If You Build It, They Will Come: The SNBENCH Architecture

1
If You Build It, They Will ComeThe SNBENCH
Architecture

• Adam BradleyAzer Bestavros Michael Long
• Computer Science Department
• Boston University

2
Before we begin

• Welcome
• To
• Summer!

3
Sensorium Infrastructure _at_ BU
Sensorium A common space equipped with video
sensors (VS) for ubiquitous recognition and
tracking of activities therein

• Infrastructure
• Range of VS Elements
• Programmable VS Network
• Backend compute engines
• Backend TByte storage
• Mobile/wireless query units
• Research Engineer

4
snBench

• The Sensorium is the computer
• Design/implement the programming and run-time
  infrastructure necessary for developers to
  specify and deploy truly distributed applications
  over a heterogeneous network of Sensing Elements
  (SEs) and Computing Elements (CEs)

What sensors could I use and what functionality
do I get from them?
5
snBench Goals

• Write Once, Run Wherever
• Dont program nodes Program the network!
• Start with building blocks
• Sensors
• Stock algorithms (edge detect, face count, FFT)
• Dynamic modules (novel algorithms)
• Glue together with high-level language
• Conditionals, loops, functions
• Pretend the network isnt there
• Single System Image Programming Paradigm

6
snBench Programming Cycle

• Program
• Program specified by gluing together building
  blocks using SNAFU language
• Compile
• SNAFU program is compiled to produce a plan of
  execution expressed in STEP
• Map and Link
• Service Dispatcher decomposes STEP plans into
  smaller linked dispatch-able STEPs
• Load and Execute
• STEP plans are dispatched (i.e., loaded) into
  SXE execution environments

7
SNAFU SNet Apps as FUnctions!

• Functional specification language
• e.g., identify the face seen through camera 1

identify(facefind(snapshot(cam1)))
8
SNAFU SNet Apps as FUnctions!

• Use annotative functions for constraints
• e.g., minimum acceptable resolution
• e.g., what streams can be exposed

facecount(resn(800x600x24b,snapshot(cam1)))
public(facecount(snapshot(private(cam1)))))
9
SNAFU SNet Apps as FUnctions!

• Events in time captured by triggers
• e.g., motion detected at night triggers email

email(security_at_bu.edu, trigger(
(motion(snapshot(cam2)) (2amltNOWlt4am)),
snapshot(cam2)))
10
SNAFU SNet Apps as FUnctions!

• Three trigger types
• trigger(p,a) Wait until p
• do / no-op / until (p) a
• level_trigger(p,a) Whenever p
• while (true) if (p) a
• edge_trigger Whenever p becomes true
• while (true) if (p) a while (p)
• Value of trigger is value of as evaluation
• Level and edge triggers produce streams
• a.k.a. persistent queries living in network

11
SNAFU SNet Apps as FUnctions!

• Trigger QoS (Scheduling annotations)

period(100ms, level_trigger(f(cam1), g(cam1)))
12
SNAFU SNet Apps as FUnctions!

• Retrieving values from triggers
• Non-blocking read - Last result
• Blocking read - Wait for next result
• Fresh read - Wait for a from scratch result
• Recursion
• LAST_TRIGGER_EVALUATION term
• Last value produced by innermost(?) trigger term
• Not sure what to call it head recursion ?

13
STEP Sensorium Typed Exec Plan
Instruction Set Architecture is a DAG
email
edge_trigger
security_at_bu.edu
email(security_at_bu.edu, edge_trigger(
(motion(snapshot(cam2)) (2amltNOWlt4am)),
snapshot(cam2)))

motion
lt
lt
snapshot
clock
4am
2am
cam2
14
STEP Sensorium Typed Exec Plan

• Notes
• Evaluation percolates up from leaf nodes toward
  roots.
• Sensor nodes provide fresh data at all times.
• Function nodes evaluate once then disable
  themselves.
• Trigger nodes can re-enable children for
  re-evaluation.

email
edge_trigger
security_at_bu.edu

motion
lt
lt
snapshot
clock
4am
2am
cam2
15
snBench Runtime Setting

• SNAFU-to-STEP compiler
• SXE Sensorium eXecution Environment
• SD Service Dispatcher

SXE
SXE
SXE
SD, SXE
SXE
SXE
SXE
Compiler, Web Browser, SXE(?)
16
Map, Link, and Dispatch
email
SXE
edge_trigger
security_at_bu.edu

SXE
motion
lt
lt
snapshot
clock
4AM
2AM
SXE
cam2
17
Map, Link, and Dispatch
email
SXE
edge_trigger
security_at_bu.edu
SXE
SXE
18
Why snBench?

