flash Related Articles

IntroductionIn-memory computing (IMC), a technique of future computing, stores data in RAM to run calculations entirely in computer memory. With the rise of the big data era, faster data processing capabilities are required. Computer memory and storage space are also growing exponentially to adapt to large-capacity data collection and complex data analysis, which promotes the development of AI (artificial intelligence), and then derives emerging stuff, that is, in-memory computing.In-memory Computing (IMC) ExplainedCatalogIntroductionⅠ Memory Wall: Processor /Memory Performance GapⅡ Developing RequirementⅢ What Is In-memory Computing?3.1 In-memory Computing Definition3.2 Four Realization MethodsⅣ Driving Force of In-memory Computing and Market Prospects4.1 In-memory Computing for AI4.2 In-memory Computing Product Outlook4.3 In-memory Computing Market and ProspectⅤ ConclusionⅠ Memory Wall: Processor / Memory Performance GapThe von Neumann architecture has occupied the dominant position in computer system when the computer invented. This kind of calculation method is to store the data in the main memory first, and then fetch the instructions from the main memory to execute them in order when running. We all know that if the connecting speed of the memory cannot keep up with the performance of the CPU, the computing will be limited. This is a memory wall. At the same time, in terms of efficiency, the von Neumann architecture also has obvious shortcomings. It consumes more energy to read and write data than to calculate once time.Figure 1. Von Neumann Architecture DiagramThe performance of computer processors has developed rapidly based on Moore's Law, and has been directly improved with the invention of transistors. The main memory of the computer uses the DRAM. It is a high-density storage solution based on capacitor charging and discharging. Its performance (speed) depends on two aspects, namely the reading/writing speed of the capacitor charging and discharging in the memory and the interface bandwidth between the devices. The read/write speed of capacitor charging and discharging has increased with Moore’s Law, but the speed is not as fast as the processor. In addition, the interface between DRAM and the processor is a mixed-signal circuit, and its bandwidth increasing speed is mainly restricted by the signal integrity of the traces on the PCB. This has also caused the performance improvement of DRAM to be much slower than that of the processor. At present, the performance of DRAM has become an huge bottleneck of overall computer performance, the so-called "memory wall".  It blocks the computing performance improvement.Figure 2. Moore's Law Effect Ⅱ Developing RequirementIn the current AI technology, with the increasing amount of data and calculations, the original von Neumann architecture is facing more and more challenges. Rely on expanding CPU, the hardware architecture can’t have a large amount of calculation. Also the larger storage capacity is heavily rely on the past architecture, it is also very unsuitable for AI. When the memory capacity is large to a certain extent, it can only show that certain technologies need innovation. In order to solve the "memory wall" problem, future computers are not based on computing memory, but the in-memory computing, thereby reducing the cost of data access in the calculation process.Figure 3. Conventional Computing vs In-memory Computing Ⅲ What Is In-memory Computing?3.1 In-memory Computing DefinitionIn-memory computing (or in-memory computation) is a technique based on RAM data storage and indexing, which proposed by the MIT research group, and its main purpose is to accelerate the convolution calculation. We know that convolution calculations can be expanded into weighted accumulation calculations. From another perspective, it is actually a weighted average of multiple numbers. Therefore, the circuit realizes the weighted average of the charge domain. The weight (1-bit) is stored in SRAM, and the input data (7-bit digital signal) becomes an analog signal through the DAC. According to the corresponding weight in the SRAM, the output is multiplied by 1 or -1 in the analog domain, which averaged in the analog domain, and finally read out by the ADC as a digital signal. Specifically, since the weight of the multiplication is 1-bit (1 or -1), it can be controlled by using a switch and a differential line simply. If the weight is 1, the capacitor on the side of the differential line is charged to the required output value. Otherwise, let the other side of the differential line be charged to this value. As for average, connect several differential lines together in the charge domain.Of course, there is more than one circuit for in-memory calculation, and the calculation accuracy is not limited to 1-bit. However, we can see the above examples that the core idea of in-memory calculations is generally to convert calculations into weighted calculations. Store the weights in the memory unit, then modifications on the core circuit of the memory (such as the readout circuit) are made. So that the process of reading is like a process in which the input data and weights are multiplied in the analog domain, that is, convolution. Because convolution is a core part of AI and other calculations, in-memory computing can be widely used in such applications. In-memory computing uses analog circuits for calculations, which is the difference compared with traditional digital logic calculations.In more traditional architectures, there are some multiply-accumulate circuits (MAC) for tensor math, especially the matrix multiplication. These architectures attempt to arrange the MAC in a way that moves weights and activations to the appropriate location. Activations are calculated from the previous neural network layer. Multiplication usually involves activations and weights, both must be moved to the place where multiplies them. In-memory computing makes use of it. Therefore, if the weights are stored in memory, the memory can access through activations to obtain multiplication and accumulation. The only difference from the actual memory is that the in-memory computing concatenates all word lines at once, instead of decoding the input to get one word line only.Figure 4. In-memory Computing Diagram3.2 Four Realization MethodsThe attempt is to enter the analog domain and treat the storage unit as an analog unit instead of a digital unit to reduce consumption. We have already got a way to use simulation on the front end of the inference engine. That is in-memory computing. Therefore, we take digital data, using a DAC to convert it to an analog value, and then driving a memory with these analog content to obtain an analog bit-line output, finally using an ADC to convert the result back to a digital format. However, the in-memory computing is still in the exploratory stage, and there are many specific implementation methods to study, currently there are three types: RRAM, Flash, SRAM, and DRAM.Based on RRAMRRAM is the most common method of doing this, because it is easy to use by applying Ohm's law to a series of resistors, but it still has the problem of relying on RRAM. The relationship between programming and resistance is non-linear, which requires more work to be done to make viable calculation circuits in RRAM memory for market. So it is just an idea, and the specific plan is still under study. Based on FlashNOR Flash memory has a more traditional word-line/bit-line structure. It is both resistive and capacitive. Generally, the memory cell is a transistor that is turned on or off. However, if it is partially conductive, it can be used as a resistor. The resistance depends on the amount of charge on the floating gate of the memory cell (capacitor). When running all the time, the cell will conduct to its maximum capacity. During this process, it does not conduct at all, however, it can be partially programmed. There is a problem is that you cannot precisely control the number of electrons. Moreover, the response to any number will vary with the process and temperature and other variables.Two companies are studying this method. Microchip owns their memBrain array, thanks to their acquisition of SST, and Mythic is a start-up company dedicated to an inference engine that uses in-memory computing with flash memory. Both companies said that they are using extensive calibration techniques to deal with this change.Another issue, flash cells will lose electrons over time. Electrons will flow around, which brings up an interesting topic: on this type of memory array, data retention and durability will be like.From the application point of view, it depends on whether it is to be used in cloud computing or edge inference engine. At the edge, it may perform certain fixed reasoning functions throughout the life cycle of the device. Therefore, if there are enough arrays, then you will load the weights for the first time and don't need to program it anymore (unless you do a update), because the flash memory is non-volatile. Although you still need to move activations, there is no need to move the weights, which will be stored permanently in the array. This would indicate that data durability (number of times the device can be programmed before cumulative damage accelerates electron leakages to an unacceptable level) does not matter, it only need to program once.In contrast, in cloud applications, the device is likely to be shared as a general-purpose computing resource, so this requires reprogramming for each new application. This means that battery life becomes more important in the cloud. Mythic claims to have a 10K write cycle, and has observed that even if it is reprogrammed every day, it will last for more than 10 years.If set an analog value for it and use an analog value in the cell, then in theory, each electron is important. However, if there is enough electron migration, you need to refresh the storage unit, or compensate for electrons change in some way. Because the same analog input today will produce different results than a year ago. The calibration circuit can also deal with some aging problems. However, for data retention, Mythic said they do perform regular updates of the weight values stored in flash memory. This will make persistence the main wear-out mechanism rather than data