public inbox for gcc-cvs@sourceware.org
help / color / mirror / Atom feed
* [gcc/devel/omp/gcc-11] Fortran: delinearize multi-dimensional array accesses
@ 2021-11-17 8:17 Frederik Harwath
0 siblings, 0 replies; only message in thread
From: Frederik Harwath @ 2021-11-17 8:17 UTC (permalink / raw)
To: gcc-cvs
https://gcc.gnu.org/g:e208eefbaa3f9f590171fce79c7366636770b348
commit e208eefbaa3f9f590171fce79c7366636770b348
Author: Sandra Loosemore <sandra@codesourcery.com>
Date: Tue Nov 16 16:09:51 2021 +0100
Fortran: delinearize multi-dimensional array accesses
The Fortran front end presently linearizes accesses to
multi-dimensional arrays by combining the indices for the various
dimensions into a series of explicit multiplies and adds with
refactoring to allow CSE of invariant parts of the computation.
Unfortunately this representation interferes with Graphite-based loop
optimizations. It is difficult to recover the original
multi-dimensional form of the access by the time loop optimizations
run because parts of it have already been optimized away or into a
form that is not easily recognizable, so it seems better to have the
Fortran front end produce delinearized accesses to begin with, a set
of nested ARRAY_REFs similar to the existing behavior of the C and C++
front ends. This is a long-standing problem that has previously been
discussed e.g. in PR 14741 and PR61000.
This patch is an initial implementation for explicit array accesses
only; it doesn't handle the accesses generated during scalarization of
whole-array or array-section operations, which follow a different code
path.
gcc/
* expr.c (get_inner_reference): Handle NOP_EXPR like
VIEW_CONVERT_EXPR.
gcc/fortran/
* lang.opt (-param=delinearize=): New.
* trans-array.c (get_class_array_vptr): New, split from...
(build_array_ref): ...here.
(get_array_lbound, get_array_ubound): New, split from...
(gfc_conv_array_ref): ...here. Additional code refactoring
plus support for delinearization of the array access.
gcc/testsuite/
* gfortran.dg/assumed_type_2.f90: Adjust patterns.
* gfortran.dg/goacc/kernels-loop-inner.f95: Likewise.
* gfortran.dg/graphite/block-3.f90: Remove xfails.
* gfortran.dg/graphite/block-4.f90: Likewise.
* gfortran.dg/inline_matmul_24.f90: Adjust patterns.
* gfortran.dg/no_arg_check_2.f90: Likewise.
* gfortran.dg/pr32921.f: Likewise.
* gfortran.dg/reassoc_4.f: Disable delinearization for this test.
Co-Authored-By: Tobias Burnus <tobias@codesourcery.com>
Diff:
---
gcc/expr.c | 1 +
gcc/fortran/lang.opt | 4 +
gcc/fortran/trans-array.c | 321 ++++++++++++++++-----
gcc/testsuite/gfortran.dg/assumed_type_2.f90 | 6 +-
.../gfortran.dg/goacc/kernels-loop-inner.f95 | 2 +-
gcc/testsuite/gfortran.dg/graphite/block-2.f | 9 +-
gcc/testsuite/gfortran.dg/graphite/block-3.f90 | 1 -
gcc/testsuite/gfortran.dg/graphite/block-4.f90 | 1 -
gcc/testsuite/gfortran.dg/graphite/id-9.f | 2 +-
gcc/testsuite/gfortran.dg/inline_matmul_24.f90 | 2 +-
gcc/testsuite/gfortran.dg/no_arg_check_2.f90 | 6 +-
gcc/testsuite/gfortran.dg/pr32921.f | 2 +-
gcc/testsuite/gfortran.dg/reassoc_4.f | 2 +-
13 files changed, 264 insertions(+), 95 deletions(-)
diff --git a/gcc/expr.c b/gcc/expr.c
index 21b7e96ed62..c7ee800c4d4 100644
--- a/gcc/expr.c
+++ b/gcc/expr.c
@@ -7539,6 +7539,7 @@ get_inner_reference (tree exp, poly_int64_pod *pbitsize,
break;
case VIEW_CONVERT_EXPR:
+ case NOP_EXPR:
break;
case MEM_REF:
diff --git a/gcc/fortran/lang.opt b/gcc/fortran/lang.opt
index dba333448c1..1548d56278a 100644
--- a/gcc/fortran/lang.opt
+++ b/gcc/fortran/lang.opt
@@ -521,6 +521,10 @@ fdefault-real-16
Fortran Var(flag_default_real_16)
Set the default real kind to an 16 byte wide type.
