1592:
1661:
3520:
2272:
1543:, an ionic reservoir, and metal contacts. The resistance of the channel is modulated by ionic exchange at the interface between the channel and the electrolyte upon application of an electric field. The charge-transfer process allows both for state retention in the absence of applied power, and for programming of multiple distinct levels, both differentiating ECRAM operation from that of a
1809:
and therefore need to have a high average resistance to limit energy dissipation. To perform high-accuracy computation and be resilient to noise, the NVM cell needs a large number of distinct states. The programming time needs only to be fast between levels, not from the highest to the lowest resistance states. During each programming cycle (
1813:), weight updates can be negative or positive, and the up/down traces therefore need symmetry to allow learning algorithms to converge. All NVM technologies do struggle with these targets. ECRAM individual cells can meet such stringent metrics, but also need to demonstrate high-density array yield and stochasticity.
1845:
Using co-planar organic multilevel cells, isolated by conductive bridge memory (CBM) devices, the team demonstrates parallel programming and addressing in up to 3×3 arrays. In particular a 2-layer neural network is mapped to the array by transferring the weights necessary to perform an inference task
1808:
NVM use as synaptic weights in lieu of storage implies significantly different requirements when it comes to target resistance range, number of levels, and programming speed and symmetry. Because the in-memory computation occurs in parallel through the array, many devices are addressed concurrently
2295:
can handle several technologies and has strict rules when it comes to materials being introduced in its expensive toolset to avoid cross-contamination and loss of device yield. In particular, metallic mobile ions, if present in active areas, can induce device drift and affect reliability. There are
1621:
The read operation is decoupled from the write operation thanks to the presence of three electrodes, therefore limiting read disturb. A small bias is applied between the channel electrodes, with the resulting read current being proportional to the channel conductivity, hence sensing the programmed
2234:
Based on hydrogen ions, H-ECRAM devices have proven fast, necessitating small driving forces to induce programming. High diffusion coefficients in various materials can be accompanied by lack of retention within the memory cell, impacting endurance. Most H-ECRAM designs use liquid and/or organic
2320:
but will still need to remain unaffected by temperatures up to ~400 °C used in subsequent steps. Together with high density patterning challenges, these restrictions make organic devices unsuitable for such integration. The ECRAMs based on 2D MXene materials have shown the potential to be
1604:
Stress to the gate, relative to channel electrodes, can be applied in the form of fixed current or bias, driving ions toward - or away from - the electrolyte/channel interface where charge transfer occurs with free carriers. Upon insertion in the channel, the ionic charge is neutralized and the
1700:
are used for classification and learning tasks, relying on a large number of matrix-multiply operations. Therefore, analog compute with NVM technology for such tasks are extremely attractive. ECRAM cells are uniquely positioned for use in analog deep learning accelerators due to their inherent
1651:
exists at the gate contact and will differ device to device depending on the programmed state. To prevent cross-talk between cells sharing a gate line, an access device to isolate each one is added in series with the memory element. Suppressing OCP in the ECRAM design, minimizes the cell
1630:
The programming speed of ECRAM cells is not limited by the bulk diffusion of ions. They indeed only need to cross the interface plane between the electrolyte and the channel to induce a change in conductivity. Nanosecond write pulses can indeed trigger programming. Trade-offs between
2225:
Based on lithium ions, Li-ECRAM devices have demonstrated repeatable and controlled switching by applying known materials from battery technology to the memory design. Consequently, such cells can exhibit an OCP which varies over several volts, depending on the programmed state.
1873:
Using metal-oxide ECRAM cells, selector-free, the team demonstrates parallel programming and addressing in 2×2 arrays. In particular, a logistic regression task is performed in-memory with 1,000 2×1 vectors as training set. 2D curve fit is achieved in a dozen epochs.
1692:'s laws, the resulting vector is then obtained by integrating the current collected at each column. For ECRAM cells, an additional line is added at each row to write the cells during programming cycles, thereby yielding a pseudo-crossbar architecture. In the field of
1853:
Individual cells are shown to have the following properties (not all achieved in the same device configuration); speed = 1 MHz read-write cycles, number of states > 50 (tunable), resistance range = 50-100 nS (tunable), endurance >
1613:. Although in ECRAM, the programming of the memory element is defined not as a change in capacity or opacity, but by a change of channel conductivity associated with atomic species being inserted or removed as a result of the stress signal.
1877:
Individual cells are shown to have the following properties (not all achieved in the same device configuration); speed = 10 ns write pulses, number of states > 1,000 (tunable), resistance range = 0-50 μS (tunable), endurance >
1684:. Hence, when using multi-level cells (MLC) at the nodes of cross-bar arrays, one can perform analog operations on time or voltage encoded data such as vector (row input signal) × matrix (memory array) multiply. Following
1680:, thereby reducing the frequency of data transfer between storage and processing units. This can ultimately improve compute time and energy efficiency over hierarchical system architectures by eliminating the
1605:
atomic species intercalate or bind to the conductive host matrix, in some cases yielding strain and localized phase transformation. Such reversible processes are equivalent to anodic/cathodic reactions in
1547:. The write operation is deterministic and can result in symmetrical potentiation and depression, making ECRAM arrays attractive for acting as artificial synaptic weights in physical implementations of
1664:(Left) Illustration of analog matrix-vector multiply operation in a pseudo-crossbar ecram array. (Right) Illustration of the programming of 50 distinct and reversible states in the ecram synaptic cell.
1555:
and semiconductor foundry compatibility associated with energy materials. Universities, government laboratories, and corporate research teams have contributed to the development of ECRAM for
3003:
Yang, J.-T.; Ge, C.; Du, J.-Y.; Huang, H.-Y.; He, M.; Wang, C.; Lu, H.-B.; Yang, G.-Z.; Jin, K.-J. (2018). "Artificial
Synapses Emulated by an Electrolyte-Gated Tungsten-Oxide Transistor".
2296:
several other considerations for the foundries; including safety, cost, volume, etc. Hence, lithium ion-based Li-ECRAM faces unique challenges beyond the presence of OCP.
622:
3257:
2692:
Fuller, E.J.; Keene, S.T.; Melianas, A.; Wang, Z.; Agarwal, S.; Li, Y.; Tuchman, Y.; James, C.D.; Marinella, M.J.; Yang, J.J.; Salleo, A.; Talin, A.A. (2019).
1805:
has published such requirements, a subset of which is listed here. Algorithm and hardware co-design can relax them somewhat but not without other trade-offs.
3063:
Melianas, Armantas; Kang, Min-A; VahidMohammadi, Armin; Quill, Tyler James; Tian, Weiqian; Gogotsi, Yury; Salleo, Alberto; Hamedi, Mahiar Max (March 2022).
2243:
electrolyte that achieved ultrafast modulation characteristics with high energy efficiency. The same year researchers at the Royal
Institute of Technology
17:
2283:. This puts constraints on materials used, and the techniques employed to fabricate functional devices. The implications for ECRAM are described here.
