Brkopt 2116

High Speed Optics
25G, 40G, 100G & Beyond
Errol Roberts, DSE

BRKOPT-2116
Network Operators are Leaving Ketchup in the Bottle
NPU Friction Ethernet Friction Transponder Friction DWDM
10G
25G 50G
200G 40G 100G ITU
50G 150G 50GHz
Terabits 100G 200G Grid
200G
400G
NPU Capacity Growing Interconnect Efficiency Spectrum Efficiency

We need to reduce friction between different layers of the network to get the more ketchup out of the
bottle
Client side and Line side optics innovations are the key to success
2016 Cisco and/or its affiliates. All rights reserved. Cisco Public
Setting the stage......
ITU-T define OTN Transport Network
carrying Ethernet Traffic
IEEE defined Ethernet Regen

OA
TxP
Mux/Demux
ROADM
DC & Client Optics Line Optics
Within a building/campus (< 10km) Across country (a few hundred to 1000s km)
Grey optics Multiple channels / Fiber (DWDM)
Mainly Ethernet (some POS, OTN) OTN
Solve for Cost, Power, Density Solve for Spectral efficiency and Performance
2016 Cisco and/or its affiliates. All rights reserved. Cisco Public 4
Agenda
Introduction
Industry Trends
Standards
Client Side Optics
Impact of High Speed Optics on the DC Fabric
Line Side Optics
Beyond 100G
Conclusion
Exponential Data Growth People-to-People
Video, Mobile & Cloud is Driving Traffic Growth
Content & traffic patterns are becoming more dynamic and People-to-Machine
distributed
The Internet of Everything will accelerate traffic beyond
recognition:
Radically increase volume
Dramatically change traffic patterns Machine-to-Machine
Challenge traffic engineering and management
Demand new service definitions (SLAs)
To keep pace, Enterprise and Service Providers need

agile solutions that reduce complexity and TCO
Solutions need to offer lower cost/bit for the overall network
Growth in the Cloud
By 2019, 83% of global data center traffic come from cloud
services and applications
18% of traffic between datacenters & end users
9% between data centers for replication & inter-

database links
73% will be coming from within the datacenter,

storage, production, development and
authentication traffic
1 zetabyte is trillion gigabytes

Ethernet Roadmap
Evolution of New speeds:
25Gb/s, 50Gb/s, 200Gb/s, 400Gb/s

2.5Gb/s & 5Gb/s for wireless
Development and deployment at

points all along the Ethernet value
chain have exploded!!
6 Ethernet speeds in 5 years, same

amount as the previous 40 years
provided !!
Ethernet & OTN Evolution
Ethernet has undergone continual innovation since standardization
Transport systems evolving to 400G
FE GE 10GE 40/100GE
Standard Demand and Innovation
Ethernet continue
SDH Payload Eth Payload

OTN Standard Demand and Innovation
OTU1/2 OTU3 OTU4 continue
1985 1990 1995 2000 2005 2010 2015
OTN aligned with Ethernet speeds

Enterprise and Hyperscale Datacenter Trends
Use of Multimode fiber for forward and backward
connectivity in migration from 10GE->40GE->100G
where possible
Continued evaluation of Multimode vs. Single mode for
future bandwidth needs
DC Campus can consume many acres and require
significant amounts of fiber interconnect
DC Architecture is driving cost of short reach Single
mode optics down
Interconnect costs affect DC physical architecture
Increased choice of cabling options to address density,
bandwidth and reach
Data Center Fabric Trends
High bandwidth Fabric Early Integration of 100G north-south
Redundancy Model focused DC edge
Physical Infrastructure
Multiple Spines 100G Links
40 -100G Links
Wider Spine 10 - 25G Servers
Higher Scale Compute 2016 Cisco and/or its affiliates. All rights reserved. Cisco Public
Network fiber migration with increase in data rates
Multimode Fiber Single Mode Fiber
1G
1km 10km
10G
400m 10km
40G
150m 2km 10km
100G
100m 500m 2km 10km
Shorter link distances with higher data

rates on OM4 multimode fiber.
Short reach optics for single mode fiber at higher data rates.
Why are Optics More Important Now?
Time line of faceplate BW density GLP of routing line cards fully

populated with LR modules
As faceplate bandwidth increases, the number of high BW ports increases and

the cost of pluggable optics increases as a percentage of the solution cost
Router Market trends
Traditional Backbone Core

Backbone Router Network
Service
Provider
Core
Metro Core
Metro Edge/Aggregation
Service
Provider
Cell-site Devices Edge
Data Centers driving investment in the Metro

Accelerated 100G adoption
Network Migration trends
Place in Network 2014/ 2015 2016/ 2017 2018/ 2019
Hyper scale Cloud server 10G 40G 10/40G 25/50G* 25/50G* 50/100G
access
Other Cloud server 1G 10G 10G 25G 25G 50G
access
Enterprise server access 1G 10G 1G 10G 10G 25G
Enterprise Edge Routing 1G 10G 10G 100G 10G 100G
SP/Cloud Core Routing 10G 40/100G 10G 100G 100G 200/400G

Each part of the network is migrating to a different speed
*2x25G
Other Industry Trends Pluggable transceivers
Cost, reach, size, power optimization continues
QSFP28 form factor becoming de-facto for high
density 100G
SFP28 emerging as 25G form factor same port
density as 10G SFP+
QSFP-DD emerging as the 400G form factor
CFP2 Pluggables for DWDM interfaces
Advances in high order modulation techniques
electrical and optical.
Copper vs Optical cost reach size power trade-offs
OTN choice for optical transport
Market need for flexible interfaces on client devices
Other Industry Trends - Onboard optics
Current pluggables limit the faceplate density

So how do we go beyond 6TB+ ??
>2018: board-level photonics embedded optics
COBO Consortium On-board Optics [switch face-
plate, bandwidth density..]
On-board optics permit greater switch radix with lower power consumption, which is really important
as we continue to increase speed and bandwidth, - COBO
Optical Engine
COBO - Path to on-board optics Re-timing
Switch Optical Engine in a Pluggable module
Switch Optical engine on-board the line card
Switch Silicon Photonics Optical Engine mounted on the package
face-plate density & signal

