National Instruments Corporation

Adam L Bordelon

Robert E Dye

Haoran Yi

Mary E Fletcher

Jeffrey L Kodosky

Darren R Schmidt

Somashekaracharya G Bhaskaracharya

Brady C Duggan

System and method for automatically parallelizing iterative functionality in a data flow program. A data flow program is stored that includes a first data flow program portion, where the first data flow program portion is iterative. Program code implementing a plurality of second data flow program portions is automatically generated based on the first data flow program portion, where each of the second data flow program portions is configured to execute a respective one or more iterations. The plurality of second data flow program portions are configured to execute at least a portion of iterations concurrently during execution of the data flow program. Execution of the plurality of second data flow program portions is functionally equivalent to sequential execution of the iterations of the first data flow program portion.

Loop parallelization analyzer for data flow programs

A system and method for rearranging algebraic expressions occurring in program code based on a scheme of ranking operands. The system scans program code to identify an algebraic expression specified by the program code. The expression includes binary operations, scalar operands and at least one array operand. The system operates on the algebraic expression to obtain a final expression by: computing a rank for each of the operands; and performing algebraic transformations on selected subexpressions of the algebraic expression so that in the final expression operands are combined in the order of their rank. The ranking scheme may be designed to force scalars to be combined before arrays, and/or, to force constants to be combined first, loop invariants second, and variants last. In some embodiments, the ranking scheme is a vector ranking scheme including two or more components (such as invariance rank, dimensional rank and data-size rank).

Rearrangement of algebraic expressions based on operand ranking schemes

System and method for vectorizing combinations of program operations. Program code is received that includes a combination of individually vectorizable program portions that collectively implement a first computation. Each individually vectorizable program portion has at least one array input and at least one array output. The combination of individually vectorizable program portions is transformed into a single vectorizable program portion that is or includes a functional composition of the combination of individually vectorizable program portions. Vectorized executable code implementing the first computation is generated based on the single vectorizable program portion. The generated executable code is directed to SIMD (Single-Instruction-Multiple-Data) computing units of a target processor.

Vectorizing combinations of program operations

Graphical indicator which specifies parallelization of iterative program code in a graphical data flow program

Automatically creating parallel iterative program code in a data flow program

Automatically creating parallel iterative program code in a graphical data flow program

Growing community of inventors

Austin, TX, United States of America

Adam L Bordelon