1 |
( please pardon my crosspost on this. It won't happen again) |
2 |
|
3 |
For those involved in high-performance computing (HPC) and computational |
4 |
science and engineering (CSE)*, Gentoo, is a powerful tool, both on the |
5 |
desktop and on servers or clusters. With it, users can build environments |
6 |
that do not waste time offering unwanted network services and system |
7 |
daemons, and the binaries for the OS can be highly optimized to take full |
8 |
advantage of the system architecture. In particular, this can improve the |
9 |
efficiency of numerical simulations that depend on floating point |
10 |
performance. Shaving 1 or 2 cycles from an operation may not seem like |
11 |
much, but when the routine is executed 5 million times per calculation, |
12 |
the savings rapidly add up. Also, Gentoo doesn't have a rigid release |
13 |
cycle with EOL dates forced on users who have working systems. |
14 |
Administrators and users have the ultimate control over when upgrades are |
15 |
made and to which packages. Finally, a group of enthusiastic volunteers |
16 |
have written ebuilds for over 100 different scientific and engineering |
17 |
applications and libraries, making them readily accessible to the user |
18 |
community. |
19 |
|
20 |
* Computational Science and Engineering is related to but distinct from |
21 |
Computer |
22 |
Science. It is not usually concerned with research into computing for its |
23 |
own |
24 |
ends, but as a tool for making advances in other fields. It covers areas as |
25 |
broad as Geographic Information Systems, Bioinformatics, Computational Fluid |
26 |
Dynamics, and Chemical Reactor Design, with many other fields as well. |
27 |
|
28 |
With the potential advantages of Gentoo-based HPC and CSE environments, we |
29 |
feel that the Gentoo community ought to do more to reach out to potential |
30 |
users and developers in these fields. Gentoo doesn't come without a |
31 |
learning curve, and even when that curve is conquered the need for a |
32 |
specialized peer group is not obviated. Furthermore, Gentoo lacks name |
33 |
recognition in these fields, and even when a developer or administrator |
34 |
finds Gentoo and discovers the benefits of its philosophy, there is often |
35 |
a sense of isolation that discourages him or her from moving forward with |
36 |
Gentoo-based solutions. To address these issues, we propose the |
37 |
formation of a Gentoo-science project, encompassing both desktop and |
38 |
server issues, with the following list of potential project goals. |
39 |
|
40 |
1) To act as a clearinghouse for information about the use of Gentoo |
41 |
Linux in computational science and engineering, including the |
42 |
installation of major third-party applications, such as Matlab and |
43 |
Mathematica, which are often less than completely Gentoo-friendly. |
44 |
|
45 |
2) To be a presence for Gentoo at technical meetings and trade shows, |
46 |
both in informal settings, such as BOFs and badge button campaigns, |
47 |
and in more formal settings, such as organized symposia or vendor |
48 |
booths. |
49 |
|
50 |
|
51 |
3) To coordinate with the sci herd and other appropriate Gentoo herds |
52 |
for bug-testing, code validation, and potential tree restructuring |
53 |
as necessary and desirable. |
54 |
|
55 |
4) To provide input to project teams about the specific needs of |
56 |
computational science and engineering users, in particular the |
57 |
gentoo-server, gentoo-cluster, and gentoo-desktop teams. |
58 |
|
59 |
5) To advocate with developers and independent software vendors for |
60 |
increased distribution neutrality in specifying software |
61 |
pre-requisites for applications, and to encourage use of packaging |
62 |
systems that are ebuild-friendly. |
63 |
|
64 |
Contact information: |
65 |
|
66 |
At present, there is no official irc channel or gentoo forum or mailing |
67 |
list for this proposed project. Once the level of interest is determined, |
68 |
a mailing list will probably be set up to make communications easier. The |
69 |
proponents of this project can often been found in #gentoo-server or |
70 |
#gentoo-cluster on irc.freenode.net. Please feel free to post your |
71 |
comments as followups to this message. E-mailed comments or requests to |
72 |
be added to the possible mailing list should be sent to afant@××××××××.cc |
73 |
(having "gentoo-science" in the subject would be greatly appreciated). |
74 |
|
75 |
Thank you to everyone for your attention and thoughts about this exciting |
76 |
new |
77 |
direction for Gentoo. |
78 |
|
79 |
Andrew Fant |
80 |
afant@××××××××.cc |
81 |
JFMuggs on freenode.net |