• A Sensorium Research Catalyst
• Extrinsic research
• Accessible framework for developing distributed
  sensing applications in heterogeneous networks
• Intrinsic research
• Languages, type systems, compilers, graph
  algorithms, schedulers, QoS engines, naming, etc.
  to make the framework efficient/useful/flexible
• Supporting research
• System context, supporting middleware/services

19
Extrinsic Research

• Flexible substrate for experimenting with
  distributed sensor applications
• Extensible w/ new algorithms (opcodes)
• Trade some speed for versatility and easy
  re-programmability/re-tasking
• Abstracts away the network
• Vision researchers dont need to understand
  communication protocols, RT schedulers, network
  resource reservation, etc.

20
Extrinsic Research Sensorium Target Applications

• Assistive Environments
• e.g. for home/hospice/elder care/
• Safety Monitoring
• e.g. in factories/daycare/garages/subways
• Intelligent Spaces
• e.g. for classrooms/meeting rooms/theaters/farms
• Secure Facilities and Homeland Security Uses
• e.g. at airports/embassies/prisons/CS labs/
• People Flow/Activity Studies
• e.g. at malls/interstates/

21
Intrinsic/Extrinsic Research

• Why limit ourselves to passive
  sensing?Control actuators with snBench programs!
• Multi-DOF Cameras
• Mobile Sensors
• Robots
• Control theory issues

22
Intrinsic Research

• Scheduling/Linking/Binding
• How did we arrive at this partitioning?
• How did we arrive at these assignments?

23
Scheduling Processing Capacity
Load averages? Busy rate? STEP nodes/s? Realtime
scheduler?
SXE
?
SXE
SXE
SXE
24
Scheduling Network Capacity
8Mb/s95
SXE
?
100Mb/s40
SXE
100Mb/s10
100Mb/s20
512kb/s75
SXE
SXE
25
Scheduling Code Presence
motion
email
empty
empty
delta
facefind
bodytrack
email
SXE
motion
oflow
delta
empty
?
SXE
snapshot
delta
SXE
SXE
26
Intrinsic Research

• Scheduling Constrained Graph embedding
  and optimization!

motion
email
empty
empty
delta
facefind
bodytrack
email
8Mb/s60
SXE
?
motion
oflow
delta
empty
100Mb/s40
SXE
100Mb/s10
100Mb/s20
snapshot
delta
512kb/s75
SXE
SXE
27
More Scheduling

• Multiple simultaneous programs may share STEP
  sub-graphs

email(security_at_bu.edu, block(
edge_trigger(motion(snapshot(cam2))
(2amltNOWlt4am), snapshot(cam2)))
trigger( facerecognizer( block(
edge_trigger(motion(snapshot(cam2))
(2amltNOWlt4am),
snapshot(cam2))), facelibrary(Adam
Bradley)), email(adams.wife_at_gmail.com, Hes
working late again.))
28
More Scheduling CSE

• Common Subexpression/Subgraph Elimination

email(security_at_bu.edu, block(
edge_trigger(motion(snapshot(cam2))
(2amltNOWlt4am), snapshot(cam2)))
trigger( facerecognizer( block(
edge_trigger( motion(snapshot(cam2))
(2amltNOWlt4am), snapshot(cam2))),
facelibrary(Adam Bradley)),
email(adams.wife_at_gmail.com, Hes working late
again.))
29
More Scheduling CSE

