Performance Enhancements in MSC'Nastran for Large Scale Design Optimization on Cray SV1 Computers

1
Performance Enhancements in MSC.Nastran for Large
Scale Design Optimization on Cray SV1 Computers
Dr. D. Obrist, Dr. H. Misra, Cray Inc. Dr. S.
Zhang, Dr. D. Chou, MSC.Software Corp.
2
Large Scale Design Optimization

• joint project between MSC.Software Corp. and
  Cray Inc. (October 2000 - July 2001)

? 2-4x shorter turnaround time
3
Characteristics of Large Scale Optimization
Problems

• millions of degrees of freedom
• hundreds of design variables and responses
• hundreds of modes

? prohibitive turnaround times for simulations ?
excessively large I/O
4
List of enhancements

• exploit the sparsity of the design model
• improved data management to process DSADJ in a
  single pass - improved vectorization
• highly optimized matrix-matrix multiplications
  from the Cray Scientific Library
• optimized sparse matrix I/O
• parallelization of DSADJ and DSVG1
• misc. improvements (GP5, EMG, MPYAD, PARTN,
  MERGE, SADD5, etc.)

5
Sparsity of the design model
In many design optimization tasks only a small
number of elements are modified during the design
process (sparse design set)
Example data recovery sub-dmap DISPRS
6
Data recovery sub-dmap DISPRS

• Industry example
• design model is 25 sparse
• 2091102 DOF
• 251 modes
• 128 design variables
• 2931 retained responses

• amount of I/O is reduced by 4x
• CPU time is reduced by 5x

7
Improved data management in DSADJ - single pass
single pass ? reduced scalar overhead
8
Industry Example IDSADJ performance
7x improved!
9
Industry Example IIDSADJ performance
9x improved!
10
Industry Example IIIDSADJ performance
13x improved!
11
Industry Example IVDSVG1 performance
10x improved!
12
Parallelization of DSVG1 and DSADJ
Parallel runs of the Industry Example III (2
million DOF) with 1, 2, and 4 processors.
13
Total Improvements over one Design Cycle
Overall improvement 2-4x !
14
Conclusions
The turnaround time for a large design
optimization task is dramatically reduced (2-4x)
...
The performance is independent of the open core
memory size ...