Flash memory. Solid State Drive. Types of flash memory. Memory card

Flash memory is a type of long-term memory for computers, in which the contents can be reprogrammed or deleted by an electric method. In comparison with the Electrically Erasable Programmable Read Only Memory, the actions on it can be performed in blocks that are in different places. Flash memory costs much less than EEPROM, so it became the dominant technology. Especially in situations where sustained and long-term data storage is necessary. Its use is allowed in a wide variety of situations: digital audio players, photo and video cameras, mobile phones and smartphones, where there are special android applications on the memory card. In addition, it is also used in USB-flash drives, traditionally used to store information and transfer it between computers. It has gained some popularity in the gamer world, where it is often used in a slip to store data on the progress of the game.

general description

Flash memory is a type that can store information on its board for a long time without using power. In addition, you can note the highest speed of data access, as well as better resistance to kinetic shock in comparison with hard drives. It is thanks to such characteristics that it has become very popular for devices that use batteries and batteries. Another undeniable advantage is that when the flash memory is compressed into a solid card, it is almost impossible to destroy it by some standard physical methods, so it can withstand boiling water and high pressure.

Low-level data access

The way to access data stored in flash memory is very different from what is used for conventional views. Low-level access is provided through the driver. Normal RAM immediately responds to calls for reading information and its records, returning the results of such operations, and the flash memory device is such that it takes time to think.

The device and the principle of operation

At present, flash memory is distributed, which is created on single-transistor elements with a "floating" shutter. Due to this, it is possible to provide a greater data storage density in comparison with the dynamic RAM, which requires a pair of transistors and a capacitor element. At the moment, the market abounds in a variety of technologies for building the basic elements for this type of media, which are developed by leading manufacturers. It differs in their number of layers, methods of recording and erasing information, as well as organization of the structure, which is usually indicated in the title.

At the moment there are a couple of types of chips that are most common: NOR and NAND. In both, the connection of the memory transistors is made to the bit lines - in parallel and sequentially, respectively. In the first type, the cell sizes are quite large, and there is a possibility for fast random access, which allows executing programs directly from memory. The second is characterized by smaller cell sizes, as well as faster sequential access, which is much more convenient if you need to build a block-type device where large-scale information will be stored.

In most portable devices, the solid state drive uses the NOR memory type. However, now more and more popular are devices with a USB interface. They use NAND-type memory. Gradually, it displaces the first.

The main problem - fragility

The first samples of USB flash drives did not please users with high speeds. However, now the speed of writing and reading information is at a level that you can view a full-length movie or run an operating system on your computer. A number of manufacturers have already demonstrated machines where the hard drive is replaced with flash memory. But this technology has a very significant drawback, which becomes an obstacle to the replacement of existing media by existing magnetic disks. Due to the features of the flash memory device, it allows you to erase and record information for a limited number of cycles, which is achievable even for small and portable devices, not to mention how often this is done on computers. If you use this type of media as a solid state drive on a PC, then a critical situation will very quickly come.

This is due to the fact that such a drive is built on the property of field-effect transistors to keep an electric charge in the "floating" gate , the absence or presence of which in the transistor is considered as a logical unit or zero in the binary system of calculus. Recording and erasing of data in NAND-memory are performed by tunneling electrons by the Fowler-Nordheim method with the participation of a dielectric. This does not require a high voltage, which allows you to make cells of minimal size. But it is this process that leads to physical deterioration of the cells, since the electric current in this case causes the electrons to penetrate the gate, overcoming the dielectric barrier. However, the guaranteed shelf life of such memory is ten years. Depreciation of the chip is not due to reading the information, but because of the operations for its erasure and recording, because reading does not require a change in the structure of cells, but only passes an electric current.

Naturally, memory manufacturers are actively working towards increasing the life of solid-state drives of this type: they are committed to ensuring the uniformity of writing / erasing processes in the cells of the array, so that some do not wear out more than others. For uniform load distribution, software paths are used primarily. For example, to eliminate this phenomenon, the technology of "equalizing wear" is applied. In this case, the data, often subject to changes, moves to the address space of the flash memory, because the recording is performed at different physical addresses. Each controller is equipped with its own alignment algorithm, so it is very difficult to compare the effectiveness of certain models, since the details of the implementation are not disclosed. Since each year the volumes of flash drives become more and more, it is necessary to apply more and more efficient algorithms to ensure the stability of the devices.

Troubleshooting

One of the most effective ways to combat this phenomenon is to reserve a certain amount of memory, which ensures the uniformity of the load and error correction by means of special logical redirection algorithms for substituting physical blocks that occur during intensive work with a flash drive. And to prevent the loss of information, cells that are out of order are blocked or replaced by backup cells. This software distribution of the blocks makes it possible to ensure the uniformity of the load, increasing the number of cycles by 3-5 times, but this is not enough.

Memory card and other types of such drives are characterized by the fact that a table with a file system is stored in their service area. It prevents disruptions in the reading of information at a logical level, for example, with an incorrect shutdown or with a sudden power outage. And since when using removable devices the system does not provide caching, then frequent overwriting has the most disastrous effect on the file allocation table and the contents of the catalogs. And even special programs for memory cards are not able to help in this situation. For example, during a single call, the user copied a thousand files. And, it would seem, only once on one occasion used for recording the blocks where they are placed. But the service areas corresponded with each update of any file, that is, the allocation tables went through this procedure a thousand times. For this reason, first of all, the blocks occupied by this data will fail. The technology of "leveling out wear" also works with such blocks, but its effectiveness is very limited. And then it does not matter what kind of computer you use, the flash drive will fail even when it is provided by the creator.

