Bob,
Thanks for your comments, and given your
pioneering contributions and lengthy career in the industry, I wish we would
get the benefit of your insights more often on this reflector.
With respect to VCSEL array yields, my comments
on multi-element yields (again, please refer to tatum_01_1106.pdf) are based on
actual high volume production data.
My guess is that Jack Jewell’s observations
on VCSEL array yields are also based on real high volume manufacturing data. Jack,
can you comment on the basis for you observations about VCSEL array yields?
If Cyoptics has high volume VCSEL
yield/cost (die and packaged) data that show something different, please bring
these in as a contribution to the HSSG. I believe that would be of great
interest.
To achieve lower cost with multiple edge-emitters
integrated with an optical mux, versus a VCSEL array (even taking into account
the difference in fiber costs) would take an extra-ordinary level of human
ingenuity. My suggestion would be to first take a fraction of that human ingenuity
and figure out how to make single element edge-emitter Transceivers lower cost
then single element VCSEL emitter Transceivers. Having 10GE-LR SMF Transceivers
at a lower cost then 10GE-SR MMF Transceivers would very welcome by end users.
Chris
From: Hartman, Robert
L. [mailto:rhartman@CYOPTICS.COM]
Sent: Friday, June 29, 2007 10:49
AM
To:
STDS-802-3-HSSG@listserv.ieee.org
Subject: Re: [HSSG] The List
Chris
While I have been following the various
inputs to the reflector without comment I must comment on your note.
Yes, log normal statistics apply to
laser whether they are VCSEL or end emitters (I believe I was a co-author on
the first paper that demonstrated that back in the ‘70s).
However when you or any others are
referring to cost, with the exception of extremely complicated
monolithic photonic integrated circuits, the optical sources are well down on a
Prato analysis of cost. For edge-emitter lasers sources, even in moderately
complex photonic integrated circuits other components usually control the cost
(such as package bodies, TEC, etc.). Therefore assuming high-enough volumes to
justify the development expenses one of the principal paths to lower cost
should be internal multiplexing and de-multiplexing within the optical engines.
In addition one should not rule out human ingenuity with respect to a means of
multiplexing many more than 4 optical sources onto one fiber while meeting all
the other performance parameters at low cost.
Robert L. Hartman Ph. D.
Vice President
Device Development
CyOptics
9999 Hamilton Blvd.
Breinigsville, PA 18031
Tel: 484-397-2094
rhartman@cyoptics.com
From: Chris Cole [mailto:chris.cole@FINISAR.COM]
Sent: Friday, June 29, 2007 1:01
PM
To:
STDS-802-3-HSSG@listserv.ieee.org
Subject: Re: [HSSG] The List
Paul,
Wenbin is correct in his cost difference
analysis.
You have taken out of context the comments
that Jack Jewell and I made. What we said is that the yield (cost) of a
12-element VCSEL Array is about 2x the yield of a 4-element Array. This is due
to non-random defect distribution on wafers which gives logarithmic yield
curves (see tatum_01_1106.pdf.) This can not be extrapolated to the relative
cost of a 12-element or 4-element parallel optics transceiver versus a single
element transceiver like SFP+. Such extrapolation ignores the many other
processing steps required to handle, package, mount, test lasers into
Transceivers. And it also ignores volume.
Chris
From: Paul Kolesar
[mailto:PKOLESAR@SYSTIMAX.COM]
Sent: Friday, June 29, 2007 6:36
AM
To: STDS-802-3-HSSG@listserv.ieee.org
Subject: Re: [HSSG] The List
Wenbin,
the
material in kolesar_01_0507 explicitly states that volume was not factored in,
so the basis of disagreement you state is out of scope of that presentation.
That said, I fully agree, and have previously stated on this reflector,
that volume is a significant factor, and have asked for more disclosure on
volume assumptions. So thanks for adding to the discussion on that front.
Your statement that I had not properly accounted for lower array yields
seems counter to Chris Cole's
assertions that 12-lane transceivers would cost less than 2.5 times the 4-lane
transceivers. Jack Jewell has also made that assertion recently.
The
comparison analogy you offer at 2G is interesting, but may be too skewed.
2G transceivers have come way down the cost curve relative to 10G for
reasons that go beyond volume at that particular data rate. The SFP form
is shared by many data rates from 1G to 4G, each contributing to the volume of
the common components. Indeed, some SFPs are data rate agile. 10G
volumes do not see anything close to the volume of these combined lower rate
applications, and there are other factors to consider that I will touch on.
