On 06.10.22 14:17, Jakub Jelinek wrote:
On Thu, Oct 06, 2022 at 12:55:01PM +0200, Tobias Burnus wrote:
I don't know whether it makes sense to handle – in the long run – the
case of se.pre/se.post being nonempty – and, if so, how.
I think it is essential not to throw those away,
if se.pre or se.post, you can e.g. expand it roughly as C/C++ ({ cond; }),
in GENERIC it can be say a TARGET_EXPR with a boolean
temporary as slot, where the the initializer will be the
se.pre part, followed by MODIFY_EXPR which sets the slot to se.expr
value and followed by se.post.
Like as attached? – It did survive regtesting.
BTW: The assumption in assume-4.f90 does not help, but I think that's
expected. I wonder whether it will work in both cases after your
gimplify work.
Tobias
-----------------
Siemens Electronic Design Automation GmbH; Anschrift: Arnulfstraße 201, 80634
München; Gesellschaft mit beschränkter Haftung; Geschäftsführer: Thomas
Heurung, Frank Thürauf; Sitz der Gesellschaft: München; Registergericht
München, HRB 106955
openmp: Map holds clause to IFN_ASSUME for Fortran
Same as r13-3107-g847f5addc4d07a2f3b95f5daa50ab4a64dfd957d did for C/C++.
Convert '!$omp assume holds(cond)' to IFN_ASSUME (cond).
gcc/fortran/
* trans-openmp.cc (gfc_trans_omp_assume): New.
(gfc_trans_omp_directive): Call it.
gcc/teststuite/
* gfortran.dg/gomp/assume-3.f90: New test.
* gfortran.dg/gomp/assume-4.f90: New test.
gcc/fortran/trans-openmp.cc | 37 +++++++++++++++++++++-
gcc/testsuite/gfortran.dg/gomp/assume-3.f90 | 46 +++++++++++++++++++++++++++
gcc/testsuite/gfortran.dg/gomp/assume-4.f90 | 48 +++++++++++++++++++++++++++++
3 files changed, 130 insertions(+), 1 deletion(-)
diff --git a/gcc/fortran/trans-openmp.cc b/gcc/fortran/trans-openmp.cc
index 21053694f81..8ea573f7d02 100644
--- a/gcc/fortran/trans-openmp.cc
+++ b/gcc/fortran/trans-openmp.cc
@@ -4570,6 +4570,41 @@ gfc_trans_oacc_wait_directive (gfc_code *code)
static tree gfc_trans_omp_sections (gfc_code *, gfc_omp_clauses *);
static tree gfc_trans_omp_workshare (gfc_code *, gfc_omp_clauses *);
+static tree
+gfc_trans_omp_assume (gfc_code *code)
+{
+ stmtblock_t block;
+ gfc_init_block (&block);
+ gfc_omp_assumptions *assume = code->ext.omp_clauses->assume;
+ if (assume)
+ for (gfc_expr_list *el = assume->holds; el; el = el->next)
+ {
+ location_t loc = gfc_get_location (&el->expr->where);
+ gfc_se se;
+ gfc_init_se (&se, NULL);
+ gfc_conv_expr (&se, el->expr);
+ tree t;
+ if (se.pre.head == NULL_TREE && se.post.head == NULL_TREE)
+ t = se.expr;
+ else
+ {
+ tree var = gfc_create_var (TREE_TYPE (se.expr), NULL);
+ stmtblock_t block2;
+ gfc_init_block (&block2);
+ gfc_add_block_to_block (&block2, &se.pre);
+ gfc_add_modify_loc (loc, &block2, var, se.expr);
+ gfc_add_block_to_block (&block2, &se.post);
+ t = gfc_finish_block (&block2);
+ t = build4 (TARGET_EXPR, boolean_type_node, var, t, NULL, NULL);
+ }
+ t = build_call_expr_internal_loc (loc, IFN_ASSUME,
+ void_type_node, 1, t);
+ gfc_add_expr_to_block (&block, t);
+ }
+ gfc_add_expr_to_block (&block, gfc_trans_omp_code (code->block->next, true));
+ return gfc_finish_block (&block);
+}
+
