Re: Some Haifa scheduler bugs

Re: Some Haifa scheduler bugs

[Jeffrey A Law]

  In message <Pine.SOL.3.90.970819092828.291B-100000@starsky.informatik.rwth-aa
chen.de>you write:
  > I've run c-torture on the egcs snapshot, using the Haifa scheduler with
  > all flags turned on. My system is an i586-linux one. Here's a patch to fix
  > some of the failures.
Thanks.

Just some comments:

  * Get a copyright assignment + disclaimer signed and sent to
  the FSF as soon as possible.  Until that time we can't take any
  of your patches and include them without rewriting them first.

  * When submitting patches, send separate patches for bugs from
  random cleanups.  The cleanups are greatly appreciated, especially
  for haifa.

  * When submitting bugfix patches, please submit a testcase, or
  refer us to a c-torture testcase and the options needed to expose
  the bug.


Specific questions/comments:

In move_insn, is there some reason why you can't call reemit_notes
during the loop on SCHED_GROUP_P insns?

ie, does this work instead?  Seems cleaner than using another loop
if it works.

{
  rtx new_last = insn;

  while (SCHED_GROUP_P (insn))
    {
      rtx prev = PREV_INSN (insn);
      move_insn1 (insn, last);
      reemit_notes (insn, insn);
      insn = prev;
    }

  move_insn1 (insn, last);
  return reemit_notes (new_last, new_last);
}

[ Of course if you had referred us to a testcase, we could check
  this ourselves.... ]

Jeff

Re: egcs: A new compiler project to merge the existing GCC forks (fwd)

[Dave Love]

>>>>> "Jeffrey" == Jeffrey A Law <law@hurl.cygnus.com> writes:

 Jeffrey> Could be -- I don't think gcc-2.7* scheduled instructions on
 Jeffrey> the x86 machines at all.

FWIW, the last gcc2 snapshot I could build (with -m586 in) typically
seemed to gain about 20% on a 586 with single-precision Fortran code,
roughly consistent with numbers reported by proprietary offerings at
the time, though some with `pentium optimization' only seemed to
perform about as well as the gcc-2.7-based g77 (generating 486 code).

If people care about Fortran performance I'll eventually do some
realistic tests on a 586, but have no access to a 686; this isn't
necessarily trivial, though, and I'm more interested in the release of
a correct g77 0.5.21 at this stage.

Re: egcs: A new compiler project to merge the existing GCC forks

[Toon Moene]

>  I got a different result. I usedd -O6 for all. f2c + gcc
>  2.7.2.1 and f2c + egcs 970814 are the same. They got 43
>  seconds on my PentiumPro 150MHz OC to 166MHz running
>  Linux 2.0.30. For g77 0.5.21-19970811 in egcs 970814, it
>  was about 57 seconds. I am not sure if g77 uses the same
>  options as gcc does.

The highest g77 entry in the list (because nobody with an Alpha  
bothered to send anything in) is:

PentiumPro 200MHz/256K cache, Linux, g77 0.5.18+gcc 2.7.2 [*] .  
29.6 s  25Apr97
PentiumPro 200MHz/256K cache, Linux, g77 0.5.18+gcc 2.7.2 [^] .  
33.0 s  25Apr97
[*]  as [^], plus -fstrength-reduce -fthread-jumps -mno-ieee-fp
[^]  -O3 -malign-double -funroll-all-loops -fomit-frame-pointer
     -ffast-math

so 43 seconds on an (effectively 166 Mhz machine) seem rather low to me

Cheers,
Toon.

Re: egcs: A new compiler project to merge the existing GCC forks

[H.J. Lu]

> 
> >  I got a different result. I usedd -O6 for all. f2c + gcc
> >  2.7.2.1 and f2c + egcs 970814 are the same. They got 43
> >  seconds on my PentiumPro 150MHz OC to 166MHz running
> >  Linux 2.0.30. For g77 0.5.21-19970811 in egcs 970814, it
> >  was about 57 seconds. I am not sure if g77 uses the same
> >  options as gcc does.
> 
> The highest g77 entry in the list (because nobody with an Alpha  
> bothered to send anything in) is:
> 
> PentiumPro 200MHz/256K cache, Linux, g77 0.5.18+gcc 2.7.2 [*] .  
> 29.6 s  25Apr97
> PentiumPro 200MHz/256K cache, Linux, g77 0.5.18+gcc 2.7.2 [^] .  
> 33.0 s  25Apr97
> [*]  as [^], plus -fstrength-reduce -fthread-jumps -mno-ieee-fp
> [^]  -O3 -malign-double -funroll-all-loops -fomit-frame-pointer
>      -ffast-math
> 
> so 43 seconds on an (effectively 166 Mhz machine) seem rather low to me

