iSLIP Switch Scheduler

Ali Mohammad Zareh BidokiApril 2002

Table of Contents The place Buffer in Crossbar Switches Example of Fabrics

PIM iSLIP (in CISCO 12000 ,5Gb/s router and

Tiny Tera 0.5 Tb/s) RRM WFA PP_VOQ

Multicasting A 2.5Tb/s Router

The place of Buffer in Crossbar

Output Buffer Shared Buffer Input buffer

InterconnectsTwo basic techniques

Input Queueing Output Queueing

Usually a non-blockingswitch fabric (e.g. crossbar)

Usually a fast bus

InterconnectsInput Queueing with Crossbar

configuration

Data

In

Data Out

Arbiter

Memory b/w = 2R

Input QueueingHead of Line Blocking

Dela

y

Load58.6% 100%

Head of Line Blocking

Virtual output Queuing Crossbar Switch fabric

Crossbar Switch fabric

To port 1

To port 1

To port 1

To port 1

Inpu

t que

ues To port 2

To port 2

To port 2

Port n queue

To port n

To port n

To port n

To port n

Port 2 queuePort 1 queue

Input port 1

Queue scheduler

Input QueueingVirtual output queues

Input QueueingVirtual Output Queues

Dela

y

Load100%

Which is better? Virtual output Queue (input

queue). Ideal Output queue.

Input QueueingVirtual output queues

ArbiterComplex!

VOQ Arbiter Input memory management

Problem Definition (bipartite)

Maximum or Maximal matching

Request Graph Maximum Matching Maximal Matching

Maximum or Maximal matching

Maximum matching Maximizes instantaneous throughput Starvation Time complexity is very high in Hardware (o(n3))

Maximal matching Can’t add any connection on the current match

without alert existing connections More practical (e.g. WFA, PIM, iSLIP, DRR,RRM)

Matching Algorithms

Each algo. is evaluated by four parameters:1. Latency(Throughput).2. Starvation free.3. Fast.4. Implementation.

3. iSLIP – Iterative Serial-Line IP(base on PIM and RRM)

2. RRM – Round-Robin Matching1. PIM - Parallel Iterative Matching

We will discuss three different matching algo.:

When no new matching can be found, the algorithm stops.

3. Accept - If an input receives a grant, it accepts one by selecting an output randomly among those that granted to this output..

2. Grant - If an unmatched output receives any requests, it grants to one by randomly selecting a request uniformly over all requests.

1. Request - Each unmatched input sends a request to every output for which it has a queued cell.

PIM - Parallel Iterative MatchingThe basic matching algorithm. Each iteration of the algorithm follows these three steps:

PIM Each iteration will eliminate at least ¾ of the remaining

connections Converge in O(logN) iterations No input queue is starved if service No memory or state is used

At the beginning of each cell time, the match begins over, independently of the matches that were made in previous cell times

PIM does not perform well for a single iteration: it limits the throughput to approximately 63%, only slightly higher than for a FIFO switch.

This is because the probability that an input will remain ungranted is (N-1/N)N , hence as N increases, the throughput tends to .63% (1-(1/e))

Implementation is hard in Hardware

RRM – Round-Robin Matching

The pointer gi to the highest priority element of the round-robin schedule is incremented (modulo N) to one location beyond the granted input.

2. Grant - If an output receives any requests, it chooses the one that appears next in a fixed, round-robin schedule starting from the highest priority element. The output notifies each input whether or not its request was granted.

1. Request - Each unmatched input sends a request to every output for which it has a queued cell.

g2

g4

g1a1

a3

a4

1

23

4

1

23

4

1

23

41

23

4

1

23

4

1

23

4

RRM – Round-Robin Matching

The pointer ai to the highest priority element of the round-robin schedule is incremented (modulo N) to one location beyond the accepted output.

3. Accept - If an input receives a grant, it accepts the one that appears next in a fixed, round-robin schedule starting from the highest priority element.

The pointer gi to the highest priority element of the round-robin schedule is incremented (modulo N) to one location beyond the granted input.

