NERSCPowering Scientific Discovery Since 1974

2004 User Survey Results

Software

 

  • Legend
  • Software Satisfaction - by Score
  • Software Satisfaction - by Platform
  • Software Comments

 

Legend:

Satisfaction Average Score
Mostly Satisfied 5.50 - 6.49
Somewhat Satisfied 4.50 - 5.49
Significance of Change
not significant

 

Software Satisfaction - by Score

7=Very satisfied, 6=Mostly satisfied, 5=Somewhat satisfied, 4=Neutral, 3=Somewhat dissatisfied, 2=Mostly dissatisfied, 1=Very dissatisfied

 

Item Num who rated this item as: Total Responses Average Score Std. Dev. Change from 2003
1 2 3 4 5 6 7
SP SW: Fortran compilers

2 3 8 53 81 147 6.41 0.80 0.07
PDSF SW: Software environment


4 1 13 24 42 6.36 0.93 0.03
SP SW: Software environment


5 9 70 71 155 6.34 0.73 0.10
SP SW: Programming libraries

1 8 2 60 54 125 6.26 0.84 -0.01
SP SW: C/C++ compilers

2 5 6 35 46 94 6.26 0.95 0.04
PDSF SW: C/C++ compilers


5 1 12 20 38 6.24 1.02 -0.20
PDSF SW: Programming libraries


5 1 14 16 36 6.14 1.02 0.14
SP SW: Applications software


10 6 37 38 91 6.13 0.96 0.13
SP SW: General tools and utilities

4 8 14 43 33 102 5.91 1.06 -0.07
PDSF SW: Fortran compilers


6 1 6 10 23 5.87 1.25 -0.16
SP SW: Performance and debugging tools
2 5 7 16 54 34 118 5.84 1.14 0.27
PDSF SW: General tools and utilities
1
5 2 17 10 35 5.83 1.18 -0.10
PDSF SW: Applications software

1 6 2 14 10 33 5.79 1.17 -0.08
PDSF SW: Performance and debugging tools
1
5 4 15 10 35 5.77 1.19 0.46
SP SW: Visualization software
2 2 18 4 19 17 62 5.40 1.41 0.32
Escher SW: visualization software
1 1 9
4 6 21 5.10 1.58 0.35
Newton SW: application software 1 1 2 8
5 5 22 4.82 1.76  

 

Software Satisfaction - by Platform

7=Very satisfied, 6=Mostly satisfied, 5=Somewhat satisfied, 4=Neutral, 3=Somewhat dissatisfied, 2=Mostly dissatisfied, 1=Very dissatisfied

 

Item Num who rated this item as: Total Responses Average Score Std. Dev. Change from 2003
1 2 3 4 5 6 7
SP SW: Fortran compilers

2 3 8 53 81 147 6.41 0.80 0.07
SP SW: Software environment


5 9 70 71 155 6.34 0.73 0.10
SP SW: Programming libraries

1 8 2 60 54 125 6.26 0.84 -0.01
SP SW: C/C++ compilers

2 5 6 35 46 94 6.26 0.95 0.04
SP SW: Applications software


10 6 37 38 91 6.13 0.96 0.13
SP SW: General tools and utilities

4 8 14 43 33 102 5.91 1.06 -0.07
SP SW: Performance and debugging tools
2 5 7 16 54 34 118 5.84 1.14 0.27
SP SW: Visualization software
2 2 18 4 19 17 62 5.40 1.41 0.32
PDSF SW: Software environment


4 1 13 24 42 6.36 0.93 0.03
PDSF SW: C/C++ compilers


5 1 12 20 38 6.24 1.02 -0.20
PDSF SW: Programming libraries


5 1 14 16 36 6.14 1.02 0.14
PDSF SW: Fortran compilers


6 1 6 10 23 5.87 1.25 -0.16
PDSF SW: General tools and utilities
1
5 2 17 10 35 5.83 1.18 -0.10
PDSF SW: Applications software

1 6 2 14 10 33 5.79 1.17 -0.08
PDSF SW: Performance and debugging tools
1
5 4 15 10 35 5.77 1.19 0.46
Escher SW: visualization software
1 1 9
4 6 21 5.10 1.58 0.35
Newton SW: application software 1 1 2 8
5 5 22 4.82 1.76  

 

Comments about Software:   15 responses

 

6   Suggestions / requests for improvements
4   Comments on debugging and performance tools
4   Some dissatisfaction
2   Satisfied
Suggestions / requests for improvements:   6 responses

It would be nice to have uniform support for 64-bit including GNU software. But consultants quickly addressed and solved problems.

Loadleveler is a mess. In there nothing better?

... Running multiple processors interactively is such a pain.

I would like to have VASP available.

In general, the NERSC software configuration suits my needs very well.
One anticipated development would be welcome: In order to take advantage of some of latest enhancements to the Parallel Environment on AIX, one needs to compile with -q64. However, we require HDF5 for our I/O. To my understanding there is no HDF library that has been build to link to a 64-bit addressing code. Can this be addressed so that we can make better use of the system?

NERSC response: 64-bit versions of the HDF5 library are available on Seaborg. Refer to the I/O Libraries on Seaborg web page for more information.

My applications involve the discretization of nonlinear operators. To solve these problems I have used the Toolkit for Advanced Optimization (TAO) and PETSc. Its nice to have these latest versions of these packages on the system, but I have installed them myself on a couple of occasions.

Comments on debugging and performance tools:   4 responses

Totalview is such a pain. ...

need better debugging and performance evaluation tools. The totalview is not so great. The xprofiler is great. But need better performance evaluation tools for MPI communication times, etc.

Part of the problem here is my lack of knowledge of performance, debugging, general tools and debugging. This may be as much my fault as anyones but for some reason I have not learned how to find them and learn about them. I do believe that there was a one line lecture on some debugging tool but either I was not available at that time or the type of network it was offered on was not available to me.

The loss of poe+ after the OS upgrade in September 2004 is a significant problem.

Some dissatisfaction:   4 responses

I miss Linux's less command when I use Seaborg.

The IBM compilers tend to be annoying, but that's mostly because I'm used to GNU C.

f-secure does not seem to have any graphics capabilities. So use of visualization software seems limited.

Connections to Escher/Newton are too slow. There are considerable amount of time delay when using AVS/Mathematica remotely from Escher/Newton.

Satisfied:   2 responses

My uses are limited to a few compilers and IDL. Both of these work up to my satisfaction.

We have been very much satisfied with NERSC's software resources so far.