33:
131:, load/store units, etc.). As this happens on the Ī¼op-level, sub-operations of different machine (macro) instructions may often intermix in a particular Ī¼op-sequence, forming partially reordered machine instructions as a direct consequence of the out-of-order dispatching of microinstructions from several macro instructions. However, this is not the same as the
142:
Execution optimization has gone even further; processors not only translate many machine instructions into a series of Ī¼ops, but also do the opposite when appropriate; they combine certain machine instruction sequences (such as a compare followed by a conditional jump) into a more complex Ī¼op which
113:
processors more easily handle asynchronous parallel and speculative execution: As with traditional microcode, one or more table lookups (or equivalent) is done to locate the appropriate Ī¼op-sequence based on the encoding and semantics of the machine instruction (the decoding or translation step),
126:
out of a normal single-threaded program possible (provided that dependencies are checked, etc.). It opens up for more analysis and therefore also for reordering of code sequences in order to dynamically optimize mapping and scheduling of Ī¼ops onto machine resources (such as
121:
This buffering means that the fetch and decode stages can be more detached from the execution units than is feasible in a more traditional microcoded (or hard-wired) design. As this allows a degree of freedom regarding execution order, it makes some extraction of
89:, each step of a macro-instruction is decomposed during its execution so the CPU determines and steps through a series of micro-operations. The execution of micro-operations is performed under control of the CPU's
135:, which aims at the fact that a more complex microinstruction may replace a few simpler microinstructions in certain cases, typically in order to minimize state changes and usage of the queue and
169:) is a widespread example of this technique. The size of this cache may be stated in terms of how many thousands (or strictly multiple of 1024) of micro-operations it can store:
154:, so that if the same macroinstruction is executed again, the processor can directly access the decoded micro-operations from the cache, instead of decoding them again. The
109:
or perhaps just the sequencing of certain multi-step operations or addressing modes. More recently, Ī¼ops have also been employed in a different way in order to let modern
1456:
428:
234:
1567:
750:
1269:
547:
1426:
992:
809:
1780:
772:
1421:
1493:
1775:
1246:
143:
fits the execution model better and thus can be executed faster or with less machine resources involved. This is also known as
36:
A high-level illustration showing the decomposition of machine instructions into micro-operations, performed during typical
2190:
1314:
577:
421:
2200:
1341:
300:
468:
66:) are detailed low-level instructions used in some designs to implement complex machine instructions (sometimes termed
361:
ISLPED'01: Proceedings of the 2001 International
Symposium on Low Power Electronics and Design (IEEE Cat. No.01TH8581)
268:"The microarchitecture of Intel, AMD and VIA CPUs: An optimization guide for assembly programmers and compiler makers"
1508:
1336:
1309:
688:
380:
353:
2364:
2323:
1886:
779:
745:
740:
659:
624:
110:
93:, which decides on their execution while performing various optimizations such as reordering, fusion and caching.
2359:
2298:
2195:
1596:
1503:
1304:
525:
414:
1324:
1043:
478:
1498:
1346:
1319:
1180:
794:
755:
612:
123:
1935:
1697:
1173:
1134:
789:
784:
718:
530:
1562:
1259:
957:
654:
2212:
1859:
1276:
767:
735:
505:
493:
473:
221:
86:
2303:
2266:
2256:
644:
17:
2318:
1725:
1661:
1638:
1488:
1450:
1286:
1236:
1231:
708:
602:
510:
139:
space, therefore reducing power consumption. Micro-op fusion is used in some modern CPU designs.