In
order for the 2G analogy to apply well to the 10G rate, the SFP+ would need to
displace not only other 10G forms, but also the SFP. Is this part of your
volume assumptions? If not, then the volume argument favoring SFP+ seems
thin, since both the SFP+ and QSFP are new. SFP+ may have a lead in the
market, but it is early in the conversion cycle. QSFP does have multiple
applications that span a wide variety of data rates, such as the 10 and 20G
(and future 40G) rates of InfiniBand and current and future Fibre Channel rates
at 10G, 20G, 34G and 40G, and it offers much higher density. With the
front panel surfaces of high-end boxes completely packed with I/O, this density
offers opportunity for relief. With all this yet to play out, I am still
unclear as to the assumptions that support the assertions of volumes favoring
SFP+. Can you offer details to support that view, particually on the
displacement of SFP?
Regards,
Paul Kolesar
CommScope Inc.
Enterprise® Solutions
1300 East Lookout Drive
Richardson, TX 75082
Phone: 972.792.3155
Fax: 972.792.3111
eMail: pkolesar@commscope.com
|
Wenbin Jiang
<Wenbin.Jiang@JDSU.COM>
06/29/2007
01:29 AM
|
Please respond
to
Wenbin Jiang <Wenbin.Jiang@JDSU.COM>
|
|
|
To
|
STDS-802-3-HSSG@listserv.ieee.org
|
|
cc
|
|
|
Subject
|
Re: [HSSG] The List
|
|
Paul,
I have reviewed your presentation, kolesar_01_0507. I do not
agree with you on the cost comparison between the 4xSFP+ and the QSFP. It has
failed to take the volume difference and low array yield into account. I would expect
that the SFP+ volume is going to be substantially higher and therefore cost
lower. Since 40G QSFP does not exist, a good benchmark is to compare 12 2G-SFP
modules with a pair of 12-channel parallel 2.5G TX+RX modules. One has a large
volume base while the other is not. The low volume array modules cost 2x to 3x
of the high volume single channel modules.
Wenbin
From: Paul Kolesar
[mailto:PKOLESAR@SYSTIMAX.COM]
Sent: Thursday, June 28, 2007 2:51 PM
To: STDS-802-3-HSSG@listserv.ieee.org
Subject: Re: [HSSG] The List
Wenbin,
my presentation from May, kolesar_01_0507, addresses my views on the intrinsic
costs of items 1, 3, and 4 of your list. Regarding item 2, I do not know
how to factor in the costs of reduced performance specs on SFP+, since that
gets too subtle. To me the issue was not if there could be cost
reductions for SFP+ PMDs but rather if SFP+ systems were capable of 10GBASE-S
performance. There have been statements that SFP+ meets 10GBASE-S specs
which imply that its cost improvements relative to XFP do not bring with them
significant performance impairments. If this is true for a broad set of
suppliers and systems, then there may be little benefit in a reduced
performance 10GBASE-S spec. Also the cost savings of a reduced
performance spec would be quite dependent upon which parameters are relaxed and
would likely be quite vendor-specific. So we may end up with little added
clarity in pursuing item 2.
In the pursuit of clarity, I have asked for criticism of kolesar_01_0507 and
for disclosure on the impact of volume assumptions on others' relative cost
claims between 4xSFP+ and QSFP. I hope that through these additional
inputs a sufficiently complete picture emerges of the costs of the available
alternatives. I see these specific issues as better communicated through
discussion on the reflector than by presentation at the meeting. But I am
open to either approach. The latter at least has the benefit of being
counted as a contribution, although I think reflector threads should also be
included in such counts.
Regards,
Paul Kolesar
CommScope Inc.
Enterprise® Solutions
1300 East Lookout Drive
Richardson, TX 75082
Phone: 972.792.3155
Fax: 972.792.3111
eMail: pkolesar@commscope.com
|
Wenbin Jiang <Wenbin.Jiang@JDSU.COM>
06/28/2007
01:54 PM
|
Please respond
to
Wenbin Jiang <Wenbin.Jiang@JDSU.COM>
|
|
|
To
|
STDS-802-3-HSSG@listserv.ieee.org
|
|
cc
|
|
|
Subject
|
Re: [HSSG] The List
|
|
There are clearly confusions/questions on the economic feasibility of 40GE 100m
objectives. Would appreciate a presentation to compare the relative cost among
the following:
1. 4x10G
LAG (10GBASE-SR compliant per lane, possibly 4 x SFP+ or QSFP, whichever
costing lower?)
2. 4x10G
LAG (relaxed spec from 10GBASE-SR, but similar to the 40GE per lane basis.
Possibly relaxed spec 4 x SFP+ or QSFP?)
3. 40GE
compliant (presumably QSFP?)
