250:
4656:
1925:
1935:
70:
1945:
172:
29:
326:, the other threads can continue taking advantage of the unused computing resources, which may lead to faster overall execution, as these resources would have been idle if only a single thread were executed. Also, if a thread cannot use all the computing resources of the CPU (because instructions depend on each other's result), running another thread may prevent those resources from becoming idle.
610:
In addition to the hardware costs discussed in the block type of multithreading, interleaved multithreading has an additional cost of each pipeline stage tracking the thread ID of the instruction it is processing. Also, since there are more threads being executed concurrently in the pipeline, shared
532:
Additional hardware support for multithreading allows thread switching to be done in one CPU cycle, bringing performance improvements. Also, additional hardware allows each thread to behave as if it were executing alone and not sharing any hardware resources with other threads, minimizing the amount
848:
A major area of research is the thread scheduler that must quickly choose from among the list of ready-to-run threads to execute next, as well as maintain the ready-to-run and stalled thread lists. An important subtopic is the different thread priority schemes that can be used by the scheduler. The
398:
The simplest type of multithreading occurs when one thread runs until it is blocked by an event that normally would create a long-latency stall. Such a stall might be a cache miss that has to access off-chip memory, which might take hundreds of CPU cycles for the data to return. Instead of waiting
757:
In addition to the hardware costs discussed for interleaved multithreading, SMT has the additional cost of each pipeline stage tracking the thread ID of each instruction being processed. Again, shared resources such as caches and TLBs have to be sized for the large number of active threads being
528:
The goal of multithreading hardware support is to allow quick switching between a blocked thread and another thread ready to run. Switching from one thread to another means the hardware switches from using one register set to another. To achieve this goal, the hardware for the program visible
629:. Whereas a normal superscalar processor issues multiple instructions from a single thread every CPU cycle, in simultaneous multithreading (SMT) a superscalar processor can issue instructions from multiple threads every CPU cycle. Recognizing that any single thread has a limited amount of
361:
extensions and performing data prefetches (as a good video encoder might) do not suffer from cache misses or idle computing resources. Such programs therefore do not benefit from hardware multithreading and can indeed see degraded performance due to contention for shared resources.
863:
to be created for each thread. This allows each thread to run its own operating system on the same processor. On the other hand, if only user-mode state is saved, then less hardware is required, which would allow more threads to be active at one time for the same die area or cost.
301:. Even though it is very difficult to further speed up a single thread or single program, most computer systems are actually multitasking among multiple threads or programs. Thus, techniques that improve the throughput of all tasks result in overall performance gains.
606:
This type of multithreading was first called barrel processing, in which the staves of a barrel represent the pipeline stages and their executing threads. Interleaved, preemptive, fine-grained or time-sliced multithreading are more modern terminology.
338:(TLBs). As a result, execution times of a single thread are not improved and can be degraded, even when only one thread is executing, due to lower frequencies or additional pipeline stages that are necessary to accommodate thread-switching hardware.
365:
From the software standpoint, hardware support for multithreading is more visible to software, requiring more changes to both application programs and operating systems than multiprocessing. Hardware techniques used to support
399:
for the stall to resolve, a threaded processor would switch execution to another thread that was ready to run. Only when the data for the previous thread had arrived, would the previous thread be placed back on the list of
566:. Since one thread is relatively independent from other threads, there is less chance of one instruction in one pipelining stage needing an output from an older instruction in the pipeline. Conceptually, it is similar to
529:
registers, as well as some processor control registers (such as the program counter), is replicated. For example, to quickly switch between two threads, the processor is built with two sets of registers.
349:, while a synthetic program just performing a loop of non-optimized dependent floating-point operations actually gains a 100% speed improvement when run in parallel. On the other hand, hand-tuned
525:, in which tasks voluntarily give up execution time when they need to wait upon some type of event. This type of multithreading is known as block, cooperative or coarse-grained multithreading.
87:
42:
3982:
3009:
633:, this type of multithreading tries to exploit parallelism available across multiple threads to decrease the waste associated with unused issue slots.
1981:
134:
106:
903:
3120:
2303:
4072:
2822:
859:
If the multithreading scheme replicates all of the software-visible state, including privileged control registers and TLBs, then it enables
113:
3924:
2100:
2979:
2545:
2362:
940:
48:
3333:
968:
544:
for interrupts. Such schemes can be considered a type of block multithreading among the user program thread and the interrupt threads.
120:
2325:
2974:
3046:
102:
3328:
1678:
570:
multitasking used in operating systems; an analogy would be that the time slice given to each active thread is one CPU cycle.
1703:
930:
4093:
4320:
3743:
2867:
2130:
1974:
1554:
4343:
3753:
2894:
1708:
987:
934:
852:
Another area of research is what type of events should cause a thread switch: cache misses, inter-thread communication,
4232:
2021:
1220:
849:
thread scheduler might be implemented totally in software, totally in hardware, or as a hardware/software combination.
4088:
4338:
4315:
3061:
2889:
2862:
2241:
1860:
1688:
1225:
371:
233:
215:
153:
56:
197:
4681:
3917:
3876:
3439:
2332:
2298:
2293:
2212:
2177:
1948:
1049:
127:
4686:
4310:
4125:
3851:
3748:
3149:
3056:
2857:
2078:
1967:
1336:
189:
4417:
4331:
4280:
2877:
2596:
2031:
1627:
1589:
1253:
961:
182:
91:
4641:
4475:
4326:
4013:
3051:
2899:
2872:
2733:
2347:
2308:
2165:
1769:
1746:
1476:
1466:
833:
762:
630:
290:
4701:
3488:
3250:
2726:
2687:
2342:
2337:
2271:
2083:
1850:
1438:
1346:
1258:
1034:
1019:
335:
4696:
4660:
4606:
4066:
3910:
3115:
2812:
2510:
2207:
1938:
1673:
1178:
620:
4585:
4380:
4265:
4227:
4077:
3967:
3765:
3412:
2829:
2320:
2288:
2058:
2046:
2026:
1910:
1559:
883:
777:
522:
346:
611:
resources such as caches and TLBs need to be larger to avoid thrashing between the different threads.
533:
of software changes needed within the application and the operating system to support multithreading.
4601:
4580:
4525:
4412:
4402:
4375:
4237:
3856:
3819:
3809:
2197:
1928:
1855:
1830:
1693:
1341:
954:
910:
367:
274:
4691:
4555:
4181:
4120:
4033:
3871:
3278:
3214:
3191:
3041:
3003:
2839:
2789:
2784:
2261:
2155:
2063:
1779:
1612:
1205:
1074:
812:
808:
804:
4616:
4611:
4470:
4061:
3824:
3607:
3501:
3465:
3382:
3366:
3208:
2997:
2956:
2944:
2807:
2721:
2642:
2407:
2068:
2011:
1840:
1774:
1665:
1481:
1148:
837:
751:
388:
334:
Multiple threads can interfere with each other when sharing hardware resources such as caches or
266:
193:
80:
4355:
4287:
4191:
4083:
4038:
3630:
3602:
3512:
3477:
3226:
3220:
3202:
2936:
2930:
2834:
2738:
2629:
2568:
2430:
2073:
1905:
1736:
1617:
1384:
1374:
1369:
567:
298:
4447:
4407:
4360:
4350:
4145:
4008:
3947:
3804:
3713:
3459:
3171:
2989:
2748:
2716:
2674:
2586:
2387:
2202:
2192:
2182:
2172:
2142:
2125:
1990:
1875:
1845:
1835:
1731:
1645:
1521:
1461:
1428:
1418:
1308:
1273:
1263:
1200:
1069:
1044:
1039:
1004:
626:
354:
258:
4387:
4275:
4270:
4260:
4247:
4043:
3834:
3770:
3356:
3078:
2968:
2915:
2447:
2160:
2016:
1998:
1635:
1607:
1579:
1574:
1403:
1379:
1331:
1316:
1298:
1288:
1283:
1245:
1195:
1190:
1107:
1053:
853:
563:
294:
270:
8:
4550:
4505:
4305:
4171:
3881:
3866:
3686:
3537:
3519:
3483:
3471:
3125:
3072:
2849:
2765:
2647:
2502:
2397:
2256:
1900:
1825:
1741:
1726:
1491:
1278:
1235:
1230:
1127:
1117:
1089:
4575:
4424:
4397:
4222:
4186:
4176:
4135:
3977:
3957:
3952:
3933:
3738:
3730:
3582:
3557:
3361:
3236:
2760:
2701:
2581:
2313:
2041:
1865:
1764:
1640:
1597:
1506:
1448:
1433:
1423:
1215:
1014:
17:
941:
Operating System | Difference between
Multitasking, Multithreading and Multiprocessing
4621:
4297:
4255:
4150:
3691:
3658:
3574:
3506:
3407:
3397:
3387:
3318:
3313:
3308:
3231:
3160:
3066:
3026:
2659:
2609:
2559:
2535:
2417:
2357:
2352:
2234:
2150:
1885:
1815:
1794:
1756:
1564:
1531:
1511:
1210:
1122:
996:
350:
754:" is used to denote when instructions from only one thread can be issued at a time.
4631:
4430:
4365:
4212:
4028:
4023:
4018:
3987:
3861:
3794:
3780:
3635:
3542:
3496:
3303:
3298:
3293:
3288:
3283:
3273:
3143:
3110:
3021:
3016:
2925:
2777:
2772:
2755:
2743:
2682:
2246:
2224:
2110:
2088:
2006:
1718:
1602:
1569:
1364:
1293:
1182:
1168:
1163:
1112:
1099:
1024:
977:
816:
553:
400:
4495:
4435:
4370:
4217:
4207:
4140:
4130:
3972:
3962:
3775:
3760:
3708:
3612:
3587:
3424:
3417:
3268:
3263:
3258:
3197:
3105:
3095:
2817:
2652:
2604:
2367:
2251:
2219:
2120:
2115:
2036:
1789:
1683:
1655:
1549:
1501:
1486:
1471:
1326:
1321:
1268:
1158:
1132:
1084:
1029:
878:
860:
559:
537:
310:
323:
4626:
4442:
4099:
3992:
3886:
3720:
3703:
3696:
3592:
3449:
3186:
3100:
3031:
2614:
2576:
2525:
2520:
2515:
2229:
2053:
1895:
1799:
1698:
1544:
1516:
541:
4675:
4515:
4392:
3681:
3597:
2637:
2619:
2412:
2105:
1784:
1079:
819:
2540:
4115:
3891:
3829:
3645:
3622:
3434:
3155:
2093:
1880:
1539:
4636:
3676:
3640:
3351:
3323:
3181:
3036:
1959:
1870:
1496:
1408:
873:
770:
249:
3562:
3552:
3547:
3529:
3429:
3402:
2664:
2497:
2467:
2187:
1890:
1820:
1413:
1153:
1009:
253:
A process with two threads of execution, running on a single processor
246:
Ability of a CPU to provide multiple threads of execution concurrently
4510:
4485:
3902:
3653:
3650:
3392:
2462:
2440:
1395:
1356:
750:
To distinguish the other types of multithreading from SMT, the term "
540:
and embedded processors have multiple register banks to allow quick
200:. Statements consisting only of original research should be removed.
69:
4560:
4540:
4465:
3668:
2487:
1456:
946:
826:
286:
4565:
4545:
4520:
4155:
2477:
2435:
521:
Conceptually, it is similar to cooperative multi-tasking used in
464:
is issued, which is a load instruction that misses in all caches.
358:
4535:
4530:
2492:
2457:
2422:
800:
796:
792:
788:
784:
766:
374:. Thread scheduling is also a major problem in multithreading.
293:
have stalled since the late 1990s. This allowed the concept of
2950:
2482:
2452:
774:
342:
558:
The purpose of Fine grained multithreading is to remove all
4570:
4500:
4490:
3814:
2962:
2882:
2472:
823:
904:"Intel Hyper-Threading Technology, Technical User's Guide"
4480:
4457:
2402:
2392:
830:
781:
937:, March 2003, by Theo Ungerer, Borut Robi and Jurij Silc
382:
289:
has become more popular as efforts to further exploit
625:
The most advanced type of multithreading applies to
931:
A Survey of
Processors with Explicit Multithreading
94:. Unsourced material may be challenged and removed.
304:Two major techniques for throughput computing are
4673:
393:
370:often parallel the software techniques used for
297:to re-emerge from the more specialized field of
474:: thread scheduler invoked, switches to thread
614:
547:
3918:
1975:
986:Note: This template roughly follows the 2012
962:
2980:Computer performance by orders of magnitude
843:
103:"Multithreading" computer architecture
57:Learn how and when to remove these messages
3925:
3911:
1989:
1982:
1968:
969:
955:
377:
234:Learn how and when to remove this message
216:Learn how and when to remove this message
154:Learn how and when to remove this message
248:
4674:
3932:
1679:Knowledge representation and reasoning
345:claims up to 30% improvement with its
3906:
1963:
1704:Philosophy of artificial intelligence
950:
2951:Floating-point operations per second
1030:Energy consumption (Green computing)
976:
165:
92:adding citations to reliable sources
63:
22:
1709:Distributed artificial intelligence
988:ACM Computing Classification System
383:Interleaved/Temporal multithreading
13:
1221:Integrated development environment
14:
4713:
1689:Automated planning and scheduling
1226:Software configuration management
924:
38:This article has multiple issues.
4655:
4654:
3877:Semiconductor device fabrication
1943:
1933:
1924:
1923:
329:
170:
68:
27:
4126:Analysis of parallel algorithms
3852:History of general-purpose CPUs
2079:Nondeterministic Turing machine
1934:
1337:Computational complexity theory
79:needs additional citations for
46:or discuss these issues on the
2032:Deterministic finite automaton
1128:Network performance evaluation
896:
746:are all simultaneously issued.
707:are all simultaneously issued.
1:
4073:Simultaneous and heterogenous
2823:Simultaneous and heterogenous
1492:Multimedia information system
1477:Geographic information system
1467:Enterprise information system
1063:Computer systems organization
889:
631:instruction-level parallelism
598:: an instruction from thread
584:: an instruction from thread
394:Coarse-grained multithreading
336:translation lookaside buffers
317:
291:instruction-level parallelism
269:(CPU) (or a single core in a
16:For threads in software, see
4661:Category: Parallel computing
3507:Integrated memory controller
3489:Translation lookaside buffer
2688:Memory dependence prediction
2131:Random-access stored program
2084:Probabilistic Turing machine
1851:Computational social science
1439:Theoretical computer science
1259:Software development process
1035:Electronic design automation
1020:Very Large Scale Integration
943:GeeksforGeeks, 6 Sept. 2018.
909:. p. 13. Archived from
7:
2963:Synaptic updates per second
1674:Natural language processing
1462:Information storage systems
867:
621:Simultaneous multithreading
615:Simultaneous multithreading
548:Fine grained multithreading
523:real-time operating systems
341:Overall efficiency varies;
280:
196:the claims made and adding
10:
4718:
3968:High-performance computing
3367:Heterogeneous architecture
2289:Orthogonal instruction set
2059:Alternating Turing machine
2047:Quantum cellular automaton
1590:Human–computer interaction
1560:Intrusion detection system
1472:Social information systems
1457:Database management system
884:Speculative multithreading
778:Hyper-Threading Technology
667:are simultaneously issued.
618:
562:stalls from the execution
551:
386:
347:Hyper-Threading Technology
322:If a thread gets a lot of
15:
4650:
4602:Automatic parallelization
4594:
4456:
4296:
4246:
4238:Application checkpointing
4200:
4164:
4108:
4052:
4001:
3940:
3857:Microprocessor chronology
3844:
3820:Dynamic frequency scaling
3793:
3729:
3667:
3621:
3573:
3528:
3448:
3375:
3344:
3249:
3170:
3134:
3088:
2988:
2975:Cache performance metrics
2914:
2848:
2798:
2709:
2700:
2673:
2628:
2595:
2567:
2558:
2378:
2281:
2270:
2141:
1997:
1919:
1856:Computational engineering
1831:Computational mathematics
1808:
1755:
1717:
1664:
1626:
1588:
1530:
1447:
1393:
1355:
1307:
1244:
1177:
1141:
1098:
1062:
995:
984:
3872:Hardware security module
3215:Digital signal processor
3192:Graphics processing unit
3004:Graphics processing unit
1866:Computational healthcare
1861:Differentiable computing
1780:Graphics processing unit
1206:Domain-specific language
1075:Computational complexity
844:Implementation specifics
761:Implementations include
4682:Central processing unit
4617:Embarrassingly parallel
4612:Deterministic algorithm
3825:Dynamic voltage scaling
3608:Memory address register
3502:Branch target predictor
3466:Address generation unit
3209:Physics processing unit
2998:Central processing unit
2957:Transactions per second
2945:Instructions per second
2868:Array processing (SIMT)
2012:Stored-program computer
1841:Computational chemistry
1775:Photograph manipulation
1666:Artificial intelligence
1482:Decision support system
752:temporal multithreading
389:Temporal multithreading
378:Types of multithreading
267:central processing unit
4687:Instruction processing
4332:Associative processing
4288:Non-blocking algorithm
4094:Clustered multi-thread
3631:Hardwired control unit
3513:Memory management unit
3478:Memory management unit
3227:Secure cryptoprocessor
3221:Tensor Processing Unit
3203:Vision processing unit
2937:Cycles per instruction
2931:Instructions per cycle
2878:Associative processing
2569:Instruction pipelining
1991:Processor technologies
1906:Educational technology
1737:Reinforcement learning
1487:Process control system
1385:Computational geometry
1375:Algorithmic efficiency
1370:Analysis of algorithms
1025:Systems on Chip (SoCs)
627:superscalar processors
299:transaction processing
273:) to provide multiple
254:
4448:Hardware acceleration
4361:Superscalar processor
4351:Dataflow architecture
3948:Distributed computing
3714:Sum-addressed decoder
3460:Arithmetic logic unit
2587:Classic RISC pipeline
2541:Epiphany architecture
2388:Motorola 68000 series
1876:Electronic publishing
1846:Computational biology
1836:Computational physics
1732:Unsupervised learning
1646:Distributed computing
1522:Information retrieval
1429:Mathematical analysis
1419:Mathematical software
1309:Theory of computation
1274:Software construction
1264:Requirements analysis
1142:Software organization
1070:Computer architecture
1040:Hardware acceleration
1005:Printed circuit board
372:computer multitasking
259:computer architecture
252:
4327:Pipelined processing
4276:Explicit parallelism
4271:Implicit parallelism
4261:Dataflow programming
3835:Performance per watt
3413:replacement policies
3079:Package on a package
2969:Performance per watt
2873:Pipelined processing
2643:Tomasulo's algorithm
2448:Clipper architecture
2304:Application-specific
2017:Finite-state machine
1636:Concurrent computing
1608:Ubiquitous computing
1580:Application security
1575:Information security
1404:Discrete mathematics
1380:Randomized algorithm
1332:Computability theory
1317:Model of computation
1289:Software maintenance
1284:Software engineering
1246:Software development
1196:Programming language
1191:Programming paradigm
1108:Network architecture
840:microarchitectures.
295:throughput computing
275:threads of execution
271:multi-core processor
265:is the ability of a
88:improve this article
4702:Threads (computing)
4551:Parallel Extensions
4356:Pipelined processor
3867:Digital electronics
3520:Instruction decoder
3472:Floating-point unit
3126:Soft microprocessor
3073:System in a package
2648:Reservation station
2178:Transport-triggered
1911:Document management
1901:Operations research
1826:Enterprise software
1742:Multi-task learning
1727:Supervised learning
1449:Information systems
1279:Software deployment
1236:Software repository
1090:Real-time computing
285:The multithreading
4697:Parallel computing
4425:Massively parallel
4403:distributed shared
4223:Cache invalidation
4187:Instruction window
3978:Manycore processor
3958:Massively parallel
3953:Parallel computing
3934:Parallel computing
3739:Integrated circuit
3583:Processor register
3237:Baseband processor
2582:Operand forwarding
2042:Cellular automaton
1694:Search methodology
1641:Parallel computing
1598:Interaction design
1507:Computing platform
1434:Numerical analysis
1424:Information theory
1216:Software framework
1179:Software notations
1118:Network components
1015:Integrated circuit
699:, and instruction
255:
181:possibly contains
18:Thread (computing)
4669:
4668:
4622:Parallel slowdown
4256:Stream processing
4146:Karp–Flatt metric
3900:
3899:
3789:
3788:
3408:Instruction cache
3398:Scratchpad memory
3245:
3244:
3232:Network processor
3161:Network on a chip
3116:Ultra-low-voltage
3067:Multi-chip module
2910:
2909:
2696:
2695:
2683:Branch prediction
2660:Register renaming
2554:
2553:
2536:VISC architecture
2358:Quantum computing
2353:VISC architecture
2235:Secondary storage
2151:Microarchitecture
2111:Register machines
1957:
1956:
1886:Electronic voting
1816:Quantum Computing
1809:Applied computing
1795:Image compression
1565:Hardware security
1555:Security services
1512:Digital marketing
1299:Open-source model
1211:Modeling language
1123:Network scheduler
856:completion, etc.
773:(not completed),
728:and instructions
542:context switching
536:Many families of
351:assembly language
244:
243:
236:
226:
225:
218:
183:original research
164:
163:
156:
138:
61:
4709:
4658:
4657:
4632:Software lockout
4431:Computer cluster
4366:Vector processor
4321:Array processing
4306:Flynn's taxonomy
4213:Memory coherence
3988:Computer network
3927:
3920:
3913:
3904:
3903:
3862:Processor design
3754:Power management
3636:Instruction unit
3497:Branch predictor
3446:
3445:
3144:System on a chip
3086:
3085:
2926:Transistor count
2850:Flynn's taxonomy
2707:
2706:
2565:
2564:
2368:Addressing modes
2279:
2278:
2225:Memory hierarchy
2089:Hypercomputation
2007:Abstract machine
1984:
1977:
1970:
1961:
1960:
1947:
1946:
1937:
1936:
1927:
1926:
1747:Cross-validation
1719:Machine learning
1603:Social computing
1570:Network security
1365:Algorithm design
1294:Programming team
1254:Control variable
1231:Software library
1169:Software quality
1164:Operating system
1113:Network protocol
978:Computer science
971:
964:
957:
948:
947:
918:
917:
915:
908:
900:
861:virtual machines
817:Sun Microsystems
745:
741:
734:
727:
723:
716:
706:
702:
698:
694:
687:
683:
676:
666:
662:
659:and instruction
658:
654:
647:
643:
601:
597:
587:
583:
554:Barrel processor
538:microcontrollers
516:
512:
505:
495:
491:
487:
477:
473:
463:
459:
452:
442:
438:
431:
421:
417:
413:
239:
232:
221:
214:
210:
207:
201:
198:inline citations
174:
173:
166:
159:
152:
148:
145:
139:
137:
96:
72:
64:
53:
31:
30:
23:
4717:
4716:
4712:
4711:
4710:
4708:
4707:
4706:
4692:Microprocessors
4672:
4671:
4670:
4665:
4646:
4590:
4496:Coarray Fortran
4452:
4436:Beowulf cluster
4292:
4242:
4233:Synchronization
4218:Cache coherence
4208:Multiprocessing
4196:
4160:
4141:Cost efficiency
4136:Gustafson's law
4104:
4048:
3997:
3973:Multiprocessing
3963:Cloud computing
3936:
3931:
3901:
3896:
3882:Tick–tock model
3840:
3796:
3785:
3725:
3709:Address decoder
3663:
3617:
3613:Program counter
3588:Status register
3569:
3524:
3484:Load–store unit
3451:
3444:
3371:
3340:
3241:
3198:Image processor
3173:
3166:
3136:
3130:
3106:Microcontroller
3096:Embedded system
3084:
2984:
2917:
2906:
2844:
2794:
2692:
2669:
2653:Re-order buffer
2624:
2605:Data dependency
2591:
2550:
2380:
2374:
2273:
2272:Instruction set
2266:
2252:Multiprocessing
2220:Cache hierarchy
2213:Register/memory
2137:
2037:Queue automaton
1993:
1988:
1958:
1953:
1944:
1915:
1896:Word processing
1804:
1790:Virtual reality
1751:
1713:
1684:Computer vision
1660:
1656:Multiprocessing
1622:
1584:
1550:Security hacker
1526:
1502:Digital library
1443:
1394:Mathematics of
1389:
1351:
1327:Automata theory
1322:Formal language
1303:
1269:Software design
1240:
1173:
1159:Virtual machine
1137:
1133:Network service
1094:
1085:Embedded system
1058:
991:
980:
975:
927:
922:
921:
913:
906:
902:
901:
897:
892:
879:Super-threading
870:
846:
743:
736:
729:
725:
718:
711:
704:
700:
696:
689:
685:
678:
671:
664:
660:
656:
649:
645:
644:: instructions
641:
623:
617:
599:
592:
585:
578:
560:data dependency
556:
550:
514:
507:
500:
493:
489:
482:
475:
468:
461:
454:
447:
440:
433:
426:
419:
415:
411:
396:
391:
385:
380:
353:programs using
332:
320:
311:multiprocessing
283:
247:
240:
229:
228:
227:
222:
211:
205:
202:
187:
175:
171:
160:
149:
143:
140:
97:
95:
85:
73:
32:
28:
21:
12:
11:
5:
4715:
4705:
4704:
4699:
4694:
4689:
4684:
4667:
4666:
4664:
4663:
4651:
4648:
4647:
4645:
4644:
4639:
4634:
4629:
4627:Race condition
4624:
4619:
4614:
4609:
4604:
4598:
4596:
4592:
4591:
4589:
4588:
4583:
4578:
4573:
4568:
4563:
4558:
4553:
4548:
4543:
4538:
4533:
4528:
4523:
4518:
4513:
4508:
4503:
4498:
4493:
4488:
4483:
4478:
4473:
4468:
4462:
4460:
4454:
4453:
4451:
4450:
4445:
4440:
4439:
4438:
4428:
4422:
4421:
4420:
4415:
4410:
4405:
4400:
4395:
4385:
4384:
4383:
4378:
4371:Multiprocessor
4368:
4363:
4358:
4353:
4348:
4347:
4346:
4341:
4336:
4335:
4334:
4329:
4324:
4313:
4302:
4300:
4294:
4293:
4291:
4290:
4285:
4284:
4283:
4278:
4273:
4263:
4258:
4252:
4250:
4244:
4243:
4241:
4240:
4235:
4230:
4225:
4220:
4215:
4210:
4204:
4202:
4198:
4197:
4195:
4194:
4189:
4184:
4179:
4174:
4168:
4166:
4162:
4161:
4159:
4158:
4153:
4148:
4143:
4138:
4133:
4128:
4123:
4118:
4112:
4110:
4106:
4105:
4103:
4102:
4100:Hardware scout
4097:
4091:
4086:
4081:
4075:
4070:
4064:
4058:
4056:
4054:Multithreading
4050:
4049:
4047:
4046:
4041:
4036:
4031:
4026:
4021:
4016:
4011:
4005:
4003:
3999:
3998:
3996:
3995:
3993:Systolic array
3990:
3985:
3980:
3975:
3970:
3965:
3960:
3955:
3950:
3944:
3942:
3938:
3937:
3930:
3929:
3922:
3915:
3907:
3898:
3897:
3895:
3894:
3889:
3887:Pin grid array
3884:
3879:
3874:
3869:
3864:
3859:
3854:
3848:
3846:
3842:
3841:
3839:
3838:
3832:
3827:
3822:
3817:
3812:
3807:
3801:
3799:
3791:
3790:
3787:
3786:
3784:
3783:
3778:
3773:
3768:
3763:
3758:
3757:
3756:
3751:
3746:
3735:
3733:
3727:
3726:
3724:
3723:
3721:Barrel shifter
3718:
3717:
3716:
3711:
3704:Binary decoder
3701:
3700:
3699:
3689:
3684:
3679:
3673:
3671:
3665:
3664:
3662:
3661:
3656:
3648:
3643:
3638:
3633:
3627:
3625:
3619:
3618:
3616:
3615:
3610:
3605:
3600:
3595:
3593:Stack register
3590:
3585:
3579:
3577:
3571:
3570:
3568:
3567:
3566:
3565:
3560:
3550:
3545:
3540:
3534:
3532:
3526:
3525:
3523:
3522:
3517:
3516:
3515:
3504:
3499:
3494:
3493:
3492:
3486:
3475:
3469:
3463:
3456:
3454:
3443:
3442:
3437:
3432:
3427:
3422:
3421:
3420:
3415:
3410:
3405:
3400:
3395:
3385:
3379:
3377:
3373:
3372:
3370:
3369:
3364:
3359:
3354:
3348:
3346:
3342:
3341:
3339:
3338:
3337:
3336:
3326:
3321:
3316:
3311:
3306:
3301:
3296:
3291:
3286:
3281:
3276:
3271:
3266:
3261:
3255:
3253:
3247:
3246:
3243:
3242:
3240:
3239:
3234:
3229:
3224:
3218:
3212:
3206:
3200:
3195:
3189:
3187:AI accelerator
3184:
3178:
3176:
3168:
3167:
3165:
3164:
3158:
3153:
3150:Multiprocessor
3147:
3140:
3138:
3132:
3131:
3129:
3128:
3123:
3118:
3113:
3108:
3103:
3101:Microprocessor
3098:
3092:
3090:
3089:By application
3083:
3082:
3076:
3070:
3064:
3059:
3054:
3049:
3044:
3039:
3034:
3032:Tile processor
3029:
3024:
3019:
3014:
3013:
3012:
3001:
2994:
2992:
2986:
2985:
2983:
2982:
2977:
2972:
2966:
2960:
2954:
2948:
2942:
2941:
2940:
2928:
2922:
2920:
2912:
2911:
2908:
2907:
2905:
2904:
2903:
2902:
2892:
2887:
2886:
2885:
2880:
2875:
2870:
2860:
2854:
2852:
2846:
2845:
2843:
2842:
2837:
2832:
2827:
2826:
2825:
2820:
2818:Hyperthreading
2810:
2804:
2802:
2800:Multithreading
2796:
2795:
2793:
2792:
2787:
2782:
2781:
2780:
2770:
2769:
2768:
2763:
2753:
2752:
2751:
2746:
2736:
2731:
2730:
2729:
2724:
2713:
2711:
2704:
2698:
2697:
2694:
2693:
2691:
2690:
2685:
2679:
2677:
2671:
2670:
2668:
2667:
2662:
2657:
2656:
2655:
2650:
2640:
2634:
2632:
2626:
2625:
2623:
2622:
2617:
2612:
2607:
2601:
2599:
2593:
2592:
2590:
2589:
2584:
2579:
2577:Pipeline stall
2573:
2571:
2562:
2556:
2555:
2552:
2551:
2549:
2548:
2543:
2538:
2533:
2530:
2529:
2528:
2526:z/Architecture
2523:
2518:
2513:
2505:
2500:
2495:
2490:
2485:
2480:
2475:
2470:
2465:
2460:
2455:
2450:
2445:
2444:
2443:
2438:
2433:
2425:
2420:
2415:
2410:
2405:
2400:
2395:
2390:
2384:
2382:
2376:
2375:
2373:
2372:
2371:
2370:
2360:
2355:
2350:
2345:
2340:
2335:
2330:
2329:
2328:
2318:
2317:
2316:
2306:
2301:
2296:
2291:
2285:
2283:
2276:
2268:
2267:
2265:
2264:
2259:
2254:
2249:
2244:
2239:
2238:
2237:
2232:
2230:Virtual memory
2222:
2217:
2216:
2215:
2210:
2205:
2200:
2190:
2185:
2180:
2175:
2170:
2169:
2168:
2158:
2153:
2147:
2145:
2139:
2138:
2136:
2135:
2134:
2133:
2128:
2123:
2118:
2108:
2103:
2098:
2097:
2096:
2091:
2086:
2081:
2076:
2071:
2066:
2061:
2054:Turing machine
2051:
2050:
2049:
2044:
2039:
2034:
2029:
2024:
2014:
2009:
2003:
2001:
1995:
1994:
1987:
1986:
1979:
1972:
1964:
1955:
1954:
1952:
1951:
1941:
1931:
1920:
1917:
1916:
1914:
1913:
1908:
1903:
1898:
1893:
1888:
1883:
1878:
1873:
1868:
1863:
1858:
1853:
1848:
1843:
1838:
1833:
1828:
1823:
1818:
1812:
1810:
1806:
1805:
1803:
1802:
1800:Solid modeling
1797:
1792:
1787:
1782:
1777:
1772:
1767:
1761:
1759:
1753:
1752:
1750:
1749:
1744:
1739:
1734:
1729:
1723:
1721:
1715:
1714:
1712:
1711:
1706:
1701:
1699:Control method
1696:
1691:
1686:
1681:
1676:
1670:
1668:
1662:
1661:
1659:
1658:
1653:
1651:Multithreading
1648:
1643:
1638:
1632:
1630:
1624:
1623:
1621:
1620:
1615:
1610:
1605:
1600:
1594:
1592:
1586:
1585:
1583:
1582:
1577:
1572:
1567:
1562:
1557:
1552:
1547:
1545:Formal methods
1542:
1536:
1534:
1528:
1527:
1525:
1524:
1519:
1517:World Wide Web
1514:
1509:
1504:
1499:
1494:
1489:
1484:
1479:
1474:
1469:
1464:
1459:
1453:
1451:
1445:
1444:
1442:
1441:
1436:
1431:
1426:
1421:
1416:
1411:
1406:
1400:
1398:
1391:
1390:
1388:
1387:
1382:
1377:
1372:
1367:
1361:
1359:
1353:
1352:
1350:
1349:
1344:
1339:
1334:
1329:
1324:
1319:
1313:
1311:
1305:
1304:
1302:
1301:
1296:
1291:
1286:
1281:
1276:
1271:
1266:
1261:
1256:
1250:
1248:
1242:
1241:
1239:
1238:
1233:
1228:
1223:
1218:
1213:
1208:
1203:
1198:
1193:
1187:
1185:
1175:
1174:
1172:
1171:
1166:
1161:
1156:
1151:
1145:
1143:
1139:
1138:
1136:
1135:
1130:
1125:
1120:
1115:
1110:
1104:
1102:
1096:
1095:
1093:
1092:
1087:
1082:
1077:
1072:
1066:
1064:
1060:
1059:
1057:
1056:
1047:
1042:
1037:
1032:
1027:
1022:
1017:
1012:
1007:
1001:
999:
993:
992:
985:
982:
981:
974:
973:
966:
959:
951:
945:
944:
938:
926:
925:External links
923:
920:
919:
916:on 2010-08-21.
894:
893:
891:
888:
887:
886:
881:
876:
869:
866:
845:
842:
748:
747:
717:: instruction
708:
688:, instruction
677:: instruction
668:
619:Main article:
616:
613:
604:
603:
589:
552:Main article:
549:
546:
519:
518:
506:: instruction
497:
488:: instruction
479:
465:
453:: instruction
444:
432:: instruction
423:
414:: instruction
395:
392:
387:Main article:
384:
381:
379:
376:
368:multithreading
331:
328:
319:
316:
306:multithreading
282:
279:
263:multithreading
245:
242:
241:
224:
223:
178:
176:
169:
162:
161:
76:
74:
67:
62:
36:
35:
33:
26:
9:
6:
4:
3:
2:
4714:
4703:
4700:
4698:
4695:
4693:
4690:
4688:
4685:
4683:
4680:
4679:
4677:
4662:
4653:
4652:
4649:
4643:
4640:
4638:
4635:
4633:
4630:
4628:
4625:
4623:
4620:
4618:
4615:
4613:
4610:
4608:
4605:
4603:
4600:
4599:
4597:
4593:
4587:
4584:
4582:
4579:
4577:
4574:
4572:
4569:
4567:
4564:
4562:
4559:
4557:
4554:
4552:
4549:
4547:
4544:
4542:
4539:
4537:
4534:
4532:
4529:
4527:
4524:
4522:
4519:
4517:
4516:Global Arrays
4514:
4512:
4509:
4507:
4504:
4502:
4499:
4497:
4494:
4492:
4489:
4487:
4484:
4482:
4479:
4477:
4474:
4472:
4469:
4467:
4464:
4463:
4461:
4459:
4455:
4449:
4446:
4444:
4443:Grid computer
4441:
4437:
4434:
4433:
4432:
4429:
4426:
4423:
4419:
4416:
4414:
4411:
4409:
4406:
4404:
4401:
4399:
4396:
4394:
4391:
4390:
4389:
4386:
4382:
4379:
4377:
4374:
4373:
4372:
4369:
4367:
4364:
4362:
4359:
4357:
4354:
4352:
4349:
4345:
4342:
4340:
4337:
4333:
4330:
4328:
4325:
4322:
4319:
4318:
4317:
4314:
4312:
4309:
4308:
4307:
4304:
4303:
4301:
4299:
4295:
4289:
4286:
4282:
4279:
4277:
4274:
4272:
4269:
4268:
4267:
4264:
4262:
4259:
4257:
4254:
4253:
4251:
4249:
4245:
4239:
4236:
4234:
4231:
4229:
4226:
4224:
4221:
4219:
4216:
4214:
4211:
4209:
4206:
4205:
4203:
4199:
4193:
4190:
4188:
4185:
4183:
4180:
4178:
4175:
4173:
4170:
4169:
4167:
4163:
4157:
4154:
4152:
4149:
4147:
4144:
4142:
4139:
4137:
4134:
4132:
4129:
4127:
4124:
4122:
4119:
4117:
4114:
4113:
4111:
4107:
4101:
4098:
4095:
4092:
4090:
4087:
4085:
4082:
4079:
4076:
4074:
4071:
4068:
4065:
4063:
4060:
4059:
4057:
4055:
4051:
4045:
4042:
4040:
4037:
4035:
4032:
4030:
4027:
4025:
4022:
4020:
4017:
4015:
4012:
4010:
4007:
4006:
4004:
4000:
3994:
3991:
3989:
3986:
3984:
3981:
3979:
3976:
3974:
3971:
3969:
3966:
3964:
3961:
3959:
3956:
3954:
3951:
3949:
3946:
3945:
3943:
3939:
3935:
3928:
3923:
3921:
3916:
3914:
3909:
3908:
3905:
3893:
3890:
3888:
3885:
3883:
3880:
3878:
3875:
3873:
3870:
3868:
3865:
3863:
3860:
3858:
3855:
3853:
3850:
3849:
3847:
3843:
3836:
3833:
3831:
3828:
3826:
3823:
3821:
3818:
3816:
3813:
3811:
3808:
3806:
3803:
3802:
3800:
3798:
3792:
3782:
3779:
3777:
3774:
3772:
3769:
3767:
3764:
3762:
3759:
3755:
3752:
3750:
3747:
3745:
3742:
3741:
3740:
3737:
3736:
3734:
3732:
3728:
3722:
3719:
3715:
3712:
3710:
3707:
3706:
3705:
3702:
3698:
3695:
3694:
3693:
3690:
3688:
3685:
3683:
3682:Demultiplexer
3680:
3678:
3675:
3674:
3672:
3670:
3666:
3660:
3657:
3655:
3652:
3649:
3647:
3644:
3642:
3639:
3637:
3634:
3632:
3629:
3628:
3626:
3624:
3620:
3614:
3611:
3609:
3606:
3604:
3603:Memory buffer
3601:
3599:
3598:Register file
3596:
3594:
3591:
3589:
3586:
3584:
3581:
3580:
3578:
3576:
3572:
3564:
3561:
3559:
3556:
3555:
3554:
3551:
3549:
3546:
3544:
3541:
3539:
3538:Combinational
3536:
3535:
3533:
3531:
3527:
3521:
3518:
3514:
3511:
3510:
3508:
3505:
3503:
3500:
3498:
3495:
3490:
3487:
3485:
3482:
3481:
3479:
3476:
3473:
3470:
3467:
3464:
3461:
3458:
3457:
3455:
3453:
3447:
3441:
3438:
3436:
3433:
3431:
3428:
3426:
3423:
3419:
3416:
3414:
3411:
3409:
3406:
3404:
3401:
3399:
3396:
3394:
3391:
3390:
3389:
3386:
3384:
3381:
3380:
3378:
3374:
3368:
3365:
3363:
3360:
3358:
3355:
3353:
3350:
3349:
3347:
3343:
3335:
3332:
3331:
3330:
3327:
3325:
3322:
3320:
3317:
3315:
3312:
3310:
3307:
3305:
3302:
3300:
3297:
3295:
3292:
3290:
3287:
3285:
3282:
3280:
3277:
3275:
3272:
3270:
3267:
3265:
3262:
3260:
3257:
3256:
3254:
3252:
3248:
3238:
3235:
3233:
3230:
3228:
3225:
3222:
3219:
3216:
3213:
3210:
3207:
3204:
3201:
3199:
3196:
3193:
3190:
3188:
3185:
3183:
3180:
3179:
3177:
3175:
3169:
3162:
3159:
3157:
3154:
3151:
3148:
3145:
3142:
3141:
3139:
3133:
3127:
3124:
3122:
3119:
3117:
3114:
3112:
3109:
3107:
3104:
3102:
3099:
3097:
3094:
3093:
3091:
3087:
3080:
3077:
3074:
3071:
3068:
3065:
3063:
3060:
3058:
3055:
3053:
3050:
3048:
3045:
3043:
3040:
3038:
3035:
3033:
3030:
3028:
3025:
3023:
3020:
3018:
3015:
3011:
3008:
3007:
3005:
3002:
2999:
2996:
2995:
2993:
2991:
2987:
2981:
2978:
2976:
2973:
2970:
2967:
2964:
2961:
2958:
2955:
2952:
2949:
2946:
2943:
2938:
2935:
2934:
2932:
2929:
2927:
2924:
2923:
2921:
2919:
2913:
2901:
2898:
2897:
2896:
2893:
2891:
2888:
2884:
2881:
2879:
2876:
2874:
2871:
2869:
2866:
2865:
2864:
2861:
2859:
2856:
2855:
2853:
2851:
2847:
2841:
2838:
2836:
2833:
2831:
2828:
2824:
2821:
2819:
2816:
2815:
2814:
2811:
2809:
2806:
2805:
2803:
2801:
2797:
2791:
2788:
2786:
2783:
2779:
2776:
2775:
2774:
2771:
2767:
2764:
2762:
2759:
2758:
2757:
2754:
2750:
2747:
2745:
2742:
2741:
2740:
2737:
2735:
2732:
2728:
2725:
2723:
2720:
2719:
2718:
2715:
2714:
2712:
2708:
2705:
2703:
2699:
2689:
2686:
2684:
2681:
2680:
2678:
2676:
2672:
2666:
2663:
2661:
2658:
2654:
2651:
2649:
2646:
2645:
2644:
2641:
2639:
2638:Scoreboarding
2636:
2635:
2633:
2631:
2627:
2621:
2620:False sharing
2618:
2616:
2613:
2611:
2608:
2606:
2603:
2602:
2600:
2598:
2594:
2588:
2585:
2583:
2580:
2578:
2575:
2574:
2572:
2570:
2566:
2563:
2561:
2557:
2547:
2544:
2542:
2539:
2537:
2534:
2531:
2527:
2524:
2522:
2519:
2517:
2514:
2512:
2509:
2508:
2506:
2504:
2501:
2499:
2496:
2494:
2491:
2489:
2486:
2484:
2481:
2479:
2476:
2474:
2471:
2469:
2466:
2464:
2461:
2459:
2456:
2454:
2451:
2449:
2446:
2442:
2439:
2437:
2434:
2432:
2429:
2428:
2426:
2424:
2421:
2419:
2416:
2414:
2413:Stanford MIPS
2411:
2409:
2406:
2404:
2401:
2399:
2396:
2394:
2391:
2389:
2386:
2385:
2383:
2377:
2369:
2366:
2365:
2364:
2361:
2359:
2356:
2354:
2351:
2349:
2346:
2344:
2341:
2339:
2336:
2334:
2331:
2327:
2324:
2323:
2322:
2319:
2315:
2312:
2311:
2310:
2307:
2305:
2302:
2300:
2297:
2295:
2292:
2290:
2287:
2286:
2284:
2280:
2277:
2275:
2274:architectures
2269:
2263:
2260:
2258:
2255:
2253:
2250:
2248:
2245:
2243:
2242:Heterogeneous
2240:
2236:
2233:
2231:
2228:
2227:
2226:
2223:
2221:
2218:
2214:
2211:
2209:
2206:
2204:
2201:
2199:
2196:
2195:
2194:
2193:Memory access
2191:
2189:
2186:
2184:
2181:
2179:
2176:
2174:
2171:
2167:
2164:
2163:
2162:
2159:
2157:
2154:
2152:
2149:
2148:
2146:
2144:
2140:
2132:
2129:
2127:
2126:Random-access
2124:
2122:
2119:
2117:
2114:
2113:
2112:
2109:
2107:
2106:Stack machine
2104:
2102:
2099:
2095:
2092:
2090:
2087:
2085:
2082:
2080:
2077:
2075:
2072:
2070:
2067:
2065:
2062:
2060:
2057:
2056:
2055:
2052:
2048:
2045:
2043:
2040:
2038:
2035:
2033:
2030:
2028:
2025:
2023:
2022:with datapath
2020:
2019:
2018:
2015:
2013:
2010:
2008:
2005:
2004:
2002:
2000:
1996:
1992:
1985:
1980:
1978:
1973:
1971:
1966:
1965:
1962:
1950:
1942:
1940:
1932:
1930:
1922:
1921:
1918:
1912:
1909:
1907:
1904:
1902:
1899:
1897:
1894:
1892:
1889:
1887:
1884:
1882:
1879:
1877:
1874:
1872:
1869:
1867:
1864:
1862:
1859:
1857:
1854:
1852:
1849:
1847:
1844:
1842:
1839:
1837:
1834:
1832:
1829:
1827:
1824:
1822:
1819:
1817:
1814:
1813:
1811:
1807:
1801:
1798:
1796:
1793:
1791:
1788:
1786:
1785:Mixed reality
1783:
1781:
1778:
1776:
1773:
1771:
1768:
1766:
1763:
1762:
1760:
1758:
1754:
1748:
1745:
1743:
1740:
1738:
1735:
1733:
1730:
1728:
1725:
1724:
1722:
1720:
1716:
1710:
1707:
1705:
1702:
1700:
1697:
1695:
1692:
1690:
1687:
1685:
1682:
1680:
1677:
1675:
1672:
1671:
1669:
1667:
1663:
1657:
1654:
1652:
1649:
1647:
1644:
1642:
1639:
1637:
1634:
1633:
1631:
1629:
1625:
1619:
1618:Accessibility
1616:
1614:
1613:Visualization
1611:
1609:
1606:
1604:
1601:
1599:
1596:
1595:
1593:
1591:
1587:
1581:
1578:
1576:
1573:
1571:
1568:
1566:
1563:
1561:
1558:
1556:
1553:
1551:
1548:
1546:
1543:
1541:
1538:
1537:
1535:
1533:
1529:
1523:
1520:
1518:
1515:
1513:
1510:
1508:
1505:
1503:
1500:
1498:
1495:
1493:
1490:
1488:
1485:
1483:
1480:
1478:
1475:
1473:
1470:
1468:
1465:
1463:
1460:
1458:
1455:
1454:
1452:
1450:
1446:
1440:
1437:
1435:
1432:
1430:
1427:
1425:
1422:
1420:
1417:
1415:
1412:
1410:
1407:
1405:
1402:
1401:
1399:
1397:
1392:
1386:
1383:
1381:
1378:
1376:
1373:
1371:
1368:
1366:
1363:
1362:
1360:
1358:
1354:
1348:
1345:
1343:
1340:
1338:
1335:
1333:
1330:
1328:
1325:
1323:
1320:
1318:
1315:
1314:
1312:
1310:
1306:
1300:
1297:
1295:
1292:
1290:
1287:
1285:
1282:
1280:
1277:
1275:
1272:
1270:
1267:
1265:
1262:
1260:
1257:
1255:
1252:
1251:
1249:
1247:
1243:
1237:
1234:
1232:
1229:
1227:
1224:
1222:
1219:
1217:
1214:
1212:
1209:
1207:
1204:
1202:
1199:
1197:
1194:
1192:
1189:
1188:
1186:
1184:
1180:
1176:
1170:
1167:
1165:
1162:
1160:
1157:
1155:
1152:
1150:
1147:
1146:
1144:
1140:
1134:
1131:
1129:
1126:
1124:
1121:
1119:
1116:
1114:
1111:
1109:
1106:
1105:
1103:
1101:
1097:
1091:
1088:
1086:
1083:
1081:
1080:Dependability
1078:
1076:
1073:
1071:
1068:
1067:
1065:
1061:
1055:
1051:
1048:
1046:
1043:
1041:
1038:
1036:
1033:
1031:
1028:
1026:
1023:
1021:
1018:
1016:
1013:
1011:
1008:
1006:
1003:
1002:
1000:
998:
994:
989:
983:
979:
972:
967:
965:
960:
958:
953:
952:
949:
942:
939:
936:
932:
929:
928:
912:
905:
899:
895:
885:
882:
880:
877:
875:
872:
871:
865:
862:
857:
855:
850:
841:
839:
835:
832:
828:
825:
821:
820:UltraSPARC T2
818:
814:
810:
806:
802:
798:
794:
790:
786:
783:
779:
776:
772:
768:
764:
759:
755:
753:
739:
732:
721:
714:
709:
692:
681:
674:
669:
652:
639:
638:
637:
636:For example:
634:
632:
628:
622:
612:
608:
595:
590:
581:
576:
575:
574:
573:For example:
571:
569:
565:
561:
555:
545:
543:
539:
534:
530:
526:
524:
510:
503:
498:
485:
480:
471:
466:
457:
450:
445:
436:
429:
424:
409:
408:
407:
406:For example:
404:
402:
390:
375:
373:
369:
363:
360:
356:
352:
348:
344:
339:
337:
330:Disadvantages
327:
325:
315:
313:
312:
307:
302:
300:
296:
292:
288:
278:
276:
272:
268:
264:
260:
251:
238:
235:
220:
217:
209:
199:
195:
191:
185:
184:
179:This article
177:
168:
167:
158:
155:
147:
136:
133:
129:
126:
122:
119:
115:
112:
108:
105: –
104:
100:
99:Find sources:
93:
89:
83:
82:
77:This article
75:
71:
66:
65:
60:
58:
51:
50:
45:
44:
39:
34:
25:
24:
19:
4201:Coordination
4131:Amdahl's law
4067:Simultaneous
4053:
3892:Chip carrier
3830:Clock gating
3749:Mixed-signal
3646:Write buffer
3623:Control unit
3435:Clock signal
3174:accelerators
3156:Cypress PSoC
2813:Simultaneous
2799:
2630:Out-of-order
2262:Neuromorphic
2143:Architecture
2101:Belt machine
2094:Zeno machine
2027:Hierarchical
1881:Cyberwarfare
1650:
1540:Cryptography
911:the original
898:
858:
851:
847:
760:
756:
749:
742:from thread
737:
730:
724:from thread
719:
712:
703:from thread
695:from thread
690:
684:from thread
679:
672:
663:from thread
655:from thread
650:
635:
624:
609:
605:
593:
579:
572:
557:
535:
531:
527:
520:
513:from thread
508:
501:
492:from thread
483:
469:
460:from thread
455:
448:
439:from thread
434:
427:
418:from thread
405:
401:ready-to-run
397:
364:
340:
333:
324:cache misses
321:
309:
305:
303:
284:
262:
256:
230:
212:
206:October 2010
203:
180:
150:
144:October 2009
141:
131:
124:
117:
110:
98:
86:Please help
81:verification
78:
54:
47:
41:
40:Please help
37:
4637:Scalability
4398:distributed
4281:Concurrency
4248:Programming
4089:Cooperative
4078:Speculative
4014:Instruction
3677:Multiplexer
3641:Data buffer
3352:Single-core
3324:bit slicing
3182:Coprocessor
3037:Coprocessor
2918:performance
2840:Cooperative
2830:Speculative
2790:Distributed
2749:Superscalar
2734:Instruction
2702:Parallelism
2675:Speculative
2507:System/3x0
2379:Instruction
2156:Von Neumann
2069:Post–Turing
1891:Video games
1871:Digital art
1628:Concurrency
1497:Data mining
1409:Probability
1149:Interpreter
874:Async/await
758:processed.
4676:Categories
4642:Starvation
4381:asymmetric
4116:PRAM model
4084:Preemptive
3797:management
3692:Multiplier
3553:Logic gate
3543:Sequential
3450:Functional
3430:Clock rate
3403:Data cache
3376:Components
3357:Multi-core
3345:Core count
2835:Preemptive
2739:Pipelining
2722:Bit-serial
2665:Wide-issue
2610:Structural
2532:Tilera ISA
2498:MicroBlaze
2468:ETRAX CRIS
2363:Comparison
2208:Load–store
2188:Endianness
1949:Glossaries
1821:E-commerce
1414:Statistics
1357:Algorithms
1154:Middleware
1010:Peripheral
890:References
602:is issued.
588:is issued.
568:preemptive
517:is issued.
496:is issued.
443:is issued.
422:is issued.
318:Advantages
190:improve it
114:newspapers
43:improve it
4376:symmetric
4121:PEM model
3731:Circuitry
3651:Microcode
3575:Registers
3418:coherence
3393:CPU cache
3251:Word size
2916:Processor
2560:Execution
2463:DEC Alpha
2441:Power ISA
2257:Cognitive
2064:Universal
1770:Rendering
1765:Animation
1396:computing
1347:Semantics
1045:Processor
834:Bulldozer
403:threads.
194:verifying
49:talk page
4607:Deadlock
4595:Problems
4561:pthreads
4541:OpenHMPP
4466:Ateji PX
4427:computer
4298:Hardware
4165:Elements
4151:Slowdown
4062:Temporal
4044:Pipeline
3669:Datapath
3362:Manycore
3334:variable
3172:Hardware
2808:Temporal
2488:OpenRISC
2183:Cellular
2173:Dataflow
2166:modified
1929:Category
1757:Graphics
1532:Security
1201:Compiler
1100:Networks
997:Hardware
868:See also
564:pipeline
287:paradigm
281:Overview
4566:RaftLib
4546:OpenACC
4521:GPUOpen
4511:C++ AMP
4486:Charm++
4228:Barrier
4172:Process
4156:Speedup
3941:General
3845:Related
3776:Quantum
3766:Digital
3761:Boolean
3659:Counter
3558:Quantum
3319:512-bit
3314:256-bit
3309:128-bit
3152:(MPSoC)
3137:on chip
3135:Systems
2953:(FLOPS)
2766:Process
2615:Control
2597:Hazards
2483:Itanium
2478:Unicore
2436:PowerPC
2161:Harvard
2121:Pointer
2116:Counter
2074:Quantum
1939:Outline
765:(later
359:AltiVec
188:Please
128:scholar
4659:
4536:OpenCL
4531:OpenMP
4476:Chapel
4393:shared
4388:Memory
4323:(SIMT)
4266:Models
4177:Thread
4109:Theory
4080:(SpMT)
4034:Memory
4019:Thread
4002:Levels
3781:Switch
3771:Analog
3509:(IMC)
3480:(MMU)
3329:others
3304:64-bit
3299:48-bit
3294:32-bit
3289:24-bit
3284:16-bit
3279:15-bit
3274:12-bit
3111:Mobile
3027:Stream
3022:Barrel
3017:Vector
3006:(GPU)
2965:(SUPS)
2933:(IPC)
2785:Memory
2778:Vector
2761:Thread
2744:Scalar
2546:Others
2493:RISC-V
2458:SuperH
2427:Power
2423:MIPS-X
2398:PDP-11
2247:Fabric
1999:Models
829:, and
803:, IBM
801:POWER9
797:POWER8
793:POWER7
789:POWER6
785:POWER5
767:Compaq
710:Cycle
670:Cycle
640:Cycle
591:Cycle
577:Cycle
499:Cycle
481:Cycle
467:Cycle
446:Cycle
425:Cycle
410:Cycle
130:
123:
116:
109:
101:
4506:Dryad
4471:Boost
4192:Array
4182:Fiber
4096:(CMT)
4069:(SMT)
3983:GPGPU
3837:(PPW)
3795:Power
3687:Adder
3563:Array
3530:Logic
3491:(TLB)
3474:(FPU)
3468:(AGU)
3462:(ALU)
3452:units
3388:Cache
3269:8-bit
3264:4-bit
3259:1-bit
3223:(TPU)
3217:(DSP)
3211:(PPU)
3205:(VPU)
3194:(GPU)
3163:(NoC)
3146:(SoC)
3081:(PoP)
3075:(SiP)
3069:(MCM)
3010:GPGPU
3000:(CPU)
2990:Types
2971:(PPW)
2959:(TPS)
2947:(IPS)
2939:(CPI)
2710:Level
2521:S/390
2516:S/370
2511:S/360
2453:SPARC
2431:POWER
2314:TRIPS
2282:Types
1342:Logic
1183:tools
914:(PDF)
907:(PDF)
775:Intel
343:Intel
135:JSTOR
121:books
4571:ROCm
4501:CUDA
4491:Cilk
4458:APIs
4418:COMA
4413:NUMA
4344:MIMD
4339:MISD
4316:SIMD
4311:SISD
4039:Loop
4029:Data
4024:Task
3815:ACPI
3548:Glue
3440:FIFO
3383:Core
3121:ASIP
3062:CPLD
3057:FPOA
3052:FPGA
3047:ASIC
2900:SPMD
2895:MIMD
2890:MISD
2883:SWAR
2863:SIMD
2858:SISD
2773:Data
2756:Task
2727:Word
2473:M32R
2418:MIPS
2381:sets
2348:ZISC
2343:NISC
2338:OISC
2333:MISC
2326:EPIC
2321:VLIW
2309:EDGE
2299:RISC
2294:CISC
2203:HUMA
2198:NUMA
1181:and
1054:Form
1050:Size
836:and
824:Cray
735:and
648:and
308:and
107:news
4586:ZPL
4581:TBB
4576:UPC
4556:PVM
4526:MPI
4481:HPX
4408:UMA
4009:Bit
3810:APM
3805:PMU
3697:CPU
3654:ROM
3425:Bus
3042:PAL
2717:Bit
2503:LMC
2408:ARM
2403:x86
2393:VAX
935:ACM
854:DMA
838:Zen
831:AMD
827:XMT
813:z15
809:z14
805:z13
782:IBM
771:EV8
763:DEC
740:+ 2
733:+ 1
722:+ 3
715:+ 2
693:+ 1
682:+ 2
675:+ 1
653:+ 1
596:+ 2
582:+ 1
511:+ 1
504:+ 5
486:+ 4
472:+ 3
458:+ 2
451:+ 2
437:+ 1
430:+ 1
357:or
355:MMX
257:In
192:by
90:by
4678::
3744:3D
1052:/
933:,
822:,
815:,
780:,
769:)
314:.
277:.
261:,
52:.
3926:e
3919:t
3912:v
1983:e
1976:t
1969:v
990:.
970:e
963:t
956:v
811:/
807:/
799:/
795:/
791:/
787:/
744:C
738:m
731:m
726:A
720:j
713:i
705:C
701:m
697:B
691:k
686:A
680:j
673:i
665:B
661:k
657:A
651:j
646:j
642:i
600:C
594:i
586:B
580:i
515:B
509:k
502:i
494:B
490:k
484:i
478:.
476:B
470:i
462:A
456:j
449:i
441:A
435:j
428:i
420:A
416:j
412:i
237:)
231:(
219:)
213:(
208:)
204:(
186:.
157:)
151:(
146:)
142:(
132:·
125:·
118:·
111:·
84:.
59:)
55:(
20:.
Text is available under the Creative Commons Attribution-ShareAlike License. Additional terms may apply.