Staccato: shared-memory work-stealing task scheduler with cache-aware memory management

2019 ◽  
Vol 15 (4) ◽  
pp. 394 ◽  
Author(s):  
Ruslan Kuchumov ◽  
Andrey Sokolov ◽  
Vladimir Korkhov
Keyword(s):  
Shared Memory ◽  
Memory Management ◽  
Work Stealing ◽  
Memory Work

Memory management for parallel tasks in shared memory

2005 ◽  
pp. 165-178
Author(s):  
K. G. Langendoen ◽  
H. L. Muller ◽  
W. G. Vree
Keyword(s):  
Shared Memory ◽  
Memory Management ◽  
Parallel Tasks

PARALLEL BUDDY MEMORY MANAGEMENT

1992 ◽  
Vol 02 (04) ◽  
pp. 391-398 ◽  
Author(s):  
THEODORE JOHNSON ◽  
TIMOTHY A. DAVIS
Keyword(s):  
Shared Memory ◽  
Memory Management ◽  
Sparse Matrix ◽  
Parallel Programs ◽  
Memory Allocation ◽  
Multiprocessor Systems ◽  
Matrix Algorithm ◽  
Buddy System ◽  
Shared Memory Multiprocessor ◽  
Dynamic Storage

Shared memory multiprocessor systems need efficient dynamic storage allocators, both for system purposes and to support parallel programs. Memory managers are often based on the buddy system, which provides fast allocation and release. Previous parallel buddy memory managers made no attempt to coordinate the allocation, splitting and release of blocks, and as a result needlessly fragment memory. We present a fast and simple parallel buddy memory manager that is also as space efficient as a serial buddy memory manager. We test our algorithms using memory allocation/deallocation traces collected from a parallel sparse matrix algorithm.

scholarly journals L2 cache performance analysis for MPSoC by tag – comparision

2017 ◽  
Vol 7 (1.5) ◽  
pp. 285
Author(s):  
Jenitha A ◽  
Elumalai R
Keyword(s):  
Performance Analysis ◽  
Shared Memory ◽  
Memory Management ◽  
Memory Systems ◽  
Critical Problem ◽  
Energy Current ◽  
L2 Cache ◽  
Application Processor ◽  
Cache Miss ◽  
Embedded Applications

Memory systems in many applications are becoming increasingly large, contributing to many challenges in the memory management that has led to many method to manage memory. The tag comparison consumes large amount of cache energy. Current methods provide tag comparison cache or failure of the expected cache. Here is proposed an idea based on new call Comparing Tag stages, filter bloom is presented to improve the efficiency of the cache to predict failure and partial tag comparison for the cold line of verification and full comparison check for direct labels. Moreover, the administration of the cache that is filled with cache lines occurs when there is a cache miss. Today's embedded applications use MPSoC. The  MPSoC consists of the following ie more than one  processors, shared memory among the processors available and a global  off-chip memory. Planning of the activities of an integrated application processor and memory partition between processors are two main critical problem. Here, for an integrated application, both task scheduling and partitioning the integrated available L2 cache to reduce the runtime approach is used.

Современные интервальные подходы к вычислению решений непрерывных игр 

2018 ◽  
Author(s):  
B.J. Kubica
Keyword(s):  
Shared Memory ◽  
Branch And Bound ◽  
Memory Management ◽  
Nash Equilibria ◽  
Automatic Differentiation ◽  
Difficult Problem ◽  
Interval Methods ◽  
Interval Matrices ◽  
Management Techniques ◽  
Interval Branch And Bound

Computing Nash equilibria in continuous games is a difficult problem, but interval methods have already been applied to its solution quite successfully. The purpose of this paper is to briefly survey previous efforts and achievements of the author related to the topic, and to consider some advanced tools for accelerating the interval branch-and-bound-type methods. In particular, we discuss computing eigenvalues of interval matrices, use of algorithmic (automatic) differentiation, memory management techniques as well as advanced parallelization in both shared-memory and distributedmemory environments. Дан краткий анализ результатов исследований по применению интервальных методов для вычисления равновесия по Нэшу в непрерывных играх. Рассмотрены некоторые современные подходы к ускорению интервальных методов типа ветвей и границ. В частности, обсуждаются такие вопросы, как вычисление собственных значений интервальных матриц, использование алгоритмического(автоматического) дифференцирования, методы управления памятью, инструменты распараллеливания в средах с разделяемой и распределенной памятью.