On-board optics adds
integrity efficiencies to the line card 2016 Cisco and/or its affiliates. All rights reserved. Cisco Public
Silicon Photonics
Potential for transceiver on a chip
Optical devices can be made
cheaply using standard
semiconductor CMOS
fabrication techniques
Optics can be integrated with
microelectronic chips.
Silicon integrated optical chips
that can generate, modulate,
process and detect light signals
Silicon Photonics is the most promising optical technology for:
Solving for Cost, Power, Density for DC & Client optics
Solve for Spectral efficiency and Performance for DCI & Long Haul optics
Optical Technology Trends
DC & Client optics
How can we go faster

Increase Signaling speed
Evolution of Ethernet speed roadmap
Adopt advanced modulation formats
carrying more bits/s, but keep the baud rate low
Increase number of fibers (Parallelize)
Aggregating data over several number of fibers/ lanes
Increase number of wavelengths
Combining data over multiple wavelengths (WDM)
Optical technology
Is the key enabler for systems to maintain pace with the
requirements of the bandwidth pressures
Challenge Goal
Form Factor Size reduction Port Density increase
Power reduction Port Density increase
Reach System/network scaling
Packaging simplification Increased Yield, lowers cost
The next speed (400G/1T) System Scale, lower costs

Alignment Needed to Achieve TCO Goals
DC Network Infrastructure
ASIC BW & Port
Speed
Innovation
Standardization
Open Ecosystems
Cabling Optics Speed and

Infrastructure Size
Single Lane .. Less Complexity (and Lower Cost)
TX 4 x 10G TX/RX Toolkit:
2 x 20G
Duplex Duplex
Duplex Duplex
(Cisco BiDi)
Multimode Multimode
Fiber Fiber Multimode Multimode Speed-up,
Fiber Fiber
4 x 10G 2 x 20G WDM,
RX Modulation
TX/RX
TX 4 x 10G TX
1 x 25G Toolkit:
Server TOR
Server TOR Speed-up,
WDM,
4 x 10G 1 x 25G Modulation
RX RX
4 x 10G TX 1 x 50G w/ Toolkit:
modulation Speed-up,
Server TOR Server TOR
WDM,
Modulation
4 x 10G
RX 1 x 50G w/
modulation
Single Lane .. Less Complexity (and Lower Cost)
The 100G Switch Link Example
TX
TX/RX
4 x 10G
4 x 25G
TOR Switch
TOR Switch
4 x 10G 4 x 25G
RX
TX/RX
Toolkit: Speed-up, WDM, Modulation
Higher Order Modulation
Same Data and Data Rate; but lower frequency (baud rate).
PAM-2 1 (1 level)
0110 100011
1-bit Symbols
1 Level
0 (0 level)
0 Level
1 1 (3 level)
0110 100011
PAM-4 1 0 (2 level) 3 Level
2-bit Symbols
2 Level
0 1 (1 level)
But 4 levels 1 Level
0 0 (0 level)
0 Level
Lessens many transmission penalties

Why higher order Enables lower bandwidth components and materials
modulation? Reduces wavelengths & fibers compared to NRZ
Optical connectivity increasingly important
for DC Performance, Scale, and Cost!
Need to optimize all

- cost, power, density -
simultaneously
Design Choices will vary by

network use-case!
Never ending balancing act!
Standards
Industry Standards Groups
IEEE Control Plane
Physical interfaces for Backplane, Copper,
Fiber PMDs
IEEE ITU IEEE
ITU Study Group 15: Optical and Transport OIF OIF
Networks
OTU4 frame format
Client Interfaces Hardware
Single mapping for 40GE/100GE into Layer 2/1 Vendors
OTU3/OTU4 (e.g.) interoperability Transport Component
OTL protocol enabling OTU3/4 over multi- Networks Interoperability,
lane optics Layer 1/0 Commonality
interoperability
OIF: 100G Long-distance DWDM
Transmission
100G standardization coordinated among ITU,
Industry consolidation around a single
IEEE, and OIF
100G DWDM solution
Proactively eliminate interop issues encountered
with 40G
Ethernet Speed Trends
Parallel fiber (MPO) Dual fiber (LC)

New Ethernet Standards Call for Interest (CFI)
Leading Application Space for next
generation Data Center Ethernet
ITU-Defined Core
OTN Transport Optimized multi-lane interconnect
for switch connectivity
Optimized single lane interconnect

IEEE Router
for servers and switches
defined Leaf/Spine
Ethernet
Scope of
TOR/Leaf
CFI
Server
Why 50Gb/s & 200Gb/s Ethernet?
Enables similar topology as 10 & 40 Parallel Implementation
Gb/s and 25 &100 Gb/s Ethernet 4 x 10Gb/s 40Gb/s
Single 50 Gb/s SFP56 port

4 x 25Gb/s 100Gb/s
implementation
Quad 50 Gb/s QSFP56 breakout 4 x 50Gb/s 200Gb/s
implementation possible
16 x 25Gb/s 400Gb/s
Maximizes ports and bandwidth in
ToR switch faceplate 8 x 50Gb/s 400Gb/s
Dense rack server
4 x 100Gb/s 400Gb/s
New Standards leverage previous industry
investment
Technology Nomenclature Description Status
Backplanes 100GBASE-KR4 4 x 25 Gb/s (NRZ) Deployed. Legacy 4x installed

100GBASE-KP4 4 x 25 Gb/s (PAM-4) base requiring upgrade
Chip-to-Module CDAUI-8 8 x 50 Gb/s PAM-4 IEEE P802.3bs in Task Force

Review
Chip-to-Chip CEI-56G-VSR-PAM 56 Gb/s PAM-4 Straw Ballot
SMF Optical 400GBASE-FR8 8 x 50 Gb/s PAM-4 IEEE P802.3bs in Task Force

400GBASE-DR4 4 x 100 Gb/s PAM-4 Review
Module Form Factor SFP56 1 x 50 Gb/s Summary Document SFF-8402
QSFP56 4 x 50 Gb/s Summary Document SFF-8665
100G Transceiver Form Factors
CFP CPAK CFP2 CFP4 QSFP28
82 35 42 22 18
52
86
101
140
107
4x25G
13.6 11.6 12.4 9.5 8.5
Power <32 W < 7.5 W < 8W, 12 W < 5 or 6 W <= 3.5 W

dissipation
QSFP28 is the NEW! QSFP 100G transceiver form factor

Offers the same port density as the QSFP 40G form factor
Transceiver form factors serial speeds
SFP+ 10G
Same port density as 10G for 25G & 50G (future)
ASIC TX
(10G SERDES) 10GbE 25GbE 50GbE
RX
NRZ
Form Factor SFP+ SFP28 SFP56
SFP28 25G (~2016) Modulation NRZ NRZ PAM4
ASIC Lane scheme 1 x 10G 1 x 25G 1 x 50G

