NASA Logo

NTRS

NTRS - NASA Technical Reports Server

Back to Results
Applications of automatic differentiation in computational fluid dynamicsAutomatic differentiation (AD) is a powerful computational method that provides for computing exact sensitivity derivatives (SD) from existing computer programs for multidisciplinary design optimization (MDO) or in sensitivity analysis. A pre-compiler AD tool for FORTRAN programs called ADIFOR has been developed. The ADIFOR tool has been easily and quickly applied by NASA Langley researchers to assess the feasibility and computational impact of AD in MDO with several different FORTRAN programs. These include a state-of-the-art three dimensional multigrid Navier-Stokes flow solver for wings or aircraft configurations in transonic turbulent flow. With ADIFOR the user specifies sets of independent and dependent variables with an existing computer code. ADIFOR then traces the dependency path throughout the code, applies the chain rule to formulate derivative expressions, and generates new code to compute the required SD matrix. The resulting codes have been verified to compute exact non-geometric and geometric SD for a variety of cases. in less time than is required to compute the SD matrix using centered divided differences.
Document ID
19950010046
Acquisition Source
Legacy CDMS
Document Type
Conference Paper
Authors
Green, Lawrence L.
(NASA Langley Research Center Hampton, VA, United States)
Carle, A.
(NASA Langley Research Center Hampton, VA, United States)
Bischof, C.
(NASA Langley Research Center Hampton, VA, United States)
Haigler, Kara J.
(NASA Langley Research Center Hampton, VA, United States)
Newman, Perry A.
(NASA Langley Research Center Hampton, VA, United States)
Date Acquired
September 6, 2013
Publication Date
October 1, 1994
Publication Information
Publication: The Role of Computers in Research and Development at Langley Research Center
Subject Category
Fluid Mechanics And Heat Transfer
Accession Number
95N16461
Distribution Limits
Public
Copyright
Work of the US Gov. Public Use Permitted.
No Preview Available