+-param=delinearize=
+Common Joined UInteger Var(flag_delinearize_aref) Init(1) IntegerRange(0,1) Param Optimization
+Delinearize array references.
+
fdollar-ok
Fortran Var(flag_dollar_ok)
Allow dollar signs in entity names.
diff --git a/gcc/fortran/trans-array.c b/gcc/fortran/trans-array.c
index b7d94992972..3eb9a177817 100644
--- a/gcc/fortran/trans-array.c
+++ b/gcc/fortran/trans-array.c
@@ -3747,11 +3747,9 @@ add_to_offset (tree *cst_offset, tree *offset, tree t)
}
}
-
static tree
-build_array_ref (tree desc, tree offset, tree decl, tree vptr)
+get_class_array_vptr (tree desc, tree vptr)
{
- tree tmp;
tree type;
tree cdesc;
@@ -3775,19 +3773,74 @@ build_array_ref (tree desc, tree offset, tree decl, tree vptr)
&& GFC_CLASS_TYPE_P (TYPE_CANONICAL (type)))
vptr = gfc_class_vptr_get (TREE_OPERAND (cdesc, 0));
}
+ return vptr;
+}
+static tree
+build_array_ref (tree desc, tree offset, tree decl, tree vptr)
+{
+ tree tmp;
+ vptr = get_class_array_vptr (desc, vptr);
tmp = gfc_conv_array_data (desc);
tmp = build_fold_indirect_ref_loc (input_location, tmp);
tmp = gfc_build_array_ref (tmp, offset, decl, vptr);
return tmp;
}
+/* Get the declared lower bound for rank N of array DECL which might
+ be either a bare array or a descriptor. This differs from
+ gfc_conv_array_lbound because it gets information for temporary array
+ objects from AR instead of the descriptor (they can differ). */
+
+static tree
+get_array_lbound (tree decl, int n, gfc_symbol *sym,
+ gfc_array_ref *ar, gfc_se *se)
+{
+ if (sym->attr.temporary)
+ {
+ gfc_se tmpse;
+ gfc_init_se (&tmpse, se);
+ gfc_conv_expr_type (&tmpse, ar->as->lower[n], gfc_array_index_type);
+ gfc_add_block_to_block (&se->pre, &tmpse.pre);
+ return tmpse.expr;
+ }
+ else
+ return gfc_conv_array_lbound (decl, n);
+}
+
+/* Similarly for the upper bound. */
+static tree
+get_array_ubound (tree decl, int n, gfc_symbol *sym,
+ gfc_array_ref *ar, gfc_se *se)
+{
+ if (sym->attr.temporary)
+ {
+ gfc_se tmpse;
+ gfc_init_se (&tmpse, se);
+ gfc_conv_expr_type (&tmpse, ar->as->upper[n], gfc_array_index_type);
+ gfc_add_block_to_block (&se->pre, &tmpse.pre);
+ return tmpse.expr;
+ }
+ else
+ return gfc_conv_array_ubound (decl, n);
+}
+
/* Build an array reference. se->expr already holds the array descriptor.
This should be either a variable, indirect variable reference or component
reference. For arrays which do not have a descriptor, se->expr will be
the data pointer.