CDR TX
(25G SERDES)
CDR RX
NRZ
SFP56 50G (future)

ASIC CDR TX
(50G SERDES)
CDR RX
PAM4 Laser Driver
Rx-TIA
Transceiver form factors parallel speeds
NEW! 100G QSFP provides the same port
QSFP 40G QSFP 100G
density as 40G
CDR TX
TX Optical MUX
Optical MUX
CDR TX
TX Industry Need:
CDR TX
TX ASIC
ASIC
TX CDR TX A pluggable transceiver form factor for
10G 25G 400G that provides similar port density that
SERDES SERDES
Optical DEMUX
CDR RX provides similar port density as 40G &
Optical DEMUX
RX
NRZ NRZ CDR RX
RX 100G: QSFP-DD form factor emerging
RX CDR RX
RX CDR RX
aka QSFP28
Laser Driver
Rx-TIA
Parallel Data Streams Multi Layer Distribution (MLD)
MAC/ PM PM MAC/
PCS D D PCS
(4x25Gb/s)
Multi-lane Distribution (in the PCS layer) provides a simple way to map
40G/100G to physical interfaces of different lane widths with Virtual lanes
Data from any particular virtual lane will reside on the same electrical and
optical lane across the link No skew introduced between bits within the virtual
lane
IEEE Standard vs MSA Form-factor
IEEE defines physical network interfaces
10GBASE-SR, 40GBASE-LR4, 100GBASE-LR4 etc
MSA define transceiver form factors
QSFP, QSFP28, SFP+, X2 etc
defined by a group of transceiver vendors based on
technology availability and roadmap
PMDs of the same speed/ reach/ protocol must interoperate,
irrespective of the form factor
MSAs are also creating new application-specific Physical
Network Interface
100G-CWDM4 & 100G-PSM4
Market need is also driving non-standard interfaces

40G-BiDi, 40G-CSR4
MSA = Multi Source Agreement
Ethernet Physical Interfaces
1G 10G 40G 100G 25G 400G
40km
ER 40km 100G-ER4
SMF LX LR 10km 40G-LR4 100G-LR4 10km 400G-FR8 10km
40G-FR 2km, Optical

Transport only 400G-DR4 500m
LX4 300m
Ribbon cabling
MMF SX SR 300m (N x 4, N x 10)
LRM 220m 40G-SR4 100m OM3

100G-SR10
T 100G-SR4 25G-SR 400G-SR16 100m
OM4
Copper T CX4 15m
40G-CR4 100G-CR10
100G-CR4 25G-CR
Industry Response in Datacenter Non-Standard
Solutions for 100m and 2km DC sweet spot
1G 10G 40G 100G 25G
25G-LRL
SMF 40G-LRL4/Lite 1-2km
100G-CWDM4
40G-PLR4 1km
And more non-
100G-PSM4 standard
40G-CSR4 300m interfaces to
MMF 40G-XSR4 300m come....
FET10 100m
SRL 100m Cisco BiDi 100m Cisco BiDi Future
AOC Cables AOC <30m AOC <30m AOC <30m AOC <30m
Q: Are these solutions proprietary?

A: They are not based on an IEEE standard but in most cases comply with relevant MSA for
pluggable interfaces to allow use across different vendors equipment.
DC & Client Side Optics
40GE Transceivers and
Cables
Cisco 40G Portfolio For your
reference
Wide Range of optics & cables for High Density 40G Applications
Multimode fiber, duplex
40GBASE-SR4
Multimode fiber Ribbon
FET-40G Single mode fiber, duplex
Single mode fiber Ribbon
40G-BiDi Cisco BiDi
40GBASE-CSR4
40GBASE-LR4
4x10G BASE-LR
40GBASE-ER4
10m 100m 300m 500m/ 2km 10km 40km 80km

1km Max. Distance
QSFP40G Pluggable Transceivers Single mode fiber
TX TX
Optical MUX
TX TX
Optical MUX
Optical MUX
TX TX TX TX
TX TX TX TX
ASIC ASIC ASIC ASIC
TX TX TX TX
10G 10G 10G 10G
SERDES SERDES SERDES SERDES
Optical DEMUX
Optical DEMUX
Optical DEMUX
RX RX RX RX
NRZ NRZ NRZ NRZ
RX RX RX RX
RX RX RX RX
RX RX RX RX
40G ER4 4x10G LR

40G LR4 Lite 40G LR4
40km reach 10km reach
2km reach 10km reach
Single mode fiber Single mode fiber
Single mode fiber Single mode fiber
2-fiber LC connector 12-fiber MPO connector
2-fiber LC connector 2-fiber LC connector
QSFP40G Pluggable Transceivers Multimode fiber
TX TX
TX TX
TX
TX TX
ASIC ASIC ASIC ASIC
TX TX
10G 10G 10G 10G
SERDES SERDES SERDES SERDES
RX RX
NRZ NRZ NRZ NRZ
RX RX
RX RX RX RX
RX RX
40G BiDi 40G Monitor BiDi 40G-SR4 40G-CSR4
150m OM4 reach Monitor BiDi 150m OM4 reach 400m OM4 reach
Multimode fiber Multimode fiber Multimode fiber Multimode fiber
2-fiber LC connector LC connector 12-fiber MPO connector 12-fiber MPO connector
For external link monitoring
40G QSFP Cables and Adapters
40G Copper Cables:

QSFP to QSFP 40G
QSFP to 4 X SFP10G Breakout
cables
QSFP TO SFP/SFP+ adapter
40G Optical Cables (AOC): QSFP adapter supports

QSFP to QSFP 40G one SFP or SFP+ module
QSFP to 4 X SFP10G Breakout 10G connectivity on a 40G
cables port
Why AOC cables? QSFP 40G CABLE
DIAMETER
AOC Active Optical Cables

AOC cables are thinner than twinax Copper cables
Enables improved air Flow
Primarily used for ToR to server or ToR to Leaf connectivity
No Electromagnetic Interference
Reach upto 30m (Copper cables have reach limitations with increasing
speeds)
Less weight and Flexible: Significantly simplifies Cable management
3mm 10mm
AOC Twinax
copper
cable
QSFP40G as high density 10G
MPO-LC break-out cable
SR
SFP+
QSFP+
SR
SFP+ Interoperable with
40G-SR4/CSR4 SR 10G SR
QSFP40G 40G-SR SFP+
SR
SFP+
LC-Duplex
MPO-LC break-out cable

