Quick, Quick, Slow: Fast And Slow Memory Now In One Device
Want a computer that is functional as soon as you hit the power button (no lag time)? Wish that those enormous server farms didn’t gobble quite as much energy? You’re in luck! Researchers have developed a new device that should enable both of these things. The trick? Combining two memory functions into a single device.
The computer you are using to read this blog uses two types of memory: volatile and nonvolatile. Volatile memory requires a constant source of power, but it’s also really fast. It’s what allows your laptop to operate quickly. Nonvolatile memory does not require a constant source of power (it’s what’s in your flash drive), but it’s also pretty sluggish. It’s where your computer saves stuff when it’s turned off.
Computer researchers from NC State have come up with a device that can perform both volatile and nonvolatile memory operations. It’s called a double floating-gate field effect transistor. Existing nonvolatile memory used in data storage devices utilizes a single floating gate, which stores charge in the floating gate to signify a 1 or 0 (i.e., one ‘bit’ of information). By using two floating gates, the device can store a bit in a nonvolatile mode, and/or it can store a bit in a fast, volatile mode – like the normal main memory on your computer. This is a big deal for at least a couple of reasons.
One: it allows “instant on” computing. In other words, the computer would be ready to go as soon as you hit the power button. The computer could start immediately because it wouldn’t have to retrieve start-up data from its hard drive – the data could be stored in its main memory.
Two: it could save a ton of power. Server farms use an enormous amount of energy, even when internet traffic is low, because server farms can’t power down parts of their operation without affecting their main memory. The double floating-gate transistor would allow portions of the server memory to be turned off during periods of low use without affecting performance.
The research will be published in the February issue of IEEE’s Computer. Now, a quick qualifier for you tech types: the new device does not have the potential to replace SRAM.
For everyone else, here’s an explanation from Daniel Schinke, who worked on the team to develop the new double floating-gate transistor: “There are two types of volatile memories: Static Random Access Memory (SRAM) and Dynamic Random Access Memory (DRAM). They are both implemented in a computer. SRAM is used in the cache memory of the computer (which is in very close proximity to the processor) whereas the DRAM is used in the main memory of the computer. Our device has potential to replace the DRAM, which allows the computer to start up instantly and to enable power proportional computing due to its unified volatile and nonvolatile memory operation capability, [but not the SRAM].”
The key here is that these transistors can save things one way or another.
