[Bug tree-optimization/37021] New: Fortran Complex reduction / multiplication not vectorized

[Bug tree-optimization/37021] New: Fortran Complex reduction / multiplication not vectorized

[rguenth at gcc dot gnu dot org]

subroutine to_product_of(self,a,b,a1,a2)
  complex(kind=8) :: self (:)
  complex(kind=8), intent(in) :: a(:,:)
  complex(kind=8), intent(in) :: b(:)
  integer a1,a2
  self = ZERO
  do i = 1,a1
    do j = 1,a2
      self(i) = self(i) + a(i,j)*b(j)
    end do
  end do
end subroutine

There are numerous reasons this is not vectorized at the moment:
 1) aliasing doesn't tell apart the data of self, a and b
 2) the reduction is obfuscated by extra SSA_NAME copies from store-motion
    (after you fix 1)
 3) REALPART_EXPR < (*ptr)[i] > is not handled by data dependency analysis
 4) ... ?


-- 
           Summary: Fortran Complex reduction / multiplication not
                    vectorized
           Product: gcc
           Version: 4.4.0
            Status: UNCONFIRMED
          Keywords: missed-optimization, alias
          Severity: enhancement
          Priority: P3
         Component: tree-optimization
        AssignedTo: unassigned at gcc dot gnu dot org
        ReportedBy: rguenth at gcc dot gnu dot org


http://gcc.gnu.org/bugzilla/show_bug.cgi?id=37021

[Bug tree-optimization/37021] Fortran Complex reduction / multiplication not vectorized

[rguenth at gcc dot gnu dot org]

------- Comment #1 from rguenth at gcc dot gnu dot org  2008-08-04 17:58 -------
Patch for 1) http://gcc.gnu.org/ml/gcc-patches/2008-08/msg00221.html
Patch for 2) http://gcc.gnu.org/ml/gcc-patches/2008-08/msg00226.html

I didn't yet start on 3), so 4) is unknown yet (as is 5, 6, ... ;))


-- 


http://gcc.gnu.org/bugzilla/show_bug.cgi?id=37021

[Bug tree-optimization/37021] Fortran Complex reduction / multiplication not vectorized

[rguenth at gcc dot gnu dot org]

------- Comment #2 from rguenth at gcc dot gnu dot org  2008-08-19 15:29 -------
3) is because data-ref requires a constant step

  else if (!simple_iv (loop, stmt, poffset, &offset_iv, false))
    {
      if (dump_file && (dump_flags & TDF_DETAILS))
        fprintf (dump_file, "failed: evolution of offset is not affine.\n");
      return;

but the step is (<unnamed-signed:64>) ((<unnamed-unsigned:64>) stride.3_36 *
16)

as we are dealing with general incoming arrays which are arbitrary striped.
Fixing this requires for example versioning for a constant stride.


-- 


http://gcc.gnu.org/bugzilla/show_bug.cgi?id=37021

[Bug tree-optimization/37021] Fortran Complex reduction / multiplication not vectorized

[rguenth at gcc dot gnu dot org]

------- Comment #3 from rguenth at gcc dot gnu dot org  2009-01-21 15:43 -------
Mine.  I am working on adding versioning for non-constant strides.


-- 

rguenth at gcc dot gnu dot org changed:

           What    |Removed                     |Added
----------------------------------------------------------------------------
                 CC|                            |irar at il dot ibm dot com
         AssignedTo|unassigned at gcc dot gnu   |rguenth at gcc dot gnu dot
                   |dot org                     |org
             Status|UNCONFIRMED                 |ASSIGNED
     Ever Confirmed|0                           |1
   Last reconfirmed|0000-00-00 00:00:00         |2009-01-21 15:43:08
               date|                            |


http://gcc.gnu.org/bugzilla/show_bug.cgi?id=37021

[Bug tree-optimization/37021] Fortran Complex reduction / multiplication not vectorized

[rguenth at gcc dot gnu dot org]

------- Comment #4 from rguenth at gcc dot gnu dot org  2009-01-23 15:33 -------
The testcase should be

subroutine to_product_of(self,a,b,a1,a2)
  complex(kind=8) :: self (:)
  complex(kind=8), intent(in) :: a(:,:)
  complex(kind=8), intent(in) :: b(:)
  integer a1,a2
  do i = 1,a1
    do j = 1,a2
      self(i) = self(i) + a(j,i)*b(j)
    end do
  end do
end subroutine

to be meaningful - otherwise we are accessing a in non-continuous ways in the
inner loop which would prevent vectorization.

