Final Report– PRACE PreparatoryAccessType A

1. General information

1.1. Proposal ID

1.2. Type ofproject granted

Preparatory Access Type A – Code scalability and performance

Tests to obtain the relevant parameters necessary when applying to future PRACE calls for Project Access.

1.3. Period of access to the PRACE facilities

1.4. Name of the PRACE facility assigned

2. Project information

2.1. Project name to which corresponds the tested code

2.2. Research field

(Please click twice in the box of your research field and select “checked”)

Astrophysics / Engineering and Energy
Earth Sciences and Environment / Mathematics and Computer Science
Medicine and Life Sciences / Finance and Social Science
Chemistry and Materials / Linguistics and Encryption
Fundamental Physics

2.3. Institutions and research team members

2.4. Summary of the project interest (Maximum 300 words)

Please fill in the field with the same text used in the application form.

3. Main features of the code

3.1. Name of the code(s).

3.2. Type of the code distribution(e.g. open source, commercial, academic…etc.)

3.3. Computational problem executed(e.g. N-body problem, Navier-stokesequation…etc.)

3.4.Computational method (e.g. FEM, FVM, PIC, spectral methods…etc.)

3.5. Kind of parallelism used(e.g. MPI, OpenMP, MPI/OpenMP, pthreads, embarrassingly parallelism…etc.)

3.6. Main libraries used (e.g. FFTW, MKL, BLAS, LAPACK…etc.), version and language (Fortran, C, C++…etc.). Did you use the /usr/local one?

3.7. Which other software did you use on the PRACE machines? Did you use some post-processing or pre-processing tools?

4. Compilation step

4.1. How is the program compiled? (e.g. makefile, script…etc.)

4.3. Difficulties met to compile, if any, and how they were tackled.

4.4. Which version of the compiler and version of the MPI library did you use?

4.5. Did you use any tools to study the behaviour of your code? (e.g. debugger, profiler…etc.)

5. Execution step

5.1. How is the program launched?

5.2. Difficulties met to launch the code, if any, and how they were tackled.

6. Communication patterns

6.1. If you know which are the main communication patterns used in your code configuration, select the ones from the mentioned below:

Many/few/no point to point communications
Many/few/no collective communications
Barrier
Reduction
Broadcast
Scatter/gather
All to all

7. Results of the scalability testing

7.1. Summary of the obtained results from the scalability testing (Maximum 500 words)

Show the scaling behaviour of your application. Which progress did you achieve? Does it fulfil your expectations? If not, what were the reasons?

7.2. Images or graphics showing results from the scalability testing (Minimum resolution of 300 dpi)

All tables and figures (including photographs, schemas, graphs and diagrams) should be numbered with Arabic numerals (1, 2,...n) and include a descriptive caption. Please attach the images to this form.

7.3. Data to deploy scalability curves

A) Some typical user test cases

Please include the data for each test case.

Number of cores / Wall clock time / Speed-up vs the first one / Number of Nodes / Number of process

B) Strong scaling curve

Please include the data in order to deploy the scalability curve when the number of processors varies for a fixed total problem size.

Number of cores / Wall clock time / Speed-up vs the first one / Number of Nodes / Number of process

C) Weal scaling curve

Please include the data in order to deploy the scalability curve when the number of processors varies for a fixed problem size per processor.

Number of cores / Wall clock time / Speed-up vs the first one / Number of Nodes / Number of process

7.4. Publications or reports regarding the scalability testing.

Please use the following format: Author(s). “Title”. Publication, volume, issue, page, month year

8. Results on Input/Output

8.1. Size of the data and/or the number of files. (Maximum 300 words)

8.2. Please, let us know if you used some MPI-IO features. (Maximum 300 words)

9. Main results

What are your conclusions? What do you think of the usability of the assigned PRACE system?

10. Feedback and technical deployment

10.1. Feedback on the centres/PRACE mechanism(Maximum 500 words)

10.2. Explanation of how the computer time was used compared with the work plan presented in the proposal. Justification of discrepancies, especially if the computer time was not completely used.(Maximum 500 words)

10.3. Please, let us know if you plan to apply for PRACE Project Access in the future? If not, explain us why. (Maximum 500 words)

Page 1 of 5