2. Grant - If an output receives any requests, it chooses the one that appears next in a fixed, round-robin schedule starting from the highest priority element. The output notifies each input whether or not its request was granted.

1. Request - Each unmatched input sends a request to every output for which it has a queued cell.

a1

a3

a4

1

23

4

1

23

4

1

23

41

23

4

1

23

4

1

23

4

g2

g4

g1

RRM – Round-Robin Matching

The pointer ai to the highest priority element of the round-robin schedule is incremented (modulo N) to one location beyond the accepted output.

3. Accept - If an input receives a grant, it accepts the one that appears next in a fixed, round-robin schedule starting from the highest priority element.

The pointer gi to the highest priority element of the round-robin schedule is incremented (modulo N) to one location beyond the granted input.

2. Grant - If an output receives any requests, it chooses the one that appears next in a fixed, round-robin schedule starting from the highest priority element. The output notifies each input whether or not its request was granted.

1. Request - Each unmatched input sends a request to every output for which it has a queued cell.

a1

a3

a4

1

23

4

1

23

4

1

23

41

23

4

1

23

4

1

23

4

g2

g4

g1

RRM – Round-Robin Matching

g2

g3

g1a1

a2

a3

12

3

12

3

12

312

3

12

3

12

3

First cycle

The RRM is not starvation free:In the following example, we assume there are always cells waiting to be transferred. The destination is always the same.

RRM – Round-Robin Matching

g2

g3

g1

a1

a2

a3

12

3

12

3

12

312

3

12

3

12

3

First cycle

The RRM is not starvation free:In the following example, we assume there are always cells waiting to be transferred. The destination is always the same.

RRM – Round-Robin Matching

g2

g3

g1

a1

a2

a3

12

3

12

3

12

312

3

12

3

12

3

First cycle

The RRM is not starvation free:In the following example, we assume there are always cells waiting to be transferred. The destination is always the same.

RRM – Round-Robin Matching

g2

g3

g1

a1

a2

a3

12

3

12

3

12

312

3

12

3

12

3

First cycle

The RRM is not starvation free:In the following example, we assume there are always cells waiting to be transferred. The destination is always the same.

RRM – Round-Robin Matching

g2

g3

g1

a1

a2

a3

12

3

12

3

12

312

3

12

3

12

3

First cycle

The RRM is not starvation free:In the following example, we assume there are always cells waiting to be transferred. The destination is always the same.

RRM – Round-Robin Matching

g2

g3

g1

a1

a2

a3

12

3

12

3

12

312

3

12

3

12

3

Second cycle

The RRM is not starvation free:In the following example, we assume there are always cells waiting to be transferred. The destination is always the same.

RRM – Round-Robin Matching

g2

g3

g1

a1

a2

a3

12

3

12

3

12

312

3

12

3

12

3

Second cycle

The RRM is not starvation free:In the following example, we assume there are always cells waiting to be transferred. The destination is always the same.

RRM – Round-Robin MatchingThe RRM is not starvation free:In the following example, we assume there are always cells waiting to be transferred. The destination is always the same.

g2

g3

g1

a1

a2

a3

12

3

12

3

12

312

3

12

3

12

3

Second cycle

At this point the sequence of the events will repeat itself:Outputs 1 and 3 will always grant input 1, while output 2 will always grant input 1 at the first iteration of the first cycle, but input 1 will select output 1 indefinitely, leaving output 2 to grant either input 2 or input 3.Thus the cell from input 1 to output 2 will never be granted.In order to solve this starvation the iSlip algorithm was developed.

RRM RRM overcomes two problem

Complexity Unfairness

the round-robin arbiters are much simpler and can perform faster than random arbiters.

The rotating priority aids the algorithm in assigning bandwidth equally and more fairly among requesting connections.

Its throughput is about 63%

2x2 switch with RRM algorithm under heavy load.

synchronization of output arbiters leads to a throughput of just 50%.

