Second International Workshop on High-performance Infrastructure for Scalable Tools, Venice, Italy
25 June 2012 - 25 June 2012
Italy
The Second International Workshop on High-performance Infrastructure for Scalable Tools will take place from 25 to 29 June 2012 in Venice, Italy.
From laptops to supercomputers, increasingly complex multicore and accelerator hardware is driving rapid growth in concurrency. At the high end, exascale systems are expected to support over 100 million threads, primarily due to increased intra-node concurrency. To take full advantage of this increased concurrency, new software and programming models are necessary. With increased system and application complexity, scalable tools are critical for diagnosing the root causes of performance and correctness problems.
To diagnose and correct problems in highly concurrent systems, tools themselves are becoming more complex. These require sophisticated infrastructure to measure, analyse, diagnose and present the causes of an execution's anomalies. To manage this complexity, there is a need for abstractions that simplify tool design and for infrastructure that is reusable and extensible.
Topics set to be covered during the event will include:
- generic, reusable tool-infrastructure components;
- tool-component interoperability;
- tool-runtime design;
- scalable online and offline attribution, data management, and analysis techniques;
- monitoring, attribution, and analysis approaches for novel parallel programming models;
- scalable presentation of results.For further information, please visit: http://wwwx.cs.unc.edu/~tgamblin/whist-2012(opens in new window)
From laptops to supercomputers, increasingly complex multicore and accelerator hardware is driving rapid growth in concurrency. At the high end, exascale systems are expected to support over 100 million threads, primarily due to increased intra-node concurrency. To take full advantage of this increased concurrency, new software and programming models are necessary. With increased system and application complexity, scalable tools are critical for diagnosing the root causes of performance and correctness problems.
To diagnose and correct problems in highly concurrent systems, tools themselves are becoming more complex. These require sophisticated infrastructure to measure, analyse, diagnose and present the causes of an execution's anomalies. To manage this complexity, there is a need for abstractions that simplify tool design and for infrastructure that is reusable and extensible.
Topics set to be covered during the event will include:
- generic, reusable tool-infrastructure components;
- tool-component interoperability;
- tool-runtime design;
- scalable online and offline attribution, data management, and analysis techniques;
- monitoring, attribution, and analysis approaches for novel parallel programming models;
- scalable presentation of results.For further information, please visit: http://wwwx.cs.unc.edu/~tgamblin/whist-2012(opens in new window)