A portable, object-based parallel library and layered framework for real-time radar signal processing

DeLuca, Cecelia; Heisey, Curtis W.; Bond, Robert; Daly, J.

doi:10.1007/3-540-63827-x_67

Cited by 10 publications

(2 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Maps and map-like constructs have a history in HighPerformance Fortran [5] , MIT Lincoln Laboratory SpaceTime Adaptive Processing Library (STAPL) [6] , ||VSIPL++, and Parallel Vector Library (PVL) [7] . Additionally, a map is a key construct in pMatlab [8] and Parallel Vector Tile Optimizing Library (PVTOL) [9] .…”

Section: Mapsmentioning

confidence: 99%

Performance Modeling and Mapping of Sparse Computations

Bliss

Mohindra

O’Reilly

2008

2008 DoD HPCMP Users Group Conference

View full text Add to dashboard Cite

In the past, knowledge processing (anomaly detection, target identification, social network analysis) of sensor data did not require real-time processing speeds. However, the rapid growth in the size of the data and the shortening time scale of the required data analysis are driving the need for applications that provide real-time signal and knowledge processing at the sensor front end. Many knowledge processing techniques, such as Bayesian networks, social networks, and neural networks, have a graph abstraction. Graph algorithms are difficult to parallelize and thus cannot take advantage of multi-core architectures. Many graph operations can be cast as sparse linear algebra operations. While this increases the ease of programming, parallel sparse algorithms are still inefficient. This paper presents a search-based mapping and routing approach for sparse operations. Since finding well-performing maps and routes for sparse operations is a computationally intensive task, the mapping and routing algorithms have been parallelized to take advantage of the Lincoln Laboratory cluster computing capability, LLGrid. Our parallelization of the approach yielded near linear speed up and the mapping and routing results demonstrate over an order of magnitude performance improvement over traditional mapping techniques.

show abstract

Section: Mapsmentioning

confidence: 99%

Performance Modeling and Mapping of Sparse Computations

Bliss

Mohindra

O’Reilly

2008

2008 DoD HPCMP Users Group Conference

View full text Add to dashboard Cite

show abstract

“…The Embedded Digital Systems Group at Lincoln Laboratory has been developing parallel libraries for more than 10 years [6]. The libraries developed there include STAPL (Space-Time Adaptive Processing Library) [14], PVL (Parallel Vector Library) [28], and pMatlab [27]. All of these libraries have increased the level of abstraction by implementing a map layer that insulates the algorithm developer from writing complicated message-passing code.…”

Section: Figure 24 Matrix Multiplication Generalized Codementioning

confidence: 99%