what is main memory in computer

Primary Memory (Main Memory)

Data and instructions, on which computer is currently working, are held by one of the primary memory. However, it has limited capacity and volatile which means data is lost when power is switched off. It is generally made up of semiconductor device. Though these memories are not as fast as registers, CPU can find the data and instruction required to be processed reside in main memory. There are two subcategories of Primary memory: RAM and ROM.

Read Only Memory (ROM): It cannot normally be changed, is capable of holding onto its data even when the computer is switched off. This is used for BIOS programs. Though traditional ROMs donot support writing into them, some ROM chips (Flash ROM) can be reprogrammed electronically. Random Access Memory (RAM): It is also known as primary memory. It is the place where programs and data are temporarily stored and waiting to be executed by the CPU. RAM is volatile and loses its contents when the power is switched off.

Features of Primary Memory:

These are semiconductor memories.

It is known as main memory

Usually volatile memory.

Data is lost in case of power is switched off.

Faster than secondary memories.

A computer cannot run without primary memory.

Classification of RAM

RAM is basically divided into 2 types:

1. Static RAM

2. Dynamic RAM

Static RAM (SRAM). It stores bits using two-state logical circuits called flip-flops. These circuits are stable and will retain their states until there is power. The state can deliberately be changed by software. However, the contents of SRAM are lost if it loses power.

Dynamic RAM (DRAM). It stores data bits using minuscule electric charges. These charges leak away rapidly, and so they must be refreshed or rewritten constantly. Memory module has dedicated circuitry to do so automatically. Though for large quantities, dynamic RAM is much cheaper than static RAM, the need to constantly refresh the contents makes it slower than static RAM. However to cut cost, the main memory of a computer is always DRAM

DRAM physical formats. One of the most important components of the computer is the dynamic RAM. Overall system performance is critically determined by the amount of DRAM installed in a computer. Dynamic RAMs are made of silicon chips which are nowadays supplied in the form of memory modules and are grouped as memory chips mounted on small circuit boards. They plug into the system board in much the same way as an expansion card. Two forms of module are in common use:

SIMM (Single Inline Memory Module) has a data path of 32 bits (the card has 32 data lines).

DIMM (Double Inline Memory Module) has a data path of 64 bits (the card has 64 data lines).

Asynchronous DRAM. Asynchronous DRAM (ADRAM) is independent of the CPUs external clock. Asynchronous DRAM chips are created with codes which end in a numerical value that is related to the access time of the memory(often 1 10 of the actual value). The difference between the time when the information is requested from memory and the time when the data is returned, is essentially known as the access time of the DRAM. Common access times attributed to asynchronous DRAM were in the 40- to 120-nanosecond (ns) vicinity. A lower access time is obviously better for overall performance.

ADRAM is not synchronized to the frontside bus and this ensures that it often requires wait states to be inserted through the BIOS setup for a faster CPU to be able to use the same memory as a slower CPU. These wait states represent intervals when the CPU had to mark time and do nothing but waiting for the memory subsystem to become ready again for subsequent access. Common asynchronous DRAM technologies included Fast Page Mode (FPM), Extended Data Out (EDO), and Burst EDO (BEDO).

Synchronous DRAM. Synchronous DRAM (SDRAM) shares a common clock signal with the computers system-bus clock. This ecosystem is ensured by the common signal that all local-bus components use for each step that they perform. For this reason, SDRAM is tied to the speed of the FSB and hence the processor and eliminates the need to configure the CPU to wait for the memory to catch up. FSB is the short for Front Side Bus, which is also known as the Processor Bus, Memory Bus, or System Bus. FSB essentially connects the CPU (chipset) with the main memory and L2 cache.

SDRAM: Further Classification.

Single Data Rate SDRAM: With SDR SDRAM, for each data pin, 1 bit of data can be transmitted, for every time the system clock ticks. This limits the bit rate per pin of SDRAM to the corresponding numerical value of the clocks frequency.

Double data rate (DDR) SDRAM: It earns its name because it doubles the transfer rate of ordinary SDRAM; This is achived by doublepumping the data and transferring a bit per pin on both the rising and falling edges of the clock signal. This lets the system to obtain twice the transfer rate at the same FSB clock frequency.

DDR2 SDRAM: The 2 in DDR2 can be thought of as yet another multiplier of 2 in the SDRAM technology, which uses a lower peak voltage in order to keep power consumption down (1.8V vs. the 2.5V of DDR). Still like DDR, double-pumping DDR2, uses both sweeps of the clock signal for data transfer. Internally, DDR2 further splits each clock pulse in two which enables the RAM to double the number of operations it can perform per FSB clock cycle. DDR2 nominally produces four times the throughput that SDR is capable of producing, through enhancements in the electrical interface and buffers, as well as through adding off-chip drivers.

DDR3 SDRAM: This naming convention proved that the 2 in DDR2 was not meant to be a multiplier. Rather it was a revision mark of sorts for DDR2 was the second version of DDR, and thus DDR3 is the third version. DDR3 memory type was designed to be twice as fast as the DDR2 memory but operates with the same system clock speed. Similar to DDR2, DDR3 is required to lower power consumption to make up for higher frequencies. In fact, the peak voltage for DDR3 is only 1.5V.

what is main memory in computer