Global ETD Search
Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.
Results
Showing 1 to 20 of 36 for “"Distributed memory systems"”.
-
Tunable shared-memory abstractions for distributed-memory systems
Distributed memory multiprocessor architectures offer enormous computational power, by exploiting the concurrent execution of many loosely connected processors. Yet, such scalability is not without price. Interface delays and low interconnection bandwidth to the distributed memories make internode …
-
Extending the HybridThread SMP Model for Distributed Memory Systems
Memory Hierarchy is of growing importance in system design today. As Moore's Law allows system designers to include more processors within their designs, data locality becomes a priority. Traditional multiprocessor systems on chip (MPSoC) experience difficulty scaling as the quantity of processors …
-
Code generation of array constructs for distributed memory systems
Programming for high-performance systems to fully utilize the potential of the computing system is a complex problem. This is particularly evident when programming distributed memory clusters containing multiple NUMA chips and GPUs on each node since it would require a complex combination of MPI, …
-
Parallel and scalable combinatorial string algorithms on distributed memory systems
… performance. In this work, we present our distributed-memory parallel algorithms for indexing large datasets, including algorithms for the distributed construction of suffix arrays, LCP arrays, and suffix trees. We formulate a generalized version of the All-Nearest-Smaller-Values problem, …
-
Logical rings in the mutual exclusion problem of distributed memory systems
In this thesis, we investigate distributed mutual exclusion algorithms and delineate the features of a new distributed mutual exclusion algorithm. The basis of the algorithm is the logical ring structure employed in token-based mutual exclusion algorithms. Specifically, there exists dynamic …
-
Image pyramid segmentation using parallel machines
… linking (FPL) image segmentation for shared memory systems and parallel FPL image segmentation for distributed memory systems. The algorithms are designed for the purpose of increasing the speed of FPL which is a specific approach to pyramid image segmentation. Both algorithms divide the …
-
Garbage Collection for General Graphs
… modern programming language. With multi-core and distributed systems, most programs written recently are heavily multi-threaded and distributed. Distributed and multi-threaded programs are called concurrent programs. Manual memory management is cumbersome and difficult in concurrent programs. …
-
Measurement-Based Performance Models of Numerical Problems on Loosely-Coupled Systems
Multiprocessor systems offer the potential of significant performance improvements over uniprocessors. Performance evaluation is necessary to effectively utilize these systems and to uncover and remove performance bottlenecks, which prevent the realization of their performance potential. …
-
On Hardware-Agnostic Programming for Parallel Architectures
Writing programs for parallel systems is difficult and time consuming. Typically, a separate program has to be written for each platform, and the different processors and memories have to be coordinated manually. These challenges make it important to build programming languages that can abstract …
-
Dynamic Load Balancing for a hp-adaptive Discontinuous Galerkin Wave Equation Solver via Spacing-Filling Curve and Advanced Data Structure
… and storing. It can be built independently on distributed memory systems. It provides high control of the mesh resolution and efficient data management operations. Results using this approach on the adaptive wave equation solver confirm that its memory usage remains low on up to 16,384 …
-
Extending the Polyhedral Compilation Model for Debugging and Optimization of SPMD-style Explicitly-Parallel Programs
… today, as exemplified by OpenMP for multi-core systems, CUDA and OpenCL for accelerator systems, and MPI for distributed-memory systems. The basic idea behind the SPMD model, which differentiates it from task-parallel models, is that all logical processors (worker threads) execute the same …
-
Hybrid-PGAS Memory Hierarchy for Next Generation HPC Systems
… next generation high performance computing (HPC) systems present a new host of challenges. There is a growing disparity between computational performance vs. network and storage device throughput and among the energy costs of computational, memory, and communication operations. Chapel is a …
-
Υποστήριξη χρόνου εκτέλεσης για μοντέλα προγραμματισμού κοινής μνήμης και περάσματος μηνυμάτων σε συστάδες πολυεπεξεργαστικών συστημάτων
… combines architectural elements of both shared memory and distributed memorycomputers Their major programming models are message passing the hybrid model (thecombination of message passing between nodes and the use of a shared memory model inside thenodes) and finally the shared memory …
-
Stochastic models for performance analyses of iterative algorithms in distributed environments
… the performance of iterative algorithms in distributed environments. The parallelization of certain iterative algorithms is indeed a crucial issue for the efficient solution of large or complex optimization problems. Diverse implementation techniques for such parallelizations have become …
-
Point-to-Point and Barrier Synchronization in Distributed SPMD Systems
Distributed memory programming models are very often the only way to scale up large scientific applications. To ensure correctness and optimal performance in distributed applications, it is necessary to use general, high-level, but efficient synchronization constructs. Implementing distributed …
-
Scheduling real-time periodic tasks in multiprocessor systems
… an important issue in the design of real-time systems. In this thesis, we have addressed the scheduling of both hard and soft real-time periodic tasks on multiple processor systems. We differentiate between hard and soft real-time jobs by using a quality of service (QoS) factor. The proposed …
-
Compiler Optimizations for Irregular Memory Access Patterns in the PGAS Programming Model
… graphs and matrices exhibit fine-grain irregular memory accesses patterns, leading to both performance and productivity challenges on today's distributed-memory systems. The Partitioned Global Address Space (PGAS) model attempts to address these challenges by combining the memory of physically …
-
Development of an AMR Octree DSMC approach for shock dominated flows
… complex triangulated geometries. With the use of distributed memory systems and Message-Passing-Interface (MPI) for communication, the code is potentially scalable. However, to simulate continuum-like conditions involving multi-scale physics, better scalability that has yet been achieved is …
-
Communication-efficient Second-order Optimization Methods on Modern Parallel Systems
… defined as the data movement among levels of a memory hierarchy or between processors. On modern computer architectures, the communication costis often orders of magnitude larger than the computation cost and this gap is rapidly increasing. This suggests that for the best performance the …
Page 1 of 2