LR
SFP+
QSFP+
SFP+
LR Interoperable with
4x10G LR 10G LR
QSFP 4x10G-LR SFP+
LR
LR
SFP+
LC-Duplex
Switches with QSFP40G ports can used in the high-density 10G mode
100G Transceivers and
Cables
Multiple Mode Fiber, Parallel
Single Mode Fiber, Dual
Single Mode Fiber, Parallel
IEEE compliant 100G-CR4
<5m Copper Cables
4x SFP28 Breakout
IEEE compliant (25G)
<5m Copper
100G AOC
IEEE compatible(100G)<30m Active Optical
IEEE compliant 100G SR4 12 fiber MPO, MMF

100m on MMF (OM4)
IEEE compliant 100G LR4
10km on SMF
100G PSM4 12 fiber MPO, SMF

MSA compliant 500m on SMF
100G CWDM4 2 fiber LC, SMF
MSA compliant 2km on SMF
25km/ 40km/ 80km Optical innovation needed
5m 30m 100m 500m 2km 10km 25km 40km 80km

QSFP28 Pluggable transceivers Single mode fiber
CDR TX CDR TX CDR TX
Optical MUX
Optical MUX

ASIC ASIC ASIC
25G 25G 25G

SERDES SERDES SERDES
CDR RX CDR RX
Optical DEMUX
CDR RX
Optical DEMUX
NRZ NRZ NRZ CDR RX

CDR RX CDR RX
CDR RX CDR RX CDR RX
CDR RX CDR RX CDR RX
100G-LR4 100G-CWDM4 100G-PSM4
10km reach 2km reach 500m reach

Single mode fiber Single mode fiber Single mode fiber
2-fiber LC connector 2-fiber LC connector 12-fiber MPO connector
QSFP28 Pluggable transceivers Multimode fiber
CDR TX
CDR TX
TX
CDR TX
ASIC ASIC
CDR TX
25G 25G
SERDES SERDES
CDR RX
NRZ NRZ CDR RX

RX CDR RX
CDR RX
100G-BiDi (future) 100G-SR4
100m OM4 100m reach OM4

Multimode fiber Single mode fiber
2-fiber LC connector 12-fiber MPO connector
100G QSFP Cables
100G Copper Cables:

QSFP to QSFP 100G
QSFP to 4 X SFP28G Breakout
cables For ToR to 25G Server Connectivity
For ToR to Server or

100G Optical Cables (AOC): ToR to Leaf Connectivity
QSFP to QSFP 100G
Upto 30m
IEEE compliant 100G-SR10 Multiple Mode Fiber, Parallel
100m MMF Single Mode Fiber, Dual
10x10G LR
IEEE compliant (10G) 10km on SMF Single Mode Fiber, Parallel
10x10G ERL
IEEE compatible (10G) 25km on SMF
IEEE compliant 100G LR4

10km on SMF
IEEE compatible 100G ER4L
25km on SMF
100G SR4 12 fiber MPO, MMF

IEEE compliant 100m MMF OM4
100G PSM4 12 fiber MPO, SMF 2016
MSA compliant 500m on SMF
100G CWDM4 2 fiber LC, SMF
MSA compliant 2km on SMF
40km/ 80km Optical innovation needed
500m 2km 10km 25km 40km 80km

CPAK 100G Pluggable transceivers High Density
10G For single mode and multimode fibers
TX TX TX
ASIC ASIC ASIC
10G 10G 10G

SERDES SERDES
SERDES
NRZ NRZ NRZ

RX RX RX
100G-SR10 or 10x10G SR 10 x 10G LR 10 x 10G ERL
150m reach OM4 10km reach 25km reach

Multimode fiber Single mode fiber Single mode fiber
2x12-fiber MPO connector 2x12-fiber MPO connector 2x12-fiber MPO connector
Anyport 100 Gb CPAK Line Card Solution For your
reference
Breaking the Fixed-Port Paradigm with CPAK

One CPAK Line Card Can Support 100G, 40G & 10G
10G Ports
Router/
Switch
MPO-24 to 10x Duplex LC

SMF or MMF
40G Ports
SR10 10X10G-LR
Router/
Switch
MPO-24 to 2x MPO-12
SMF or MMF
Extend the investment of a single line card to manage migration from 10G and 40G to 100G
High Density Connectivity
4x10G 10x10G 4x25G
Highest Density 10G Links with High Density 10G Links with CPAK Highest Density 25G links with
QSFP 40G portfolio 100G portfolio QSFP 100G portfolio
Enables 128 10G links per slot Enables 100 10G links per slot Enables 144 25G links per slot
4x10G breakout Cable 1-10m
10x10G SR CPAK 150m OM4 MMF 4x25G breakout cable 1-5m
4x10G breakout AOC 1-15m
10x10G LR CPAK 10km SMF 4x25G SR QSFP-100G 100m OM4 MMF
4x10G SR QSFP+ 400m OM4 MMF
10x10G ERL CPAK 25km SMF 4x25G PSM4 QSFP-100G 500m SMF
4x10G LR lite QSFP+ 2km SMF
4x10G LR QSFP+ 10km SMF
CFP2 to CPAK Adapter
Allows you to take advantage of CMOS Photonics in 100G CFP2 platforms

(Nexus 9k)
Allows CPAK modules to operate in CFP2 ports
Impact of High Speed Optics on the
DC Fabric
Traffic Growth / Data Center Growth
The Need for Speed & Efficiency Apples Maiden, NC 500k sf, Data Center
Physical scaling of data centers

Mapping Topology to Infrastructure
Cabling complexity
Standards & Interop
Form Factors
m km
As traffic grows, data centers (DC) grow

As DC grows and speed increases link distances must keep pace
Switches, routers and servers must manage higher capacity
Router & Switch Capacity and Efficiency Must Keep Pace

The impact of Cloud Data Center
Operational challenges
Scale and upgrade requirements drove new
architectures (aka Leaf-Spine)
Interconnect Challenges
New architectures droves higher interconnect
density
Flatter hierarchy more homogeneity
Ecosystem Challenges
High volume
Quicker cadence
Higher emphasis on cost & density
Switch ASIC re-architecture
DC Architecture Evolution
core
Spine 2
aggregation
Spine 1

10G/40G
access
leaf
Traditional tree-based architecture New Leaf-Spine Fat-tree Architecture

