Cluster Information

From Earlham Cluster Department

(Difference between revisions)
Jump to: navigation, search
(Current To-Do)
(Current To-Do)
Line 3: Line 3:
* Writeup for Jeff Krause -- see email -- '''Aaron, Sam, Fitz, Gus?, Charlie?'''
* Writeup for Jeff Krause -- see email -- '''Aaron, Sam, Fitz, Gus?, Charlie?'''
-
* Brad's Graphing Tool  (12/Oct/09)  -- '''Brad'''
+
* Brad's Graphing Tool  (19/Oct/09)  -- '''Brad'''
   * 2 y-axis scales (runtime and problem size)
   * 2 y-axis scales (runtime and problem size)
   * error bars for left and right y-axes with checkboxes for each
   * error bars for left and right y-axes with checkboxes for each
   * eps file for the poster
   * eps file for the poster
-
* TeraGrid Runs  (12/Oct/09) -- '''Aaron, Sam, Gus'''
+
* TeraGrid Runs  (19/Oct/09) -- '''Aaron, Sam, Gus'''
   * Update configure.ac based on Fitz's notes from Kraken
   * Update configure.ac based on Fitz's notes from Kraken
-
* New LittleFe Boards  (12/Oct/09) -- '''Gus'''
+
* New LittleFe Boards  (19/Oct/09) -- '''Gus'''
   * Order the boards -- '''Charlie'''
   * Order the boards -- '''Charlie'''
   '''Board Criteria:'''
   '''Board Criteria:'''
Line 16: Line 16:
   * 2 GB ram
   * 2 GB ram
   * Cuda Enabled (with chip on board); OpenCL O.K. too
   * Cuda Enabled (with chip on board); OpenCL O.K. too
-
* BCCD Testing  (12/Oct/09) -- '''Gus, Sam, and Aaron'''
+
* BCCD Testing  (19/Oct/09) -- '''Gus, Sam, and Aaron'''
   * How many node boot up as dhcp servers?  (answer:  just the first one, confirmed 10/13)
   * How many node boot up as dhcp servers?  (answer:  just the first one, confirmed 10/13)
   * Liberation testing -- '''Charlie, Gus, Sam, Aaron''' -- moved to Tuesday, 10/20 @ 2:30p
   * Liberation testing -- '''Charlie, Gus, Sam, Aaron''' -- moved to Tuesday, 10/20 @ 2:30p
Line 31: Line 31:
* Code Sanity Check  (12/Oct/09) -- '''Aaron and Sam'''
* Code Sanity Check  (12/Oct/09) -- '''Aaron and Sam'''
   * Take exact same set of runs on Sooner
   * Take exact same set of runs on Sooner
-
* EC/SCED Poster Sessions  (12/Oct/09) '''Aaron, Sam, Fitz, and Brad'''
+
* EC/SCED Poster Sessions  (19/Oct/09) '''Aaron, Sam, Fitz, and Brad'''
   * Describe the environment we've created -- how we obtain results is just as interesting as results themselves
   * Describe the environment we've created -- how we obtain results is just as interesting as results themselves
   * Pick good graphs
   * Pick good graphs

Revision as of 18:49, 19 October 2009

Contents

Current To-Do

Date represents last meeting where we discussed the item

 * 2 y-axis scales (runtime and problem size)
 * error bars for left and right y-axes with checkboxes for each
 * eps file for the poster
 * Update configure.ac based on Fitz's notes from Kraken
 * Order the boards -- Charlie
 Board Criteria:
 * mini itx form factor
 * at least 2 core (probably max 2 core)
 * 2 GB ram
 * Cuda Enabled (with chip on board); OpenCL O.K. too
 * How many node boot up as dhcp servers?  (answer:  just the first one, confirmed 10/13)
 * Liberation testing -- Charlie, Gus, Sam, Aaron -- moved to Tuesday, 10/20 @ 2:30p
 * Verify no I/O errors in dmesg
 * Test all boot options, including linux 5
 * Send /etc/bccd-revision to Skylar w/ each email
 * Test MPICH2 on Life, paramspace, GalaxSee, etc.
   * module unload openmpi && module load mpich2 && make clean && make
   * for MPICH2, machines file must be in current directory
   * do -np 2, 4, etc.
 * Send flight info to Jeff Krause -- Charlie
 * Talk to Travel-On -- Brad and Charlie
 * Take exact same set of runs on Sooner
 * Describe the environment we've created -- how we obtain results is just as interesting as results themselves
 * Pick good graphs
 * Add text of TeraGrid poster into CVS -- Sam
 * Update Fitz's abstract -- Fitz
 * EC -- Wednesday (10/21) @ 6 pm
 * SCEd -- Combine TeraGrid and Fitz posters

Summer of Fun (2009)

An external doc for GalaxSee
Documentation for OpenSim GalaxSee

What's in the database?

GalaxSee (MPI) area-under-curve (MPI, openmpi) area-under-curve (Hybrid, openmpi)
acl0-5 bs0-5 GigE bs0-5 IB acl0-5 bs0-5 GigE bs0-5 IB acl0-5 bs0-5 GigE bs0-5 IB
np X-XX 2-20 2-48 2-48 2-12 2-48 2-48 2-20 2-48 2-48

What works so far? B = builds, R = runs, W = works

B-builds, R-runs area under curve GalaxSee (standalone)
Serial MPI OpenMP Hybrid Serial MPI OpenMP Hybrid
acls BRW BRW BRW BRW BRW
bobsced0 BRW BRW BRW BRW BRW
c13 BRW
pople
Charlie's laptop BRW

To Do

Implementations of area under the curve

GalaxSee Goals

GalaxSee - scale to petascale with MPI and OpenMP hybrid.

LittleFe

Notes from May 21, 2009 Review

BobSCEd Upgrade

Build a new image for BobSCEd:

  1. One of the Suse versions supported for Gaussian09 on EM64T [v11.1] - Red Hat Enterprise Linux 5.3; SuSE Linux 9.3, 10.3, 11.1; or SuSE Linux Enterprise 10 (see G09 platform list) <-- CentOS 5.3 runs Gaussian binaries for RHEL ok
  2. Firmware update?
  3. C3 tools and configuration [v4.0.1]
  4. Ganglia and configuration [v3.1.2]
  5. PBS and configuration [v2.3.16]
  6. /cluster/bobsced local to bs0
  7. /cluster/... passed-through to compute nodes
  8. Large local scratch space on each node
  9. Gaussian09
  10. WebMO and configuration [v9.1] - Gamess, Gaussian, Mopac, Tinker
  11. Infiniband and configuration
  12. GNU toolchain with OpenMPI and MPICH [GCC v4.4.0], [OpenMPI v1.3.2] [MPICH v1.2.7p1]
  13. Intel toolchain with OpenMPI and native libraries
  14. Sage with do-dads (see Charlie)
  15. Systemimager for the client nodes?

Installed:

Fix the broken nodes.

(Old) To Do

BCCD Liberation

Curriculum Modules

LittleFe

Infrastructure

SC Education

Current Projects

Past Projects

General Stuff

Items Particular to a Specific Cluster

Curriculum Modules

Possible Future Projects

Archive

Personal tools
Namespaces
Variants
Actions
websites
wiki
this semester
Toolbox