Skip to content

R
riscv-gcc-1
Commit 5d9c602d by Thomas Koenig
Options

re PR fortran/90539 (481.wrf slowdown by 25% on Intel Kaby with -Ofast… 

re PR fortran/90539 (481.wrf slowdown by 25% on Intel Kaby with -Ofast -march=native starting with r271377)

2019-06-02  Thomas Koenig  <tkoenig@gcc.gnu.org>

	PR fortran/90539
	* trans-expr.c (gfc_conv_subref_array_arg): If the size of the
	expression can be determined to be one, treat it as contiguous.
	Set likelyhood of presence of an actual argument according to
	PRED_FORTRAN_ABSENT_DUMMY and likelyhood of being contiguous
	according to PRED_FORTRAN_CONTIGUOUS.

2019-06-02  Thomas Koenig  <tkoenig@gcc.gnu.org>

	PR fortran/90539
	* predict.def (PRED_FORTRAN_CONTIGUOUS): New predictor.

2019-06-02  Thomas Koenig  <tkoenig@gcc.gnu.org>

	PR fortran/90539
	* gfortran.dg/internal_pack_24.f90: New test.

From-SVN: r271844
parent 5efdd6ee
Showing with 107 additions and 13 deletions
gcc/ChangeLog
2019-06-02 Thomas Koenig <tkoenig@gcc.gnu.org>
PR fortran/90539
* predict.def (PRED_FORTRAN_CONTIGUOUS): New predictor.
2019-06-01 Martin Sebor <msebor@redhat.com>
PR middle-end/90694
......
gcc/fortran/ChangeLog
2019-06-02 Thomas Koenig <tkoenig@gcc.gnu.org>
PR fortran/90539
* trans-expr.c (gfc_conv_subref_array_arg): If the size of the
expression can be determined to be one, treat it as contiguous.
Set likelyhood of presence of an actual argument according to
PRED_FORTRAN_ABSENT_DUMMY and likelyhood of being contiguous
according to PRED_FORTRAN_CONTIGUOUS.
2019-05-30 Thomas Koenig <tkoenig@gcc.gnu.org>
* gfc-internals.texi (Translating to GENERIC): New chapter.
* gfc-internals.texi (Translating to GENERIC): New chapter.
2019-05-30 Marek Polacek <polacek@redhat.com>
......
gcc/fortran/trans-expr.c
......@@ -4922,15 +4922,35 @@ class_array_fcn:
gfc_se cont_se, array_se;
stmtblock_t if_block, else_block;
tree if_stmt, else_stmt;
mpz_t size;
bool size_set;
cont_var = gfc_create_var (boolean_type_node, "contiguous");
/* cont_var = is_contiguous (expr); . */
gfc_init_se (&cont_se, parmse);
gfc_conv_is_contiguous_expr (&cont_se, expr);
gfc_add_block_to_block (&se->pre, &(&cont_se)->pre);
gfc_add_modify (&se->pre, cont_var, cont_se.expr);
gfc_add_block_to_block (&se->pre, &(&cont_se)->post);
/* If the size is known to be one at compile-time, set
cont_var to true unconditionally. This may look
inelegant, but we're only doing this during
optimization, so the statements will be optimized away,
and this saves complexity here. */
size_set = gfc_array_size (expr, &size);
if (size_set && mpz_cmp_ui (size, 1) == 0)
{
gfc_add_modify (&se->pre, cont_var,
build_one_cst (boolean_type_node));
}
else
{
/* cont_var = is_contiguous (expr); . */
gfc_init_se (&cont_se, parmse);
gfc_conv_is_contiguous_expr (&cont_se, expr);
gfc_add_block_to_block (&se->pre, &(&cont_se)->pre);
gfc_add_modify (&se->pre, cont_var, cont_se.expr);
