Unsurpassed Performance & Ultra Scale Computing

Presented By:
NITHIN KUMAR T
408019
MCA V Semester
Introduction
The word "supercomputer" entered the mainstream lexicon
in 1996 and 1997 when IBM's Deep Blue supercomputer
challenged the world chess champion in two tournaments
broadcast around the world.

Since then, IBM has been busy improving its

supercomputer technology and tackling much deeper
problems.

Their latest project, code named Blue Gene, is poised to

shatter all records for computer and network performance.
What is a Super Computer?
A supercomputer is a computer that is at the frontline of
current processing capacity, particularly speed of calculation.

Today, supercomputers are typically one-of-a-kind custom

designs produced by "traditional" companies such
as Cray, IBM and Hewlett-Packard, who had purchased many
of the 1980s companies to gain their experience.
Why we need Super Computers?
Supercomputers are very useful in highly calculation-
intensive tasks such as
• Problems involving quantum physics, 
• Weather forecasting,
• Climate research, 
• Molecular modeling (computing the structures and
properties of chemical compounds,
biological macromolecules, polymers, and crystals),
• Physical simulations (such as simulation of airplanes
in wind tunnels, simulation of the detonation
of nuclear weapons, and research into nuclear fusion).
Why we need Super Computers?
•Also, they are useful for a particular class of problems,
known as Grand Challenge problems, full solution for such
problems require semi-infinite computing resources.
NASA’s Linux-based Super Computer
Why Supercomputers are Fast
Several elements of a supercomputer contribute to its high
level of performance:
▫ Numerous high-performance processors (CPUs) for parallel
processing
▫ Specially-designed high-speed internal networks
▫ Specially-designed or tuned operating systems
What is Blue gene?
Blue Gene is a computer architecture project designed to
produce several supercomputers that are designed to reach
operating speeds in the PFLOPS (petaFLOPS = 1015) range,
and currently reaching sustained speeds of nearly
500 TFLOPS (teraFLOPS = 1012).

It is a cooperative project among IBM(particularly IBM

Rochester and the Thomas J. Watson Research Center),
the Lawrence Livermore National Laboratory(LLNL),
the United States Department of Energy (which is partially
funding the project), and academia.
* Computer architecture is the conceptual design and fundamental operational structure of a
computer system.
* FLOPS (or flops or flop/s) is an acronym meaning FLoating point Operations Per Second.
Blue Gene
• A massively parallel supercomputer using tens of
thousands of embedded PowerPC processors
supporting a large memory space
• With standard compilers and message passing
environment
Why the name Blue gene?
“Blue” - The corporate color of IBM

“Gene” - The intended use of the Blue Gene clusters was for
Computational biology.
Why Blue Gene?
Blue Gene is an IBM Research project dedicated to
exploring the
frontiers in supercomputing:
- in computer architecture,
- in the software required to program and control massively
parallel systems, and
- in the use of computation to advance the understanding of
important biological processes such as protein folding.

Learning more about biomolecular mechanisms is expected

to give medical researchers better understanding of
diseases, as well as potential cures.
History
• Dec’99, IBM Research announced $100M US effort to
build a Petaflop scale supercomputer.
• Two goals of The Blue Gene project :
▫ Massively parallel machine architecture and software
▫ Bio-Molecular Simulation – advance orders of magnitude
• November 2001, Partnership with Lawrence Livermore
National Laboratory (LLNL)

and this resulted in …

BLUE GENE
Blue Gene Projects
There are four Blue Gene projects in development:
- Blue Gene/L,
- Blue Gene/C,
- Blue Gene/P, and
- Blue Gene/Q.
Blue Gene/L
The first computer in the Blue Gene series, is Blue
Gene/L.
It is developed through a partnership with Lawrence
Livermore National Laboratory (LLNL).

The term Blue Gene/L sometimes refers to the computer

installed at LLNL; and sometimes refers to the architecture
of that computer.

As of November 2006, there are 27 computers on

the Top500 list using the Blue Gene/L architecture.
Blue Gene/L Super Computer
History of Blue gene/L
In December 1999, IBM announced a $100 million research
initiative for a five-year effort to build a massively parallel
computer, to be applied to the study of biomolecular
phenomena.

The project has two main goals:

- to advance understanding of the biomolecular
mechanisms via large-scale simulation, and
- to explore novel ideas in massively parallel
machine architecture and software

* Parallel computing is a form of computation in which many calculations are

carried out simultaneously,
History of Blue gene/L
In November 2001, Lawrence Livermore National
Laboratory(LLNL) joined IBM as a research partner for
Blue Gene.

Blue Gene/L is al100 TFLOPSso the first supercomputer

ever to run over  sustained on a real world application.
This achievement won the 2005 Gordon Bell Prize.

In November 2007, the LLNL Blue Gene/L remained at the

number one spot as the world's fastest supercomputer.
 Blue Gene/L System
64 Racks
Overview Rack

32 node cards
65,536 chips
Scalable from 1 rack to 64 racks 1,024 chips
Rack has 2048 processors with 512 MB or 1
GB DRAM/node

Node card
180/360 TF/s
32 chips 32 TB
16 compute, 0-2 IO cards
2.8/5.6 TF/s
512 GB
Compute node

2 chips

90/180 GF/s
Chip 16 GB November 2006 Top500 List www.top500.org
2 processors
2 in Top10 (#1 and #3)
5.6/11.2 GF/s 9 in Top30
1.0 GB 16 in Top100
2.8/5.6 GF/s 27 overall in Top150

19
Blue Gene/L Architecture contd…

1024 nodes

System Overview
Blue Gene/L Architecture
Each compute node has two 700MHz PowerPC 440
embedded processors

Each of the dual processors on the compute node has two

"floating point units (FPU)," engines for performing
mathematical calculations.

The dual FPUs give each Blue Gene/L node a theoretical

peak performance of 5.6GFLOPS (gigaFLOPS).
Blue Gene/L Architecture
Compute nodes are packaged two per compute card, with
16 compute cards plus up to 2 I/O nodes per node board.

There are 32 node boards per cabinet/rack. 

By integration of all essential sub-systems on a single chip,

each Compute or I/O node dissipates low power (about 17
watts, including DRAMs).
One Blue Gene/L nodeboard
Blue Gene/C (Cyclops64)
Blue Gene/C (now renamed to Cyclops64) is a sister-project
to Blue Gene/L.

It is a massively parallel, supercomputer-on-a-chip cellular

architecture.

The Cyclops64 project aims to create the

first "supercomputer on a chip".
Blue Gene/C (Cyclops64)
Cyclops64 exposes much of the underlying hardware to the
programmer, allowing the programmer to write very high
performance, finely tuned software.

One negative consequence is that efficiently programming

Cyclops64 is difficult.

The theoretical peak performance of a Cyclops64 chip is

80 gigaflops 
Blue Gene/P
On June 26, 2007, IBM unveiled Blue Gene/P, the second
generation of the Blue Gene supercomputer.

Designed to run continuously at 1PFLOPS (petaFLOPS), it

can be configured to reach speeds in excess of 3 PFLOPS.

It is at least seven times more energy efficient than any

other supercomputer, accomplished by using many small,
low-power chips connected through five specialized
networks.
Blue Gene/P Architecture
Four 850 MHz PowerPC, 450 processors are integrated on
each Blue Gene/P chip.

The 1-PFLOPS Blue Gene/P configuration is a 294,912-

processor, 72-rack system harnessed to a high-speed,
optical network.

Blue Gene/P can be scaled to an 884,736-processor, 216-

rack cluster to achieve 3-PFLOPS performance.

A standard Blue Gene/P configuration will house 4,096

processors per rack.
Blue Gene/Q
The last known supercomputer design in the Blue Gene
series, Blue Gene/Q is aimed to reach 20 Petaflops in the
2011 time frame.

It will continue to expand and enhance the Blue Gene/L

and /P architectures with higher frequency at much
improved performance per watt.
Conclusion
U.S President Obama recognized IBM and its Blue Gene
family of supercomputers with the National Medal of
Technology and Innovation.

The influence of the Blue Gene supercomputer's energy-

efficient design and computing model can be seen today
across the Information Technology industry.

Today, 18 of the top 20 most energy efficient

supercomputers in the world are built on IBM high
performance computing technology.
Conclusion
Blue Gene has some unusual features, but IBM has tried as
much as possible to anchor the system to more mainstream
technology.

Blue Gene would influence the way in which mainstream

computers of the future are built.

Staying on the beaten path is the best way to take advantage

of technology that's improving fastest, and it also makes it
easier to create products out of the Blue Gene research.
Thank U !! 