- a(i, j, k) = base[offset + i * stride[0] + j * stride[1] + k * stride[2]]*/
+
+ There are two strategies here. In the traditional case, multidimensional
+ arrays are explicitly linearized into a one-dimensional array, with the
+ index computed as if by
+ a(i, j, k) = base[offset + i * stride[0] + j * stride[1] + k * stride[2]]
+
+ However, we can often get better code using the Graphite framework
+ and scalar evolutions in the middle end, which expects to see
+ multidimensional array accesses represented as nested ARRAY_REFs, similar
+ to what the C/C++ front ends produce. Delinearization is controlled
+ by flag_delinearize_aref. */
void
gfc_conv_array_ref (gfc_se * se, gfc_array_ref * ar, gfc_expr *expr,
@@ -3798,11 +3851,16 @@ gfc_conv_array_ref (gfc_se * se, gfc_array_ref * ar, gfc_expr *expr,
tree tmp;
tree stride;
tree decl = NULL_TREE;
+ tree cooked_decl = NULL_TREE;
+ tree vptr = se->class_vptr;
gfc_se indexse;
gfc_se tmpse;
gfc_symbol * sym = expr->symtree->n.sym;
char *var_name = NULL;
+ tree aref = NULL_TREE;
+ tree atype = NULL_TREE;
+ /* Handle coarrays. */
if (ar->dimen == 0)
{
gcc_assert (ar->codimen || sym->attr.select_rank_temporary
@@ -3862,15 +3920,160 @@ gfc_conv_array_ref (gfc_se * se, gfc_array_ref * ar, gfc_expr *expr,
}
}
+ /* Per comments above, DECL is not always a declaration. It may be
+ either a variable, indirect variable reference, or component
+ reference. It may have array or pointer type, or it may be a
+ descriptor with RECORD_TYPE. */
decl = se->expr;
if (IS_CLASS_ARRAY (sym) && sym->attr.dummy && ar->as->type != AS_DEFERRED)
decl = sym->backend_decl;
- cst_offset = offset = gfc_index_zero_node;
- add_to_offset (&cst_offset, &offset, gfc_conv_array_offset (decl));
+ /* A pointer array component can be detected from its field decl. Fix
+ the descriptor, mark the resulting variable decl and store it in
+ COOKED_DECL to pass to gfc_build_array_ref. */
+ if (get_CFI_desc (sym, expr, &cooked_decl, ar))
+ cooked_decl = build_fold_indirect_ref_loc (input_location, cooked_decl);
+ if (!expr->ts.deferred && !sym->attr.codimension
+ && is_pointer_array (se->expr))
+ {
+ if (TREE_CODE (se->expr) == COMPONENT_REF)
+ cooked_decl = se->expr;
+ else if (TREE_CODE (se->expr) == INDIRECT_REF)
+ cooked_decl = TREE_OPERAND (se->expr, 0);
+ else
+ cooked_decl = se->expr;
+ }
+ else if (expr->ts.deferred
+ || (sym->ts.type == BT_CHARACTER
+ && sym->attr.select_type_temporary))
+ {
+ if (GFC_DESCRIPTOR_TYPE_P (TREE_TYPE (se->expr)))
+ {
+ cooked_decl = se->expr;
+ if (TREE_CODE (cooked_decl) == INDIRECT_REF)
+ cooked_decl = TREE_OPERAND (cooked_decl, 0);
+ }
+ else
+ cooked_decl = sym->backend_decl;
+ }
+ else if (sym->ts.type == BT_CLASS)
+ {
+ if (UNLIMITED_POLY (sym))
+ {
+ gfc_expr *class_expr = gfc_find_and_cut_at_last_class_ref (expr);
+ gfc_init_se (&tmpse, NULL);
+ gfc_conv_expr (&tmpse, class_expr);
+ if (!se->class_vptr)
+ vptr = gfc_class_vptr_get (tmpse.expr);
+ gfc_free_expr (class_expr);
+ cooked_decl = tmpse.expr;
+ }
+ else
+ cooked_decl = NULL_TREE;
+ }
+
+ /* Find the base of the array; this normally has ARRAY_TYPE. */
+ tree base = build_fold_indirect_ref_loc (input_location,
+ gfc_conv_array_data (se->expr));
+ tree type = TREE_TYPE (base);
- /* Calculate the offsets from all the dimensions. Make sure to associate
- the final offset so that we form a chain of loop invariant summands. */
+ /* Handle special cases, copied from gfc_build_array_ref. After we get
+ through this, we know TYPE definitely is an ARRAY_TYPE. */
+ if (GFC_ARRAY_TYPE_P (type) && GFC_TYPE_ARRAY_RANK (type) == 0)
+ {
+ gcc_assert (GFC_TYPE_ARRAY_CORANK (type) > 0);
+ se->expr = fold_convert (TYPE_MAIN_VARIANT (type), base);
+ return;
+ }
+ if (TREE_CODE (type) != ARRAY_TYPE)
+ {
+ gcc_assert (cooked_decl == NULL_TREE);
+ se->expr = base;
+ return;
+ }
+
+ /* Check for cases where we cannot delinearize. */
+
+ bool delinearize = flag_delinearize_aref;
+
+ /* There is no point in trying to delinearize 1-dimensional arrays. */
+ if (ar->dimen == 1)
+ delinearize = false;
+
+ if (delinearize
+ && (GFC_DESCRIPTOR_TYPE_P (TREE_TYPE (se->expr))
+ || (DECL_P (se->expr)
+ && DECL_LANG_SPECIFIC (se->expr)
+ && GFC_DECL_SAVED_DESCRIPTOR (se->expr))))
+ {
+ /* Descriptor arrays that may not be contiguous cannot
+ be delinearized without using the stride in the descriptor,
+ which generally involves introducing a division operation.
