Response #1: 2005-11-11

General

1. Is dense linear algebra a performance bottleneck in your applications?
Yes

2. How often do your applications use the arithmetic precisions listed below:

3. What dense matrix sizes are most important or time-consuming for your application?
1,000s X 1,000s

4. Does your application come close to, or run out of memory on important problems?
Yes

5. Number of processors used for your application:

6. Which architectures do you use or intend to use in the next three years?
Multi-core-thread, Symmetric-multi-procs, Distributed-shared-memory, Distributed-memory, Hybrid-shared

7. Do you use any other sequential or parallel dense linear algebra packages other than LAPACK or ScaLAPACK?
Steven Kenny

8. Please rank how the following features would be useful to your current or planned applications?

9. Do your applications solve linear algebra problems of the type?
Generalized eigenvalue, Symmetric eigenvalue

LAPACK Usage

1. Do you use LAPACK (or a vendor version of LAPACK )?
Yes

4. If you use LAPACK, do you use a vendors version or one obtained directly from Netlib?
Vendor, Netlib

5. If you have used both a vendors version of LAPACK and Netlibs, how do the two versions compare?
Generally the vendor versions are faster showing considerably speed up over the Netlib versions.

6. Do your applications make direct LAPACK calls?
Yes

7. Do your applications use libraries which depend on LAPACK?
Yes

8. Do your applications use a higher-level interface to LAPACK?
No

10. Is the LAPACK procedure interface a barrier to more extensive use?
No

11. From which languages do you call LAPACK routines?
C, Fortran 90/95

15. How frequently do you refer to the LAPACK Users Guide?
Frequently

ScaLAPACK Usage

1. Do you use ScaLAPACK (or a vendor version of ScaLAPACK )?
Yes

4. If you use ScaLAPACK, do you use a vendors version or one obtained directly from Netlib?
Vendor

5. If you have used both a vendors version of ScaLAPACK and Netlibs, how do the two versions compare?
Vendor implementations are faster. I have also found them to be more robust. We have had cases where the Netlib verrsion fails but the vendor version works.

6. Do your applications make direct ScaLAPACK calls?
Yes

7. Do your applications use libraries which depend on ScaLAPACK?
No

8. Do your applications use a higher-level interface to ScaLAPACK?
No

10. Is the ScaLAPACK procedure interface a barrier to more extensive use?
Yes

11. From which languages do you call ScaLAPACK routines?
C

13. How could the ScaLAPACK interface be improved to feel more natural to your application and implementation language?
The most major problem is the errors that are given when the workspace is too small. The message that comes from ScaLAPACK is often incorrect and says that the problem is due to an incorrect argument to a routine. I would also like to use ScaLAPACK in a way that allowed several parallel diagonalisations to be carried out in parallel. This is mentioned in the BLACS documentation but does not seem to work.

14. If you have installed ScaLAPACK yourself, how could the installation process be improved?
The interaction between BLACS, PBLAS and ScaLAPACK. The installation process is made difficult due to the fact it seems necessary to compile several times to get the uncerscores correct.

15. How frequently do you refer to the ScaLAPACK Users Guide?
Frequently

Targeted Environment Specifics

1. Under which operating system environments do your applications run?
AIX, Linux, Mac OS X

2a. Please specify any particular libraries of frameworks used?
MPI

3. If your applications run in a distributed-memory environment, which styles of parallelism do they employ?
Message passing

Additional Information