[dpdk-dev] [PATCH v2] Implement memcmp using AVX/SSE instructions.

[Jay Rolette]

On Tue, May 12, 2015 at 8:16 PM, Ravi Kerur <rkerur at gmail.com> wrote:

> On Mon, May 11, 2015 at 3:29 PM, Don Provan <dprovan at bivio.net> wrote:
>
> > I probably shouldn't stick my nose into this, but I can't help myself.
> >
> > An experienced programmer will tend to ignore the documentation for
> > a routine named "blahblah_memcmp" and just assume it functions like
> > memcmp. Whether or not there's currently a use case in DPDK is
> > completely irrelevant because as soon as there *is* a use case, some
> > poor DPDK developer will try to use rte_memcmp for that and may or
> > may not have a test case that reveals their mistake.
> >
>
> In general I agree with you. However, comparison is a hit(equal) or
> miss(unequal) is generally the case in networking. I haven't seen cases
> where "less than" or "greater than" has mattered.
>

It's useful when you need to make sure packets from both sides of a
conversation go to the same processing queue/thread. Instead of hashing the
5-tuple from the packet as src.ip, dst.ip, src.dport, dst.dport, etc., you
can use lesser.ip, higher.ip, lesser.sport, higher.dport, etc.

Very common when you are doing deep packet inspection.

Jay