Session 5
Government Funded Standards
Dr. Edward Baranoski
MIT Lincoln Laboratory
This work is sponsored by the High Performance Computing Modernization Office under Air Force Contract F19628-00-C0002. Opinions, interpretations, conclusions, and recommendations are those of the author and are not necessarily
endorsed by the Department of Defense.
MIT Lincoln Laboratory
999999-1
XYZ 7/12/2016
Outline
• Introduction
• DoD Need
• Standards Goals
• Key Efforts
• Summary
999999-2
XYZ 7/12/2016
MIT Lincoln Laboratory
Why Is DoD Concerned with
Embedded Software?
$3.0
Software
Hardware
Source: “HPEC Market Study” March 2001
Estimated DoD expenditures
for embedded signal and
image processing hardware
and software ($B)
$2.0
$1.0
•
FY
05
FY
04
FY
03
FY
02
FY
01
FY
00
FY
99
FY
98
$0.0
COTS acquisition practices have shifted the burden from “point design”
hardware to “point design” software (i.e. COTS HW requires COTS SW)
•
Software costs for embedded systems could be reduced by one-third
with improved programming models, methodologies, and standards
999999-3
XYZ 7/12/2016
MIT Lincoln Laboratory
Evolution of Software Support Towards
“Write Once, Run Anywhere/Anysize”
DoD software
development
COTS
development
Application
Application
Middleware
Application
Application
Vendor SW
1990
Application
Middleware
999999-4
XYZ 7/12/2016
Middleware
Embedded SW
Standards
Vendor
Software
Vendor
Software
Vendor
Software
2000
Application
Middleware
•
Application software has traditionally
been tied to the hardware
•
Many acquisition programs are
developing stove-piped middleware
“standards”
•
Open software standards can provide
portability, performance, and
productivity benefits
•
Support “Write Once, Run
Anywhere/Anysize”
2005
Application
Middleware
MIT Lincoln Laboratory
DoD Standards Goal
Common Imagery Processor (CIP)
DARPA
Shared memory server
Embedded
multiprocessor
Applied Research
Development
Gov’t
Funded
Initiatives
APG-73
Demonstration
Programs
Goal: Transition advanced software
technology and practices into major
defense acquisition programs
999999-5
XYZ 7/12/2016
Enhanced Tactical Radar Correlator
(ETRAC)
MIT Lincoln Laboratory
Measuring Success
Program Goals
• Develop and integrate software
•
•
technologies for embedded
parallel systems to address
portability, productivity, and
performance
Engage acquisition community
to promote technology
insertion
Deliver quantifiable benefits
Portability:
reduction in lines-of-code to
change port/scale to new
system
Productivity: reduction in overall lines-ofcode
Performance: computation and
communication benchmarks
999999-6
XYZ 7/12/2016
Demonstrate
Gov’t
Funded
Initiatives
Interoperable & Scalable
Performance (1.5x)
MIT Lincoln Laboratory
Outline
• Introduction
• Key Efforts
• Summary
999999-7
XYZ 7/12/2016
•
•
•
•
VSIPL
VSIPL++
DRI
SCA
MIT Lincoln Laboratory
Standards in Systems
Parallel Embedded Processor
System
Controller
Node
Controller
Data Communication:
MPI, MPI/RT, DRI
Control
Communication:
CORBA, HP-CORBA
SCA
P0
Consoles
P1
P2
Other
Computers
P3
Computation:
VSIPL
Government funded standards must
integrate with the entire system
999999-8
XYZ 7/12/2016
Definitions
VSIPL = Vector, Signal, and Image
Processing Library
MPI = Message-passing interface
MPI/RT = MPI real-time
DRI = Data Re-org Interface
CORBA = Common Object Request Broker
Architecture
HP-CORBA = High Performance CORBA
MIT Lincoln Laboratory
VSIPL
Development Status of the
