Random access memory: Encyclopedia - Random access memory

Random access memory

Random-access memory (commonly known by its acronym RAM) refers to data storage formats and equipment that allow the stored data to be accessed in any order -- that is, at random, not just in sequence. In contrast, other types of memory devices (such as magnetic tapes, disks, and drums) can access data on the storage medium only in a predetermined order due to constraints in their mechanical design.

Generally, RAM in a computer is considered main memory (or primary storage): the working area used for displaying and manipulating data. This type of RAM is usually in the form of integrated circuits (IC). These are commonly called memory sticks or RAM sticks because they are manufactured as small circuit boards with plastic packaging and are about the size of a stick of gum. Most personal computers have slots for adding and replacing memory chips.

RAM is typically erased when a computer is shut down, though some RAM chips maintain data indefinitely without electrical power. Technically, RAM devices are not limited to memory chips, and random-access memory as a storage format is not limited to use as working memory. In a broad sense, modern storage devices for long-term or secondary storage, including magnetic media and laser-readable CDs and DVDs, are forms of random-access memory.

Most RAM can be both written to and read from, so "RAM" is often used interchangeably with "read-write memory." In this sense, RAM is the opposite of read-only memory (ROM). Strictly speaking, however, "RAM" and "ROM" are not mutually exclusive designations because "RAM" refers only to the method of accessing stored data, not whether data can be written.

Random access memory - Overview

Computers use RAM to hold the program code and data during computation. A defining characteristic of RAM is that all memory locations can be accessed at almost the same speed. Most other technologies have inherent delays for reading a particular bit or byte.

Early main memory systems built from vacuum tubes behaved much like modern RAM, except the devices failed frequently. Core memory, which used wires attached to small ferrite electromagnetic cores, also had roughly equal access time (the term “core” is still used by some programmers to describe the RAM main memory of a computer). The basic concepts of tube and core memory are used in modern RAM implemented with integrated circuits.

Alternative primary storage mechanisms usually involved a non-uniform delay for memory access. Delay line memory used a sequence of sound wave pulses in mercury-filled tubes to hold a series of bits. Drum memory acted much like the modern hard disk, storing data magnetically in continuous circular bands. (See primary storage for a greater discussion of these alternatives and others.)

Many types of RAM are volatile, which means that unlike some other forms of computer storage such as disk storage and tape storage, they lose all data when the computer is powered down. Modern RAM generally stores a bit of data as either a charge in a capacitor, as in "dynamic RAM," or the state of a flip-flop, as in "static RAM".

Currently, there are several types of non-volatile RAM under development, which will preserve data while powered down. Technologies that are being used include carbon nanotube technology and magnetic tunnel effect.

In the summer of 2003, a 128KB Magnetic RAM chip was introduced, which was manufactured with 0.18µm technology. The core technology of MRAM is based on the magnetic tunnel effect. In June of 2004, Infineon Technologies unveiled a 16MB prototype based on 0.18µm technology once again.

As for carbon nanotube memory, a high-tech startup Nantero has built a functioning prototype 10GB array in 2004.

Software can "partition" a portion of a computer's RAM, allowing it to act as a much-faster hard drive, which is referred to as a RAM disk. Unless the memory used is non-volatile, a RAM disk does not maintain the stored data if the computer is shut down.

Some types of RAM can detect or correct random unintentional faults known as memory errors in the stored data (see RAM parity).

Random access memory - The memory wall

The term "memory wall," first officially coined in Hitting the Memory Wall: Implications of the Obvious, refers to the growing disparity between CPU and memory speed. From 1986 to 2000, CPU speed improved at an annual rate of 55% while memory speed only improved at 10%. Given these trends, it was expected that memory latency would become an overwhelming bottleneck in computer performance.

Currently, CPU speed improvements have slowed significantly which in part can be attributed to major physical barriers and in part to the fact that we have already hit the memory wall in some sense. Intel summarized these causes in their Platform 2015 documentation : "First of all, as chip geometries shrink and clock frequencies rise, the transistor leakage current increases, leading to excess power consumption and heat (more on power consumption below). Secondly, the advantages of higher clock speeds are in part negated by memory latency, since memory access times have not been able to keep pace with increasing clock frequencies. Third, for certain applications, traditional serial architectures are becoming less efficient as processors get faster (due to the so-called Von Neumann bottleneck), further undercutting any gains that frequency increases might otherwise buy. In addition, resistance-capacitance (RC) delays in signal transmission are growing as feature sizes shrink, imposing an additional bottleneck that frequency increases don’t address."

The resistance-capacitance (RC) delays in signal transmission were also noted in Clock Rate versus IPC: The End of the Road for Conventional Microarchitectures where a limit of 12.5% CPU performance improvement on average annually between 2000 and 2014 was projected. The data on Intel Processors clearly shows a slowdown in performance improvements in more recent processors.

Random access memory - Shadow RAM

Shadow RAM is the part of RAM with its contents copied from ROMs from where it will run much faster [1]. (ROM is in general slower than RAM.) The original ROM is disabled and the new location on the RAM is write protected. This process is called shadowing.

Random access memory - Types of RAM

Random access memory - Common

• Static RAM (SRAM)
• Non-Volatile RAM (NV-RAM)
• Dynamic RAM (DRAM)
  • Fast Page Mode DRAM
  • EDO RAM or Extended Data Out DRAM
  • XDR DRAM
  • SDRAM or Synchronous DRAM
    • DDR SDRAM or Double Data Rate Synchronous DRAM; now being replaced by DDR2
    • RDRAM or Rambus DRAM

Random access memory - Uncommon

• Dual-ported RAM
• Video RAM, a dual-port memory with one random access port and one sequential access port. This is becoming more popular as people need more and more video memory. See description under Dynamic RAM.
• WRAM
• MRAM
• feRAM
• ZRAM and TTRAM

Random access memory - RAM packaging

Semiconductor RAM is produced as integrated circuits (ICs). RAM ICs are often assembled into plug-in modules. Some standard module types are:

• Dual in-line Package (DIP)
• Single in-line memory module (SIMM)
• Dual in-line memory module (DIMM)
• Rambus modules are actually DIMMs, but are often referred to (by Rambus themselves and others) as RIMMs due to their proprietary slot.
• Small outline DIMM (SO-DIMM). Smaller version of the DIMM, used in laptops. Comes in versions with 72 (32 bit), 144 (64 bit), 200 (72 bit) pins
• Small outline RIMM (SO-RIMM)

Random access memory - RAM manufacturers

Major manufacturers of semiconductor RAM as of 2005:

Adapted from the Wikipedia article "Random access memory", under the G.N U Free Docmentation License. Please also see http://en.wikipedia.org/wiki