Page Size Research Articles

SPEC CPU2006 sensitivity to memory page sizes

SPEC CPU2006 is a compute-intensive industry standard benchmark suite published in August 2006. This paper characterizes the memory access behavior of SPEC CPU2006 running on IBM POWER5+ microprocessors. We measure the maximum and average memory usage of the benchmarks to validate SPEC's memory requirement criteria. This paper also analyzes how different page sizes affect the performance of the benchmarks. The experiment reveals that 64 KB and 16 MB pages improve the performance up to 46.9% and 50.9%, respectively.

A 56-nm CMOS 99-${\hbox {mm}}^{2} $ 8-Gb Multi-Level NAND Flash Memory With 10-MB/s Program Throughput

A single 3.3-V only, 8-Gb NAND flash memory with the smallest chip to date, 98.8 mm2, has been successfully developed. This is the world's first integrated semiconductor chip fabricated with 56-nm CMOS technologies. The effective cell size including the select transistors is 0.0075 mum2 per bit, which is the smallest ever reported. To decrease the chip size, a very efficient floor plan with one-sided row decoder, one-sided page buffer, and one-sided pad is introduced. As a result, an excellent 70% cell area efficiency is realized. The program throughput is drastically improved to twice as large as previously reported and comparable to binary memories. The best ever 10-MB/s programming is realized by increasing the page size from 4kB to 8kB. In addition, noise cancellation circuits and the dual VDD-line scheme realize both a small die size and a fast programming. An external page copy achieves a fast 93-ms block copy, efficiently using a 1-MB block size

Effect of the pH of Heating on the Qualitative and Quantitative Compositions of the Sera of Reconstituted Skim Milks and on the Mechanisms of Formation of Soluble Aggregates

The effect of the pH of heating (6.3-7.3) on the composition of sera in reconstituted skimmed milks was investigated. A combination of SDS-PAGE analysis and size exclusion chromatography (SEC) combined with an original approach to the analysis of the SEC profiles was performed. The composition of the sera varied greatly when the pH of heating was adjusted below and above the natural pH of milk. The formation, composition, and concentration of heat-induced soluble complexes depended on the combination of the effect of adjusting the pH of the milk and the heat treatment. Two types of mechanism for the formation of soluble aggregates appeared to exist, depending on the pH of the milk. The first type results from the formation of WP/kappa-casein aggregates at the surface of the micelle, and these were detached partially into the serum in larger amount as the pH increased up to 6.7, where it reaches a maximum. The second type of complexes, whose amount increased as the pH of heating increased from 6.7 to 7.3, may be formed between caseins (kappa- but also perhaps some alpha(s)-casein) and aggregated WP resulting in complexes that are smaller in size and with a higher kappa-casein/whey protein ratio than the first type.

Media tilt tolerance of bit-based and page-based holographic storage systems

Tilt tolerance of media is compared for bit-based and page-based holographic storage systems having an equal diffraction efficiency per bit detector, dynamic range of the medium, and surface recording density. We have formalized the diffraction efficiency degradation caused by aberrations of a reconstructing reference beam induced by tilt of the medium, using a coupled wave theory in the Fourier domain. The bit-based holographic storage system has a larger media tilt tolerance compared with a page-based system with relatively large page size.

Image oversampling for page-oriented optical data storage

Page-oriented data storage systems incorporate optical detector arrays [such as complementary metal-oxide semiconductor (CMOS) arrays] in order to read data images. For laboratory demonstrations the detector array is typically pixel matched to the data image [Opt. Lett. 22, 1509 (1997)]. This approach requires exceedingly high-performance optics and mechanics for the simultaneous alignment of each data-bearing pixel image to a detector element to be achieved. Systems intended for commercialization are designed with detector arrays that spatially sample the image at or above the Nyquist rate in order to read poorly aligned and distorted images [S. Redfield, Holographic Data Storage (Springer-Verlag, 2000), pp. 347-349]. However, for data page sizes exceeding a megapixel this approach becomes prohibitive in terms of detector bandwidth, size, power, cost, and processing requirements. We have instead developed a sub-Nyquist oversampling methodology that can recover arbitrarily aligned and distorted megapixel data page images with pixel-matched fidelity by using fewer than double the number of detector pixels. Features required for practicable implementation are described, including fiducials for alignment determination.