• Common Subexpression/Subgraph Elimination

email(security_at_bu.edu, block(
edge_trigger(motion(snapshot(cam2))
(2amltNOWlt4am), snapshot(cam2)))
Common Subgraph
trigger( facerecognizer( block(
edge_trigger( motion(snapshot(cam2))
(2amltNOWlt4am), snapshot(cam2))),
facelibrary(Adam Bradley)),
email(adams.wife_at_gmail.com, Hes working late
again.))
30
More Scheduling CSE
Common Subexpression/Subgraph Elimination
email(security_at_bu.edu, block(
edge_trigger(motion(snapshot(cam2))
(2amltNOWlt4am), snapshot(cam2)))
trigger( facerecognizer( block(
edge_trigger( motion(snapshot(cam2))
(2amltNOWlt4am), snapshot(cam2))),
facelibrary(Adam Bradley)),
email(adams.wife_at_gmail.com, Hes working late
again.))
31
More Scheduling CSE
Common Subexpression/Subgraph Elimination
email(security_at_bu.edu, block(
edge_trigger(motion(snapshot(cam2))
(2amltNOWlt4am), snapshot(cam2)))
SXE
SXE
trigger( facerecognizer( block(
edge_trigger( motion(snapshot(cam2))
(2amltNOWlt4am), snapshot(cam2))),
facelibrary(Adam Bradley)),
email(adams.wife_at_gmail.com, Hes working late
again.))
SXE
32
Intrinsic Research

• Program Optimization
• What to optimize?
• STEP Node count?
• Trigger count? (More or less?)

let x snapshot(cam2) in email(security_at_bu.edu,
block( edge_trigger(motion(x)
(2amltNOWlt4am), x)))
let x snapshot(cam2) in trigger(
edge_trigger(motion(x) (2amltNOWlt4am),
true), email(security_at_bu.edu, x))
33
More Scheduling Architecture

• What if we cant run SXE on a node?
• STEP a compile-able virtual ISA
• Embedded C dialects?
• Java ME?
• Support alternate linking protocols
• Serial (base station)
• SN wireless protocols (e.g. 802.15.4)

34
Intrinsic Research

• Better Programming Languages
• Alternate Execution Environments

SnLOG
SnQL
SnC
SNAFU
STEP
SXE
Native C
JXTA
J2ME
35
Intrinsic Research

• Scheduling/Real-Time Type Systems
• Resource Management Type Inference
• Actualizers (SD is a mini-ITM)
• Static and dynamic type checks

period(100ms, let x period(75ms,
edge_trigger(y, z)) in
edge_trigger(f(x), g(x))
level_trigger( state(4MB, entropymeasure(
bw(2MBps, deltastream(cam1)))),
period_gt(250ms, signal(actuator1, true))
36
Intrinsic Research

• Intentional Naming
• Naming sensors by identity The webcam in
  Azers Office
• Naming sensors by property Any two cams which
  see point X from perspectives gt90 degrees
  apart
• Naming sensors by dynamic attribute Any cam
  which sees Adam
• May depend upon existence of persistent queries.
  What p.q.s should we instantiate to produce the
  highest odds of success at the lowest cost?
• Wearables as part of the Sensorium?

37
Intrinsic Research

• How do you offer RealTime, QoS, etc. if you dont
  know about the timing of atomic operations?
• Live profiling of new opcodes
• Speculative/probabilistic scheduling
• Run-time scheduler parameter changes

38
Supporting Research

• SXE Implementations and Internals
• SXE itself as high-performance service
• Real-time scheduling
• Self-profiling
• Fast I/O delivery (Lives in kernel sandbox?)
• Programmer can upload their own functions
• C, Java, C, Perl, Matlab, whatever
• Automatically generate glue to link with SXE
• Sandboxing issues

39
Current Status

• Whitepaper
• SNAFU and STEP syntax (tentative)
• SNAFU type principles (tentative)
• 1G Implementation (work in progress)
• Java
• SNAFU-to-STEP compiler
• Service Dispatcher
• SXE (with HTTP-based interface)
• JAR-based extensibility
• Expect first live demo mid-summer

40
If You Build It, They Will ComeThe SNBENCH
Architecture

• Adam BradleyAzer Bestavros Michael Long
• Computer Science Department
• Boston University