LES Code Parallelization - Revision history

Soon-Heum Ko (NSC) at 09:41, 31 August 2012

2012-08-31T09:41:03Z

Soon-Heum Ko (NSC) at 10:55, 15 March 2012

2012-03-15T10:55:07Z

Soon-Heum Ko (NSC) at 08:52, 15 March 2012

2012-03-15T08:52:19Z

Soon-Heum Ko (NSC) at 08:50, 15 March 2012

2012-03-15T08:50:48Z

Soon-Heum Ko (NSC) at 16:06, 14 March 2012

2012-03-14T16:06:06Z

Joel Hedlund (NSC) at 09:45, 13 March 2012

2012-03-13T09:45:05Z

Soon-Heum Ko (NSC) at 13:36, 12 March 2012

2012-03-12T13:36:37Z

Joel Hedlund (NSC) at 13:28, 8 February 2012

2012-02-08T13:28:02Z

Soon-Heum Ko (NSC): Created page with "{{project info |description=Parallelization of a Large Eddy Simulation Code |financing=SNIC |active=Yes |start date=2011-03-01 |end date= }} This is a NSC-promoted project of su..."

2012-02-07T11:37:21Z

Created page with "{{project info |description=Parallelization of a Large Eddy Simulation Code |financing=SNIC |active=Yes |start date=2011-03-01 |end date= }} This is a NSC-promoted project of su..."

New page

{{project info
|description=Parallelization of a Large Eddy Simulation Code
|financing=SNIC
|active=Yes
|start date=2011-03-01
|end date=
}}

This is a NSC-promoted project of supporting code parallelization for prominent Swedish scientists. A serial Large Eddy Simulation (LES) code by Dr. L. Davidson at Charmers University has been selected as the candidate. We provide

- The distinct partitioning code for 3-D structured geometries

- Inter-processor and global communicators for halo information exchange on baseline convection-diffusion code

- Parallelization of the 1-D multigrid pressure Poisson solver

== Members ==
{{#ask: [[Category:Person]] [[project::{{PAGENAME}}]]
|?centre
|?role
|?field
}}

@@ Line 17: / Line 17: @@
 Prof. Lars Davidson's LES (Large Eddy Simulation) fluid dynamics code has been chosen as a pilot project of NSC's code parallelisation service. We devise the standalone domain partitioning code for decomposing the computational domain to each core. We deploy the MPI communicator for the halo cell exchange, which has several forms so that the communication routine fits with the regular 3-D data structure and 1-D converted data structure used for the multi-grid implementation. Parallel performance shows the linear speed-up on small number of processors, up to 20 cores. We do not observe more speed-up with increased number of processor in this strong-scale instrumentation, because the original domain size is designed very small (around 2 million mesh points) to enable the performance measurement from a single-core run. Nevertheless, we expect that the code will show the good performance on larger number of cores in case of the weak scale test. Furthermore, we emphasize that this parallelisation effort faciliate the more-detailed flow simulations in a complex geometry whose mesh system shall be constructed with lots of mesh points which has been exceeding the capacity of a single core program. We find that the change of time integration scheme will further improve the performance by providing the better convergence criteria, which will be one of main objectives of a next project.
-Full details will be updated [http://www.nsc.liu.se/~sko/LES_Parallel here].
+Full details will be updated [http://www.nsc.liu.se/~sko/Projects/LES_Parallel here].
 == Members ==

