[3.1.1] Re: GCC performance regression - its memset!

[Mark Mitchell]

--On Monday, May 20, 2002 04:48:39 PM +0200 Jan Hubicka <jh@suse.cz> wrote:

>>
>> Hmm, an pasto.
>> In memcpy case I got it right, while in memset I broke it.  I am
>> attaching patch I am testing currently.  OK for mainline/branch assuming
>> it passes?
>>
>> COncerning the inlining, gcc inlines all memcpys with size smaller than
>> 64 bytes. Perhaps this should be extended to 128 bytes in case we are
>> still about 2 times as bad. This is partly due to lame implementation of
>> memset in glibc too :(
>
> Mark,
> Would this patch be OK for 3.1.1 branch?  It fixes serious
> misscompilation. Not really regression, since extra switch is needed, but
> that switch seems to be popular.

Which extra switch?  I couldn't see it in the code, but I can never
remember all the switches. :-)

If this patch has been applied on the mainline and no problems have been
reported, then it is OK for the branch.

Thanks,

--
Mark Mitchell                   mark@codesourcery.com
CodeSourcery, LLC               http://www.codesourcery.com