2403:
Tang, Jianshi; Bishop, Douglas; Kim, Seyoung; Copel, Matt; Gokmen, Tayfun; Todorov, Teodor; Shin, SangHoon; Lee, Ko-Tao; Solomon, Paul (2018-12-01).
2337:. However, the cost and complexity associated with such scheme negatively affects the value proposition for displacing existing memory technologies.
3130:
1643:
ECRAM arrays are integrated in a pseudo-crossbar layout, the gate access line being common to all devices in a row or column. If a change in
2454:
2333:
where the device array is fabricated independently from the logic controls and then bonded to the FET-containing chip to enable its use as
1583:
built an inorganic, CMOS-compatible protonic technology that achieved near-ideal modulation characteristics using nanosecond fast pulses
3619:
2576:
Onen, Murat; Emond, Nicolas; Wang, Baoming; Zhang, Difei; Ross, Frances M.; Li, Ju; Yildiz, Bilge; del Alamo, Jesús A. (29 July 2022).
3155:
2247:
showed ECRAMS based on hydrogen intercalation into the 2D material MXene, marking the first demonstration of high speed 2D ECRAMs.
617:
637:
3225:
3183:
3374:
2304:
Memory arrays require logic periphery to operate and interface with the rest of the compute system. Such periphery is based on
1511:
3559:
2653:
2549:
2424:
2236:
1580:
1052:
3344:
3463:
3203:
3123:
1839:
3597:
2893:
Yang, C.-S.; Shang, D.-S.; Liu, N.; Fuller, E.J.; Agrawal, S.; Alec Talin, A.; Li, Y.-Q.; Shen, B.-G.; Sun, Y. (2018).
1261:
213:
2263:
technology used in commercial semiconductor offerings. MO-ECRAM do enable negligible OCP and sub-μs write operations.
258:
2244:
1000:
943:
263:
3585:
111:
1793:
Physical implementation of artificial neural networks (ANN) must perform at iso-accuracy when benchmarked against
3265:
1568:
1326:
986:
930:
3327:
3305:
3116:
1890:
Various institutions have demonstrated ECRAM cells with vastly different materials, layouts, and performances.
1702:
1012:
681:
493:
89:
1539:
analog acceleration. An ECRAM cell is a three-terminal device composed of a conductive channel, an insulating
3524:
3490:
1361:
3624:
2679:, proceedings of the international conference in Solid-State Devices and Materials (SSDM), pp. 23-24 (2018)
2280:
1831:
1635:, electronic conductivity, etc., can yield settling transients, limiting the maximum read-write frequency.
1560:
712:
607:
508:
2321:
unaffected by 400 °C heating, but additional development is needed for the integration of ion conductors.
1685:
669:
2859:"Artificial Synapses: Low-Power, Electrochemically Tunable Graphene Synapses for Neuromorphic Computing"
2754:"Acceleration of Deep Neural Network Training with Resistive Cross-Point Devices: Design Considerations"
3495:
3431:
1548:
1504:
1301:
1200:
1072:
702:
691:
800:
3478:
3438:
2636:
Tang, J. (2018). "ECRAM as
Scalable Synaptic Cell for High-Speed, Low-Power Neuromorphic Computing".
2330:
1798:
1794:
1644:
563:
498:
393:
3546:
2279:
For advanced semiconductor memory or compute applications, a technology needs to be compatible with
1647:, the driving force of a battery, occurs upon ionic exchange between channel and gate electrode, an
3250:
2305:
1373:
1356:
845:
131:
3443:
3416:
3245:
3178:
2694:"Parallel programming of an ionic floating-gate memory array for scalable neuromorphic computing"
2491:
1693:
1544:
1368:
1185:
908:
313:
148:
126:
106:
59:
3048:, proceedings of the IEEE international Silicon Nanoelectronics Workshop (SNW), pp. 31-32 (2018)
3453:
3448:
3421:
3339:
1681:
1648:
1552:
1241:
458:
328:
268:
1866:
As reported in a 2019 proceeding of the IEEE International
Electron Device Meeting (IEDM), by
590:
3629:
3379:
3240:
3139:
2334:
2292:
2240:
1610:
1497:
744:
662:
448:
253:
233:
223:
79:
44:
3572:
3426:
3389:
3369:
3285:
3166:
2956:
2705:
2367:
1697:
1440:
1308:
1087:
1047:
970:
583:
488:
378:
273:
136:
116:
99:
94:
2895:"All-Solid-State Synaptic Transistor with Ultralow Conductance for Neuromorphic Computing"
2532:
Kim, S. (2019). "Metal-oxide based, CMOS-compatible ECRAM for Deep
Learning Accelerator".
8:
3483:
3458:
3295:
3188:
1835:
1706:
1677:
1673:
1572:
1564:
1528:
1037:
960:
827:
779:
632:
443:
141:
2960:
2709:
2371:
1652:
size/complexity, allowing for selector-free parallel read/programming of device arrays.
3500:
3213:
3198:
3171:
3094:
3028:
2977:
2944:
2922:
2831:
2804:
2780:
2753:
2731:
2659:
2615:
2555:
2430:
1446:
1411:
1057:
483:
468:
413:
408:
398:
373:
298:
2578:
1701:
deterministic and symmetric programming nature when compared to other devices such as
1591:
3322:
3275:
3098:
3086:
3020:
2982:
2926:
2914:
2836:
2785:
2735:
2723:
2649:
2619:
2607:
2599:
2559:
2545:
2420:
2404:
2385:
2313:
2260:
1123:
1118:
1042:
1007:
861:
839:
738:
697:
600:
438:
163:
3032:
2663:
2511:
2434:
1797:
weights in software. This sets the boundary for device properties needed for analog
3468:
3384:
3300:
3280:
3235:
3230:
3076:
3012:
2972:
2964:
2906:
2870:
2826:
2816:
2775:
2765:
2713:
2641:
2591:
2541:
2537:
2412:
2375:
2317:
1810:
1632:
1556:
1532:
1458:
1452:
1378:
1341:
1331:
1296:
1108:
1062:
1030:
805:
788:
473:
433:
193:
178:
74:
64:
2405:"ECRAM as Scalable Synaptic Cell for High-Speed, Low-Power Neuromorphic Computing"
1660:
1351:
1178:
1165:
856:
851:
707:
574:
553:
528:
388:
308:
238:
208:
183:
69:
40:
2455:"Finite element modeling of electrochemical random access memory - iis-projects"
3560:"The path to the "perfect" analog material and system: IBM at IEDM and NeurIPS"
3473:
3193:
2968:
2857:
Sharbati, M.T.; Du, Y.; Torres, J.; Ardolino, N.D.; Yun, M.; Xiong, F. (2018).
