Computer Memory
Computer memory refers to the physical devices used to store data and instructions for processing in a computer. It comes in various forms such as RAM (random access memory) and ROM (read-only memory), and is essential for the functioning of a computer system. Memory allows for the temporary storage and retrieval of data and instructions during processing.
4 Key excerpts on "Computer Memory"
eBook - ePubEncyclopedia of Computer Science and Technology
Volume 14 - Very Large Data Base Systems to Zero-Memory and Markov Information Source
- Jack Belzer, Albert G. Holzman, Allen Kent(Authors)
- 2021(Publication Date)
- CRC Press(Publisher)
...VIRTUAL MEMORY SYSTEMS INTRODUCTION The main or primary memory of a computer system is the memory in which the instructions and data of a program must reside in order to be accessed by the processor. The maximum amount of main memory a processor is capable of addressing is referred to as its physical address space. A direct relationship exists between the cost of a system and the size of its physical address space. The larger it is, the greater the cost due to the increased number of bits and, thus, the increased amount of circuitry required for addressing. Because addresses, or components of addresses, are stored as part of instructions, larger address spaces can necessitate larger memory word sizes or result in multiple word instructions. It is a challenging problem to minimize the cost of the system and still provide a reasonable physical address space. Another truism related to memories is the faster the memory, the higher its cost. Systems have been designed having several different memories of varying size and speed, i.e., a memory hierarchy, since the earliest days of electronic computing. The minimal hierarchy consists of two levels, a relatively small amount of fast primary memory and a larger amount of slower secondary memory. Several different strategies have evolved which distribute instructions and data among the various memories in the hierarchy with the goal of keeping those instructions and data most likely to be referenced in the fastest memory. In recent years the term "virtual memory" has come to be associated with specific systems, those that are paged and/or segmented. Memory mappings of various sorts and for various reasons, however, are an integral part of most computer systems. Any system having an address mapping can be thought of as having virtual memory...
eBook - ePub- Rajesh Singh, Anita Gehlot, Rajesh Singh, Anita Gehlot(Authors)
- 2021(Publication Date)
- CRC Press(Publisher)
...62 A universal memory that never runs out of steam Urvashi Sharma 1,2,*, Sachin Mishra 2,*, Gulshan Kumar 1,3,*, Reji Thomas 1,4,* 1. Introduction Digital semiconductor memories are inevitable in computers and use electronic assembly for information storage and processing. The semiconductor memories are categorized as: (1) volatile memories (loss of data with the shutdown of power); (2) non-volatile memories (NVMs) (no loss of information with the shutdown of power). random-access memory (RAM) is volatile memories that support read and write of data multiple times; they can be further classified into Static random-access memory (SRAM) and dynamic random-access memory (DRAM) [ 1 – 3 ], respectively, used as cache memory and primary memory. The “cache memory” in the central processing unit (CPU), configured with six transistors (i.e. 2-cross coupled transistors and 4-pass transistors) is an SRAM having less power required for retention/write/re-write and excellent read-out [ 4 ]. The cross-coupled transistors are used to store memory bits in inverter pairs of complementary metal-oxide semiconductor (CMOS). The p-MOS configuration is being replaced with a 4-pass transistor structure of high impedance resistors. This reduces the storage of information with an increase in power dissipation. Synchronous DRAM (SDRAM) and mobile DRAM (MDRAM) come into the group of high-density volatile memories. In DRAM, the arrangement of 1-capacitor (used for storing) and 1-transistor form a cell used for storing one bit of information. The size of this single cell is 6F 2 (“F” is the smallest feature size) having read/write time ~10 ns/10 ns. The DRAM is generally termed as “primary memory” [ 4 ]. The capacitor is at logic “1” considered as charged while discharged state with logic “0”. These logic “1” and “0” designate the data storage on the capacitor. The inconsistent power requirement in refreshing the bits after every few milliseconds (ms) raises the complication in processors...
eBook - ePub- Jerry C. Whitaker(Author)
- 2018(Publication Date)
- CRC Press(Publisher)
...8 Memory Devices Shih-Lien Lu 8.1 Introduction 8.2 Memory Organization Memory Hierarchy • System Level Memory Organization • Memory Device Organization 8.3 Memory Device Types Read-Only Memory • Random Access Memory (RAM) • Special Memory Structures 8.4 Interfacing Memory Devices Accessing DRAMs • Refreshing the DRAM 8.5 Error Detection and Correction 8.1 Introduction Memory is an essential part of any computation system. It is used to store both the computation instructions and the data. Logically, memory can be viewed as a collection of sequential locations, each with a unique address as its label and capable of storing information. Accessing memory is accomplished by supplying the address of the desired data to the device. Memory devices can be categorized according to their functionality and fall into two major categories, read-only-memory (ROM), and write-and-read memory or random-access memory (RAM). There is also another subcategory of ROM: mostly read but sometimes write memory or flash ROM memory. Within the RAM category there are two types of memory devices differentiated by storage characteristics, static RAM (SRAM) and dynamic RAM (DRAM) respectively. DRAM devices need to be refreshed periodically to prevent the corruption of their contents due to charge leakage. SRAM devices, on the other hand, do not need to be refreshed. Both SRAM and DRAM are volatile memory devices, which means that their contents are lost if the power supply is removed from these devices. Nonvolatile memory, the opposite of volatile memory, retains its contents even when the supply power is turned off. All current ROM devices, including mostly read sometimes write devices are nonvolatile memories. Except for a very few special memories, these devices are all interfaced in a similar way. When an address is presented to a memory device, and sometimes after a control signal is strobed, the information stored at the specified address is retrieved after a certain delay...
eBook - ePubThe Cerebral Computer
An Introduction To the Computational Structure of the Human Brain
- Robert J. Baron(Author)
- 2013(Publication Date)
- Psychology Press(Publisher)
...3 INFORMATION STORAGE INTRODUCTION I will begin this chapter with descriptions of two types of computer storage systems, addressed and associative, and I will discuss the hardware required for each of them. Since all of the storage techniques devised by computer architects while designing modem computers have occurred naturally during the evolution of man, a study of computer storage systems will serve as a gentle introduction into the mechanisms of information storage in the human brain. I will then describe neural storage networks and their computational and control structures. I will defer until Chapter 6 a discussion of human memory since an understanding of information storage in general must precede an understanding of the relationship between information storage and memory. The appendix of this chapter presents the details of one neural network model for cortical storage. The model emphasizes the control structures and mechanisms needed for converting dynamic patterns into static patterns and vice versa. ADDRESSED COMPUTER STORAGE SYSTEMS It is approximately correct to think of a computer storage system as a collection of registers together with their control circuitry. An N-word storage system, for example, consists of N register, together with the circuitry necessary for distributing information to them during storage and gathering information from them during recall. Historically, each register together with its control circuitry has been called a memory location and I will continue to follow that custom here. Each register is connected to an internal output bus through a set of switches which are inside the register, and each register receives inputs from an internal input bus. Note that a correspondence is maintained between input bus wire and output bus wire throughout the system. Refer to Figure 3.1...