2271:
2054:
1948:
1912:
1829:
1813:
1655:
1444:
1403:
1391:
1254:
1168:
1089:
854:
515:
458:
82:
47:
2077:
2049:
1959:
1924:
1673:
1667:
1649:
1383:
1377:
1281:
1185:
1076:
1015:
877:
520:
2251:
2160:
1906:
1618:
1436:
1195:
1163:
1121:
1033:
834:
649:
639:
629:
619:
589:
572:
437:
155:
151:
128:
114:
however, instead of having rigid Ī¼op-sequences controlling the CPU directly from a microcode-
2281:
2217:
1803:
1525:
1415:
1362:
894:
607:
463:
445:
193:
8:
2328:
2313:
2133:
1984:
1966:
1930:
1918:
1572:
1519:
1296:
1212:
1094:
949:
844:
703:
150:
Another way to try to improve performance is to cache the decoded micro-operations in a
2185:
2177:
2029:
2004:
1808:
1683:
1207:
1148:
1028:
760:
488:
386:
352:
Baruch
Solomon; Avi Mendelson; Doron Orenstein; Yoav Almog; Ronny Ronen (August 2001).
74:
267:
2138:
2105:
2021:
1953:
1854:
1844:
1834:
1765:
1760:
1755:
1678:
1607:
1513:
1473:
1106:
1056:
1006:
982:
864:
804:
799:
681:
597:
376:
67:
37:
27:
Low-level instructions used in some designs to implement complex machine instructions
390:
351:
2308:
2241:
2227:
2082:
1989:
1943:
1750:
1745:
1740:
1735:
1730:
1720:
1590:
1557:
1468:
1463:
1372:
1224:
1219:
1202:
1190:
1129:
693:
671:
557:
535:
453:
368:
354:"Micro-Operation Cache: A Power Aware Frontend for Variable Instruction Length ISA"
230:
115:
85:(CPU), and performing arithmetic or logical operations on registers. In a typical
77:, including transferring data between registers or between registers and external
2222:
2207:
2155:
2059:
2034:
1871:
1864:
1715:
1710:
1705:
1644:
1552:
1542:
1264:
1099:
1051:
814:
698:
666:
567:
562:
483:
136:
78:
73:
Usually, micro-operations perform basic operations on data stored in one or more
2333:
2167:
2150:
2143:
2039:
1896:
1633:
1547:
1478:
1061:
1023:
972:
967:
962:
676:
500:
2353:
2128:
2044:
1084:
1066:
859:
552:
307:
118:, Ī¼ops are here dynamically buffered for rescheduling before being executed.
987:
372:
194:"Computer Organization and Architecture, Chapter 15. Control Unit Operation"
2338:
2276:
2092:
2069:
1881:
1602:
540:
90:
2123:
2087:
1798:
1770:
1628:
1483:
406:
301:"The Architecture of the Nehalem Processor and Nehalem-EP SMP Platforms"
2009:
1999:
1994:
1976:
1876:
1849:
1111:
944:
914:
634:
106:
331:
2100:
2097:
1839:
909:
887:
263:
166:
102:
2115:
934:
162:
44:
32:
924:
882:
939:
904:
869:
101:
Various forms of Ī¼ops have long been the basis for traditional
1397:
929:
899:
364:
159:
105:
routines used to simplify the implementation of a particular
233:, Digital Systems Department. October 1968 . List DSD 68/6.
2261:
1409:
1329:
919:
849:
839:
223:
FM1600B Microcircuit
Computer Ferranti Digital Systems
298:
2351:
422:
214:
1427:Computer performance by orders of magnitude
258:
256:
254:
188:
186:
436:
429:
415:
306:. Texas A&M University. Archived from
294:
292:
290:
262:
251:
183:
31:
14:
2352:
287:
410:
332:"Intel Pentium 4 1.4GHz & 1.5GHz"
1398:Floating-point operations per second
299:Michael E. Thomadakis (2011-03-17).