1470:
1388:
1231:
888:
750:
686:
558:
543:
523:
518:
463:
428:
383:
333:
323:
318:
303:
198:
188:
121:
2645:
2416:
3613:
3505:
3332:
3090:
2821:
2770:
2603:
2309:
1536:
1476:
1103:
1098:
1067:
822:
732:
548:
538:
533:
513:
348:
338:
218:
203:
2718:
2693:
2595:
3409:
3208:
3081:
3064:
3024:
3016:
2986:
2945:"Protonic solid-state electrochemical synapse for physical neural networks"
2910:
2875:
2858:
2840:
2789:
2727:
2611:
2389:
1802:
1689:
1606:
1423:
1417:
1383:
1251:
1206:
1190:
1082:
878:
873:
833:
795:
478:
453:
353:
288:
243:
228:
3586:"Stanford researchers' artificial synapse is fast, efficient and durable"
3404:
3399:
3220:
1736:
1563:
designed a lithium-based cell inspired by solid-state battery materials,
1540:
1482:
1434:
868:
403:
343:
248:
30:"Electrochemical synapse" redirects here. For synapses in the brain, see
3108:
3364:
2462:
2380:
2355:
1782:
1077:
903:
657:
423:
418:
293:
158:
84:
2918:
2894:
3394:
3065:"High-Speed Ionic Synaptic Memory Based on 2D Titanium Carbide MXene"
2579:"Nanosecond protonic programmable resistors for analog deep learning"
1464:
1429:
1266:
1195:
1093:
964:
955:
652:
595:
363:
283:
1575:
task in an array of metal-oxide ECRAM designed for insertion in the
3315:
3290:
2805:"Algorithm for Training Neural Networks on Resistive Device Arrays"
1847:
1393:
1336:
1271:
1226:
1211:
981:
950:
923:
898:
756:
642:
368:
278:
173:
168:
3558:
Ambrogio, S.; Adusumilli, P.; Eleftheriou, E. (11 December 2019).
2354:
Shi, J.; Ha, S. D.; Zhou, Y.; Schoofs, F.; Ramanathan, S. (2013).
2271:
1291:
1281:
1276:
1236:
1138:
1133:
1113:
918:
893:
883:
674:
31:
1571:
demonstrated in-memory selector-free parallel programming for a
3062:
1286:
1246:
1128:
1017:
815:
358:
3573:"Engineers design a device that operates like a brain synapse"
3557:
3310:
2316:. Memory cells can be inserted between upper metal levels at
1221:
1158:
1153:
1148:
810:
767:
761:
647:
627:
612:
1801:. In the design of their resisistive processing unit (RPU),
2256:
1576:
1216:
503:
153:
2329:
One way to introduce novel memory materials can be to use
1892:
An example set for discrete cells is listed in the table.
1256:
1143:
913:
2856:
3598:"Sandia Powers Breakthroughs in Neuromorphic Computing"
2691:
2638:
2018 IEEE International
Electron Devices Meeting (IEDM)
2534:
2019 IEEE International
Electron Devices Meeting (IEDM)
2409:
2018 IEEE International
Electron Devices Meeting (IEDM)
3547:"Searching for the Perfect Artificial Synapse for AI"
2239:demonstrated a CMOS-compatible technology based on
1816:
2892:
2577:
2575:
2402:
1595:ECRAM synaptic cell layout and operating principle
2324:
1826:As reported in a 2019 publication in Science, by
3611:
2852:
2850:
2353:
1821:
2888:
2886:
2747:
2745:
2687:
2685:
2235:electrolytes. In a 2022 study, researchers at
3124:
3002:
2998:
2996:
2847:
2802:
2482:
2480:
2478:
2312:substrates with a high thermal budget at the
1505:
2942:
2356:"A correlated nickelate synaptic transistor"
1525:Electrochemical Random-Access Memory (ECRAM)
2938:
2936:
2883:
2796:
2751:
2742:
2682:
2631:
2629:
2255:Metal-oxide based ECRAM, are inspired from
3519:
3131:
3117:
2993:
2670:
2527:
2525:
2523:
2521:
2519:
2503:
2501:
2499:
2475:
2299:
1512:
1498:
3138:
3080:
2976:
2874:
2830:
2820:
2779:
2769:
2717:
2379:
3570:
3039:
2933:
2626:
2286:
2270:
1659:
1590:
1567:built an organic proton-based cell, and
3226:Carbon nanotube field-effect transistor
3184:Applications of artificial intelligence
2516:
2496:
1885:
1828:Elliot J. Fuller, Alec A. Talin, et al.
1551:. The technological challenges include
14:
3612:
3583:
3375:Differential technological development
2571:
2569:
1850:operation on the binary input vector.
3544:
3112:
3058:
3056:
3054:
2943:Yao, X.; Klyukin, K.; Lu, W. (2020).
2237:Massachusetts Institute of Technology
1581:Massachusetts Institute of Technology
1569:International Business Machines (IBM)
1053:Vision Electronic Recording Apparatus
3345:Three-dimensional integrated circuit
2635:
1655:
18:Electrochemical random-access memory
3464:Future-oriented technology analysis
3204:Progress in artificial intelligence
2566:
2531:
2281:very large scale integration (VLSI)
1840:University of Massachusetts Amherst
24:
3051:
214:Data validation and reconciliation
25:
3641:
3620:Non-volatile random-access memory
3537:
2512:Nature Electronics, 1, 386 (2018)
264:Distributed file system for cloud
3545:Moore, S.K. (11 December 2018).
3518:
2803:Tayfun, G.; Haensch, H. (2020).
1817:Demos with ECRAM Synaptic Arrays
1549:artificial neural networks (ANN)
112:Areal density (computer storage)
3571:Chandler, D.L. (19 June 2020).
3241:Fourth-generation optical discs
2492:Adv. Mater., 29, 1604310 (2017)
2306:field-effect transistors (FETs)
1868:Seyoung Kim, John Rozen, et al.
1861:
1712:
931:Programmable metallization cell
2752:Tayfun, G.; Yurii, V. (2016).
2542:10.1109/IEDM19573.2019.8993463
2447:
2396:
2347:
2331:heterogeneous integration (HI)
2325:Heterogeneous integration (HI)
1533:multiple levels per cell (MLC)
494:Persistence (computer science)
13:
1:
3491:Technology in science fiction
3069:Advanced Functional Materials
2340:
1882:write ops, size < 1×1 μm.
1703:resistive RAM (ReRAM or RRAM)
1545:field-effect transistor (FET)
1362:Electronic quantum holography
27:Novel type of computer memory
3584:Kubota, T. (25 April 2019).
1858:write ops, size = 50×50 μm.
