The HPEC Challenge Benchmark
Suite
Ryan Haney, Theresa Meuse, Jeremy Kepner and
James Lebak
Massachusetts Institute of Technology
Lincoln Laboratory
HPEC 2005
This work is sponsored by the Defense Advanced Research Projects Agency under Air Force
Contract FA8721-05-C-0002. Opinions, interpretations, conclusions, and recommendations are
those of the authors and are not necessarily endorsed by the United States Government.
MIT Lincoln Laboratory
Haney - 1
HPEC 10/20/2005
Acknowledgements
• Lincoln Laboratory PCA Team
–
–
–
–
Matthew Alexander
Jeanette Baran-Gale
Hector Chan
Edmund Wong
• Shomo Tech Systems
– Marti Bancroft
• Silicon Graphics Incorporated
– William Harrod
• Sponsor
– Robert Graybill, DARPA PCA and HPCS Programs
Haney - 2
HPEC 10/20/2005
MIT Lincoln Laboratory
HPEC Challenge Benchmark Suite
• PCA program kernel benchmarks
– Single-processor operations
– Drawn from many different DoD applications
– Represent both “front-end” signal processing and “back-end”
knowledge processing
• HPCS program Synthetic SAR benchmark
– Multi-processor compact application
– Representative of a real application workload
– Designed to be easily scalable and verifiable
Haney - 3
HPEC 10/20/2005
MIT Lincoln Laboratory
Outline
• Introduction
• Kernel Level Benchmarks
• SAR Benchmark
– Overview
– System Architecture
– Computational Components
• Release Information
• Summary
Haney - 4
HPEC 10/20/2005
MIT Lincoln Laboratory
Spotlight SAR System
•
Principal performance goal:
Throughput
– Maximize rate of results
– Overlapped IO and computing
Haney - 5
HPEC 10/20/2005
•
Intent of Compact App:
– Scalable
– High Compute Fidelity
– Self-Verifying
MIT Lincoln Laboratory
SAR System Architecture
Front-End Sensor Processing
Kernel #1
Data Read
and Image
Formation
Scalable Data
and Template
Generator
SAR
Image
Template
Insertion
Kernel #2
Image
Storage
SAR
Image
Templates
Raw
SAR
Files
Computation
Groups of
Template
Files
Raw SAR
Data Files
SAR
Image
Files
HPEC community
has traditionally
focused on
Computation …
Kernel #3
Image
Retrieval
Raw
SAR
File
SAR
Image
Files
Template
Files
Groups of
Template
Files
Template
Files
SAR
Images
Templates
Sub-Image
Detection
Files
Sub-Image
Detection
Files
Kernel #4
Detection
File IO
Image
Files
Template
Files
Detections
Validation
… but File IO
performance is
increasingly
important
Back-End Knowledge Formation
Haney - 6
HPEC 10/20/2005
MIT Lincoln Laboratory
Data Generation and Computational Stages
Sensor Processing
Scalable Data
and Template
Generator
Raw
SAR
Kernel #1
Image
Formation
SAR
Image
Kernel #2
Image
Storage
SAR
Image
Templates
Templates
Raw
SAR
Files
Template
Insertion
Raw
SAR
File
Groups of
Template
Files
Raw SAR
Data Files
SAR
Image
Files
Template
Files
Sub-Image
Detection
Files
Groups of
Template
Files
SAR
Image
Files
Template
Files
Kernel #3
Image
Retrieval
SAR
Image
Image
Files
Template
Files
Detection
Files
Kernel #4
Detection
Detections
Validation
Templates
Knowledge Formation
Haney - 7
HPEC 10/20/2005
MIT Lincoln Laboratory
SAR Overview
• Radar captures echo returns from a
‘swath’ on the ground
• Notional linear FM chirp pulse train,
plus two ideally non-overlapping
echoes returned from different
positions on the swath
Synthetic Aperture, L
Fixed to Broadside
...
