This title appears in the Scientific Report :
2014
Please use the identifier:
http://dx.doi.org/10.3233/978-1-61499-381-0-773 in citations.
Profiling Hybrid HMPP Applications with Score-P on Heterogeneous Hardware
Profiling Hybrid HMPP Applications with Score-P on Heterogeneous Hardware
In heterogeneous environments with multi-core systems and accelerators, programming and optimizing large parallel applications turns into a time-intensive and hardware-dependent challenge. To assist application developers in this process, a number of tools and high-level compilers have been develope...
Saved in:
Personal Name(s): | Schlütter, Marc |
---|---|
Philippen, Peter / Morin, Laurent / Geimer, Markus / Mohr, Bernd | |
Contributing Institute: |
Jülich Supercomputing Center; JSC |
Published in: |
Parallel Computing: Accelerating Computational Science and Engineering (CSE) |
Imprint: |
IOS Press
2014
|
Physical Description: |
773 - 782 |
ISBN: |
978-1-61499-380-3 |
DOI: |
10.3233/978-1-61499-381-0-773 |
Conference: | International Conference on Parallel Computing, Munich (Germany), 2013-09-10 - 2013-09-13 |
Document Type: |
Contribution to a book Contribution to a conference proceedings |
Research Program: |
Computational Science and Mathematical Methods |
Series Title: |
Advances in Parallel Computing
25 |
Publikationsportal JuSER |
In heterogeneous environments with multi-core systems and accelerators, programming and optimizing large parallel applications turns into a time-intensive and hardware-dependent challenge. To assist application developers in this process, a number of tools and high-level compilers have been developed. Directive-based programming models such as HMPP and OpenACC provide abstractions over low-level GPU programming models,such as CUDA or OpenCL. The compilers developed by CAPS automatically transform the pragma-annotated application code into low-level code, thereby allowing the parallelization and optimization for a given accelerator hardware. To analyze the performance of parallel applications, multiple partners in Germany and the US jointly develop the community measurement infrastructure Score-P. Score-P gathers performance execution profiles, which can be presented and analyzed within the CUBE result browser, and collects detailed event traces to be processed by post-mortem analysis tools such as Scalasca and Vampir.In this paper we present the integration and combined use of Score-P and the CAPS compilers as one approach to efficiently parallelize and optimize codes. Specifically, we describe the PHMPP profiling interface, it's implementation in Score-P, and the presentation of preliminary results in CUBE. |