With the versioning for stride == 1 I get then

.L13:
        movupd  16(%rax), %xmm1
        movupd  (%rax), %xmm3
        incl    %ecx
        movupd  (%rdx), %xmm4
        addq    $32, %rax
        movapd  %xmm3, %xmm0
        unpckhpd        %xmm1, %xmm3
        unpcklpd        %xmm1, %xmm0
        movupd  16(%rdx), %xmm1
        movapd  %xmm4, %xmm2
        addq    $32, %rdx
        movapd  %xmm3, %xmm9
        cmpl    %ecx, %r8d
        unpcklpd        %xmm1, %xmm2
        unpckhpd        %xmm1, %xmm4
        movapd  %xmm4, %xmm1
        movapd  %xmm2, %xmm4
        mulpd   %xmm1, %xmm9
        mulpd   %xmm0, %xmm4
        mulpd   %xmm3, %xmm2
        mulpd   %xmm1, %xmm0
        subpd   %xmm9, %xmm4
        addpd   %xmm2, %xmm0
        addpd   %xmm4, %xmm6
        addpd   %xmm0, %xmm5
        ja      .L13
        haddpd  %xmm5, %xmm5
        cmpl    %r15d, %edi
        movl    -4(%rsp), %ecx
        haddpd  %xmm6, %xmm6
        addsd   %xmm5, %xmm8
        addsd   %xmm6, %xmm7
        jne     .L12
        jmp     .L14

for the innermost loop, followed by a tail loop (peel for niters).  This is
about 15% faster on AMD K10 than the non-vectorized loop (if you disable
the cost-model and make sure to have enough iterations in the inner loop
to pay back for the extra guarding conditions).


-- 


http://gcc.gnu.org/bugzilla/show_bug.cgi?id=37021

[Bug tree-optimization/37021] Fortran Complex reduction / multiplication not vectorized

[rguenth at gcc dot gnu dot org]

------- Comment #5 from rguenth at gcc dot gnu dot org  2009-01-23 15:36 -------
So,

 4) The vectorized version sucks because we have to use peeling for niters
    because we need to unroll the loop once and cannot apply SLP here.

Q1: does SLP work with reductions at all?
Q2: does SLP do pattern recognition?

First of all we would need to recognize a complex reduction as a single
vectorized reduction.  Second we need to vectorize the complex multiplication
with SLP, feeding the reduction with one resulting complex vector.


-- 


http://gcc.gnu.org/bugzilla/show_bug.cgi?id=37021

[Bug tree-optimization/37021] Fortran Complex reduction / multiplication not vectorized

[irar at il dot ibm dot com]

------- Comment #6 from irar at il dot ibm dot com  2009-01-25 09:12 -------
(In reply to comment #5)
> So,
>  4) The vectorized version sucks because we have to use peeling for niters
>     because we need to unroll the loop once and cannot apply SLP here.

What do you mean by "unroll the loop once"?

> Q1: does SLP work with reductions at all?

No. SLP currently originates from groups of strided stores.

> Q2: does SLP do pattern recognition?

Pattern recoginition is done before SLP, and SLP handles stmts that were marked
as a part of a pattern. There is no SLP specific pattern recoginition.

> First of all we would need to recognize a complex reduction as a single
> vectorized reduction.  Second we need to vectorize the complex multiplication
> with SLP, feeding the reduction with one resulting complex vector.


-- 


http://gcc.gnu.org/bugzilla/show_bug.cgi?id=37021

[Bug tree-optimization/37021] Fortran Complex reduction / multiplication not vectorized

[rguenther at suse dot de]

------- Comment #7 from rguenther at suse dot de  2009-01-25 11:04 -------
Subject: Re:  Fortran Complex reduction /
 multiplication not vectorized

On Sun, 25 Jan 2009, irar at il dot ibm dot com wrote:

> 
> 
> ------- Comment #6 from irar at il dot ibm dot com  2009-01-25 09:12 -------
> (In reply to comment #5)
> > So,
> >  4) The vectorized version sucks because we have to use peeling for niters
> >     because we need to unroll the loop once and cannot apply SLP here.
> 
> What do you mean by "unroll the loop once"?

The vectorization factor is two, so we need two copies of the loop body
(which means unrolling it once and creating an epilogue loop because
niter may be odd)

> > Q1: does SLP work with reductions at all?
> 
> No. SLP currently originates from groups of strided stores.

Ah, I see.  In this loop we have two reductions, so to apply SLP
we would need to see that we can use a group of reductions for SLP?

> > Q2: does SLP do pattern recognition?
> 
> Pattern recoginition is done before SLP, and SLP handles stmts that were marked
> as a part of a pattern. There is no SLP specific pattern recoginition.

Ok, but with a reduction it won't help me here.

