Section: New Results

Combining Locking and Data Management Interfaces

Participants : Jens Gustedt, Mariem Saied, Daniel Salas.

Handling data consistency in parallel and distributed settings is a challenging task, in particular if we want to allow for an easy to handle asynchronism between tasks. Our publication [1] shows how to produce deadlock-free iterative programs that implement strong overlapping between communication, IO and computation.

An implementation (ORWL) of our ideas of combining control and data management in C has been undertaken, see Section 6.8. In previous work it has demonstrated its efficiency for a large variety of platforms.

This year, wee have been able to use the knowledge of the communication structure of ORWL programs to map tasks to cores and thereby achieve interesting performance gains on multicore architectures, see [16]. We propose a topology-aware placement module that is based on the Hardware Locality framework, HWLOC, and that takes the characteristics of the application, of the runtime and of the architecture into account. The aim is double. On one hand we increase the abstraction and the portability of the framework, and on the other hand we enhance the performance of the model’s runtime.

Within the framework of the thesis of Daniel Salas we have successfully applied ORWL to process large histopathology images. We are now able to treat such images distributed on several machines or shared in an accelerator (Xeon Phi) transparently for the user.