hyPACK-2013 Mode-1 : Multi-threading -Performance & Math. Libraries
The Performance Library is a set of optimized, high-speed mathematical subroutines for numerically
intensive problems that arise in HPC, financial and other compute-intensive applications.
With optimized compiler switches give performance boost for compute-intensive applications.
Tuning and performance of an application Program based Compiler optimisation techniques, compiler switches,
memory allocators and use of System tuned mathematical libraries play an
important role to extract sustained performance of an application.
Effective use of right
Compiler Optimisation flags with choice of available mathematical libraries on multi-core
processors may improve the performance dramatically.
Click here ...... to know more about Tuning & performance/Codes
The High Performance Computing (HPC) tools such as highly optimized compilers and libraries, code-level
and Memory debuggers, Thread analyzer, Application Performance analyzer, and system-profiling tools help
developer to take full advantage of multi-core architecture systems.
The commercial HPC tools, which are provided by
Intel Software tools,
AMD,
IBM POWER-6/POWER-7 AIX,
HP,
Sun Studio 12, and
PGI Compilers
will be useful to developers from performance point of view. Also, the
open source tools
PAPI,
HPCToolkit,
Jumpshot,
Parallel Processing Scientific (commercial /Open Source) libraries
( PetSc,
Netlib Repository Benchmarks,
PetSc,
MATLAB) and
other popular Sparse Matrix Computations libraries
provide an optimized environment for the development
of single, multi-threaded, and distributed MPI
applications, leading to more robust scalable software.
Systeam and Application Benchmarks such as
Top-500 Benchmarks,
HPC Challenge benchmarks
NAS
are executed on hyPACK-2013 Laboratory computing systems.
Several factors such as proper
use of threading, understanding of how threads operate, algorithm used for your application, the
threading application programming interface (API), the compiler runtime environment, Use of tuned
scientific computing libraries and the
number of multi-cores used for your application require serious attention. A brief summary of
mathematical libraries and examples are discussed.
List of Programs:
|