SmartApps

One general avenue to obtain optimized performance on large and complex systems is to approach optimization from a global perspective of the complete system in a customized manner for each application, i.e., application-centric optimization . Lately, there have been encouraging developments in reconfigurable operating systems and hardware that will enable customized optimization. For example, machines built with PIM's and FPGA's can be quickly reconfigured to better fit a certain application and operating systems, such as IBM's K42, can have their services customized to fit the needs and characteristics of an application. While progress in operating system and hardware and hardware has made re-configuration possible, we still need strategies and techniques to exploit them for improved application performance.In this paper, we describe the approach we are using in our smart application (SMARTAPPS) project. In the SMARTAPP executable, the compiler embeds most run-time system services and a feedback loop to monitor performance and trigger run-time adaptations. At run-time, after incorporating the code's input and determining the system's state, the SMARTAPP performs an instance specific optimization. During execution, the application continually monitors its performance and the available resources to determine if restructuring should occur. The framework includes mechanisms for performing the actual restructuring at various levels including: algorithmic adaptation, tuning reconfigurable OS services (scheduling policy, page size, etc.), and system configuration (e.g., number of processors). This paper concentrates on the techniques for providing customized system services for communication, thread scheduling, memory management, and performance monitoring and modeling.

Foundations of Biogeography: Classic Papers with Commentaries (review)

Reviewed by: Foundations of Biogeography: Classic Papers with Commentaries Bruce D. Patterson Foundations of Biogeography: Classic Papers with Commentaries. Edited by Mark V. Lomolino, Dov F. Sax, and James H. Brown . Chicago: Univ. of Chicago Press, 2004. Pp. 1,238. $135 (cloth), $45 (paper). Biogeography, the study of patterns and processes shaping the distribution of life, has been a recurring part of curricula in biology for the last century or two, but only lately has it asserted its maturity. Despite illustrious expositors throughout history—from Alexander von Humboldt to E. O. Wilson—biogeography has mainly been pursued by scientists from other disciplines. And because biotic distributions are shaped by behavior, ecology, physiology, systematics, climate, and geology, scientists from each of these fields have introduced their own approaches, paradigms, and preferred interpretations to its practice. For some time, this cross-fertilization of biogeography by diverse scientific traditions has been at once the field's greatest asset and crippling legacy. After all, didn't Charles Darwin and Alfred Russel Wallace achieve their revolutionary insights into evolution by natural selection by studying biological variation within a geographic [End Page 152] context? One still senses the great potential of biogeography to foster other major scientific revolutions and consequently cranes an ear at every cry of "Eu-reka!" At the same time, synthesis and unification have remained elusive, and more often than not one hears instead a clamorous din. In this book, editors Mark Lomolino, Dov Sax, and Jim Brown offer copious evidence both of biogeography's hybrid ancestry and its methodological and conceptual richness. They sought to produce a collection of fundamental contributions to biogeography that could serve as a unified and easily accessible foundation for future development. All three are leaders of the newly organized International Biogeography Society (www.biogeography.org), drawn from the dominant phalanx of geographical ecologists. Brown and Lomolino are also authors of the most comprehensive and copiously documented textbook on biogeography now available, and all three contribute importantly to the primary literature. And if these credentials were not enough, the editors convened a quorum of 20 biogeographers from various fields at the National Center for Ecological Analysis and Synthesis in Santa Barbara (October 1–4, 2000) to help them frame the field and identify its intellectual heritage in the form of seminal ideas and publications. This volume is a result of that dialogue, and many of its section editors and essayists were participants in the Santa Barbara meetings. The volume is a collection of 72 articles (or excerpts of articles) that largely span the scope of biogeography and that carry its size to the limits of single-volume bindings. The book is divided into eight parts, each prefaced by a contemporary essay/overview: early classics (including articles published from 1761 to 1953); earth history, vicariance, and dispersal (1924 to 1982); species ranges (1922 to 1979); revolutions in historical biogeography (1962 to 1978); diversification (1942 to 1972); the importance of islands (1921 to 1982); assembly rules (1946 to 1979); and gradients in species diversity (1950 to 1975). There can be little doubt that the collection of original papers will be useful for modern students and professionals alike. There can't be 10 scientists in the world that had all of these works in their working library prior to this collection, and many classics are, in their original versions, beyond the reach of all but the most tenacious library-loan systems. Selected by committee, they include many classical works and omit few papers of comparable stature—although one conspicuous absence is an excerpt from Andrewartha and Birch's classic book The Distribution and Abundance of Animals (1954), an eloquent demonstration that distribution and abundance were different facets of the same phenomenon that admitted a wealth of additional data and methods to biogeographic analysis. The articles themselves are clearly reprinted in facsimile form, buffering (but not eliminating altogether) the diverse page sizes, type sizes and fonts, and formatting of the original works. Page headers that identify section and volume pagination is helpful for orientation within the volume; footers focused on the classic papers themselves might have helped readers keep track of particular articles. The essays that introduce each part of the book...