Optimized for N-S traffic Optimized for E-W traffic (still valid for N-S traffic)
Over-subscription in access, aggregation and core Increased availability n+1; & scale, add/remove nodes quickly
port-channels to aggregation STP, MLAG Over-subscription only in access, 1:1 to spine
Connected with 1G to 10G hosts Higher ports counts in Agg/spine-Core! to connect Each leaf
each spine in cluster
Concede with 10/40 GE transition
Major Impact on Electronics I/O and Interconnect

Impact of Link Speed
Three non-oversubscribed topologies:
2010Gbps 540Gbps 2100Gbps
Uplinks Uplinks Uplinks
2010Gbps 2010Gbps 2010Gbps

Downlinks Downlinks Downlinks
http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6627738
Avg FCT: Large (10MB,) background flows
FCT (normalized to
20
Impact of link Speed Intuition 15 OQ-Switch
optimal)
10 20x10Gbps
5 5x40Gbps
2x100Gbps
0
Higher speed links improve ECMP 30 50 70
Load (%) 40/100Gbps fabric: ~ same FCT as OQ
efficiency
10Gbps fabric: FCT up 40% worse than OQ
Prob of 100% throughput = 3.27%

2010Gbps 2100Gbps
Uplinks Uplinks
1 2 20
Prob of 100% throughput = 99.95%
1110Gbps flows 1 2
(55% load) 2016 Cisco and/or its affiliates. All rights reserved. Cisco Public
Design Considerations
Increased BW Utilization due to 40G / 100G speedup
2x
40/100G
8 x 10G
8 x 10G 8 x 10G
Expected Max Effective Throughput = 86.33% Expected Max Effective Throughput = 65.6%
Uplink speed ups avoid hashing collisions to the provide effective

utilization of available capacity
A speedup of 40G on uplinks for 10G attached servers results in FCT
that are 1240% lower than that of a 10G fabric
Building High Density Systems for Cloud DC
applications
High Density switching Silicon
Gen1: 40 GbE ports w/ 10G serdes
Gen2: 100 GbE ports w/ 25G serdes
Gen3: higher ports counts 100GbE w/ 25G serdes
Gen4: 200 GbE / 400 GbE w/ 50G serdes
High Density Pluggable Form Factors
SFP & QSFP are the work horse form factors
Everything else is transitory
Pluggable Form Factors
Pluggable Form Factors continue to be the norm

SFP & QSFP provide system densities consistent with Cloud DC
architecture requirements
Backwards compatibility offers huge value
Customer flexibility/refresh cycles
System design re-use
Economies of scale
A key enabler for highly dense 100G and 400G is an upgrade for
QSFP
Key Success Criteria to address NG Cloud DC
Switch Silicon Integration
50 Gb/s serdes
400 GbE MAC (200 GbE too but at same time, impact may be less)
32 ports
Pluggable Form factor capable of supporting 400 GbE

Technology Roadmap
Integration (SiPhotonics, InP) Focus on Market requirements
Packaging Not on development simplicity
Interop
Ideally not have 100GbE MSA breadth
Focus the industry investment
For your
reference
Data Center Cabling Architecture Considerations

Optics will drive physical architecture
Employ a main cross-connect at a MDA, for best management, scalability and growth
Plan for future device optics density and reach; fiber density parallel (SM/MM); <300m
(MM)
Use low loss connectors (<0.35dB/fiber) to enable MDA
Allocate rack space for orderly fiber count growth and network device interface scale
Plan for future high density 10G/25Gserver access to be addressed by 25/40/100GE
break out cables
Switch Architecture Type for Access Modular or ToR
Choice of SM or SM, Duplex or Parallel adoption time frame will determine choice
MDA: Main Distribution Area

Line Side Optics
Inter-DC connectivity in the Cloud-era
More than DCI
Enterprise Data Center inter-connect
Enterprise Data Center to Provider Data
Ent DC1 Ent DC2 Center
Provider Data Center to Provider Data Center
PE PE
DCI with varying EGN

SP EPN requirements:
CE DCPE CE
DCPE Multiple 100G needs

DCE
DCE Higher Density Interconnect in
SP DC1 SP DC2 metro
Intra DC architecture extend
beyond metro
Tunable lasers and coherent receivers key
enablers
Key enablers
Transmitter can tune its lasers frequency Receiver can select any channel from of a
to any channel in the ITU grid. composite (unfiltered) signal.
Tunable lasers work with colorless add/drop to enable touchless changes in the frequency of an optical
signal. Coherent receivers simplify the construction of colorless and omni-directional ROADM nodes, by
eliminating the need to de-multiplex a signal down to the individual wavelength.
100G Technology: Coherent Detection
Direct Detection
Must correct for impairments in the physical domain (insert DCUs)
Forced to live with non-correctable impairments via network design (limit distance, regenerate,
adjust channel spacing)
Dumb detection (OOK), no Digital Signal Processing, only FEC
DCU DCU DCU
DD DD
Regen
Coherent Detection
Moves impairment correction from the optical domain into the digital domain
Allows for digital correction of impairments (powerful DSP) vs. physical correction of impairments
(DCUs). Adds advanced FEC.
Massive performance improvements over Direct Detection.
CD
Dispersion
DCU 2016 Compensation 76Unit
Cisco and/or its affiliates. All rights reserved. Cisco Public
Todays SW selectable Data Rates
Modulation Baud Rate Line Rate Payload Rate Distance
BPSK 28 GBaud 56 Gbps 50 Gbps 10,000 km
QPSK 32 GBaud 112 Gbps 100 Gbps 6,800 km
16-QAM 32/40 GBaud 224 Gbps 200/250 Gbps 1,200 km
CFP2 ACO Coherent Optics Pluggable
32GBaud
Integrated Coherent Optical TX

Coherent 4 Transmitter
Optical Signal
DSP
Integrated Coherent Optical
Receiver RX
4
On Host Board CFP2-ACO Module
Optics in the pluggable CFP2, electronics on the line card

Reduces the components inside the module improved power management
Only a CFP2-ACO can be used on the port; not gray optics
ACO Analog Coherent Optics

The WDM promise of Silicon Photonics
100G DPQPSK Measurement Results OFC 2013
DP-QPSK Eye Opportunistic evaluation.

