Hi Jakub,
On 6/8/20 5:30 PM, Jakub Jelinek wrote:
I really don't see what is special exactly on TREE_READONLY DECL_ARTIFICIAL
I have now split-off the missed-optimization task to a new
PR, PR95583, to be handled in a proper way instead of trying
to cook-up a hackish special-case version.
This patch now simply sets the force_output flag.
(a) As output_offload_tables() (i.e. LTO streamout)
comes very early, one could just set the force_output flag
in this file without further checks or omp-offload.c changes
(b) Alternatively, one check that it really works by using
gcc_assert (symtab_node::get (it));
in either or both files.
(c) or assuming that some optimization worked, one could use:
if (!symtab_node::get (it))
continue;
The patch does (c) as trimming it to (b) or (a) is trival.
All should give currently the same result; the assert checks
for this, the "if (...)" is future-optimizations proof, but
I fear that before adding passes before output_offload_tables()
it makes no difference. (→new PR).
(The omp_finish_file comes late enough, but as the LTO has been
written before, it does not help.)
OK? What about backporting to GCC 10?
Tobias
-----------------
Mentor Graphics (Deutschland) GmbH, Arnulfstraße 201, 80634 München / Germany
Registergericht München HRB 106955, Geschäftsführer: Thomas Heurung, Alexander
Walter
openmp: ensure variables in offload table are streamed out (PRs 94848 + 95551)
gcc/ChangeLog:
PR lto/94848
PR middle-end/95551
* omp-offload.c (add_decls_addresses_to_decl_constructor,
omp_finish_file): Skip removed items.
* lto-cgraph.c (output_offload_tables): Likewise; set force_output
to this node for variables and functions.
libgomp/ChangeLog:
PR lto/94848
PR middle-end/95551
* testsuite/libgomp.fortran/target-var.f90: New test.
gcc/lto-cgraph.c | 8 ++++++
gcc/omp-offload.c | 12 ++++++++-
libgomp/testsuite/libgomp.fortran/target-var.f90 | 32 ++++++++++++++++++++++++
3 files changed, 51 insertions(+), 1 deletion(-)
diff --git a/gcc/lto-cgraph.c b/gcc/lto-cgraph.c
index a671c671fa7..93a99f3465b 100644
--- a/gcc/lto-cgraph.c
+++ b/gcc/lto-cgraph.c
@@ -1069,6 +1069,10 @@ output_offload_tables (void)
for (unsigned i = 0; i < vec_safe_length (offload_funcs); i++)
{
+ symtab_node *node = symtab_node::get ((*offload_funcs)[i]);
+ if (!node)
+ continue;
+ node->force_output = true;
streamer_write_enum (ob->main_stream, LTO_symtab_tags,
LTO_symtab_last_tag, LTO_symtab_unavail_node);
lto_output_fn_decl_ref (ob->decl_state, ob->main_stream,
@@ -1077,6 +1081,10 @@ output_offload_tables (void)
for (unsigned i = 0; i < vec_safe_length (offload_vars); i++)
{
+ symtab_node *node = symtab_node::get ((*offload_vars)[i]);
+ if (!node)
+ continue;
+ node->force_output = true;
streamer_write_enum (ob->main_stream, LTO_symtab_tags,
LTO_symtab_last_tag, LTO_symtab_variable);
lto_output_var_decl_ref (ob->decl_state, ob->main_stream,
diff --git a/gcc/omp-offload.c b/gcc/omp-offload.c
index b2df91a5724..4e44cfc9d0a 100644
--- a/gcc/omp-offload.c
+++ b/gcc/omp-offload.c
@@ -125,6 +125,10 @@ add_decls_addresses_to_decl_constructor (vec<tree, va_gc> *v_decls,
#endif
&& lookup_attribute ("omp declare target link", DECL_ATTRIBUTES (it));
+ /* See also omp_finish_file and output_offload_tables in lto-cgraph.c. */
+ if (!symtab_node::get (it))
+ continue;
+
tree size = NULL_TREE;
if (is_var)
size = fold_convert (const_ptr_type_node, DECL_SIZE_UNIT (it));
@@ -341,7 +345,7 @@ omp_finish_file (void)
add_decls_addresses_to_decl_constructor (offload_vars, v_v);
tree vars_decl_type = build_array_type_nelts (pointer_sized_int_node,
- num_vars * 2);
+ vec_safe_length (v_v));
tree funcs_decl_type = build_array_type_nelts (pointer_sized_int_node,
num_funcs);
SET_TYPE_ALIGN (vars_decl_type, TYPE_ALIGN (pointer_sized_int_node));
@@ -376,11 +380,17 @@ omp_finish_file (void)
for (unsigned i = 0; i < num_funcs; i++)
{
tree it = (*offload_funcs)[i];
+ /* See also add_decls_addresses_to_decl_constructor
+ and output_offload_tables in lto-cgraph.c. */
+ if (!symtab_node::get (it))
+ continue;
targetm.record_offload_symbol (it);
}
for (unsigned i = 0; i < num_vars; i++)
{
tree it = (*offload_vars)[i];
+ if (!symtab_node::get (it))
+ continue;
#ifdef ACCEL_COMPILER
if (DECL_HAS_VALUE_EXPR_P (it)
&& lookup_attribute ("omp declare target link",
diff --git a/libgomp/testsuite/libgomp.fortran/target-var.f90 b/libgomp/testsuite/libgomp.fortran/target-var.f90
new file mode 100644
index 00000000000..5e5ccd47c96
--- /dev/null
+++ b/libgomp/testsuite/libgomp.fortran/target-var.f90
@@ -0,0 +1,32 @@
+! { dg-additional-options "-O3" }
+!
+! With -O3 the static local variable A.10 generated for
+! the array constructor [-2, -4, ..., -20] is optimized
+! away - which has to be handled in the offload_vars table.
+!
+program main
+ implicit none (type, external)
+ integer :: j
+ integer, allocatable :: A(:)
+
+ A = [(3*j, j=1, 10)]
+ call bar (A)
+ deallocate (A)
+contains
+ subroutine bar (array)
+ integer :: i
+ integer :: array(:)
+
+ !$omp target map(from:array)
+ !$acc parallel copyout(array)
+ array = [(-2*i, i = 1, size(array))]
+ !$omp do private(array)
+ !$acc loop gang private(array)
+ do i = 1, 10
+ array(i) = 9*i
+ end do
+ if (any (array /= [(-2*i, i = 1, 10)])) error stop 2
+ !$omp end target
+ !$acc end parallel
+ end subroutine bar
+end
