Understanding Computer Memory: RAM and ROM Explained

Posted on Jan 19, 2025 in Computers

Item 4.3: Memory

Content:

  1. Memory
  2. Technical Specifications
  3. Types of Memories
  4. Random Access Memory
  5. Technological Characteristics
  6. Static RAM
  7. Dynamic RAM
  8. Types of Dynamic RAM
  9. Memory RAM Dynamic Classification as Physical Form
  10. Performance of Random Access Memory
  11. Read Only Memory

Memory

The term “memory” applies to any electronic component capable of storing data temporarily. There are two main categories of memories:

  • Internal memory that stores data temporarily while programs are running. Internal memory uses micro-conductors, i.e. fast, specialized electronic circuits. The internal memory corresponds to what we call random access memory (RAM).
  • Auxiliary memory (also called physical memory or external memory) that stores information in the long term, even after shutdown. The auxiliary memory corresponds to magnetic storage devices such as hard disks, optical storage devices such as CD-ROMs and DVD-ROMs, and read-only memories.

Technical Specifications

The main features of a memory are:

  • Capacity, which represents the global volume of information (in bits) that memory can store. Another way to express it is by indicating the number of cells and the number of bits in each cell. For example, 16Kx8 means it has 16k of addressable cells, each with 8 bits, or 16 Kbytes.
  • Latency is the delay between the time that happens when the memory device receives an address and the time when the first bit of data is available from the memory device. This delay is also known as access time, which corresponds to the time interval between the application read/write and data availability. Latency is usually measured in nanoseconds (ns) (a nanosecond is one billionth of a second (10-9 sec)). Latency measures the speed of RAM.
  • Cycle time, which represents the minimum time interval between two successive hits.

Consequently, the time required to access information in memory is equal to the time of the cycle latency.

  • Performance, which defines the amount of information exchanged per unit time, expressed in bits per second.
  • Non-volatility, which characterizes the ability of memory to store data when it no longer receives power.

The ideal memory has a large capacity with very narrow access times and cycle times, high performance, and is not volatile. Consequently, the time required to access information in memory is equal to the time of the cycle latency.

However, fast memories are also the most expensive. This is the reason why a computer uses different technologies that are interconnected and hierarchically organized.

9k =

The fastest memories are located in small quantities near the processor. The auxiliary memories, which are not as fast, are used to store information permanently.

The mission of all memory, whatever its kind, is to store information. In general, system memory is responsible for storing the data from the CPU (or Central Processing Unit).

Types of Memory

Random Access Memory

All RAM (Random Access Memory) has a number of common technological characteristics. For example, all operations can read and write, which distinguishes them from ROM-type memory, which are slower. Moreover, they are all random routing, i.e. all memory cells have the same access time, which distinguishes them from sequential access memory and direct access. Finally, all of them are volatile memories, which, as we saw, means that they hold the information until power is interrupted.

Random access memory, RAM, is usually called the main system memory, i.e. a space that can store data temporarily while a program is running.

The size of the RAM is measured in gigabytes (GB). The RAM is composed of a number of boxes or memory locations capable of storing data or an instruction. Each box contains 8 bits, i.e. a byte, so if the RAM is 1 MB, you can store 1,048,576 characters and have 1,048,576 memory cells. Each of the memory cells is identified with a number, which is known as a memory address. The aim is that the control unit cells can differentiate themselves from others.

The main memory capacity is given by the number of positions multiplied by the length of the same expressed in bits or bytes.