CSC 456 Spring 2012/11a NC - Revision history

Nknichol: /* mordred2 (Kerlabs) */

2012-04-23T18:03:17Z

mordred2 (Kerlabs)

← Older revision		Revision as of 18:03, 23 April 2012
Line 26:		Line 26:

	==mordred2 (Kerlabs)==		==mordred2 (Kerlabs)==
	The mordred2 is one of several clusters operated by Kerlabs. It is a distributed shared memory system running the open source software Kerrighed. The cluster contains 110 nodes, each with 2 dual-core AMD Opteron processors and 4GB of memory, making it the largest known cluster running Kerrighed.<ref name="mordred2"/> Its distributed shared memory is provided on the software level by the Linux extension Kerrighed. The software provides sequential consistency, process migration to another node, and checkpointing (the ability to return to a previous application state in case of failure).<ref name="kerrighed"/>		The mordred2 is one of several clusters operated by Kerlabs. It is a distributed shared memory system running the open source software Kerrighed. The cluster contains 110 nodes, each with 2 dual-core AMD Opteron processors and 4GB of memory, making it the largest known cluster running Kerrighed.<ref name="mordred2"/> Its distributed shared memory is provided on the software level by the Linux extension Kerrighed. This extension allows the programmer to treat remote memory accesses as shared memory accesses, effectively abstracting away the message passing required by underlying DSM hardware. The software provides sequential consistency, process migration to another node, and checkpointing (the ability to return to a previous application state in case of failure).<ref name="kerrighed"/>

	==References==		==References==

Nknichol: /* Large-Scale Multiprocessor Examples */

2012-04-23T17:57:08Z

Large-Scale Multiprocessor Examples

← Older revision		Revision as of 17:57, 23 April 2012
Line 4:		Line 4:
	==Large-Scale Multiprocessor Examples==		==Large-Scale Multiprocessor Examples==

	Some examples of large-scale multiprocessor systems include Fujitsu's K Computer, the Tianhe-1A from the National Supercomputer Center in Tianjin, China, and mordred2 from Kerlabs~~. Overall, in large cluster computers, message passing is much more popular than distributed shared memory~~.		Some examples of large-scale multiprocessor systems include Fujitsu's K Computer, the Tianhe-1A from the National Supercomputer Center in Tianjin, China, and mordred2 from Kerlabs.

	==K Computer==		==K Computer==

Nknichol: /* K Computer */

2012-04-23T17:56:01Z

K Computer

← Older revision		Revision as of 17:56, 23 April 2012
Line 10:		Line 10:
	Made by [http://www.fujitsu.com/global/ Fujitsu], the K Computer consists of 88,128 processors between 864 cabinets. Each cabinet contains 96 nodes which, in turn, each contain one processor and 16 GBytes of memory. <ref name="kprocs"/>		Made by [http://www.fujitsu.com/global/ Fujitsu], the K Computer consists of 88,128 processors between 864 cabinets. Each cabinet contains 96 nodes which, in turn, each contain one processor and 16 GBytes of memory. <ref name="kprocs"/>

	The system is networked together via [http://en.wikipedia.org/wiki/Point-to-point_(network_topology)#Point-to-point point-to-point], or direct, connection. Fujitsu has their own proprietary network, known as the "Tofu Interconnect". It is a six-dimensional [http://en.wikipedia.org/wiki/Mesh_topology mesh]/[http://en.wikipedia.org/wiki/Torus_interconnect torus] topology. Each set of 12 nodes is called a "node group" and is considered the unit of job allocation. Each node group is connected to adjacent node groups via a three-dimensional torus network. Additionally, the nodes within each node group are adjacently connection via their own three-dimensional mesh/torus. <ref name="kpdf"/><ref name="ktofu"/><ref name="knetwork"/> ~~[[What topology? Surely not 95^2 links!]]~~		The system is networked together via [http://en.wikipedia.org/wiki/Point-to-point_(network_topology)#Point-to-point point-to-point], or direct, connection. Fujitsu has their own proprietary network, known as the "Tofu Interconnect". It is a six-dimensional [http://en.wikipedia.org/wiki/Mesh_topology mesh]/[http://en.wikipedia.org/wiki/Torus_interconnect torus] topology. Each set of 12 nodes is called a "node group" and is considered the unit of job allocation. Each node group is connected to adjacent node groups via a three-dimensional torus network. Additionally, the nodes within each node group are adjacently connection via their own three-dimensional mesh/torus. <ref name="kpdf"/><ref name="ktofu"/><ref name="knetwork"/>

	The K Computer is not a [http://en.wikipedia.org/wiki/Distributed_shared_memory distributed shared memory] (DSM) machine in which the physically separate nodes are addressed as one logically shared address space. Instead, the K Computer utilizes a [http://en.wikipedia.org/wiki/Message_Passing_Interface message passing interface] (MPI), allowing the nodes to pass messages to one another as needed.		The K Computer utilizes a [http://en.wikipedia.org/wiki/Message_Passing_Interface message passing interface] (MPI), allowing the nodes to pass messages to one another as needed.

	==Tianhe-1A==		==Tianhe-1A==

Nknichol: /* Tianhe-1A */

2012-04-23T17:55:21Z

Tianhe-1A

← Older revision		Revision as of 17:55, 23 April 2012
Line 21:		Line 21:
	The Arch interconnect uses point-to-point connections in a hybrid fat tree configuration.		The Arch interconnect uses point-to-point connections in a hybrid fat tree configuration.

