Information Technology Reference
In-Depth Information
NAS Parallel Benchmark
on Amazon EC2
high-performance network provisioning solution
can be devised for this problem.
LINPACK Benchmark on Amazon
Cluster Compute Instances
In order to find out if and how clouds are suit-
able for HPC applications, Ed Walker (Walker
2008) run an HPC benchmark on Amazon EC2.
He used several macro and micro benchmarks to
examine the “delta” between clusters composed
of state-of-the-art CPUs from Amazon EC2
versus an HPC cluster at the National Center
for Supercomputing Applications (NCSA). He
used the NAS Parallel Benchmarks (NAS 2010)
to measure the performance of these clusters for
frequently occurring scientific calculations. Also,
since the Message-Passing Interface (MPI) library
is an important programming tool used widely in
scientific computing, his results demonstrate the
MPI performance in these clusters by using the
mpptest micro benchmark. For his benchmark
study on EC2 he use the high-CPU extra large
instances provided by the EC2 service.
The NAS Parallel Benchmarks (NPB 2010)
comprise a widely used set of programs designed
to evaluate the performance of HPC systems. The
core benchmark consists of eight programs: five
parallel kernels and three simulated applications.
In aggregate, the benchmark suite mimics the criti-
cal computation and data movement involved in
computational fluid dynamics and other “typical”
scientific computation.
Research from Ed Walker (2008) about the
runtimes of each of the NPB programs in the
benchmark shows a performance degradation of
approximately 7%-21% for the programs running
on the EC2 nodes compared to running them on
the NCSA cluster compute node.
Further results and an in-depth analysis showed
that message-passing latencies and bandwidth
are an order of magnitude inferior between EC2
compute nodes compared to between compute
nodes on the NCSA cluster. Walker (2008) con-
cluded that substantial improvements could be
provided to the HPC scientific community if a
In July 2010, Amazon announced its Cluster Com-
pute Instances (CCI 2010) specifically designed
to combine high compute performance with high
performance network capability to meet the needs
of HPC applications. Unique to Cluster Compute
instances is the ability to group them into clusters
of instances for use with HPC applications. This
is particularly valuable for those applications that
rely on protocols like Message Passing Interface
(MPI) for tightly coupled inter-node communi-
cation. Cluster Compute instances function just
like other Amazon EC2 instances but also offer
the following features for optimal performance
with HPC applications:
•
When run as a cluster of instances, they
provide low latency, full bisection 10 Gbps
bandwidth between instances. Cluster siz-
es up through and above 128 instances are
supported.
•
Cluster Compute instances include the spe-
cific processor architecture in their defini-
tion to allow developers to tune their appli-
cations by compiling applications for that
specific processor architecture in order to
achieve optimal performance.
The Cluster Compute instance family cur-
rently contains a single instance type, the Cluster
Compute Quadruple Extra Large with the follow-
ing specifications: 23 GB of memory, 33.5 EC2
Compute Units (2 x Intel Xeon X5570, quad-core
“Nehalem” architecture), 1690 GB of instance
storage, 64-bit platform, and I/O Performance:
Very High (10 Gigabit Ethernet).
As has been benchmarked by the Lawrence
Berkeley Laboratory team ( 2010), some applica-
tions can expect 10x better performance than on
Search WWH ::
Custom Search