v5: > - Add Ipv6 and TCP packet length checks. > v4: > - rebase to master. > - use static key lenghts for different packet types. > v3: > - rebase to master. > v2: > - fix the CI build. > - fix check-patch for co-author. > --- > > Kumar Amber (4): > mfex_avx512: Calculate pkt offsets at compile time. > mfex_avx512: Calculate miniflow_bits at compile time. > dpif-netdev/mfex: Add AVX512 ipv6 traffic profiles > dpif-netdev/mfex: Add ipv6 profile based hashing. > > NEWS | 4 + > acinclude.m4 | 1 + > lib/automake.mk | 5 +- > lib/dp-packet.h | 43 ++++ > lib/dpif-netdev-extract-avx512.c | 349 > +++++++++++++++++++++++++++++- > lib/dpif-netdev-private-extract.c | 51 ++++- > lib/dpif-netdev-private-extract.h | 20 ++ > lib/flow.c | 4 + > 8 files changed, 463 insertions(+), 14 deletions(-) > > -- > 2.25.1 _______________________________________________ dev mailing list d...@openvswitch.org https://mail.openvswitch.org/mailman/listinfo/ovs-dev