Oct/097
On Merchant Silicon and Lawnmowing
Custom or Merchant Silicon?
Hello there!
I've been on a bit of a vacation the past couple of weeks, so sorry for the slow-down in posting frequency. But now, I am back at my desk, with a decent speed Internet connection, and too many ideas on what to write about.
---------
Chance had it that today a friend of mine sent me an email reminding me of a blog post I wrote about a year and a half ago titled - 'On Merchant Silicon and Mowing my Yard.' It was a piece, purposefully a bit inflammatory, designed to have a bit of a go at the guys who were drawing some interesting comparisons to product lines I worked on.
As often happens, times change.
Reading this email which spoon-fed my prior writings back to me, I had to reflect a bit. Does merchant silicon matter? Is it a sell out? What creates customer value in a networking product? Is it the silicon, the software, the system as a whole, how it operates with other adjacent products, etc...
Realistically, to me, what most people seem to care about in a switch is that it works, at the performance rates necessary, and that the software is stable and has the features they need to accomplish the networking task at hand.
Inside this system there is a collection of silicon, some of which may be custom, some which comes from vendors other than the systems manufacturer. The PHYs are almost always 3rd party, the CPUs as well, most every part is always 'merchant silicon' except the switch fabric and the packet processor. These are custom in some switches, or merchant in others depending on that specific vendors goals for that particular product.
Ethernet continues to evolves and offers lots of opportunities for innovation and improvement - some of these will require new silicon, some will require new software. Using merchant silicon sometimes will affect a vendors ability to control the pace and order they bring features to market that require new silicon. However, with the breadth of silicon available in the market today there are several viable silicon choices.
Custom chips create their own set of challenges - most vendors doing their own chips actually do their own logic and rely on a third party to actually build the chips and fab them out, deal with the process challenges, etc. The vendors doing full custom take on a high cost burden up front and hope they get enough market traction to enable future R&D in their ASIC teams. In this period of compressed budgets these programs tend to be one of the first things to get financial focus. What do you think- is one better than the other, or is a healthy mix appropriate for our maturing industry?
P.S. Oh, and I outsourced yard mowing... too time consuming and others did a better job than I ever could.
Author: Douglas Gourlay
high-tech executive with interests in networking, virtualization, cloud computing, and IT/Tech government policy. VP of Marketing at Arista Networks - this blog reflects Doug's personal views and opinions and not necessarily those of Arista Networks.Additional comments powered by BackType
default gateway
- Vendor Math September 18, 2009
- Implications of Virtualization and Cloud August 19, 2009
- Virtualization's Impact on Networks August 6, 2009
- Brad Reese, PR's Worst Nightmare August 5, 2009
- Hello World, and Random Career Thoughts August 4, 2009
October 20th, 2009
Nice retort. I thought I might get an e-mail back but who knew that you had so much time to blog? And you’re just back from vacation?
I wonder what other old post of yours I can find???
October 21st, 2009
Oh I am sure there are some out there lurking for you to find my friend! Had a great vacation – btw am in your neck of the woods next week if you’re around.
October 21st, 2009
You know what changed my friend – I think more than anything I have seen in some vendors that core product line investment levels get funding in almost a sine-wave fashion. Once the product ships then the funding levels are reduced or flat-lined and then the team is never funded to stay current on ASIC processes and such. Over time you have products with very old ASIC architectures which end up taking a lot of power for little performance gain.
What really scared me into an awakening is seeing the investment levels ‘pure play’ networking silicon companies like Broadcom, Fulcrum, Marvell, Dune, etc are putting into their chipsets. They are using very cutting edge processes, 45nm etc, and doing so with 100’s and sometimes 1000’s of engineers working on the chipsets. This level of investment results in extremely capable silicon that is designed with quite flexible packet processing engines that can be re-purposed for many different networking applications. It’s not a one-size fits all, but with the maturation of the market there are pretty capable silicon systems available that are quite programmable and solve a good chunk of the networking use-cases.
dg
October 20th, 2009
I guess a healthy mix makes sense, but then again I don’t outsource my yard work…
Well-written post, DG!
October 20th, 2009
Doug,
You knew this would eventually come back to bite you, it always does in networking architectures
Jump in the way-back machine and see Welfleet distributed processing vs. Cisco 7000s with a single RP…and then Cisco moved to VIPs and distributed processing (GSR, etc.). Kalpana originally did cut-through switching, until networks melted because of bad CRCs, so we went back to fast bridging (aka Store-Forward Switching) and now I hear that people want to go back to cut-through again for latency. Somewhere I’m sure there are people at Cisco that are upset about the original Granite K1 chip that was considered impossible to manufacture, and Andy has probably taken those lessons along to Arista.
It’s all cyclical. What you bash today will be what you’re pitching in 24 months. Just remember Gracely’s Theorem of Technology – “There are no great new ideas, just reapplication of old ideas on newer CPUs and bigger bandwidth”.
October 21st, 2009
Well said Brian! I figured I needed to ‘eat crow’ before too many other people found out about my lawn mowing past and decided to mow it for me…
Many things have come full-circle, although its also good to see some innovation also being delivered by vendors to customers in networking – whether requiring silicon innovation, or software, or protocol. One area I am personally very interested in is improving the operational/administrative experience of networking products — I like adding things there that make life easier and simplify complex workflows. Think there is still a lot of room to improve there.
dg
October 22nd, 2009
The pendulum of progress swings widely between these two technologies. That is, at a given point in time custom silicon may have an edge but some new development such as smaller fab size or or better chip design software might mean that merchant silicon gains an edge before the new spin of custom silicon.
Frankly, who cares. If you think that the engine inside your car affects your ability to get to the shop to buy beer, you really don’t understand the problem.