Improving website accessibility for people with early-stage dementia: A preliminary investigation

This study, conducted collaboratively with five men who have a diagnosis of early-stage Alzheimer's disease (AD), is the first stage of a formative research project aimed at developing a new website for people with dementia. Recommendations derived from a literature review of the implications of dementia-related cognitive changes for website design were combined with general web accessibility guidelines to provide a basis for the initial design of a new website. This website was compared with an equivalent site, containing the same information but based on an existing design, in terms of accessibility, ease of use, and user satisfaction. Participants were very satisfied with both sites, but responses did indicate some specific areas where one site was preferred over another. Observational data highlighted significant strengths of the new site as well as some limitations, and resulted in clear recommendations for enhancing the design. In particular, the study suggested that limiting the size of web pages to the amount of information that can be displayed on a computer screen at any one time could reduce the level of difficulty encountered by the participants. The results also suggested the importance of reducing cognitive load through limiting the number of choices required at any one time, the very opposite of the ethos of much website design.

Historical Atlas of Central America

All scholars of Central America and the Western Hemisphere will welcome this reference work, the first comprehensive atlas of the region, containing carefully researched maps that provide insights into the history of the Central American isthmus. The volume contains over five hundred full-color maps detailing the region’s locational and physical characteristics, its demography, cultures, and history. Carefully prepared by two geographers and a historian, the oversized volume is organized into two-page sections; each includes several maps and a brief text narrating the events portrayed in the maps, in many cases accompanied by graphs, charts, and photos. The maps were prepared first, with the text designed to complement the maps. The preface states that the work seeks to encompass “a detailed cartographic survey of Central America’s development” and “a text offering a new interpretation” (p. xi). The text’s balanced narration of the historical events reflects prevailing historical interpretations, as is appropriate for a reference work. The authors stress that “the complexity and diversity of Central America exceeds those of many areas that are far larger” (p. xi) and that the isthmus played a central role in global and regional transportation.Reflecting this isthmian outlook, both the maps and accompanying narratives focus on the common elements, regionwide trends, and events of broad significance, rather than events in particular sections or the individual countries. Adopting and laying out clearly a broad definition of the region, the work extends outside the confines of the colonial Captaincy General of Central America to include Belize and Panama. Other areas that at times were governed through and considered part of this colonial jurisdiction (such as portions of southern Mexico and the Yucatán) are also included. Residents of the isthmus do not always include areas beyond the five core countries when discussing Central America.The initial pages use maps, charts, and graphs to provide comparative data on the physical, geological, climatic, and environmental dimensions of the region and place the region in its global setting. Coverage of the colonial era deals not just with the Spanish Empire but also with struggles between competing colonial powers to gain control of the region. Detailed maps cover such aspects as the movements of the conquistadores, set-tlement and population patterns, towns, encomiendas, land use, haciendas, commercial networks, and trade. Due consideration is also given to the situation of the Indians, the church, and such aspects as pirates, fortifications, transport, and transisthmian routes. The maps of colonial jurisdictions clearly demonstrate the origins of postindependence boundary disputes. The two chapters covering the postcolonial era include maps tracing conflicts and uprisings, as well as economic aspects such as crops, industrialization, shipping lines, transportation routes, and urbanization. Scholars will undoubtedly find the detailed maps tracing the expansion of key crops, the changing balance of the economic importance of the key urban centers, and such aspects as health and education, poverty, migrants and refugees, agrarian reform, and environmental characteristics, most useful, since they provide unique regional perspectives.Inevitably, a work of this type involves editorial decisions that will surprise some users. Seeing an oversized volume labeled as an atlas, the typical reader is likely to be surprised to find that there are few full-page maps. Rather, there are typically several smaller maps on each two-page spread and relatively few full-page ones. This partly reflects the shape and size of Central America in relation to the page size. There are several regional maps spread over two facing pages, but they overlap rather than fitting together into a single overview. This organization reflects the decision to include narration as well as the maps, charts, and graphs, while limiting each topical section to a single spread. Reflecting the authors’ determination to focus on regionwide perspectives, the volume lacks detailed full-page maps of individual nations. Although some maps show the distribution of items by provinces within different nations, there are no maps labeling provinces by name. While the authors can assume that scholars using the atlas will already be familiar with the provinces, since this is intended as a reference work, some users would undoubtedly have appreciated full-page political maps of each country.This volume constitutes a valuable contribution to the study of Central America and will be useful to both scholars of the region and to general users wishing to learn about Central America. It will become an essential item for all university and research libraries and for scholars in all disciplines who study Central America.