static tree
gfc_trans_omp_atomic (gfc_code *code)
{
@@ -7488,7 +7523,7 @@ gfc_trans_omp_directive (gfc_code *code)
switch (code->op)
{
case EXEC_OMP_ASSUME:
- return gfc_trans_omp_code (code->block->next, true);
+ return gfc_trans_omp_assume (code);
case EXEC_OMP_ATOMIC:
return gfc_trans_omp_atomic (code);
case EXEC_OMP_BARRIER:
diff --git a/gcc/testsuite/gfortran.dg/gomp/assume-3.f90 b/gcc/testsuite/gfortran.dg/gomp/assume-3.f90
new file mode 100644
index 00000000000..e5deace306e
--- /dev/null
+++ b/gcc/testsuite/gfortran.dg/gomp/assume-3.f90
@@ -0,0 +1,46 @@
+! { dg-do compile }
+! { dg-options "-fopenmp -O2 -fdump-tree-optimized -fdump-tree-original" }
+
+! { dg-final { scan-tree-dump-times ".ASSUME \\(x == 42\\);" 1 "original" } }
+! { dg-final { scan-tree-dump-times ".ASSUME \\(x <= 41\\);" 1 "original" } }
+! { dg-final { scan-tree-dump-times ".ASSUME \\(y <= 6\\);" 1 "original" } }
+! { dg-final { scan-tree-dump-times ".ASSUME \\(y > 5\\);" 1 "original" } }
+
+! { dg-final { scan-tree-dump-times "return 42;" 3 "optimized" } }
+! { dg-final { scan-tree-dump-not "return -1;" "optimized" } }
+
+integer function foo (x)
+ implicit none
+ integer, value :: x
+ integer :: y
+ !$omp assume holds (x == 42)
+ y = x;
+ !$omp end assume
+ foo = y
+end
+
+integer function bar (x)
+ implicit none
+ integer, value :: x
+ !$omp assume holds (x < 42)
+ block
+ end block
+ if (x == 42) then
+ bar = -1
+ return
+ end if
+ bar = 42
+end
+
+integer function foobar (y)
+ implicit none
+ integer, value :: y
+ !$omp assume holds(y > 5) holds (y < 7)
+ block
+ if (y == 6) then
+ foobar = 42
+ return
+ end if
+ end block
+ foobar = -1
+end
diff --git a/gcc/testsuite/gfortran.dg/gomp/assume-4.f90 b/gcc/testsuite/gfortran.dg/gomp/assume-4.f90
new file mode 100644
index 00000000000..f1f91924cea
--- /dev/null
+++ b/gcc/testsuite/gfortran.dg/gomp/assume-4.f90
@@ -0,0 +1,48 @@
+! { dg-do compile }
+! { dg-options "-fopenmp -O2 -fdump-tree-original -fdump-tree-optimized" }
+! { dg-final { scan-tree-dump-times ".ASSUME \\(i_lower_bound \\(\\) < i\\);" 1 "original" }
+! { dg-final { scan-tree-dump-times ".ASSUME \\(TARGET_EXPR <D.\[0-9\]+, D.\[0-9\]+ = j_upper_bound \\(\\);" 1 "original" }
+! { dg-final { scan-tree-dump-times "__builtin_free" 1 "original" }
+
+! { dg-final { scan-tree-dump-not "i_lower_bound" "optimized" }
+! { dg-final { scan-tree-dump-not "j_upper_bound" "optimized" }
+! { dg-final { scan-tree-dump-not "__builtin_free" "optimized" }
+
+! Note: Currently, the assumption does not help with optimization in either variant.
+
+ implicit none
+ integer, value :: i
+
+ !$omp assume holds(i > i_lower_bound ())
+ block
+ if (i > 4) then
+ f = 42
+ else
+ f = -1
+ end if
+ end block
+contains
+ function i_lower_bound ()
+ integer :: i_lower_bound
+ i_lower_bound = 5
+ end function
+end
+
+integer function g(j)
+ implicit none
+ integer, value :: j
+
+ !$omp assume holds(j < j_upper_bound ())
+ block
+ if (j < 10) then
+ g = 42
+ else
+ g = -1
+ end if
+ end block
+contains
+ function j_upper_bound ()
+ integer, allocatable :: j_upper_bound
+ j_upper_bound = 10
+ end function
+end