Power Dissipation <1W Lot of room for improvement
including drive circuits with optimized ICs
1.0E-01
SiP Modualtor 1.0
1.0E-02 BER=1e-2 BER=1e-3
OSNR Penalty [dB]

LN Modualtor
BER=1e-4 BER=1e-5
1.0E-03 0.5
BER
1.0E-04
0.0
1.0E-05
-0.5
1.0E-06
1.0E-07 -1.0
12.00 13.00 14.00 15.00 16.00 17.00 18.00 19.00 20.00 0 10000 20000 30000 40000 50000
OSNR[dB/0.1 nm] CD [ps/nm]
B-t-B Measurements @ 100Gbps OSNR Penalty of SiP wrt LiNbO3
Silicon Photonics suitable for 250G 2016 Cisco and/or its affiliates. All rights reserved. Cisco Public 80
High Speed Client Implementations
Interface Independent Functionality
IP-over-
Router Ethernet
Router Router
OTN
IP-over-DWDM
DWDM Client Client
Pre-FEC error threshold is monitored directly by
router
RP initiates fast re-route based on internal trigger
directly from PLIM
FEC
Gray Client - Ethernet OTN
OTN
Pre-FEC error threshold is monitored by transponder Ethernet
Trigger
Trigger
Ethernet trigger is generated by transponder and
sent to router which initiates fast re-route Transponder
Transponder
Gray Client - OTN

FEC FEC
Pre-FEC error threshold is monitored by transponder
OTN PF-FDI trigger is generated by transponder and
sent to router which initiates fast re-route
OTN interface monitors end-to-end path
Beyond 100G/250
Client Side Industry Optics Roadmap
Ethernet and signaling rates
Ethernet Rates
Signaling
10 GbE 40 GbE 100 GbE 400 GbE 25 GbE 50 GbE 200 GbE
Rates
Enabled by
2.5 Gb/s
availability
of
Then drove Enabled by Enabled by

10 Gb/s
development availability availability
of of of
Then drove Enabled by Enabled by

25 Gb/s
development availability availability
of of of
Is driving
50 Gb/s Enabled by
development
availability of
of
Will be
optimized by Is driving
100 Gb/s development
of
~ Chronological
What Will Change to Continue to Scale?
28G 56G Electrical Optical Fibers
SMF or MMF
28G 56G Electrical Electrical
Analog
Lanes Lanes
400G 400G
S&R Coherent 600G Line
ASIC DSP 200G System
400G 400G
DWDM
Multi-Terabit Multi-Rate Optic
Processor DSP
100G 200G/400G Grey Optics
SR-10, SR-4, CWDM-4, +8QAM
LR-4 Lite, LR-4
+32QAM
Client Side Optics: QSFP28, QSFP56,
QSFP28-DD, QSFP56-DD, COBO +64QAM
Flexibility: FlexE, FlexMod, and FlexRate Double Baud Rate
5
Introducing QSFP-DD (new 2x 100 GbE and 400
GbE capable pluggable module)
Improved thermals supports

>2.5x QSFP power
QSFP-DD
75.85 mm
70.00 mm Essentially the same as QSFP but with

extra row of contacts. Allows boards to be
QSFP backwards compatible to both.
Supports 8 electrical IO
8x50G (CDAUI) 400 GbE
Dual 4x25G (CAUI) 2x 100 GbE
Host System fully backwards compatible to QSFP
Cooling/Thermal improvements enable up to 10W

Advanced 2x1 cage design
MSA has been announced

13 founding companies
Spec under development
Original QSFP contacts
Line Side Objectives for 100Gb/s
Cost reduction
Increased system density
OSNR performance improvement
Spectral efficiency
reach optimized interfaces
capacity optimized interfaces
flexible wavelength assignment (flex spectrum)
optimized channel spacing
cross-talk compensation between channels
Line Interfaces Whats Next ?
Higher data rates: 200G, 400G, 1T
Flex Ethernet ... available today
Flex Spectrum
Flexible modulation techniques
PM-BPSK, PM-QPSK, PM-16QAM, PM-64QAM, .
All come at the expense of reduced distance
Hybrid Modulation for Improved capacity

Spectral Efficiency
Nyquist Filtering
Dynamic bandwidth filters (Flex spectrum ROADM technology)
Network Today ......
NPU Transponder DWDM
10GE/40GE/100GE 10G/40G/100G DWDM 50Ghz/100Ghz

interfaces interfaces DWDM systems
Ethernet MAC/PCS layer fixed at 10G, 100G , 400G
SW Selectable Modulation (100G to 200G /wavelength)
Fixed Grid DWDM systems allow 50Ghz OR 100Ghz channels moving to
flexspectrum
Optimize Data Rate vs Reach
Flex Ethernet Beak existing dependancies FlexE Client a FlexE Client b FlexE Client z
Enable flexibility on Ethernet interface: 64B/66B

encode
64B/66B
encode

64B/66B
encode
Error Control
Block
Generator
Client
Eliminate existing Hierarchies - Custom rates Clock

Domain
Idle insert/ Idle insert/ Idle insert/
FlexE delete delete delete
Clock 66B block distribution and
Domain Insertion into master calendar
Eliminate LAG Inefficiencies Control Calendar
Calendar
Match transport bandwidth

Overhead Insertion FlexE Client a FlexE Client b Distribution
FlexE Client z
Sub-calendar
Sub-calendar
Sub-calendar

64B/66B 64B/66B 64B/66B
PHY N
PHY B
PHY A
Break Ethernet and transport roadmap marriage
decode decode decode

Client
FlexE defined
Idle Idle Idle Clock
sublayers Doma
insert/ insert/ insert/
FlexE
in
802.3 defined delete delete delete
sublayers 66B block extraction from Clock
Standardized under OIF Control

PCS lane distribution
and AM insertion
Scramble Scramble master calendar
Calendar
Scramble Doma
in
Deskew
100GBASE- 100GBASE- 100GBASE- Calendar
Overhead extraction
R PMA R PMA R PMA Interleaving
Effort initially patented by Cisco
Sub-calendar
Sub-calendar
Sub-calendar
LF generator
PHY A PHY B N
PHY
PHY B
PHY N
PHY A
Lower Layers Lower Layers Lower Layers
and PMD and PMD and PMD
FlexE defined
Implementation led by Cisco, Google, Juniper sublayers

802.3 defined
sublayers
Descramble Descramble Descramble
and others PCS lane deskew,

interleave, and
AM removal 100GBAS 100GBAS 100GBAS
E-R PMA E-R PMA E-R PMA
Above figures are copied from the OIF FlexE 1.0 Implementation
agreement. Available on oiforum.com early in 2016.
Optimize Data Rate vs Distance
Flex Ethernet (FlexE) Worlds first Demo OFC 2016
Ability to leverage the full capacity of the NPU
Ability to specify any Data Rate with no Hashing inefficiencies
Ability to grow the Data Rate in 25/50G granularity upto max NPU capacity
independent of IEEE or ITU hierarchies
Ability to dynamically adjust data rates to match the physical layer performance
400Gig
400Gig 400Gig
X
NPU NPU
50Gig
350Gig
Truly Optimize Data Rate vs Reach
Tools to Increase and Optimize System Capacity
Speed up & WDM & Modulation
Multi-Modulation Superchannel Formation

