Active message applications programming interface and communication subsystem organization

High-performance network hardware is advancing, with multi-gigabit link bandwidths and sub-microsecond switch latencies. Network-interface hardware also continues to evolve, although the design space remains lar ge and diverse. One critical abstraction, a simple, portable, and general-purpose communications interface, is required to make ef fective use of these increasingly high-performance networks and their capable interfaces. Without a new interface, the software overheads of existing ones will dominate communication costs, and many applications may not benefit from the advancements in network hardware. This document specifies a new active message communications interface for these networks. Its primitives, in essence an instruction set for communications, map ef ficiently onto underlying network hardware and compose ef fectively into higher -level protocols and applications. For high-performance implementations, the interface enables direct application -network interface interactions. In the common case, for applications exhibiting locality in communication, these interactions bypass the operating system. T o nable the construction of lar ge-scale, general-purpose systems, the interface supports the protected multiprogramming of many users onto finite network resources.This document also describes a prototype system that uses the virtual-memory facilities of the Solaris operating system to implement virtual networks that support protected, network multiprogramming. The system caches the active communication endpoints in network-interface memory and demand-pages them between the host and network-interface memories.

[1]  Bennet S. Yee,et al.  1 Strongbox : A System for Self-Securing Programs , 1991 .

[2]  Richard P. Martin,et al.  HPAM: an active message layer for a network of hp workstations , 1994, Symposium Record Hot Interconnects II.

[3]  James R. Larus,et al.  Fine-grain access control for distributed shared memory , 1994, ASPLOS VI.

[4]  Jon Beecroft,et al.  Meiko CS-2 Interconnect Elan-Elite Design , 1994, Parallel Comput..

[5]  Robert W. Horst TNet: A Reliable System Area Network , 1995, IEEE Micro.

[6]  Anthony Skjellum,et al.  Extending the message passing interface (MPI) , 1994, Proceedings Scalable Parallel Libraries Conference.

[7]  Nathan E. Doss,et al.  Inter-communicator Extensions to MPI in the MPIX ( MPI eXtension ) Library , 1994 .

[8]  Kirk L. Johnson,et al.  CRL: high-performance all-software distributed shared memory , 1995, SOSP.

[9]  Steve R. Kleiman,et al.  SunOS Multi-thread Architecture , 1991, USENIX Winter.

[10]  Thorsten von Eicken,et al.  Low-latency communication over ATM networks using active messages , 1994, Symposium Record Hot Interconnects II.

[11]  Scott B. Marovich,et al.  Hamlyn: a high-performance network interface with sender-based memory management , 1995 .

[12]  David E. Culler,et al.  A case for NOW (networks of workstation) , 1995, PODC '95.

[13]  Lewis W. Tucker,et al.  CMMD: Active Messages on the CM-5 , 1994, Parallel Comput..

[14]  Robbert van Renesse,et al.  Using Sparse Capabilities in a Distributed Operating System , 1986, ICDCS.

[15]  Chris J. Scheiman,et al.  Experience with active messages on the Meiko CS-2 , 1995, Proceedings of 9th International Parallel Processing Symposium.

[16]  Thorsten von Eicken,et al.  Low-Latency Communication Over ATM Networks Using Active Messages , 1995, IEEE Micro.

[17]  Peter Druschel,et al.  Experiences with a high-speed network adaptor: a software perspective , 1994, SIGCOMM 1994.

[18]  Message Passing Interface Forum MPI: A message - passing interface standard , 1994 .

[19]  Manfred Morari,et al.  The Design and Evolution of Zipcode , 1994, Parallel Comput..

[20]  Robbert van Renesse,et al.  Design and Performance of Horus: A Lightweight Group Communications System , 1994 .

[21]  Charles L. Seitz,et al.  Myrinet: A Gigabit-per-Second Local Area Network , 1995, IEEE Micro.

[22]  Thorsten von Eicken,et al.  U-Net: a user-level network interface for parallel and distributed computing , 1995, SOSP.

[23]  David A. Patterson,et al.  Logp quantified: the case for low-overhead local area networks , 1995 .

[24]  Nathan E. Doss,et al.  MPI++: Issues and Features , 1994 .

[25]  Larry L. Peterson,et al.  Fbufs: a high-bandwidth cross-domain transfer facility , 1994, SOSP '93.

[26]  Bernard A. Traversat Distributed-Memory OS for Highly Parallel Systems : Experiences and Lessons from Paragon OSF / 1 and SUNMOS , 1994 .

[27]  Kai Li,et al.  Two virtual memory mapped network interface designs , 1994, Symposium Record Hot Interconnects II.

[28]  Kai Li,et al.  Retrospective: virtual memory mapped network interface for the SHRIMP multicomputer , 1994, ISCA '98.

[29]  Bennet S. Yee,et al.  Using Secure Coprocessors , 1994 .