This paper describes a portable benchmark suite that assesses the ability of cluster networking hardware and software to overlap MPI communication and computation. The Communication Offload MPI-based Benchmark, or COMB, uses two methods to characterize the ability of messages to make progress concurrently, with computational processing on the host processor(s). COMB measures the relationship between MPI communication bandwidth and host CPU availability.

Benchmark (surveying)

Computer cluster

10.1109/clustr.2002.1137785

Cite

Citations (59)

Panel: What is a Lightweight Kernel?.

Rolf Riesen Arthur B. Maccabe Balazs Gerofi David N. Lombard John R. Lange

Lightweight kernels (LWK) have been in use on the compute nodes of supercomputers for decades. Although many high-end systems now run Linux, interest in options and alternatives has increased in the last couple of years. Future extreme-scale systems require rethinking of the operating system, and modern LWKs may well play a role in the final solution. In the course of our research, it has become clear that no single definition for a lightweight kernel exists. This paper describes what we mean by the term and what makes LWKs different from other operating system kernels.

Kernel (algebra)

Source

Cite

Citations (0)

Single System Image.

Parallel Computing (2011)

Rolf Riesen Arthur B. Maccabe

Source

Cite

Citations (2)

MapReduce

Springer eBooks (2011)

David Padua Amol Ghoting John A. Gunnels Mark S. Squillante José Meseguer

10.1007/978-0-387-09766-4_20000

Cite

Citations (0)

Making CORBA objects persistent: the object database adapter approach

USENIX Conference on Object-Oriented Technologies and Systems (1997)

Francisco C. R. Reverbel Arthur B. Maccabe

This paper discusses a realization of object persistence in a CORBA-based distributed system. In our approach, persistence of CORBA objects is accomplished by the integration of the ORB with an ODBMS. This approach is not limited to pure object-oriented database systems, as the ODBMS may be a combination of a relational DBMS and an object-relational mapper. The design and implementation of an Object Database Adapter that integrates an ORB and an ODBMS with C++ bindings is presented. The ODA uses delegation (rather than inheritance) to connect user-provided implementation classes and IDL-generated classes. Only the user-defined parts of CORBA objects are actually stored in a database. Their IDL-generated parts are dynamically instantiated, in transient memory, by the ODA. Persistent relationships between CORBA objects within a server are not realized at the CORBA level, but at the level of implementation objects. Database traversals and queries can therefore be executed at ODBMS speeds. The paper discusses in some detail a number of implementation issues, such as caching. ODA support to local transactions, ODA interfaces, and CORBA server organization are also examined.

Interoperable Object Reference

Orb (optics)

Adapter (computing)

Object request broker

Source

Cite

Citations (6)

Hobbes

Ron Brightwell Ron Oldfield Arthur B. Maccabe David E. Bernholdt

This paper describes our vision for Hobbes, an operating system and runtime (OS/R) framework for extreme-scale systems. The Hobbes design explicitly supports application composition, which is emerging as a key approach for applications to address scalability and power concerns anticipated with coming extreme-scale architectures. We make use of virtualization technologies to provide the flexibility to support requirements of application components for different node-level operating systems and runtimes, as well as different mappings of the components onto the hardware. We describe the architecture of the Hobbes OS/R, how we will address the cross-cutting concerns of power/energy, scheduling of massive levels of parallelism, and resilience. We also outline how the "users" of the OS/R (programming models, applications, and tools) influence the design.

Resilience

10.1145/2491661.2481427

Cite

Citations (45)

Design, Implementation, and Performance of MPI on Portals 3.0

The International Journal of High Performance Computing Applications (2003)

Ron Brightwell Rolf Riesen Arthur B. Maccabe

This paper describes an implementation of the Message Passing Interface (MPI) on the Portals 3.0 data movement layer. Portals 3.0 provides low-level building blocks that are flexible enough to support higher-level message passing layers, such as MPI, very efficiently. Portals 3.0 is also designed to allow for programmable network interface cards to offload message processing from the host processor, allowing for the ability to overlap computation and MPI communication. We describe the basic building blocks in Portals 3.0, show how they can be put together to implement MPI, and describe the protocols of our MPI implementation. We look at several key operations within the implementation and describe the effects that a Portals 3.0 implementation has on scalability and performance. We also present preliminary performance results from our implementation for Myrinet.

Myrinet

Message Passing Interface

Interface (matter)

10.1177/1094342003017001002

Cite

Citations (27)