TEA CO 2 Laser Simulator: A software tool to predict the output pulse characteristics of TEA CO 2 laser

“TEA CO 2 Laser Simulator” has been designed to simulate the dynamic emission processes of the TEA CO 2 laser based on the six-temperature model. The program predicts the behavior of the laser output pulse (power, energy, pulse duration, delay time, FWHM, etc.) depending on the physical and geometrical input parameters (pressure ratio of gas mixture, reflecting area of the output mirror, media length, losses, filling and decay factors, etc.). Program summary Title of program: TEA_CO2 Catalogue identifier: ADVW Program summary URL: http://cpc.cs.qub.ac.uk/summaries/ADVW Program obtainable from: CPC Program Library, Queen's University of Belfast, N. Ireland Computer: P.IV DELL PC Setup: Atomic Energy Commission of Syria, Scientific Services Department, Mathematics and Informatics Division Operating system: MS-Windows 9x, 2000, XP Programming language: Delphi 6.0 No. of lines in distributed program, including test data, etc.: 47 315 No. of bytes in distributed program, including test data, etc.:7 681 109 Distribution format:tar.gz Classification: 15 Laser Physics Nature of the physical problem: “TEA CO 2 Laser Simulator” is a program that predicts the behavior of the laser output pulse by studying the effect of the physical and geometrical input parameters on the characteristics of the output laser pulse. The laser active medium consists of a CO 2–N 2–He gas mixture. Method of solution: Six-temperature model, for the dynamics emission of TEA CO 2 laser, has been adapted in order to predict the parameters of laser output pulses. A simulation of the laser electrical pumping was carried out using two approaches; empirical function equation (8) and differential equation (9). Typical running time: The program's running time mainly depends on both integration interval and step; for a 4 μs period of time and 0.001 μs integration step (defaults values used in the program), the running time will be about 4 seconds. Restrictions on the complexity: Using a very small integration step might leads to stop the program run due to the huge number of calculating points and to a small paging file size of the MS-Windows virtual memory. In such case, it is recommended to enlarge the paging file size to the appropriate size, or to use a bigger value of integration step.

ARC based superpaging

This paper explores the use of the ARC algorithm for swapping policy in superpaging systems. The different page sizes can affect the algorithm and as a result the algorithm will not be as effective as the original one for traditional paging systems. We suggest to modify the threshold of the ARC algorithm, so it will give more weight to the frequently accessed pages and less weight to the recent pages.

Optimizing instruction TLB energy using software and hardware techniques

Power consumption and power density for the Translation Look-aside Buffer (TLB) are important considerations not only in its design, but can have a consequence on cache design as well. After pointing out the importance of instruction TLB (iTLB) power optimization, this article embarks on a new philosophy for reducing the number of accesses to this structure. The overall idea is to keep a translation currently being used in a register and avoid going to the iTLB as far as possible---until there is a page change. We propose four different approaches for achieving this, and experimentally demonstrate that one of these schemes that uses a combination of compiler and hardware enhancements can reduce iTLB dynamic power by over 85% in most cases.The proposed approaches can work with different instruction-cache (iL1) lookup mechanisms and achieve significant iTLB power savings without compromising on performance. Their importance grows with higher iL1 miss rates and larger page sizes. They can work very well with large iTLB structures that can possibly consume more power and take longer to lookup, without the iTLB getting into the common case. Further, we also experimentally demonstrate that they can provide performance savings for virtually indexed, virtually tagged iL1 caches, and can even make physically indexed, physically tagged iL1 caches a possible choice for implementation.

