Multiple instruction, multiple data: Difference between revisions

Revision as of 14:29, 4 February 2016

Revision as of 06:34, 31 May 2016

Line 4:

==Examples==

An example of MIMD system is [[Xeon_PhiXeon Phi|Intel Xeon Phi]], descended from [[Larrabee_%28microarchitecture%29Larrabee (microarchitecture)|Larrabee]] microarchitecture.<ref>http://perilsofparallel.blogspot.gr/2008/09/larrabee-vs-nvidia-mimd-vs-simd.html</ref> These processors have multiple processing cores (up to 61 as of 2015) that can execute different instructions on different data.

Most parallel computers, as of 2013, are MIMD systems.<ref>http://software.intel.com/en-us/articles/mimd</ref>

Line 13:

From a programmer's point of view, this memory model is better understood than the distributed memory model. Another advantage is that memory coherence is managed by the operating system and not the written program. Two known disadvantages are: scalability beyond thirty-two processors is difficult, and the shared memory model is less flexible than the distributed memory model.<ref name="Ibaroudene-slides"/>

There are many examples of shared memory (multiprocessors): UMA ([[Uniform Memory Access]]), COMA ([[Cache Only Memory Access]]) and NUMA ([[Non-Uniform Memory Access]]).<ref name=tanenbaum>{{cite book|author=[[Andrew S. Tanenbaum]]|title=Structured Computer Organization|pages=559-585559–585|publisher=Prentice-Hall|year=1997|url=http://cwx.prenhall.com/bookbind/pubbooks/tanenbaum2/chapter0/deluxe.html|edition=4|isbn=978-0130959904}}</ref>

===Bus-based===

Line 26:

== Distributed memory ==

In distributed memory MIMD machines, each processor has its own individual memory ___location. Each processor has no direct knowledge about other processor's memory. For data to be shared, it must be passed from one processor to another as a message. Since there is no shared memory, contention is not as great a problem with these machines. It is not economically feasible to connect a large number of processors directly to each other. A way to avoid this multitude of direct connections is to connect each processor to just a few others. This type of design can be inefficient because of the added time required to pass a message from one processor to another along the message path. The amount of time required for processors to perform simple message routing can be substantial. Systems were designed to reduce this time loss and [[Connection Machine|hypercube]] and [[Mesh networking|mesh]] are among two of the popular interconnection schemes.

Examples of distributed memory (multicomputers) include [[Massively parallel (computing)|MPP (massively parallel processors)]] and [[Computer cluster|COW (clusters of workstations)]]. The former is complex and expensive: lots of super-computers coupled by broad-band networks. Examples include hypercube and mesh interconections. COW is the "home-made" version for a fraction of the price.<ref name=tanenbaum/>