this is what you are looking for:
http://www.intel.com/software/products/global/techtopics/mysql.pdf
according to intel- mysql ab provided all the performance data- much
more than 20% performance boost sometimes.
I'll be darned if their compiler flags work- maybe with 4.1 (apparently
that's what they used) but not with 4.0.18
yonah
Chris Nolan wrote:
> Victor Medina wrote:
>
>> Hi!
>> On Wed, 2004-03-24 at 09:51, Yonah Russ wrote:
>>
>>
>>> Hi,
>>> I'm trying to compile mysql 4.0.18 with icc 8.0 on RH AS 3u1. I'm
>>>
>>
>> ----8<
>> GUAO! nice!, let us know how faster it is with the Intel compiler, just
>> curious! =)
>>
>>
> An ad in one of the Linux magazines I leaf through on occassion showed
> some pretty noticable improvements (in the order of 20% in some
> cases), but I'm betting that these were crafted test cases, as we all
> know that MySQL's two "main" storage engines are extremely smart when
> it comes to using discs.
>
>>
>>
>>> fyi- there is a problem with the configure/libtool script when you
>>> don't compile -static and you use ipo... the compilation runs icc
>>> -shared to link the libraries but it needs the -ipo option as well.
>>>
>>>
>>
>> ----8< must probably no one here uses the Intel compiler since it is
>> paid =(
>>
>>
>>
>>> it dies with this error:
>>>
>>> IPO Warning: unresolved : rl_attempted_completion_function
>>> Referenced in ipo_icc5X7oE4.o
>>> IPO Warning: unresolved : rl_completion_entry_function
>>>
>>
>> ----8<
>>
>> Ncurses devel and the readline libriries must be installed for the
>> client to compile
>>
>> Best Regards!
>>
>>
>