24:
25:
2376:
2324:Semiconductor device fabrication
96:
2299:History of general-purpose CPUs
526:Nondeterministic Turing machine
240:from the original on 2020-05-19
479:Deterministic finite automaton
345:
324:
13:
1:
1270:Simultaneous and heterogenous
176:
124:instruction-level parallelism
1954:Integrated memory controller
1936:Translation lookaside buffer
1135:Memory dependence prediction
578:Random-access stored program
531:Probabilistic Turing machine
229:. Bracknell, Berkshire, UK:
7:
1410:Synaptic updates per second
38:fetch-decode-execute cycles
10:
2381:
1814:Heterogeneous architecture
736:Orthogonal instruction set
506:Alternating Turing machine
494:Quantum cellular automaton
87:fetch-decode-execute cycle
2304:Microprocessor chronology
2291:
2267:Dynamic frequency scaling
2240:
2176:
2114:
2068:
2020:
1975:
1895:
1822:
1791:
1696:
1617:
1581:
1535:
1435:
1422:Cache performance metrics
1361:
1295:
1245:
1156:
1147:
1120:
1075:
1042:
1014:
1005:
825:
728:
717:
588:
444:
2319:Hardware security module
1662:Digital signal processor
1639:Graphics processing unit
1451:Graphics processing unit
48:central processing units
2365:Central processing unit
2272:Dynamic voltage scaling
2055:Memory address register
1949:Branch target predictor
1913:Address generation unit
1656:Physics processing unit
1445:Central processing unit
1404:Transactions per second
1392:Instructions per second
1315:Array processing (SIMT)
459:Stored-program computer
373:10.1109/LPE.2001.945363
334:. AnandTech. 2000-11-20
83:central processing unit
62:, historically also as
2360:Instruction processing
2078:Hardwired control unit
1960:Memory management unit
1925:Memory management unit
1674:Secure cryptoprocessor
1668:Tensor Processing Unit
1650:Vision processing unit
1384:Cycles per instruction
1378:Instructions per cycle
1325:Associative processing
1016:Instruction pipelining
438:Processor technologies
40:
2161:Sum-addressed decoder
1907:Arithmetic logic unit
1034:Classic RISC pipeline
988:Epiphany architecture
835:Motorola 68000 series
156:execution trace cache
152:micro-operation cache
35:
2282:Performance per watt
1860:replacement policies
1526:Package on a package
1416:Performance per watt
1320:Pipelined processing
1090:Tomasulo's algorithm
895:Clipper architecture
751:Application-specific
464:Finite-state machine
2314:Digital electronics
1967:Instruction decoder
1919:Floating-point unit
1573:Soft microprocessor
1520:System in a package
1095:Reservation station
625:Transport-triggered
165:microarchitecture (
2186:Integrated circuit
2030:Processor register
1684:Baseband processor
1029:Operand forwarding
489:Cellular automaton
70:in this context).
68:macro-instructions
41:
2347:
2346:
2236:
2235:
1855:Instruction cache
1845:Scratchpad memory
1692:
1691:
1679:Network processor
1608:Network on a chip
1563:Ultra-low-voltage
1514:Multi-chip module
1357:
1356:
1143:
1142:
1130:Branch prediction
1107:Register renaming
1001:
1000:
983:VISC architecture
805:Quantum computing
800:VISC architecture
682:Secondary storage
598:Microarchitecture
558:Register machines
16:(Redirected from
2372:
2309:Processor design
2201:Power management
2083:Instruction unit
1944:Branch predictor
1893:
1892:
1591:System on a chip
1533:
1532:
1373:Transistor count
1297:Flynn's taxonomy
1154:
1153:
1012:
1011:
815:Addressing modes
726:
725:
672:Memory hierarchy
536:Hypercomputation
454:Abstract machine
431:
424:
417:
408:
407:
401:
400:
398:
397:
367:. pp. 4ā9.
