[Bug optimization/15036] New: [3.4 regression] Performance and code size regression compared to 3.3

[Bug optimization/15036] New: [3.4 regression] Performance and code size regression compared to 3.3

[martin at mpa-garching dot mpg dot de]

When compiling the following code:

template<typename T> class xcomplex
  {
  public:
    T re, im;

    xcomplex (const T &re_, const T &im_)
      : re(re_), im(im_) {}
    template<typename U> xcomplex (const xcomplex<U> &orig)
      : re(orig.re), im(orig.im) {}
    xcomplex operator* (const T &fact) const
      { return xcomplex (re*fact,im*fact); }
  };

void foo (xcomplex<double> *a, double *b, xcomplex<double> *c)
  {
  for (int m=0; m<1000; ++m)
    c[m]=a[m]*b[m];
  }


g++ 3.4 produces bigger (and slower) code than 3.3:

~/tmp>g++ -O2 -S -v perf.cc
Reading specs from
/afs/mpa/common/pdsoft/appl/gcc-3.3.2/lib/gcc-lib/i686-pc-linux-gnu/3.3.2/specs
Configured with: /scratch/gcc-3.3.2/configure
--prefix=/afs/mpa/common/pdsoft/appl/gcc-3.3.2 --enable-languages=c++
--disable-checking
Thread model: posix
gcc version 3.3.2
 /afs/mpa/common/pdsoft/appl/gcc-3.3.2/lib/gcc-lib/i686-pc-linux-gnu/3.3.2/cc1plus
-quiet -v -D__GNUC__=3 -D__GNUC_MINOR__=3 -D__GNUC_PATCHLEVEL__=2 -D_GNU_SOURCE
perf.cc -D__GNUG__=3 -quiet -dumpbase perf.cc -auxbase perf -O2 -version -o perf.s
GNU C++ version 3.3.2 (i686-pc-linux-gnu)
        compiled by GNU C version 3.3.2.
GGC heuristics: --param ggc-min-expand=63 --param ggc-min-heapsize=63318
ignoring nonexistent directory
"/afs/mpa/common/pdsoft/appl/gcc-3.3.2/i686-pc-linux-gnu/include"
#include "..." search starts here:
#include <...> search starts here:
 /afs/mpa/common/pdsoft/appl/gcc-3.3.2/include/c++/3.3.2
 /afs/mpa/common/pdsoft/appl/gcc-3.3.2/include/c++/3.3.2/i686-pc-linux-gnu
 /afs/mpa/common/pdsoft/appl/gcc-3.3.2/include/c++/3.3.2/backward
 /usr/local/include
 /afs/mpa/common/pdsoft/appl/gcc-3.3.2/include
 /afs/mpa/common/pdsoft/appl/gcc-3.3.2/lib/gcc-lib/i686-pc-linux-gnu/3.3.2/include
 /usr/include
End of search list.

~/tmp>cat perf.s
        .file   "perf.cc"
        .text
        .align 2
        .p2align 4,,15
.globl _Z3fooP8xcomplexIdEPdS1_
        .type   _Z3fooP8xcomplexIdEPdS1_, @function
_Z3fooP8xcomplexIdEPdS1_:
.LFB10:
        pushl   %ebp
.LCFI0:
        movl    %esp, %ebp
.LCFI1:
        pushl   %edi
.LCFI2:
        pushl   %esi
.LCFI3:
        xorl    %esi, %esi
        pushl   %ebx
.LCFI4:
        subl    $28, %esp
.LCFI5:
        movl    8(%ebp), %edi
        movl    16(%ebp), %ebx
        movl    12(%ebp), %ecx
        .p2align 4,,15
.L8:
        fldl    (%ecx)
        movl    %esi, %edx
        sall    $4, %edx
        leal    (%edx,%edi), %eax
        incl    %esi
        addl    $8, %ecx
        fldl    (%eax)
        cmpl    $999, %esi
        fmul    %st(1), %st
        fxch    %st(1)
        fmull   8(%eax)
        fxch    %st(1)
        fstpl   -40(%ebp)
        movl    -40(%ebp), %eax
        fstpl   -32(%ebp)
        movl    %eax, (%ebx,%edx)
        movl    -36(%ebp), %eax
        movl    %eax, 4(%ebx,%edx)
        movl    -32(%ebp), %eax
        movl    %eax, 8(%ebx,%edx)
        movl    -28(%ebp), %eax
        movl    %eax, 12(%ebx,%edx)
        jle     .L8
        addl    $28, %esp
        popl    %ebx
        popl    %esi
        popl    %edi
        popl    %ebp
        ret
.LFE10:
        .size   _Z3fooP8xcomplexIdEPdS1_, .-_Z3fooP8xcomplexIdEPdS1_
        .ident  "GCC: (GNU) 3.3.2"


