re PR tree-optimization/68128 (A huge regression in Parboil v2.5 OpenMP CUTCP test (2.5 times lower performance))
PR tree-optimization/68128
* tree.h (OMP_CLAUSE_SHARED_READONLY): Define.
* gimplify.c: Include gimple-walk.h.
(enum gimplify_omp_var_data): Add GOVD_WRITTEN.
(omp_notice_variable): Set flags to n->value if n already
exists in target region, but we need to jump to do_outer.
(omp_shared_to_firstprivate_optimizable_decl_p,
omp_mark_stores, omp_find_stores_op, omp_find_stores_stmt): New
functions.
(gimplify_adjust_omp_clauses_1): Set OMP_CLAUSE_SHARED_READONLY
on OMP_CLAUSE_SHARED if it is a scalar non-addressable that is
not modified in the body. Call omp_mark_stores for outer
contexts on OMP_CLAUSE_SHARED clauses if they could be written
in the body or on OMP_CLAUSE_LASTPRIVATE.
(gimplify_adjust_omp_clauses): Add body argument, call
omp_find_stores_{stmt,op} on the body through walk_gimple_seq.
Set OMP_CLAUSE_SHARED_READONLY
on OMP_CLAUSE_SHARED if it is a scalar non-addressable that is
not modified in the body. Call omp_mark_stores for outer
contexts on OMP_CLAUSE_SHARED clauses if they could be written
in the body or on OMP_CLAUSE_LASTPRIVATE or on OMP_CLAUSE_LINEAR
without OMP_CLAUSE_LINEAR_NO_COPYOUT or on OMP_CLAUSE_REDUCTION.
(gimplify_oacc_cache, gimplify_omp_parallel, gimplify_omp_task,
gimplify_omp_for, gimplify_omp_workshare, gimplify_omp_target_update,
gimplify_expr): Adjust gimplify_adjust_omp_clauses callers.
* tree-nested.c (convert_nonlocal_omp_clauses,
convert_local_omp_clauses): Clear OMP_CLAUSE_SHARED_READONLY on
non-local vars or local vars referenced from nested routines.
* omp-low.c (scan_sharing_clauses): For OMP_CLAUSE_SHARED_READONLY
attempt to optimize it into OMP_CLAUSE_FIRSTPRIVATE. Even for
TREE_READONLY, don't call use_pointer_for_field with non-NULL
second argument until we are sure we are keeping OMP_CLAUSE_SHARED.
* gcc.dg/gomp/pr68128-1.c: New test.
* gcc.dg/gomp/pr68128-2.c: New test.
From-SVN: r230932