It should be noted that the increase in the capacity of microcircuits of such devices has led only to the fact that the total number of recording cycles has decreased, since the cells are becoming smaller, and therefore less and less voltage is needed to dissipate the oxide barriers that isolate the "floating gate". And here the situation develops in such a way that with the increase in the capacity of the devices used, the problem of their reliability has become more and more aggravated, and the memory card class now depends on many factors. The reliability of the work of such a solution is determined by its technical features, as well as by the situation on the market that has developed at the moment. Because of tough competition, manufacturers are forced to reduce the cost of production by any means. Including by simplifying the design, the use of components from a cheaper set, weakening control over manufacturing and other methods. For example, the Samsung memory card will cost more than less known analogs, but its reliability causes much less questions. But even here it is difficult to talk about the complete absence of problems, and it is difficult to expect anything more from devices of completely unknown producers.

Development prospects

With obvious advantages, there are a number of drawbacks that characterize the SD memory card, preventing further expansion of its field of application. That is why the constant search for alternative solutions in this area is ongoing. Of course, first of all they try to improve existing types of flash memory, which will not lead to any fundamental changes in the existing production process. Therefore, there is no need to doubt only one thing: firms engaged in the manufacture of these types of drives will try to use their full potential before moving to another type, continuing to improve traditional technology. For example, Sony's memory card is currently available in a wide range of volumes, so it is assumed that it will continue to be sold actively.

However, to date, on the threshold of industrial implementation is a whole range of technologies for alternative storage of data, some of which can be implemented immediately in the event of a favorable market situation.

Ferroelectric RAM (FRAM)

Technology ferroelectric principle of information storage (Ferroelectric RAM, FRAM) is proposed with the goal of increasing the potential of non-volatile memory. It is considered that the mechanism of operation of available technologies, consisting in rewriting data during the readout with all modifications of the base components, leads to a certain restraint of the device's high-speed potential. And FRAM is a memory characterized by simplicity, high reliability and speed in operation. These properties are now typical for DRAM - non-volatile RAM, which exists at the moment. But there will also be added the possibility of long-term data storage, which is characterized by an SD memory card. Among the advantages of this technology is the resistance to various types of penetrating radiations, which may prove to be in demand in special devices that are used to work in conditions of increased radioactivity or in space exploration. The mechanism of information storage is realized here due to the application of the ferroelectric effect. It implies that the material is capable of maintaining polarization in the absence of an external electric field. Each FRAM memory cell is formed by placing a hyperfine film of a ferroelectric material in the form of crystals between a pair of flat metal electrodes forming a capacitor. Data in this case is stored inside the crystal structure. And this prevents the effect of leakage of the charge, which causes loss of information. The data in the FRAM memory is retained even when the power supply is disconnected.

Magnetic RAM (MRAM)

Another type of memory, which is considered very promising today, is MRAM. It is characterized by rather high speed indicators and non-volatility. The elementary cell in this case is a thin magnetic film placed on a silicon substrate. MRAM is a static memory. It does not need to be rewritten periodically, and the information will not be lost when the power is turned off. At the moment, most experts agree that this type of memory can be called next-generation technology, since the existing prototype demonstrates rather high speed indicators. Another advantage of this solution is the low cost of chips. Flash memory is manufactured in accordance with a specialized CMOS process. And MRAM chips can be manufactured in a standard process. And the materials can serve those that are used in conventional magnetic media. To produce large quantities of such chips is much cheaper than all the others. An important property of MRAM-memory is the ability to instantly turn on. And this is especially valuable for mobile devices. After all, in this type the value of the cell is determined by the magnetic charge, and not by the electric charge, as in traditional flash memory.

Ovonic Unified Memory (OUM)

Another type of memory, on which many companies are actively working, is a solid-state drive based on amorphous semiconductors. It is based on the technology of phase transition, which is similar to the principle of recording on conventional discs. Here the phase state of matter in an electric field varies from crystalline to amorphous. And this change is maintained even in the absence of tension. From traditional optical disks such devices differ in that heating occurs due to the action of an electric current, rather than a laser. Reading in this case is carried out due to the difference in the reflectivity of the substance in various states, which is perceived by the sensor of the drive. Theoretically, this solution has a high density of data storage and maximum reliability, as well as increased speed. High here is an indicator of the maximum number of cycles of rewriting, for which the computer is used, the flash drive lags several orders of magnitude in this case.

Chalcogenide RAM (CRAM) and Phase Change Memory (PRAM)

This technology is also based on phase transitions, when in one phase the substance used in the carrier acts as a non-conductive amorphous material, and in the second serves as a crystalline conductor. The transition of the memory cell from one state to another is accomplished by electric fields and heating. Such chips are characterized by resistance to ionizing radiation.

Information-Multilayered Imprinted CArd (Info-MICA)

The work of devices built on the basis of this technology is carried out on the principle of thin-film holography. The information is written as follows: first a two-dimensional image is generated, which is transmitted to the hologram using CGH technology. The data is read out by fixing the laser beam at the edge of one of the recording layers serving as optical waveguides. Light propagates along the axis, which is placed parallel to the plane of the layer, forming an image at the output corresponding to information recorded earlier. The initial data can be obtained at any time thanks to the inverse coding algorithm.

This type of memory advantageously differs from semiconductor memory due to the fact that it provides high density of recording, low power consumption, as well as low cost of media, environmental security and protection from unauthorized use. But such a memory card does not allow the data to be rewritten, so it can serve only as a long-term storage, replacement of a paper medium or an alternative to optical disks for the distribution of multimedia content.