In computer architecture, the Memory Hierarchy separates computer storage into the hierarchy based response time. It is developed to organize the memory in such a way that it can minimize the access time.
The memory hierarchy affects the performance in computer architectural design, algorithm predictions, and low-level programming constructs the involving locality of reference.
We can say that the memory unit is the collection of storage units or devices together. It can store binary information in the forms of bits. The memory hierarchy is design into two parts which are given below:
1. External or Secondary Memory
There are several types of external memory that exists, such as magnetic disk, optical disk, magnetic tape, and peripheral storage devices. These devices are accessible by the processor through the I/O module.
2. Internal memory or primary memory
The main memory, cache memory, and CPU registers are existing in the primary or internal memory. This memory is directly accessible by the processor.
Characteristics of Memory Hierarchy
The capacity is the global volume information of the memory can store. If we move from top to bottom in the hierarchy, the access time increases.
- Access time
The access time is the time interval between the read /write request and the availability of the data. If we move from top to bottom in the hierarchy, the access time increases.
When the computer system was designed without memory hierarchy design, the speed gap increases between the CPU registers and main memory due to the vast difference in access time.
The result in lower performance of the system and thus, the improvement was required. This improvement was made in the form memory hierarchy design that’s why the performance of the computer system increases. The most significant ways to improve system performance is minimizing how far down the memory hierarchy has to go to manipulate the data.
- Cost per bit
If we move from bottom to top in the memory hierarchy, the cost per bit is increased. The internal memory is costlier then external memory in the computer system.
Registers in CPU
The processor register is quickly accessible location available to the computer’s central processing unit. The registers generally consist of the small amount of fast storage, although some registers have exact hardware functions and may be read-only or write-only.
The CPU cache is a hardware cache which is used by the Central Processing Unit of the computer to reduce the average cost to access data from main memory. The Cache is a smaller, faster memory, located closer to the processor core, which stores the copies of data from the frequently used primary memory location.
The Cache memory is also called the CPU memory. It is high – speed static Random Access Memory that the computer microprocessor can access more quickly as compared to regular Random Access Memory.
The Cache is the small-sized type of volatile computer memory which provides high-speed data access to the processor and stores frequently by using the computer programs, applications, and data. It is also the fastest memory in the computer and integrated on to the motherboard and directly embedded in the processor or main Random Access Memory.
The main memory in the computer system is Random Access Memory. This memory is also known as the RAM in short. It is the part of the computer system that stores operating system software, software application and other information for the Central Processing Unit. The CPU has fast and direct access when the user needed to perform the task.
The Ram is one of the fastest types of memory and can allow the data to be read and written. The main memory refers to the computer hardware integrated circuits which store information for the immediate use in the computer system. This memory is synonymous with the term “primary storage.”
The disk cache is a mechanism to improve the time taken to read from or write to the hard disk. It is included as the part of the hard disk. It can also be the specified portion of Random Access Memory. The disk cache is the cache memory which is used to speed up the process of storing and accessing the data from the host hard disk.
The magnetic storage or magnetic recording is the storage of data on the magnetized medium. It uses different patterns of magnetization in the magnet sable material to store the data. It is a form of non-volatile memory. The information is accessed by using one or more read/write heads.
It is the most common form of secondary storage in the computer system. This memory provides fast access and high storage capacities at a reasonable cost. The magnetic disk drives contain metal disks which are coated on both sides with the iron oxide recording material.
The magnetic tape is the medium of magnetic recording, made from the thin magnetizable coating on the long, narrow strip of plastic film. In 1928, it was developed in Germany. It is based on the magnetic wire recording. It is the type of physical storage media for different kinds of data. The magnetic tape is considered as an analog solution. It is the oldest technology for electronic data storage.
In the computer system, the optical disk is the recording technology. It is flat, a circular disk which can encode the binary data in the form of pits and lands on the special material. It is the computer storage disk that stores the data digitally and uses a laser beam to read and write the data.
The Optical disk is primarily used as the portable and secondary storage device. This disk can store more data than the previous generation of magnetic storage media. The compact disk, digital versatile or video disk and the Blue-ray disk are the most commonly used form of optical disks. These types of the disk are generally used for:
1. Distribute the software to customers.
2. Store a large amount of data in the form of music, images, and videos.
3. Transfer the data to different computer systems or devices.
4. Back up the data from the local machine.