Home  Memory

Aug 9 2019

Key Characteristics of Main Computer Memories

Introduction

In computing system, Memory refers to the computer hardware integrated circuits that store information for immediate use in a computer. Like many things, computer memory comes in many different types and has numerous applications nowadays. It is the most essential element of a computing system because without it computer can't perform simple tasks, and people can't live without Internet, so learn more about the different types of computer memory characteristics can help us to enjoy the life and work well.

Computer memories that often act as extensions of our memory, and this video explains how computer memory works. 

The following expreessed are the key characteristics of main computer memories.

  • Semiconductor memory 

A computer memory composed of a semiconductor is called a semiconductor memory, and the memory of the semiconductor is small in size, low in power, and short in access time. What’s more, when the power is lost, the stored data is also lost, which is a kind of volatile memory.

  • Magnetic material memory

A computer memory made of magnetic material is called a magnetic memory. A layer of magnetic material is coated on metal or plastic to store data. The feature is that non-volatile, the data will not disappear after power-off, and the access speed is slow.

  • Disk storage 

The optical disk storage uses a laser to read on a magneto-optical material, which is non-volatility with good durability and high recording density. It is now used in computer systems as external storage.

computering memory

Random Access Memory ( RAM )

The contents of the storage unit can be freely taken out or stored as needed. Such a memory will lose its storage contents when the power is turned off, therefore, it mainly used to store programs for short-term use. It is characterized by nonvolatile, that is, power loss then memory loss.

There are two main types of RAM, one is called static RAM (SRAM). SRAM is very fast, in other words, it is the fastest storage device for reading and writing, but it is also very expensive. So it is only used in demanding places, the primary buffer or secondary buffer of CPU, for example. The other is called dynamic RAM (DRAM). DRAM keeps data for a short time and slower than SRAM, but it is faster than any ROM, but DRAM is cheaper than SRAM in terms of price. Many computers memory is DRAM.

SRAM (static random access memory) does not need to be refreshed when power is applied, that is, data will not lost, and is generally not multiplexed with row and column addresses. DRAM (dynamic random access memory) requires constant refresh to save data. Moreover, its row and column addresses are multiplexed, and many have page mode.

Read Only Memory ( ROM )

ROM usually refers to solidified computer memory (write once, read repeatedly), which is  opposite to the RAM.

There are several categories of ROM. PROM is a programmable ROM, but it can be programmed once only, that is, after the software is written, it cannot be modified. This is an early product that is impossible to use nowadays.The EPROM, its original program is wiped out by ultraviolet light, is a general-purpose memory. Another type of EEPROM is electronically erased, which is expensive, has a long write time with very slow writing speed.

FLASH memory, combines the advantages of ROM and RAM, not only with the ability of electronic erasable programmable, but also does not loss data when power off and can quickly read data after power on. This memory is often used in U disk and MP3.

Currently, Flash has two main types, NOR Flash and NADN Flash. The reading of NOR Flash is the same as the common SDRAM. Users can directly run the code loaded in NOR FLASH, which can reduce the capacity of SRAM to save costs. NAND Flash does not take the read technology of internal memory. Its read is performed in the form of reading one block, usually 512 bytes at a time. In addition, users can't run the code directly on NAND Flash, so many manufacturers will give a small NOR Flash when produce a NAND Flash to run the boot code.

Generally, NOR Flash is used for small-capacity, because it has a fast reading speed and is used to store important information such as operating system. For large-capacity NAND flash, the most common application is disk on chip (DOC) used in embedded systems. And the "flash disk" we usually use, can be erased online.

computer memory

Note:

We can usually think that RAM is the data memory of the microcontroller (the data here includes internal data memory, usually user RAM area, bit addressable area, and work group register) and special function register SFR). ROM is the program memory of the MCU, and some MCUs may also include data memory. The data here refers to the data to be saved, that is, the data still existing after the MCU is powered off, in other words, the final collected data remained. The RAM only plays a role of saving data temporarily when the microcontroller is running. For example, some processing operations are performed on the collected data, so that an intermediate quantity is generated, and the RAM is used to temporarily access the intermediate quantity, and finally the result is placed in a ROM.

