论文信息 - Virtual Parallelism allows Relaxing the Synchronization Constraints of SIMD Computing Paradigm

Virtual Parallelism allows Relaxing the Synchronization Constraints of SIMD Computing Paradigm

In this paper we propose to introduce execution autonomy in the SIMD paradigm to overcome its rigidity while preserving the advantages of its synchronous programming model and we show that Virtual Parallelism support is a necessary condition to the profitable application of execution autonomy. We define execution autonomy as the capability of each processing element of a massively parallel computer to execute the instructions in a block of code of a single common program autonomously and asynchronously. We define virtual parallelism as the capability to emulate a n processors array on a m processor array with n/m performance degradation. In past related works the relaxation of SIMD synchronization has been already proposed, nevertheless its relation with Virtual Parallelism has never been studied.

Massimo Maresca | Pierpaolo Baglietto | Mauro Migliardi

[1] Richard M. Brown,et al. The ILLIAC IV Computer , 1968, IEEE Transactions on Computers.

[2] W. Daniel Hillis,et al. Data parallel algorithms , 1986, CACM.

[3] Howard Jay Siegel,et al. Data Management and Control-Flow Aspects of an SIMD/SPMD Parallel Language/Compiler , 1993, IEEE Trans. Parallel Distributed Syst..

[4] Dionysios I. Reisis,et al. Parallel Computations on Reconfigurable Meshes , 1993, IEEE Trans. Computers.

[5] W. Daniel Hillis,et al. The CM-5 Connection Machine: a scalable supercomputer , 1993, CACM.

[6] M. Maresca,et al. Parallel architectures for vision , 1988 .

[7] Massimo Maresca,et al. Polymorphic Processor Arrays , 1993, IEEE Trans. Parallel Distributed Syst..

[8] Massimo Maresca,et al. Introducing Execution Autonomy in the SIMD Computing Paradigm , 1994, EUROSIM.

[9] Mitsuhisa Sato,et al. Thread-based programming for the EM-4 hybrid dataflow machine , 1992, ISCA '92.

[10] HillisW. Daniel,et al. The CM-5 Connection Machine , 1993 .

[11] Charles C. Weems. Asynchronous SIMD: an architectural concept for high performance image processing , 1997, Proceedings Fourth IEEE International Workshop on Computer Architecture for Machine Perception. CAMP'97.

[12] Steve Rehfuss,et al. Comparing SFMD and SPMD Computation for On-Chip Multiprocessing of Intermediate Level Image Understanding Algorithms , 1997 .