1832:Sandia National Laboratories
1822:Sandia National Laboratories
1694:artificial intelligence (AI)
1668:
1649:open circuit potential (OCP)
1586:
1561:Sandia National Laboratories
1553:open circuit potential (OCP)
713:Video RAM (dual-ported DRAM)
509:Non-RAID drive architectures
7:
2335:high bandwidth memory (HBM)
2250:
2220:
10:
3646:
3496:Technology readiness level
3432:Technological unemployment
2969:10.1038/s41467-020-16866-6
2229:
1799:deep learning accelerators
1698:deep neural networks (DNN)
1579:. In 2022, researchers at
1302:Holographic Versatile Disc
1201:Compact Disc Digital Audio
1073:Magnetic-tape data storage
692:Content-addressable memory
29:
3514:
3479:Technological singularity
3439:Technological convergence
3357:
3153:
3146:
2809:Frontiers in Neuroscience
2758:Frontiers in Neuroscience
2646:10.1109/IEDM.2018.8614551
2417:10.1109/IEDM.2018.8614551
1707:phase-change memory (PCM)
1674:Non-volatile memory (NVM)
1645:electrochemical potential
1638:
1529:non-volatile memory (NVM)
499:Persistent data structure
394:Digital rights management
3251:Holographic data storage
2822:10.3389/fnins.2020.00103
2771:10.3389/fnins.2016.00333
2314:front end of line (FEOL)
2308:built on the surface of
2275:Processed 200mm si wafer
1834:, in collaboration with
1795:floating point precision
1625:
1599:
1374:DNA digital data storage
1357:Holographic data storage
846:Solid-state hybrid drive
132:Network-attached storage
3444:Technological evolution
3417:Exploratory engineering
3246:3D optical data storage
3179:Artificial intelligence
2719:10.1126/science.aaw5581
2596:10.1126/science.abp8064
2461:. Zürich, Switzerland:
2459:iis-projects.ee.ethz.ch
2318:back end of line (BEOL)
2300:Back end of line (BEOL)
2266:
1616:
1577:back end of line (BEOL)
1369:5D optical data storage
1186:3D optical data storage
909:Universal Flash Storage
314:Replication (computing)
259:Distributed file system
149:Single-instance storage
127:Direct-attached storage
107:Continuous availability
3454:Technology forecasting
3449:Technological paradigm
3422:Proactionary principle
3340:Software-defined radio
3082:10.1002/adfm.202109970
3017:10.1002/adma.201801548
2911:10.1002/adfm.201804170
2876:10.1002/adma.201870273
2508:Y. van de Burgt et al.
2276:
1682:Von Neumann bottleneck
1665:
1611:electrochromic devices
1596:
1242:Nintendo optical discs
459:Storage virtualization
329:Information repository
269:Distributed data store
3380:Disruptive innovation
3140:Emerging technologies
2640:. pp. 13.1.1–4.
2536:. pp. 35.7.1–4.
2411:. pp. 13.1.1–4.
2360:Nature Communications
2293:semiconductor foundry
2287:Semiconductor foundry
2274:
2241:phosphosilicate glass
1676:can be leveraged for
1663:
1622:state of the device.
1594:
745:Mellon optical memory
733:Williams–Kilburn tube
449:Locality of reference
254:Clustered file system
80:Memory access pattern
3427:Technological change
3370:Collingridge dilemma
3167:Ambient intelligence
1886:Cell implementations
1441:Magnetic-core memory
1088:Digital Data Storage
1048:Quadruplex videotape
489:In-memory processing
379:Information transfer
274:Distributed database
137:Storage area network
117:Block (data storage)
3625:Non-volatile memory
3484:Technology scouting
3459:Accelerating change
3189:Machine translation
2961:2020NatCo..11.3134Y
2710:2019Sci...364..570F
2488:E. J. Fuller et al.
2372:2013NatCo...4.2676S
1870:from IBM Research:
1836:Stanford University
1573:logistic regression
1565:Stanford University
1038:Phonograph cylinder
976:Electrochemical RAM
828:Solid-state storage
444:Memory segmentation
142:Block-level storage
3501:Technology roadmap
3214:Speech recognition
3199:Mobile translation
3172:Internet of things
2381:10.1038/ncomms3676
2277:
1907:Write Pulse Length
1666:
1597:
1447:Plated-wire memory
1412:Paper data storage
1058:Magnetic recording
484:In-memory database
469:Memory-mapped file
414:Volume boot record
409:Master boot record
399:Volume (computing)
374:Data communication
299:Data deduplication
3564:IBM Research Blog
3534:
3533:
3353:
3352:
3323:Optical computing
2899:Adv. Funct. Mater
2655:978-1-7281-1987-8
2590:(6605): 539–543.
2551:978-1-7281-4032-2
2426:978-1-7281-1987-8
2261:high-k/metal gate
2218:
2217:
1791:
1790:
1768:up/down asymmetry
1678:in-memory compute
1656:Synaptic function
1522:
1521:
1119:8 mm video format
1043:Phonograph record
862:Flash Core Module
840:Solid-state drive
739:Delay-line memory
698:Computational RAM
601:Scratchpad memory
439:Disk partitioning
164:Unstructured data
90:Secondary storage
16:(Redirected from
3637:
3605:
3593:
3580:
3567:
3554:
3522:
3521:
3469:Horizon scanning
3385:Ephemeralization
3301:Racetrack memory
3236:Extended reality
3231:Cybermethodology
3151:
3150:
3133:
3126:
3119:
3110:
3109:
3103:
3102:
3084:
3060:
3049:
3043:
3037:
3036:
3000:
2991:
2990:
2980:
2940:
2931:
2930:
2890:
2881:
2880:
2878:
2854:
2845:
2844:
2834:
2824:
2800:
2794:
2793:
2783:
2773:
2749:
2740:
2739:
2721:
2689:
2680:
2677:D. Bishop et al.
2674:
2668:
2667:
2633:
2624:
2623:
2581:
2573:
2564:
2563:
2529:
2514:
2505:
2494:
2484:
2473:
2472:
2470:
2469:
2451:
2445:
2444:
2442:
2441:
2400:
2394:
2393:
2383:
2351:
2193:
2188:
2187:
2186:
2175:
2174:
2173:
2156:
2151:
2150:
2149:
2138:
2137:
2136:
2119:
2114:
2113:
2112:
2101:
2100:
2099:
2082:
2074:
2073:
2072:
2055:
2049:
2048:
2047:
2036:
2035:
2034:
2017:
2009:
2008:
2007:
1990:
1984:
1983:
1982:
1974:
1973:
1962:
1961:
1960:
1943:
1937:
1936:
1935:
1924:
1923:
1922:
1895:
1894:
1881:
1857:
1811:back-propagation
1717:
1716:
1633:gate capacitance
1557:analog computing
1514:
1507:
1500:
1459:Thin-film memory
1453:Core rope memory
1379:Universal memory
1342:Millipede memory
1332:Racetrack memory
1297:Ultra HD Blu-ray
1109:Linear Tape-Open
1063:Magnetic storage
1031:Analog recording
474:Software entropy
434:Disk aggregation
194:Data degradation
179:Data compression
75:Memory hierarchy
65:Memory coherence
37:
36:
21:
3645:
3644:
3640:
3639:
3638:
3636:
3635:
3634:
3610:
3609:
3608:
3596:
3540:
3535:
3530:
3510:
3349:
3160:
3157:
3156:Information and
3142:
3137:
3107:
3106:
3075:(12): 2109970.
3061:
3052:
3044:
3040:
3011:(34): 1801548.