retention. Microchip stated that its data retention time is TBD, but it is likely to reprogram the device quarterly or annually to restore the unit.So they need a large number of high-quality ADCs and DACs to keep the signal-to-noise ratio (SNR) within a scope of accurate reasoning, which is the focus of designing work. Mythic claims that they provide a novel ADC, so that Microchip can share it to reduce the number required. Although ADC does consume energy, it also greatly reduces overall system consumption. Based on SRAMThis idea came from a lecture at Hot Chips at Princeton University. By definition, SRAM is a bistable unit. Therefore, it cannot be in an intermediate state, how should this be handled? And the DACs and ADCs that need to be corrected more over than the array in terms of area and power consumption.The point of this problem boils down to the question of how to simulate. They explained that this method uses more than one-bit line for calculation. Since the unit is still a digital value, it takes several bit lines to perform a calculation. The bit line can be split, and different groups perform different multiplications. The following figure illustrates it.Figure 5. Bit LineWith 8 inputs at a time, so the input vector is sliced and several consecutive multiplications are carried out to obtain the final results. The bit line charge is deposited on the capacitor. When ready to read, the charge is read out and sent to the ADC for conversion back to the digital domain. Their basic unit structure is as follows:Figure 6. Bit CellThese capacitors may affect chip size issues, but they said that the metal above the cell can be used. Of course, one cell is now 80% larger than the standard 6T SRAM cell (even without capacitors), but they say that their overall circuit is still much smaller than a required circuit based on standard digital implementation. In addition, since their basic array operations are still in digital form, they are less sensitive to noise and changes, which means their ADCs can be simpler and consume less power.Figure 7. Chip SizeBased on DRAMThis idea refers to not using a lot of power to obtain DRAM content, and in some way incorporate calculations into the CPU or other computing structures and directly run it on the DRAM die, which is what UPMEM does. A simple processor is built on the DRAM die, also the architecture will not compete with Xeon chips, they call this set "processing in memory" or PIM.Figure 8. PIM ChipInstead of bringing data to calculations, they bring calculations to data. The runtime is performed by the CPU in DRAM chip. That is, there is no need to move the data to any location outside of the DRAM chip, just send the calculating result back to the host system. Also, since ML calculations usually involve a lot of reduction, less data required for calculations. Although this does require some minor changes to the DRAM, they did not change the manufacturing process. Under this case, a standard DRAM module will provide multiple opportunities for distributed computing. At the same time, it becomes complicated to use this function to write a program.They said that a server using PIM offload will consume twice as much power than a standard server connected to a DRAM module without PIM. However, with a throughput of 20 times, it still provides them with a 10 times energy efficiency advantage. In addition, this method can help defend against side-channel security attacks. Thus a group of computing threads originally contained in one or more CPUs flows to DRAM. Therefore, it is necessary to check all DRAMs and figure out where thread is in some way, but this will be a difficult task. Ⅳ Driving Force of In-memory Computing and Market Prospects4.1 In-memory Computing for AIPeople have recognized the problem of "memory wall" for a long time, but why is in-memory computing only raised in the past two years? So we have to analyze the boost behind its rise.The first motivation is the rise of AI based on neural networks, especially the hope that AI can be popularized in mobile and embedded devices. So that in-memory computing with a high energy efficiency ratio has attracted attention. In addition, neural networks have a high tolerance for errors in calculation accuracy. Therefore, errors introduced in simulation calculations of in-memory computing can often be accepted. That is to say in-memory computing and AI are good partners for each other.The second motivation is the new memory. For in-memory computing, the memory characteristics often determine the efficiency of in-memory computing. Therefore, new memories improvement will often drive the development of in-memory computing. For example, the recently popular ReRAM uses resistance modulation to store data, so the readout of each bit uses a current signal instead of a traditional charge signal. In this way, it is a very natural operation for current to accumulate (combining several currents directly to achieve the sum of currents, even without additional circuits). That is to say, ReRAM is very suitable for in-memory calculations. From the perspective of memory promotion, new memories are also willing to catch up with the AT trend. Therefore, new memory manufacturers are also happy to see in-memory computing based on their own memories to accelerate AI development, which will broaden the memory market. 4.2 In-memory Computing Product OutlookChip products for in-memory computing are expected to come in two forms. The first form is sold as a memory IP with computing functions. Such memory IP may be traditional SRAM, or new memory such as eFlash, ReRAM, MRAM, and PCM.The second form is to directly build AI acceleration chips based on in-memory calculations. For example, Mythic plans to make PCIe accelerator cards based on flash memory, that is, access data with the main CPU through the PCIe interface. The weight data is stored on the Mythic memory chip, so that when the data is sent to the Mythic IPU, the calculation can be directly read out. In this way, the action of reading the weights data is eliminated.Figure 9. Mythic is a Pcie Accelerator 4.3 In-memory Computing Market and ProspectWhat impact will in-memory computing have on the AI chip market? First of all, we see that in-memory computing uses analog calculations, so its accuracy will be affected by the low signal-to-noise ratio. Usually the upper limit of accuracy is about 8-bit, and it can only do fixed-point calculations not the floating-point calculations. So in-memory computing is not suitable for the AI training market that requires high calculation accuracy. In other words, the main battlefield of in-memory computing is the AI inference market. For example, it is more suitable for embedded artificial intelligence, which has high requirements for energy efficiency not the accuracy. In fact, in-memory computing is actually most suitable for occasions where large memory is needed. For instance, flash is inherently required in IoT and other scenarios, so if you can add the in-memory computing to flash, it is quite suitable. However, introducing in-memory computing in a large storage memory may not appropriate. Based on this analysis, we believe that in-memory computing may become an important part of embedded AI (such as smart IoT) in the future. Ⅴ ConclusionWith the rise of AI and new memories, in-memory computing has also become a new hot spot. Based on the unique characteristics of the memory, it combines with analog calculations in memory, thereby greatly reducing the memory read and write operations in AI. Although the accuracy of calculation in the memory is limited by analog calculation, it is also suitable for embedded AI applications that pursue energy efficiency most and can accept a certain loss of accuracy. Frequently Asked Questions about In-Memory Computing Technology1. Why do we need in memory computing?In-Memory Computing provides super-fast performance (thousands of times faster) and scale of never-ending quantities of data, and simplifies access to increasing numbers of data sources. 2. What does in memory mean?An in-memory database is a type of purpose-built database that relies primarily on memory for data storage, in contrast to databases that store data on disk or SSDs. ... Because all data is stored and managed exclusively in main memory, it is at risk of being lost upon a process or server failure. 3. How does in memory computing work?In-memory computing means using a type of middleware software that allows one to store data in RAM, across a cluster of computers, and process it in parallel. Consider operational datasets typically stored in a centralized database which you can now store in “connected” RAM across multiple computers. 4. What is in memory computing in SAP HANA?An In-Memory database means all the data from source system is stored in a RAM memory. In a conventional Database system, all data is stored in hard disk. It provides faster access of data to multicore CPUs for information processing and analysis. 5. How is data stored in memory?Normally memory is described as a storage facility where data can be stored and retrieved by the use of an address. This is accurate but incomplete. A computer memory is a mechanism whereby if you supply it with an address it delivers up for you the data that you previously stored using that address. 6. What is in memory data processing?In-memory processing is the practice of taking action on data entirely in computer memory (e.g., in RAM). ... Since the storage appears as one big, single allocation of RAM, large data sets can be processed all at once, versus processing data sets that only fit into the RAM of a single computer. 7. What is in memory database processing and what advantages does it provide?The major advantage of systems using in-memory databases vs traditional database systems is: its performance speed. ... Source data is loaded into the system memory in a compressed and format. Therefore, in-memory processing reduces disk seek time for accessing data and streamlining the work involved in processing queries. 8. What is big data computing?Big data computing is an emerging data science paradigm of multi dimensional information mining for scientific discovery and business analytics over large scale infrastructure. ... Big data is characterized by 5V's such as volume, velocity, variety, veracity, and value.

