This is the mail archive of the gcc-patches@gcc.gnu.org mailing list for the GCC 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: Vectorized _cpp_clean_line


On 08/12/2010 03:23 PM, Richard Henderson wrote:
> On 08/12/2010 03:07 PM, Andi Kleen wrote:
>> At least for sse 4.2 I'm not sure the table lookup
>> for alignment is worth it. The unaligned loads are quite
>> cheap on current micro architectures with sse 4.2 
>> and the page end test is also not that expensive.
> 
> Perhaps.  That's something else that will want testing, as
> it's all of a dozen instructions.

Alternately, we can check for page end only at the end
of the buffer.  Because obviously all the middle bits
of the buffer are present.

I've done nothing with the indirect branch yet, but here's
a version that bootstraps and checks ok for x86_64 (w/sse4.2).
It also bootstraps on i686 (w/sse2 but not sse4.2); I've just
started the test run for that though.


r~

Attachment: searchline-2
Description: Text document


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