+ That's unlikely to produce optimal code, so avoid doing it. */
+ tree desc = se->expr;
+ if (!GFC_DESCRIPTOR_TYPE_P (TREE_TYPE (se->expr)))
+ desc = GFC_DECL_SAVED_DESCRIPTOR (se->expr);
+ tree tmptype = TREE_TYPE (desc);
+ if (POINTER_TYPE_P (tmptype))
+ tmptype = TREE_TYPE (tmptype);
+ enum gfc_array_kind akind = GFC_TYPE_ARRAY_AKIND (tmptype);
+ if (akind != GFC_ARRAY_ASSUMED_SHAPE_CONT
+ && akind != GFC_ARRAY_ASSUMED_RANK_CONT
+ && akind != GFC_ARRAY_ALLOCATABLE
+ && akind != GFC_ARRAY_POINTER_CONT)
+ delinearize = false;
+ }
+
+ /* See gfc_build_array_ref in trans.c. If we have a cooked_decl or
+ vptr, then we most likely have to do pointer arithmetic using a
+ linearized array offset. */
+ if (delinearize && cooked_decl)
+ delinearize = false;
+ else if (delinearize && get_class_array_vptr (se->expr, vptr))
+ delinearize = false;
+
+ if (!delinearize)
+ {
+ /* Initialize the offset from the array descriptor. This accounts
+ for the array base being something other than zero. */
+ cst_offset = offset = gfc_index_zero_node;
+ add_to_offset (&cst_offset, &offset, gfc_conv_array_offset (decl));
+ }
+ else
+ {
+ /* If we are delinearizing, build up the nested array type using the
+ dimension information we have for each rank. */
+ atype = TREE_TYPE (type);
+ for (n = 0; n < ar->dimen; n++)
+ {
+ /* We're working from the outermost nested array reference inward
+ in this step. ATYPE is the element type for the access in
+ this rank; build the new array type based on the bounds
+ information and store it back into ATYPE for the next rank's
+ processing. */
+ tree lbound = get_array_lbound (decl, n, sym, ar, se);
+ tree ubound = get_array_ubound (decl, n, sym, ar, se);
+ tree dimen = build_range_type (TREE_TYPE (lbound),
+ lbound, ubound);
+ atype = build_array_type (atype, dimen);
+
+ /* Emit a DECL_EXPR for the array type so the gimplification of
+ its type sizes works correctly. */
+ if (! TYPE_NAME (atype))
+ TYPE_NAME (atype) = build_decl (UNKNOWN_LOCATION, TYPE_DECL,
+ NULL_TREE, atype);
+ gfc_add_expr_to_block (&se->pre,
+ build1 (DECL_EXPR, atype,
+ TYPE_NAME (atype)));
+ }
+
+ /* Cast base to the innermost array type. */
+ if (DECL_P (base))
+ TREE_ADDRESSABLE (base) = 1;
+ aref = build1 (NOP_EXPR, atype, base);
+ }
+
+ /* Process indices in reverse order. */
for (n = ar->dimen - 1; n >= 0; n--)
{
/* Calculate the index for this dimension. */
@@ -3888,16 +4091,7 @@ gfc_conv_array_ref (gfc_se * se, gfc_array_ref * ar, gfc_expr *expr,
indexse.expr = save_expr (indexse.expr);
/* Lower bound. */
- tmp = gfc_conv_array_lbound (decl, n);
- if (sym->attr.temporary)
- {
- gfc_init_se (&tmpse, se);
- gfc_conv_expr_type (&tmpse, ar->as->lower[n],
- gfc_array_index_type);
- gfc_add_block_to_block (&se->pre, &tmpse.pre);
- tmp = tmpse.expr;
- }
-
+ tmp = get_array_lbound (decl, n, sym, ar, se);
cond = fold_build2_loc (input_location, LT_EXPR, logical_type_node,
indexse.expr, tmp);
msg = xasprintf ("Index '%%ld' of dimension %d of array '%s' "
