[P4-dev] General question on P4

Andy Fingerhut andy.fingerhut at gmail.com
Sat Apr 8 17:44:36 EDT 2017

Except for one thing, everything you said sounds good to me.

The one exception is that I haven't heard the term NPU used to include the
part of the system that runs the control plane code.  In my experience
those are called Supervisor CPUs, control plane CPU, or route processor
CPU, but no matter which of those names you call them, they tend to be
off-the-shelf PowerPC, MIPS, Intel, or Arm CPUs, the same kind you would
find in servers or embedded devices.

NPU I have usually heard to mean some kind of highly programmable device
that is tailored for packet forwarding, similar to the categories of ASICs
you mention for packet forwarding.  Often they are even more flexible in
what they can do, but at a significant cost in lower packet rate per chip
than other networking ASICs.  They often allow even more flexibility than
even the programmable ASICs, e.g. can run code that processes every byte of
the payload, whereas even the programmable networking ASICs tend to focus
on flexibility in packet headers.


On Sat, Apr 8, 2017 at 1:38 PM, Rommel Bajamundi <rommel at bajamundi.com>

> Ok... I would like to understand this better.  It is my understanding:
> NPU = router processor, executes control plane (CP), a type of integrated
> circuit(IC)
> ASIC= chipset with some prebuilt pipeline to do stuff to offload NPU, I.e.
> Bit Torrent algorithm built into IC, to offload compute and or GPU
> resources do the math on the ASIC. Or  Instead of asking NPU where to
> forward packets, define a FIB that can be part of the packet parsing
> pipeline to do a lookup and forward.
> Fixed pipeline ASIC = pre-built parsing and decision tree to accelerate DP
> forwarding
> Flexible pipeline ASIC= some ability to modify the flow through decision
> tree, but not necessarily the ability to change headers parsed with some
> offloaded functionality that balances speed and features,
> Programmable ASIC= highest flexibility, flexible parser
> P4 = higher layer programming language built to define data plane parser,
> still needs some NPU for programmatic decisions
> It is my understanding that, Tofino, gave you the flexibility to do stuff
> on DP I.e send some log even based on ingress packet, or parse 10 bytes
> after offset 0x08 and lookup, parse a header like GTP and store it as part
> of your EcMP hash.
> Benefits:
> -Portable code, assuming P4 capable ASIC was same P4 version
> - Flexible parser.... mobile guys can parse GTP now, or craft VxLAN over
> IPv6 can be done without waiting for support.
> I would liken this to modern day switching using Broadcom or mellanox with
> intel as NPU.  Intel does all the determining of FIB and calculating RIB
> and putting those into tables that the ASIC deals with.
> I am not a programmer or Hw engineer.   But this is how I understand it.
> It was my assumption that the value of Tofino is its ability to have a long
> lifecycle due to the programmability, address unsupported protocols by
> current vendors, & address new protocols created.  One would only need
> chassis upgrades if pps runs out.
> Rommel
> On Apr 8, 2017, at 1:48 PM, Michael Borokhovich <michaelbor at gmail.com>
> wrote:
> Hi Andy,
> Thank you for the insight. If this is the performance difference, then of
> course the advantage of P4 ASIC (e.g., Tofino) is obvious. I see that
> EZchip NP5 supports 300 millions packets per second. But I didn't find a
> similar spec for Tofino. Also, this comparison should be done for
> comparable programs since each additional piece of functionality
> (parsing/modifying an additional header field or doing an additional table
> search) affects this pps metrics.
> But again, if Tofino indeed achieves ~10 times more pps than e.g., EZchip
> NP5 for the same program, than I clearly see the benefit and the novelty.
> Michael.
> On Fri, Apr 7, 2017 at 5:52 PM, Andy Fingerhut <andy.fingerhut at gmail.com>
> wrote:
>> In case it isn't obvious, max packet rate that you can achieve in an ASIC
>> turns into a significant difference in cost when buying the equipment and
>> paying the power bill for a network.
>> Suppose you have a choice of a programmable ASIC that goes at 2 billion
>> packets per second, and an NPU that goes up to 200 million packets per
>> second, and they both cost roughly the same amount and consume the same
>> power.
>> You have some part of a data center connecting a bunch of hosts together
>> where you decide that kind of programmability is important.  You do some
>> calculations to determine those hosts need 200 billion packets per second
>> of forwarding capacity between them.
>> Do you want buy and provide power for 200/2 = 100 fast programmable
>> ASICs, or 200/.2 = 1,000 programmable NPUs?
>> Andy
>> On Fri, Apr 7, 2017 at 2:37 PM, Andy Fingerhut <andy.fingerhut at gmail.com>
>> wrote:
