Operand isolation

In electronic low power digital synchronous circuit design, operand isolation is a technique for minimizing the energy overhead associated with redundant operations by selectively blocking the propagation of switching activity through the circuit.[1] This technique isolates sections of the circuit (operation) from "seeing" changes on their inputs (operands) unless they are expected to respond to them. This is usually done using latches at the inputs of the circuit. The latches become transparent only when the result of the operation is going to be used. One can also use multiplexers or simple AND gates instead of latches.

Overhead

There is some area overhead associated with this technique since the circuit designer needs to add extra circuitry, i.e. latches, at the inputs. Also, if the latches are being added in a pipeline stage, they might change the critical path, and hence increase the cycle time. In cases where the overhead is not acceptable, one can think of clock gating as an alternative method of low power design.

gollark: > Using a laser is some pussy ass shitWhat would you prefer?
gollark: Especially in protest-type things.
gollark: Yes. It's quite common.
gollark: That sounds bad.
gollark: > you didnt realize reatailers use face mapping technology for years?Not sure about that, but I would definitely want to *minimize* the amount of cameras and/or spying in any case.

See also

References

This article is issued from Wikipedia. The text is licensed under Creative Commons - Attribution - Sharealike. Additional terms may apply for the media files.