261:
4674:
1943:
1953:
81:
1963:
183:
40:
337:, 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.
621:
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
543:
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
859:
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
409:
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
768:
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
539:
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
640:. 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
372:
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.
874:
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.
312:. 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.
617:
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.
349:(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.
376:
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
410:
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
577:. 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
540:
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.
360:, 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
536:, 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.
98:
53:
4000:
3027:
644:, this type of multithreading tries to exploit parallelism available across multiple threads to decrease the waste associated with unused issue slots.
1999:
145:
117:
914:
3138:
2321:
4090:
2840:
870:
If the multithreading scheme replicates all of the software-visible state, including privileged control registers and TLBs, then it enables
124:
3942:
2118:
2997:
2563:
2380:
951:
59:
3351:
979:
555:
for interrupts. Such schemes can be considered a type of block multithreading among the user program thread and the interrupt threads.
131:
2343:
2992:
3064:
113:
3346:
1696:
581:
multitasking used in operating systems; an analogy would be that the time slice given to each active thread is one CPU cycle.
1721:
941:
4111:
4338:
3761:
2885:
2148:
1992:
1572:
4361:
3771:
2912:
1726:
998:
945:
863:
Another area of research is what type of events should cause a thread switch: cache misses, inter-thread communication,
4250:
2039:
1231:
860:
thread scheduler might be implemented totally in software, totally in hardware, or as a hardware/software combination.
4106:
4356:
4333:
3079:
2907:
2880:
2259:
1878:
1706:
1236:
382:
244:
226:
164:
67:
208:
4699:
3935:
3894:
3457:
2350:
2316:
2311:
2230:
2195:
1966:
1060:
138:
4704:
4328:
4143:
3869:
3766:
3167:
3074:
2875:
2096:
1985:
1354:
200:
4435:
4349:
4298:
2895:
2614:
2049:
1645:
1607:
1264:
972:
193:
102:
17:
4659:
4493:
4344:
4031:
3069:
2917:
2890:
2751:
2365:
2326:
2183:
1787:
1764:
1494:
1484:
844:
773:
641:
301:
4719:
3506:
3268:
2744:
2705:
2360:
2355:
2289:
2101:
1868:
1456:
1364:
1269:
1045:
1030:
346:
4714:
4678:
4624:
4084:
3928:
3133:
2830:
2528:
2225:
1956:
1691:
1189:
631:
4603:
4398:
4283:
4245:
4095:
3985:
3783:
3430:
2847:
2338:
2306:
2076:
2064:
2044:
1928:
1577:
894:
788:
533:
357:
622:
resources such as caches and TLBs need to be larger to avoid thrashing between the different threads.
544:
of software changes needed within the application and the operating system to support multithreading.
4619:
4598:
4543:
4430:
4420:
4393:
4255:
3874:
3837:
3827:
2215:
1946:
1873:
1848:
1711:
1359:
965:
921:
378:
285:
4709:
4573:
4199:
4138:
4051:
3889:
3296:
3232:
3209:
3059:
3021:
2857:
2807:
2802:
2279:
2173:
2081:
1797:
1630:
1216:
1085:
823:
819:
815:
4634:
4629:
4488:
4079:
3842:
3625:
3519:
3483:
3400:
3384:
3226:
3015:
2974:
2962:
2825:
2739:
2660:
2425:
2086:
2029:
1858:
1792:
1683:
1499:
1159:
848:
762:
399:
345:
Multiple threads can interfere with each other when sharing hardware resources such as caches or
277:
204:
91:
4373:
4305:
4209:
4101:
4056:
3648:
3620:
3530:
3495:
3244:
3238:
3220:
2954:
2948:
2852:
2756:
2647:
2586:
2448:
2091:
1923:
1754:
1635:
1402:
1392:
1387:
578:
309:
4465:
4425:
4378:
4368:
4163:
4026:
3965:
3822:
3731:
3477:
3189:
3007:
2766:
2734:
2692:
2604:
2405:
2220:
2210:
2200:
2190:
2160:
2143:
2008:
1893:
1863:
1853:
1749:
1663:
1539:
1479:
1446:
1436:
1319:
1284:
1274:
1211:
1080:
1055:
1050:
1015:
637:
365:
269:
4405:
4293:
4288:
4278:
4265:
4061:
3852:
3788:
3374:
3096:
2986:
2933:
2465:
2178:
2034:
2016:
1653:
1625:
1597:
1592:
1421:
1397:
1349:
1332:
1327:
1309:
1299:
1294:
1256:
1206:
1201:
1118:
1064:
864:
574:
305:
281:
8:
4568:
4523:
4323:
4189:
3899:
3884:
3704:
3555:
3537:
3501:
3489:
3143:
3090:
2867:
2783:
2665:
2520:
2415:
2274:
1918:
1843:
1759:
1744:
1509:
1289:
1246:
1241:
1138:
1128:
1100:
4593:
4442:
4415:
4240:
4204:
4194:
4153:
3995:
3975:
3970:
3951:
3756:
3748:
3600:
3575:
3379:
3254:
2778:
2719:
2599:
2331:
2059:
1883:
1782:
1658:
1615:
1524:
1466:
1451:
1441:
1226:
1025:
28:
952:
Operating System | Difference between
Multitasking, Multithreading and Multiprocessing
4639:
4315:
4273:
4168:
3709:
3676:
3592:
3524:
3425:
3415:
3405:
3336:
3331:
3326:
3249:
3178:
3084:
3044:
2677:
2627:
2577:
2553:
2435:
2375:
2370:
2252:
2168:
1903:
1833:
1812:
1774:
1582:
1549:
1529:
1221:
1133:
1007:
361:
765:" is used to denote when instructions from only one thread can be issued at a time.
4649:
4448:
4383:
4230:
4046:
4041:
4036:
4005:
3879:
3812:
3798:
3653:
3560:
3514:
3321:
3316:
3311:
3306:
3301:
3291:
3161:
3128:
3039:
3034:
2943:
2795:
2790:
2773:
2761:
2700:
2264:
2242:
2128:
2106:
2024:
1736:
1620:
1587:
1382:
1304:
1193:
1179:
1174:
1123:
1110:
1035:
988:
827:
564:
411:
4513:
4453:
4388:
4235:
4225:
4158:
4148:
3990:
3980:
3793:
3778:
3726:
3630:
3605:
3442:
3435:
3286:
3281:
3276:
3215:
3123:
3113:
2835:
2670:
2622:
2385:
2269:
2237:
2138:
2133:
2054:
1807:
1701:
1673:
1567:
1519:
1504:
1489:
1344:
1339:
1279:
1169:
1143:
1095:
1040:
889:
871:
570:
548:
321:
334:
4644:
4460:
4117:
4010:
3904:
3738:
3721:
3714:
3610:
3467:
3204:
3118:
3049:
2632:
2594:
2543:
2538:
2533:
2247:
2071:
1913:
1817:
1716:
1562:
1534:
552:
4693:
4533:
4410:
3699:
3615:
2655:
2637:
2430:
2123:
1802:
1090:
830:
2558:
4133:
3909:
3847:
3663:
3640:
3452:
3173:
2111:
1898:
1557:
4654:
3694:
3658:
3369:
3341:
3199:
3054:
1977:
1888:
1514:
1426:
884:
781:
260:
3580:
3570:
3565:
3547:
3447:
3420:
2682:
2515:
2485:
2205:
1908:
1838:
1431:
1164:
1020:
264:
A process with two threads of execution, running on a single processor
257:
Ability of a CPU to provide multiple threads of execution concurrently
4528:
4503:
3920:
3671:
3668:
3410:
2480:
2458:
1413:
1374:
761:
To distinguish the other types of multithreading from SMT, the term "
551:
and embedded processors have multiple register banks to allow quick
211:. Statements consisting only of original research should be removed.
80:
4578:
4558:
4483:
3686:
2505:
1474:
957:
837:
297:
4583:
4563:
4538:
4173:
2495:
2453:
532:
Conceptually, it is similar to cooperative multi-tasking used in
475:
is issued, which is a load instruction that misses in all caches.
369:
4553:
4548:
2510:
2475:
2440:
811:
807:
803:
799:
795:
777:
385:. Thread scheduling is also a major problem in multithreading.
304:
have stalled since the late 1990s. This allowed the concept of
2968:
2500:
2470:
785:
353:
569:
The purpose of Fine grained multithreading is to remove all
4588:
4518:
4508:
3832:
2980:
2900:
2490:
834:
915:"Intel Hyper-Threading Technology, Technical User's Guide"
4498:
4475:
2420:
2410:
841:
792:
948:, March 2003, by Theo Ungerer, Borut Robi and Jurij Silc
393:
300:
has become more popular as efforts to further exploit
636:
The most advanced type of multithreading applies to
942:
A Survey of
Processors with Explicit Multithreading
105:. Unsourced material may be challenged and removed.
315:Two major techniques for throughput computing are
4691:
404:
381:often parallel the software techniques used for
308:to re-emerge from the more specialized field of
485:: thread scheduler invoked, switches to thread
625:
558:
3936:
1993:
997:Note: This template roughly follows the 2012
973:
2998:Computer performance by orders of magnitude
854:
114:"Multithreading" computer architecture
68:Learn how and when to remove these messages
3943:
3929:
2007:
2000:
1986:
980:
966:
388:
245:Learn how and when to remove this message
227:Learn how and when to remove this message
165:Learn how and when to remove this message
259:
14:
4692:
3950:
1697:Knowledge representation and reasoning
356:claims up to 30% improvement with its
3924:
1981:
1722:Philosophy of artificial intelligence
961:
2969:Floating-point operations per second
1041:Energy consumption (Green computing)
987:
176:
103:adding citations to reliable sources
74:
33:
1727:Distributed artificial intelligence
999:ACM Computing Classification System
394:Interleaved/Temporal multithreading
24:
1232:Integrated development environment
25:
4731:
1707:Automated planning and scheduling
1237:Software configuration management
935:
49:This article has multiple issues.
4673:
4672:
3895:Semiconductor device fabrication
1961:
1951:
1942:
1941:
340:
181:
79:
38:
4144:Analysis of parallel algorithms
3870:History of general-purpose CPUs
2097:Nondeterministic Turing machine
1952:
1355:Computational complexity theory
90:needs additional citations for
57:or discuss these issues on the
2050:Deterministic finite automaton
1139:Network performance evaluation
907:
757:are all simultaneously issued.
718:are all simultaneously issued.
13:
1:
4091:Simultaneous and heterogenous
2841:Simultaneous and heterogenous
1510:Multimedia information system
1495:Geographic information system
1485:Enterprise information system
1074:Computer systems organization
900:
642:instruction-level parallelism
609:: an instruction from thread
595:: an instruction from thread
405:Coarse-grained multithreading
347:translation lookaside buffers
328:
302:instruction-level parallelism
280:(CPU) (or a single core in a
27:For threads in software, see
4679:Category: Parallel computing
3525:Integrated memory controller
3507:Translation lookaside buffer
2706:Memory dependence prediction
2149:Random-access stored program
2102:Probabilistic Turing machine
1869:Computational social science
1457:Theoretical computer science
1270:Software development process
1046:Electronic design automation
1031:Very Large Scale Integration
954:GeeksforGeeks, 6 Sept. 2018.
920:. p. 13. Archived from
7:
2981:Synaptic updates per second
1692:Natural language processing
1480:Information storage systems
878:
632:Simultaneous multithreading
626:Simultaneous multithreading
559:Fine grained multithreading
534:real-time operating systems
352:Overall efficiency varies;
291:
207:the claims made and adding
10:
4736:
3986:High-performance computing
3385:Heterogeneous architecture
2307:Orthogonal instruction set
2077:Alternating Turing machine
2065:Quantum cellular automaton
1608:Human–computer interaction
1578:Intrusion detection system
1490:Social information systems
1475:Database management system
895:Speculative multithreading
789:Hyper-Threading Technology
678:are simultaneously issued.
629:
573:stalls from the execution
562:
397:
358:Hyper-Threading Technology
333:If a thread gets a lot of
26:
4668:
4620:Automatic parallelization
4612:
4474:
4314:
4264:
4256:Application checkpointing
4218:
4182:
4126:
4070:
4019:
3958:
3875:Microprocessor chronology
3862:
3838:Dynamic frequency scaling
3811:
3747:
3685:
3639:
3591:
3546:
3466:
3393:
3362:
3267:
3188:
3152:
3106:
3006:
2993:Cache performance metrics
2932:
2866:
2816:
2727:
2718:
2691:
2646:
2613:
2585:
2576:
2396:
2299:
2288:
2159:
2015:
1937:
1874:Computational engineering
1849:Computational mathematics
1826:
1773:
1735:
1682:
1644:
1606:
1548:
1465:
1411:
1373:
1318:
1255:
1188:
1152:
1109:
1073:
1006:
995:
3890:Hardware security module
3233:Digital signal processor
3210:Graphics processing unit
3022:Graphics processing unit
1884:Computational healthcare
1879:Differentiable computing
1798:Graphics processing unit
1217:Domain-specific language
1086:Computational complexity
855:Implementation specifics
772:Implementations include
4700:Central processing unit
4635:Embarrassingly parallel
4630:Deterministic algorithm
3843:Dynamic voltage scaling
3626:Memory address register
3520:Branch target predictor
3484:Address generation unit
3227:Physics processing unit
3016:Central processing unit
2975:Transactions per second
2963:Instructions per second
2886:Array processing (SIMT)
2030:Stored-program computer
1859:Computational chemistry
1793:Photograph manipulation
1684:Artificial intelligence
1500:Decision support system
763:temporal multithreading
400:Temporal multithreading
389:Types of multithreading
278:central processing unit
4705:Instruction processing
4350:Associative processing
4306:Non-blocking algorithm
4112:Clustered multi-thread
3649:Hardwired control unit
3531:Memory management unit
3496:Memory management unit
3245:Secure cryptoprocessor
3239:Tensor Processing Unit
3221:Vision processing unit
2955:Cycles per instruction
2949:Instructions per cycle
2896:Associative processing
2587:Instruction pipelining
2009:Processor technologies
1924:Educational technology
1755:Reinforcement learning
1505:Process control system
1403:Computational geometry
1393:Algorithmic efficiency
1388:Analysis of algorithms
1036:Systems on Chip (SoCs)
638:superscalar processors
310:transaction processing
284:) to provide multiple
265:
4466:Hardware acceleration
4379:Superscalar processor
4369:Dataflow architecture
3966:Distributed computing
3732:Sum-addressed decoder
3478:Arithmetic logic unit
2605:Classic RISC pipeline
2559:Epiphany architecture
2406:Motorola 68000 series
1894:Electronic publishing
1864:Computational biology
1854:Computational physics
1750:Unsupervised learning
1664:Distributed computing
1540:Information retrieval
1447:Mathematical analysis
1437:Mathematical software
1320:Theory of computation
1285:Software construction
1275:Requirements analysis
1153:Software organization
1081:Computer architecture
1051:Hardware acceleration
1016:Printed circuit board
383:computer multitasking
270:computer architecture
263:
4345:Pipelined processing
4294:Explicit parallelism
4289:Implicit parallelism
4279:Dataflow programming
3853:Performance per watt
3431:replacement policies
3097:Package on a package
2987:Performance per watt
2891:Pipelined processing
2661:Tomasulo's algorithm
2466:Clipper architecture
2322:Application-specific
2035:Finite-state machine
1654:Concurrent computing
1626:Ubiquitous computing
1598:Application security
1593:Information security
1422:Discrete mathematics
1398:Randomized algorithm
1350:Computability theory
1328:Model of computation
1300:Software maintenance
1295:Software engineering
1257:Software development
1207:Programming language
1202:Programming paradigm
1119:Network architecture
851:microarchitectures.
306:throughput computing
286:threads of execution
282:multi-core processor
276:is the ability of a
99:improve this article
4720:Threads (computing)
4569:Parallel Extensions
4374:Pipelined processor
3885:Digital electronics
3538:Instruction decoder
3490:Floating-point unit
3144:Soft microprocessor
3091:System in a package
2666:Reservation station
2196:Transport-triggered
1929:Document management
1919:Operations research
1844:Enterprise software
1760:Multi-task learning
1745:Supervised learning
1467:Information systems
1290:Software deployment
1247:Software repository
1101:Real-time computing
296:The multithreading
4715:Parallel computing
4443:Massively parallel
4421:distributed shared
4241:Cache invalidation
4205:Instruction window
3996:Manycore processor
3976:Massively parallel
3971:Parallel computing
3952:Parallel computing
3757:Integrated circuit
3601:Processor register
3255:Baseband processor
2600:Operand forwarding
2060:Cellular automaton
1712:Search methodology
1659:Parallel computing
1616:Interaction design
1525:Computing platform
1452:Numerical analysis
1442:Information theory
1227:Software framework
1190:Software notations
1129:Network components
1026:Integrated circuit
710:, and instruction
266:
192:possibly contains
29:Thread (computing)
4687:
4686:
4640:Parallel slowdown
4274:Stream processing
4164:Karp–Flatt metric
3918:
3917:
3807:
3806:
3426:Instruction cache
3416:Scratchpad memory
3263:
3262:
3250:Network processor
3179:Network on a chip
3134:Ultra-low-voltage
3085:Multi-chip module
2928:
2927:
2714:
2713:
2701:Branch prediction
2678:Register renaming
2572:
2571:
2554:VISC architecture
2376:Quantum computing
2371:VISC architecture
2253:Secondary storage
2169:Microarchitecture
2129:Register machines
1975:
1974:
1904:Electronic voting
1834:Quantum Computing
1827:Applied computing
1813:Image compression
1583:Hardware security
1573:Security services
1530:Digital marketing
1310:Open-source model
1222:Modeling language
1134:Network scheduler
867:completion, etc.
784:(not completed),
739:and instructions
553:context switching
547:Many families of
362:assembly language
255:
254:
247:
237:
236:
229:
194:original research
175:
174:
167:
149:
72:
16:(Redirected from
4727:
4676:
4675:
4650:Software lockout
4449:Computer cluster
4384:Vector processor
4339:Array processing
4324:Flynn's taxonomy
4231:Memory coherence
4006:Computer network
3945:
3938:
3931:
3922:
3921:
3880:Processor design
3772:Power management
3654:Instruction unit
3515:Branch predictor
3464:
3463:
3162:System on a chip
3104:
3103:
2944:Transistor count
2868:Flynn's taxonomy
2725:
2724:
2583:
2582:
2386:Addressing modes
2297:
2296:
2243:Memory hierarchy
2107:Hypercomputation
2025:Abstract machine
2002:
1995:
1988:
1979:
1978:
1965:
1964:
1955:
1954:
1945:
1944:
1765:Cross-validation
1737:Machine learning
1621:Social computing
1588:Network security
1383:Algorithm design
1305:Programming team
1265:Control variable
1242:Software library
1180:Software quality
1175:Operating system
1124:Network protocol
989:Computer science
982:
975:
968:
959:
958:
929:
928:
926:
919:
911:
872:virtual machines
828:Sun Microsystems
756:
752:
745:
738:
734:
727:
717:
713:
709:
705:
698:
694:
687:
677:
673:
670:and instruction
669:
665:
658:
654:
612:
608:
598:
594:
565:Barrel processor
549:microcontrollers
527:
523:
516:
506:
502:
498:
488:
484:
474:
470:
463:
453:
449:
442:
432:
428:
424:
250:
243:
232:
225:
221:
218:
212:
209:inline citations
185:
184:
177:
170:
163:
159:
156:
150:
148:
107:
83:
75:
64:
42:
41:
34:
21:
4735:
4734:
4730:
4729:
4728:
4726:
4725:
4724:
4710:Microprocessors
4690:
4689:
4688:
4683:
4664:
4608:
4514:Coarray Fortran
4470:
4454:Beowulf cluster
4310:
4260:
4251:Synchronization
4236:Cache coherence
4226:Multiprocessing
4214:
4178:
4159:Cost efficiency
4154:Gustafson's law
4122:
4066:
4015:
3991:Multiprocessing
3981:Cloud computing
3954:
3949:
3919:
3914:
3900:Tick–tock model
3858:
3814:
3803:
3743:
3727:Address decoder
3681:
3635:
3631:Program counter
3606:Status register
3587:
3542:
3502:Load–store unit
3469:
3462:
3389:
3358:
3259:
3216:Image processor
3191:
3184:
3154:
3148:
3124:Microcontroller
3114:Embedded system
3102:
3002:
2935:
2924:
2862:
2812:
2710:
2687:
2671:Re-order buffer
2642:
2623:Data dependency
2609:
2568:
2398:
2392:
2291:
2290:Instruction set
2284:
2270:Multiprocessing
2238:Cache hierarchy
2231:Register/memory
2155:
2055:Queue automaton
2011:
2006:
1976:
1971:
1962:
1933:
1914:Word processing
1822:
1808:Virtual reality
1769:
1731:
1702:Computer vision
1678:
1674:Multiprocessing
1640:
1602:
1568:Security hacker
1544:
1520:Digital library
1461:
1412:Mathematics of
1407:
1369:
1345:Automata theory
1340:Formal language
1314:
1280:Software design
1251:
1184:
1170:Virtual machine
1148:
1144:Network service
1105:
1096:Embedded system
1069:
1002:
991:
986:
938:
933:
932:
924:
917:
913:
912:
908:
903:
890:Super-threading
881:
857:
754:
747:
740:
736:
729:
722:
715:
711:
707:
700:
696:
689:
682:
675:
671:
667:
660:
656:
655:: instructions
652:
634:
628:
610:
603:
596:
589:
571:data dependency
567:
561:
525:
518:
511:
504:
500:
493:
486:
479:
472:
465:
458:
451:
444:
437:
430:
426:
422:
407:
402:
396:
391:
364:programs using
343:
331:
322:multiprocessing
294:
258:
251:
240:
239:
238:
233:
222:
216:
213:
198:
186:
182:
171:
160:
154:
151:
108:
106:
96:
84:
43:
39:
32:
23:
22:
15:
12:
11:
5:
4733:
4723:
4722:
4717:
4712:
4707:
4702:
4685:
4684:
4682:
4681:
4669:
4666:
4665:
4663:
4662:
4657:
4652:
4647:
4645:Race condition
4642:
4637:
4632:
4627:
4622:
4616:
4614:
4610:
4609:
4607:
4606:
4601:
4596:
4591:
4586:
4581:
4576:
4571:
4566:
4561:
4556:
4551:
4546:
4541:
4536:
4531:
4526:
4521:
4516:
4511:
4506:
4501:
4496:
4491:
4486:
4480:
4478:
4472:
4471:
4469:
4468:
4463:
4458:
4457:
4456:
4446:
4440:
4439:
4438:
4433:
4428:
4423:
4418:
4413:
4403:
4402:
4401:
4396:
4389:Multiprocessor
4386:
4381:
4376:
4371:
4366:
4365:
4364:
4359:
4354:
4353:
4352:
4347:
4342:
4331:
4320:
4318:
4312:
4311:
4309:
4308:
4303:
4302:
4301:
4296:
4291:
4281:
4276:
4270:
4268:
4262:
4261:
4259:
4258:
4253:
4248:
4243:
4238:
4233:
4228:
4222:
4220:
4216:
4215:
4213:
4212:
4207:
4202:
4197:
4192:
4186:
4184:
4180:
4179:
4177:
4176:
4171:
4166:
4161:
4156:
4151:
4146:
4141:
4136:
4130:
4128:
4124:
4123:
4121:
4120:
4118:Hardware scout
4115:
4109:
4104:
4099:
4093:
4088:
4082:
4076:
4074:
4072:Multithreading
4068:
4067:
4065:
4064:
4059:
4054:
4049:
4044:
4039:
4034:
4029:
4023:
4021:
4017:
4016:
4014:
4013:
4011:Systolic array
4008:
4003:
3998:
3993:
3988:
3983:
3978:
3973:
3968:
3962:
3960:
3956:
3955:
3948:
3947:
3940:
3933:
3925:
3916:
3915:
3913:
3912:
3907:
3905:Pin grid array
3902:
3897:
3892:
3887:
3882:
3877:
3872:
3866:
3864:
3860:
3859:
3857:
3856:
3850:
3845:
3840:
3835:
3830:
3825:
3819:
3817:
3809:
3808:
3805:
3804:
3802:
3801:
3796:
3791:
3786:
3781:
3776:
3775:
3774:
3769:
3764:
3753:
3751:
3745:
3744:
3742:
3741:
3739:Barrel shifter
3736:
3735:
3734:
3729:
3722:Binary decoder
3719:
3718:
3717:
3707:
3702:
3697:
3691:
3689:
3683:
3682:
3680:
3679:
3674:
3666:
3661:
3656:
3651:
3645:
3643:
3637:
3636:
3634:
3633:
3628:
3623:
3618:
3613:
3611:Stack register
3608:
3603:
3597:
3595:
3589:
3588:
3586:
3585:
3584:
3583:
3578:
3568:
3563:
3558:
3552:
3550:
3544:
3543:
3541:
3540:
3535:
3534:
3533:
3522:
3517:
3512:
3511:
3510:
3504:
3493:
3487:
3481:
3474:
3472:
3461:
3460:
3455:
3450:
3445:
3440:
3439:
3438:
3433:
3428:
3423:
3418:
3413:
3403:
3397:
3395:
3391:
3390:
3388:
3387:
3382:
3377:
3372:
3366:
3364:
3360:
3359:
3357:
3356:
3355:
3354:
3344:
3339:
3334:
3329:
3324:
3319:
3314:
3309:
3304:
3299:
3294:
3289:
3284:
3279:
3273:
3271:
3265:
3264:
3261:
3260:
3258:
3257:
3252:
3247:
3242:
3236:
3230:
3224:
3218:
3213:
3207:
3205:AI accelerator
3202:
3196:
3194:
3186:
3185:
3183:
3182:
3176:
3171:
3168:Multiprocessor
3165:
3158:
3156:
3150:
3149:
3147:
3146:
3141:
3136:
3131:
3126:
3121:
3119:Microprocessor
3116:
3110:
3108:
3107:By application
3101:
3100:
3094:
3088:
3082:
3077:
3072:
3067:
3062:
3057:
3052:
3050:Tile processor
3047:
3042:
3037:
3032:
3031:
3030:
3019:
3012:
3010:
3004:
3003:
3001:
3000:
2995:
2990:
2984:
2978:
2972:
2966:
2960:
2959:
2958:
2946:
2940:
2938:
2930:
2929:
2926:
2925:
2923:
2922:
2921:
2920:
2910:
2905:
2904:
2903:
2898:
2893:
2888:
2878:
2872:
2870:
2864:
2863:
2861:
2860:
2855:
2850:
2845:
2844:
2843:
2838:
2836:Hyperthreading
2828:
2822:
2820:
2818:Multithreading
2814:
2813:
2811:
2810:
2805:
2800:
2799:
2798:
2788:
2787:
2786:
2781:
2771:
2770:
2769:
2764:
2754:
2749:
2748:
2747:
2742:
2731:
2729:
2722:
2716:
2715:
2712:
2711:
2709:
2708:
2703:
2697:
2695:
2689:
2688:
2686:
2685:
2680:
2675:
2674:
2673:
2668:
2658:
2652:
2650:
2644:
2643:
2641:
2640:
2635:
2630:
2625:
2619:
2617:
2611:
2610:
2608:
2607:
2602:
2597:
2595:Pipeline stall
2591:
2589:
2580:
2574:
2573:
2570:
2569:
2567:
2566:
2561:
2556:
2551:
2548:
2547:
2546:
2544:z/Architecture
2541:
2536:
2531:
2523:
2518:
2513:
2508:
2503:
2498:
2493:
2488:
2483:
2478:
2473:
2468:
2463:
2462:
2461:
2456:
2451:
2443:
2438:
2433:
2428:
2423:
2418:
2413:
2408:
2402:
2400:
2394:
2393:
2391:
2390:
2389:
2388:
2378:
2373:
2368:
2363:
2358:
2353:
2348:
2347:
2346:
2336:
2335:
2334:
2324:
2319:
2314:
2309:
2303:
2301:
2294:
2286:
2285:
2283:
2282:
2277:
2272:
2267:
2262:
2257:
2256:
2255:
2250:
2248:Virtual memory
2240:
2235:
2234:
2233:
2228:
2223:
2218:
2208:
2203:
2198:
2193:
2188:
2187:
2186:
2176:
2171:
2165:
2163:
2157:
2156:
2154:
2153:
2152:
2151:
2146:
2141:
2136:
2126:
2121:
2116:
2115:
2114:
2109:
2104:
2099:
2094:
2089:
2084:
2079:
2072:Turing machine
2069:
2068:
2067:
2062:
2057:
2052:
2047:
2042:
2032:
2027:
2021:
2019:
2013:
2012:
2005:
2004:
1997:
1990:
1982:
1973:
1972:
1970:
1969:
1959:
1949:
1938:
1935:
1934:
1932:
1931:
1926:
1921:
1916:
1911:
1906:
1901:
1896:
1891:
1886:
1881:
1876:
1871:
1866:
1861:
1856:
1851:
1846:
1841:
1836:
1830:
1828:
1824:
1823:
1821:
1820:
1818:Solid modeling
1815:
1810:
1805:
1800:
1795:
1790:
1785:
1779:
1777:
1771:
1770:
1768:
1767:
1762:
1757:
1752:
1747:
1741:
1739:
1733:
1732:
1730:
1729:
1724:
1719:
1717:Control method
1714:
1709:
1704:
1699:
1694:
1688:
1686:
1680:
1679:
1677:
1676:
1671:
1669:Multithreading
1666:
1661:
1656:
1650:
1648:
1642:
1641:
1639:
1638:
1633:
1628:
1623:
1618:
1612:
1610:
1604:
1603:
1601:
1600:
1595:
1590:
1585:
1580:
1575:
1570:
1565:
1563:Formal methods
1560:
1554:
1552:
1546:
1545:
1543:
1542:
1537:
1535:World Wide Web
1532:
1527:
1522:
1517:
1512:
1507:
1502:
1497:
1492:
1487:
1482:
1477:
1471:
1469:
1463:
1462:
1460:
1459:
1454:
1449:
1444:
1439:
1434:
1429:
1424:
1418:
1416:
1409:
1408:
1406:
1405:
1400:
1395:
1390:
1385:
1379:
1377:
1371:
1370:
1368:
1367:
1362:
1357:
1352:
1347:
1342:
1337:
1336:
1335:
1324:
1322:
1316:
1315:
1313:
1312:
1307:
1302:
1297:
1292:
1287:
1282:
1277:
1272:
1267:
1261:
1259:
1253:
1252:
1250:
1249:
1244:
1239:
1234:
1229:
1224:
1219:
1214:
1209:
1204:
1198:
1196:
1186:
1185:
1183:
1182:
1177:
1172:
1167:
1162:
1156:
1154:
1150:
1149:
1147:
1146:
1141:
1136:
1131:
1126:
1121:
1115:
1113:
1107:
1106:
1104:
1103:
1098:
1093:
1088:
1083:
1077:
1075:
1071:
1070:
1068:
1067:
1058:
1053:
1048:
1043:
1038:
1033:
1028:
1023:
1018:
1012:
1010:
1004:
1003:
996:
993:
992:
985:
984:
977:
970:
962:
956:
955:
949:
937:
936:External links
934:
931:
930:
927:on 2010-08-21.
905:
904:
902:
899:
898:
897:
892:
887:
880:
877:
856:
853:
759:
758:
728:: instruction
719:
699:, instruction
688:: instruction
679:
630:Main article:
627:
624:
615:
614:
600:
563:Main article:
560:
557:
530:
529:
517:: instruction
508:
499:: instruction
490:
476:
464:: instruction
455:
443:: instruction
434:
425:: instruction
406:
403:
398:Main article:
395:
392:
390:
387:
379:multithreading
342:
339:
330:
327:
317:multithreading
293:
290:
274:multithreading
256:
253:
252:
235:
234:
189:
187:
180:
173:
172:
87:
85:
78:
73:
47:
46:
44:
37:
18:Multi-threaded
9:
6:
4:
3:
2:
4732:
4721:
4718:
4716:
4713:
4711:
4708:
4706:
4703:
4701:
4698:
4697:
4695:
4680:
4671:
4670:
4667:
4661:
4658:
4656:
4653:
4651:
4648:
4646:
4643:
4641:
4638:
4636:
4633:
4631:
4628:
4626:
4623:
4621:
4618:
4617:
4615:
4611:
4605:
4602:
4600:
4597:
4595:
4592:
4590:
4587:
4585:
4582:
4580:
4577:
4575:
4572:
4570:
4567:
4565:
4562:
4560:
4557:
4555:
4552:
4550:
4547:
4545:
4542:
4540:
4537:
4535:
4534:Global Arrays
4532:
4530:
4527:
4525:
4522:
4520:
4517:
4515:
4512:
4510:
4507:
4505:
4502:
4500:
4497:
4495:
4492:
4490:
4487:
4485:
4482:
4481:
4479:
4477:
4473:
4467:
4464:
4462:
4461:Grid computer
4459:
4455:
4452:
4451:
4450:
4447:
4444:
4441:
4437:
4434:
4432:
4429:
4427:
4424:
4422:
4419:
4417:
4414:
4412:
4409:
4408:
4407:
4404:
4400:
4397:
4395:
4392:
4391:
4390:
4387:
4385:
4382:
4380:
4377:
4375:
4372:
4370:
4367:
4363:
4360:
4358:
4355:
4351:
4348:
4346:
4343:
4340:
4337:
4336:
4335:
4332:
4330:
4327:
4326:
4325:
4322:
4321:
4319:
4317:
4313:
4307:
4304:
4300:
4297:
4295:
4292:
4290:
4287:
4286:
4285:
4282:
4280:
4277:
4275:
4272:
4271:
4269:
4267:
4263:
4257:
4254:
4252:
4249:
4247:
4244:
4242:
4239:
4237:
4234:
4232:
4229:
4227:
4224:
4223:
4221:
4217:
4211:
4208:
4206:
4203:
4201:
4198:
4196:
4193:
4191:
4188:
4187:
4185:
4181:
4175:
4172:
4170:
4167:
4165:
4162:
4160:
4157:
4155:
4152:
4150:
4147:
4145:
4142:
4140:
4137:
4135:
4132:
4131:
4129:
4125:
4119:
4116:
4113:
4110:
4108:
4105:
4103:
4100:
4097:
4094:
4092:
4089:
4086:
4083:
4081:
4078:
4077:
4075:
4073:
4069:
4063:
4060:
4058:
4055:
4053:
4050:
4048:
4045:
4043:
4040:
4038:
4035:
4033:
4030:
4028:
4025:
4024:
4022:
4018:
4012:
4009:
4007:
4004:
4002:
3999:
3997:
3994:
3992:
3989:
3987:
3984:
3982:
3979:
3977:
3974:
3972:
3969:
3967:
3964:
3963:
3961:
3957:
3953:
3946:
3941:
3939:
3934:
3932:
3927:
3926:
3923:
3911:
3908:
3906:
3903:
3901:
3898:
3896:
3893:
3891:
3888:
3886:
3883:
3881:
3878:
3876:
3873:
3871:
3868:
3867:
3865:
3861:
3854:
3851:
3849:
3846:
3844:
3841:
3839:
3836:
3834:
3831:
3829:
3826:
3824:
3821:
3820:
3818:
3816:
3810:
3800:
3797:
3795:
3792:
3790:
3787:
3785:
3782:
3780:
3777:
3773:
3770:
3768:
3765:
3763:
3760:
3759:
3758:
3755:
3754:
3752:
3750:
3746:
3740:
3737:
3733:
3730:
3728:
3725:
3724:
3723:
3720:
3716:
3713:
3712:
3711:
3708:
3706:
3703:
3701:
3700:Demultiplexer
3698:
3696:
3693:
3692:
3690:
3688:
3684:
3678:
3675:
3673:
3670:
3667:
3665:
3662:
3660:
3657:
3655:
3652:
3650:
3647:
3646:
3644:
3642:
3638:
3632:
3629:
3627:
3624:
3622:
3621:Memory buffer
3619:
3617:
3616:Register file
3614:
3612:
3609:
3607:
3604:
3602:
3599:
3598:
3596:
3594:
3590:
3582:
3579:
3577:
3574:
3573:
3572:
3569:
3567:
3564:
3562:
3559:
3557:
3556:Combinational
3554:
3553:
3551:
3549:
3545:
3539:
3536:
3532:
3529:
3528:
3526:
3523:
3521:
3518:
3516:
3513:
3508:
3505:
3503:
3500:
3499:
3497:
3494:
3491:
3488:
3485:
3482:
3479:
3476:
3475:
3473:
3471:
3465:
3459:
3456:
3454:
3451:
3449:
3446:
3444:
3441:
3437:
3434:
3432:
3429:
3427:
3424:
3422:
3419:
3417:
3414:
3412:
3409:
3408:
3407:
3404:
3402:
3399:
3398:
3396:
3392:
3386:
3383:
3381:
3378:
3376:
3373:
3371:
3368:
3367:
3365:
3361:
3353:
3350:
3349:
3348:
3345:
3343:
3340:
3338:
3335:
3333:
3330:
3328:
3325:
3323:
3320:
3318:
3315:
3313:
3310:
3308:
3305:
3303:
3300:
3298:
3295:
3293:
3290:
3288:
3285:
3283:
3280:
3278:
3275:
3274:
3272:
3270:
3266:
3256:
3253:
3251:
3248:
3246:
3243:
3240:
3237:
3234:
3231:
3228:
3225:
3222:
3219:
3217:
3214:
3211:
3208:
3206:
3203:
3201:
3198:
3197:
3195:
3193:
3187:
3180:
3177:
3175:
3172:
3169:
3166:
3163:
3160:
3159:
3157:
3151:
3145:
3142:
3140:
3137:
3135:
3132:
3130:
3127:
3125:
3122:
3120:
3117:
3115:
3112:
3111:
3109:
3105:
3098:
3095:
3092:
3089:
3086:
3083:
3081:
3078:
3076:
3073:
3071:
3068:
3066:
3063:
3061:
3058:
3056:
3053:
3051:
3048:
3046:
3043:
3041:
3038:
3036:
3033:
3029:
3026:
3025:
3023:
3020:
3017:
3014:
3013:
3011:
3009:
3005:
2999:
2996:
2994:
2991:
2988:
2985:
2982:
2979:
2976:
2973:
2970:
2967:
2964:
2961:
2956:
2953:
2952:
2950:
2947:
2945:
2942:
2941:
2939:
2937:
2931:
2919:
2916:
2915:
2914:
2911:
2909:
2906:
2902:
2899:
2897:
2894:
2892:
2889:
2887:
2884:
2883:
2882:
2879:
2877:
2874:
2873:
2871:
2869:
2865:
2859:
2856:
2854:
2851:
2849:
2846:
2842:
2839:
2837:
2834:
2833:
2832:
2829:
2827:
2824:
2823:
2821:
2819:
2815:
2809:
2806:
2804:
2801:
2797:
2794:
2793:
2792:
2789:
2785:
2782:
2780:
2777:
2776:
2775:
2772:
2768:
2765:
2763:
2760:
2759:
2758:
2755:
2753:
2750:
2746:
2743:
2741:
2738:
2737:
2736:
2733:
2732:
2730:
2726:
2723:
2721:
2717:
2707:
2704:
2702:
2699:
2698:
2696:
2694:
2690:
2684:
2681:
2679:
2676:
2672:
2669:
2667:
2664:
2663:
2662:
2659:
2657:
2656:Scoreboarding
2654:
2653:
2651:
2649:
2645:
2639:
2638:False sharing
2636:
2634:
2631:
2629:
2626:
2624:
2621:
2620:
2618:
2616:
2612:
2606:
2603:
2601:
2598:
2596:
2593:
2592:
2590:
2588:
2584:
2581:
2579:
2575:
2565:
2562:
2560:
2557:
2555:
2552:
2549:
2545:
2542:
2540:
2537:
2535:
2532:
2530:
2527:
2526:
2524:
2522:
2519:
2517:
2514:
2512:
2509:
2507:
2504:
2502:
2499:
2497:
2494:
2492:
2489:
2487:
2484:
2482:
2479:
2477:
2474:
2472:
2469:
2467:
2464:
2460:
2457:
2455:
2452:
2450:
2447:
2446:
2444:
2442:
2439:
2437:
2434:
2432:
2431:Stanford MIPS
2429:
2427:
2424:
2422:
2419:
2417:
2414:
2412:
2409:
2407:
2404:
2403:
2401:
2395:
2387:
2384:
2383:
2382:
2379:
2377:
2374:
2372:
2369:
2367:
2364:
2362:
2359:
2357:
2354:
2352:
2349:
2345:
2342:
2341:
2340:
2337:
2333:
2330:
2329:
2328:
2325:
2323:
2320:
2318:
2315:
2313:
2310:
2308:
2305:
2304:
2302:
2298:
2295:
2293:
2292:architectures
2287:
2281:
2278:
2276:
2273:
2271:
2268:
2266:
2263:
2261:
2260:Heterogeneous
2258:
2254:
2251:
2249:
2246:
2245:
2244:
2241:
2239:
2236:
2232:
2229:
2227:
2224:
2222:
2219:
2217:
2214:
2213:
2212:
2211:Memory access
2209:
2207:
2204:
2202:
2199:
2197:
2194:
2192:
2189:
2185:
2182:
2181:
2180:
2177:
2175:
2172:
2170:
2167:
2166:
2164:
2162:
2158:
2150:
2147:
2145:
2144:Random-access
2142:
2140:
2137:
2135:
2132:
2131:
2130:
2127:
2125:
2124:Stack machine
2122:
2120:
2117:
2113:
2110:
2108:
2105:
2103:
2100:
2098:
2095:
2093:
2090:
2088:
2085:
2083:
2080:
2078:
2075:
2074:
2073:
2070:
2066:
2063:
2061:
2058:
2056:
2053:
2051:
2048:
2046:
2043:
2041:
2040:with datapath
2038:
2037:
2036:
2033:
2031:
2028:
2026:
2023:
2022:
2020:
2018:
2014:
2010:
2003:
1998:
1996:
1991:
1989:
1984:
1983:
1980:
1968:
1960:
1958:
1950:
1948:
1940:
1939:
1936:
1930:
1927:
1925:
1922:
1920:
1917:
1915:
1912:
1910:
1907:
1905:
1902:
1900:
1897:
1895:
1892:
1890:
1887:
1885:
1882:
1880:
1877:
1875:
1872:
1870:
1867:
1865:
1862:
1860:
1857:
1855:
1852:
1850:
1847:
1845:
1842:
1840:
1837:
1835:
1832:
1831:
1829:
1825:
1819:
1816:
1814:
1811:
1809:
1806:
1804:
1803:Mixed reality
1801:
1799:
1796:
1794:
1791:
1789:
1786:
1784:
1781:
1780:
1778:
1776:
1772:
1766:
1763:
1761:
1758:
1756:
1753:
1751:
1748:
1746:
1743:
1742:
1740:
1738:
1734:
1728:
1725:
1723:
1720:
1718:
1715:
1713:
1710:
1708:
1705:
1703:
1700:
1698:
1695:
1693:
1690:
1689:
1687:
1685:
1681:
1675:
1672:
1670:
1667:
1665:
1662:
1660:
1657:
1655:
1652:
1651:
1649:
1647:
1643:
1637:
1636:Accessibility
1634:
1632:
1631:Visualization
1629:
1627:
1624:
1622:
1619:
1617:
1614:
1613:
1611:
1609:
1605:
1599:
1596:
1594:
1591:
1589:
1586:
1584:
1581:
1579:
1576:
1574:
1571:
1569:
1566:
1564:
1561:
1559:
1556:
1555:
1553:
1551:
1547:
1541:
1538:
1536:
1533:
1531:
1528:
1526:
1523:
1521:
1518:
1516:
1513:
1511:
1508:
1506:
1503:
1501:
1498:
1496:
1493:
1491:
1488:
1486:
1483:
1481:
1478:
1476:
1473:
1472:
1470:
1468:
1464:
1458:
1455:
1453:
1450:
1448:
1445:
1443:
1440:
1438:
1435:
1433:
1430:
1428:
1425:
1423:
1420:
1419:
1417:
1415:
1410:
1404:
1401:
1399:
1396:
1394:
1391:
1389:
1386:
1384:
1381:
1380:
1378:
1376:
1372:
1366:
1363:
1361:
1358:
1356:
1353:
1351:
1348:
1346:
1343:
1341:
1338:
1334:
1331:
1330:
1329:
1326:
1325:
1323:
1321:
1317:
1311:
1308:
1306:
1303:
1301:
1298:
1296:
1293:
1291:
1288:
1286:
1283:
1281:
1278:
1276:
1273:
1271:
1268:
1266:
1263:
1262:
1260:
1258:
1254:
1248:
1245:
1243:
1240:
1238:
1235:
1233:
1230:
1228:
1225:
1223:
1220:
1218:
1215:
1213:
1210:
1208:
1205:
1203:
1200:
1199:
1197:
1195:
1191:
1187:
1181:
1178:
1176:
1173:
1171:
1168:
1166:
1163:
1161:
1158:
1157:
1155:
1151:
1145:
1142:
1140:
1137:
1135:
1132:
1130:
1127:
1125:
1122:
1120:
1117:
1116:
1114:
1112:
1108:
1102:
1099:
1097:
1094:
1092:
1091:Dependability
1089:
1087:
1084:
1082:
1079:
1078:
1076:
1072:
1066:
1062:
1059:
1057:
1054:
1052:
1049:
1047:
1044:
1042:
1039:
1037:
1034:
1032:
1029:
1027:
1024:
1022:
1019:
1017:
1014:
1013:
1011:
1009:
1005:
1000:
994:
990:
983:
978:
976:
971:
969:
964:
963:
960:
953:
950:
947:
943:
940:
939:
923:
916:
910:
906:
896:
893:
891:
888:
886:
883:
882:
876:
873:
868:
866:
861:
852:
850:
846:
843:
839:
836:
832:
831:UltraSPARC T2
829:
825:
821:
817:
813:
809:
805:
801:
797:
794:
790:
787:
783:
779:
775:
770:
766:
764:
750:
743:
732:
725:
720:
703:
692:
685:
680:
663:
650:
649:
648:
647:For example:
645:
643:
639:
633:
623:
619:
606:
601:
592:
587:
586:
585:
584:For example:
582:
580:
576:
572:
566:
556:
554:
550:
545:
541:
537:
535:
521:
514:
509:
496:
491:
482:
477:
468:
461:
456:
447:
440:
435:
420:
419:
418:
417:For example:
415:
413:
401:
386:
384:
380:
374:
371:
367:
363:
359:
355:
350:
348:
341:Disadvantages
338:
336:
326:
324:
323:
318:
313:
311:
307:
303:
299:
289:
287:
283:
279:
275:
271:
262:
249:
246:
231:
228:
220:
210:
206:
202:
196:
195:
190:This article
188:
179:
178:
169:
166:
158:
147:
144:
140:
137:
133:
130:
126:
123:
119:
116: –
115:
111:
110:Find sources:
104:
100:
94:
93:
88:This article
86:
82:
77:
76:
71:
69:
62:
61:
56:
55:
50:
45:
36:
35:
30:
19:
4219:Coordination
4149:Amdahl's law
4085:Simultaneous
4071:
3910:Chip carrier
3848:Clock gating
3767:Mixed-signal
3664:Write buffer
3641:Control unit
3453:Clock signal
3192:accelerators
3174:Cypress PSoC
2831:Simultaneous
2817:
2648:Out-of-order
2280:Neuromorphic
2161:Architecture
2119:Belt machine
2112:Zeno machine
2045:Hierarchical
1899:Cyberwarfare
1668:
1558:Cryptography
922:the original
909:
869:
862:
858:
771:
767:
760:
753:from thread
748:
741:
735:from thread
730:
723:
714:from thread
706:from thread
701:
695:from thread
690:
683:
674:from thread
666:from thread
661:
646:
635:
620:
616:
604:
590:
583:
568:
546:
542:
538:
531:
524:from thread
519:
512:
503:from thread
494:
480:
471:from thread
466:
459:
450:from thread
445:
438:
429:from thread
416:
412:ready-to-run
408:
375:
351:
344:
335:cache misses
332:
320:
316:
314:
295:
273:
267:
241:
223:
217:October 2010
214:
191:
161:
155:October 2009
152:
142:
135:
128:
121:
109:
97:Please help
92:verification
89:
65:
58:
52:
51:Please help
48:
4655:Scalability
4416:distributed
4299:Concurrency
4266:Programming
4107:Cooperative
4096:Speculative
4032:Instruction
3695:Multiplexer
3659:Data buffer
3370:Single-core
3342:bit slicing
3200:Coprocessor
3055:Coprocessor
2936:performance
2858:Cooperative
2848:Speculative
2808:Distributed
2767:Superscalar
2752:Instruction
2720:Parallelism
2693:Speculative
2525:System/3x0
2397:Instruction
2174:Von Neumann
2087:Post–Turing
1909:Video games
1889:Digital art
1646:Concurrency
1515:Data mining
1427:Probability
1160:Interpreter
885:Async/await
769:processed.
4694:Categories
4660:Starvation
4399:asymmetric
4134:PRAM model
4102:Preemptive
3815:management
3710:Multiplier
3571:Logic gate
3561:Sequential
3468:Functional
3448:Clock rate
3421:Data cache
3394:Components
3375:Multi-core
3363:Core count
2853:Preemptive
2757:Pipelining
2740:Bit-serial
2683:Wide-issue
2628:Structural
2550:Tilera ISA
2516:MicroBlaze
2486:ETRAX CRIS
2381:Comparison
2226:Load–store
2206:Endianness
1967:Glossaries
1839:E-commerce
1432:Statistics
1375:Algorithms
1333:Stochastic
1165:Middleware
1021:Peripheral
901:References
613:is issued.
599:is issued.
579:preemptive
528:is issued.
507:is issued.
454:is issued.
433:is issued.
329:Advantages
201:improve it
125:newspapers
54:improve it
4394:symmetric
4139:PEM model
3749:Circuitry
3669:Microcode
3593:Registers
3436:coherence
3411:CPU cache
3269:Word size
2934:Processor
2578:Execution
2481:DEC Alpha
2459:Power ISA
2275:Cognitive
2082:Universal
1788:Rendering
1783:Animation
1414:computing
1365:Semantics
1056:Processor
845:Bulldozer
414:threads.
205:verifying
60:talk page
4625:Deadlock
4613:Problems
4579:pthreads
4559:OpenHMPP
4484:Ateji PX
4445:computer
4316:Hardware
4183:Elements
4169:Slowdown
4080:Temporal
4062:Pipeline
3687:Datapath
3380:Manycore
3352:variable
3190:Hardware
2826:Temporal
2506:OpenRISC
2201:Cellular
2191:Dataflow
2184:modified
1947:Category
1775:Graphics
1550:Security
1212:Compiler
1111:Networks
1008:Hardware
879:See also
575:pipeline
298:paradigm
292:Overview
4584:RaftLib
4564:OpenACC
4539:GPUOpen
4529:C++ AMP
4504:Charm++
4246:Barrier
4190:Process
4174:Speedup
3959:General
3863:Related
3794:Quantum
3784:Digital
3779:Boolean
3677:Counter
3576:Quantum
3337:512-bit
3332:256-bit
3327:128-bit
3170:(MPSoC)
3155:on chip
3153:Systems
2971:(FLOPS)
2784:Process
2633:Control
2615:Hazards
2501:Itanium
2496:Unicore
2454:PowerPC
2179:Harvard
2139:Pointer
2134:Counter
2092:Quantum
1957:Outline
776:(later
370:AltiVec
199:Please
139:scholar
4677:
4554:OpenCL
4549:OpenMP
4494:Chapel
4411:shared
4406:Memory
4341:(SIMT)
4284:Models
4195:Thread
4127:Theory
4098:(SpMT)
4052:Memory
4037:Thread
4020:Levels
3799:Switch
3789:Analog
3527:(IMC)
3498:(MMU)
3347:others
3322:64-bit
3317:48-bit
3312:32-bit
3307:24-bit
3302:16-bit
3297:15-bit
3292:12-bit
3129:Mobile
3045:Stream
3040:Barrel
3035:Vector
3024:(GPU)
2983:(SUPS)
2951:(IPC)
2803:Memory
2796:Vector
2779:Thread
2762:Scalar
2564:Others
2511:RISC-V
2476:SuperH
2445:Power
2441:MIPS-X
2416:PDP-11
2265:Fabric
2017:Models
840:, and
814:, IBM
812:POWER9
808:POWER8
804:POWER7
800:POWER6
796:POWER5
778:Compaq
721:Cycle
681:Cycle
651:Cycle
602:Cycle
588:Cycle
510:Cycle
492:Cycle
478:Cycle
457:Cycle
436:Cycle
421:Cycle
141:
134:
127:
120:
112:
4524:Dryad
4489:Boost
4210:Array
4200:Fiber
4114:(CMT)
4087:(SMT)
4001:GPGPU
3855:(PPW)
3813:Power
3705:Adder
3581:Array
3548:Logic
3509:(TLB)
3492:(FPU)
3486:(AGU)
3480:(ALU)
3470:units
3406:Cache
3287:8-bit
3282:4-bit
3277:1-bit
3241:(TPU)
3235:(DSP)
3229:(PPU)
3223:(VPU)
3212:(GPU)
3181:(NoC)
3164:(SoC)
3099:(PoP)
3093:(SiP)
3087:(MCM)
3028:GPGPU
3018:(CPU)
3008:Types
2989:(PPW)
2977:(TPS)
2965:(IPS)
2957:(CPI)
2728:Level
2539:S/390
2534:S/370
2529:S/360
2471:SPARC
2449:POWER
2332:TRIPS
2300:Types
1360:Logic
1194:tools
925:(PDF)
918:(PDF)
786:Intel
354:Intel
146:JSTOR
132:books
4589:ROCm
4519:CUDA
4509:Cilk
4476:APIs
4436:COMA
4431:NUMA
4362:MIMD
4357:MISD
4334:SIMD
4329:SISD
4057:Loop
4047:Data
4042:Task
3833:ACPI
3566:Glue
3458:FIFO
3401:Core
3139:ASIP
3080:CPLD
3075:FPOA
3070:FPGA
3065:ASIC
2918:SPMD
2913:MIMD
2908:MISD
2901:SWAR
2881:SIMD
2876:SISD
2791:Data
2774:Task
2745:Word
2491:M32R
2436:MIPS
2399:sets
2366:ZISC
2361:NISC
2356:OISC
2351:MISC
2344:EPIC
2339:VLIW
2327:EDGE
2317:RISC
2312:CISC
2221:HUMA
2216:NUMA
1192:and
1065:Form
1061:Size
847:and
835:Cray
746:and
659:and
319:and
118:news
4604:ZPL
4599:TBB
4594:UPC
4574:PVM
4544:MPI
4499:HPX
4426:UMA
4027:Bit
3828:APM
3823:PMU
3715:CPU
3672:ROM
3443:Bus
3060:PAL
2735:Bit
2521:LMC
2426:ARM
2421:x86
2411:VAX
946:ACM
865:DMA
849:Zen
842:AMD
838:XMT
824:z15
820:z14
816:z13
793:IBM
782:EV8
774:DEC
751:+ 2
744:+ 1
733:+ 3
726:+ 2
704:+ 1
693:+ 2
686:+ 1
664:+ 1
607:+ 2
593:+ 1
522:+ 1
515:+ 5
497:+ 4
483:+ 3
469:+ 2
462:+ 2
448:+ 1
441:+ 1
368:or
366:MMX
268:In
203:by
101:by
4696::
3762:3D
1063:/
944:,
833:,
826:,
791:,
780:)
325:.
288:.
272:,
63:.
3944:e
3937:t
3930:v
2001:e
1994:t
1987:v
1001:.
981:e
974:t
967:v
822:/
818:/
810:/
806:/
802:/
798:/
755:C
749:m
742:m
737:A
731:j
724:i
716:C
712:m
708:B
702:k
697:A
691:j
684:i
676:B
672:k
668:A
662:j
657:j
653:i
611:C
605:i
597:B
591:i
526:B
520:k
513:i
505:B
501:k
495:i
489:.
487:B
481:i
473:A
467:j
460:i
452:A
446:j
439:i
431:A
427:j
423:i
248:)
242:(
230:)
224:(
219:)
215:(
197:.
168:)
162:(
157:)
153:(
143:·
136:·
129:·
122:·
95:.
70:)
66:(
31:.
20:)
Text is available under the Creative Commons Attribution-ShareAlike License. Additional terms may apply.