Memory Hierarchy And Uses of Storage Devices

Memory Hierarchy

Memory hierarchy can be defined as the structural organization of various kinds of memory units used in a computer system. The objective of placing memory units into a hierarchy is to locate them promptly according to their uses. Memory units are placed into the hierarchical system on the basis of their increasing capacity and speed. The memory hierarchy consists of different levels where each level is of higher speed and smaller size than its lower levels.

The memory hierarchy found on computers is as follows:

1. Registers
2. Level 1 (L1) cache
3. Level 2 (L2) cache
4. Main memory
5. Secondary memory

Registers: Register is a temporary memory present in CPU. It is used for storing data instructions while it is being processed by CPU. CPU contains registers like MAR, MBR, TR, etc. It is a local storage space on a CPU that holds data that is being processed. Registers generally occupy the top-most position in the hierarchy of the memory (simply memory hierarchy) because it provides high speed and fast access.

Generally, the amount or total numbers of data (they can hold) is measured in terms of bits. For example, the two most general terms that are used, 32-bit processor and 64-bit processor, generally refer to the size of the register on the processor.

Level 1 (L1) cache: L1 cache is the second highest performing unit in the memory hierarchy. Cache memory built into PC’s CPU is called level 1 cache. The cost per byte of a cache memory is much lower than the registers.

Level 2 (L2) cache: The cache memory built into the motherboard is called Level-2 (L2) cache.

Some have both L1 and L2 cache known as the L3 cache. L3  is normally found outside the CPU usually in Motherboard of High-End machines (Gaming, Servers etc.). Certain newer CPUs contain on-die L3 cache. The speed or performance of L1 is higher than L2 and L2 is higher than L3. But the size or the capacity of L1 is smaller than L2 is smaller than L3. We can say, the speed or performance of cache has an inverse relationship with size or capacity.

Typical Core I CPU contains

L1 cache 64kB per core

L2 cache 256kB per core

L3 cache 1MB to 8MB shared

The CPU retrieves data and information more quickly from cache memory than it does from RAM or disk.

Cache hit: The successful retrieval of requested data from the cache is known as a cache hit.

Cache miss: The failure to find requested data in the cache is known as cache miss.

Main memory: Random Access Memory (RAM) is considered to be the main memory of the computer. It is placed on the fourth place in the memory hierarchy. RAM is a high-speed memory that holds a copy of the OS, currently executing a program and other information being processed. It is called Random Access Memory because any of the location on a chip can be randomly used to store and retrieve data and instructions. It can be written to and read from at any time. The information stored in the RAM is temporary (volatile) because it depends on supply of electricity when the power is shut off the data is lost.

Secondary memory: It is also known as External memory/Storage memory/Auxiliary memory/Backup memory. Secondary memory is not directly accessible to CPU. They are non-volatile in nature. Unlike primary memory, secondary memory can have huge storage capacity. This memory basically supports the primary memory. Secondary storage is the storage device that is in non-volatile state (data is not erased after a power cut ), capable of storing a large volume of data for long-term purpose and staying outside the CPU and primary storage. It is used for storing data and instructions permanently. It is also used for carrying data from one computer to another. It is usually slower for read/write and cheaper.

Uses of storage devices

The devices which are capable of storing data in a computer are called storage devices.

The uses of primary storage devices are as follows:

1. It is used by the processor for direct accessibility.
2. It can be written to and read from at any time.
3. It allows efficient sharing of the memory space.
4. The CPU continuously reads instructions stored there and executes them as required.

The uses of secondary storage devices are as follows:

1. This memory basically supports the primary memory.
2. It is used for storing data and instructions permanently.
3. It is also used for carrying data from one computer to another

Reference

keyes, J. Financial Services Information Systems (Best Practices), Auerbach Publications; 2 Sub edition