This is the mail archive of the
mailing list for the glibc project.
Re: [PATCH] Add math benchmark latency test
Siddhesh Poyarekar wrote:
> BTW, this will only work for functions that have the same first argument
> and return types. This is OK for now, but it might be something to fix
> in future. A comment to that effect in the code would be very useful
> because I'm pretty sure I'll forget about it in the next 15 minutes or
> so and Wilco will too, maybe later than that :)
I've added a comment. It would fail on say pointer + float but works fine
if the types support addition between them. The latency test doesn't work
for sincos (somehow the madd is left out), but I'll fix that when I add a
workload for it.