Re: Some regressions from the dataflow merge

2007-06-15 Thread Maxim Kuvyrkov
Seongbae Park (???, ???) wrote: ... I'm looking at it. It is either a scheduler problem, or some other problem downstream triggered by the scheduler. However, I'm having hard time adding fine-grained dbg_cnt to our scheduler - do you know who might be interested in adding insn level dbg_cnt in

Re: Some regressions from the dataflow merge

2007-06-14 Thread Seongbae Park (박성배, 朴成培)
On 6/14/07, Richard Guenther <[EMAIL PROTECTED]> wrote: On Wed, 13 Jun 2007, Kenneth Zadeck wrote: > Richard Guenther wrote: > > On Tue, 12 Jun 2007, Richard Guenther wrote: > > > > > >> On ia64 SPEC2000 I see fma3d and applu now miscompare. > >> > > > > On x86_64 186.wupwise ICEs with -O2 -ffas

Re: Some regressions from the dataflow merge

2007-06-14 Thread Richard Guenther
On Wed, 13 Jun 2007, Kenneth Zadeck wrote: > Richard Guenther wrote: > > On Tue, 12 Jun 2007, Richard Guenther wrote: > > > > > >> On ia64 SPEC2000 I see fma3d and applu now miscompare. > >> > > > > On x86_64 186.wupwise ICEs with -O2 -ffast-math and FDO: > > > > /gcc/spec/sb-haydn-fdo-64/

Re: Some regressions from the dataflow merge

2007-06-13 Thread Richard Guenther
On 6/13/07, Kenneth Zadeck <[EMAIL PROTECTED]> wrote: Richard Guenther wrote: > On Tue, 12 Jun 2007, Richard Guenther wrote: > > >> On ia64 SPEC2000 I see fma3d and applu now miscompare. >> > > On x86_64 186.wupwise ICEs with -O2 -ffast-math and FDO: > > /gcc/spec/sb-haydn-fdo-64/x86_64/install-2

Re: Some regressions from the dataflow merge

2007-06-13 Thread Kenneth Zadeck
Richard Guenther wrote: > On Tue, 12 Jun 2007, Richard Guenther wrote: > > >> On ia64 SPEC2000 I see fma3d and applu now miscompare. >> > > On x86_64 186.wupwise ICEs with -O2 -ffast-math and FDO: > > /gcc/spec/sb-haydn-fdo-64/x86_64/install-200706120559/bin/gfortran -c -o > zscal.o

Re: Some regressions from the dataflow merge

2007-06-12 Thread Kenneth Zadeck
Seongbae Park (???, ???) wrote: > On 6/12/07, Richard Guenther <[EMAIL PROTECTED]> wrote: >> On Tue, 12 Jun 2007, Richard Guenther wrote: >> >> > >> > On ia64 SPEC2000 I see fma3d and applu now miscompare. >> >> On x86_64 186.wupwise ICEs with -O2 -ffast-math and FDO: >> >> /gcc/spec/sb-haydn-fdo-6

Re: Some regressions from the dataflow merge

2007-06-12 Thread Seongbae Park (박성배, 朴成培)
On 6/12/07, Richard Guenther <[EMAIL PROTECTED]> wrote: On Tue, 12 Jun 2007, Richard Guenther wrote: > > On ia64 SPEC2000 I see fma3d and applu now miscompare. On x86_64 186.wupwise ICEs with -O2 -ffast-math and FDO: /gcc/spec/sb-haydn-fdo-64/x86_64/install-200706120559/bin/gfortran -c -o zsca

Re: Some regressions from the dataflow merge

2007-06-12 Thread Richard Guenther
On Tue, 12 Jun 2007, Richard Guenther wrote: > > On ia64 SPEC2000 I see fma3d and applu now miscompare. On x86_64 186.wupwise ICEs with -O2 -ffast-math and FDO: /gcc/spec/sb-haydn-fdo-64/x86_64/install-200706120559/bin/gfortran -c -o zscal.o-fprofile-use -O2 -ffast-math zscal.

RE: Some regressions from the dataflow merge

2007-06-12 Thread Dave Korn
On 12 June 2007 15:55, Kenneth Zadeck wrote: > Dave Korn wrote: >> On 12 June 2007 15:05, Kenneth Zadeck wrote: >>> Richard Guenther wrote: >>> On ia64 SPEC2000 I see fma3d and applu now miscompare, and we have on x86_64 some performance regressions with Botan (a collection of cryp

Re: Some regressions from the dataflow merge

2007-06-12 Thread Kenneth Zadeck
Dave Korn wrote: > On 12 June 2007 15:05, Kenneth Zadeck wrote: > > >> Richard Guenther wrote: >> >>> On ia64 SPEC2000 I see fma3d and applu now miscompare, and we have >>> on x86_64 some performance regressions with Botan (a collection of >>> cryptographic algorithms (see >>> http://www.su

Re: Some regressions from the dataflow merge

2007-06-12 Thread Richard Guenther
On Tue, 12 Jun 2007, Kenneth Zadeck wrote: > Richard Guenther wrote: > > On Tue, 12 Jun 2007, Kenneth Zadeck wrote: > > > > > >> Richard Guenther wrote: > >> > >>> On ia64 SPEC2000 I see fma3d and applu now miscompare, and we have > >>> on x86_64 some performance regressions with Botan (a

Re: Some regressions from the dataflow merge

2007-06-12 Thread Kenneth Zadeck
Richard Guenther wrote: > On Tue, 12 Jun 2007, Kenneth Zadeck wrote: > > >> Richard Guenther wrote: >> >>> On ia64 SPEC2000 I see fma3d and applu now miscompare, and we have >>> on x86_64 some performance regressions with Botan (a collection of >>> cryptographic algorithms (see >>> http://

RE: Some regressions from the dataflow merge

2007-06-12 Thread Dave Korn
On 12 June 2007 15:05, Kenneth Zadeck wrote: > Richard Guenther wrote: >> On ia64 SPEC2000 I see fma3d and applu now miscompare, and we have >> on x86_64 some performance regressions with Botan (a collection of >> cryptographic algorithms (see >> http://www.suse.de/~gcctest/c++bench/botan/)) - tho

Re: Some regressions from the dataflow merge

2007-06-12 Thread Richard Guenther
On Tue, 12 Jun 2007, Kenneth Zadeck wrote: > Richard Guenther wrote: > > On ia64 SPEC2000 I see fma3d and applu now miscompare, and we have > > on x86_64 some performance regressions with Botan (a collection of > > cryptographic algorithms (see > > http://www.suse.de/~gcctest/c++bench/botan/)) -

Re: Some regressions from the dataflow merge

2007-06-12 Thread Kenneth Zadeck
Richard Guenther wrote: > On ia64 SPEC2000 I see fma3d and applu now miscompare, and we have > on x86_64 some performance regressions with Botan (a collection of > cryptographic algorithms (see > http://www.suse.de/~gcctest/c++bench/botan/)) - those are reasonably > small enough to investigate, bu

Some regressions from the dataflow merge

2007-06-12 Thread Richard Guenther
On ia64 SPEC2000 I see fma3d and applu now miscompare, and we have on x86_64 some performance regressions with Botan (a collection of cryptographic algorithms (see http://www.suse.de/~gcctest/c++bench/botan/)) - those are reasonably small enough to investigate, but wait another day in case its ju