@@ -3912,16 +4106,7 @@ gfc_conv_array_ref (gfc_se * se, gfc_array_ref * ar, gfc_expr *expr,
arrays. */
if (n < ar->dimen - 1 || ar->as->type != AS_ASSUMED_SIZE)
{
- tmp = gfc_conv_array_ubound (decl, n);
- if (sym->attr.temporary)
- {
- gfc_init_se (&tmpse, se);
- gfc_conv_expr_type (&tmpse, ar->as->upper[n],
- gfc_array_index_type);
- gfc_add_block_to_block (&se->pre, &tmpse.pre);
- tmp = tmpse.expr;
- }
-
+ tmp = get_array_ubound (decl, n, sym, ar, se);
cond = fold_build2_loc (input_location, GT_EXPR,
logical_type_node, indexse.expr, tmp);
msg = xasprintf ("Index '%%ld' of dimension %d of array '%s' "
@@ -3934,65 +4119,41 @@ gfc_conv_array_ref (gfc_se * se, gfc_array_ref * ar, gfc_expr *expr,
}
}
- /* Multiply the index by the stride. */
- stride = gfc_conv_array_stride (decl, n);
- tmp = fold_build2_loc (input_location, MULT_EXPR, gfc_array_index_type,
- indexse.expr, stride);
-
- /* And add it to the total. */
- add_to_offset (&cst_offset, &offset, tmp);
- }
-
- if (!integer_zerop (cst_offset))
- offset = fold_build2_loc (input_location, PLUS_EXPR,
- gfc_array_index_type, offset, cst_offset);
-
- /* A pointer array component can be detected from its field decl. Fix
- the descriptor, mark the resulting variable decl and pass it to
- build_array_ref. */
- decl = NULL_TREE;
- if (get_CFI_desc (sym, expr, &decl, ar))
- decl = build_fold_indirect_ref_loc (input_location, decl);
- if (!expr->ts.deferred && !sym->attr.codimension
- && is_pointer_array (se->expr))
- {
- if (TREE_CODE (se->expr) == COMPONENT_REF)
- decl = se->expr;
- else if (TREE_CODE (se->expr) == INDIRECT_REF)
- decl = TREE_OPERAND (se->expr, 0);
- else
- decl = se->expr;
- }
- else if (expr->ts.deferred
- || (sym->ts.type == BT_CHARACTER
- && sym->attr.select_type_temporary))
- {
- if (GFC_DESCRIPTOR_TYPE_P (TREE_TYPE (se->expr)))
+ if (!delinearize)
{
- decl = se->expr;
- if (TREE_CODE (decl) == INDIRECT_REF)
- decl = TREE_OPERAND (decl, 0);
+ /* Multiply the index by the stride. */
+ stride = gfc_conv_array_stride (decl, n);
+ tmp = fold_build2_loc (input_location, MULT_EXPR,
+ gfc_array_index_type,
+ indexse.expr, stride);
+
+ /* And add it to the total. */
+ add_to_offset (&cst_offset, &offset, tmp);
}
else
- decl = sym->backend_decl;
- }
- else if (sym->ts.type == BT_CLASS)
- {
- if (UNLIMITED_POLY (sym))
{
- gfc_expr *class_expr = gfc_find_and_cut_at_last_class_ref (expr);
- gfc_init_se (&tmpse, NULL);
- gfc_conv_expr (&tmpse, class_expr);
- if (!se->class_vptr)
- se->class_vptr = gfc_class_vptr_get (tmpse.expr);
- gfc_free_expr (class_expr);
- decl = tmpse.expr;
+ /* Peel off a layer of array nesting from ATYPE to
+ to get the result type of the new ARRAY_REF. */
+ atype = TREE_TYPE (atype);
+ aref = build4 (ARRAY_REF, atype, aref, indexse.expr,
+ NULL_TREE, NULL_TREE);
}
- else
- decl = NULL_TREE;
}
- se->expr = build_array_ref (se->expr, offset, decl, se->class_vptr);
+ if (!delinearize)
+ {
+ /* Build a linearized array reference using the offset from all
+ dimensions. */
+ if (!integer_zerop (cst_offset))