	The system also uses message passing, so neither a system-wide cache coherency protocol nor a memory consistency protocol is necessary.<ref name="tianhe_mpi"/>		The system also uses message passing (MPI), so neither a system-wide cache coherency protocol nor a memory consistency protocol is necessary.<ref name="tianhe_mpi"/>

	This cluster computer cost $88 million to build and an additional $20 million per year for electricity and operating expenses.<ref name="tianhe" />		This cluster computer cost $88 million to build and an additional $20 million per year for electricity and operating expenses.<ref name="tianhe" />

Nknichol: /* Tianhe-1A */

2012-04-23T17:55:02Z

Tianhe-1A

← Older revision		Revision as of 17:55, 23 April 2012
Line 21:		Line 21:
	The Arch interconnect uses point-to-point connections in a hybrid fat tree configuration.		The Arch interconnect uses point-to-point connections in a hybrid fat tree configuration.

	The system uses message passing ~~rather than shared memory~~, so neither a system-wide cache coherency protocol nor a memory consistency protocol is necessary.<ref name="tianhe_mpi"/>		The system also uses message passing, so neither a system-wide cache coherency protocol nor a memory consistency protocol is necessary.<ref name="tianhe_mpi"/>

	This cluster computer cost $88 million to build and an additional $20 million per year for electricity and operating expenses.<ref name="tianhe" />		This cluster computer cost $88 million to build and an additional $20 million per year for electricity and operating expenses.<ref name="tianhe" />

Nknichol: /* References */

2012-04-23T17:54:31Z

References

← Older revision		Revision as of 17:54, 23 April 2012
Line 38:		Line 38:
	<ref name="mordred2">http://kerrighed.org/php/clusterview.php?id=29</ref>		<ref name="mordred2">http://kerrighed.org/php/clusterview.php?id=29</ref>
	<ref name="tianhe">http://en.wikipedia.org/wiki/Tianhe-1</ref>		<ref name="tianhe">http://en.wikipedia.org/wiki/Tianhe-1</ref>
			<ref name="tianhe_mpi">https://www.google.com/url?sa=t&rct=j&q=&esrc=s&source=web&cd=4&ved=0CD8QFjAD&url=http%3A%2F%2Fsoftware.intel.com%2Ffile%2F39450&ei=iZaVT4fEC4Tetgfgtfm1Cw&usg=AFQjCNFCsxJccaKAuD5knOPxC6VQAR-xbQ</ref>
	</references>		</references>

Nknichol: /* Tianhe-1A */

2012-04-23T17:54:11Z

Tianhe-1A

← Older revision		Revision as of 17:54, 23 April 2012
Line 21:		Line 21:
	The Arch interconnect uses point-to-point connections in a hybrid fat tree configuration.		The Arch interconnect uses point-to-point connections in a hybrid fat tree configuration.

	The system uses message passing rather than shared memory, so neither a system-wide cache coherency protocol nor a memory consistency protocol is necessary.		The system uses message passing rather than shared memory, so neither a system-wide cache coherency protocol nor a memory consistency protocol is necessary.<ref name="tianhe_mpi"/>

	This cluster computer cost $88 million to build and an additional $20 million per year for electricity and operating expenses.<ref name="tianhe" />		This cluster computer cost $88 million to build and an additional $20 million per year for electricity and operating expenses.<ref name="tianhe" />

Nknichol at 17:10, 23 April 2012

2012-04-23T17:10:13Z

← Older revision		Revision as of 17:10, 23 April 2012
Line 1:		Line 1:
	==~~Write-up~~==		==Motivation For Article==
	~~11b. Current~~ large-scale ~~multiprocessors~~. ~~Who sells them, how do you assemble them~~ into systems, ~~what~~ consistency models ~~do they use (briefly~~, ~~don't redo 10b), do they maintain coherence across~~ the ~~whole~~ system~~, & how?~~		This aims to briefly outline the architecture of current large scale multiprocessor systems. We will go into detail about several current systems including their manufacturer, physical composition and connecting network, memory consistency models, and how data is kept coherent within the system.

	==Large-Scale Multiprocessor Examples==		==Large-Scale Multiprocessor Examples==

Nknichol at 17:01, 23 April 2012

2012-04-23T17:01:12Z

← Older revision		Revision as of 17:01, 23 April 2012
Line 1:		Line 1:
			==Write-up==
			11b. Current large-scale multiprocessors. Who sells them, how do you assemble them into systems, what consistency models do they use (briefly, don't redo 10b), do they maintain coherence across the whole system, & how?

	==Large-Scale Multiprocessor Examples==		==Large-Scale Multiprocessor Examples==

Nknichol: /* Large-Scale Multiprocessor Examples */

2012-04-16T22:40:52Z

Large-Scale Multiprocessor Examples

← Older revision		Revision as of 22:40, 16 April 2012
Line 1:		Line 1:
	==Large-Scale Multiprocessor Examples==		==Large-Scale Multiprocessor Examples==

	Some examples of large-scale multiprocessor systems include Fujitsu's K Computer, the Tianhe-1A from the National Supercomputer Center in Tianjin, China, and ~~[another example or two] [[How 'bout IBM's~~ large ~~systems--Blue Gene~~, ~~etc]]~~.		Some examples of large-scale multiprocessor systems include Fujitsu's K Computer, the Tianhe-1A from the National Supercomputer Center in Tianjin, China, and mordred2 from Kerlabs. Overall, in large cluster computers, message passing is much more popular than distributed shared memory.

	==K Computer==		==K Computer==