With -O3 -malign-double -funroll-all-loops -fomit-frame-pointer
-ffast-math -fstrength-reduce -fthread-jumps -mno-ieee-fp, I got

35.25 s for egcs 970814 + f2c.
41.78 s for g77 in egcs 970814.

I think that is right in line. BTW, I got signal 11 when I added
-march=i686.


-- 
H.J. Lu (hjl@gnu.ai.mit.edu)

Re: egcs: A new compiler project to merge the existing GCC forks

[Dave Love]

Speaking as a g77 pentium-y person, I'd disregard these mdbnch results
for now.  I doubt detailed discussion of g77 and f2c options is
appropriate here.

[What does -O6 do, anyhow?]

Re: egcs: A new compiler project to merge the existing GCC forks

[H.J. Lu]

> 
> 
> I downloaded this a few days ago - compiles and runs without any
> problems on a PentiumPro Linux 2.0.30 (Redhat 4.2) system - but:
> 
> execution speed (floating point) of a test case (mdbench) compiled
> with f2c+gcc is about 10% slower than using gcc 2.7.2.1 - it is
> about the same or very slighly faster than g77 0.5.19.1 when using
> g77 0.5.21 - when using single precision both f2c+gcc and g77 are
> about 10-25% slower than their gcc 2.7.2.1/g77 0.5.19.1 counter-
> parts.
> 
> I had hoped that performance would improve rather than get worse -
> is it so hard to optimize for x86? - I am back right now to the old
> stuff, unless I get to hear a convincing reason why to switch.

Here is some good news. I used:

# gcc -O6 -o egcs.O6 mdbnch.c -lf2c -lm -march=i686

Now the runtime was reduced from 43 seconds to about 39.5 seconds.
FYI, the Pentium Pro (i686) switch is only available in egcs.
If you compile your libf2c.a in egcs with -march=i686 -O6, you
may get even more performance boost. Further more, we are working on
new x86 floating point performance enhancement in egcs. It should
be available soon.


-- 
H.J. Lu (hjl@gnu.ai.mit.edu)

Re: egcs: A new compiler project to merge the existing GCC forks

[H.J. Lu]

> 
> 
> I downloaded this a few days ago - compiles and runs without any
> problems on a PentiumPro Linux 2.0.30 (Redhat 4.2) system - but:
> 
> execution speed (floating point) of a test case (mdbench) compiled
> with f2c+gcc is about 10% slower than using gcc 2.7.2.1 - it is
> about the same or very slighly faster than g77 0.5.19.1 when using
> g77 0.5.21 - when using single precision both f2c+gcc and g77 are
> about 10-25% slower than their gcc 2.7.2.1/g77 0.5.19.1 counter-
> parts.
> 
> I had hoped that performance would improve rather than get worse -
> is it so hard to optimize for x86? - I am back right now to the old
> stuff, unless I get to hear a convincing reason why to switch.
> 

I got a different result. I usedd -O6 for all. f2c + gcc 2.7.2.1 and
f2c + egcs 970814 are the same. They got 43 seconds on my PentiumPro
150MHz OC to 166MHz running Linux 2.0.30. For g77 0.5.21-19970811 in
egcs 970814, it was about 57 seconds. I am not sure if g77 uses the
same options as gcc does.

BTW, do you know egcs 970814 comes with its own libf2c.a. Are you
sure both gcc 2.7.2.1 and egcs 970814 use the same libf2c.a?

I did:

# f2c -A mdbnch.f
# gcc-2.7.2.1  -O6 -c mdbnch.c
# gcc  -O6 -o 2.7.2.1.O6 mdbnch.o -lf2c -lm
# gcc  -O6 -o egcs.O6 mdbnch.c -lf2c -lm

So that the same libf2c.a from egcs 970814 is used.


-- 
H.J. Lu (hjl@gnu.ai.mit.edu)