Nice to meet you. I'm Ume Onigiri, and I've been full of things I don't understand since I joined the company.
This time, I wrote about the time when I first learned about FPGA.
When I first joined the company: "Well, what is FPGA?"
Senior: "It is a device that allows you to rewrite logic circuits and their connections by programming."
When I first heard that FPGAs could be programmed to rewrite circuits and connections, I had the following image.
The wiring moves and connects the placed logic elements.
But that is impossible, isn't it?
Then how can rewriting be possible?
To solve such a question, I investigated the principle of FPGA rewritability.
The rewritable parts of an FPGA are largely composed of logic elements (LE) and interconnections, as shown in the figure below.
The roles of LEs and interconnections are explained below.
The LE consists of a look-up table (LUT) and a flip-flop (FF).
The LUT has four inputs and one output and can be represented as a truth table as shown in the figure below.
The LUT table information is stored in SRAM. Therefore, by rewriting the table information in the SRAM, the LUT can be used as various types of logic.
The figure below shows an example in which the logic of a 4-input, 1-output AND circuit is written to the LUT.
The wiring connects multiple LE horizontally and vertically. The point of intersection of these wires is the point of intersection.
This part consists of a switch called a path transistor, which can transmit signals in any direction, up, down, left, or right.
This allows the LEs to be freely connected to each other.
It turns out that the LE and the wiring each work well together to create a rewritable device.
Once I understood the rewritable principle, I was a little embarrassed that I thought the wiring worked.
New Engineer's Blush Blog Articles