Dear Michael,
Thanks for updating the patch. I am afraid that my attention to
gfortran is somewhat limited at present. However, I see that
Dominique has verified your patch and that all is well.
The resulting speed up for nf.f90 is rather remarkable. What specific
feature of the fortran leads to a 30=>15s ?
Cheers
Paul
On Mon, Apr 11, 2011 at 6:04 PM, Michael Matz <m...@suse.de> wrote:
> On Sat, 9 Apr 2011, Paul Richard Thomas wrote:
>
>> I find that both nf.f90 and capacita.f90 segfault in runtime for any
>> stack size.
>
> Try this patch. I've verified that capacita and nf work with it and
> -march=native -ffast-math -funroll-loops -fstack-arrays -O3 . In fact all
> of polyhedron works for me on these flags. (I've set a ulimit -s of
> 512MB, but I don't know if such a large amount is required).
>
>
> Ciao,
> Michael.
>
> * trans-array.c (toplevel): Include gimple.h.
> (gfc_trans_allocate_array_storage): Check flag_stack_arrays,
> properly expand variable length arrays.
> (gfc_trans_auto_array_allocation): If flag_stack_arrays create
> variable length decls and associate them with their scope.
> * gfortran.h (gfc_option_t): Add flag_stack_arrays member.
> * options.c (gfc_init_options): Handle -fstack_arrays option.
> * lang.opt (fstack-arrays): Add option.
> * invoke.texi (Code Gen Options): Document it.
> * Make-lang.in (trans-array.o): Depend on GIMPLE_H.
>
> Index: trans-array.c
> ===================================================================
> *** trans-array.c (revision 172206)
> --- trans-array.c (working copy)
> *************** along with GCC; see the file COPYING3.
> *** 81,86 ****
> --- 81,87 ----
> #include "system.h"
> #include "coretypes.h"
> #include "tree.h"
> + #include "gimple.h"
> #include "diagnostic-core.h" /* For internal_error/fatal_error. */
> #include "flags.h"
> #include "gfortran.h"
> *************** gfc_trans_allocate_array_storage (stmtbl
> *** 630,647 ****
> {
> /* Allocate the temporary. */
> onstack = !dynamic && initial == NULL_TREE
> ! && gfc_can_put_var_on_stack (size);
>
> if (onstack)
> {
> /* Make a temporary variable to hold the data. */
> tmp = fold_build2_loc (input_location, MINUS_EXPR, TREE_TYPE (nelem),
> nelem, gfc_index_one_node);
> tmp = build_range_type (gfc_array_index_type, gfc_index_zero_node,
> tmp);
> tmp = build_array_type (gfc_get_element_type (TREE_TYPE (desc)),
> tmp);
> tmp = gfc_create_var (tmp, "A");
> tmp = gfc_build_addr_expr (NULL_TREE, tmp);
> gfc_conv_descriptor_data_set (pre, desc, tmp);
> }
> --- 631,654 ----
> {
> /* Allocate the temporary. */
> onstack = !dynamic && initial == NULL_TREE
> ! && (gfc_option.flag_stack_arrays
> ! || gfc_can_put_var_on_stack (size));
>
> if (onstack)
> {
> /* Make a temporary variable to hold the data. */
> tmp = fold_build2_loc (input_location, MINUS_EXPR, TREE_TYPE (nelem),
> nelem, gfc_index_one_node);
> + tmp = gfc_evaluate_now (tmp, pre);
> tmp = build_range_type (gfc_array_index_type, gfc_index_zero_node,
> tmp);
> tmp = build_array_type (gfc_get_element_type (TREE_TYPE (desc)),
> tmp);
> tmp = gfc_create_var (tmp, "A");
> + gfc_add_expr_to_block (pre,
> + fold_build1_loc (input_location,
> + DECL_EXPR, TREE_TYPE (tmp),
> + tmp));
> tmp = gfc_build_addr_expr (NULL_TREE, tmp);
> gfc_conv_descriptor_data_set (pre, desc, tmp);
> }
> *************** gfc_trans_auto_array_allocation (tree de
> *** 4744,4749 ****
> --- 4751,4758 ----
> tree tmp;
> tree size;
> tree offset;
> + tree space;
> + tree inittree;