+ offset = fold_build2_loc (input_location, PLUS_EXPR,
+ gfc_array_index_type, offset, cst_offset);
+ se->class_vptr = vptr;
+ vptr = get_class_array_vptr (se->expr, vptr);
+ se->expr = gfc_build_array_ref (base, offset, cooked_decl, vptr);
+ }
+ else
+ /* Return the outermost ARRAY_REF we already built. */
+ se->expr = aref;
}
diff --git a/gcc/testsuite/gfortran.dg/assumed_type_2.f90 b/gcc/testsuite/gfortran.dg/assumed_type_2.f90
index 5d3cd7eaece..07be87ef1eb 100644
--- a/gcc/testsuite/gfortran.dg/assumed_type_2.f90
+++ b/gcc/testsuite/gfortran.dg/assumed_type_2.f90
@@ -147,12 +147,12 @@ end
! { dg-final { scan-tree-dump-times "sub_scalar .&scalar_int," 1 "original" } }
! { dg-final { scan-tree-dump-times "sub_scalar .&scalar_t1," 1 "original" } }
-! { dg-final { scan-tree-dump-times "sub_scalar .&array_int.1.," 1 "original" } }
+! { dg-final { scan-tree-dump-times "sub_scalar .&.*array_int" 1 "original" } }
! { dg-final { scan-tree-dump-times "sub_scalar .&scalar_t1," 1 "original" } }
-! { dg-final { scan-tree-dump-times "sub_scalar .&\\(.\\(real.kind=4..0:. . restrict\\) array_real_alloc.data" 1 "original" } }
+! { dg-final { scan-tree-dump-times "sub_scalar .&.*real.kind=4..0.*restrict.*array_real_alloc.data" 1 "original" } }
! { dg-final { scan-tree-dump-times "sub_scalar .\\(character.kind=1..1:1. .\\) .array_char_ptr.data" 1 "original" } }
-! { dg-final { scan-tree-dump-times "sub_scalar .&\\(.\\(struct t2.0:. . restrict\\) array_t2_alloc.data" 1 "original" } }
+! { dg-final { scan-tree-dump-times "sub_scalar .&.*struct t2.0:..*restrict.*array_t2_alloc.data" 1 "original" } }
! { dg-final { scan-tree-dump-times "sub_scalar .\\(struct t3 .\\) .array_t3_ptr.data" 1 "original" } }
! { dg-final { scan-tree-dump-times "sub_scalar .\\(struct t1 .\\) array_class_t1_alloc._data.data" 1 "original" } }
! { dg-final { scan-tree-dump-times "sub_scalar .\\(struct t1 .\\) \\(array_class_t1_ptr._data.dat" 1 "original" } }
diff --git a/gcc/testsuite/gfortran.dg/goacc/kernels-loop-inner.f95 b/gcc/testsuite/gfortran.dg/goacc/kernels-loop-inner.f95
index b2eb98959f8..23e64d29ab3 100644
--- a/gcc/testsuite/gfortran.dg/goacc/kernels-loop-inner.f95
+++ b/gcc/testsuite/gfortran.dg/goacc/kernels-loop-inner.f95
@@ -9,7 +9,7 @@ program main
integer :: a(100,100), b(100,100)
integer :: i, j, d
- !$acc kernels ! { dg-message "optimized: assigned OpenACC seq loop parallelism" }
+ !$acc kernels ! { dg-message "optimized: assigned OpenACC gang loop parallelism" }
do i=1,100
do j=1,100
a(i,j) = 1
diff --git a/gcc/testsuite/gfortran.dg/graphite/block-2.f b/gcc/testsuite/gfortran.dg/graphite/block-2.f
index bea8ddeb826..266da378c5d 100644
--- a/gcc/testsuite/gfortran.dg/graphite/block-2.f
+++ b/gcc/testsuite/gfortran.dg/graphite/block-2.f
@@ -1,5 +1,11 @@
! { dg-do compile }
! { dg-additional-options "-std=legacy" }
+
+! ldist introduces a __builtin_memset for the first loop and hence
+! breaks the testcases's assumption regarding the number of SCoPs
+! because Graphite cannot deal with the call.