4. 100GE
compliant (SNAP12 TX+RX?)
Wenbin Jiang
From: Dove, Dan [mailto:dan.dove@HP.COM]
Sent: Thursday, June 28, 2007 8:52 AM
To: STDS-802-3-HSSG@listserv.ieee.org
Subject: Re: [HSSG] The List
Paul,
With regard to the point I made about a "relaxed spec for 10G" vs
writing an "entirely new Ethernet spec with multiple PMDs for 40G",
it was in response to your contention that 10GBASE-SR would be more expensive
to build than one channel of a new, unwritten, and parametrically relaxed 40G
PMD. My point was not that it is *necessary* to have a relaxed spec for 10G,
but rather that if such a relaxation is to be done, it would be less
conflictive with existing projects to do a 10G PMD than an entire set of PMDs
and a 40G MAC spec that lacks distinction from 100G in the market place. (ie:
Two higher speed Ethernets coming out at the same time with only a slight
difference in speed)
It is my firm opinion that we can build 10GBASE-SR compliant SFP+ transceivers
and that the total solution cost compared to X2 or XFP will be significantly lower
in cost than today's solution cost because of the repartitioning of the
functionality, the rapidly diminishing cost of EDC, and the port density
improvements which will allow system vendors to distribute infrastructure cost
into more ports than is possible today.
Dan
From: Paul Kolesar [mailto:PKOLESAR@SYSTIMAX.COM]
Sent: Wednesday, June 27, 2007 4:40 PM
To: STDS-802-3-HSSG@listserv.ieee.org
Subject: Re: [HSSG] The List
Ali,
there seems to be a theme throughout your response that implies that cost is
paramount and compliance to 10GBASE-S is of secondary importance. This
subtle but very significant posture may be pervasive with others as well.
In my comparisons I have been holding 10G LAG implementations to the
requirements of 10GBASE-S. Dan suggested that a relaxed spec version of
10GBASE-S could be an alternative that makes LAG more attractive from a cost
perspective. And I am asking Jack to clarify his statements with respect
to compliance. Now you make similar intonations. While this may be
an alternative, it is one that distorts the reality of the day. We do not
have a relaxed spec, and although it is possible to conceive of such a change,
there is no study group activity in that direction. So it seems mostly
academic at this point because proprietary solutions of this sort do not ensure
interoperability. We need to be very clear on this assumption in our
comparisons going forward.
Regards,
Paul Kolesar
CommScope Inc.
Enterprise® Solutions
1300 East Lookout Drive
Richardson, TX 75082
Phone: 972.792.3155
Fax: 972.792.3111
eMail: pkolesar@commscope.com
|
"Ali Ghiasi"
<aghiasi@broadcom.com>
06/27/2007
12:33 PM
|
|
To
|
"Jack Jewell"
<Jack.Jewell@PICOLIGHT.COM>, "Paul Kolesar"
<pkolesar@systimax.com>
|
|
cc
|
STDS-802-3-HSSG@listserv.ieee.org
|
|
Subject
|
Re: [HSSG] The List
|
|
Jack and Paul
The question is not whether SFP+ can achieve 300 m SR reach similar to XFP, but
how do we get to 10G SFP+
at 2.5x the cost of 1G classic SFP for DCE (Data Center Ethernet) with max
reach of 100 m.
If we can get to 10G SFP+ at 2.5x the cost of 1G at 300 m then the 10G PAR
objective is complete, but how long
do we wait the need is know. But I do know the combination of lower cost
optics with EDC can deliver
the 2.5x cost objective for DCE applications near term. To get to these
cost the transmitter very likely
will not be fully SR compliant and in that case it does not matter if the reach
is 100 or 300 m.
The current assumption in the HSSG is that you can achieve SFP+ limiting
performance with 4 or 10 channels without the
use of CDR in the module, with more crosstalk, less optimum layout, SerDes
having more jitter and less tolerance compare
to small port count PHYs, optics ??? You will get small benefit from
reducing fiber reach to 100m but not enough to close the
link budget. As Dan mentioned EDC is becoming an standard feature on PHYs
and we definitely need to leverage it for 40G/100G.
Use of linear interface is an approach that can close the link budget without
the use of CDR in the module, relax the optics
specifications, and the same interface can support passive copper Twin-ax up to
10m.
Ali
Jack Jewell wrote:
Input from a transceiver vendor with experience and interest in both serial and
parallel modules:
First, SFP+ achieves the 300m SR objective with similar ease as XFP.
While a reduced-reach 10G PMD might reduce costs, it's a retreating
approach that requires the customer to purchase higher-cost transceivers to
fill in the reach gap, e.g. for reaches between 100m and 300m.. A reduced
operating temperature range offers immediate cost savings for some customers
without compromising reach and without any new standards specifications.
