Parallel Composition of Scheduling Solvers

Author(s):  
Daniel Fontaine ◽  
Laurent Michel ◽  
Pascal Van Hentenryck
Keyword(s):  
1991 ◽  
Vol 14 (1) ◽  
pp. 39-73
Author(s):  
Rita Loogen ◽  
Ursula Goltz

We present a non-interleaving model for non deterministic concurrent processes that is based on labelled event structures. We define operators on labelled event structures like parallel composition, nondeterministic combination, choice, prefixing and hiding. These operators correspond to the operations of the “Theory of Communicating Sequential Processes” (TCSP). Infinite processes are defined using the metric approach. The dynamic behaviour of event structures is defined by a transition relation which describes the execution of partially ordered sets of actions, abstracting from internal events.


2012 ◽  
Vol 23 (04) ◽  
pp. 831-851 ◽  
Author(s):  
GUOQIANG LI ◽  
XIAOJUAN CAI ◽  
SHOJI YUEN

Timed automata are commonly recognized as a formal behavioral model for real-time systems. For compositional system design, parallel composition of timed automata as proposed by Larsen et al. [22] is useful. Although parallel composition provides a general method for system construction, in the low level behavior, components often behave sequentially by passing control via communication. This paper proposes a behavioral model, named controller automata, to combine timed automata by focusing on the control passing between components. In a controller automaton, to each state a timed automaton is assigned. A timed automaton at a state may be preempted by the control passing to another state by a global labeled transition. A controller automaton properly extends the expressive power because of the stack, but this can make the reachability problem undecidable. Given a strict partial order over states, we show that this problem can be avoided and a controller automaton can be faithfully translated into a timed automaton.


2021 ◽  
Author(s):  
Eric Alcaide ◽  
Stella Biderman ◽  
Amalio Telenti ◽  
Michael Cyrus Maher

The conversion of proteins between internal and cartesian coordinates is a limiting step in many pipelines, such as molecular dynamics simulations and machine learning models. This conversion is typically carried out by sequential or parallel applications of the Natural extension of Reference Frame (NeRF) algorithm. This work proposes a massively parallel NeRF implementation which, depending on the polymer length, achieves speedups between 400-1000x over the previous state-of-the-art NeRF implementation. It accomplishes this by dividing the conversion into three main phases: a parallel composition of the monomer backbone, the assembly of backbone subunits, and the parallel elongation of sidechains; and by batching computations into a minimal number of efficient matrix operations. Special emphasis is placed on reusability and ease of use within diverse pipelines. We open source the code (available at https://github.com/EleutherAI/mp_nerf) and provide a corresponding python package.


2008 ◽  
Vol 125 ◽  
pp. 012040 ◽  
Author(s):  
J R Cary ◽  
J Candy ◽  
R H Cohen ◽  
S Krasheninnikov ◽  
D C McCune ◽  
...  

Sign in / Sign up

Export Citation Format

Share Document