[Bug tree-optimization/33447] New: Non-empty latch block prevents loop vectorization

[irar at il dot ibm dot com]

The following loop (from linpk.f90) contains a non-empty latch block before
tree optimizations:

Source code:
Line
               m = MOD(N,4)
323                IF ( m.NE.0 ) THEN
324                   DO i = 1 , m
325                      Dy(i) = Dy(i) + Da*Dx(i)
326                   ENDDO
327                   IF ( N.LT.4 ) RETURN
328                ENDIF
329                mp1 = m + 1
330                DO i = mp1 , N , 4
331                   Dy(i) = Dy(i) + Da*Dx(i)
332                   Dy(i+1) = Dy(i+1) + Da*Dx(i+1)
333                   Dy(i+2) = Dy(i+2) + Da*Dx(i+2)
334                   Dy(i+3) = Dy(i+3) + Da*Dx(i+3)
335                ENDDO 

The first SSA dump:

<bb 17>:
  ...

  if (countm1.32_8 == 0)
    goto <bb 19>;
  else
    goto <bb 18>;

<bb 18>:
  countm1.32_98 = countm1.32_8 + 4294967295;
  goto <bb 17>;

This is also related to PR 28643 and PR 33244. However, in these PRs some tree
optimization puts stmts/phi nodes in the latch block, while in the lnpck
example the latch block is non-empty to begin with.


-- 
           Summary: Non-empty latch block prevents loop vectorization
           Product: gcc
           Version: 4.3.0
            Status: UNCONFIRMED
          Keywords: missed-optimization
          Severity: enhancement
          Priority: P3
         Component: tree-optimization
        AssignedTo: unassigned at gcc dot gnu dot org
        ReportedBy: irar at il dot ibm dot com


http://gcc.gnu.org/bugzilla/show_bug.cgi?id=33447