Ⅰ IntroductionIn recent years, with the rapid development of the internet of things (IoT) and electronic technologies, embedded devices such as mobile phones, smartwatches, and sports bracelets have become important elements of cloud computing, IoT, and big data analytics. Embedded terminal devices become more usual in daily life. However, to meet the high storage requirements of these increasingly diverse applications, scientific research personnel face more challenges. Non-volatile memory is more and more popular in the market due to its advantages such as low energy consumption, non-volatile, high density, and low latency. The following is a basic introduction to new non-volatile memory with good future development prospects.The Future of Non-volatile MemoryCatalogⅠ IntroductionⅡ TerminologyⅢ Concept and ClassificationⅣ One Question Related to Non-volatile Memory and Going Further4.1 Question4.2 AnswerⅡ TerminologyMemory is an important part of computer systems. According to different positions in the storage system, memory can be simply divided into three types: on-chip memory, main memory, and hard disk. Correspondingly, static memory (SRAM), dynamic memory (DRAM), and magnetic disks have become the traditional technologies to realize these storage system. Over the past 40 years, these three technologies have achieved tremendous technical and commercial success. With the exception of magnetic disks, the manufacture of both static and dynamic memory relies on semiconductor integration technology. Although these two technologies are different, they also have a common characteristic: they both use the accumulation and release of charge on semiconductor devices to achieve data storage. For example, in a dynamic memory, the charge is used to represent a logic 1, and the discharge represents logic 0. In static memory, this process is achieved by charging and discharging the parasitic capacitance of the transistor. For example, solid-state storage, which widely used in flash memory, also stores data by capturing and releasing the charge on the floating gate of the transistor.With the improvement of manufacturing technologies, the size of semiconductor nano devices has continued to shrink, and the charges that can be stored on all of the above traditional memory devices has also decreased, which has brought serious reliability issues: First, more leakage current; second, a small perturbation of charges will have a relatively greater impact. In addition, the inherent limitations of the charge storage mechanism itself also can't be avoided, the processing of traditional mainstream memories at the nanoscale and the process disturbances are also very challenging.From the aspect of functions, static memory and dynamic memory both belong to the volatile memory category. Its characteristic is that when the power supply is off, the data stored in the memory will disappear and cannot be recovered. Especially in the design of dynamic memory, the charge on the capacitor will gradually leak out as the time increases. Therefore, the stored info need to be refreshed periodically. The static memory doesn't have this issue, but the area of the memory cell is usually large (about 20 times that of the dynamic memory cell), causing serious leakage current. Flash memory belongs to the non-volatile memory, and the data stored on it will be retained for a long time after the power off. In terms of performance, the first two types of memory read & write speed are on the level of nanoseconds, while the flash memory are on the level of hundreds of microseconds or even milliseconds. For the reading mode, the static memory and the dynamic memory can achieve random storage, for example, any one or several memory cells can be read and written at will. It different for Flash, although its storage density is high, the read operation must be performed in units of pages. Moreover, the content update of the flash memory cannot be achieved by directly overwriting the original content, but must be written to a new erased page. In addition, the maximum times of read and write supported by flash memory is extremely limited, typically between thousands of and millions of times. Ⅲ Concept and ClassificationConcept: Non-volatile memory refers to the computer memory of the person whose stored data will not disappear when the power is turned off. It is characterized by non-volatile, byte-by-byte access, high storage density, low energy consumption, and fast read and write speed, but the read speed  far faster than write, in other words, they are asymmetric in a limited life.Classification: According to whether the data in the memory can be rewritten at any time, the traditional non-volatile memory can be divided into two categories: read-only memory (ROM) and Flash memory. New type non-volatile memory compared with traditional non-volatile memory, its device has greatly improved energy consumption, read and write speed, integration density, etc. At present, the newly developed new non-volatile memory mainly includes four types: dielectric memory (FRAM), magnetic medium memory (MRAM), Ovonic phase change memory (OUM), and polymer memory (PFRAM).The following highlights four new non-volatile memories.The technical limitations of traditional memories and the huge challenges brought by the light weight have prompted researchers to look for a new generation of memory devices. People want to find a memory with the following characteristics:1) Nano level read and write speed of static memory2) Integrated density with dynamic memory and even flash memory level3) Flash-like non-volatile memory featuresAlthough such a storage technology has not been fully realized at present, some very promising new storage devices have been developed, and some have even entered the production stage. The four newly developed non-volatile memories are very promising for data processing, because of the limitations of traditional non-volatile memories, it is very likely to replace flash memory in the future.Table 1. New Non-volatile Memories Basic SituationsItemPerformanceManufactureLimitationApplicationFerroelectric RAM(FRAM)1) low energy consumption 2) high read & write speed3) long storage time4) low power operation5) anti-radiationsmaller size1) limit read & write times2) low storage density3) low reliability1) RF IC card2) fast-start memory3) embedded cache4) aerospaceMagnetic RAM(MRAM)1) high read & write speed 2) unlimited read & write times3) low power operationsimple circuithigh cost1) storage2) industrial automation, 3) games 4) energy management 5) communication 6) transportation7) aerospace electronics8) sensor terminalsPhase Change Memory (OUM) 1) long service life2) safety 3) low energy consumption1) small capacity2) low cost1) lower read &write speed2) poor temperature characteristic1) wired and wireless communications2) consumer electronics 3) PC and embedded devicesPolymeric RAM1) good stability 2) low power operation1) 3D stack2) easy processing3) low cost1) limit read & write times, 2) destructiveness1) PC 2) digital camera 3) mobile phoneFRAMa. IntoductionFRAM is the non-volatile memory technology in the new generation. In terms of performance, it consumes low energy and can store data for a long time although there is power failure. It combines the characteristics of high read-write speed of RAM and long-term data storage of ROM. Embedded FRAM in the non-volatile memory situation of radiation-resistant and low-power has great significance. It can be embedded in the chip in a more direct way and has better performance than any other alternative chips. In terms of manufacturing and technology, FRAM is easier to reduce size than flash memory due to the advanced nodes (65 nm or smaller), and does not require the use of very thin oxides or high voltages. b. LimitationWhen FRAM reaches a certain times of read and write, FRAM cells will lose their durability, and the FRAM yield problem caused by array size restrictions and further improvements in storage density and reliability still need to be resolved.c. ApplicationFRAM is a non-volatile memory that combines the advantages of low power consumption, high speed, long service life, and anti-radiation. It is promising in RF 1C card, fast startup memory, and system chip of cache and aerospace.d. Commercial progressFrom the point of international respect, well-known American company Ramtorn, which developed the first 4K bit commercial ferroelectric memory in 1993; after 1998, Ramtorn focused on product research and development, and handed over all production to semiconductor manufacturers. With the time goes by, Ramtorn represents the highest level of PZT-based commercial ferroelectric memory. Many other countries started late in the field of ferroelectric research and mainly based on scientific research. For example, the main work of some countries is still the preparation of ferroelectric thin films. MRAMa. MRAM BasicsMRAM is a non-volatile memory. For the performance, the write speed of MRAM is extremely fast, almost 1000 times that of flash memory, and 20 times that of FRAM. And it has unlimited read and write times, also it can switch on and off instantly and extend the battery life of portable computers. In terms of manufacturing and technology, the circuit of MRAM is simpler than ordinary memories, and only one readout circuit is needed for chip access. In addition, MRAM is easier to integrate (only 5 photomask layers are needed in the entire process), and there is no need to redesign at the transistor level of flash memory. All other core technologies used in the design can remain the same and work consistently.From 1986 to 1988, Albert Fert and Peter Grünberg discovered that nano-multilayer films composed of alternating ferromagnetic and non-magnetic metal layers made of molecular beam epitaxy have a much larger size than AMR, which is named as giant magnetoresistance (GMR). GMR is a quantum mechanical magnetoresistance effect observed in multilayers composed of alternating ferromagnetic and non-magnetic conductive layers, but it was difficult to put into practice. Soon, further research by Parkin team found that the (ferromagnetic / non-magnetic metal / ferromagnetic) three-layer