Active messages: a mechanism for integrated communication and computation
ISCA '92 Proceedings of the 19th annual international symposium on Computer architecture
The network architecture of the Connection Machine CM-5 (extended abstract)
SPAA '92 Proceedings of the fourth annual ACM symposium on Parallel algorithms and architectures
Generating communication for array statements: design, implementation, and evaluation
Journal of Parallel and Distributed Computing - Special issue on data parallel algorithms and programming
An architecture for optimal all-to-all personalized communication
SPAA '94 Proceedings of the sixth annual ACM symposium on Parallel algorithms and architectures
AP1000+: architectural support of PUT/GET interface for parallelizing compiler
ASPLOS VI Proceedings of the sixth international conference on Architectural support for programming languages and operating systems
Task Parallelism in a High Performance Fortran Framework
IEEE Parallel & Distributed Technology: Systems & Technology
Measurement of Communication Rates on the Cray T3D Interprocessor Network
HPCN Europe 1994 Proceedings of the nternational Conference and Exhibition on High-Performance Computing and Networking Volume II: Networking and Tools
Decoupling synchronization and data transfer in message passing systems of parallel computers
ICS '95 Proceedings of the 9th international conference on Supercomputing
Fast message assembly using compact address relations
Proceedings of the 1996 ACM SIGMETRICS international conference on Measurement and modeling of computer systems
From AAPC algorithms to high performance permutation routing and sorting
Proceedings of the eighth annual ACM symposium on Parallel algorithms and architectures
Euro-Par '00 Proceedings from the 6th International Euro-Par Conference on Parallel Processing
Predicting and Evaluating Distributed Communication Performance
Proceedings of the 2004 ACM/IEEE conference on Supercomputing
OS support for a commodity database on PC clusters: distributed devices vs. distributed file systems
ADC '05 Proceedings of the 16th Australasian database conference - Volume 39
Dodging the cost of unavoidable memory copies in message logging protocols
EuroMPI'10 Proceedings of the 17th European MPI users' group meeting conference on Recent advances in the message passing interface
SymCall: symbiotic virtualization through VMM-to-guest upcalls
Proceedings of the 7th ACM SIGPLAN/SIGOPS international conference on Virtual execution environments
Implementation and performance optimization of a parallel contour line generation algorithm
Computers & Geosciences
| Hi-index | 0.00 |
Communication in a parallel system frequently involves moving data from the memory of one node to the memory of another; this is the standard communication model employed in message passing systems. Depending on the application, we observe a variety of patterns as part of communication steps, e.g., regular (i.e. blocks of data), strided, or irregular (indexed) memory accesses. The effective speed of these communication steps is determined by the network bandwidth and the memory bandwidth, and measurements on current parallel supercomputers indicate that the performance is limited by the memory bandwidth rather than the network bandwidth.Current systems provide a wealth of options to perform communication, and a compiler or user is faced with the difficulty of finding the communication operations that best use the available memory and network bandwidth. This paper provides a framework to evaluate different solutions for inter-node communication and presents the copy-transfer model; this model captures the contributions of the memory system to inter-node communication. We demonstrate the usefulness of this simple model by applying it to two commercial parallel systems, the Cray T3D and the Intel Paragon.In particular we identify two methods to transfer data between nodes in these two machines. In buffer-packing transfers, a contiguous block of data is transferred across the network. If the data are not stored contiguously, they are copied to (gathering) or from (scattering) buffers in local memory before and after the transfer. Chained transfers perform gathering, transfer and scattering in one step, reading the data elements with some non-sequential pattern and immediately transferring them on to the destination.Our model and measurements indicate that chaining of the gather, transfer, and scatter operations results in better performance than buffer packing for many important access patterns. Most standard message passing libraries (like MPI, PVM or NX) force the parallelizing compiler (or the programmer) to employ the buffer-packing communication operations. However, the addition of hardware support dedicated to communication (e.g., DMAs, line-transfer units) now gives the compiler a wider range of options.