1. I Brazilian LHC Computing Workshop Welcome

2. Purpose
Discuss the computing needs of each experiment and establish the amount of computing resource that should be available in Brazil for processing the LHC data
Make a strategic plan to guarantee that  the different middleware and software could smoothly run in all the resources
Pursue the real integration of the resources in a distributed LHC Tier 2 ( Tier 1) facility
Discuss about a unified administrative/technical structure to present ourselves as a single, coherent and organized group to CERN and to our financial agencies
Establish guidelines for new resource and infrastructure projects
30/Mar/2006
S. F. Novaes

3. OSG X LCG X AliEn X Dirac X …
LHCb:
Very small participation from US
Syracuse University: 11 out of 654 members
Focused on European solutions
LCG, EGEE
 EELA (E-Infrastructure shared between Europe and Latin America)
Using DIRAC Grid Framework for LHCb
Distributed Infrastructure with Remote Agent Control
Python based grid job management system
Follows Condor model of job pools
Service Oriented Architecture
Alice
Alice Environment
Starting point for developing the gLite, next generation of grid middleware developed by EGEE
Projects using AliEn
ALICE is using for simulation, reconstruction and distributed analysis of physics data
Panda at GSI, Darmstadt is using for simulation
Mammogrid, European Federated Mammogram Database
AliEn will be progressively interfaced to emerging products from both Europe and the US
30/Mar/2006
S. F. Novaes

4. A Distributed Infrastructure
The Evaluation Panel agrees with the idea of establishing a common Nordic grid. The Nordic countries, individually, appear to have difficulties with establishing the sufficient critical mass to become attractive collaboration partners in the larger grid projects in Europe and the rest of the world. But the establishment of Nordic Data Grid Facility will ensure – for scientist in the Nordic countries – a grid infrastructure which is of sufficient critical mass to join various scientific projects needing grid and high performance computing in Europe and the rest of the world.
Evaluation of NorduGrid (Spring 2005)
30/Mar/2006
S. F. Novaes

5. Present Status and New Initiatives
Present Computing Power:
SPRACE:
240 processors = 1.45 TeraFlops = 310 kSi2k (after last upgrade)
15 TB of disk space
HEPGrid UERJ:
200 processors = 1.06 TeraFlops = 210 kSi2k
7 TB of disk space
UFRJ and CBPF
???
New initiatives
GridUNESP
A set of cluster focused on different branches of Science (UNESP)
New proposals:
30/Mar/2006
S. F. Novaes

6. Several research areas:
High Energy Physics
Lattice QCD
High Tc Superconductivity
Bioinformatics
Genomics and Cancer Studies
Protein Folding
Molecular Biology
Geological and Hydrographic Modeling
Fluid Dynamics and Turbulent Flow
Numerical Methods in Mechanical Engineering.
Tier 0
512 processors + 12 TB RAID
Tiers 1
7 X 64 processors + 4 TB RAID
30/Mar/2006
S. F. Novaes

7. Venue: University of São Paulo (USP)
8 May (Monday)
Venue: University of São Paulo (USP)
09:45 – 10:00
Welcome
10:00 – 10:30
Alice Computing
Alexandre Suaide
10:30 – 11:00
Atlas Computing
Fernando Marroquim
11:00 – 11:30
Coffee Break
11:30 – 12:00
CMS Computing
Andre Sznajder
12:00 – 12:30
LHCb Computing
Miriam Gandelman
12:30 – 14:00
Lunch
14:00 – 14:30
The EELA Project
Diego Carvalho
14:30 – 15:00
LCG-OSG Interoperability
Ruth Pordes
15:00 – 15:30
15:30 – 16:00
Distributed Tier 2: A Case Study
Horst Severini et al.
16:00 – 18:00
Discussion: Perspectives & Outlook
Sérgio Novaes (moderator)
20:00
Dinner:
30/Mar/2006
S. F. Novaes