>>> I don't have experience with all NPUs, but many I have seen top out on
>>> the order of hundreds of millions of packets per second with current
>>> technology.
>>> With the same current technology, it is possible to design fixed
>>> function ASICs, and programmable ASICs like Barefoot's Tofino, that achieve
>>> billions of packets per second.
>>> The main difference that I am aware of is that many NPUs are based on
>>> parallel arrays of 32-bit or 64-bit processor cores, and each core requires
>>> many cycles for things like constructing table search keys and performing
>>> side effects on the 'packet vector' (state maintained while forwarding the
>>> packet about that packet only).  If you want to go at billions of packets
>>> per second, the only way I know to get there is to have fixed or
>>> configurable hardware that can do those things in 1 or 2 clock cycles per
>>> packet.
>>> You can write a compiler that compiles a P4 program to run on an NPU as
>>> described above, and it will achieve portability of the P4 program, but it
>>> won't make that NPU able to go at billions of packets per second.  It is
>>> limited in performance by its hardware architecture.
>>> There are proprietary methods for programming some ASICs that can go at
>>> billions of packets per second, but all that I know of are lower level than
>>> P4 and non-portable.
>>> Andy
>>> On Thu, Apr 6, 2017 at 6:37 PM, Michael Borokhovich <
>>> michaelbor at gmail.com> wrote:
>>>> Hi Remy,
>>>> I'm not confusing hardware with the language... What I mean is that P4
>>>> + ASIC that supports it claims to give us programmable data-plane and this
>>>> is claimed to be the innovation. But that is exactly the purpose of NPUs -
>>>> to give us programmable data-plane and NPUs are around for a very long
>>>> time. So maybe I'm missing the point of innovation that P4 + ASIC that
>>>> supports it gives. As Nate said, and I agree, one big advantage is
>>>> portability and the other - ability to do verification.
>>>> So, P4 brings kind of an open standard for programmable ASICs which is
>>>> analogous to a programming language (e.g., C) for regular CPUs. While each
>>>> NPU currently have its own language and a programming style.
>>>> What do you think?
>>>> Thanks,
>>>> Michael.
>>>> On Thu, Apr 6, 2017 at 2:07 PM, Remy Chang <remy at barefootnetworks.com>
>>>> wrote:
>>>>> Hi Michael,
>>>>> It seems you're conflating hardware with language.  NPU, programmable
>>>>> ASIC, general purpose CPU, and even GPU can all potentially execute p4
>>>>> code.
>>>>> Regards,
>>>>> Remy
>>>>> On Apr 6, 2017 10:57, "Michael Borokhovich" <michaelbor at gmail.com>
>>>>> wrote:
>>>>> Thanks for the reply Nate!
>>>>> So, to summarize, the benefits of P4 approach are: portability and
>>>>> performance. Other than that you probably can achieve the same (if not
>>>>> better) flexibility/programmability with an NPU. Is this correct?
>>>>> On Thu, Apr 6, 2017 at 1:01 AM, Nate Foster <jnfoster at cs.cornell.edu>
>>>>> wrote:
>>>>>> Your question seems to be more about the relative merits of various
>>>>>> architectures than the P4 language. But yes an ASIC is generally more
>>>>>> efficient than an NPU, at least at scale.
>>>>>> Beyond efficiency there are other benefits to expressing a data plane
>>>>>> algorithm in an open framework like P4. For example, a P4 programs should
>>>>>> be relatively easy to port to a different target. The same is unlikely to
>>>>>> be true for C programs written against closed SDKs.
>>>>>> -N
>>>>>> On Wed, Apr 5, 2017 at 6:59 PM, Michael Borokhovich <
>>>>>> michaelbor at gmail.com> wrote:
>>>>>>> Hi,
>>>>>>> P4 allows for configurable data-plane, e.g., we can easily support
>>>>>>> new custom protocols. However, the same functionality may be achieved by
>>>>>>> using a network processor, e.g., EZchip (the one I had experience with).
>>>>>>> As I understand, the advantages of programmable ASIC/FPGA that
>>>>>>> supports P4 is better performance and a lower price than a network
>>>>>>> processor?
>>>>>>> What do you think?
>>>>>>> Thanks!
>>>>>>> Michael.
>>>>>>> _______________________________________________
>>>>>>> P4-dev mailing list
>>>>>>> P4-dev at lists.p4.org
>>>>>>> http://lists.p4.org/mailman/listinfo/p4-dev_lists.p4.org
>>>>> _______________________________________________
>>>>> P4-dev mailing list
>>>>> P4-dev at lists.p4.org
>>>>> http://lists.p4.org/mailman/listinfo/p4-dev_lists.p4.org
>>>> _______________________________________________
>>>> P4-dev mailing list
>>>> P4-dev at lists.p4.org
>>>> http://lists.p4.org/mailman/listinfo/p4-dev_lists.p4.org
> _______________________________________________
> P4-dev mailing list
> P4-dev at lists.p4.org
> http://lists.p4.org/mailman/listinfo/p4-dev_lists.p4.org
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.p4.org/pipermail/p4-dev_lists.p4.org/attachments/20170408/755a1452/attachment-0002.html>

More information about the P4-dev mailing list