ROM can only read data from it under normal working conditions, and can't modify or rewrite data at any time. Its advantage is that the circuit structure is simple, and the data will not be lost after power off; the disadvantage is that it is only suitable for storing those fixed data. The fundamental difference between RAM and ROM is that RAM can write or read memory data at any time under normal operating conditions.


Static RAM ( SRAM )

It is a computer memory with a static access function that saves the data inside it without refreshing the circuit. Unlike DRAM memory, which needs to refresh the circuit, there is a need to charge and refresh the DRAM regularly, otherwise the internal storage data will disappear.

SRAM has higher performance, but SRAM also has its shortcoming, that is, its lower integration degree. Same-capacity DRAM memory can be designed to be smaller, but the SRAM requires a lot of size, thus the SRAM memory on the motherboard takes up a portion of the area.

Advantages: High speed, do not refresh circuit based on the memory characteristic , and the whole working efficiency can be improved.

Disadvantages: Low integration, large power consumption, and high price, but there is a small amount of it is used in key systems to improve efficiency.

Dynamic RAM ( DRAM )

DRAM can only keep data for a short time. To maintain data, DRAM uses capacitor to store data, so it must be refreshed once in a while. If the memory unit is not refreshed, the stored information will be lost. 

The memory of the computer we usually refer to is dynamic random access memory (DRAM). The so-called "dynamic" in here means that when we write data to DRAM, after a period of time, the data will be lost, so we need an additional circuit to perform a memory refresh operation. The specific working process is as follows: whether a DRAM memory cell stores 0 or 1 depends on whether the capacitor has a charge, having charge represents 1, and no charge represents 0.

However, for a long time, the capacitor representing 1 will discharge, and the capacitor representing 0 will absorb the charge. This is the cause of data loss. The regularly refresh operation is to check the capacitor: If the charge is greater than 1/2 of the full charge, it is considered to be 1 and fully charge the capacitor; if the charge is less than 1/2, it is considered to represent 0, and the capacitor is discharged.

Note:

The structure of a DRAM memory cell is very simple, so it achieves a much higher level of integration than SRAM, but its access speed is not as fast as SRAM.

Synchronous Static RAM ( SSRAM ) and Synchronous Dynamic RAM ( SDRAM )

Synchronization means that the memory needs a clock, and the transmission of internal commands and data are based on it. Random means that the data is not stored in a linear order, but the data is read and written by the specified address. All accesses to the SSRAM are initiated on the rising/falling edge of the clock. Addresses, data inputs, and other control signals are all related to the clock signal. This is different from asynchronous SRAM, where access to it is independent of clock and data input and output are controlled by address changes.

MASK ROM

A mask read-only memory is a manufacturer that prepares a ROM or EPROM with raw data as a sample in advance for mass production, and then mass-produces the same ROM as the sample. This is a mass production. The ROM sample is the MASK ROM, and the data burned in the MASK ROM can never be modified.

One-time Programmable ROM ( OTP ROM )

Programmable ROM: once the content has been written, it is impossible to modify, so it can only be written once.

Erasable programmable ROM: erased with ultraviolet light, written with high voltage programming ( +21V or +12V ).

Electrically Erasable Programmable ROM (EEPROM) is used for electrical signal erasure.

FLASH Memory

Electrical signal can be erased.

memory in ic


  • The difference between MASK ROM,FALSH ROM and OTP ROM

The program of MASK ROM is solidified at the factory, and suitable for applications where the program is fixed; FALSH ROM's program can be erased repeatedly, with great flexibility, but at a higher price, and suitable for price-insensitive applications or development purposes; OTP ROM price is between the MASK ROM and FALSH ROM, and can be programmed once, therefore, it is suitable for applications that require both flexibility and low cost, especially for electronic products that need continuous refurbishment and meet rapid mass production.

The commonality between OTP ROM and PROM is that they can only be programmed once.