358:
349:
343:
342:
340:
339:
328:
322:
321:
319:
318:
312:
305:
296:
285:
284:
282:
281:
272:
260:
249:
248:
246:
245:
239:
231:Ferranti Limited
228:
218:
212:
211:
209:
208:
198:
190:
52:micro-operations
21:
2380:
2379:
2375:
2374:
2373:
2371:
2370:
2369:
2350:
2349:
2348:
2343:
2329:Tickātock model
2287:
2243:
2232:
2172:
2156:Address decoder
2110:
2064:
2060:Program counter
2035:Status register
2016:
1971:
1931:Loadāstore unit
1898:
1891:
1818:
1787:
1688:
1645:Image processor
1620:
1613:
1583:
1577:
1553:Microcontroller
1543:Embedded system
1531:
1431:
1364:
1353:
1291:
1241:
1139:
1116:
1100:Re-order buffer
1071:
1052:Data dependency
1038:
997:
827:
821:
720:
719:Instruction set
713:
699:Multiprocessing
667:Cache hierarchy
660:Register/memory
584:
484:Queue automaton
440:
435:
405:
404:
395:
393:
383:
356:
350:
346:
337:
335:
330:
329:
325:
316:
314:
310:
303:
297:
288:
279:
277:
270:
261:
252:
243:
241:
237:
226:
220:
219:
215:
206:
204:
196:
192:
191:
184:
179:
145:macro-op fusion
137:re-order buffer
133:micro-op fusion
99:
54:(also known as
28:
23:
22:
15:
12:
11:
5:
2378:
2368:
2367:
2362:
2345:
2344:
2342:
2341:
2336:
2334:Pin grid array
2331:
2326:
2321:
2316:
2311:
2306:
2301:
2295:
2293:
2289:
2288:
2286:
2285:
2279:
2274:
2269:
2264:
2259:
2254:
2248:
2246:
2238:
2237:
2234:
2233:
2231:
2230:
2225:
2220:
2215:
2210:
2205:
2204:
2203:
2198:
2193:
2182:
2180:
2174:
2173:
2171:
2170:
2168:Barrel shifter
2165:
2164:
2163:
2158:
2151:Binary decoder
2148:
2147:
2146:
2136:
2131:
2126:
2120:
2118:
2112:
2111:
2109:
2108:
2103:
2095:
2090:
2085:
2080:
2074:
2072:
2066:
2065:
2063:
2062:
2057:
2052:
2047:
2042:
2040:Stack register
2037:
2032:
2026:
2024:
2018:
2017:
2015:
2014:
2013:
2012:
2007:
1997:
1992:
1987:
1981:
1979:
1973:
1972:
1970:
1969:
1964:
1963:
1962:
1951:
1946:
1941:
1940:
1939:
1933:
1922:
1916:
1910:
1903:
1901:
1890:
1889:
1884:
1879:
1874:
1869:
1868:
1867:
1862:
1857:
1852:
1847:
1842:
1832:
1826:
1824:
1820:
1819:
1817:
1816:
1811:
1806:
1801:
1795:
1793:
1789:
1788:
1786:
1785:
1784:
1783:
1773:
1768:
1763:
1758:
1753:
1748:
1743:
1738:
1733:
1728:
1723:
1718:
1713:
1708:
1702:
1700:
1694:
1693:
1690:
1689:
1687:
1686:
1681:
1676:
1671:
1665:
1659:
1653:
1647:
1642:
1636:
1634:AI accelerator
1631:
1625:
1623:
1615:
1614:
1612:
1611:
1605:
1600:
1597:Multiprocessor
1594:
1587:
1585:
1579:
1578:
1576:
1575:
1570:
1565:
1560:
1555:
1550:
1548:Microprocessor
1545:
1539:
1537:
1536:By application
1530:
1529:
1523:
1517:
1511:
1506:
1501:
1496:
1491:
1486:
1481:
1479:Tile processor
1476:
1471:
1466:
1461:
1460:
1459:
1448:
1441:
1439:
1433:
1432:
1430:
1429:
1424:
1419:
1413:
1407:
1401:
1395:
1389:
1388:
1387:
1375:
1369:
1367:
1359:
1358:
1355:
1354:
1352:
1351:
1350:
1349:
1339:
1334:
1333:
1332:
1327:
1322:
1317:
1307:
1301:
1299:
1293:
1292:
1290:
1289:
1284:
1279:
1274:
1273:
1272:
1267:
1265:Hyperthreading
1257:
1251:
1249:
1247:Multithreading
1243:
1242:
1240:
1239:
1234:
1229:
1228:
1227:
1217:
1216:
1215:
1210:
1200:
1199:
1198:
1193:
1183:
1178:
1177:
1176:
1171:
1160:
1158:
1151:
1145:
1144:
1141:
1140:
1138:
1137:
1132:
1126:
1124:
1118:
1117:
1115:
1114:
1109:
1104:
1103:
1102:
1097:
1087:
1081:
1079:
1073:
1072:
1070:
1069:
1064:
1059:
1054:
1048:
1046:
1040:
1039:
1037:
1036:
1031:
1026:
1024:Pipeline stall
1020:
1018:
1009:
1003:
1002:
999:
998:
996:
995:
990:
985:
980:
977:
976:
975:
973:z/Architecture
970:
965:
960:
952:
947:
942:
937:
932:
927:
922:
917:
912:
907:
902:
897:
892:
891:
890:
885:
880:
872:
867:
862:
857:
852:
847:
842:
837:
831:
829:
823:
822:
820:
819:
818:
817:
807:
802:
797:
792:
787:
782:
777:
776:
775:
765:
764:
763:
753:
748:
743:
738:
732:
730:
723:
715:
714:
712:
711:
706:
701:
696:
691:
686:
685:
684:
679:
677:Virtual memory
669:
664:
663:
662:
657:
652:
647:
637:
632:
627:
622:
617:
616:
615:
605:
600:
594:
592:
586:
585:
583:
582:
581:
580:
575:
570:
565:
555:
550:
545:
544:
543:
538:
533:
528:
523:
518:
513:
508:
501:Turing machine
498:
497:
496:
491:
486:
481:
476:
471:
461:
456:
450:
448:
442:
441:
434:
433:
426:
419:
411:
403:
402:
381:
344:
323:
286:
266:(2014-02-19).
250:
213:
201:umcs.maine.edu
181:
180:
178:
175:
98:
95:
26:
9:
6:
4:
3:
2:
2377:
2366:
2363:
2361:
2358:
2357:
2355:
2340:
2337:
2335:
2332:
2330:
2327:
2325:
2322:
2320:
2317:
2315:
2312:
2310:
2307:
2305:
2302:
2300:
2297:
2296:
2294:
2290:
2283:
2280:
2278:
2275:
2273:
2270:
2268:
2265:
2263:
2260:
2258:
2255:
2253:
2250:
2249:
2247:
2245:
2239:
2229:
2226:
2224:
2221:
2219:
2216:
2214:
2211:
2209:
2206:
2202:
2199:
2197:
2194:
2192:
2189:
2188:
2187:
2184:
2183:
2181:
2179:
2175:
2169:
2166:
2162:
2159:
2157:
2154:
2153:
2152:
2149:
2145:
2142:
2141:
2140:
2137:
2135:
2132:
2130:
2129:Demultiplexer
2127:
2125:
2122:
2121:
2119:
2117:
2113:
2107:
2104:
2102:
2099:
2096:
2094:
2091:
2089:
2086:
2084:
2081:
2079:
2076:
2075:
2073:
2071:
2067:
2061:
2058:
2056:
2053:
2051:
2050:Memory buffer
2048:
2046:
2045:Register file
2043:
2041:
2038:
2036:
2033:
2031:
2028:
2027:
2025:
2023:
2019:
2011:
2008:
2006:
2003:
2002:
2001:
1998:
1996:
1993:
1991:
1988:
1986:
1985:Combinational
1983:
1982:
1980:
1978:
1974:
1968:
1965:
1961:
1958:
1957:
1955:
1952:
1950:
1947:
1945:
1942:
1937:
1934:
1932:
1929:
1928:
1926:
1923:
1920:
1917:
1914:
1911:
1908:
1905:
1904:
1902:
1900:
1894:
1888:
1885:
1883:
1880:
1878:
1875:
1873:
1870:
1866:
1863:
1861:
1858:
1856:
1853:
1851:
1848:
1846:
1843:
1841:
1838:
1837:
1836:
1833:
1831:
1828:
1827:
1825:
1821:
1815:
1812:
1810:
1807:
1805:
1802:
1800:
1797:
1796:
1794:
1790:
1782:
1779:
1778:
1777:
1774:
1772:
1769:
1767:
1764:
1762:
1759:
1757:
1754:
1752:
1749:
1747:
1744:
1742:
1739:
1737:
1734:
1732:
1729:
1727:
1724:
1722:
1719:
1717:
1714:
1712:
1709:
1707:
1704:
1703:
1701:
1699:
1695:
1685:
1682:
1680:
1677:
1675:
1672:
1669:
1666:
1663:
1660:
1657:
1654:
1651:
1648:
1646:
1643:
1640:
1637:
1635:
1632:
1630:
1627:
1626:
1624:
1622:
1616:
1609:
1606:
1604:
1601:
1598:
1595:
1592:
1589:
1588:
1586:
1580:
1574:
1571:
1569:
1566:
1564:
1561:
1559:
1556:
1554:
1551:
1549:
1546:
1544:
1541:
1540:
1538:
1534:
1527:
1524:
1521:
1518:
1515:
1512:
1510:
1507:
1505:
1502:
1500:
1497:
1495:
1492:
1490:
1487:
1485:
1482:
1480:
1477:
1475:
1472:
1470:
1467:
1465:
1462:
1458:
1455:
1454:
1452:
1449:
1446:
1443:
1442:
1440:
1438:
1434:
1428:
1425:
1423:
1420:
1417:
1414:
1411:
1408:
1405:
1402:
1399:
1396:
1393:
1390:
1385:
1382:
1381:
1379:
1376:
1374:
1371:
1370:
1368:
1366:
1360:
1348:
1345:
1344:
1343:
1340:
1338:
1335:
1331:
1328:
1326:
1323:
1321:
1318:
1316:
1313:
1312:
1311:
1308:
1306:
1303:
1302:
1300:
1298:
1294:
1288:
1285:
1283:
1280:
1278:
1275:
1271:
1268:
1266:
1263:
1262:
1261:
1258:
1256:
1253:
1252:
1250:
1248:
1244:
1238:
1235:
1233:
1230:
1226:
1223:
1222:
1221:
1218:
1214:
1211:
1209:
1206:
1205:
1204:
1201:
1197:
1194:
1192:
1189:
1188:
1187:
1184:
1182:
1179:
1175:
1172:
1170:
1167:
1166:
1165:
1162:
1161:
1159:
1155:
1152:
1150:
1146:
1136:
1133:
1131:
1128:
1127:
1125:
1123:
1119:
1113:
1110:
1108:
1105:
1101:
1098:
1096:
1093:
1092:
1091:
1088:
1086:
1085:Scoreboarding
1083:
1082:
1080:
1078:
1074:
1068:
1067:False sharing
1065:
1063:
1060:
1058:
1055:
1053:
1050:
1049:
1047:
1045:
1041:
1035:
1032:
1030:
1027:
1025:
1022:
1021:
1019:
1017:
1013:
1010:
1008:
1004:
994:
991:
989:
986:
984:
981:
978:
974:
971:
969:
966:
964:
961:
959:
956:
955:
953:
951:
948:
946:
943:
941:
938:
936:
933:
931:
928:
926:
923:
921:
918:
916:
913:
911:
908:
906:
903:
901:
898:
896:
893:
889:
886:
884:
881:
879:
876:
875:
873:
871:
868:
866:
863:
861:
860:Stanford MIPS
