Main site  Forum  Search

Email contact  Register  Log in

Topic: Does using float vs double float elements effect training

Author	Message
ltrigero Joined: Sep 30, 2019 Posts: 19	Posted: Dec 8, 2019 12:08 AM    Post subject: Does using float vs double float elements effect training What's the difference between the two and are there circumstances where it would effect training?
jarek Joined: Oct 22, 2007 Posts: 1073	Posted: Dec 8, 2019 1:00 AM    Post subject: Double float is a higher precision, than a single float. But also potentially slower (only matters with large designs) and less tested (because rarely used). Double float elements could be useful in some special situations, for example with very high precision ADC converters (more than 24 bits). But in most cases single float is perfectly enough. I would stick with single float designs. And only use double float when really needed (they can be mixed).
ltrigero Joined: Sep 30, 2019 Posts: 19	Posted: Dec 8, 2019 2:02 AM    Post subject: Okay, and what about scalar and vector elements?
jarek Joined: Oct 22, 2007 Posts: 1073	Posted: Dec 8, 2019 2:09 AM    Post subject: Those are unrelated. Scalar has one value. Vector has many.