This is the mail archive of the
gcc-patches@gcc.gnu.org
mailing list for the GCC project.
Re: New rematerialization sub-pass in LRA
- From: Evgeny Stupachenko <evstupac at gmail dot com>
- To: Sebastian Pop <sebpop at gmail dot com>
- Cc: Vladimir Makarov <vmakarov at redhat dot com>, GCC Patches <gcc-patches at gcc dot gnu dot org>
- Date: Mon, 13 Oct 2014 19:54:36 +0400
- Subject: Re: New rematerialization sub-pass in LRA
- Authentication-results: sourceware.org; auth=none
- References: <5437F4EC dot 2070809 at redhat dot com> <20141010223103 dot GA8587 at f1 dot c dot bardezibar dot internal>
I don't see significant performance changes from the patch (with and
without patch enabling ebx) on x86 in 32bits mode.
Thanks,
Evgeny
On Sat, Oct 11, 2014 at 2:31 AM, Sebastian Pop <sebpop@gmail.com> wrote:
> Vladimir Makarov wrote:
>> I've tested and benchmarked the sub-pass on x86-64 and ARM. The
>> sub-pass permits to generate a smaller code in average on both
>> architecture (although improvement no-significant), adds < 0.4%
>> additional compilation time in -O2 mode of release GCC (according user
>> time of compilation of 500K lines fortran program and valgrind lakey #
>> insns in combine.i compilation) and about 0.7% in -O0 mode. As the
>> performance result, the best I found is 1% SPECFP2000 improvement on
>> ARM Ecynos 5410 (973 vs 963) but for Intel Haswell the performance
>> results are practically the same (Haswell has a very good
>> sophisticated memory sub-system).
>
> On aarch64 I have seen some minor perf improvements to libpng compress and
> decompress. The patch does not change the perf for all other benchmarks that I
> have tested.
>
> Thanks,
> Sebastian