• 목록
• 답변
• 글쓰기
• 게시판 리스트 옵션
  • 수정
  • 삭제

Static random-access memory (static RAM or SRAM) is a sort of random-access memory (RAM) that uses latching circuitry (flip-flop) to retailer each bit. SRAM is volatile memory; data is misplaced when energy is removed. SRAM will hold its information completely in the presence of power, while data in DRAM decays in seconds and thus should be periodically refreshed. SRAM is quicker than DRAM but it's costlier in terms of silicon space and cost. Usually, SRAM is used for the cache and internal registers of a CPU while DRAM is used for a computer's predominant memory. Semiconductor bipolar SRAM was invented in 1963 by Robert Norman at Fairchild Semiconductor. Metal-oxide-semiconductor SRAM (MOS-SRAM) was invented in 1964 by John Schmidt at Fairchild Semiconductor. The primary machine was a 64-bit MOS p-channel SRAM. SRAM was the principle driver behind any new CMOS-based expertise fabrication process for the reason that 1960s, when CMOS was invented.

In 1964, Arnold Farber and Eugene Schlig, working for IBM, created a hard-wired memory cell, utilizing a transistor gate and tunnel diode latch. They replaced the latch with two transistors and two resistors, a configuration that turned known as the Farber-Schlig cell. That 12 months they submitted an invention disclosure, but it was initially rejected. In 1965, Benjamin Agusta and his team at IBM created a 16-bit silicon memory chip primarily based on the Farber-Schlig cell, with 84 transistors, 64 resistors, and four diodes. It was designed through the use of rubylith. Though it can be characterized as unstable memory, SRAM exhibits knowledge remanence. SRAM presents a easy knowledge entry model and doesn't require a refresh circuit. Efficiency and reliability are good and energy consumption is low when idle. Since SRAM requires extra transistors per bit to implement, it is less dense and more expensive than DRAM and in addition has a higher power consumption during read or write entry. The facility consumption of SRAM varies broadly relying on how often it's accessed.

Many classes of industrial and scientific subsystems, automotive electronics, and similar embedded programs, comprise SRAM which, on this context, could also be referred to as embedded SRAM (ESRAM). Some amount can be embedded in virtually all trendy appliances, toys, etc. that implement an digital user interface. SRAM in its dual-ported type is generally used for actual-time digital sign processing circuits. SRAM is utilized in private computers, workstations and peripheral equipment: CPU register files, inside CPU caches and GPU caches, exhausting disk buffers, and so on. LCD screens additionally might make use of SRAM to hold the picture displayed. SRAM was used for the main memory of many early personal computers such because the ZX80, TRS-eighty Mannequin 100, and VIC-20. Some early memory improvement solution cards within the late 1980s to early nineteen nineties used SRAM as a storage medium, which required a lithium battery to retain the contents of the SRAM. SRAM because of the ease of interfacing.

It is way simpler to work with than DRAM as there are not any refresh cycles and the deal with and information buses are often immediately accessible. In addition to buses and power connections, SRAM often requires only three controls: Chip Enable (CE), memory improvement solution Write Enable (WE) and Output Enable (OE). In synchronous SRAM, Clock (CLK) can also be included. Non-unstable SRAM (nvSRAM) has normal SRAM functionality, but they save the information when the ability provide is lost, ensuring preservation of crucial info. Pseudostatic RAM (PSRAM) is DRAM mixed with a self-refresh circuit. It seems externally as slower SRAM, albeit with a density and price benefit over true SRAM, and without the access complexity of DRAM. Asynchronous - independent of clock frequency; data in and knowledge out are managed by handle transition. Examples embody the ubiquitous 28-pin 8K × eight and 32K × eight chips (usually but not at all times named something alongside the traces of 6264 and 62C256 respectively), as well as comparable products as much as sixteen Mbit per chip.

Synchronous - all timings are initiated by the clock edges. Address, information in and other control indicators are associated with the clock indicators. Within the nineties, asynchronous SRAM was once employed for fast entry time. Asynchronous SRAM was used as fundamental memory for small cache-much less embedded processors used in everything from industrial electronics and measurement systems to onerous disks and networking tools, among many different applications. These days, synchronous SRAM (e.g. DDR SRAM) is fairly employed similarly to synchronous DRAM - DDR SDRAM memory is relatively used than asynchronous DRAM. Synchronous memory interface is much faster as access time might be significantly lowered by employing pipeline structure. Furthermore, as DRAM is way cheaper than SRAM, SRAM is usually replaced by DRAM, especially within the case when a large quantity of knowledge is required. SRAM memory is, nevertheless, a lot sooner for random (not block / burst) entry. Due to this fact, SRAM memory is primarily used for CPU cache, small on-chip memory, FIFOs or different small buffers.