Data-flow Concurrency on Distributed Multi-core Systems

The Dynamic Data-Flow model of execution has many inherit properties, such as tolerance to latencies and distributed concurrency, which make it suitable for distributed execution. Data-Driven Multithreading (DDM) is a hybrid Data-flow/Control-flow model that implements the Data-Flow principles at the Thread level on sequential processors. In this paper we demonstrated that the DataDriven Multithreading Virtual Machine (DDM-VM), can achieve high performance in Distributed Nodes (multi-core systems). A shared Global Address Space is supported across all the Nodes in the system to facilitate data movement. We have evaluated our work on both Homogeneous and Heterogeneous systems. The performance evaluation shows that the distributed execution achieves 80-84% of the maximum possible speedup using off-the-shelf networking.

[1]  H. Peter Hofstee,et al.  Introduction to the Cell multiprocessor , 2005, IBM J. Res. Dev..

[2]  Arvind,et al.  The U-Interpreter , 1982, Computer.

[3]  Rosa M. Badia,et al.  CellSs: a Programming Model for the Cell BE Architecture , 2006, ACM/IEEE SC 2006 Conference (SC'06).

[4]  Pen-Chung Yew,et al.  Data Prefetching and Data Forwarding in Shared Memory Multiprocessors , 1994, 1994 Internatonal Conference on Parallel Processing Vol. 2.

[5]  Veljko M. Milutinovic,et al.  Distributed shared memory: concepts and systems , 1997, IEEE Parallel Distributed Technol. Syst. Appl..

[6]  Alejandro Duran,et al.  Productive Cluster Programming with OmpSs , 2011, Euro-Par.

[7]  Jack Dongarra,et al.  A Proposal for a User-Level, Message-Passing Interface in a Distributed Memory Environment , 1993 .

[8]  Paraskevas Evripidou,et al.  Data-Driven Multithreading Using Conventional Microprocessors , 2006, IEEE Transactions on Parallel and Distributed Systems.

[9]  Paraskevas Evripidou,et al.  DDM-VMc: the data-driven multithreading virtual machine for the cell processor , 2011, HiPEAC.

[10]  Paraskevas Evripidou,et al.  CacheFlow: A Short-Term Optimal Cache Management Policy for Data Driven Multithreading , 2004, Euro-Par.

[11]  Josep Torrellas,et al.  Data Forwarding in Scalable Shared-Memory Multiprocessors , 1996, IEEE Trans. Parallel Distributed Syst..

[12]  Eduard Ayguadé,et al.  Hierarchical Task-Based Programming With StarSs , 2009, Int. J. High Perform. Comput. Appl..

[13]  Paraskevas Evripidou.  Thread Synchronization Unit (TSU): A Building Block for High Performance Computers , 1997, ISHPC.

[14]  Bradford L. Chamberlain,et al.  Parallel Programmability and the Chapel Language , 2007, Int. J. High Perform. Comput. Appl..

[15]  Vivek Sarkar,et al.  X10: an object-oriented approach to non-uniform cluster computing , 2005, OOPSLA '05.

[16]  Paraskevas Evripidou,et al.  Programming multi-core architectures using Data-Flow techniques , 2010, 2010 International Conference on Embedded Computer Systems: Architectures, Modeling and Simulation.

[17]  Katherine Yelick,et al.  Introduction to UPC and Language Specification , 2000 .

[18]  Jesús Labarta,et al.  CellSs: Making it easier to program the Cell Broadband Engine processor , 2007, IBM J. Res. Dev..

[19]  Paraskevas Evripidou,et al.  TFlux: A Portable Platform for Data-Driven Multithreading on Commodity Multicore Systems , 2008, 2008 37th International Conference on Parallel Processing.