This is the mail archive of the libc-alpha@sourceware.org mailing list for the glibc project.


Index Nav: [Date Index] [Subject Index] [Author Index] [Thread Index]
Message Nav: [Date Prev] [Date Next] [Thread Prev] [Thread Next]
Other format: [Raw text]

Re: [PATCH] powerpc: Add a POWER8-optimized version of powf()


Paul Clarke wrote:
On 05/27/2017 07:55 AM, Wilco Dijkstra wrote:

> I'm not easily able to test and validate performance on other platforms. 
> I'm not sure the maintainers of those other platforms would want me to, anyway.
>
> I do understand the motivation to encourage architecture-agnostic code in lieu of architecture-specific.
>
> How about making it fairly trivial to share the code, by dropping it in a common place,
> like /sysdeps/generic or /sysdeps/wordsize-64 or /sysdeps/ieee754?  Other arches 
> can then easily include it without having to copy it or include it from a foreign arch directory,  when and if they wish.
>
> This seems like an issue that would be commonly encountered.  Are there generally recommended practices?

Not as far as I know. The current math code is a mess due to all the different directories,
the odd wrappers, the headers that can bypass the wrappers and on top of that the ifuncs...
So we will need to simplify all this, starting with removing the wrappers.

>> As it happens Szabolcs wrote a prototype powf that is not only
>> more accurate but also 4x faster, all using generic code. With these gains, target
>> specific math functions will be obsolete...
>
> Is that forthcoming?

Yes - after they are published under a less restrictive license. In GLIBC we'll need to agree
on how to deal with the wrappers and establish a good place to add new math functions.

Wilco

    

Index Nav: [Date Index] [Subject Index] [Author Index] [Thread Index]
Message Nav: [Date Prev] [Date Next] [Thread Prev] [Thread Next]