858:
856:
853:
851:
848:
846:
843:
841:
838:
836:
833:
832:
830:
824:
816:
813:
812:
811:
808:
806:
803:
801:
798:
796:
793:
791:
788:
786:
783:
781:
778:
774:
771:
770:
769:
766:
762:
759:
758:
757:
754:
752:
749:
747:
744:
742:
739:
737:
734:
733:
731:
727:
724:
722:
721:architectures
716:
710:
707:
705:
702:
700:
697:
695:
692:
690:
689:Heterogeneous
687:
683:
680:
678:
675:
674:
673:
670:
668:
665:
661:
658:
656:
653:
651:
648:
646:
643:
642:
641:
640:Memory access
638:
636:
633:
631:
628:
626:
623:
621:
618:
614:
611:
610:
609:
606:
604:
601:
599:
596:
595:
593:
591:
587:
579:
576:
574:
573:Random-access
571:
569:
566:
564:
561:
560:
559:
556:
554:
553:Stack machine
551:
549:
546:
542:
539:
537:
534:
532:
529:
527:
524:
522:
519:
517:
514:
512:
509:
507:
504:
503:
502:
499:
495:
492:
490:
487:
485:
482:
480:
477:
475:
472:
470:
469:with datapath
467:
466:
465:
462:
460:
457:
455:
452:
451:
449:
447:
443:
439:
432:
427:
425:
420:
418:
413:
412:
409:
392:
388:
384:
382:1-58113-371-5
378:
374:
370:
366:
362:
355:
348:
333:
327:
313:on 2014-08-11
309:
302:
295:
293:
291:
276:
269:
265:
259:
257:
255:
236:
232:
225:
224:
217:
202:
195:
189:
187:
182:
174:
172:
168:
164:
161:
157:
153:
148:
146:
140:
138:
134:
130:
125:
119:
117:
112:
108:
104:
97:Optimizations
94:
92:
88:
84:
80:
76:
71:
69:
65:
64:micro-actions
61:
57:
53:
49:
46:
39:
34:
30:
19:
2339:Chip carrier
2277:Clock gating
2196:Mixed-signal
2093:Write buffer
2070:Control unit
1882:Clock signal
1621:accelerators
1603:Cypress PSoC
1260:Simultaneous
1077:Out-of-order
709:Neuromorphic
590:Architecture
548:Belt machine
541:Zeno machine
474:Hierarchical
394:. Retrieved
360:
347:
336:. Retrieved
326:
315:. Retrieved
308:the original
278:. Retrieved
274:
242:. Retrieved
222:
216:
205:. Retrieved
203:. 2010-03-16
200:
170:
149:
144:
141:
132:
120:
100:
91:control unit
72:
63:
59:
55:
51:
42:
29:
2124:Multiplexer
2088:Data buffer
1799:Single-core
1771:bit slicing
1629:Coprocessor
1484:Coprocessor
1365:performance
1287:Cooperative
1277:Speculative
1237:Distributed
1196:Superscalar
1181:Instruction
1149:Parallelism
1122:Speculative
954:System/3x0
826:Instruction
603:Von Neumann
516:PostāTuring
2354:Categories
2244:management
2139:Multiplier
2000:Logic gate
1990:Sequential
1897:Functional
1877:Clock rate
1850:Data cache
1823:Components
1804:Multi-core
1792:Core count
1282:Preemptive
1186:Pipelining
1169:Bit-serial
1112:Wide-issue
1057:Structural
979:Tilera ISA
945:MicroBlaze
915:ETRAX CRIS
810:Comparison
655:Loadāstore