+! { dg-additional-options "-fdisable-tree-ldist" }
+
SUBROUTINE MATRIX_MUL_UNROLLED (A, B, C, L, M, N)
DIMENSION A(L,M), B(M,N), C(L,N)
@@ -18,5 +24,4 @@
RETURN
END
-! Disabled for now as it requires delinearization.
-! { dg-final { scan-tree-dump-times "number of SCoPs: 2" 1 "graphite" { xfail *-*-* } } }
+! { dg-final { scan-tree-dump-times "number of SCoPs: 2" 1 "graphite" } }
diff --git a/gcc/testsuite/gfortran.dg/graphite/block-3.f90 b/gcc/testsuite/gfortran.dg/graphite/block-3.f90
index 452de734905..60c7952c365 100644
--- a/gcc/testsuite/gfortran.dg/graphite/block-3.f90
+++ b/gcc/testsuite/gfortran.dg/graphite/block-3.f90
@@ -12,6 +12,5 @@ enddo
end subroutine matrix_multiply
-! { dg-final { scan-tree-dump-times "number of SCoPs: 1" 1 "graphite" { xfail *-*-* } } }
! { dg-final { scan-tree-dump-times "will be loop blocked" 1 "graphite" { xfail *-*-* } } }
diff --git a/gcc/testsuite/gfortran.dg/graphite/block-4.f90 b/gcc/testsuite/gfortran.dg/graphite/block-4.f90
index 42af5b62444..1bc7a1bb2ae 100644
--- a/gcc/testsuite/gfortran.dg/graphite/block-4.f90
+++ b/gcc/testsuite/gfortran.dg/graphite/block-4.f90
@@ -15,6 +15,5 @@ enddo
end subroutine matrix_multiply
-! { dg-final { scan-tree-dump-times "number of SCoPs: 1" 1 "graphite" { xfail *-*-* } } }
! { dg-final { scan-tree-dump-times "will be loop blocked" 1 "graphite" { xfail *-*-* } } }
diff --git a/gcc/testsuite/gfortran.dg/graphite/id-9.f b/gcc/testsuite/gfortran.dg/graphite/id-9.f
index c9393708897..a43f02bdd42 100644
--- a/gcc/testsuite/gfortran.dg/graphite/id-9.f
+++ b/gcc/testsuite/gfortran.dg/graphite/id-9.f
@@ -8,7 +8,7 @@
do l=1,3
do k=1,l
enddo
- bar(k,l)=bar(k,l)+(v3b-1.d0)
+ bar(k,l)=bar(k,l)+(v3b-1.d0) ! { dg-bogus ".*iteration 2 invokes undefined behavior" "TODO-kernels Caused by delinearization patch" { xfail *-*-* } }
enddo
enddo
do m=1,ne
diff --git a/gcc/testsuite/gfortran.dg/inline_matmul_24.f90 b/gcc/testsuite/gfortran.dg/inline_matmul_24.f90
index 3168d5f1006..8d84f3cdb01 100644
--- a/gcc/testsuite/gfortran.dg/inline_matmul_24.f90
+++ b/gcc/testsuite/gfortran.dg/inline_matmul_24.f90
@@ -39,4 +39,4 @@ program testMATMUL
call abort()
end if
end program testMATMUL
-! { dg-final { scan-tree-dump-times "gamma5\\\[__var_1_do \\* 4 \\+ __var_2_do\\\]|gamma5\\\[NON_LVALUE_EXPR <__var_1_do> \\* 4 \\+ NON_LVALUE_EXPR <__var_2_do>\\\]" 1 "original" } }
+! { dg-final { scan-tree-dump-times "gamma5.*\\\[NON_LVALUE_EXPR <__var_1_do>\\\]\\\[NON_LVALUE_EXPR <__var_2_do>\\\]" 1 "original" } }
diff --git a/gcc/testsuite/gfortran.dg/no_arg_check_2.f90 b/gcc/testsuite/gfortran.dg/no_arg_check_2.f90
index 3570b9719eb..0900dd82646 100644
--- a/gcc/testsuite/gfortran.dg/no_arg_check_2.f90
+++ b/gcc/testsuite/gfortran.dg/no_arg_check_2.f90
@@ -129,12 +129,12 @@ end
