Browsing by Author "Michell, Stephen"
Now showing 1 - 4 of 4
Results Per Page
Sort Options
- An Execution Model for Fine-Grained Parallelism in AdaPublication . Pinho, Luís Miguel; Moore, Brad; Michell, Stephen; Taft, S. TuckerThis paper extends the authors earlier proposal for providing Ada with support for fine-grained parallelism with an execution model based on the concept of abstract executors, detailing the progress guarantees that these executors must provide and how these can be assured even in the presence of potentially blocking operations. The paper also describes how this execution model can be applied to real-time systems.
- Constraints on the Use of Executors in Real-time SystemsPublication . Michell, Stephen; Moore, Brad; Pinho, Luís Miguel; Taft, S. TuckerPrevious work proposed work to include parallelism in Ada to improve the use of multicore processors. This work proposed a model of Tasklets to carry the expressions of parallelism, and introduced the notion of executors to map the execution of Tasklets on hardware. In developing the model, a number of choices arise that effect how well the model will accommodate real-time systems. These choices become constraints which are examined and reasonable choices proposed for adoption in Ada.
- Real-Time Fine-Grained Parallelism in AdaPublication . Pinho, Luís Miguel; Moore, Brad; Michell, Stephen; Taft, S. TuckerThe approach for fine-grained parallelism in Ada presented at the last Real-Time Ada Workshop has been revised, both in terms of the language mechanisms to specify parallelism, as well as in terms of the underlying execution model. This paper summarizes the current state of the proposal, further detailing how programmers can control the behavior of the parallel execution, and discussing the issues which are still open.
- Reduction of Parallel Computation in the Parallel Model for AdaPublication . Taft, S. Tucker; Moore, Brad; Pinho, Luís Miguel; Michell, StephenOne of the most common program constructs to be parallelized (and where most of the times gains are obtained) is parallel loops. This paper discusses different approaches to support loop parallelization in the fine-grained parallelism model for Ada currently being proposed, focusing in particular in the issues related to reducing operations.