film made by sputtering technology has a much larger giant magnetic resistance at room temperature than a single-layer ferromagnetic metal. For the spin valve, opened the way for practical use of GMR.The discovery and research of GMR had led to the realization of high-sensitivity read heads in high-density disks, and promoted the development of the entire modern hard disk industry. The earliest application of spin valve sensors in hard disk read heads was in the IBM Deskstar 16GP Titan, which was released in 1997 and has a storage capacity of 16.8GB. In 2007, Hitachi introduced the Deskstar 7K1000, the first 1TB hard drive.b. MRAM LimitationMRAM is much higher than flash memory in the production costs.c. MRAM ApplicationWith the advantages of low power consumption, high-speed reading, high integration, radiation resistance and unlimited rewrites, MRAM is used in storage, industrial automation, gaming, energy management, communications, consumption electronic,transportation and avionics fields. In addition, the IOT and big data analytics are gradually emerging,ubiquitous sensor terminals need to collect massive amounts of data, in order to save storage power consumption, MRAM and STT-MRAM have become the better choices for their relatively good performance.d. MRAM Commercial ProgressIn 2006, Freescale launched the world’s first commercial MRAM product with a capacity of 4Mb. Judging from the current product specifications and development status, the use of MRAM is still limited to some specific markets. From the perspective of cost and capacity, it cannot compete with NAND flash memory with a maximum capacity of 8Gb and DRAM with 512Mb capacity. However, with Samsung, Intel, TSMC and Global Foundry and other integrated circuit leaders strengthening investment in R & D and related production lines, STT-MRAM is gradually begin mass production, partially replacing SRAM and DRAM products and becoming one of the mainstream memories. OUMa. OUM BasicPhase change memory is a kind of memory that realizes information storage through material phase change. It is the non-volatile and large-capacity storage technology advocated by Intel, the world's number one semiconductor chip manufacturer. In terms of performance, it has a long read and write operation life and is easier to integrate than flash memory. OUM memory cells are extremely dense, and read operations is more safer than other memories. Low energy consumption, requiring very low power to operate. In addition, OUM unit can write about 1 billion times, which makes it an ideal alternative to large-capacity memory in portable devices. From the aspect of manufacturing process, compared with the integration of existing logic circuits, its storage unit is only 1/3 of MRAM and FRAM, and its production cost is lower than other new memories.Crystalline Phase and Amorphous Phase ChangeAlthough phase change memory is often categorized as “new memory”, the concept of “phase change” has introduced over 50 years. In 1962, the phase transition of As-Te glass was discovered. In 1968, Stanford Robert Ovshinsky described in an article that certain semiconductor materials can rapidly switch between two different states of resistance and conductivity under the action of an electric field (on the order of 10μs), he utilized chain structures, cross links, polymeric concepts, and divalent structural bonding with a huge number of unbonded lone pairs to achieve what is now referred to as the “Ovshinsky Effect”, an effect that turns special types of glassy, thin films into semiconductors upon application of low voltage. This discovery directly led to a large number of subsequent studies on the phase transition of thin films based on tellurium-arsenide-germanium-silicon alloy materials or sulfur-based glasses. In 1970, Nevill and Gordon Moore demonstrated the world’s first 256-bit phase change memory, and Moore was later known for putting forward the famous “Moore's Law” about the number of transistors in a dense integrated circuit doubles about every two years and served as the co-founder of Fairchild Semiconductor and CEO of Intel. After that, research on semiconductor memories based on phase change materials has gradually slowed down due to issues such as materials and power consumption, but phase change materials have been used very successfully in rewritable optical discs such as CD-RW / DVD-RW.   b. OUM LimitationThe read and write speed and frequency of OUM are not as good as FRAM and MRAM, and how to maintain its driving temperature stably is also a big technical problem.c. OUM ApplicationPhase change memory is suitable for wired and wireless communication equipment, consumer electronics, PC and other embedded applications due to its fast read and write speed, strong upgrade capabilities, and low power consumption. For example, it is used in the aerospace embedded system and used in smart meters to further integrate its storage architecture.d. OUM Commercial ProgressPhase change memory, as one of the most promising new memories, can be embedded at all levels of the memory architecture. Because of the similarity between phase change memory and dynamic memory, especially its lower power consumption and scalability, it has been considered as the best substitute for dynamic memory. But phase change memory also has disadvantages. The first is its limited times of erases and writes (usually only 107 to 108). If the number of erasing and writing exceeds this limit, the life of the memory cell will end, and the device can no longer be used. The second disadvantage is the limited write speed. The write speed of phase change memory is 6-10 times slower than dynamic memory. Write Operation of Phase Change Memory UnitNevertheless, phase change memory still has good applications in some fields. Several related studies have proposed various methods to overcome these shortcomings. For example, an architecture adjustment is used to compensate for the loss caused by the performance of writing, which can greatly reduce power consumption, thereby accelerating the commercialization of phase change memory as the main memory of a computer.In addition, the multi-level cell technology has been successfully implemented on phase change memory. In the design of a multi-level cell phase change memory, 2N resistive states are used to represent N digits, respectively, in other words, in a 2-bit multi-level cell phase change memory, 00, 01, 10, and 11 can be represented by four different resistance values, respectively. In the specific design, the resistance of the phase change material can be changed by adjusting the amplitude and time of the writing current / voltage. PFRAMa. PFRAM BasicsPFRAM is a plastic, polymer-based, and non-volatile memory. In terms of performance, PFRAM has advantages such as good stability and low power consumption. From manufacturing process, high density can be obtained through three-dimensional stacking technology, which is easy to make and has extremely low manufacturing costs, only about 10% of NOR-type flash memory.b. PFRAM LimitationPFRAM has a limited read and write operation life and its reads are destructive.c. PFRAM ApplicationThe final product of (PFRAM will be an all-organic storage system, which will be suitable for personal computers, handheld computers, digital cameras, mobile phones, handheld radios and communication devices, GPS systems, audio, video, game background program and other important fields.d. PFRAM Commercial ProgressPFRAM develops slowly in commercial use, and Intel is in a leading position. In 2014, Intel recruited JonKrueger (architecture and software engineer) to work for its polymer memory group and greatly promote the development of multi-layer plastic memory, finally their work is close to the software development stage, which indicates that this memory technology will accelerate to the market.Memory technology will continue to improve to meet different applications. On the one hand, The new type memories will create a new market and enter various application markets, on the other hand, it involves new materials and research concepts, it will be difficult to become the mainstream of the market in a long time. However, in the aerospace, industrial automation,  embedded cache of system chip and other sub-application areas, the new non-volatile memory will gradually transfer its technological breakthroughs to market penetration and achieve rapid development.With the advent of the 5G era, the development of application markets such as the IOT, artificial intelligence, and smart cities, and the urgent need for diverse memory requirements, coupled with traditional memory market change, new type memories will play an increasingly important role in the market. Ⅳ Questions Related to Non-volatile Memory and Going Further 1. Which memory is called non-volatile memory?Examples of non-volatile memory include read-only memory (see ROM), flash memory, most types of magnetic computer storage devices (e.g. hard disks, floppy discs and magnetic tape), optical discs, and early computer storage methods such as paper tape and punched cards. 2. Which is non-volatile memory RAM or ROM?RAM, which stands for random access memory, and ROM, which stands for read-only memory, are both present in your computer. RAM is volatile memory that temporarily stores the files you are working on. ROM is non-volatile memory that permanently stores instructions for your computer. 3. What is another name for non-volatile memory?Non-volatile memory (NVM) or non-volatile storage is a type of computer memory that can retain stored information even after power is removed. 4. Which is the most non-volatile memory?NAND flash, the most common type used in data storage, includes several variants, such as single-level cells or one bit per multi-level cell or two bits per cell; three-level cells or three bits per cell and quad-level cells or four bits per cell, respectively. 5. What is non-volatile memory explain with example?NV or non-volatile memory is a term used to describe memory or storage that is saved regardless if the computer has power. ... An example of non-volatile memory and storage is a computer hard drive, flash memory, and ROM.

