Cray MTA (original) (raw)
The Cray MTA, formerly known as the Tera MTA, is a supercomputer architecture based on thousands of independent threads, fine-grain communication and synchronization between threads, and latency tolerance for irregular computations. An uncommon feature of the MTA is several workloads can be interleaved with good performance. Typically, supercomputers are dedicated to a task at a time. The MTA allows idle threads to be allocated to other tasks with very little effect on the main calculations.
| Property | Value |
|---|---|
| dbo:abstract | The Cray MTA, formerly known as the Tera MTA, is a supercomputer architecture based on thousands of independent threads, fine-grain communication and synchronization between threads, and latency tolerance for irregular computations. Each MTA processor (CPU) has a high-performance ALU with many independent register sets, each running an independent thread. For example, the Cray MTA-2 uses 128 register sets and thus 128 threads per CPU/ALU. All MTAs to date use a barrel processor arrangement, with a thread switch on every cycle, with blocked (stalled) threads skipped to avoid wasting ALU cycles. When a thread performs a memory read, execution blocks until data returns; meanwhile, other threads continue executing. With enough threads (concurrency), there are nearly always runnable threads to "cover" for blocked threads, and the ALUs stay busy. The memory system uses to ensure correct ordering. For example, an array A is initially written with "empty" bits, and any thread reading a value from A blocks until another thread writes a value. This ensures correct ordering, but allows fine-grained interleaving and provides a simple programming model. The memory system is also "randomized", with adjacent physical addresses going to different memory banks. Thus, when two threads access memory simultaneously, they rarely conflict unless they are accessing the same location. A goal of the MTA is that porting codes from other machines is straightforward, but gives good performance. A parallelizing FORTRAN compiler can produce high performance for some codes with little manual intervention. Where manual porting is required, the simple and fine-grained synchronization model often allows programmers to write code the "obvious" way yet achieve good performance. A further goal is that programs for the MTA will be scalable – that is, when run on an MTA with twice as many CPUs, the same program will have nearly twice the performance. Both of these are challenges for many other high-performance computer systems. An uncommon feature of the MTA is several workloads can be interleaved with good performance. Typically, supercomputers are dedicated to a task at a time. The MTA allows idle threads to be allocated to other tasks with very little effect on the main calculations. (en) |
| dbo:wikiPageExternalLink | https://web.archive.org/web/20100115102337/http:/cray.com/CustomEngineering/KnowledgeManagement/CrayXMTSystem.aspx |
| dbo:wikiPageID | 25458359 (xsd:integer) |
| dbo:wikiPageLength | 7619 (xsd:nonNegativeInteger) |
| dbo:wikiPageRevisionID | 1007370826 (xsd:integer) |
| dbo:wikiPageWikiLink | dbr:Compiler dbr:Arithmetic_logic_unit dbr:Supercomputer dbr:FORTRAN dbr:Barrel_processor dbr:Cray_XMT dbc:Supercomputers dbr:Heterogeneous_Element_Processor dbc:Cray_products dbr:CMOS dbr:CPU dbr:San_Diego_Supercomputer_Center dbr:Scalability dbr:Naval_Research_Laboratory dbr:GaAs dbr:MTA-2 dbr:Full/empty_bits |
| dbp:wikiPageUsesTemplate | dbt:Mono dbt:Reflist dbt:Snd |
| dct:subject | dbc:Supercomputers dbc:Cray_products |
| gold:hypernym | dbr:Architecture |
| rdf:type | dbo:Company yago:WikicatCrayProducts yago:WikicatSupercomputers yago:Artifact100021939 yago:Commodity103076708 yago:Computer103082979 yago:Device103183080 yago:DigitalComputer103196324 yago:Instrumentality103575240 yago:Machine103699975 yago:Mainframe103711711 yago:Merchandise103748886 yago:Object100002684 yago:PhysicalEntity100001930 yago:Supercomputer104358117 yago:Whole100003553 |
| rdfs:comment | The Cray MTA, formerly known as the Tera MTA, is a supercomputer architecture based on thousands of independent threads, fine-grain communication and synchronization between threads, and latency tolerance for irregular computations. An uncommon feature of the MTA is several workloads can be interleaved with good performance. Typically, supercomputers are dedicated to a task at a time. The MTA allows idle threads to be allocated to other tasks with very little effect on the main calculations. (en) |
| rdfs:label | Cray MTA (en) |
| owl:sameAs | freebase:Cray MTA yago-res:Cray MTA wikidata:Cray MTA https://global.dbpedia.org/id/4iMFm |
| prov:wasDerivedFrom | wikipedia-en:Cray_MTA?oldid=1007370826&ns=0 |
| foaf:isPrimaryTopicOf | wikipedia-en:Cray_MTA |
| is dbo:influencedBy of | dbr:Chapel_(programming_language) |
| is dbo:wikiPageRedirects of | dbr:Tera_MTA |
| is dbo:wikiPageWikiLink of | dbr:Barrel_processor dbr:Cray_MTA-2 dbr:Chapel_(programming_language) dbr:Heterogeneous_Element_Processor dbr:Tera_Computer_Company dbr:Tera_MTA |
| is foaf:primaryTopic of | wikipedia-en:Cray_MTA |