635:Endianness
396:2014-03-21
338:2013-10-06
317:2014-03-21
280:2014-03-21
244:2020-05-19
207:2014-12-29
177:References
107:CPU design
2178:Circuitry
2098:Microcode
2022:Registers
1865:coherence
1840:CPU cache
1698:Word size
1363:Processor
1007:Execution
910:DEC Alpha
888:Power ISA
704:Cognitive
511:Universal
275:agner.org
264:Agner Fog
167:Pentium 4
158:found in
103:microcode
75:registers
56:micro-ops
18:Micro-ops
2116:Datapath
1809:Manycore
1781:variable
1619:Hardware
1255:Temporal
935:OpenRISC
630:Cellular
620:Dataflow
613:modified
391:10934861
235:Archived
163:NetBurst
45:computer
2292:Related
2223:Quantum
2213:Digital
2208:Boolean
2106:Counter
2005:Quantum
1766:512-bit
1761:256-bit
1756:128-bit
1599:(MPSoC)
1584:on chip
1582:Systems
1400:(FLOPS)
1213:Process
1062:Control
1044:Hazards
930:Itanium
925:Unicore
883:PowerPC
608:Harvard
568:Pointer
563:Counter
521:Quantum
81:of the
2228:Switch
2218:Analog
1956:(IMC)
1927:(MMU)
1776:others
1751:64-bit
1746:48-bit
1741:32-bit
1736:24-bit
1731:16-bit
1726:15-bit
1721:12-bit
1558:Mobile
1474:Stream
1469:Barrel
1464:Vector
1453:(GPU)
1412:(SUPS)
1380:(IPC)
1232:Memory
1225:Vector
1208:Thread
1191:Scalar
993:Others
940:RISC-V
905:SuperH
874:Power
870:MIPS-X
845:PDP-11
694:Fabric
446:Models
389:
379:
2284:(PPW)
2242:Power
2134:Adder
2010:Array
1977:Logic
1938:(TLB)
1921:(FPU)
1915:(AGU)
1909:(ALU)
1899:units
1835:Cache
1716:8-bit
1711:4-bit
1706:1-bit
1670:(TPU)
1664:(DSP)
1658:(PPU)
1652:(VPU)
1641:(GPU)
1610:(NoC)
1593:(SoC)
1528:(PoP)
1522:(SiP)
1516:(MCM)
1457:GPGPU
1447:(CPU)
1437:Types
1418:(PPW)
1406:(TPS)
1394:(IPS)
1386:(CPI)
1157:Level
968:S/390
963:S/370
958:S/360
900:SPARC
878:POWER
761:TRIPS
729:Types
387:S2CID
365:Intel
357:(PDF)
311:(PDF)
304:(PDF)
271:(PDF)
238:(PDF)
227:(PDF)
197:(PDF)
171:KĪ¼ops
160:Intel
79:buses
2262:ACPI
1995:Glue
1887:FIFO
1830:Core
1568:ASIP
1509:CPLD
1504:FPOA
1499:FPGA
1494:ASIC
1347:SPMD
1342:MIMD
1337:MISD
1330:SWAR
1310:SIMD
1305:SISD
1220:Data
1203:Task
1174:Word
920:M32R
865:MIPS
828:sets
795:ZISC
790:NISC
785:OISC
780:MISC
773:EPIC
768:VLIW
756:EDGE
746:RISC
741:CISC
650:HUMA
645:NUMA
377:ISBN
129:ALUs
111:CISC
60:Ī¼ops
2257:APM
2252:PMU
2144:CPU
2101:ROM
1872:Bus
1489:PAL
1164:Bit
950:LMC
855:ARM
850:x86
840:VAX
369:doi
116:ROM
58:or
43:In
2356::
2191:3D
385:.
375:.
363:.
359:.
289:^
273:.
253:^
199:.
185:^
173:.
147:.
50:,
430:e
423:t
416:v
399:.
371::
341:.
320:.
283:.
247:.
210:.
20:)
Text is available under the Creative Commons Attribution-ShareAlike License. Additional terms may apply.