Hello, I just do the Coursera lectures about Deep Leanring by Andrew Ng, and want to implement what I learned in Julia (lecture is in Python), so I can check my understanding. So there is a small neural net, and it takes time, and I change the numerical type from Float64 to Float32 and get like 30%…

Massive performance penalty for Float16 compared to Float32

ChrisRackauckas November 3, 2017, 7:23pm 3

Don’t benchmark in the global scope. Put that in a function and run twice.

4 Likes

CSV Reading (rewrite in C?)

Topic		Replies	Views
Time it takes to multiply two floats Numerics float	2	418	August 18, 2022
Apples to apples comparison of A\b with Float64 and Float16 on A64FX Performance question , linearalgebra	12	753	May 2, 2022
Worse performance of LU-decomposition for Float32 than for Float64 Performance linearalgebra	7	436	November 5, 2020
Int numerical calculation speed slower than Float? Performance	12	1699	February 17, 2020
Performance of Float32 exponential Performance	4	1440	December 21, 2019