Use of a linear receiver and EDC and relaxed Tx specs can also achieve
the 300m reach at reduced cost. For this application, the amount of
compensation required is far less than what is required for LRM. EDC is
becoming widely available, to the point of being a standard feature of PHY ICs,
so the cost of this EDC is becoming insignificant. Forward-looking
standards efforts will achieve their full impact by making use of EDC.
For QSFP,. Here again, EDC offers great advantage, and ignoring it would
be a mistake. But crosstalk introduces module-level limitations that
might motivate reach reduction or other modification to the PMD.
Comparing costs, the SFP+ will be lower than QSFP for the forseeable future
(per lane for the same spec). The only advantage of QSFP over SFP+ is
density and possibly simpler cabling. However, a 12-channel parallel
module pair, e.g. SNAP12, offers greater density than QSFP and 2.5-3X the
bandwidth at <2X the cost.
Jack
From: Dove, Dan [mailto:dan.dove@HP.COM]
Sent: Wednesday, June 27, 2007 9:32 AM
To: STDS-802-3-HSSG@listserv.ieee.org
Subject: Re: [HSSG] The List
Paul,
Regarding SFP+, I am very familiar with the technology and have been tracking
the SFF-8431 development. The architecture re-distribution of cost that SFP+
offers will have a substantial impact on cost, especially when combined with
the higher density we can achieve with smaller geometry ASICs and multiport
PHYs that will come with it.
As for QSFP, I am less familiar with whether or not it will provide a cost
improvement over SFP+ or be capable of meeting the existing SR spec. This is
something for the QSFP experts to consider, but like I said, a shorter 10G PMD
might be the avenue to take rather than an identity challenged 40G spec.
Regarding LAG, my conversation with HP Server architects indicates there are a
number of avenues for improvement of LAG under development.
I cited these areas in my earlier message and would appreciate them being
addressed rather than ignored.
Dan
From: Paul Kolesar [mailto:PKOLESAR@SYSTIMAX.COM]
Sent: Wednesday, June 27, 2007 8:04 AM
To: STDS-802-3-HSSG@listserv.ieee.org
Subject: Re: [HSSG] The List
Dan,
I can't tell how successfully SFP+ and QSFP will be at meeting the existing
10GBASE-S spec. If they can, a new shorter distance 10G PMD would not be
of value. If they can't, then a new PMD spec may be worth while.
Those attempting to implement these lower cost platforms need to weigh in
to provide guidance. In the event that either the QSFP and/or SFP+ can
meet 10GBASE-S specs in multiple vendor's platforms, or that a new shorter
distance spec is developed that allows lower cost, the performance issues of
LAG will remain. I believe Howard's presentations on LAG have indicated
that improving LAG would not be without compromise, leading me to conclude
that, however improved, LAG performance could not become equivalent to a 40G
pipe. Developing a 40G spec would ensure a solution that simultaneously
addresses these cost and performance issues.
Regards,
Paul Kolesar
CommScope Inc.
Enterprise® Solutions
1300 East Lookout Drive
Richardson, TX 75082
Phone: 972.792.3155
Fax: 972.792.3111
eMail: pkolesar@commscope.com
Hi Paul,
Good points. I was not really expecting to see a significant cost differential
at the PMD although its a good argument that a 100m PMD would be less expensive.
If this is the case, why not do another 10G PMD focused on lowering the cost of
server interconnect? I believe that would be a smaller project and have a much
less significant impact on 100G development.
Thanks,
Dan
From: Paul Kolesar [mailto:PKOLESAR@SYSTIMAX.COM]
Sent: Tuesday, June 26, 2007 6:16 PM
To: STDS-802-3-HSSG@listserv.ieee.org
Subject: Re: [HSSG] The List
Dan,
thanks for your detailed thoughts and proposals. I appreciate the points
you made regarding the volume effect of 10G components on the cost comparison.
The presentation I submitted for the May interim looked at the intrinsic
cost factors and did not attempt to include volume in the equation. But
volume certainly can be a significant factor. Your suggestion to look
into its impact when comparing 4x10G LAG to 40G is reasonable, but complicated
at the PMD level. As my May presentation shows there are a few ways to
implement LAG on MMF. One uses the XFP, another the SFP+, still another
the QSFP. Today the XFP is shipping to the 10GBASE-S spec, and supports
300m transmission. Designs using SFP+ and QSFP will be more challenged to
meet this spec due to jitter, so it remains to be seen how successfully these
lower cost form factors can substitute for the XFP in 10GBASE-S compliant LAG.