scholarly journals Nunca Más, Nie Wieder: ethical aspects of remembering in the narratives of Ravensbrück. Survivors, their descendants and other persons engaged in memory work = Nunca mas, nie wieder: aspectos éticos del recuerdo en la narrativa de los supervivientes de Rravensbrück, sus descendientes y otras personas involucradas en el trabajo de la memoria

2019 ◽  
pp. 175
Author(s):  
Sarka Kadlecova
Keyword(s):  
Collective Memory ◽  
Shared Memory ◽  
Social Theory ◽  
Concentration Camp ◽  
Collective Trauma ◽  
Ethical Aspects ◽  
Shared Trauma ◽  
Ethnographic Fieldwork ◽  
Memory Work ◽  
Political Work

Resumen: Este artículo trata de la memoria colectiva de un campo de concentración nazi para mujeres. El objetivo de este texto es examinar la posibilidad de la construcción de la memoria compartida por las supervivientes del campo de concentración Ravensbrück, sus descendientes y otras personas, principalmente mujeres, dedicadas al trabajo de memoria en torno a este dominio particular. A partir de la teoría social del trauma de Jeffrey Alexander, se presentarán unos ejemplos del intenso trabajo cultural y político necesario para crear un trauma compartido. Con base en el análisis de los datos creados durante la investigación etnográfica multisitio, el artículo explorará los aspectos éticos del proceso de recordar y la fabricación de un trauma colectivo.Palabras clave: Ravensbrück, teoría social del trauma de Jeffrey Alexander.Abstract: This article deals with collective memory of a women’s concentration camp in Nazi Germany. The objective of this text is to examine the possibility of the construction of a shared memory by survivors of the concentration camp Ravensbrück, their descendants and other persons, mainly women, engaged in the memory work around this particular site of memory. Drawing on Jeffrey Alexander’s social theory of trauma, a number of examples of the intensive cultural and political work necessary for creating a shared trauma will be presented. Based on the data created during multi-sited ethnographic fieldwork, the article will explore ethical aspects of the process of remembering and the fabrication of collective trauma.  Keywords: Ravensbrück, Jeffrey Alexander’s social theory of trauma.

scholarly journals The Optimal Control of Two Work-Stealing Deques, Moving One After Another in a Shared Memory

2019 ◽  
Vol 10 (1) ◽  
pp. 19-32
Author(s):  
Eugene Aleksandrovich Barkovsky ◽  
Anna Aleksandrovna Lazutina ◽  
Andrew Vladimirovich Sokolov
Keyword(s):  
Shared Memory ◽  
Simulation Models ◽  
Work Stealing ◽  
New Approach ◽  
Integer Points ◽  
Network Applications ◽  
Cyclic Representation ◽  
The Monte Carlo Method ◽  
The One ◽  
The Mathematical Model

In the parallel work-stealing load balancers, each core owns personal buffer of tasks called deque. One end of the deque is used by its owner to add and retrieve tasks, while the second end is used by other cores to steal tasks. In the paper two representation methods of deques are analyzed: partitioned serial cyclic representation of deques (one of the conventional techniques); and the new approach proposed by our team, without partition of shared memory in advance between deques moving one after another in a circle. Previously we analyzed these methods for representing FIFO queues in network applications, where the “One after another” way gave the best result for some values of the system parameters. Purpose of this research is to construct and analyze models of the process of work with two circular deques located in shared memory, where they movie one after another in a circle. The mathematical model is constructed in the form of a random walk by integer points in the pyramid. The simulation model is constructed using the Monte Carlo method. The used work-stealing strategy is stealing of one element. We propose the mathematical and simulation models of this process and carry out numerical experiments.

Sign in / Sign up

Export Citation Format

Share Document