> bool onstack;
>
> gcc_assert (!(sym->attr.pointer || sym->attr.allocatable));
> *************** gfc_trans_auto_array_allocation (tree de
> *** 4800,4814 ****
> return;
> }
>
> ! /* The size is the number of elements in the array, so multiply by the
> ! size of an element to get the total size. */
> ! tmp = TYPE_SIZE_UNIT (gfc_get_element_type (type));
> ! size = fold_build2_loc (input_location, MULT_EXPR, gfc_array_index_type,
> ! size, fold_convert (gfc_array_index_type, tmp));
>
> ! /* Allocate memory to hold the data. */
> ! tmp = gfc_call_malloc (&init, TREE_TYPE (decl), size);
> ! gfc_add_modify (&init, decl, tmp);
>
> /* Set offset of the array. */
> if (TREE_CODE (GFC_TYPE_ARRAY_OFFSET (type)) == VAR_DECL)
> --- 4809,4838 ----
> return;
> }
>
> ! if (gfc_option.flag_stack_arrays)
> ! {
> ! gcc_assert (TREE_CODE (TREE_TYPE (decl)) == POINTER_TYPE);
> ! space = build_decl (sym->declared_at.lb->location,
> ! VAR_DECL, create_tmp_var_name ("A"),
> ! TREE_TYPE (TREE_TYPE (decl)));
> ! gfc_trans_vla_type_sizes (sym, &init);
> ! }
> ! else
> ! {
> ! /* The size is the number of elements in the array, so multiply by the
> ! size of an element to get the total size. */
> ! tmp = TYPE_SIZE_UNIT (gfc_get_element_type (type));
> ! size = fold_build2_loc (input_location, MULT_EXPR,
> gfc_array_index_type,
> ! size, fold_convert (gfc_array_index_type, tmp));
>
> ! /* Allocate memory to hold the data. */
> ! tmp = gfc_call_malloc (&init, TREE_TYPE (decl), size);
> ! gfc_add_modify (&init, decl, tmp);
> !
> ! /* Free the temporary. */
> ! tmp = gfc_call_free (convert (pvoid_type_node, decl));
> ! space = NULL_TREE;
> ! }
>
> /* Set offset of the array. */
> if (TREE_CODE (GFC_TYPE_ARRAY_OFFSET (type)) == VAR_DECL)
> *************** gfc_trans_auto_array_allocation (tree de
> *** 4817,4826 ****
> /* Automatic arrays should not have initializers. */
> gcc_assert (!sym->value);
>
> ! /* Free the temporary. */
> ! tmp = gfc_call_free (convert (pvoid_type_node, decl));
>
> ! gfc_add_init_cleanup (block, gfc_finish_block (&init), tmp);
> }
>
>
> --- 4841,4866 ----
> /* Automatic arrays should not have initializers. */
> gcc_assert (!sym->value);
>
> ! inittree = gfc_finish_block (&init);
> !
> ! if (space)
> ! {
> ! tree addr;
> ! pushdecl (space);
>
> ! /* Don't create new scope, emit the DECL_EXPR in exactly the scope
> ! where also space is located. */
> ! gfc_init_block (&init);
> ! tmp = fold_build1_loc (input_location, DECL_EXPR,
> ! TREE_TYPE (space), space);
> ! gfc_add_expr_to_block (&init, tmp);
> ! addr = fold_build1_loc (sym->declared_at.lb->location,
> ! ADDR_EXPR, TREE_TYPE (decl), space);
> ! gfc_add_modify (&init, decl, addr);
> ! gfc_add_init_cleanup (block, gfc_finish_block (&init), NULL_TREE);
> ! tmp = NULL_TREE;
> ! }
> ! gfc_add_init_cleanup (block, inittree, tmp);
> }
>
>
> Index: Make-lang.in
> ===================================================================
> *** Make-lang.in (revision 172206)
> --- Make-lang.in (working copy)
> *************** fortran/trans-stmt.o: $(GFORTRAN_TRANS_D
> *** 353,359 ****
> fortran/trans-openmp.o: $(GFORTRAN_TRANS_DEPS)
> fortran/trans-io.o: $(GFORTRAN_TRANS_DEPS) gt-fortran-trans-io.h \
> fortran/ioparm.def
> ! fortran/trans-array.o: $(GFORTRAN_TRANS_DEPS)
> fortran/trans-intrinsic.o: $(GFORTRAN_TRANS_DEPS) fortran/mathbuiltins.def \
> gt-fortran-trans-intrinsic.h
> fortran/dependency.o: $(GFORTRAN_TRANS_DEPS) fortran/dependency.h
> --- 353,359 ----