Perfo

rman

ce

Synchronization

iSLIP – Iterative Serial-Line IP2. Grant - If an output receives any requests, it chooses the one that appears next in a fixed, round-robin schedule starting from the highest priority element. The output notifies each input whether or not its request was granted.

g2

g4

g1a1

a3

a4

1

23

4

1

23

4

1

23

41

23

4

1

23

4

1

23

4

The pointer gi to the highest priority element of the round-robin schedule is incremented (modulo N) to one location beyond the granted input if and only if the grant is accepted in Step 3 of the first iteration.

iSLIP – Iterative Serial-Line IP

The pointer gi to the highest priority element of the round-robin schedule is incremented (modulo N) to one location beyond the granted input if and only if the grant is accepted in Step 3 of the first iteration.

2. Grant - If an output receives any requests, it chooses the one that appears next in a fixed, round-robin schedule starting from the highest priority element. The output notifies each input whether or not its request was granted.

g2

g4

g1

1

23

4

1

23

4

1

23

41

23

4

1

23

4

1

23

4

a1

a3

a4

iSLIP properties

Property 1. Lowest priority is given to the most recently made connection.

If input i successfully connects to output j, both a i and g j are updated and the connection from input i to output j becomes the lowest priority connection in the next cell time.

Property 2. No connection is starved. This is because an input will continue to request an output until it is successful. The output will serve at most other inputs first, waiting at most N cell times to be accepted by each input. Therefore, a requesting input is always served in less than N 2 cell times.

Property 3. Under heavy load, all queues with a common output have the same throughput. This is a consequence of Property 2: the output pointer moves to each requesting input in a fixed order, thus pr-viding each with the same throughput.

iSLIP properties Simple to implement in hardware Starvation free Its throughput is about 100% It is fair As the load increases, the number of

synchronized arbiters decreases (see Figure), leading to a large sized match.

Under uniform 100% offered load the iSLIP arbiters adapt to a time-division multiplexing scheme.

It converge in O(1)

Bursty Arrivals

Burstiness Reduction Results indicate that iSLIP reduces the average burst

length, and will tend to be more burst-reducing as the offered load increases.

This is because the probability of switching between multiple connections increases as the utilization increases.

As the load increases, the contention increases and bursts are interleaved at the output. In fact, if the offered load exceeds approximately 70%, the average burst length drops to exactly one cell.

Burstiness Reduction

Multiple Iteration The pointer gi to the highest priority element of the

round-robin schedule is incremented (modulo N) to one location beyond the granted input if and only if the grant is accepted in Step 3 of the first iteration.

Note that pointers g i and a i are only updated for matches found in the first iteration.

It converge in O(logN)

Multiple Iteration

All with 4 iterations

Implementation

Implementation(2N arbiters)

Implementation(N arbiters)Each arbiter is used for both inputand output arbitration. In this case, each arbiter contains two registers to hold pointers gi and ai .

Implementation

Priority in iSLIP

Why iSLIP is good for high speed?

input buffers are separated Separated scheduler for each input

and output Each work independently

Multicasting Fanout splitting: higher throughput, but not as simple Non-fanout splitting:Easy, but low throughput

Multicasting (ESLIP: Combining Unicast and Multicast-use in CISCO 12000)

IP packet in iSLIP switch (2N2 Queue)

Arbiter

Linecard

LCS

LCS

1: Req

LCS Ingress Flow control(2.5Tb/s)

3: DataSwitch

Scheduler

Switch

Scheduler

2: Grant/credit

Seq num

Switch

Fabric

Switch

Fabric

Switch Port

Req

Grant

LCS Over Optical Fiber 10Gb/s Linecards

10Gb/s Linecard

LCS

Switch

Scheduler

Switch

Scheduler

Switch

Fabric

Switch

Fabric

10Gb/s Switch Port

LCS

12 multimode fibers

12 multimode fibers

2.5Gb/s LVDS

GENETQuad Serdes

2.56Tb/s IP router

LCS

1000ft/300m

Port #256

Port #1

2.56Tb/s switch core

Linecards

PortProcessor

opticsLCS Protocol

optics

PortProcessor

opticsLCS Protocol

optics

Crossbar

Switch core architecturePort #1

Scheduler

Request

Grant/Credit

Cell Data

Port #256