A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2010; you can also visit the original URL.
The file type is application/pdf
.
Filters
Data conversion for process/thread migration and checkpointing
2003
2003 International Conference on Parallel Processing, 2003. Proceedings.
Process/thread migration and checkpointing schemes support load balancing, load sharing and fault tolerance to improve application performance and system resource usage on workstation clusters. ...
This speeds up the data conversion process and eases the programming task dramatically, especially for the large data trunks common to migration and checkpointing. ...
To hide the different levels of heterogeneity, we have developed an application level process/thread migration and checkpointing package, MigThread, which abstracts the computation state up to the language ...
doi:10.1109/icpp.2003.1240612
dblp:conf/icpp/JiangCW03
fatcat:dksswg6hafh7hmvopx3fek4bw4
Process/thread migration and checkpointing in heterogeneous distributed systems
2004
37th Annual Hawaii International Conference on System Sciences, 2004. Proceedings of the
Process/thread migration and checkpointing are indispensable for resource sharing, cycle stealing, and other modes of interaction. ...
For heterogeneity, a novel data conversion scheme is proposed to analyze data types automatically and convert data only on the receiver side. ...
With this feature, virtually all programs will be qualified for migration/checkpointing. Figure 1 . 1 Process/thread and migration/checkpoing options in MigThread. ...
doi:10.1109/hicss.2004.1265665
dblp:conf/hicss/JiangC04
fatcat:bjewn2tqp5bkbcpnp3tiwn3die
Dynamic Transparent General Purpose Process Migration for Linux
2012
International Journal of Grid Computing & Applications
In this paper, we proposed a process migration framework for Linux OS. It is a multilayer architecture to confine every functionality independent section of the system in separate layer. ...
This architecture is capable of supporting diverse applications due to generic user space interface and dynamic structure that can be modified according to demands. ...
Not every combination of the execution context and quiescing method is valid for process migration because of the checkpoint/restart subsystem weakness in mapping process threads on the source machine ...
doi:10.5121/ijgca.2012.3402
fatcat:b32vbgudbzfp5f7ys3hxkghndu
Automating Live Update for Generic Server Programs
2017
IEEE Transactions on Software Engineering
This paper presents Mutable Checkpoint-Restart (MCR), a new live update solution for generic (multiprocess and multithreaded) server programs written in C. ...
code paths to automatically restore the old program threads and reinitialize a relevant portion of the program data structures. ...
When all the per-process threads complete, MCR transitions to the second phase of the protocol and waits for all the controller threads to report quiescence. ...
doi:10.1109/tse.2016.2584066
fatcat:2po4wff2q5aadiausxoa46ssrm
Fault Tolerance Techniques for High-Performance Computing
[chapter]
2015
Computer Communications and Networks
We cover the Young/Daly formula for the optimal period and much more! Next we explain how the efficiency of checkpointing can be improved via fault prediction or replication. ...
The emphasis is on checkpointing, the de-facto standard technique for resilience in High Performance Computing. ...
and Technology Agency (JST). ...
doi:10.1007/978-3-319-20943-2_1
fatcat:2rehvmh6bvdsvbru6ukpcij6ae
Message Passing Interface (MPI)
[chapter]
2005
Advanced Computer Architecture and Parallel Processing
software packages, presenting a steep learning curve for new developers and third parties. ...
The result is an MPI implementation that is highly modular, has published abstraction and interface boundaries, and is significantly easier to develop, maintain, and use as a vehicle for research. ...
However, this is the PID of the process (thread) that invoked MPI INIT (and therefore kinit()), and the PID that will be returned by lam getpid(). ...
doi:10.1002/0471478385.ch9
fatcat:dze6oxxnirftpnqrdqzuczbzcu
Hardware Acceleration for Container Migration on Resource-Constrained Platforms
2020
IEEE Access
b: Process/Thread Context Switching The concurrent processing of multiple applications results in CPU context switching between processes and threads. ...
Conversely, for uploading a container image, the clients needs to compress and encrypt the container image. ...
doi:10.1109/access.2020.3024675
fatcat:vp3mio7z3rg43afi7lvd73t67q
Towards Interactive, Adaptive and Result-aware Big Data Analytics
[article]
2022
arXiv
pre-print
There have been demands for making the analytics process more interactive and adaptive, especially for long running jobs. ...