3001:
2994:
2941:
2934:
2905:(42): 1804170.
2891:
2884:
2855:
2848:
2801:
2797:
2750:
2743:
2704:(6440): 570–4.
2690:
2683:
2675:
2671:
2656:
2634:
2627:
2574:
2567:
2552:
2530:
2517:
2506:
2497:
2485:
2476:
2467:
2465:
2453:
2452:
2448:
2439:
2437:
2427:
2401:
2397:
2352:
2348:
2343:
2327:
2302:
2289:
2269:
2253:
2232:
2223:
2191:
2185:
2182:
2181:
2180:
2178:
2172:
2170:
2169:
2168:
2166:
2154:
2148:
2145:
2144:
2143:
2141:
2135:
2133:
2132:
2131:
2129:
2117:
2111:
2108:
2107:
2106:
2104:
2098:
2096:
2095:
2094:
2092:
2080:
2071:
2069:
2068:
2067:
2065:
2053:
2046:
2043:
2042:
2041:
2039:
2033:
2031:
2030:
2029:
2027:
2015:
2006:
2004:
2003:
2002:
2000:
1988:
1981:
1978:
1977:
1976:
1972:
1969:
1968:
1967:
1965:
1959:
1957:
1956:
1955:
1953:
1941:
1934:
1931:
1930:
1929:
1927:
1921:
1919:
1918:
1917:
1915:
1891:
1888:
1879:
1864:
1855:
1846:resulting in a
1824:
1819:
1727:
1715:
1671:
1658:
1641:
1628:
1619:
1602:
1589:
1518:
1489:
1488:
1407:
1399:
1398:
1352:Patterned media
1322:
1314:
1313:
1181:
1171:
1170:
1166:Hard disk drive
1033:
1023:
1022:
1003:
992:
991:
946:
936:
935:
857:IBM FlashSystem
852:USB flash drive
791:
774:
773:
728:
720:
719:
708:Dual-ported RAM
586:
569:
568:
529:Cloud computing
389:Copy protection
309:Data redundancy
239:Shared resource
209:Data validation
184:Data corruption
159:Structured data
70:Cache coherence
55:
41:Computer memory
35:
28:
23:
22:
15:
12:
11:
5:
3643:
3633:
3632:
3627:
3622:
3607:
3606:
3594:
3581:
3568:
3555:
3541:
3539:
3538:External links
3536:
3532:
3531:
3529:
3528:
3515:
3512:
3511:
3509:
3508:
3503:
3498:
3493:
3488:
3487:
3486:
3481:
3476:
3471:
3466:
3461:
3451:
3446:
3441:
3436:
3435:
3434:
3424:
3419:
3414:
3413:
3412:
3407:
3402:
3397:
3387:
3382:
3377:
3372:
3367:
3361:
3359:
3355:
3354:
3351:
3350:
3348:
3347:
3342:
3337:
3336:
3335:
3325:
3320:
3319:
3318:
3313:
3308:
3303:
3298:
3293:
3288:
3283:
3278:
3273:
3268:
3260:
3255:
3254:
3253:
3248:
3238:
3233:
3228:
3223:
3218:
3217:
3216:
3211:
3206:
3201:
3196:
3194:Machine vision
3191:
3186:
3176:
3175:
3174:
3163:
3161:
3158:communications
3154:
3148:
3144:
3143:
3136:
3135:
3128:
3121:
3113:
3105:
3104:
3050:
3038:
2992:
2932:
2882:
2846:
2795:
2741:
2681:
2669:
2654:
2625:
2565:
2550:
2515:
2495:
2474:
2446:
2425:
2395:
2345:
2344:
2342:
2339:
2326:
2323:
2301:
2298:
2288:
2285:
2268:
2265:
2259:materials and
2252:
2249:
2231:
2228:
2222:
2219:
2216:
2215:
2213:
2210:
2207:
2204:
2200:
2199:
2197:
2194:
2189:
2183:
2176:
2171:
2163:
2162:
2160:
2157:
2152:
2146:
2139:
2134:
2126:
2125:
2123:
2120:
2115:
2109:
2102:
2097:
2089:
2088:
2086:
2083:
2078:
2075:
2070:
2062:
2061:
2059:
2056:
2050:
2044:
2037:
2032:
2024:
2023:
2021:
2018:
2013:
2010:
2005:
1997:
1996:
1994:
1991:
1985:
1979:
1970:
1963:
1958:
1950:
1949:
1947:
1944:
1938:
1932:
1925:
1920:
1912:
1911:
1908:
1905:
1902:
1899:
1887:
1884:
1863:
1860:
1823:
1820:
1818:
1815:
1789:
1788:
1785:
1780:
1776:
1775:
1772:
1769:
1765:
1764:
1761:
1758:
1754:
1753:
1750:
1747:
1743:
1742:
1739:
1734:
1730:
1729:
1724:
1721:
1714:
1711:
1670:
1667:
1657:
1654:
1640:
1637:
1627:
1624:
1618:
1615:
1601:
1598:
1588:
1585:
1520:
1519:
1517:
1516:
1509:
1502:
1494:
1491:
1490:
1487:
1486:
1480:
1474:
1471:Twistor memory
1468:
1462:
1456:
1450:
1444:
1438:
1432:
1427:
1421:
1415:
1408:
1405:
1404:
1401:
1400:
1397:
1396:
1391:
1389:Quantum memory
1386:
1381:
1376:
1371:
1366:
1365:
1364:
1354:
1349:
1344:
1339:
1334:
1329:
1323:
1321:In development
1320:
1319:
1316:
1315:
1312:
1311:
1306:
1305:
1304:
1299:
1294:
1289:
1284:
1279:
1274:
1269:
1264:
1259:
1254:
1249:
1244:
1239:
1234:
1232:Super Video CD
1229:
1224:
1219:
1214:
1209:
1204:
1198:
1193:
1182:
1177:
1176:
1173:
1172:
1169:
1168:
1163:
1162:
1161:
1156:
1151:
1146:
1141:
1136:
1131:
1126:
1121:
1116:
1111:
1106:
1101:
1096:
1091:
1085:
1080:
1075:
1070:
1065:
1055:
1050:
1045:
1040:
1034:
1029:
1028:
1025:
1024:
1021:
1020:
1015:
1010:
1004:
998:
997:
994:
993:
990:
989:
984:
979:
973:
968:
958:
953:
947:
942:
941:
938:
937:
934:
933:
928:
927:
926:
921:
916:
911:
906:
901:
896:
891:
889:MultiMediaCard
886:
881:
876:
866:
865:
864:
859:
854:
849:
843:
837:
825:
820:
819:
818:
813:
803:
798:
792:
787:
786:
783:
782:
776:
775:
772:
771:
765:
759:
754:
751:Selectron tube
748:
742:
736:
729:
726:
725:
722:
721:
718:
717:
716:
715:
705:
700:
695:
689:
684:
679:
678:
677:
667:
666:
665:
660:
655:
650:
645:
640:
635:
630:
625:
620:
615:
605:
604:
603:
598:
591:Hardware cache
587:
582:
581:
578:
577:
571:
570:
567:
566:
561:
556:
551:
546:
544:Edge computing
541:
536:
531:
526:
524:Grid computing
521:
519:Bank switching
516:
511:
506:
501:
496:
491:
486:
481:
476:
471:
466:
464:Virtual memory
461:
456:
451:
446:
441:
436:
431:
429:Disk mirroring
426:
421:
416:
411:
406:
401:
396:
391:
386:
384:Temporary file
381:
376:
371:
366:
361:
356:
351:
346:
341:
336:
334:Knowledge base
331:
326:
324:Storage record
321:
319:Memory refresh
316:
311:
306:
304:Data structure
301:
296:
291:
286:
281:
276:
271:
266:
261:
256:
251:
246:
241:
236:
231:
226:
221:
216:
211:
206:
201:
199:Data integrity
196:
191:
189:Data cleansing
186:
181:
176:
171:
166:
161:
156:
151:
146:
145:
144:
139:
129:
124:
122:Object storage
119:
114:
109:
104:
103:
102:
92:
87:
82:
77:
72:
67:
62:
56:
53:
52:
49:
48:
26:
9:
6:
4:
3:
2:
3642:
3631:
3628:
3626:
3623:
3621:
3618:
3617:
3615:
3604:. 1 May 2019.