Adjust spectral efficiency by Optimize spectral efficiency by tightly
transmitting more or less bits per spacing sub-carriers using Flex-
symbol at a given baud rate Spectrum ROADM
Flex Baud Rate Hybrid Modulation

Increase the bit rate by increasing Mix different modulation formats in the
the rate at which symbols are time domain to achieve a greater
transmitted bandwidth/distance granularity
Higher order modulation schemes
BPSK QPSK 8-QAM 16-QAM 64-QAM
Bits/
Symbol 2 4 6 8 12
(2 pol.)
Capacity 50G 100G 150G 200G 300G

@32Gbaud
Increasing the capacity per WDM channel requires sending

more complex signals; trading between spectral efficiency
and reach
3x (64-QAM vs QPSK) gain
Baud rate increase
Higher baud rates

2x rate (1/2 carriers), but with Nyquist spectral
density improvements only below 5%
While higher NLI and implementation
impairment might indeed affect reach/bandwidth.
Meng Qiu, Qunbi Zhuge, Xian Xu, M. Chagnon, M. Morsy-Osman, and
David V. Plant Subcarrier Multiplexing Using DACs for Fiber
Nonlinearity Mitigation in Coherent Optical Communication Systems,
in
Proc. OFC 2014, paper Tu3J.2, San Francisco (CA), Mar. 2014.
Will higher baud rate be really required by bandwidth demand ?

No, transport over multiple wavelengths will be supported by new protocols (FlexE,
OTUCn)
But cost and real estate reduction will justify it.
Optimize Data Rate vs Distance
Flexible Modulation (FlexMod)
Different modulations provide
different capacity
Different modulations provide
different reach
Next Gen Chip sets provide
the ability to SW config
Capacity vs Reach
Flex Mod will close the Gap
and provide for 25Gig
granularity
Dynamic Data Rates
Current Solutions are Still too Inflexible FlexE and FlexMod optimize Capacity vs Reach
What we need:
400Gbps 64QAM More granularity and uniformity of
bandwidth / distance steps
Todays Hierarchy defined in the IEEE and ITU provides
network limitations
Terminate predefined Standard Data Rates
10G, 100G, 400G, . 1.6T?
200Gbps 16QAM Data Rate specified by reach
Bit Weakens ability to optimaze DR vs. Reach
Rate
Wasted Capacity
100Gbps QPPSK
50Gbps BPSK
Distance / OSNR
Adoption of hybrid modulation
Interleaving of different modulation schemes
symbols enables continuous optimization of the
capacity for every reach.
Flex Mod and Flex E allows for the mixing of
different Constellations providing for 25GHz of
Data Rate Granularity
16-QAM QPSK 16-QAM QPSK 16-QAM
time
Time Domain
50G
Hybrid 32 GBaud
BPSK
BPSK
BPSK
QPSK
BPSK
BPSK
BPSK
QPSK
BPSK
BPSK
BPSK
QPSK
BPSK
BPSK
Modulation QPSK QPSK QPSK QPSK QPSK QPSK QPSK
Mix of constellations in
QPSK QPSK QPSK 16QAM QPSK QPSK QPSK
the time domain

QPSK 16QAM QPSK 16QAM QPSK 16QAM QPSK
16QAM 16QAM QPSK 16QAM 16QAM 16QAM QPSK

Variable reach 16QAM 16QAM 16QAM 16QAM 16QAM 16QAM 16QAM 200G
Signal processing needs 16QAM 16QAM 16QAM 64QAM 16QAM 16QAM 16QAM
only small changes 16QAM 64QAM 16QAM 64QAM 16QAM 64QAM 16QAM
Add one new modulation 64QAM 64QAM 16QAM 64QAM 64QAM 64QAM 16QAM
format 64QAM 64QAM 64QAM 64QAM 64QAM 64QAM 64QAM 300G

16QAM 16QAM 16QAM 64QAM 16QAM 16QAM 16QAM

42 GBaud
64QAM 64QAM 64QAM 64QAM 64QAM 64QAM 64QAM 400G


56 GBaud 64QAM 64QAM 16QAM 64QAM 64QAM 64QAM 16QAM
64QAM 64QAM 64QAM 64QAM 64QAM 64QAM 64QAM 600G

DWDM Network capacity limited
by channel spacing imposed with fix ITU Grid
Superchannels require a new kind of ROADM, one that can switch
chunks of bandwidth larger and yet more granular than 50GHz
50 GHz ITU Grid 50 GHz ITU Grid

12.5 GHz Slices
Superchannel with Minimal Spacing

Rigid Spacing,Wasted Spectrum
Efficient Spectrum Use
Each 50GHz carrier provisioned and Superchannel switched through the
switched individually ROADM network as a single entity
This requires Flexible Spectrum allocation Flex Spectrum

Available today!!
Flex Spectrum
100 Gb/s 100 Gb/s Pulse shaped

PM-QPSK PM-16QAM 100 Gb/s
PM-16QAM
fstart1 fstop1 fstart2 fstop2
The amount of spectrum allocated to a given wavelength can be flexibly provisioned
Aggregates continuous portions of the spectrum with programmable start/ stop frequencies
Can allow growth up to 1Tb/s bandwidth
ITU-T Superchannels
WDM channels with a granularity of 12.5 GHz, and

Ability to define an aggregate superchannel spectral width of N 12.5 GHz
Accommodates any combination of optical carriers, modulations, and data rate.
FlexSpectrum & Capacity Relationships
80ch system: From 4Tb/s to From 16Tb/s to 24Tb/s
6Tb/s per fiber Moving from Moving from 50GHz to
50GHz to 33GHz Chs spacing 33GHz Chs spacing
From 8Tb/s to 12Tb/s per fiber

Moving from 50GHz to 33GHz
Chs spacing
Network Tomorrow .......
Flexible, efficient and dynamic mapping of packet services to optical transport
NPU Transponder DWDM
Superchannels
2x50G 2x200G
Flex FlexE Flex Mod FlexFlexspectrum