Ⅰ IntroductionWith the improvement of computer technology, the demand for non-volatile memory is increasing, their read and write speed requirements are getting faster and faster, and the power consumption  are becoming smaller and smaller as required by users. But the traditional non-volatile memory such as EEPROM , FLASH, etc. have been difficult to meet these needs.Traditional mainstream semiconductor memories can be divided into two categories: volatile and nonvolatile. Volatile memory includes static random access memory (SRAM) and dynamic random access memory (DRAM). Both SRAM and DRAM lose their saved data when power off. Although RAM is easy to use and performs well, a big disadvantage of it is data loss.Non-volatile memory does not lose stored data in the case of a power failure, because all mainstream non-volatile memories are derived from read-only memory (ROM) technology. ROM, what is called a read-only memory is definitely not easy to write, in fact, it cannot be written at all. All memories developed by ROM technology are difficult to write data, including EPROM, EEPROM and Flash. And these memories not only have a slow writing speed, but also can only be erased and written in a limited number of times.Based on improving semiconductor technologies, ferroelectric memory, a new type of memories, has some unique characteristics. Ferroelectric memory is compatible with all the functions of RAM, and it is a non-volatile memory like a ROM. In other words, ferroelectric memory bridges the gap between these two types of storage, a type of non-volatile RAM. Compared with traditional non-volatile memory, it has attracted much attention due to its advantages such as low power consumption, fast read and write speed, and strong anti-irradiation capability. CatalogⅠ IntroductionⅡ TerminologyⅢ Working PrincipleⅣ FRAM Material FeaturesⅤ Circuit StructureⅥ Reading and Writing ProcessⅦ FRAM StructureⅧ Comparison of FRAM with Other Storage TechnologiesⅨ FRAM UsageⅩ SummaryⅪ One Question Related to FRAM and Going Further11.1 Question11.2 AnswerⅡ TerminologyFerroelectric Memory (FeRAM)Ferroelectric memory (FRAM), also known as F-RAM or FeRAM, is a type of random access memory with fast read and write speed, and the ability to retain data after power is turned off (such as read-only memory and flash memory) is combined, which is the most commonly used type of personal computer memory. Since it is not as dense as dynamic random access memory (DRAM) and static random access memory (SRAM), that is, it cannot store as much data as they do in the same space. In other words, it cannot replace DRAM and SRAM technologies. However, because it can store data quickly with very low power conditions, it is widely used in consumer’s small devices, such as personal digital assistants (PDA), mobile phones, power meters, smart cards, and security systems. FRAM’s read and write speed is faster than flash memory. In some applications, it may also replace electrically erasable read-only memory (EEPROM) and static random access memory (SRAM), and will become a key component of future wireless products. Ⅲ Working PrincipleFeRAM or ferroelectric RAM seems to indicate that an iron element exists within the memory this is not actually the case. A ferroelectric is a material containing a crystal that can spontaneously polarize. It has two states that can be reversed by an external electric field. When an electric field is applied to the ferroelectric crystal, the central atom moves in the crystal following the electric field direction. When an atom moving, it passes through an energy barrier, causing charge breakdown. Internal circuits react to the charge breakdown and set the memory. After the electric field is removed, the central atom remains polarization state, which makes the materials non-volatile, so the state of the memory is preserved. Because there is no atomic collision in the entire physical process, the ferroelectric memory has the characteristics of high read and write speed, ultra-low power consumption, and unlimited writes, making it very suitable to act as temporary storage memory in important systems to transfer various data between subsystems, for each subsystem to read and write frequently.Therefore, with an external electric field, the polarization characteristics of ferroelectric materials will change. When this electric field is removed, the data can still be saved. Without an external electric field, there are two stable states of polarization characteristics. Figure 1 is a hysteresis loop of a ferroelectric material capacitor, showing the different polarities of the ferroelectric capacitor under different applied electric fields. Among them, the two most important parameters are the degree of residual polarization Pr, and the coercive field Ec. In the absence of electric field effect, +/- Pr represents two states of “0” and “1”. To obtain these two states, the applied electric field must be greater than +/- Ec, at this time, the required threshold voltage is also determined.Figure 1. Ferroelectric Hysteresis LoopThe industry explores the use of ferroelectric materials for DRAM: using them as dielectric materials in DRAM capacitors. That is, ferroelectrics are used to replace high-K dielectric materials in standard logic devices, and finally non-volatile transistors are formed, which are FeFETs. The two stable polarization states of the ferroelectric gate oxide change the threshold voltage of the transistor, even when the supply voltage is removed. Therefore, the binary state is encoded in the threshold voltage of the transistor. The writing operation of the memory cell can be completed by applying a pulse on the gate of the transistor, which will change the polarization state of the ferroelectric material and affect the threshold voltage. For example, applying a positive pulse will reduce the threshold voltage, making the transistor in the “on” state. Reading is done by measuring the drain current. This memory mode is similar to the operating mode of a NAND flash: electrons are injected and drawn out of the floating gate, which adjusting the threshold voltage of the transistor.In contrast, the leakage current factor of ferroelectric capacitors is not as important as traditional non-volatile memories such as EEPROM and FLASH, because the information storage of FeRAM is realized by polarization, not free electrons. Ⅳ FRAM Material FeaturesIdeal ferroelectric materials need to meet the following characteristics:Small dielectric constantReasonable self-polarization degree (~ 5μC/ cm2)High Curie temperature (outside the storage and operating temperature range of the device)The thickness of ferroelectric materials should be thin (submicron) to make the coercive field EC smaller. Ferroelectric materials should stand a certain breakdown filed strength.Internal switching speed should be fast (nanosecond level)The ability to keep the data and the long-lasting ability will be good.If used by the military, it is also required to be able to resist radiation exposure. Good chemical stabilityGood processing uniformityEasy to integrate into CMOS processNo bad effect on the surrounding circuitsSmall pollution After years of research and development, there are currently two main types of mainstream ferroelectric materials: PZT and SBT.PZT is lead zirconate titanate PbZrxTil-xO3; SBT is strontium bismuth tantalate Sr1-yBi2 + xTa2O9. The structure of these two materials is shown in Figure 2. Figure 2. Schematic Diagram of PZT and SBT Material StructurePZT is the most studied and widely used. Its advantage is that it can be made at lower temperatures by sputtering and MOCVD. It has the advantages of large residual polarization, cheap raw materials, and low crystallization temperature.; its disadvantages are fatigue degradation problems, and lead pollution to the environment. Moreover, the film deposition process of these materials has proved to be very challenging. At the same time, the extremely high dielectric constant (about 300) of these materials is a big obstacle to their integration into transistors.In addition, scientists have discovered the presence of a ferroelectric phase in a less complex material, hafnium oxide (HfO2), which raise a new concept of storage concept. The researchers found that the ferroelectric phase) can be stabilized by doping silicon (Si) into HfO2. Compared with PZT, HfO2 has a lower dielectric constant and can deposit thin films in a conformal manner (ie, the atomic layer deposition (ALD) process). Most importantly, scientists are familiar with HfO2, because it is the HK gate oxide material in the logic device HKMG. By modifying this CMOS-compatible material, logic transistors can become non-volatile FeFET memory transistors.Functional verification of FeFETs has been implemented in a two-dimensional planar architecture. At the same time, the HfO2 conformal deposition process makes 3D stacking possible, for example, depositing ferroelectric materials on vertical “walls’ to stack transistors in a vertical direction.In terms of materials, 3D FeFETs can solve some of the challenges brought by 2D FeFET structures. One challenge is related to the polycrystalline nature of the HfO2. Scaling the thickness of the HfO2 film will significantly reduce the number of grains in this layer. Because not all the crystal grains have the same polarization direction, the reduction of crystal grains will affect the consistency of the transistor’s response to the external electric field, and eventually lead to large differences between the tubes. By 3D stacking, this drawback is overcome in physical filed. That is, HfO2 does not need to be compressed too thinly, thereby reducing tube-to-tube variation.These vertical FeFETs are expected to have more advantages than complex 3D NAND flash memory, including simple process, lower power consumption and faster speed. Compared to 3D NAND flash memory, vertical FeFET can be programmed at a lower voltage, which improves memory reliability and scalability.The biggest advantage of SBT is that it does not have the problem of fatigue degradation, and it does not contain lead, which meets EU environmental standards; however, its disadvantages are that the process temperature is higher, which makes the process integration difficult, and the degree of residual polarization is small. The comparison of the two materials is shown in Table 1.Table 1. Comparison between PZT and SBT  PZTSBTStructureABO3Layered structureDeposition technologySol-gel,MOCVDSol-gel,MOCVDProcess temperature450℃~700℃750℃~850℃Residual polarity3012Fatigue10101010Data hold85℃@10a- At present, from the perspective of environmental protection, PZT has been banned, but from the perspective of performance and process integration of ferroelectric memory and cost, SBT has no advantages compared to PZT. Therefore, the selection of ferroelectric materials is worth discussing. Ⅴ Circuit StructureThe circuit structure of the ferroelectric memory is mainly divided into the following three types: 2 transistors-2 capacitors (2T2C), 1 transistor-2 capacitors (1T2C), 1 transistor-1 capacitor (1T1C), as shown in Figure 3. The 2T2C structure has two opposite capacitors for each bit as a reference to each other, so the reliability is better, but occupies too much space, which is not suitable for high-density applications. The transistor / single capacitor structure can be used like a DRAM to provide a reference for each column of the memory array, compared with the existing 2T2C structure, they effectively reduce the required space of the memory cell by half. This design greatly improves the efficiency of ferroelectric memory and reduces the production cost of ferroelectric memory products. The 1T1C structure has a higher integration density (8F2), but its reliability is poor. And the 1T2C structure is a compromise between these two structures. Figure 3. Three FRAM StructuresAt present, in order to obtain a high-density memory, 1T1C structure is mostly used (as shown in Figure 4). In addition, a chain structure is also adopted, thus Chain FeRAM is made. This structure is similar to the NAND structure. Through this method, a higher storage density than 1T1C can be obtained, but this method will also greatly increase the access time. Chain FeRAM (CFeRAM) structure is shown in Figure 5. Figure 4. 