Vector, Signal, and Image Processing Library (VSIPL)
Mark Richards / Georgia Institute of Technology
Dan Campbell / Georgia Tech Research Institute
Randall Judd / U.S. Navy SPAWAR Systems Center
James Lebak / MIT Lincoln Laboratory
Rick Pancoast / Lockheed Martin
Will describe API status, vendor adoption and Forum plans
Some other VSIPL work at HPEC:
•
•
•
•
999999-9
XYZ 7/12/2016
VSIPL, from API to Product, Sacco/SKY
National Weather Radar Testbed, Walsh/SKY
SIP-7 Experience, Linderman & Bergmann / AFRL
HPEC-SI Demonstration, Sroka / MITRE
MIT Lincoln Laboratory
VSIPL++
VSIPL++: Intuitive Programming Using C++ Templates
Mark Mitchell Jeffrey D. Oldham
CodeSourcery LLC
Implementors of prototype VSIPL++
Will describe API and its benefits:
–
–
–
–
–
999999-10
XYZ 7/12/2016
Direct support for parallel computation
Simpler syntax and improved type-checking
Reduced validation verification (V&V) costs
Support for specialized data storage formats
Potential for higher performance
MIT Lincoln Laboratory
HPEC-SI: VSIPL++ and Parallel VSIPL
Time
Phase 3
Applied Research:
Self-optimization
Phase 2
Fault tolerance
Phase 1
Applied Research:
prototype
Unified Comp/Comm Lib
Development:
VSIPL++
Object-Oriented Standards
Development:
prototype
Fault tolerance
Demonstration:
Development:
Parallel
Unified Comp/Comm Lib VSIPL++
Unified Comp/Comm Lib
Demonstration:
Object-Oriented Standards
Demonstration:
Existing Standards
VSIPL++
VSIPL
MPI
Demonstrate insertions into
fielded systems (e.g., CIP)
•
High-level code
abstraction
•
Reduce code size 3x
Parallel
VSIPL++
Unified embedded
computation/
communication
standard
•Demonstrate scalability
Demonstrate 3x portability
999999-11
XYZ 7/12/2016
Functionality
Applied Research:
MIT Lincoln Laboratory
Technical Scope
Development
Applied Research
VSIPL++
Parallel VSIPL++
-MAPPING (data parallelism)
-Early binding (computations)
-Compatibility (backward/forward)
-Local Knowledge (accessing local data)
-Extensibility (adding new functions)
-Remote Procedure Calls (CORBA)
-C++ Compiler Support
-Test Suite
-Adoption Incentives (vendor, integrator)
999999-12
XYZ 7/12/2016
-MAPPING (task/pipeline parallel)
-Reconfiguration (for fault tolerance)
-Threads
-Reliability/Availability
-Data Permutation (DRI functionality)
-Tools (profiles, timers, ...)
-Quality of Service
MIT Lincoln Laboratory
DRI
Data Reorganization Interface (DRI)
Kenneth Cain, Jr. / Mercury Computer Systems
Anthony Skjellum / MPI Software Technology
Technology Focus
•
Higher level abstraction for collective communication (i.e. “corner turn”)
Will describe API status, vendor adoption and Forum plans
999999-13
XYZ 7/12/2016
MIT Lincoln Laboratory
SCA
Software Communications Architecture (SCA)
Compliant Software Defined Radios
S. Murat Bicer / Mercury Computer Systems
Jeffrey Smith / Mercury Computer Systems
Technical goal:
•
Open architecture radios across multiple domains
Will describe:
• Advantages and difficulties of implementing a SCA-compliant software
defined radio
• An implementation to define a Minimum SCA OMG Specification
999999-14
XYZ 7/12/2016
MIT Lincoln Laboratory
Summary
•
Government funded standards play a key role in transitioning DoD
developed technology into DoD systems
•
Four efforts are critical for the future success of DoD embedded
computing systems
999999-15
XYZ 7/12/2016
–
VSIPL
–
VSIPL++ and Parallel VSIPL
–
DRI
–
SCA
MIT Lincoln Laboratory