Question regarding type `ee_f16`
JOE1994 opened this issue · comments
Hello, I noticed that there is no type definition provided for ee_f16
inside the project (although it is used to define type MATDAT
). core_portme.h
, which contains definitions for most of the ee_~
types doesn't contain definition for ee_f16
. Are benchmark users expected to provide their own implementation and definition for ee_f16
to run the benchmark with ee_f16
? Thank you 🤓
Lines 103 to 110 in 21d473a
Hi @JOE1994,
This is dead code as the floating-point matrix multiply was never activated in production. Given the fact that there is no standard C way of defining a 16-bit float, it would require, as you pointed out, a user-specific definition for that platform.
Thanks,
Peter