@@ Line 15: / Line 15: @@
 ----- Abstract
-Prof. Lars Davidson's LES (Large Eddy Simulation) fluid dynamics code has been chosen as a pilot project of NSC's code parallelisation service. We devise the standalone domain partitioning code for decomposing the computational domain to each processor. We deploy the MPI communicator for the halo cell exchange, which has several forms so that the communication routine fits with the regular 3-D data structure and 1-D converted data structure for the multi-grid scheme imposition. Parallel performance shows the linear speed-up on low number of processors, up to 20 cores. We do not observe more speed-up with increased number of processor in this strong-scale instrumentation, because the original domain size is designed very small (around 2 million mesh points) to compare the performance from a single-core run. Nevertheless, we expect that the code will show the good performance on larger number of cores, in case of the weak scale test. Furthermore, we emphasize that this parallelisation effort faciliate the more-detailed flow simulations in a complex geometry whose mesh system shall be constructed with lots of mesh points. We find that the change of time integration scheme will further improve the performance by providing the better convergence criteria, which will be one of main objectives of a next project.
+Prof. Lars Davidson's LES (Large Eddy Simulation) fluid dynamics code has been chosen as a pilot project of NSC's code parallelisation service. We devise the standalone domain partitioning code for decomposing the computational domain to each core. We deploy the MPI communicator for the halo cell exchange, which has several forms so that the communication routine fits with the regular 3-D data structure and 1-D converted data structure used for the multi-grid implementation. Parallel performance shows the linear speed-up on small number of processors, up to 20 cores. We do not observe more speed-up with increased number of processor in this strong-scale instrumentation, because the original domain size is designed very small (around 2 million mesh points) to enable the performance measurement from a single-core run. Nevertheless, we expect that the code will show the good performance on larger number of cores in case of the weak scale test. Furthermore, we emphasize that this parallelisation effort faciliate the more-detailed flow simulations in a complex geometry whose mesh system shall be constructed with lots of mesh points which has been exceeding the capacity of a single core program. We find that the change of time integration scheme will further improve the performance by providing the better convergence criteria, which will be one of main objectives of a next project.
 Full details will be updated [http://www.nsc.liu.se/~sko/LES_Parallel here].

@@ Line 3: / Line 3: @@
 |fields=Computational fluid dynamics
 |financing=SNIC
-|active=Yes
+|active=No
 |start date=2011-03-01
 |end date=2012-02-29

@@ Line 14: / Line 14: @@
 * Parallelization of the 1-D multigrid pressure Poisson solver
------ Abstract -----
+----- Abstract
 Prof. Lars Davidson's LES (Large Eddy Simulation) fluid dynamics code has been chosen as a pilot project of NSC's code parallelisation service. We devise the standalone domain partitioning code for decomposing the computational domain to each processor. We deploy the MPI communicator for the halo cell exchange, which has several forms so that the communication routine fits with the regular 3-D data structure and 1-D converted data structure for the multi-grid scheme imposition. Parallel performance shows the linear speed-up on low number of processors, up to 20 cores. We do not observe more speed-up with increased number of processor in this strong-scale instrumentation, because the original domain size is designed very small (around 2 million mesh points) to compare the performance from a single-core run. Nevertheless, we expect that the code will show the good performance on larger number of cores, in case of the weak scale test. Furthermore, we emphasize that this parallelisation effort faciliate the more-detailed flow simulations in a complex geometry whose mesh system shall be constructed with lots of mesh points. We find that the change of time integration scheme will further improve the performance by providing the better convergence criteria, which will be one of main objectives of a next project.

@@ Line 5: / Line 5: @@
 |active=Yes
 |start date=2011-03-01
-|end date=
+|end date=2012-02-29
 }}
@@ Line 13: / Line 13: @@
 * Inter-processor and global communicators for halo information exchange on baseline convection-diffusion code
 * Parallelization of the 1-D multigrid pressure Poisson solver
 == Members ==

@@ Line 1: / Line 1: @@
 {{project info
 |description=Parallelization of a Large Eddy Simulation Code
 |financing=SNIC
 |active=Yes

@@ Line 9: / Line 9: @@
 This is a NSC-promoted project of supporting code parallelization for prominent Swedish scientists. A serial Large Eddy Simulation (LES) code by Dr. L. Davidson at Charmers University has been selected as the candidate. We provide
-* The distinct partitioning code for 3-D structured geometries
+* The distinct light-weight partitioning code for 3-D structured geometries
 * Inter-processor and global communicators for halo information exchange on baseline convection-diffusion code
 * Parallelization of the 1-D multigrid pressure Poisson solver