Much Ado About Memory

New semiconductor applications are ever changing and improving our lives, from new smartphones and wearables to healthcare, factory automation, and artificial intelligence. The humble memory chip working in the background plays a critical role in enabling these technologies. For example, that awesome picture you just took would be lost forever without memory. Your computer can’t perform the instructions you give it—like “open this document” or “add a column to my spreadsheet”—without memory’s help. And every time you hit “save,” the data you just created goes to long-term storage (memory). While these examples may be obvious, have you ever wondered how memory works? In this Tech Brief, we take a high-level look at the basics of this important technology.

Memory 101
While logic chips work as the “brains” of an electronic device, performing functions using mathematical operations, memory chips store data. The basic building block of a memory chip is a cell, a tiny circuit with a capacitor (which stores data as a charge) and one or more transistors (which activate data). The capacitor is either charged or discharged, corresponding to the two possible data values (“1” or “0”), where this smallest unit of data is known as a “bit”.

The cells are arranged in a row and have a bit line structure that connects into a memory “address” called a word line. The address provides a means of identifying a location for data storage, and the word line forms an electrical path allowing all the memory cells on that row to be activated at the same time for storage (“write”) or retrieval (“read”). Data access is initiated with electrical signals—a row address strobe (RAS) and a column address strobe (CAS)—that together pinpoint a cell’s location within an array. If a charge is stored in the selected cell’s capacitor, these signals cause the transistor to conduct, transferring the charge to the connected bit line, causing a slight voltage increase that reads as a “1”.

Memory classification
Memory technologies are often categorized by how data is stored (volatile or non-volatile) and accessed (random or sequential). In terms of function, there are two broad classes of memory: primary (main memory, or memory), which is the active type that works on data, and secondary (data storage), which provides long-term storage.

For memory, speed is critical because it holds the data currently being used and/or changed. Imagine your favorite video game pausing every time you make a move or missing a turn when your smartphone’s GPS app can’t reroute directions in time. Cache, a subset of main memory, has the highest speed requirement as it stores instructions awaiting execution. DRAM is the most common technology used for main memory because of its speed and ability to individually access the smallest unit of data, which are key requirements.

Read more here.