1T1C Layout Figure 5. Chain FeRAM (CFeRAM) Circuit StructureⅥ Reading and Writing ProcessAccording to the polarity of the electronic memory cell, a small charge amount is “0” and a large charge amount is “1”. This charge is converted into a reading voltage, which is “0” when it is less than the reference voltage and when it is greater than the reference voltage represents “1”. The stored information is read out as shown in Figure 6. Figure 6. Reading and Writing Process of FRAMDuring the reading process, the word line voltage is increased to turn on the MOS transistor, and then the drive line voltage is increased as VCC, so that different charges of the storage capacitor are distributed to the bit line parasitic capacitance, so different voltages appear on the BL to identify the data. During a writing process, the word line is raised to turn on the MOS transistor, and a pulse is applied to the drive line, so that different data on the bit line are stored in two different steady states of the ferroelectric capacitor.By adding a positive voltage or a negative voltage, these two voltages can make the capacitor into two different polarities. In this way, the information is written into the memory. Ⅶ FRAM StructureAt present, the most common device structures of ferroelectric memories are planar and stack structures. The difference between the two is the location of the dry ferroelectric capacitor and the way in which the capacitor is connected to the MOS tube. In the planar structure, the capacitor is placed above the field oxide, and the electrode of the capacitor is connected to the active area of the MOS tube through metal aluminum. The process is relatively simple, but the unit spacing is large. In the stack structure, the capacitor is placed in the source region, the lower electrode of the capacitor is connected to the source terminal of the MOS tube through a plug based on CMP process, which has a high integration density. In addition, the stack structure can adopt the method of making ferroelectric capacitors on metal wires, thereby reducing the mutual influence during the formation process. The following schematic diagrams of the two structures are shown in Figure 7 and Figure 8. Figure 7. Planar Structure Figure 8. Stack StructureThe process of the planar structure is relatively simple. The isolation uses the LOCOS structure, and the planarization does not require the CMP. The stacked structure has a high degree of integration based on advanced technique, and STI is used for isolation, in addition, CMP is required for planarization, and copper wires can be used.In addition, there is a structure that uses a ferroelectric material as the gate. Such a device can eliminate the destructive problem of data readout, and theoretically it is more space-saving and can make more greater integration. However, there are still serious problems with this structure, that is, the data storage capacity is very poor, only one month or less, so it is far from practical. Figure 9 is a schematic diagram of such a structure. Figure 9. FeFET Structure DiagramAt present, the ferroelectric memory generally adopts a planar structure with the line width more than 0.5 μm, and generally uses a stack structure when the line width is less than 0.5 μm. Ⅷ Comparison of FRAM with Other Storage TechnologiesAt present, Ramtron’s FRAM mainly includes two categories: serial FRAM and parallel FRAM. Among them, serial FRAM is divided into I2C two-line FM24×× series and SPI three-line FM25xx series. Serial FRAM is compatible with the traditional 24xx and 25xx E2PROM pins and timing, which can be directly replaced.FRAM products have the advantages of RAM and ROM, and fast read and write speed, in addition, they can be used as non-volatile memory. Due to the shortcoming of ferroelectric crystals, the number of accesses is limited, beyond which FRAM is no longer non-volatile. The maximum access times given is 10 billion, but it not means FRAM will be scrapped when over this upper limit. In the terms of it, FRAM is not non-volatile, but it can still be used as an ordinary RAM.FRAM vs E2PROMFRAM can be used as a second option for E2PROM. Except the performance of E2PROM, the FRAM access speed is much faster. When using FRAM, it must be determined that once there are 10 billion accesses is down to FRAM in the system, there is no damage.FRAM vs SRAMIn terms of speed, price, and convenience, SRAM is better than FRAM; but from the perspective of the entire design, FRAM has certain advantages. Non-volatile FRAM can hold startup programs and configuration information. If the maximum access speed of all the memories in the application is 70ns, one piece of FRAM can be used to complete the system, making the system structure more simpler.FRAM vs DRAMDRAM is suitable for applications where density and price are more important than access speed. For example, DRAM is the best choice for graphics display memory. There are a large number of pixels to be stored, and the recovery time is not very important. If you don’t need to save the last content at the next boot, use volatile DRAM memory. The role and cost of DRAM are reasonable compared with FRAM. In short, it turns out that DRAM cannot be replaced by FRAM totally.FRAM vs FlashAt present, the most commonly used program memory is Flash, which is more convenient and cheaper to use. The program memory must be non-volatile, and easier to rewrite, but the use of FRAM is limited by access times.Ⅸ FRAM UsageData collection and recordingFeRAM allows designers to write data faster and more frequently, and at a lower price than EEPROM.Typical applications: meters (electric meters, gas meters, water meters, flow meters), RF/ID instruments, car black boxes, air bags, GPS, power grid monitoring systems, and so on. Parameter setting and storageFeRAM helps designers solve the problem of data loss due to sudden power failure by storing data in real time. Parameter storage in the FeRAM is used to track the changes of the system in the past time. Its purpose includes restoring the system state or confirming a system error when the power is on.Typical applications: photocopiers, printers, industrial controls, set-top boxes, network equipment  and large household appliances. Non-volatile bufferFeRAM can quickly store data before it is stored in other memory, so that the data in the buffer will not be lost when having power failure.Typical applications: industrial systems, ATM teller machines, tax control machines, commercial settlement systems (POS), fax machines, non-volatile cache memory in hard disk, etc. Ⅹ SummaryFerroelectric memory is an emerging non-volatile memory. It started early and realized industrialization. Because of its advantages such as low power consumption, fast read and write speed, and strong anti-irradiation capabilities, there is a market for small-scale storage areas with low power consumption and radiation resistance. Having the characteristic of anti-radiation, in the case of electromagnetic waves or radiation, the data is still safe, so it has important applications in space science, medicine and other specific fields. However, the ferroelectric memory also has the disadvantages that it is difficult to improve the integration, the process is more contaminated, and it is difficult to be compatible with the CMOS technique. So that it needs further research and solution. Ⅺ One Question Related to FRAM and Going Further11.1 QuestionWhat is FRAM used for?11.2 AnswerFerroelectric RAM is a random-access memory similar in construction to DRAM but using a ferroelectric layer instead of a dielectric layer to achieve non-volatility. It is one of a growing number of alternative non-volatile random-access memory technologies that offer the same functionality as flash memory. FRAM can be used in many fields, for example, with ultra-low power consumption, it is very suitable for intelligent water meters, gas meters and so on. Frequently Asked Questions about Ferroelectric RAM1. What is FRAM memory?Ferroelectric RAM (FeRAM, F-RAM or FRAM) is a random-access memory similar in construction to DRAM but using a ferroelectric layer instead of a dielectric layer to achieve non-volatility. 2. What is ferroelectric effect?Ferroelectricity is a characteristic of certain materials that have a spontaneous electric polarization that can be reversed by the application of an external electric field. ... Thus, the prefix ferro, meaning iron, was used to describe the property despite the fact that most ferroelectric materials do not contain iron. 3. How does FRAM work?FRAM is a nonvolatile storage memory that retains its data even after the power is turned off. However, similar to commonly used DRAM (Dynamic Random Access Memory) found in personal computers, workstations, and non-handheld game-consoles, FRAM requires a memory restore after each read. 4. What are the unique characteristics of FRAM?FRAM has the characteristics of both ROM (Read Only Memory) and RAM (Random Access Memory), and features faster write, great read/write cycle endurance, and low power consumption. 5. Which enables the read and write operation in Feram?Write Operation in Ferroelectric Random Access Memory (FRAM)Similar to read operation, a pre-charge operation follows a write access. The circuit applies 'write' data to the Ferroelectric capacitors. If necessary, the new data simply switches the state of the ferroelectric crystals.

