Hello world,
the attached patch fixes the PR by removing common function elimination
in FORALL statements.
In the course of fixing this PR, I had originally fixed the ICE only to
find that the transformation (where f is a function)
forall (i=1:2)
a(i) = f(i) + f(i)
end forall
to
forall (i=1:2)
tmp = f(i)
a(i) = tmp
end forall
did the Wrong Thing. Oh well...
Regression-tested. OK for tunk?
Thomas
2011-10-09 Thomas Koenig <[email protected]>
PR fortran/50564
* frontend-passes (forall_level): New variable.
(cfe_register_funcs): Don't register functions if we
are within a forall loop.
(optimize_namespace): Set forall_level to 0 before entry.
(gfc_code_walker): Increase/decrease forall_level.
2011-10-09 Thomas Koenig <[email protected]>
PR fortran/50564
* gfortran.dg/forall_15.f90: New test case.
Index: frontend-passes.c
===================================================================
--- frontend-passes.c (Revision 179709)
+++ frontend-passes.c (Arbeitskopie)
@@ -62,6 +62,10 @@ static gfc_code *inserted_block, **changed_stateme
gfc_namespace *current_ns;
+/* If we are within any forall loop. */
+
+static int forall_level;
+
/* Entry point - run all passes for a namespace. So far, only an
optimization pass is run. */
@@ -165,6 +169,12 @@ cfe_register_funcs (gfc_expr **e, int *walk_subtre
|| (*e)->ts.u.cl->length->expr_type != EXPR_CONSTANT))
return 0;
+ /* We don't do function elimination within FORALL statements, it can
+ lead to wrong-code in certain circumstances. */
+
+ if (forall_level > 0)
+ return 0;
+
/* If we don't know the shape at compile time, we create an allocatable
temporary variable to hold the intermediate result, but only if
allocation on assignment is active. */
@@ -493,6 +503,7 @@ optimize_namespace (gfc_namespace *ns)
{
current_ns = ns;
+ forall_level = 0;
gfc_code_walker (&ns->code, convert_do_while, dummy_expr_callback, NULL);
gfc_code_walker (&ns->code, cfe_code, cfe_expr_0, NULL);
@@ -1193,6 +1204,7 @@ gfc_code_walker (gfc_code **c, walk_code_fn_t code
WALK_SUBEXPR (fa->end);
WALK_SUBEXPR (fa->stride);
}
+ forall_level ++;
break;
}
@@ -1335,6 +1347,10 @@ gfc_code_walker (gfc_code **c, walk_code_fn_t code
WALK_SUBEXPR (b->expr2);
WALK_SUBCODE (b->next);
}
+
+ if (co->op == EXEC_FORALL || co->op == EXEC_DO_CONCURRENT)
+ forall_level --;
+
}
}
return 0;
! { dg-do run }
! { dg-options "-ffrontend-optimize -fdump-tree-original" }
! PR 50564 - this used to ICE with front end optimization.
! Original test case by Andrew Benson.
program test
implicit none
double precision, dimension(2) :: timeSteps, control
integer :: iTime
double precision :: ratio
double precision :: a
ratio = 0.7d0
control(1) = ratio**(dble(1)-0.5d0)-ratio**(dble(1)-1.5d0)
control(2) = ratio**(dble(2)-0.5d0)-ratio**(dble(2)-1.5d0)
forall(iTime=1:2)
timeSteps(iTime)=ratio**(dble(iTime)-0.5d0)-ratio**(dble(iTime)-1.5d0)
end forall
if (any(abs(timesteps - control) > 1d-10)) call abort
! Make sure we still do the front-end optimization after a forall
a = cos(ratio)*cos(ratio) + sin(ratio)*sin(ratio)
if (abs(a-1.d0) > 1d-10) call abort
end program test
! { dg-final { scan-tree-dump-times "__builtin_cos" 1 "original" } }
! { dg-final { scan-tree-dump-times "__builtin_sin" 1 "original" } }
! { dg-final { cleanup-tree-dump "original" } }
