2026-09-20T12:26:42Z https://www.ideals.illinois.edu/oai-pmh

oai:www.ideals.illinois.edu:2142/83487 2023-07-11 col_2142_5131 col_2142_14770 com_2142_5130 com_2142_3518 com_2142_234

Dodds, Robert H., Jr. Gullerud, Arne Stewart 2015-09-25T21:05:12Z 2015-09-25T21:05:12Z 10000-01-01 1999 1999 To provide a computational framework suitable for the solution of these problems, this work also describes the parallel implementation of a nonlinear, implicit finite element code. The implementation employs an explicit message-passing approach using the MPI standard to maintain portability, a domain decomposition of element data to provide parallel execution, and a master-worker organization of the computational processes to enhance future extensibility. A linear preconditioned conjugate gradient (LPCG) solver serves as the core of the solution process. The parallel LPCG solver utilizes an element-by-element (EBE) structure of the computations to permit a dual-level decomposition of the element data: domain decomposition of the mesh provides efficient coarse-grain parallel execution, while decomposition of the domains into blocks of similar elements (same type, constitutive model, etc.) provides fine-grain parallel computation on each processor. A major focus of the LPCG solver is a new implementation of the Hughes-Winget element-by-element (HW) preconditioner. The implementation employs a weighted dependency graph combined with a new coloring algorithm to provide load-balanced scheduling for the preconditioner and overlapped communication/computation. This approach enables efficient parallel application of the HW preconditioner for arbitrary unstructured meshes. Made available in DSpace on 2015-09-25T21:05:12Z (GMT). No. of bitstreams: 2 license.txt: 4848 bytes, checksum: 96035ab3f5e1c23cc7138a224ce498bd (MD5) 9953033.pdf: 11215157 bytes, checksum: 9ece7e3c16f5d1708363fb9a4ad3b2cb (MD5) Previous issue date: 1999 Embargo set by: Seth Robbins for item 84768 Lift date: Forever Reason: Restricted to the U of I community idenfinitely during batch ingest of legacy ETDs Restricted to the U of I community idenfinitely during batch ingest of legacy ETDs U of I Only 158 p. Thesis (Ph.D.)--University of Illinois at Urbana-Champaign, 1999. http://hdl.handle.net/2142/83487 (MiAaPQ)AAI9953033 eng Engineering, Mechanical 3-D Modeling of Ductile Tearing Using Finite Elements: Computational Aspects and Techniques text Civil Engineering Civil Engineering University of Illinois at Urbana-Champaign Dissertation Ph.D.