Red Storm Rollout Status

1
Red Storm Rollout Status

• John P. Noe
• Sandia National Laboratories

Sandia is a multiprogram laboratory operated by
Sandia Corporation, a Lockheed Martin
Company,for the United States Department of
Energys National Nuclear Security
Administration under contract DE-AC04-94AL85000.
2
Key Dates
3
(No Transcript)
4
Movie
5
Current Status

• Physical infrastructure in place and performing
  as expected.
• System cabled (X,Z Y mostly) and passed
  manufacturing check-out
• External networks ready
• Computing infrastructure integration underway

6
Red Storm Configuration2/23/2005
Sandia
Cray Sandia
7
3/31/05 Initial Operations Milestone

• Initial Operation of all Red Storm hardware will
  be demonstrated at Sandia by providing
  functionality needed for early testing of
  applications codes. We will run the 7X acceptance
  suite and document the results.
• The 7x test suite consists of 10 applications and
  benchmarks that will be used in Red Storm
  acceptance testing. For 3/31, the codes must run
  correctly.

8
3/31 Goals

• All hardware will be online and eligible to use
  in testing, subject to expected hardware failure
  rates and modes.
• All compute nodes must be booted and available
  for use by the applications.
• All RAIDS must be configured and operational with
  formatted file system(s).
• 10GigE network connectivity to the extent
  supported by current switch configurations
• Applications running
• Standard service and I/O configurations

9
(No Transcript)
10
3Q FY 05

• Scale up Service and I/O Partitions
• Complete infrastructure integration
• Execute security tests and initiate classified
  processing nlt June 2005
• Continue scalability testing and code porting
• Begin acceptance testing of Red Storm
• Deploy Version 1 of user support documents and
  training

11
4Q FY05

• Continue enhancing stability and scaling
• Enlarge group of 'Limited Availability' users and
  codes (Q4 Milestone)
• Integration of PSE, DVS, and DART products and
  capabilities
• Revise and deploy Version 2 of user support
  documents and training
• Complete Acceptance Testing