Can a loop be vectorized with just pattern recognition?  Hm, if I
remember correctly we detect scalar patterns and then vectorize them.
We don't support detecting "vector patterns" from scalar code, correct?

Thanks,
Richard.


-- 


http://gcc.gnu.org/bugzilla/show_bug.cgi?id=37021

[Bug tree-optimization/37021] Fortran Complex reduction / multiplication not vectorized

[irar at il dot ibm dot com]

------- Comment #8 from irar at il dot ibm dot com  2009-01-25 12:17 -------
(In reply to comment #7)
> > > Q1: does SLP work with reductions at all?
> > 
> > No. SLP currently originates from groups of strided stores.
> Ah, I see.  In this loop we have two reductions, so to apply SLP
> we would need to see that we can use a group of reductions for SLP?

Yes, I think this will work.

> > > Q2: does SLP do pattern recognition?
> > 
> > Pattern recoginition is done before SLP, and SLP handles stmts that were marked
> > as a part of a pattern. There is no SLP specific pattern recoginition.
> Ok, but with a reduction it won't help me here.
> Can a loop be vectorized with just pattern recognition?  Hm, if I
> remember correctly we detect scalar patterns and then vectorize them.
> We don't support detecting "vector patterns" from scalar code, correct?

Yes, if I understand you correctly, we detect scalar patterns, but adding
vector pattern detection does not seem to be complicated.


-- 


http://gcc.gnu.org/bugzilla/show_bug.cgi?id=37021

[Bug tree-optimization/37021] Fortran Complex reduction / multiplication not vectorized

[dorit at gcc dot gnu dot org]

------- Comment #9 from dorit at gcc dot gnu dot org  2009-01-27 12:40 -------
(In reply to comment #4)
> The testcase should be
> subroutine to_product_of(self,a,b,a1,a2)
>   complex(kind=8) :: self (:)
>   complex(kind=8), intent(in) :: a(:,:)
>   complex(kind=8), intent(in) :: b(:)
>   integer a1,a2
>   do i = 1,a1
>     do j = 1,a2
>       self(i) = self(i) + a(j,i)*b(j)
>     end do
>   end do
> end subroutine
> to be meaningful - otherwise we are accessing a in non-continuous ways in the
> inner loop which would prevent vectorization.

this change from a(i,j) to a(j,i) is not required if we try to vectorize the
outer-loop, where the stride is 1. It's also a better way to vectorize the
reduction. A few limitations on the way though are:

1) somehow don't let gcc create guard code around the innermost loop to check
that it executes more than zero iterations. This creates a complicated control
flow structure within the outer-loop. For now you have to have  constant number
of iterations for the inner-loop because of that, or insert a statement like
"if (a2<=0) return;" before the loop...

2) use -fno-tree-sink cause otherwise it moves the loop iv increment to the
latch block and the vectorizer likes to have the latch block empty...

(see also PR33113 for related reference).


> With the versioning for stride == 1 I get then
> .L13:
>         movupd  16(%rax), %xmm1
>         movupd  (%rax), %xmm3
>         incl    %ecx
>         movupd  (%rdx), %xmm4
>         addq    $32, %rax
>         movapd  %xmm3, %xmm0
>         unpckhpd        %xmm1, %xmm3
>         unpcklpd        %xmm1, %xmm0
>         movupd  16(%rdx), %xmm1
>         movapd  %xmm4, %xmm2
>         addq    $32, %rdx
>         movapd  %xmm3, %xmm9
>         cmpl    %ecx, %r8d
>         unpcklpd        %xmm1, %xmm2
>         unpckhpd        %xmm1, %xmm4
>         movapd  %xmm4, %xmm1
>         movapd  %xmm2, %xmm4
>         mulpd   %xmm1, %xmm9
>         mulpd   %xmm0, %xmm4
>         mulpd   %xmm3, %xmm2
>         mulpd   %xmm1, %xmm0
>         subpd   %xmm9, %xmm4
>         addpd   %xmm2, %xmm0
>         addpd   %xmm4, %xmm6
>         addpd   %xmm0, %xmm5
>         ja      .L13
>         haddpd  %xmm5, %xmm5
>         cmpl    %r15d, %edi
>         movl    -4(%rsp), %ecx
>         haddpd  %xmm6, %xmm6
>         addsd   %xmm5, %xmm8
>         addsd   %xmm6, %xmm7
>         jne     .L12
>         jmp     .L14
> for the innermost loop, followed by a tail loop (peel for niters).  This is
> about 15% faster on AMD K10 than the non-vectorized loop (if you disable
> the cost-model and make sure to have enough iterations in the inner loop
> to pay back for the extra guarding conditions).


-- 


http://gcc.gnu.org/bugzilla/show_bug.cgi?id=37021