Spectrum
Flexible nx/25G 50G/100G/200/250G/+ Flexible nx12.5Ghz
12.5/50Ghz/100Ghz
interconnects DWDM interfaces channels
DWDM systems
Network Operators are Leaving Ketchup in the Bottle
NPU Friction Ethernet Friction Transponder Friction DWDM
10G
25G 50G
200G 40G 100G ITU
50G 150G 50GHz
Terabits 100G 200G Grid
200G
400G
NPU Capacity Growing Interconnect Efficiency Spectrum Efficiency

We need to reduce friction between different layers of the network to get the more ketchup out of the
bottle
Client side and Line side optics innovations are the key to success
Summary
Agenda
Introduction
Industry Trends
Standards
Client Side Optics
Impact of High Speed Optics on the DC Fabric
Line Side Optics
Beyond 100G
Conclusion
Alignment Needed to Achieve TCO Goals
DC Network Infrastructure
ASIC BW & Port
Speed
Innovation
Standardization
Open Ecosystems
Cabling Optics Speed and

Infrastructure Size
Summary - Trends
Transition infrastructure to duplex fiber for lower overall cost
Anyport technology with 10G/25G/40G/100G interoperability
Balance choice of optics with cost, reach, power, density, performance and
packaging
Move to high speed optics in the DC fabric improves application performance
CMOS photonics enables enable new generation of SMF optics (CPAK) and
beyond
Move to SMF backbone in DC will require low cost short reach SM optics
Evolution of high speed optics will enable flexible bandwidth, increased system
performance, drive network architecture and facilities consideration
Cisco continues to invest and lead the industry in optics innovation to drive to
lower cost structure.
Summary
There are mismatches between NPU capacity, Ethernet rates, and
transponder rates
New Ethernet rates combined with line side DWDN advances will
drive greater efficiency
Higher cost sensitivity & shorter investment cycles at the edge
Backward compatibility will de-couple investment cycles for server/
ToR & aggregation switching
Flex Spectrum and Flex Modulation are a good start towards
flexibility of trading off bandwidth vs. distance
Hybrid Modulation plus Flex Ethernet will allow operators to squeeze
every bit of bandwidth out of their networks.
Complete Your Online Session Evaluation
Give us your feedback to be
entered into a Daily Survey
Drawing. A daily winner will
participate in a raffle.
Complete your session surveys
through the Cisco Live mobile
app or from the Session Catalog
on CiscoLive.com/latam.
Dont forget: Cisco Live sessions will be available

for viewing on-demand after the event at
CiscoLive.com/Online
Presentation ID 2016 Cisco and/or its affiliates. All rights reserved. Cisco Public 111
Continue Your Education
Demos in the Cisco campus
Walk-in Self-Paced Labs
Table Topics
Meet the Engineer 1:1 meetings
Related sessions
Presentation ID 2016 Cisco and/or its affiliates. All rights reserved. Cisco Public 112
Cisco Spark
Ask Question, Get Answers www.ciscospark.com
Use Cisco Spark to communicate with the speaker after the event!
What if I have a question after visiting Cisco Live? ... Cisco Spark
*Get the Cisco Spark app from iTunes store or Google Play store
1. Go to the Cisco Live Mobile app
2. Find this session
3. Click the join link in the session description
4. Navigate to the room, room name = Session ID
5. Enter messages in the room
cs.co/ciscolive/#session ID
E.g: session ID = BRKACI-2001
Spark rooms will be available until Friday 18 November 2016
Thank you

Brkopt 2116

Uploaded by

Document Informationclick to expand document informationCisoc

Document Informationclick to expand document information

Copyright:

Available Formats

Brkopt 2116

Uploaded by

Document Information

Original Title

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

Brkopt 2116

Uploaded by

Copyright:

Available Formats

High Speed Optics

25G, 40G, 100G & Beyond

Errol Roberts, DSE

NPU Friction Ethernet Friction Transponder Friction DWDM

NPU Capacity Growing Interconnect Efficiency Spectrum Efficiency

IEEE defined Ethernet Regen

DC & Client Optics Line Optics

To keep pace, Enterprise and Service Providers need

Solutions need to offer lower cost/bit for the overall network

9% between data centers for replication & inter-

73% will be coming from within the datacenter,

1 zetabyte is trillion gigabytes

25Gb/s, 50Gb/s, 200Gb/s, 400Gb/s

Development and deployment at

6 Ethernet speeds in 5 years, same

SDH Payload Eth Payload

1985 1990 1995 2000 2005 2010 2015

OTN aligned with Ethernet speeds

Multiple Spines 100G Links

Wider Spine 10 - 25G Servers

Shorter link distances with higher data

Time line of faceplate BW density GLP of routing line cards fully

As faceplate bandwidth increases, the number of high BW ports increases and

Traditional Backbone Core

Data Centers driving investment in the Metro

Enterprise Edge Routing 1G 10G 10G 100G 10G 100G

SP/Cloud Core Routing 10G 40/100G 10G 100G 100G 200/400G

Current pluggables limit the faceplate density

Switch Optical engine on-board the line card

Switch Silicon Photonics Optical Engine mounted on the package

face-plate density & signal

How can we go faster

Form Factor Size reduction Port Density increase

Power reduction Port Density increase

Reach System/network scaling

Packaging simplification Increased Yield, lowers cost

The next speed (400G/1T) System Scale, lower costs

Cabling Optics Speed and

Toolkit: Speed-up, WDM, Modulation

Lessens many transmission penalties

Need to optimize all

Design Choices will vary by

Never ending balancing act!

Parallel fiber (MPO) Dual fiber (LC)

Optimized single lane interconnect

Gb/s and 25 &100 Gb/s Ethernet 4 x 10Gb/s 40Gb/s

Single 50 Gb/s SFP56 port

Backplanes 100GBASE-KR4 4 x 25 Gb/s (NRZ) Deployed. Legacy 4x installed

Chip-to-Module CDAUI-8 8 x 50 Gb/s PAM-4 IEEE P802.3bs in Task Force

SMF Optical 400GBASE-FR8 8 x 50 Gb/s PAM-4 IEEE P802.3bs in Task Force

13.6 11.6 12.4 9.5 8.5

Power <32 W < 7.5 W < 8W, 12 W < 5 or 6 W <= 3.5 W

QSFP28 is the NEW! QSFP 100G transceiver form factor

ASIC Lane scheme 1 x 10G 1 x 25G 1 x 50G

SFP56 50G (future)

CDR RX provides similar port density as 40G &

Market need is also driving non-standard interfaces