However, a reduced distance requirement, such as that stated in the HSSG
objectives, would greatly improve the chances that QSFP will suffice for
"40GBASE-S". So while volume is important, these unanswered
questions on suitability make it impossible from my vantage point to determine
how the volumes for 10GBASE-S will be divided among XFP, SFP+, and QSFP. And
the effects of volume on production costs are better left to those who
manufacture the devices. Perhaps individuals with such insights will
offer some scenarios.
Regards,
Paul Kolesar
CommScope Inc.
Enterprise® Solutions
1300 East Lookout Drive
Richardson, TX 75082
Phone: 972.792.3155
Fax: 972.792.3111
eMail: pkolesar@commscope.com
My fellow colleagues ,
Last week I sent out a list of items that I felt need to be addressed to ensure
that a 40G PAR would be justified. At a subsequent EA teleconference intended
to build concensus in the HSSG, I offered to review the presentations made in
support of 40G Economic Feasibility and comparing 40G vs 4x10 LAG performance
to ensure that I was not being too harsh in my consideration of the material
that was presented.
Over the weekend, I reviewed every presentation I could find on these subjects
so that I could be comfortable that I was not being unfair in my concerns.
Fortunately, it was not a huge task as there are not that many to review.
After doing so, I found myself less convinced in the validity of some
presentations that were made. This statement is not made to criticize my
colleagues, but to honor the concept of peer review which requires that we
review and criticize, otherwise we might as well just upload them to a server
and forget about them.
Specifically, I disagreed with cost arguments made on the assumption that 10G
cost remains a constant, when in fact I anticipate substantial reductions in
10G cost over the next few years at a rate much faster than today due to a few
factors;
1) Higher density/lower cost optical form factors (SFP+) allowing better
utilization of switch infrastructural cost and QSFP for NICs.
2) Smaller geometry CMOS allowing higher port densities to work in synergy with
PMD cost reductions.
3) Integration of XFI / SFI interfaces directly into ASICs or multi-port PHYs
driving 10G cost further downward.
4) Higher volumes / commoditization of 10G driving cost down much faster than
the current trajectory.
While 40G can leverage some of these elements, it cannot leverage the volume
that feeds the downward cost spiral. So in 4 years, a 40G switch port cost is
going to be based on low-volume, freshly designed and un-amortized silicon used
primarily for server interconnect, whereas a 10G port cost will be based on
amortized, high-volume silicon being used in a huge array of applications.
Having different trajectories, the relative cost for 40G will be higher than
presented. This is true for 100G as well, but who is arguing a need for 100G
based on cost? It is bandwidth that drives 100G demand.
In addition, I found presentations claiming that LAG was insufficient to
address server I/O bandwidth needs, yet those presentations failed to address
upcoming technology enhancements like TRILL and its impact combined with I/O
Virtualization, perhaps with a physical manifestation of QSFP and MPO optics
which I believe can lead to graceful performance scaling for servers that does
not demand an intermediate IEEE standard. In other words, activities and
technologies are advancing which will parse server network access into multiple
conversations that can then be put onto a LAG group with much higher than
presented performance levels.
Now, I realize that I am swimming upstream here by asking that the proponents
for "40G now" to complete a task that took the 100G proponents
almost a year to accomplish, in less than 6 months, but then I am not asking
them to do that. My first choice, the one I proposed in Geneva, was that we move
100G forward (because it is DONE) and that we continue to work on 40G (until it
is done).
This appears to be a minority position because apparently some people will
accept an unproven 40G proposal rather than risk 100G. Others think that 40G is
proven sufficiently and are demanding "40G now" or they will not
allow a 100G PAR to go forward. Those in the latter camp must either be
unconvinced of my concerns, or they think my concerns are insufficient to
justify any further work being done to justify a 40G project.
I can accept differences of opinion.
What I cannot do, however, is pretend that these issues do not exist, or that
the work we would have to spend getting a 40G standard done is not going to
delay the much needed 100G aggregation solution our customers demand. I cannot
ignore what I perceive as holes in the 40G presentations.
So, to provide a little more direction to my colleagues in the "40G now or
the HSSG stalls" crowd, I am asking you to include relative cost
trajectories in your analysis of 40G vs 10G cost models, and to include
technology enhancements to LAG (TRILL, I/O Virtualization, QSFP, MPO) in your
performance analysis.
If you feel that this is unnecessary, I am requesting that you communicate this
position to me as soon as possible so that I can prepare a presentation on
these areas of concern for the July meeting.
Respectfully,
Dan Dove
Dove Networking Solutions - Serving ProCurve Networking by HP