SUNMOS
Encyclopedia
SUNMOS is an operating system
jointly developed by Sandia National Laboratories
and the Computer Science Department at the University of New Mexico
. The goal of the project, started in 1991, is to develop a highly portable, yet efficient, operating system for massively parallel-distributed
memory systems.
SUNMOS uses a single-task
ing kernel and does not provide demand paging
. It takes control of all node
s in the distributed system. Once an application
is loaded and running, it can manage all the available memory on a node and use the full resources provided by the hardware. Applications are started and controlled from a process called yod that runs on the host node. Yod runs on a Sun
frontend for the nCUBE 2
, and on a service node on the Intel Paragon
.
SUNMOS was developed as a reaction to the heavy weight version of OSF/1 that ran as a single-system image
on the Paragon and consumed 8-12 MB of the 16 MB available on each node, leaving little memory available for the compute applications. In comparison, SUNMOS used 250 KB of memory per node. Additionally, the overhead of OSF/1 limited the network bandwidth to 35 MB/s, while SUNMOS was able to use 170 MB/s of the peak 200 MB/s available.
The ideas in SUNMOS inspired PUMA, a multitasking variant that only ran on the i860 Paragon. Among the extensions in PUMA was the Portals API
, a scalable, high performance message passing API. Intel ported PUMA and Portals to the Pentium Pro
based ASCI Red
system and named it Cougar. Cray
ported Cougar to the Opteron
based Cray XT3
and renamed it Catamount. A version of Catamount was released to the public named OpenCatamount.
In 2009, the Catamount light-weight kernel was selected for an R&D 100 Award.
Operating system
An operating system is a set of programs that manage computer hardware resources and provide common services for application software. The operating system is the most important type of system software in a computer system...
jointly developed by Sandia National Laboratories
Sandia National Laboratories
The Sandia National Laboratories, managed and operated by the Sandia Corporation , are two major United States Department of Energy research and development national laboratories....
and the Computer Science Department at the University of New Mexico
University of New Mexico
The University of New Mexico at Albuquerque is a public research university located in Albuquerque, New Mexico, in the United States. It is the state's flagship research institution...
. The goal of the project, started in 1991, is to develop a highly portable, yet efficient, operating system for massively parallel-distributed
Distributed computing
Distributed computing is a field of computer science that studies distributed systems. A distributed system consists of multiple autonomous computers that communicate through a computer network. The computers interact with each other in order to achieve a common goal...
memory systems.
SUNMOS uses a single-task
Task (computers)
A task is an execution path through address space. In other words, a set of program instructions that are loaded in memory. The address registers have been loaded with the initial address of the program. At the next clock cycle, the CPU will start execution, in accord with the program. The sense is...
ing kernel and does not provide demand paging
Demand paging
In computer operating systems, demand paging is an application of virtual memory. In a system that uses demand paging, the operating system copies a disk page into physical memory only if an attempt is made to access it...
. It takes control of all node
Node (networking)
In communication networks, a node is a connection point, either a redistribution point or a communication endpoint . The definition of a node depends on the network and protocol layer referred to...
s in the distributed system. Once an application
Application software
Application software, also known as an application or an "app", is computer software designed to help the user to perform specific tasks. Examples include enterprise software, accounting software, office suites, graphics software and media players. Many application programs deal principally with...
is loaded and running, it can manage all the available memory on a node and use the full resources provided by the hardware. Applications are started and controlled from a process called yod that runs on the host node. Yod runs on a Sun
Sun Microsystems
Sun Microsystems, Inc. was a company that sold :computers, computer components, :computer software, and :information technology services. Sun was founded on February 24, 1982...
frontend for the nCUBE 2
NCUBE
nCUBE was a series of parallel computing computers from the company of the same name. Early generations of the hardware used a custom microprocessor...
, and on a service node on the Intel Paragon
Intel Paragon
The Intel Paragon was a series of massively parallel supercomputers produced by Intel. The Paragon XP/S was a productized version of the experimental Touchstone Delta system built at Caltech, launched in 1992. The Paragon superseded Intel's earlier iPSC/860 system, to which it was closely...
.
SUNMOS was developed as a reaction to the heavy weight version of OSF/1 that ran as a single-system image
Single-system image
In distributed computing, a single system image cluster is a cluster of machines that appears to be one single system. The concept is often considered synonymous with that of a distributed operating system, but a single image may be presented for more limited purposes, just job scheduling for...
on the Paragon and consumed 8-12 MB of the 16 MB available on each node, leaving little memory available for the compute applications. In comparison, SUNMOS used 250 KB of memory per node. Additionally, the overhead of OSF/1 limited the network bandwidth to 35 MB/s, while SUNMOS was able to use 170 MB/s of the peak 200 MB/s available.
The ideas in SUNMOS inspired PUMA, a multitasking variant that only ran on the i860 Paragon. Among the extensions in PUMA was the Portals API
Portals network programming api
Portals is a low-level network API for high-performance networking on high-performance computing systems developed by Sandia National Laboratories and the University of New Mexico...
, a scalable, high performance message passing API. Intel ported PUMA and Portals to the Pentium Pro
Pentium Pro
The Pentium Pro is a sixth-generation x86 microprocessor developed and manufactured by Intel introduced in November 1, 1995 . It introduced the P6 microarchitecture and was originally intended to replace the original Pentium in a full range of applications...
based ASCI Red
ASCI Red
ASCI Red was the first computer built under the Advanced Strategic Computing Initiative . ASCI Red was built by Intel and installed at Sandia in late 1996. The design was based on the Intel Paragon computer...
system and named it Cougar. Cray
Cray
Cray Inc. is an American supercomputer manufacturer based in Seattle, Washington. The company's predecessor, Cray Research, Inc. , was founded in 1972 by computer designer Seymour Cray. Seymour Cray went on to form the spin-off Cray Computer Corporation , in 1989, which went bankrupt in 1995,...
ported Cougar to the Opteron
Opteron
Opteron is AMD's x86 server and workstation processor line, and was the first processor which supported the AMD64 instruction set architecture . It was released on April 22, 2003 with the SledgeHammer core and was intended to compete in the server and workstation markets, particularly in the same...
based Cray XT3
Cray XT3
The Cray XT3 is a distributed memory massively parallel MIMD supercomputer designed by Cray Inc. with Sandia National Laboratories under the codename Red Storm. Cray turned the design into a commercial product in 2004...
and renamed it Catamount. A version of Catamount was released to the public named OpenCatamount.
In 2009, the Catamount light-weight kernel was selected for an R&D 100 Award.
External links
- [ftp://ftp.cs.sandia.gov/pub/sunmos/ SUNMOS FTP site]
- A humorous field guide to differences between SUNMOS and OSF
- OpenCatamount.