~/tmp>g++ -O2 -S -v perf.cc
Reading specs from /afs/mpa/data/martin/ugcc34/lib/gcc/i686-pc-linux-gnu/3.4.0/specs
Configured with: /scratch/gcc34/configure --prefix=/afs/mpa/data/martin/ugcc34
--enable-languages=c++ --disable-checking
Thread model: posix
gcc version 3.4.0 20040418 (prerelease)
 /afs/mpa/data/martin/ugcc34/libexec/gcc/i686-pc-linux-gnu/3.4.0/cc1plus -quiet
-v -D_GNU_SOURCE perf.cc -quiet -dumpbase perf.cc -mtune=pentiumpro -auxbase
perf -O2 -version -o perf.s
ignoring nonexistent directory
"/afs/mpa/data/martin/ugcc34/lib/gcc/i686-pc-linux-gnu/3.4.0/../../../../i686-pc-linux-gnu/include"
#include "..." search starts here:
#include <...> search starts here:
 /afs/mpa/data/martin/ugcc34/lib/gcc/i686-pc-linux-gnu/3.4.0/../../../../include/c++/3.4.0
 /afs/mpa/data/martin/ugcc34/lib/gcc/i686-pc-linux-gnu/3.4.0/../../../../include/c++/3.4.0/i686-pc-linux-gnu
 /afs/mpa/data/martin/ugcc34/lib/gcc/i686-pc-linux-gnu/3.4.0/../../../../include/c++/3.4.0/backward
 /usr/local/include
 /afs/mpa/data/martin/ugcc34/include
 /afs/mpa/data/martin/ugcc34/lib/gcc/i686-pc-linux-gnu/3.4.0/include
 /usr/include
End of search list.
GNU C++ version 3.4.0 20040418 (prerelease) (i686-pc-linux-gnu)
        compiled by GNU C version 3.4.0 20040418 (prerelease).
GGC heuristics: --param ggc-min-expand=63 --param ggc-min-heapsize=63318


~/tmp>cat perf.s
        .file   "perf.cc"
        .text
        .align 2
        .p2align 4,,15
.globl _Z3fooP8xcomplexIdEPdS1_
        .type   _Z3fooP8xcomplexIdEPdS1_, @function
_Z3fooP8xcomplexIdEPdS1_:
.LFB5:
        pushl   %ebp
.LCFI0:
        movl    %esp, %ebp
.LCFI1:
        pushl   %edi
.LCFI2:
        pushl   %esi
.LCFI3:
        pushl   %ebx
.LCFI4:
        subl    $60, %esp
.LCFI5:
        movl    16(%ebp), %edi
        movl    $0, -60(%ebp)
        movl    12(%ebp), %esi
        .p2align 4,,15
.L7:
        fldl    (%esi)
        addl    $8, %esi
        movl    -60(%ebp), %edx
        incl    -60(%ebp)
        movl    8(%ebp), %ecx
        sall    $4, %edx
        cmpl    $999, -60(%ebp)
        leal    (%edx,%ecx), %eax
        fldl    (%eax)
        fmul    %st(1), %st
        fxch    %st(1)
        fmull   8(%eax)
        fxch    %st(1)
        fstpl   -56(%ebp)
        movl    -56(%ebp), %ebx
        movl    -52(%ebp), %ecx
        fstpl   -48(%ebp)
        movl    -48(%ebp), %eax
        movl    %ebx, -40(%ebp)
        movl    %ecx, -36(%ebp)
        movl    %eax, -32(%ebp)
        movl    -44(%ebp), %eax
        movl    %eax, -28(%ebp)
        movl    %ebx, (%edx,%edi)
        movl    %ecx, 4(%edx,%edi)
        movl    -32(%ebp), %eax
        movl    %eax, 8(%edx,%edi)
        movl    -28(%ebp), %eax
        movl    %eax, 12(%edx,%edi)
        jle     .L7
        addl    $60, %esp
        popl    %ebx
        popl    %esi
        popl    %edi
        popl    %ebp
        ret
.LFE5:
        .size   _Z3fooP8xcomplexIdEPdS1_, .-_Z3fooP8xcomplexIdEPdS1_
        .section        .note.GNU-stack,"",@progbits
        .ident  "GCC: (GNU) 3.4.0 20040418 (prerelease)"


The assembler generated by g++ 3.4 contains more movl statements inside the
loop.
This problem is also present on mainline.

