On the CALM Principle for BSP Computation
نویسندگان
چکیده
In recent times, considerable emphasis has been given to two apparently disjoint research topics: data-parallel and eventually consistent, distributed systems. In this paper we propose a study on an eventually consistent, dataparallel computational model, the keystone of which is provided by the recent finding that a class of programs exists that can be computed in an eventually consistent, coordination-free way: monotonic programs. This principle is called CALM and has been proven by Ameloot et al. for distributed, asynchronous settings. We advocate that CALM should be employed as a basic theoretical tool also for data-parallel systems, wherein computation usually proceeds synchronously in rounds and where communication is assumed to be reliable. We deem this problem relevant and interesting, especially for what concerns parallel workflow optimization, and make the case that CALM does not hold in general for dataparallel systems if the techniques developed by Ameloot et al. are directly used. In this paper we sketch how, using novel techniques, the satisfiability of the if direction of the CALM principle can still be obtained, although just for a subclass of monotonic queries.
منابع مشابه
The Principle of Relativity: From Ungar’s Gyrolanguage for Physics to Weaving Computation in Mathematics
This paper extends the scope of algebraic computation based on a non standard $times$ to the more basic case of a non standard $+$, where standard means associative and commutative. Two physically meaningful examples of a non standard $+$ are provided by the observation of motion in Special Relativity, from either outside (3D) or inside (2D or more), We revisit the ``gyro''-theory ...
متن کاملOn the CALM Principle for Bulk Synchronous Parallel Computation
Cloud computing refers to maximizing efficiency by sharing computational and storage resources, while data-parallel systems exploit the resources available in the cloud to perform parallel transformations over large amounts of data. In the same line, considerable emphasis has been recently given to two apparently disjoint research topics: data-parallel, and eventually consistent, distributed sy...
متن کاملتاثیر داروی زولدرونیک اسید در بیان و متیلاسیون ژن BSP در طول تمایز استئوبلاستیک سلولهای بنیادی مزانشیمی
Background and Aim: Bone sialoprotein (BSP) is a specific marker of osteoblastic differentiation. In this research, the effect of Zoledronic Acid on BSP expression and methylation status during osteoblastic differentiation of mesenchymal stem cells (MSCs) was evaluated. Materials and Methods: In this experimental study, MSCs were isolated from human bone marrow. For osteogenic differentiation,...
متن کاملThe design and analysis of bulk-synchronous parallel algorithms
The model of bulk-synchronous parallel (BSP) computation is an emerging paradigm of general-purpose parallel computing. This thesis presents a systematic approach to the design and analysis of BSP algorithms. We introduce an extension of the BSP model, called BSPRAM, which reconciles shared-memory style programming with e cient exploitation of data locality. The BSPRAM model can be optimally si...
متن کاملcient Computations on fault - prone BSP machines
In this paper general simulations of algorithms designed for fully operational BSP machines on BSP machines with faulty processors or unavailable processors are developed. The fail-stop model is considered, that is, if a processor fails or becomes unavailable it remains so until the end of the computation. The faults are random, that is, a processor may fail independently with probablility a, a...
متن کامل