DDR: Double Date Rate. A common DDR SDRAM refers to a double rate synchronous dynamic random access memory.

The difference between DDR SDRAM and SDRAM: SDRAM transfers data only once in one clock cycle, and it transmits data during the rising period of the clock; while DDR memory transmits data twice in one clock cycle of each period. Also it can achieve higher data rates at the same bus frequency as SDRAM.

Note: Why DDR3 can replace DDR2 memory?

Frequency: DDR3 can operate from 800MHz to 1666MHz or more; while DDR2 operates from 533MHz to 1066MHz. In general, DDR3 is twice the frequency of DDR2, and the operating performance is improved by reducing the read and write time by half.

Power consumption: DDR3 can save 16% of energy compared to DDR2, because the new generation of DDR3 operates at 1.5V, while DDR2 operates at 1.8V, which can compensate for the high power generated by excessive operating frequency. At the same time, less energy consumption can extend the life of the component.

Technology: DDR3 memory bank has increased to eight, double the DDR2. So compared to DDR2 pre-read, it will increase efficiency by 50%, which is twice the DDR2 standard.

IC Memory

  • Main technical indicators of computer memory that you should know:

Storage capacity: it generally refers to the number of storage units (N) included in a memory.

Access time (TA): it refers to the memory from the acceptance of the command to the read ∕ write data and stabilizes at the data register (MDP) output.

Memory cycle time (TMC): The minimum time required between two independent access operations, in addition, TMC is usually longer than TA.

Access rate: The total number of bits of information exchanged between main memory and the outside (such as CPU) per unit time.

Reliability: it described by the mean time between failures (MTBF), that is, the average interval time between two failures.

You May Also Like

Future Trends in NV and NVM Memories

What is Computer Memory? Types of Computer Memory

What Are the New Memory Technologies and What Problems Can They Solve?

Related Articles

  • How to Buy the Right SSD? A Purchase Gui...
    Warm hints: This article contains about 3000 words and reading time is about 15 min.How to choose SSD? Some netizens are still not very clear about the SSD of the computer and don't know how ...
  • What is Computer Memory? Types of Comput...
    Ⅰ IntroductionThis video going to trace the history of these storage technologies from punch cards, delay line memory, core memory, magnetic tape, and magnetic drums, to floppy disks, hard disk drives...
  • The Working Principle and Classification...
    Warm hints: This article contains about 7000 words and reading time is about 35 mins.IntroductionMemory is a memory device in a computer system that stores programs and data. All information on the co...
  • Classifications and Characteristics of C...
    IntroductionThe memory is an entity that memorizes information, which is important for the computer to have the ability to store data and information, to automatically execute programs continuous...
  • Future Trends in NV and NVM Memories
    IntroductionNon-volatile memory (NVM) is a computer memory that does not disappear when the current is turned off. In non-volatile memory, depending on whether the data in the memory can be rewritten ...
  • Ferroelectric Random Access Memory Techn...
    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 ...

5 comments

    • Jacky W on 2019-8-10 11:18:24

    A memory is just like a human brain. It is used to store data and instructions. Computer memory is the storage space in the computer, where data is to be processed and instructions required for processing are stored. The memory is divided into large number of small parts called cells. Each location or cell has a unique address, which varies from zero to memory size minus one. For example, if the computer has 64k words, then this memory unit has 64 * 1024 = 65536 memory locations. The address of these locations varies from 0 to 65535.

    • Emma W on 2019-8-10 11:28:03

    Computer data storage, often called storage or memory, is a technology consisting of computer components and recording media that are used to retain digital data. It is a core function and fundamental component of computers.

    • VaVamin on 2019-8-10 11:34:16

    Thank you very very much for information about everythings. It is very useful for me as physist. Thanks a lot from your service , it is very useful for us.

    • Milian on 2019-8-10 11:40:34

    Super explanation!

    • Gia Keen on 2019-8-10 11:47:14

    Very well articulated material and good examples.

Leave a Reply

Your email address will not be published.

 
 
   
Rating: