基本信息
views: 11
![](https://originalfileserver.aminer.cn/sys/aminer/icon/show-trajectory.png)
Bio
Research Topics
Fault Tolerant HPC Systems
ULFM - User Level Failure Mitigation is a set of MPI interface extensions enabling Message Passing programs to restore MPI communication capabilies affected by process failures. It supports rebuilding communicators, RMA windows and I/O Files. No particular recovery model is imposed or favored, instead a set of versatile APIs is included that provides support for differente recovery styles. The application directs the recovery, so it can pay for the cost of repairing only the necessary MPI objects. The ULFM specification is a crucial infrastructure to enable the deployment of advanced, production quality fault toleant techniques; it is a versatile solution to improve the efficiency of novel and established fault tolerant techniques. Look at the flyer.
MPICH-V is a research effort with theoretical studies, experimental evaluations and pragmatic implementations aiming to provide a MPI implementation based on MPICH, featuring multiple fault tolerant protocols. MPICH-V provides automatic fault tolerant MPI library (i.e. a totaly unchanged application linked with the mpich-v library is a fault tolerant application).
Dataflow Execution Model for HPC
PaRSEC - Parallel Runtime Scheduling and Execution Controller - is a generic framework for architecture aware scheduling and management of micro-tasks on distributed many-core heterogeneous architectures. Applications we consider can be expressed as a Direct Acyclic Graph of tasks with labeled edges designating data dependencies. DAGs are represented in a compact problem-size independent format that can be queried on-demand to discover data dependencies in a totally distributed fashion. PaRSEC assigns computation threads to the cores, overlaps communications and computations and uses a dynamic, fully-distributed scheduler based on architectural features such as NUMA nodes and algorithmic features such as data reuse. The framework includes libraries, a runtime system, and development tools to help application developers tackle the difficult task of porting their applications to highly heterogeneous and diverse environment. PaRSEC is the underlying infrastructure for the DPLASMA distributed memory, tile algorithm based linear algebra package.
Fault Tolerant HPC Systems
ULFM - User Level Failure Mitigation is a set of MPI interface extensions enabling Message Passing programs to restore MPI communication capabilies affected by process failures. It supports rebuilding communicators, RMA windows and I/O Files. No particular recovery model is imposed or favored, instead a set of versatile APIs is included that provides support for differente recovery styles. The application directs the recovery, so it can pay for the cost of repairing only the necessary MPI objects. The ULFM specification is a crucial infrastructure to enable the deployment of advanced, production quality fault toleant techniques; it is a versatile solution to improve the efficiency of novel and established fault tolerant techniques. Look at the flyer.
MPICH-V is a research effort with theoretical studies, experimental evaluations and pragmatic implementations aiming to provide a MPI implementation based on MPICH, featuring multiple fault tolerant protocols. MPICH-V provides automatic fault tolerant MPI library (i.e. a totaly unchanged application linked with the mpich-v library is a fault tolerant application).
Dataflow Execution Model for HPC
PaRSEC - Parallel Runtime Scheduling and Execution Controller - is a generic framework for architecture aware scheduling and management of micro-tasks on distributed many-core heterogeneous architectures. Applications we consider can be expressed as a Direct Acyclic Graph of tasks with labeled edges designating data dependencies. DAGs are represented in a compact problem-size independent format that can be queried on-demand to discover data dependencies in a totally distributed fashion. PaRSEC assigns computation threads to the cores, overlaps communications and computations and uses a dynamic, fully-distributed scheduler based on architectural features such as NUMA nodes and algorithmic features such as data reuse. The framework includes libraries, a runtime system, and development tools to help application developers tackle the difficult task of porting their applications to highly heterogeneous and diverse environment. PaRSEC is the underlying infrastructure for the DPLASMA distributed memory, tile algorithm based linear algebra package.
Research Interests
Papers共 96 篇Author StatisticsCo-AuthorSimilar Experts
By YearBy Citation主题筛选期刊级别筛选合作者筛选合作机构筛选
时间
引用量
主题
期刊级别
合作者
合作机构
International Workshop on Asynchronous Many-Task Systems and Applicationspp.22-33, (2024)
SC-W '23: Proceedings of the SC '23 Workshops of The International Conference on High Performance Computing, Network, Storage, and Analysispp.44-50, (2023)
Int. J. Netw. Comput.no. 1 (2022): 26-46
HAL (Le Centre pour la Communication Scientifique Directe) (2022)
Cited0Views0Bibtex
0
0
2022 IEEE/ACM 12th Workshop on Fault Tolerance for HPC at eXtreme Scale (FTXS)pp.36-46, (2022)
Future Generation Computer Systems (2020): 467-481
Load More
Author Statistics
Co-Author
Co-Institution
D-Core
- 合作者
- 学生
- 导师
Data Disclaimer
The page data are from open Internet sources, cooperative publishers and automatic analysis results through AI technology. We do not make any commitments and guarantees for the validity, accuracy, correctness, reliability, completeness and timeliness of the page data. If you have any questions, please contact us by email: report@aminer.cn