  Solid-state drive or Solid-state disk, abbreviated as SSD, is a computer storage device made of integrated circuits. You can use non-volatile memory (mainly NAND Flash in flash memory) as a permanent storage device, or use volatile memory (such as DRAM) as a temporary storage device. Solid-state hard drives often use SATA, PCI Express, mSATA, M.2, ZIF, IDE, U.2, CF, CFast... and other interfaces. At present, due to the difference between the price per unit and the maximum storage capacity of the mechanical hard disk, the solid state hard disk cannot completely replace the mechanical hard disk for the time being.   How do SSDs Work? | How does your Smartphone store data?  Catalog I What is Solid State Drive? II SSD Classification 2.1 Solid State Drive based on FLASH   Memory 2.2 Solid State Drive based on DRAM III Development History IV SSD Basic Structure 4.1 Main Control Chip 4.2 Cache Chip 4.3 Flash Memory Chip V Compare with Traditional Hard Disk VI SSD Advantages and Disadvantages 6.1 SSD Advantages 6.2 SSD Disadvantages FAQ I What is Solid State Drive?  Solid State Drive, also called solid state disk or SSD, is a hard disk made from an array of solid-state electronic memory chips, consisting of a control unit and a memory unit (FLASH chips / DRAM chips). The interface specification and definition, function and usage method of solid state disk are identical to those of ordinary hard disk drive, and the product shape and size are also the same as that of ordinary hard disk drive.  The working temperature range of SSD chip is very wide: Commercial product: 0~70℃; Industrial product: -40~85℃. Although the cost of manufacturing an SSD is high, it is still gradually being popularized into the DIY market. Due to the difference between solid state drive technology and traditional hard disk drive technology, there are many new memory manufacturers. Manufacturers only need to buy NAND memory, and then they can manufacture solid state disk with proper control chip. The new generation solid state drive generally uses SATA-2 interface, SATA-3 interface, SAS interface, MSATA interface, PCI-E interface, NGFF interface, CFast interface and SFF-8639 interface. II SSD Classification There are two kinds of storage media in solid state drive, one is FLASH chip and the other is DRAM. 2.1 Solid State Drive based on FLASH Memory Solid state drive based on FLASH memory(IDE FLASH DISK, Serial ATA Flash Disk) is using FLASH chips as its storage media. Its appearance can be made into a variety of forms, such as: Laptop hard drive, Micro hard disk, memory card, USB flash disk and etc. The biggest advantage of this SSD is that it is movable, and the data protection is not controlled by power supply. Also, it can be applied to various environments, but its service life is not too long, so it is suitable for individual users. In a flash-based solid state drive, memory cells are divided into two categories: SLC (Single Layer Cell) and MLC (Multi-level Cell).  Solid state drive based on FLASH memory The characteristics of SLC is its high cost, small volume and high speed. And for MLC, it is with characteristics of large volume, low cost but low speed. Each unit of MLC is 2bit, which is exactly twice as many as SLC. However, due to the large amount of data stored in each MLC storage cell and the relative complexity of the structure, the probability of error will increase, so the error correction must be carried out. This action will cause its performance to lag significantly behind the SLC flash memory with simple structure. In addition, the advantage of flash memory is that the number of duplicates is up to 100000 times, which is 10 times higher than that of MLC flash memory. In order to ensure the lifetime of MLC, the control chip is calibrated and the intelligent wear balance algorithm is used, so that the write times of each memory cell can be divided equally, and the mean time between failures (MTBF) can reach 1 million hours.   2.2 Solid State Drive based on DRAM Solid state drive based on DRAM is using DRAM as the storage medium. However, its application range is currently narrow. It follows the design of traditional hard disk, which can be volume setup and managed by most file system tools of operating system, and provides industrial standard PCI and FC interfaces for connecting hosts or servers. The application can be divided into two kinds: SSD hard disk and SSD hard disk array. It is a kind of high performance memory and has a long service life. The downside of it is its need for independent power supply to protect the data security. Solid state drive based on DRAM III Development History > 1956: IBM invented the world's first hard disk. > 1968: IBM restates the feasibility of Winchester technology, which established the development direction of hard disk. > 1970: StorageTek developed the first solid state hard drive. > 1989: The world's first solid state hard disk occurred. > 2006.03: Samsung took the lead in launching a solid state hard disk laptop with 32GB capacity > 2007.01: SanDisk released an 1.8-inch solid state hard disk with 32GB and 2.5-inch model with 32GB in March. > 2007.06: Toshiba has launched its first solid-state hard disk laptop with 120GB capacity. Intel SSD 520 Series > 2008. 09: The official launch of MemoRight SSD marks the accelerated entry of Chinese enterprises into solid state hard disk industry.  > 2009: With the development of SSD , all the manufacturers crushed into this industry , and the storage virtualization then entered a new stage . > 2010.2: Magnesia released the world's first solid-state disk with SATA 6Gbps interface, which breaking through the speed of SATAII interface reading and writing(300MB/s). > The end of 2010: Renice launched and patented the world's first high-performance mSATA solid state disk. > 2012: Apple uses 512GB solid state hard drives on its laptops. > 2015.08.01: TEKISM introduced the first mobile solid-state hard disk with Type-C interface. The SSD provides the latest Type-C interface and supports double-sided insertion of the USB interface. > 2016.01.01: Chinese storage company TEKISM has released the world's first Type-C fingerprint encrypted SSD. SSD M300   IV SSD Basic Structure The FLASH based SSD is the main category of solid state drives. Its internal structure is very simple. The main body of the solid state hard disk is actually a PCB board, and the most basic accessory on this PCB board is the control chip, cache chip(some low-end disks have no caching chip) and NAND flash that used for data storage. The more common solid state hard drives on the market are: LSISandForce, Indilinx, JMicron, Marvell, Phison, Goldendisk and Samsung. The main control chip is the brain of solid state hard drive. One of its functions is to reasonably allocate the load of data on each flash memory chip, and the other is to transfer the whole data and connect the flash memory chip with the external SATA interface. The ability of different master control is very different in data processing ability, algorithm, flash chip reading and writing control , which will directly lead to a ten times gap of solid state hard disk performance. Different SSD 4.1 Main Control Chip Table 1. Brand, model and product of the main control chip for solid state drive 4.2 Cache Chip   The cache chip is next to the main control chip. Solid state drive and traditional hard disk both require high speed cache chip to assist the main control chip for data processing. It is important to be noted here that there are some cheap solid state drive solutions to save the cost of the cache chip, which will have a certain impact on the performance in use.   4.3 Flash Memory Chip Apart from main control chip and caching chip, chips on the other place on PCB board are mainly NAND Flash chips. NAND Flash memory chips are divided into SLC, MLC and TLC NAND Flash memory.    V Compare with Traditional Hard Disk The interface specification and definition, function and usage method of solid state drives are almost the same as those of ordinary hard disk, and the shape and size of solid state drives are basically the same as that of ordinary 2.5 inch hard disk. Solid state drive has the advantages of fast reading and writing, light mass, low power consumption and small volume, which is not possessed by traditional mechanical hard disk. At the same time, its disadvantage is obvious. Although IDC believes that SSD is in the mainstream of the storage market, its price is still relatively high and its capacity is relatively low, once the hardware is damaged, the data is difficult to recover, and others think that the durability of solid state drives is relatively short. The main factors that influence the performance of solid state drive are main control chip, NAND flash media and firmware. Under the same conditions, what kind of interface is adopted may also affect the performance of SSD. The mainstream interface is SATA (including two kinds of interfaces for 3Gb/s and 6Gb/s) and the SSD of the PCIe 3.0 interface. Duo to the difference of the design and the principle of data reading and writing between SSD and the common disk, the internal structure of SSD is also very different. In general, the structure of solid state disk (SSD) is relatively simple and can be disassembled; therefore, most of the articles we see about SSD performance evaluation include an internal disassembly diagram of SSD. On the other hand, the data reading and writing of the ordinary mechanical disk is to lift the magnetic head by the air produced by the high speed rotation of the disc, which makes the magnetic head infinitely close to the disk without contact, and the stepper motor is used to push the head to read the data of changing the track. Therefore, its internal structure is relatively complex, more sophisticated, which is generally not allowed to disassemble. Once human disassembly, there is a strong risk of damage on the disk and disk can not work properly.This is why disassembly diagrams are largely invisible when evaluating ordinary disks.   VI SSD Advantages and Disadvantages 6.1 SSD Advantages   6.1.1 Fast reading and writing Using flash memory as storage medium, the read speed of SSD is faster than mechanical hard disk. SSD does not use (magnetic) head, and its seek time is almost 0. The speed of continuous writing is amazing, and most SSD manufacturers will claim that their solid state drives continue to read and write faster than 500MB / s! The speed of solid state hard disk is not only reflected in continuous reading and writing, but also in random reading and writing speed, which is directly reflected in most of the daily operation. Associated with this are extremely low access times, with the most common 7200 rotary mechanical drives running at 12-14 milliseconds, while solid state drives can easily reach 0.1 milliseconds or less.    6.1.2 Shock resistance Traditional hard drives are disk-type, data is stored in the disk sector. The solid state drive is made from flash memory particles (mp3, U disk, etc.), so there are no mechanical components inside the SSD. This will not affect its normal use even when moving at high speed or even with tilting, and minimize the possibility of data loss in the event of collisions and oscillations. Compared with the traditional hard disk, solid state drive has an absolute advantage.   6.1.3 Low power consumption  The power consumption of solid state drive is lower than that of traditional hard disk.   6.1.4 Noiseless Solid state drive has no mechanical motors and fans inside, thus it works with a noise value of 0 dB.Flash based solid state drives have lower energy consumption and lower calorific emissions (but the consumption of high-end or large-capacity products will be larger). There are no mechanical parts inside, so there will be no mechanical failure, no collision, no shock or vibration. Because the solid state hard disk uses the flash memory chip without mechanical parts, it has the characteristics of low heat emission and fast heat dissipation.   6.1.5 Wide range of working temperature A typical hard disk drive can only work in the range of 5 to 55℃ and most solid state drives can work at -10~70℃. The solid state hard disk is smaller in size and lighter in weight than the mechanical disk of the same capacity. The interface specification and definition, function and usage method of solid state drives are the same as those of ordinary hard disk, and the product shape and size are the same as that of ordinary hard disk. The working temperature range of the chip is very wide(-40~85 ℃).   6.1.6 Lightweight Solid state drives are lighter in weight, 20-30 grams lighter than regular 1.8-inch hard disks.   6.2 SSD Disadvantages  6.2.1 Capacity The maximum capacity of solid state drive is only 4TB. It is SanDisk Optimus MAX   6.2.2 Limited Service Life Solid state drive flash memory has the problem of limitation of erasing times.  A flash memory is completely erased once called a P / E, so the life of flash memory takes P/E units. The lifetime of the 34nm flash chip is about 5000 P / E, while the lifetime of the 25nm is about 3000 P / E. With the improvement of SSD firmware algorithm, the new SSD can provide less unnecessary writing. An 120GB solid state drive that writes 120GB of files to one P / E. In practical use, individual users often write in random rather than continuously. So there will be higher probability of bad sectors. In addition, while each sector of the solid state drive can be repeatedly erased 100000 times(SLC), in some applications such as LOG records in operating system , A sector may be read and written over and over again, in which case the actual lifetime of a solid state disk is not yet tested. However, with the equalization algorithm, the life expectancy of the memory unit is increased by 100000 writes, and the low cost MLCs have only 10, 000 write lives, while the cheap TLC flash memory is only 500 to 1, 000 times.   6.2.3 Expensive The price of the 128GB solid state drive on the market is around RMB550, while the price of the 256GB is around RMB950 .   FAQ   1. Is SSD better than HDD? SSDs in general are more reliable than HDDs, which again is a function of having no moving parts. ... SSDs commonly use less power and result in longer battery life because data access is much faster and the device is idle more often. With their spinning disks, HDDs require more power when they start up than SSDs.   2. What is a solid state drive used for? A solid-state drive (SSD) is a solid-state storage device that uses integrated circuit assemblies to store data persistently, typically using flash memory, and functioning as secondary storage in the hierarchy of computer storage.   3. Is a 256GB SSD better than a 1TB hard drive? A 1TB hard drive stores eight times as much as a 128GB SSD, and four times as much as a 256GB SSD. The bigger question is how much you really need. In fact, other developments have helped to compensate for the lower capacities of SSDs.   4. Do I need HDD if I have SSD? You don't need both but having a SSD for your operating system and a HDD for your storage drive might be the best bang for your buck. Otherwise, you only need one; a HDD is cheaper, larger, slower, and more prone to data loss. A SSD are normally smaller in storage for the same price but faster and shock resistant.   5. Should I upgrade to SSD? It's time to upgrade to an SSD if you're still using a mechanical hard drive in your computer. ... Solid-state drives are so much faster because they don't have a spinning magnetic platter and moving head. After upgrading, you'll be amazed at the performance improvements and wondering why you waited so long.   6. What are the pros and cons of a solid state drive? a. SSD is faster. b. SSD can take a licking c. HDD is cheaper; SSD is still expensive. d. HDD has greater storage capacity than SSD   7. Do solid state drives crash? SSDs can fail, but in a different way than traditional HDDs. While the latter often fail because of mechanical issues, SSDs may fail due to the methods used to write information. ... Each P/E cycle gradually degrades the memory of an SSD's cells until they eventually become worn down.   8. Can I put SSD and HDD together? The answer is absolutely yes. You can install both, but, SSD will have faster SSD speeds and HDD will still have slower HDD speeds. It is an excellent idea to use SSD and HDD at the same time. An SSD boasts many distinctive merits such as fast loading speed, low power consumption, and etc.     9. How much faster is a SSD than a HDD? As noted above,solid-state drives can read/write speeds of around 550 MB/s faster than a hard disk drive. SSDs can go even faster, provided your computer can handle it. A PCIe SSD can achieve anywhere from 1.2 GB/s to 2.2 GB/s - assuming you have a motherboard that can handle these speeds.   10. How can I tell if my SSD is failing? So here are four signs of SSD failure: Sign #1: Your computer takes a long time to save files. Sign #2: You have to restart often. Sign #3: Your computer crashes during boot. Sign #4: You receive a read-only error.

Toshiba Memory has announced development of the world’s first BiCS FLASH three-dimensional (3D) flash memory utilising Through Silicon Via (TSV) technology with 3-bit-per-cell (triple-level cell, TLC) technology. Shipments of prototypes for development purposes started in June, and product samples are scheduled for release in the second half of 2017. The prototype of this ground-breaking device will be showcased at the 2017 Flash Memory Summit in Santa Clara, California, United States, from August 7-10.Devices fabricated with TSV technology have vertical electrodes and vias that pass through silicon dies to provide connections, an architecture that realises high speed data input and output while reducing power consumption. Real-world performance has been proven previously, with the introduction of Toshiba’s 2D NAND Flash memory. Combining a 48-layer 3D flash process and TSV technology has allowed Toshiba Memory Corporation to successfully increase product programming bandwidth while achieving low power consumption. The power efficiency of a single package is approximately twice that of the same generation BiCS FLASH memory fabricated with wire-bonding technology. TSV BiCS FLASH also enables a 1-terabyte (TB) device with a 16-die stacked architecture in a single package. Toshiba Memory will commercialise BiCS FLASH with TSV technology to provide an ideal solution in respect for storage applications requiring low latency, high bandwidth and high IOPS/W, including high-end enterprise SSDs. Ref.KY32-CG7937AAKY32-CG7797AAT

B&R has selected the Hyperstone S8 Flash Memory Controller for their recently announced X90 mobile automation product line. The X90 family of products are designed for securing mobile control and I/O tasks in demanding environments experienced by industrial and mobile machines.To meet all requirements of their robust applications B&R implemented the Hyperstone S8 Flash Memory Controller, which operates over an extended temperature range and ensures the highest reliability and endurance even under extreme environmental conditions. The S8 Controller enables the use of advanced technology NAND flashes in demanding, rugged applications e.g. in commercial vehicles and outdoor applications. B&R X90 products deliver robustness and durability hence the choice of Hyperstone products.X90 mobile With a comprehensive set of standardised components, the X90 product line offers automation solutions perfect for flexible automation concepts used in mobile and outdoor applications found in agriculture and forestry, construction or municipal vehicles. Extended temperature range, strong vibrations or shocks and influences such as salt, oil and UV light must be handled by the system. Basic features of the X90 family include interfaces for CAN, USB, Ethernet and the real-time POWERLINK bus system. A flexible set up allows the addition of I/O channels and interfaces. The X90 series was introduced at Bauma 2016 in Munich.S8 The Hyperstone S8 Flash Memory Controller and its application and Flash specific firmware offer a platform for industrial high endurance Flash Memory cards or modules which are compatible with SD interface host systems. Together with Hyperstone’s proprietary hyReliability firmware, S8 provides enhanced endurance and data retention management, as well as rigorous fail-safe features, all of which are mandatory for industrial applications. Implemented hardware features and special firmware developments enable the highest data retention and refresh mechanisms, even when storage applications are faced with extreme environmental conditions.Reference:MT16JTF51264AZ-1G6M1SDUS5EB-001GMD2202-D192MT9VDDT6472HY-335 F2