gfc_add_block_to_block (&se->pre, &(&cont_se)->post);
}
if (size_set)
mpz_clear (size);
/* arrayse->expr = descriptor of a. */
gfc_init_se (&array_se, se);
......@@ -4953,7 +4973,9 @@ class_array_fcn:
/* And put the above into an if statement. */
pre_stmts = fold_build3_loc (input_location, COND_EXPR, void_type_node,
cont_var, if_stmt, else_stmt);
gfc_likely (cont_var,
PRED_FORTRAN_CONTIGUOUS),
if_stmt, else_stmt);
}
else
{
......@@ -4976,11 +4998,11 @@ class_array_fcn:
gfc_add_modify (&else_block, pointer, build_int_cst (type, 0));
else_stmt = gfc_finish_block (&else_block);
tmp = fold_build3_loc (input_location, COND_EXPR, void_type_node, present_var,
tmp = fold_build3_loc (input_location, COND_EXPR, void_type_node,
gfc_likely (present_var,
PRED_FORTRAN_ABSENT_DUMMY),
pre_stmts, else_stmt);
gfc_add_expr_to_block (&se->pre, tmp);
}
else
gfc_add_expr_to_block (&se->pre, pre_stmts);
......@@ -4995,9 +5017,16 @@ class_array_fcn:
tmp = fold_build2_loc (input_location, EQ_EXPR, boolean_type_node,
cont_var,
build_zero_cst (boolean_type_node));
tmp = gfc_unlikely (tmp, PRED_FORTRAN_CONTIGUOUS);
if (pass_optional)
post_cond = fold_build2_loc (input_location, TRUTH_ANDIF_EXPR,
boolean_type_node, present_var, tmp);
{
tree present_likely = gfc_likely (present_var,
PRED_FORTRAN_ABSENT_DUMMY);
post_cond = fold_build2_loc (input_location, TRUTH_ANDIF_EXPR,
boolean_type_node, present_likely,
tmp);
}
else
post_cond = tmp;
}
......
gcc/predict.def
......@@ -229,3 +229,10 @@ DEF_PREDICTOR (PRED_FORTRAN_ABSENT_DUMMY, "Fortran absent dummy", \
to be very likely. */
DEF_PREDICTOR (PRED_FORTRAN_LOOP_PREHEADER, "Fortran loop preheader", \
HITRATE (99), 0)
/* Fortran assumed size arrays can be non-contiguous, so they need
to be repacked. */
DEF_PREDICTOR (PRED_FORTRAN_CONTIGUOUS, "Fortran contiguous", \
HITRATE (75), 0)
gcc/testsuite/ChangeLog
2019-06-02 Thomas Koenig <tkoenig@gcc.gnu.org>
PR fortran/90539
* gfortran.dg/internal_pack_24.f90: New test.
2019-06-01 Iain Sandoe <iain@sandoe.co.uk>
PR target/90698
......
gcc/testsuite/gfortran.dg/internal_pack_24.f90 0 → 100644
! { dg-do run }
! { dg-additional-options "-O -fdump-tree-optimized" }
module y
implicit none
contains
subroutine foo(a,b,c,d,e,f)
real, dimension(1), intent(inout) :: a, b, c, d, e, f
if (any([a,b,c,d,e,f] /= [1,2,3,4,5,6])) stop 1
a = -a
b = -b
c = -c
d = -d
e = -e
f = -f
end subroutine foo
end module y
module x
use y
implicit none
contains
subroutine bar(a)
real, dimension(:) :: a
integer :: n1, n3, n5
n1 = 1
n3 = 3
n5 = 5
call foo(a(n1:n1), a(n1+1:n1+1), a(n3:n3), a(n3+1:n3+1), a(n5:n5), a(n5+1:n5+1))
end subroutine bar
end module x
program main
use x
real, dimension(6) :: a,b
b = [1,2,3,4,5,6]
a = b
call bar(a)
if (any(a /= -b)) stop 2
end program main
! { dg-final { scan-tree-dump-not "contiguous" "optimized" } }
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment