357.bt331
SPEC OMP2012 Benchmark Description File

Benchmark Name

357.bt331

Benchmark Author

R. Van der Wijngaart
T. Harris
M. Yarrow
H. Jin

Benchmark Program General Category

Computational Fluid Dynamics

Benchmark Description

BT is a simulated CFD application that uses an implicit algorithm to solve 3-dimensional (3-D) compressible Navier-Stokes equations. The finite differences solution to the problem is based on an Alternating Direction Implicit (ADI) approximate factorization that decouples the x, y and z dimensions. The resulting systems are Block-Tridiagonal of 5x5 blocks and are solved sequentially along each dimension.


Input Description

There are two approaches to control the memory and run-time requirements of the benchmark:
  1. change in mesh size,
  2. change in number of time steps taken.
For a fixed mesh size, run-time varies linearly with the number of time steps taken. Currently, input decks are available for several different pairs of mesh cubic sizes and the number of time steps taken.

For the SPEC benchmark, the reference data set uses a grid of 408x408x408 with 130 iterations and a time step of 0.00002. The train data set uses a grid of 102x102x102 with 200 iterations and a time step of 0.0003. The test data set uses a grid of 64x64x64 with 200 iterations and a time step of 0.0008.


Output Description

The program is capable of automatically verifying whether a given run conforms to the specification of the benchmark by using internally stored reference solutions. However, these reference solutions are available only for a fixed number of mesh size/time steps pairs. If the input data does not correspond to any of the internally stored reference solutions, the verification test is not performed. Otherwise, the output indicates whether or not the run was successfull in meeting the requirements of the verifications tests. To conform to the specification of the benchmark, a run should successfully pass all three verification tests. Failure in any one or more tests indicates non-conformance with the specifications.

For SPEC, the solution is output for comparison to a set of reference values.


Programming Language

Fortran

Known portability issues

None

Reference

H. Jin, M.Frumkin and J.Yan, "The OpenMP Implementation of NAS Parallel Benchmarks and Its Performance", Rept. No: NAS Technical Report NAS-99-011 October 1999 view article

Last Updated: 15 July 2010