• Summation and scaling of echo
returns realizes a challengingly long
antenna aperture along the flight path
Range,
X = 2X0
delayed transmitted
SAR waveform
s(t , u) 
  (n, m) pt  (n, m))
pulses swath
received
‘raw’ SAR
Haney - 8
HPEC 10/20/2005
reflection coefficient scale factor, different
for each return from the swath
Cross-Range, Y = 2Y0
MIT Lincoln Laboratory
Scalable Synthetic Data Generator
• Generates synthetic raw SAR
complex data
• Data size is scalable to enable
rigorous testing of high performance
computing systems
Spotlight SAR Returns
• Generates ‘templates’ that consist of
rotated and pixelated capitalized
letters
Range
– User defined scale factor determines
the size of images generated
Cross-Range
Haney - 9
HPEC 10/20/2005
MIT Lincoln Laboratory
Kernel 1 — SAR Image Formation
Spatial Frequency Domain Interpolation
s*0(w,ku)
s(t,u)
Fourier
s(w,ku)
Transform
(t,u)B(w,ku)
Matched
Filtering
Interpolation
kx = sqrt(4k2 –ku2)
ky = ku
Inverse
f(x,y)
Fourier Transform
F(kx,ky) (kx,ky) B (x,y)
Cross-Range, Pixels
Spotlight SAR Reconstruction
ky
kx
Range, Pixels
Haney - 10
HPEC 10/20/2005
o
Received
Samples
Fit a Polar
Swath
Processed
Samples
Fit a
Rectangular
Swath
f
MIT Lincoln Laboratory
Template Insertion
(untimed)
• Inserts rotated pixelated capital letter
templates into each SAR image
– Non-overlapping locations and rotations
– Randomly selects 50%
– Used as ideal detection targets in Kernel 4
X Pixels
Haney - 11
HPEC 10/20/2005
Image only inserted with
%50 random Templates
Y Pixels
Y Pixels
If inserted with
%100 Templates
X Pixels
MIT Lincoln Laboratory
Kernel 4 — Detection
• Detects targets in SAR images
1.
2.
3.
4.
Image difference
Threshold
Sub-regions
Correlate with every template
 max is target ID
•
Computationally difficult
– Many small correlations over
random pieces of a large image
•
100% recognition no false alarms
Image A
Image Difference
Thresholded Difference
Sub-region
Image B
Haney - 12
HPEC 10/20/2005
MIT Lincoln Laboratory
Benchmark Summary and
Computational Challenges
Back-End
Knowledge Formation
Front-End
Sensor Processing
Scalable Data
and Template
Generator
Raw
SAR
Templates
• Scalable synthetic
data generation
Haney - 13
HPEC 10/20/2005
Kernel #1
Image
Formation
SAR
Image
Template
Insertion
SAR
Image
Kernel #4
Detection
Detections
Validation
Templates
Templates
• Pulse compression
• Polar Interpolation
• FFT, IFFT (corner turn)
• Sequential store
• Non-sequential
retrieve
• Large & small IO
• Large Images
difference &
Threshold
• Many small
correlations on
random pieces of
large image
MIT Lincoln Laboratory
Outline
•
•
•
•
•
Haney - 14
HPEC 10/20/2005
Introduction
Kernel Level Benchmarks
SAR Benchmark
Release Information
Summary
MIT Lincoln Laboratory
HPEC Challenge Benchmark Release
• http://www.ll.mit.edu/HPECChallenge/
– Future site of documentation and
software
• Initial release is available to PCA, HPCS,
and HPEC SI program members through
respective program web pages
– Documentation
– ANSI C Kernel Benchmarks
– Single processor MATLAB SAR System
Benchmark
• Complete release will be made available
to the public in first quarter of CY06
Haney - 15
HPEC 10/20/2005
MIT Lincoln Laboratory
Summary
• The HPEC Challenge is a publicly available suite of
benchmarks for the embedded space
– Representative of a wide variety of DoD applications
• Benchmarks stress computation, communication and I/O
• Benchmarks are provided at multiple levels
– Kernel: small enough to easily understand and optimize
– Compact application: representative of real workloads
– Single-processor and multi-processor
• For more information, see
http://www.ll.mit.edu/HPECChallenge/
Haney - 16
HPEC 10/20/2005
MIT Lincoln Laboratory