-- 
           Summary: [3.4 regression] Performance and code size regression
                    compared to 3.3
           Product: gcc
           Version: 3.4.0
            Status: UNCONFIRMED
          Severity: normal
          Priority: P2
         Component: optimization
        AssignedTo: unassigned at gcc dot gnu dot org
        ReportedBy: martin at mpa-garching dot mpg dot de
                CC: gcc-bugs at gcc dot gnu dot org,martin at mpa-garching
                    dot mpg dot de
 GCC build triplet: i686-pc-linux-gnu
  GCC host triplet: i686-pc-linux-gnu
GCC target triplet: i686-pc-linux-gnu


http://gcc.gnu.org/bugzilla/show_bug.cgi?id=15036

[Bug optimization/15036] [3.4/3.5 regression] Performance and code size regression compared to 3.3

[pinskia at gcc dot gnu dot org]

------- Additional Comments From pinskia at gcc dot gnu dot org  2004-04-21 11:39 -------
Confirmed.  I suspect that multiplication operator is being created differently (but someone would need 
to look at the tree dumps).

-- 
           What    |Removed                     |Added
----------------------------------------------------------------------------
                 CC|                            |pinskia at gcc dot gnu dot
                   |                            |org
             Status|UNCONFIRMED                 |NEW
     Ever Confirmed|                            |1
           Keywords|                            |pessimizes-code
      Known to fail|                            |3.4.0 3.5.0
      Known to work|                            |3.3.3 tree-ssa
   Last reconfirmed|0000-00-00 00:00:00         |2004-04-21 11:39:42
               date|                            |
            Summary|[3.4 regression] Performance|[3.4/3.5 regression]
                   |and code size regression    |Performance and code size
                   |compared to 3.3             |regression compared to 3.3
   Target Milestone|---                         |3.4.1


http://gcc.gnu.org/bugzilla/show_bug.cgi?id=15036

[Bug rtl-optimization/15036] [3.4 regression] Performance and code size regression compared to 3.3

[mmitchel at gcc dot gnu dot org]

------- Additional Comments From mmitchel at gcc dot gnu dot org  2004-06-05 20:35 -------
Richard --

As the IA32 maintainer, would you take a look at this?

Thanks,

-- Mark

-- 
           What    |Removed                     |Added
----------------------------------------------------------------------------
                 CC|                            |rth at redhat dot com


http://gcc.gnu.org/bugzilla/show_bug.cgi?id=15036

[Bug rtl-optimization/15036] [3.4 regression] Performance and code size regression compared to 3.3

[mmitchel at gcc dot gnu dot org]

------- Additional Comments From mmitchel at gcc dot gnu dot org  2004-06-21 21:17 -------
Postponed until GCC 3.4.2.

-- 
           What    |Removed                     |Added
----------------------------------------------------------------------------
   Target Milestone|3.4.1                       |3.4.2


http://gcc.gnu.org/bugzilla/show_bug.cgi?id=15036

[Bug c++/15036] [3.4 regression] Performance and code size regression compared to 3.3

[pinskia at gcc dot gnu dot org]

------- Additional Comments From pinskia at gcc dot gnu dot org  2004-08-10 01:39 -------
In reality I think this is a front-end regression.

-- 
           What    |Removed                     |Added
----------------------------------------------------------------------------
          Component|rtl-optimization            |c++


http://gcc.gnu.org/bugzilla/show_bug.cgi?id=15036

[Bug c++/15036] [3.4 regression] Performance and code size regression compared to 3.3

[mmitchel at gcc dot gnu dot org]

------- Additional Comments From mmitchel at gcc dot gnu dot org  2004-08-29 18:51 -------
Postponed until GCC 3.4.3.

-- 
           What    |Removed                     |Added
----------------------------------------------------------------------------
   Target Milestone|3.4.2                       |3.4.3


http://gcc.gnu.org/bugzilla/show_bug.cgi?id=15036

[Bug c++/15036] [3.4 regression] Performance and code size regression compared to 3.3

[digitalmastrmind at hotmail dot com]

------- Additional Comments From digitalmastrmind at hotmail dot com  2004-09-16 18:40 -------
I was benchmarking STL containers out of curiosity and it turned out that 
inserting keys in a set/map is up to 70% slower with 3.4.x than it was with 
3.3.4...

