Compiling Parallel MATLAB for General Distributions using Telescoping Languages

Fletcher, Mary E.; McCosh, Cheryl; Jin, Guohua; Kennedy, Ken

doi:10.1109/icassp.2007.367289

Cited by 3 publications

(3 citation statements)

References 10 publications

(11 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To perform the analysis and transformation techniques described above, we use the Matlab D framework developed at Rice University [9,11]. We generate an XML file from the AST of the X10 program, then read this AST within the Matlab D compiler, convert it into SSA, perform the value numbering based algorithms presented in this chapter to infer the regions associated with arrays, points and regions in the program, then use the unique source code position to map the analysis information back into the X10 compiler.…”

Section: Intraprocedural Region Analysismentioning

confidence: 99%

See 1 more Smart Citation

Subregion Analysis and Bounds Check Elimination for High Level Arrays

Joyner

Budimlić

Sarkar

2011

Lecture Notes in Computer Science

View full text Add to dashboard Cite

For decades, the design and implementation of arrays in programming languages has reflected a natural tension between productivity and performance. Recently introduced HPCS languages (Chapel, Fortress and X10) advocate the use of high-level arrays for improved productivity. For example, high-level arrays in the X10 language support rank-independent specification of multidimensional loop and array computations using regions and points. Three aspects of X10 high-level arrays are important for productivity but pose significant performance challenges: high-level accesses are performed through point objects rather than integer indices, variables containing references to arrays are rank-independent, and all subscripts in a high-level array access must be checked for bounds violations. The first two challenges have been addressed in past work. In this paper, we address the third challenge of optimizing the overhead of array bounds checks by developing a novel region-based interprocedural array bounds analysis to automatically identify redundant checks. Elimination of redundant checks reduces the runtime overhead of bounds checks, and also enables further optimization by removing constraints that arise from precise exception semantics. We have implemented an array bounds check elimination algorithm that inserts special annotations that are recognized by a modified JVM. We also introduce array views, a high-level construct that improves productivity by allowing the programmer to access the underlying array through multiple views. We describe a technique for optimizing away the overhead of many common cases of array views in X10. Our experiments show that eliminating bounds checks using the results of the analysis described in this paper improves the performance of our benchmarks by up to 22% over JIT compilation.

show abstract

Section: Intraprocedural Region Analysismentioning

confidence: 99%

“…The lattice is shown on Figure 5. In the Matlab D compiler [11], a φ function performs a meet operation (∧) of all its arguments, where each argument is a lattice value, and assigns the result to the target of the assignment.…”

Section: Intraprocedural Region Analysismentioning

confidence: 99%

Subregion Analysis and Bounds Check Elimination for High Level Arrays

Joyner

Budimlić

Sarkar

2011

Lecture Notes in Computer Science

View full text Add to dashboard Cite

show abstract

“…MathWorks, the creators of Matlab, have produced a Distributed Computing Toolkit for parallelization, which is similar to the MatlabMPI created by Kepner at MIT Lincoln Labs [6]. Rice University is developing a parallel implementation of Matlab, MatlabD, with the goal of automatically compiling Matlab scripts into high performance Fortran [5]. One downside of many parallel implementations is that the data they use is limited to the memory size of a single CPU memory.…”

Section: Related Workmentioning

confidence: 99%