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

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

[Joern Rennecke]

>   In message <Pine.GSO.3.96.970819004905.4653A-100000@drabble>you write:
>   > can old scheduler be the source of the problem?
> Could be -- I don't think gcc-2.7* scheduled instructions on the
> x86 machines at all.
> 
> So, one interesting test would be to run the benchmark with "-O2",
> then again with "-O2 -fno-schedule-insns -fno-schedule-insns2".
> 
> That would tell us if we need to focus on the scheduler or not.

And if you look for the best performance right now, I suggest to try
-O2 -fno-schedule-insns .  Scheduling after reload can't hurt register
allocation, and it might do some good.  OTOH, it can hurt when it
disables peepholes.  It's a bity we don't have any actual peephole
optimization pass - combine.c works before reload and is limited in the
number and kind of insns it can combine, and the peepholes used by final
don't allow re-iteration and are not designed to recognize insns sequences
with some unrelated insns in-between.

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: Hello, Contrib Back end

[Jeffrey A Law]

  In message <199708191618.MAA01052@maribor.pfnet.com>you write:
  > Hi all.
  > 
  > Thanks for creating this project, I think it's very important to merge
  > these efforts.  I'll contribute back end support for the 3-Com PalmPilot 
  > PDA, done by myself, Kresten Krab Thorup, Ian Goldberg and others, and
  > maintained by myself.  about 150k patches to gcc, small ones for binutils
  > and gdb.
Great!

Note we'll need copyright paperwork and possibly an assignment from
your employeer before we can integrate the work.  Similarly for
others that have contributed to the project.

We're trying to get the assignment/disclaimer paperwork up on the
web, so hopefully you'll be able to get things moving on that front
soon.

jeff

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

[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 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)