Adding 1 milion keys to set<int> / hash_set<int> / map<int>:
1.10 / 0.68 / 1.11 bilion ticks with 3.2.2 (P233MMX / -O2 -march=pentium)
1.09 / 0.72 / 1.11 with 3.3.4
1.54 / 0.94 / 1.90 with 3.4.1
1.52 / 0.93 / 2.01 with 3.4.2

Sample loop used for measurement: (using rdtsc to estimate the tick count, 
accuracy is within 1-5%)

for(int a=0; a < 5000000; a+=5)
	intSet.insert(a);

While this is not realistic every day usage, it does appear to be 
representative of this issue and I am somewhat surprised to see it as being 
only a normal-normal issue.

-- 


http://gcc.gnu.org/bugzilla/show_bug.cgi?id=15036

[Bug c++/15036] [3.4 regression] Performance and code size regression compared to 3.3

[pcarlini at suse dot de]

------- Additional Comments From pcarlini at suse dot de  2004-09-16 18:47 -------
Daniel S., could you please try rebuilding gcc3.4.2 passing at configure time
--enable-libstdcxx-allocator=pool ? The timings should definitely change.
Thanks, Paolo.

-- 


http://gcc.gnu.org/bugzilla/show_bug.cgi?id=15036

[Bug c++/15036] [3.4 regression] Performance and code size regression compared to 3.3

[digitalmastrmind at hotmail dot com]

------- Additional Comments From digitalmastrmind at hotmail dot com  2004-09-17 23:23 -------
(In reply to comment #7)
Started the build this morning, tried my simplistic benchmark tonight with the 
new GCC build...

Thanks, this appears to have done a small miracle and made 3.4.2 5-10% faster 
than my 3.3.4 was... but it still lags ~5% behind 3.2.2 for hash_set though. 
(that 3.2.2 is from stock/up2date RH9 packages, the others are from sources 
with -O2 for GCC and -O2 -g for C/C++ libs.)

Does this mean that allocator pool used to be the default in 3.3.x and this 
behavior got dropped along the way to 3.4.x? (this certainly is what comparing 
the 3.3.4 c++configure.h file with the 3.4.2 version is hinting - I would be 
curious to read the reason(s).)

-- 


http://gcc.gnu.org/bugzilla/show_bug.cgi?id=15036

[Bug c++/15036] [3.4 regression] Performance and code size regression compared to 3.3

[pcarlini at suse dot de]

------- Additional Comments From pcarlini at suse dot de  2004-09-18 07:34 -------
> Does this mean that allocator pool used to be the default in 3.3.x and this 
> behavior got dropped along the way to 3.4.x?

Yes. To summarize a long story, allocators are a work in progress and we are
currently concentrating on yet another one, called mt_allocator. Unfortunately,
we haven't been able to forward port to a new framework in time for 3.4.0 the 
traditional pool allocator and, to be safe, we chosen the "trivial" new-based
allocator as the default. Then, for ABI stability we couldn't change that
default anymore for the next 3.4.x releases. However, for 3.4.2 and newer you
can always configure it yourself at build time to obtain a behavior very
similar to that of 3.3.x allocator. Thanks, Paolo.

-- 


http://gcc.gnu.org/bugzilla/show_bug.cgi?id=15036

[Bug c++/15036] [3.4 regression] Performance and code size regression compared to 3.3

[mmitchel at gcc dot gnu dot org]

------- Additional Comments From mmitchel at gcc dot gnu dot org  2004-11-01 00:45 -------
Postponed until GCC 3.4.4.

-- 
           What    |Removed                     |Added
----------------------------------------------------------------------------
   Target Milestone|3.4.3                       |3.4.4


http://gcc.gnu.org/bugzilla/show_bug.cgi?id=15036

[Bug c++/15036] [3.4 regression] Performance and code size regression compared to 3.3

[rth at gcc dot gnu dot org]

------- Additional Comments From rth at gcc dot gnu dot org  2005-03-31 21:53 -------
The code generated by gcc 4.0 is significantly improved:

.L2:
        fldl    -8(%ebx,%ecx,8)
        incl    %ecx
        fld     %st(0)
        fmull   (%edx)
        fxch    %st(1)
        fmull   8(%edx)
        fxch    %st(1)
        addl    $16, %edx
        fstpl   (%eax)
        fstpl   8(%eax)
        addl    $16, %eax
        cmpl    $1001, %ecx
        jne     .L2

I have no plans to address this for the 3.4 branch.

-- 
           What    |Removed                     |Added
----------------------------------------------------------------------------
             Status|NEW                         |RESOLVED
         Resolution|                            |WONTFIX
   Target Milestone|3.4.4                       |4.0.0


http://gcc.gnu.org/bugzilla/show_bug.cgi?id=15036