This is the mail archive of the
gcc@gcc.gnu.org
mailing list for the GCC project.
Re: cache misses in gcc 3.3
Tim Josling <tej@melbpc.org.au> writes:
> Gabriel Dos Reis wrote:
>>
>> Tim Josling <tej@melbpc.org.au> writes:
>>
>> | How about:
>> |
>> | Parsing/tree building: nnn.n
>> |
>> | If agreeable I will submit a patch in due course.
>>
>> I would prefer a separate entry for tree building.
>>
>> -- Gaby
>
> So would I - but there would be hundreds of thousands of calls out of the
> parse; to wrap these in timvar would be prohibitive.
Mm, no, I bet it wouldn't. We already have two calls to
timevar_push/pop for every token coming back from cpplib (TV_LEX and
TV_CPP). That hasn't been a problem.
On any quality operating system gettimeofday() is as fast as the
relevant group of deranged assembly hackers can possibly make it.
zw