This dissertation is motivated by these calls for improvement in data processing and the experiences over the past few years while working on the Texera project, which is a collaborative data analytics ...
For actor model implementations that do not support priority such as Orleans, Amber solves the problem by letting each actor delegate its data processing to an external thread, called data-processing thread ...
arXiv:2212.07096v1
fatcat:tfejbwgnszepxhtfkcesmmftxe
Grasshopper: An Orthogonally Persistent Operating System
1994
Computing Systems
Acknowledgments V/e would like to thank Karen Wyrwas, Alex Farkas, Stephen Norris, Fred Brown and David Hulse for comments on earlier versions of this paper. ...
We also thank the anonymous referees for their many helpful comments on the paper. ...
Containers provide the only abstraction over storage, loci are the agents of change (processes/threads), and capabilities are the means of access and protection in the system. ...
dblp:journals/csys/DearleBFHLRV94
fatcat:awiyt5p4jvdsncddksvrgasx34
Relative debugging for a highly parallel hybrid computer system
2015
Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis on - SC '15
Relative debugging is particularly effective when code is migrated from one platform to another, and this is of significant interest for hybrid computer architectures containing CPUs accelerators or coprocessors ...
We describe a generic data model that allows programmers to examine the global state across different types of applications, including MPI/OpenMP, MPI/OpenACC, and UPC programs. ...
Our previous work used a bitset to represent the process/thread set. ...
doi:10.1145/2807591.2807605
dblp:conf/sc/RoseGVMADJ15
fatcat:pjq7qzkylzewzlphqoermywo64
Machine-Learning Based Memory Prediction Model for Data Parallel Workloads in Apache Spark
2021
Symmetry
Then, we propose a machine-learning-based prediction model that determines the efficient memory for a given workload and data. ...
In this paper, given the type of workload and volume of the input data, we analyze the memory usage pattern and derive the efficient memory size of data-parallel workloads in Apache Spark. ...
of the task processing thread (in Java, a memory management thread is called a garbage collector) [33] . ...
doi:10.3390/sym13040697
fatcat:wg75rx55jjhyzef3pnqhxqlyfa
2017 ASCB Annual Meeting Abstracts
2017
Molecular Biology of the Cell
in disease and identifying new targets for drug development. ...
This work provided the basis for uncovering a novel endosomal sorting mechanism for PAR1 and connections between receptor sorting and signaling that play important roles in inflammation and cancer. ...
Our data confirm that actin introduces barriers leading to compartmentalization of the plasma membrane and that membrane proteins are transiently confined within actin fences. ...
doi:10.1091/mbc.e17-10-0618
pmid:29237772
pmcid:PMC5739290
fatcat:3msjrn3omzcybfanlagykayauy
Elastic Stream Processing with Latency Guarantees
2015
2015 IEEE 35th International Conference on Distributed Computing Systems
Many Big Data applications in science and industry have arisen, that require large amounts of streamed or event data to be analyzed with low latency. ...
We introduce a model for estimating the latency of a data flow, when the degrees of parallelism of the tasks within are changed. ...
ChronoStream is highlighted by its support for vertical scaling (adjusts worker process threading level) and its lightweight UDF state reconstruction scheme, that exploits state replica locality and does ...
doi:10.1109/icdcs.2015.48
dblp:conf/icdcs/LohrmannJK15
fatcat:graw4wr3xne45ge2kj7i2wpbkq
The International Exascale Software Project roadmap
2011
The international journal of high performance computing applications
for selecting valuable software research and encouraging its translation into usable, production-quality software for application developers. ...
Over the last twenty years, the open source community has provided more and more software on which the world's High Performance Computing (HPC) systems depend for performance and productivity. ...
Clearly all science areas and engineering areas that contain potential CDVs need something in all the software areas, but for the purposes of this exercise we tried to sort out areas of emphasis for each ...
doi:10.1177/1094342010391989
fatcat:twdszcjfxraijpsdcdacvpp6vm
clusterNOR: A NUMA-Optimized Clustering Framework
[article]
2021
arXiv
pre-print
Clustering algorithms are iterative and have complex data access patterns that result in many small random memory accesses. ...
, enabling computation for varying memory and hardware budgets. ...
We thank Nikita Ivkin for discussions that assisted immensely in realizing this work. ...
arXiv:1902.09527v6
fatcat:c2t5a2gkeze53faxvxyyf2esz4
« Previous
Showing results 1 — 15 out of 57 results