Distribution of Words on the World-Wide Web

The diverse words of all kinds of language are added into the World-WideWeb in an extremely complex and arbitrary manner. Behind the apparentarbitrariness topology, as we show here, there is an order hidden in theword network. By making use of Google search engine, we find that thedistributions of the basic English words andChinese characters on the web follow a universal power law. The power lawexponent of rank-ordered frequency distribution is α~0.99 forbasic English words and α~0.98 for Chinese characters.The Zipf law and page size distribution on the Web are used to explainthe phenomena.

Text characteristics of English language university Web sites

AbstractThe nature of the contents of academic Web sites is of direct relevance to the new field of scientific Web intelligence, and for search engine and topic‐specific crawler designers. We analyze word frequencies in national academic Webs using the Web sites of three English‐speaking nations: Australia, New Zealand, and the United Kingdom. Strong regularities were found in page size and word frequency distributions, but with significant anomalies. At least 26% of pages contain no words. High frequency words include university names and acronyms, Internet terminology, and computing product names: not always words in common usage away from the Web. A minority of low frequency words are spelling mistakes, with other common types including nonwords, proper names, foreign language terms or computer science variable names. Based upon these findings, recommendations for data cleansing and filtering are made, particularly for clustering applications.

A methodical approach to extracting interesting objects from dynamic web pages

This paper presents a fully automated object extraction system for web documents. Our methodology consists of a layered framework and a set of algorithms. A distinct feature of our approach is the full automation of both the extraction of data object regions from dynamic web pages and the identification of the correct object-boundary separators. We implemented the methodology in the XWRAPElite object extraction system and evaluated the system using more than 3200 pages over 75 diverse websites. Our experiments show three important and interesting results: First, our algorithms for identifying the minimal object-rich subtree achieves a 96% success rate over all the web pages we have tested. Second, our algorithms for discovering and extracting object separator tags reach the success rate of 95%. Most significantly, the overall system achieves a precision between 96% and 100% (it returns only correct objects) and excellent recall (between 95% and 96%, with very few significant objects left out). The minimal subtree extraction algorithms and the object-boundary identification algorithms are fast, about 87 milliseconds per page with an average page size of 30KB.

A new NAND-type flash memory package with smart buffer system for spatial and temporal localities

Abstract This research is to design a high performance NAND-type flash memory package with a smart buffer cache that enhances the exploitation of spatial and temporal locality. The proposed buffer structure in a NAND flash memory package, called as a smart buffer cache, consists of three parts, i.e., a fully-associative victim buffer with a small page size, a fully-associative spatial buffer with a large page size, and a dynamic fetching unit. This new NAND-type flash memory package can achieve dramatically higher performance and lower power consumption compared with any conventional NAND-type flash memory module. Our results show that the NAND flash memory package with a smart buffer cache can reduce the miss ratio by around 70% and the average memory access time by around 67%, over the conventional NAND flash memory configuration. Also, the average miss ratio and the average memory access time of the package module with smart buffer cache for a given buffer space (e.g., 3 KB) can achieve better performance than package modules with a conventional direct-mapped buffer with eight times (e.g., 32 KB) or than a fully-associative configuration with twice as much space (e.g., 8 KB).

Respectable Burial: Montreal's Mount Royal Cemetery (review)

