Thread Links Date Links
Thread Prev Thread Next Thread Index Date Prev Date Next Date Index

Re: [802.3BA] proposed 100GbE standard and roadmap to 1TbE question..

The choice of 20 virtual lanes was disccused earlier also in December 2007. In this regard, I draw your attention to a paper on "A Physical Coding Sublayer for 100GbE" by Gary Nicholl, Mark Gustlin  and Oded Trainin, of Cisco Systems Inc.
The paper discusses at length as to why the option of 20 virtual lanes suit 100GbE requirements.
Thanksand Regards,
SK Rana

On Thu, Apr 30, 2009 at 5:24 PM, Fritz, Karl <fritz.karl@xxxxxxxx> wrote:
Greetings Task Force Members,
My name is Karl Fritz and I work for the Special Purpose Processor Development Group at the Mayo Clinic in Rochester, MN.  Some of us are studying Terabit communication, so we have recently been paying more attention to your efforts.  I was pleased to see the following article in Networkworld, which mentioned that you folks are looking ahead to Terabit communication around the 2015 timeline.
However, I do have a question related to the way the signals are grouped for 100GbE protocol.  It appears that the data will be striped across 20 lanes, then down to 10 lanes (for the CAUI  protocol) and then again possibly muxed down to 4 and then 1 (according the the Ethernet Alliance November 2008 Technology Overview document).  Being that 10Gbps serdes exist, why does the standard start at 20 lanes (5 Gbps each)?  If this standard is expected to be scaleable, it appears things could get rather messy if we want to scale this to Terabit speeds (effectively multiplying all this by 10).
Could somebody enlighten me a bit or point me as to why 20 lanes was selected as a standard?  Why not go directly to 10 lanes at 10 Gbps?

Karl Fritz

Lead Engineer

Special Purpose Processor Development Group (SPPDG)

Phone: 507-538-5466

Fax: 507-284-9171

E-mail: fritz.karl@xxxxxxxx


Mayo Clinic

200 First Street SW

Rochester, MN 55905