3603:
3599:
3595:
3591:
3590:Stanford News
3587:
3582:
3578:
3574:
3569:
3565:
3561:
3556:
3552:
3551:IEEE Spectrum
3548:
3543:
3542:
3527:
3526:
3517:
3516:
3513:
3507:
3506:Transhumanism
3504:
3502:
3499:
3497:
3494:
3492:
3489:
3485:
3482:
3480:
3477:
3475:
3472:
3470:
3467:
3465:
3462:
3460:
3457:
3456:
3455:
3452:
3450:
3447:
3445:
3442:
3440:
3437:
3433:
3430:
3429:
3428:
3425:
3423:
3420:
3418:
3415:
3411:
3408:
3406:
3403:
3401:
3398:
3396:
3393:
3392:
3391:
3388:
3386:
3383:
3381:
3378:
3376:
3373:
3371:
3368:
3366:
3363:
3362:
3360:
3356:
3346:
3343:
3341:
3338:
3334:
3333:Chipless RFID
3331:
3330:
3329:
3326:
3324:
3321:
3317:
3314:
3312:
3309:
3307:
3304:
3302:
3299:
3297:
3294:
3292:
3289:
3287:
3284:
3282:
3279:
3277:
3274:
3272:
3269:
3267:
3264:
3263:
3261:
3259:
3256:
3252:
3249:
3247:
3244:
3243:
3242:
3239:
3237:
3234:
3232:
3229:
3227:
3224:
3222:
3219:
3215:
3212:
3210:
3207:
3205:
3202:
3200:
3197:
3195:
3192:
3190:
3187:
3185:
3182:
3181:
3180:
3177:
3173:
3170:
3169:
3168:
3165:
3164:
3162:
3159:
3152:
3149:
3145:
3141:
3134:
3129:
3127:
3122:
3120:
3115:
3114:
3111:
3100:
3096:
3092:
3088:
3083:
3078:
3074:
3070:
3066:
3059:
3057:
3055:
3047:
3046:J. Lee et al.
3042:
3034:
3030:
3026:
3022:
3018:
3014:
3010:
3006:
2999:
2997:
2988:
2984:
2979:
2974:
2970:
2966:
2962:
2958:
2954:
2950:
2946:
2939:
2937:
2928:
2924:
2920:
2916:
2912:
2908:
2904:
2900:
2896:
2889:
2887:
2877:
2872:
2868:
2864:
2860:
2853:
2851:
2842:
2838:
2833:
2828:
2823:
2818:
2814:
2810:
2806:
2799:
2791:
2787:
2782:
2777:
2772:
2767:
2763:
2759:
2755:
2748:
2746:
2737:
2733:
2729:
2725:
2720:
2715:
2711:
2707:
2703:
2699:
2695:
2688:
2686:
2678:
2673:
2665:
2661:
2657:
2651:
2647:
2643:
2639:
2632:
2630:
2621:
2617:
2613:
2609:
2605:
2601:
2597:
2593:
2589:
2585:
2580:
2572:
2570:
2561:
2557:
2553:
2547:
2543:
2539:
2535:
2528:
2526:
2524:
2522:
2520:
2513:
2509:
2504:
2502:
2500:
2493:
2489:
2483:
2481:
2479:
2464:
2460:
2456:
2450:
2436:
2432:
2428:
2422:
2418:
2414:
2410:
2406:
2399:
2391:
2387:
2382:
2377:
2373:
2369:
2365:
2361:
2357:
2350:
2346:
2338:
2336:
2332:
2322:
2319:
2315:
2311:
2310:silicon wafer
2307:
2297:
2294:
2284:
2282:
2273:
2264:
2262:
2258:
2248:
2246:
2242:
2238:
2227:
2214:
2211:
2208:
2205:
2202:
2201:
2198:
2195:
2190:
2177:
2165:
2164:
2161:
2158:
2155:0.025 mm
2153:
2140:
2128:
2127:
2124:
2121:
2116:
2103:
2091:
2090:
2087:
2084:
2081:0.001 mm
2079:
2076:
2064:
2063:
2060:
2057:
2051:
2038:
2026:
2025:
2022:
2019:
2014:
2011:
1999:
1998:
1995:
1992:
1986:
1964:
1952:
1951:
1948:
1945:
1939:
1926:
1914:
1913:
1909:
1906:
1903:
1900:
1897:
1896:
1893:
1883:
1875:
1871:
1869:
1859:
1851:
1849:
1843:
1841:
1837:
1833:
1829:
1814:
1812:
1806:
1804:
1800:
1796:
1786:
1784:
1781:
1778:
1777:
1773:
1770:
1767:
1766:
1762:
1759:
1756:
1755:
1751:
1748:
1745:
1744:
1740:
1738:
1735:
1732:
1731:
1726:NVM synaptic
1725:
1722:
1719:
1718:
1710:
1708:
1704:
1699:
1695:
1691:
1687:
1683:
1679:
1675:
1662:
1653:
1650:
1646:
1636:
1634:
1623:
1614:
1612:
1608:
1607:battery cells
1593:
1584:
1582:
1578:
1574:
1570:
1566:
1562:
1558:
1554:
1550:
1546:
1542:
1538:
1537:deep learning
1535:designed for
1534:
1530:
1527:is a type of
1526:
1515:
1510:
1508:
1503:
1501:
1496:
1495:
1493:
1492:
1484:
1481:
1478:
1477:Bubble memory
1475:
1472:
1469:
1466:
1463:
1460:
1457:
1454:
1451:
1448:
1445:
1442:
1439:
1436:
1433:
1431:
1428:
1425:
1422:
1419:
1416:
1413:
1410:
1409:
1403:
1402:
1395:
1392:
1390:
1387:
1385:
1382:
1380:
1377:
1375:
1372:
1370:
1367:
1363:
1360:
1359:
1358:
1355:
1353:
1350:
1348:
1345:
1343:
1340:
1338:
1335:
1333:
1330:
1328:
1325:
1324:
1318:
1317:
1310:
1307:
1303:
1300:
1298:
1295:
1293:
1290:
1288:
1285:
1283:
1280:
1278:
1275:
1273:
1270:
1268:
1265:
1263:
1260:
1258:
1255:
1253:
1250:
1248:
1245:
1243:
1240:
1238:
1235:
1233:
1230:
1228:
1225:
1223:
1220:
1218:
1215:
1213:
1210:
1208:
1205:
1202:
1199:
1197:
1194:
1192:
1189:
1188:
1187:
1184:
1183:
1180:
1175:
1174:
1167:
1164:
1160:
1157:
1155:
1152:
1150:
1147:
1145:
1142:
1140:
1137:
1135:
1132:
1130:
1127:
1125:
1122:
1120:
1117:
1115:
1112:
1110:
1107:
1105:
1104:Cassette tape
1102:
1100:
1099:Videocassette
1097:
1095:
1092:
1089:
1086:
1084:
1081:
1079:
1076:
1074:
1071:
1069:
1068:Magnetic tape
1066:
1064:
1061:
1060:
1059:
1056:
1054:
1051:
1049:
1046:
1044:
1041:
1039:
1036:
1035:
