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

Ravi Kerur rkerur at gmail.com
Wed May 13 22:07:03 CEST 2015


On Wed, May 13, 2015 at 5:21 AM, Jay Rolette <rolette at infiniteio.com> wrote:

> 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.
>

Thanks for sharing this information.

>
> Jay
>


More information about the dev mailing list