Porting HPC Applications to Grids and Clouds - Cloud, Grid and High Performance Computing: Emerging Applications - page 33

each VM running 12 threads, there were 1440
processes working in parallel.
All of the VMs were running standard operating
systems and none of the software used in the project
is cloud-specific. The portability concern for this
application would be the ability to migrate those
VM images to another provider without having
to rebuild or reconfigure the images.
The estimated cost for the cloud-based solution
is less than half the cost of an in-house solution.
That cost estimate does not include the additional
electricity or system administration costs of an
in-house solution, so the actual savings will be
even greater. Storage of the datasets will be cloud-
based as well.

For R&D experts this characteristic was seen to
be a necessary evil: implementing complex HPC
applications has never been easy.
Grid: the way station to the cloud. After 40
years of dealing with HPC, Grid computing was
indeed the next big thing for the grand challenge,
big-science researcher, while for the enterprise
CIO, the Grid was a way station on its way to the
cloud model. For the enterprise today, private and
public clouds are providing all the missing pieces:
easy to use, economies of scale, business elasticity
up and down, and pay-as you go and thus getting
rid of some capital expenditure (CapEx), but still
concerned of removing the roadblocks mentioned
above. And in cases where security matters, there
is always the private cloud solution. In more
complex HPC environments, with applications
running under different policies, private clouds
can easily connect to public clouds into a hybrid
cloud infrastructure, to balance security with
elasticity and efficiency.
Different policies, what does that mean?
No HPC simulation job is alike. Jobs differ by
priority, strategic importance, deadline, budget,
IP and licenses. In addition, the nature of the code
often necessitates a specific computer architecture,
operating system, memory, and other resources.
These important factors influence where and when
a job is running. For any new type of job, a set of
specific requirements decide on the set of specific
policies that have to be defined and programmed
into the scheduler, such that any of these jobs
will run according to these policies. Ideally, this
is guaranteed by a dynamic resource broker that
controls submission to Grid or cloud resources,
be they local or global, private or public.
Grids or clouds? One important question is
still open: how do I find out, and then 'tell' the
resource broker, whether my application should
run on the Grid or in the cloud? The answer, among
others, depends on the algorithmic structure of
the compute-intensive part of the program, which
might be intolerant of high latency and low band-
width as they are often present in public clouds.
This has been observed with benchmark results

CONCLUSION: GRIDS VERSUS
CLOUDS FOR HPC

Time and again, people ask questions like “Will
HPC codes move to the cloud?” or “Now that cloud
computing is well accepted, are Grids dead?” or
even “Should I now build my Grid in the cloud?”
Despite all the promising developments in the Grid
and cloud computing space, and the avalanche
of publications and talks on this subject, many
people still seem to be confused and hesitant to
take the next step. A number of issues are driv-
ing this uncertainty, (Gentzsch, 2009), which are
discussed in the following.
Grids didn't keep all their promises . Grids
did not evolve into the next fundamental IT in-
frastructure for mainstream HPC, as had been
anticipated by some experts. Because of the
diversity of computing environments different
middleware stacks (for department, enterprise,
global, compute, data, sensors, instruments,
etc.) had to be developed, and had to face differ-
ent usage models with different benefits. HPC
Grids are providing better resource utilization
and flexibility, while global Grids are best suited
for complex R&D application collaboration and
resource sharing. For enterprise usage, setting up
and operating Grids was often too complicated.