> fortran/trans-openmp.o: $(GFORTRAN_TRANS_DEPS)
> fortran/trans-io.o: $(GFORTRAN_TRANS_DEPS) gt-fortran-trans-io.h \
> fortran/ioparm.def
> ! fortran/trans-array.o: $(GFORTRAN_TRANS_DEPS) $(GIMPLE_H)
> fortran/trans-intrinsic.o: $(GFORTRAN_TRANS_DEPS) fortran/mathbuiltins.def \
> gt-fortran-trans-intrinsic.h
> fortran/dependency.o: $(GFORTRAN_TRANS_DEPS) fortran/dependency.h
> Index: gfortran.h
> ===================================================================
> *** gfortran.h (revision 172206)
> --- gfortran.h (working copy)
> *************** typedef struct
> *** 2220,2225 ****
> --- 2220,2226 ----
> int flag_d_lines;
> int gfc_flag_openmp;
> int flag_sign_zero;
> + int flag_stack_arrays;
> int flag_module_private;
> int flag_recursive;
> int flag_init_local_zero;
> Index: lang.opt
> ===================================================================
> *** lang.opt (revision 172206)
> --- lang.opt (working copy)
> *************** fmax-stack-var-size=
> *** 454,459 ****
> --- 454,463 ----
> Fortran RejectNegative Joined UInteger
> -fmax-stack-var-size=<n> Size in bytes of the largest array that will
> be put on the stack
>
> + fstack-arrays
> + Fortran
> + Put all local arrays on stack.
> +
> fmodule-private
> Fortran
> Set default accessibility of module entities to PRIVATE.
> Index: invoke.texi
> ===================================================================
> *** invoke.texi (revision 172206)
> --- invoke.texi (working copy)
> *************** and warnings}.
> *** 167,172 ****
> --- 167,173 ----
> -fbounds-check -fcheck-array-temporaries -fmax-array-constructor =@var{n}
> @gol
> -fcheck=@var{<all|array-temps|bounds|do|mem|pointer|recursion>} @gol
> -fcoarray=@var{<none|single|lib>} -fmax-stack-var-size=@var{n} @gol
> + -fstack-arrays @gol
> -fpack-derived -frepack-arrays -fshort-enums -fexternal-blas @gol
> -fblas-matmul-limit=@var{n} -frecursive -finit-local-zero @gol
> -finit-integer=@var{n} -finit-real=@var{<zero|inf|-inf|nan|snan>} @gol
> *************** Future versions of GNU Fortran may impro
> *** 1361,1366 ****
> --- 1362,1374 ----
>
> The default value for @var{n} is 32768.
>
> + @item -fstack-arrays
> + @opindex @code{fstack-arrays}
> + Adding this option will make the fortran compiler put all local arrays,
> + even those of unknown size onto stack memory. If your program uses very
> + large local arrays it's possible that you'll have to extend your runtime
> + limits for stack memory on some operating systems.
> +
> @item -fpack-derived
> @opindex @code{fpack-derived}
> @cindex structure packing
> Index: options.c
> ===================================================================
> *** options.c (revision 172206)
> --- options.c (working copy)
> *************** gfc_init_options (unsigned int decoded_o
> *** 123,128 ****
> --- 123,129 ----
>
> /* Default value of flag_max_stack_var_size is set in gfc_post_options. */
> gfc_option.flag_max_stack_var_size = -2;
> + gfc_option.flag_stack_arrays = 0;
>
> gfc_option.flag_range_check = 1;
> gfc_option.flag_pack_derived = 0;
> *************** gfc_handle_option (size_t scode, const c
> *** 783,788 ****
> --- 784,793 ----
> gfc_option.flag_max_stack_var_size = value;
> break;
>
> + case OPT_fstack_arrays:
> + gfc_option.flag_stack_arrays = value;
> + break;
> +
> case OPT_fmodule_private:
> gfc_option.flag_module_private = value;
> break;
>
--
The knack of flying is learning how to throw yourself at the ground and miss.
--Hitchhikers Guide to the Galaxy