Reviewed by: Respectable Burial: Montreal’s Mount Royal Cemetery James Stevens Curl (bio) Brian Young, with colour photographs by Geoffrey James. Respectable Burial: Montreal’s Mount Royal Cemetery McGill-Queen’s University Press. lv, 231. $49.95 This volume (only available in hardback) measures eleven and a half by nine inches (landscape), so is an awkward shape for the average bookshelf. It is difficult to understand why it is that shape, as the material could easily have been arranged to fit a more convenient size of page. Illustrated with colour and black-and-white material, it covers the history of Mount Royal Cemetery in Montreal from its foundation in 1852, including wearisome accounts of religious feuds between Roman Catholics and Protestants that are all too familiar, the difficulties of the Chinese communities in being permitted to carry out their customary rites, and other weighty matters that seemed to have caused endless problems in Montreal, as elsewhere. The book is really an encapsulation of the social history of death and disposal of the dead in Montreal, showing how that history evolved to the present day, with due regard to the Great and Good as well as the Great Unwashed and those at the bottom of the social pile. It is true that during the nineteenth century the cemetery began to be regarded as essential, for no town or city could really function without it, [End Page 474] so architects, engineers, and gardeners often rose to the challenge, creating some truly marvellous places that reward the visitor as well as the historian. Père-Lachaise, Montmartre, and Montparnasse in Paris, the Zentralfriedhof in Vienna, the Staglieno in Genoa, Kensal Green in London, and many, many other examples throughout Europe and America attest to the importance of the cemetery as a type, capable of infinite variety, and embellished with fine buildings and monuments set against lush landscapes that, in their maturity, often more than met the occasion. However, Respectable Burial, while dealing exhaustively with Mount Royal and the Montreal situation, is curiously provincial, and fails to connect with the wider subject that was so much a concern of eighteenth- and nineteenth-century Europeans and Americans. The thin bibliography shows that Brian Young's reading is not as wide as it should be, and he makes several mistakes (Rockwood instead of Rookwood is just one of them), quite apart from not making connections he ought to have been able to make had his study ranged somewhat further. The drawing he reproduces on page 94, for example, which he credits to a book of 1846, appeared earlier in J.C. Loudon's works, and was again published (1843) in Loudon's On the Laying Out, Planting, and Managing of Cemeteries, which appeared in facsimile in 1981, and should be essential reading for anybody undertaking any research into the vast subject of the nineteenth-century cemetery. Young mentions Loudon's book on page 16, where he sloppily calls it The Layout, Planting and Management of Cemeteries in 1843, indicating a cavalier disregard for accuracy that is extremely off-putting. Some illustrations passed the quality test, but others do not. What does Young mean on page 44 by 'an usual iron marker' (sic)? Why is the illustration on page 5 sinking to port? When distorted illustrations are passed as fit to be reproduced, and then no attempt is made to even try to make them passably straight, one has to wonder about quality control, and what author and editors were doing allowing such disasters to occur. Some other illustrations are uninformative and pointless, but some of the historical material is of interest, and has come out well. It is important that nineteenth-century cemeteries are adequately recorded, researched, and written up with as much illustrative material as possible, because such places have, for the most part, been undervalued for the best part of a century. Thus Young's book is to be welcomed, albeit with reservations, for the job could have been better done and the subject more closely related to other works. The bibliography is very rudimentary, and includes a reference to the United Kingdon (sic), which really sums it all up. Historians who do not...

The JID Legacy Project: Introspecting on Our Past

A legacy is something you inherit from the past and can bequeath to the future. Our journal's legacy includes 66 years of publication, and back issues of the JID are now available online from 1970. What can we see from this portion of our history? It is beyond the quaintness of people struggling at the limits of their techniques and the overall concepts of the day. It is an appreciation that some of today's best research may have the same aura of naivete in the face of the complex biological processes under investigation when that literature is read from the perspective of our intellectual descendents 35 or 100 years from now. Is humility the coat in which striving, even successful, scientists of today should clothe themselves? Is musing over our past most appropriately the province of very senior, white-haired—or no-haired—researchers?

Concurrent support of multiple page sizes on a skewed associative TLB

Some architecture definitions (e.g., Alpha) allow the use of multiple virtual page sizes even for a single process. Unfortunately, on current set-associative TLBs (translation lookaside buffers), pages with different sizes cannot coexist together. Thus, processors supporting multiple page sizes implement fully associative TLBs. In this research note, we show how the skewed-associative TLB can accommodate the concurrent use of multiple page sizes within a single process. This allows us to envision either medium size L1 TLBs or very large L2 TLBs supporting multiple page sizes.

A flash compression layer for SmartMedia card systems

Flash memory based SmartMedia card is becoming increasingly popular as data storage for mobile consumer electronics. Since flash memory is an order of magnitude more expensive than magnetic disks, data compression can be effectively used in managing flash memory based storage systems. However, compressed data management in flash memory is challenging because it only supports page-based I/Os. For example, when the size of compressed data is smaller than the page size, internal fragmentation occurs and this degrades the effectiveness of compression seriously. In this paper, we developed a flash compression layer (FCL) for the SmartMedia card systems. FCL stores several small compressed pages into one physical page by using a write buffer. Based on prototype implementation and simulation studies, we show that the proposed system offers the storage of flash memory more than 140% of its original size and expands the write bandwidth significantly.