This is the mail archive of the
gcc@gcc.gnu.org
mailing list for the GCC project.
Re: Speculative prefetching: report
- From: Andrew Pinski <pinskia at physics dot uc dot edu>
- To: Dale Johannesen <dalej at apple dot com>
- Cc: "gcc at gcc dot gnu dot org List" <gcc at gcc dot gnu dot org>, Zdenek Dvorak <rakdver at atrey dot karlin dot mff dot cuni dot cz>
- Date: Tue, 12 Oct 2004 15:31:56 -0400
- Subject: Re: Speculative prefetching: report
- References: <4C13D718-1C83-11D9-BA32-000A95D7CD40@apple.com>
On Oct 12, 2004, at 3:17 PM, Dale Johannesen wrote:
2. In the profile-generation phase, there is a huge code bloat
resutling from
instrumenting all the loads and stores. This badly stresses the rest
of the BE,
causing out-of-memory ICEs or unacceptably slow compile times (hours)
on
several SPECmarks. (With IMA to be sure.)
This sounds like a huge problem with any code but should be fixed
a different way than just disabling speculative prefetching because
we could run into this a different way. Maybe we should only
profile load/stores in loops.
3. The SPECmarks which did build got consistently worse results.
I did no deep analysis, but it appears to be much too aggressive about
prefetching; it will prefetch each store of an unrolled memset loop
individually,
for example I think it needs some concept of cache line size to be
useful.
This is most likely the same problem as PR 17950.
-- Pinski