! { dg-final { scan-tree-dump-times "sub_scalar .&scalar_int," 1 "original" } }
! { dg-final { scan-tree-dump-times "sub_scalar .&scalar_t1," 1 "original" } }
-! { dg-final { scan-tree-dump-times "sub_scalar .&array_int.1.," 1 "original" } }
+! { dg-final { scan-tree-dump-times "sub_scalar .&.*array_int" 1 "original" } }
! { dg-final { scan-tree-dump-times "sub_scalar .&scalar_t1," 1 "original" } }
-! { dg-final { scan-tree-dump-times "sub_scalar .&\\(.\\(real.kind=4..0:. . restrict\\) array_real_alloc.data" 1 "original" } }
+! { dg-final { scan-tree-dump-times "sub_scalar .&.*real.kind=4..0.*restrict.*array_real_alloc.data" 1 "original" } }
! { dg-final { scan-tree-dump-times "sub_scalar .\\(character.kind=1..1:1. .\\) .array_char_ptr.data" 1 "original" } }
-! { dg-final { scan-tree-dump-times "sub_scalar .&\\(.\\(struct t2.0:. . restrict\\) array_t2_alloc.data" 1 "original" } }
+! { dg-final { scan-tree-dump-times "sub_scalar .&.*struct t2.0:..*restrict.*array_t2_alloc.data" 1 "original" } }
! { dg-final { scan-tree-dump-times "sub_scalar .\\(struct t3 .\\) .array_t3_ptr.data" 1 "original" } }
! { dg-final { scan-tree-dump-times "sub_scalar .\\(struct t1 .\\) array_class_t1_alloc._data.data" 1 "original" } }
! { dg-final { scan-tree-dump-times "sub_scalar .\\(struct t1 .\\) \\(array_class_t1_ptr._data.dat" 1 "original" } }
diff --git a/gcc/testsuite/gfortran.dg/pr32921.f b/gcc/testsuite/gfortran.dg/pr32921.f
index 0661208edde..853438609c4 100644
--- a/gcc/testsuite/gfortran.dg/pr32921.f
+++ b/gcc/testsuite/gfortran.dg/pr32921.f
@@ -45,4 +45,4 @@
RETURN
END
-! { dg-final { scan-tree-dump-times "stride" 4 "lim2" } }
+! { dg-final { scan-tree-dump-times "ubound" 4 "lim2" } }
diff --git a/gcc/testsuite/gfortran.dg/reassoc_4.f b/gcc/testsuite/gfortran.dg/reassoc_4.f
index fdcb46e835c..2368b76aecb 100644
--- a/gcc/testsuite/gfortran.dg/reassoc_4.f
+++ b/gcc/testsuite/gfortran.dg/reassoc_4.f
@@ -1,5 +1,5 @@
! { dg-do compile }
-! { dg-options "-O3 -ffast-math -fdump-tree-reassoc1 --param max-completely-peeled-insns=200" }
+! { dg-options "-O3 -ffast-math -fdump-tree-reassoc1 --param max-completely-peeled-insns=200 --param delinearize=0" }
subroutine anisonl(w,vo,anisox,s,ii1,jj1,weight)
integer ii1,jj1,i1,iii1,j1,jjj1,k1,l1,m1,n1
real*8 w(3,3),vo(3,3),anisox(3,3,3,3),s(60,60),weight
^ permalink raw reply [flat|nested] only message in thread
only message in thread, other threads:[~2021-11-17 8:17 UTC | newest]
Thread overview: (only message) (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2021-11-17 8:17 [gcc/devel/omp/gcc-11] Fortran: delinearize multi-dimensional array accesses Frederik Harwath
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for read-only IMAP folder(s) and NNTP newsgroup(s).