1032:
1027:
1026:
1019:
1016:
1014:
1011:
1009:
1006:
1005:
1002:
996:
995:
988:
985:
983:
980:
977:
974:
972:
969:
966:
962:
959:
957:
954:
952:
949:
948:
945:
940:
939:
932:
929:
925:
922:
920:
917:
915:
912:
910:
907:
905:
902:
900:
897:
895:
892:
890:
887:
885:
882:
880:
877:
875:
872:
871:
870:
867:
863:
860:
858:
855:
853:
850:
847:
844:
841:
838:
835:
832:
831:
829:
826:
824:
823:ROM cartridge
821:
817:
814:
812:
809:
808:
807:
804:
802:
799:
797:
794:
793:
790:
785:
784:
781:
778:
777:
769:
766:
763:
760:
758:
755:
752:
749:
746:
743:
740:
737:
734:
731:
730:
724:
723:
714:
711:
710:
709:
706:
704:
701:
699:
696:
693:
690:
688:
685:
683:
680:
676:
673:
672:
671:
668:
664:
661:
659:
656:
654:
651:
649:
646:
644:
641:
639:
636:
634:
631:
629:
626:
624:
621:
619:
616:
614:
611:
610:
609:
606:
602:
599:
597:
594:
593:
592:
589:
588:
585:
580:
579:
576:
573:
572:
565:
562:
560:
557:
555:
552:
550:
549:Dew computing
547:
545:
542:
540:
539:Fog computing
537:
535:
534:Cloud storage
532:
530:
527:
525:
522:
520:
517:
515:
514:Memory paging
512:
510:
507:
505:
502:
500:
497:
495:
492:
490:
487:
485:
482:
480:
477:
475:
472:
470:
467:
465:
462:
460:
457:
455:
452:
450:
447:
445:
442:
440:
437:
435:
432:
430:
427:
425:
422:
420:
417:
415:
412:
410:
407:
405:
402:
400:
397:
395:
392:
390:
387:
385:
382:
380:
377:
375:
372:
370:
367:
365:
362:
360:
357:
355:
352:
350:
349:File deletion
347:
345:
342:
340:
339:Computer file
337:
335:
332:
330:
327:
325:
322:
320:
317:
315:
312:
310:
307:
305:
302:
300:
297:
295:
292:
290:
287:
285:
282:
280:
277:
275:
272:
270:
267:
265:
262:
260:
257:
255:
252:
250:
247:
245:
242:
240:
237:
235:
232:
230:
227:
225:
222:
220:
219:Data recovery
217:
215:
212:
210:
207:
205:
204:Data security
202:
200:
197:
195:
192:
190:
187:
185:
182:
180:
177:
175:
172:
170:
167:
165:
162:
160:
157:
155:
152:
150:
147:
143:
140:
138:
135:
134:
133:
130:
128:
125:
123:
120:
118:
115:
113:
110:
108:
105:
101:
100:floating-gate
98:
97:
96:
93:
91:
88:
86:
83:
81:
78:
76:
73:
71:
68:
66:
63:
61:
58:
57:
51:
50:
46:
42:
39:
38:
33:
19:
3630:Types of RAM
3601:
3589:
3576:
3563:
3550:
3523:
3410:Robot ethics
3270:
3209:Semantic Web
3072:
3068:
3045:
3041:
3008:
3004:
2952:
2948:
2902:
2898:
2866:
2862:
2812:
2808:
2798:
2761:
2757:
2701:
2697:
2676:
2672:
2637:
2587:
2583:
2533:
2507:
2487:
2466:. Retrieved
2458:
2449:
2438:. Retrieved
2408:
2398:
2363:
2359:
2349:
2328:
2303:
2290:
2278:
2254:
2233:
2224:
2192:0.01 mm
2118:0.05 mm
1889:
1876:
1872:
1867:
1865:
1862:IBM Research
1852:
1844:
1827:
1825:
1807:
1803:IBM Research
1792:
1746:on/off ratio
1728:cell target
1713:Requirements
1672:
1642:
1629:
1620:
1603:
1524:
1523:
1424:Punched tape
1418:Punched card
1384:Time crystal
1346:
1252:Hyper CD-ROM
1191:Optical disc
1083:Tape library
1018:FeFET memory
999:Early-stage
975:
879:CompactFlash
874:Memory Stick
834:Flash memory
796:Diode matrix
780:Non-volatile
564:Kryder's law
554:Amdahl's law
479:Software rot
454:Logical disk
354:File copying
289:Data storage
244:File sharing
229:Data cluster
45:data storage
3474:Moore's law
3405:Neuroethics
3400:Cyberethics
3221:Atomtronics
2955:(1): 3134.
2869:: 1870273.
1942:100 nm
1904:Device Size
1757:# of states
1559:. Notably,
1541:electrolyte
1483:Floppy disk
1435:Drum memory
869:Memory card
836:is used in:
770:(2002–2010)
735:(1946–1947)
559:Moore's law
404:Boot sector
344:Object file
249:File system
60:Memory cell
3614:Categories
3602:inside HPC
3365:Automation
3005:Adv. Mater
2949:Nat Commun
2863:Adv. Mater
2468:2020-07-16
2463:ETH Zurich
2440:2020-07-16
2341:References
2016:36 μm
1910:Reference
1838:, and the
1779:write time
1406:Historical
1078:Tape drive
904:SmartMedia
727:Historical
424:Disk image
419:Disk array
294:Data store
95:MOS memory
85:Memory map
3395:Bioethics
3281:Millipede
3099:244484634
3091:1616-301X
2927:104934211
2736:133605392
2620:251159631
2604:0036-8075
2560:211211273
2206:2D MXene
2077:PEDOT:PSS
2054:1 mm
1989:1 mm
1686:Kirchhoff
1669:Principle
1587:Operation
1465:Disk pack
1430:Plugboard
1267:DVD-Video
1196:LaserDisc
1094:Videotape
965:3D XPoint
956:Memristor
596:CPU cache
364:Core dump
284:Data bank
234:Directory
3577:MIT News
3316:UltraRAM
3033:49655665
3025:29974526
2987:32561717
2841:32174807
2790:27493624
2728:31023890
2664:58674536
2612:35901152
2435:58674536
2390:24177330
2366:: 2676.
2251:MO-ECRAM
2221:Li-ECRAM
2012:Graphene
1394:UltraRAM
1272:DVD card
1227:Video CD
1212:CD Video
982:Nano-RAM
951:Memistor
924:XQD card
899:SIM card
757:Dekatron
643:XDR DRAM
638:EDO DRAM
575:Volatile
369:Hex dump
279:Database
174:Metadata
169:Big data
3262:Memory
2978:7371700
2957:Bibcode
2919:1472248
2832:7054461
2815:: 103.
2781:4954855
2764:: 333.
2706:Bibcode
2698:Science
2584:Science
2368:Bibcode
2230:H-ECRAM
2212:200 ns
2209:100 μm
1901:Channel
1733:G range
1688:'s and
1479:(~1970)
1473:(~1968)
1455:(1960s)
1292:Blu-ray
1282:MiniDVD
1277:DVD-RAM
1237:Mini CD
1179:Optical
1139:U-matic
1134:MicroMV
1114:Betamax
978:(ECRAM)
919:MicroP2
894:SD card
884:PC Card
675:1T-SRAM
633:QDRSRAM
224:Storage
54:General
32:Synapse
3390:Ethics
3358:Topics
3147:Fields
3097:
3089:
3031:
3023:
2985:
2975:
2925:
2917:
2839:
2829:
2788:
2778:
2734:
2726:
2662:
2652:
2618:
2610:
2602:
2558:
2548:
2433:
2423:
2388:
2159:210 ms
1940:100 x
1720:Metric
1639:Arrays
1485:(1971)
1467:(1962)
1461:(1962)
1449:(1957)
1443:(1949)
1437:(1932)
1426:(1725)
1420:(1725)
1414:(1725)
1287:HD DVD
1247:CD-ROM
1203:(CDDA)
1129:MiniDV
848:(SSHD)
830:(SSS)
816:EEPROM
764:(2009)
753:(1952)
747:(1951)
741:(1947)
359:Backup
3311:SONOS
3271:ECRAM
3266:CBRAM
3258:GPGPU
3095:S2CID
3029:S2CID
2923:S2CID
2732:S2CID
2660:S2CID
2616:S2CID
2556:S2CID
2431:S2CID
2257:OxRam
2196:0.1 s
2058:10 ms
2020:10 ms
1993:0.5 s
1830:from
1763:1000
1741:9-72
1626:Speed
1600:Write
1531:with
1347:ECRAM
1327:CBRAM
1262:DVD+R
1222:CD-RW
1159:D-VHS
1154:VHS-C
1149:S-VHS
1090:(DDS)
1013:ReRAM
1008:FeRAM
1001:NVRAM
987:CBRAM
944:NVRAM
842:(SSD)
811:EPROM
768:Z-RAM
762:T-RAM
694:(CAM)
682:ReRAM
648:RDRAM
628:LPDDR
623:SGRAM
618:SDRAM
613:eDRAM
47:types
3525:List
3328:RFID
3306:RRAM
3296:PRAM
3291:NRAM
3286:MRAM
3276:FRAM
3087:ISSN
3021:PMID
2983:PMID
2915:OSTI
2837:PMID
2786:PMID
2724:PMID
2650:ISBN
2608:PMID
2600:ISSN
2546:ISBN
2421:ISBN
2386:PMID
2267:VLSI
2122:5 ms
2085:5 ms
2040:α-MO
1946:5 ns
1760:n.a.
1749:n.a.
1723:Unit
1705:and
1617:Read
1337:NRAM
1309:WORM
1217:CD-R
971:MRAM
806:PROM
801:MROM
703:VRAM
687:QRAM
670:SRAM
658:GDDR
608:DRAM
504:RAID
154:Data
43:and
3077:doi
3013:doi
2973:PMC
2965:doi
2907:doi
2871:doi
2827:PMC
2817:doi
2776:PMC
2766:doi
2714:doi
2702:364
2642:doi
2592:doi
2588:377
2538:doi
2413:doi
2376:doi
2245:KTH
1971:1−x
1898:Ion
1848:XOR
1690:Ohm
1609:or
1257:DVD
1144:VHS
961:PCM
914:SxS
789:ROM
663:HBM
653:DDR
584:RAM
3616::
3600:.
3588:.
3575:.
3562:.
3549:.
3093:.
3085:.
3073:32
3071:.
3067:.
3053:^
3027:.
3019:.
3009:30
3007:.
2995:^
2981:.
2971:.
2963:.
2953:11
2951:.
2947:.
2935:^
2921:.
2913:.
2903:28
2901:.
2897:.
2885:^
2867:30
2865:.
2861:.
2849:^
2835:.
2825:.
2813:14
2811:.
2807:.
2784:.
2774:.
2762:10
2760:.
2756:.
2744:^
2730:.
2722:.
2712:.
2700:.
2696:.
2684:^
2658:.
2648:.
2628:^
2614:.
2606:.
2598:.
2586:.
2582:.
2568:^
2554:.
2544:.
2518:^
2510:,
2498:^
2490:,
2477:^
2457:.
2429:.
2419:.
2407:.
2384:.
2374:.
2362:.
2358:.
2291:A
2203:H
2179:WO
2142:WO
2105:WO
2028:Li
2001:Li
1975:CO
1966:Li
1954:Li
1928:WO
1916:Li
1880:10
1856:10
1842::
1787:1
1783:ns
1774:5
1752:8
1737:nS
1709:.
1696:,
1207:CD
1124:DV
3592:.
3579:.
3566:.
3553:.
3132:e
3125:t
3118:v
3101:.
3079::
3035:.
3015::
2989:.
2967::
2959::
2929:.
2909::
2879:.
2873::
2843:.
2819::
2792:.
2768::
2738:.
2716::
2708::
2666:.
2644::
2622:.
2594::
2562:.
2540::
2486:'
2471:.
2443:.
2415::
2392:.
2378::
2370::
2364:4
2184:3
2167:H
2147:3
2130:H
2110:3
2093:H
2066:H
2052:~
2045:3
1987:~
1980:2
1933:3
1771:%
1513:e
1506:t
1499:v
967:)
963:(
34:.
20:)
Text is available under the Creative Commons Attribution-ShareAlike License. Additional terms may apply.