diff options
Diffstat (limited to 'gcc')
| -rw-r--r-- | gcc/ChangeLog.omp | 8 | ||||
| -rw-r--r-- | gcc/omp-expand.cc | 5 | ||||
| -rw-r--r-- | gcc/omp-general.cc | 29 |
3 files changed, 35 insertions, 7 deletions
diff --git a/gcc/ChangeLog.omp b/gcc/ChangeLog.omp index 1052b36..712473c 100644 --- a/gcc/ChangeLog.omp +++ b/gcc/ChangeLog.omp @@ -1,3 +1,11 @@ +2021-03-01 Kwok Cheung Yeung <kcy@codesourcery.com> + + * omp-expand.cc (expand_oacc_for): Convert .tile variable to + diff_type before multiplying. + * omp-general.cc (omp_extract_for_data): Use accumulated precision + of all collapsed for-loops as precision of iteration variable, up + to the precision of a long long. + 2021-02-26 Andrew Stubbs <ams@codesourcery.com> * dwarf2out.cc (gen_subprogram_die): Replace existing low/high PC diff --git a/gcc/omp-expand.cc b/gcc/omp-expand.cc index e113231..3160207 100644 --- a/gcc/omp-expand.cc +++ b/gcc/omp-expand.cc @@ -7702,7 +7702,10 @@ expand_oacc_for (struct omp_region *region, struct omp_for_data *fd) tile_size = create_tmp_var (diff_type, ".tile_size"); expr = build_int_cst (diff_type, 1); for (int ix = 0; ix < fd->collapse; ix++) - expr = fold_build2 (MULT_EXPR, diff_type, counts[ix].tile, expr); + { + tree tile = fold_convert (diff_type, counts[ix].tile); + expr = fold_build2 (MULT_EXPR, diff_type, tile, expr); + } expr = force_gimple_operand_gsi (&gsi, expr, true, NULL_TREE, true, GSI_SAME_STMT); ass = gimple_build_assign (tile_size, expr); diff --git a/gcc/omp-general.cc b/gcc/omp-general.cc index a406c57..8c7dce2 100644 --- a/gcc/omp-general.cc +++ b/gcc/omp-general.cc @@ -375,6 +375,7 @@ omp_extract_for_data (gomp_for *for_stmt, struct omp_for_data *fd, fd->non_rect = true; } } + int accum_iter_precision = 0; for (i = 0; i < cnt; i++) { if (i == 0 @@ -457,12 +458,28 @@ omp_extract_for_data (gomp_for *for_stmt, struct omp_for_data *fd, { if (fd->collapse == 1 && !fd->tiling) iter_type = TREE_TYPE (loop->v); - else if (i == 0 - || TYPE_PRECISION (iter_type) - < TYPE_PRECISION (TREE_TYPE (loop->v))) - iter_type - = build_nonstandard_integer_type - (TYPE_PRECISION (TREE_TYPE (loop->v)), 1); + else + { + int loop_precision = TYPE_PRECISION (TREE_TYPE (loop->v)); + int iter_type_precision = 0; + const int max_accum_precision + = TYPE_PRECISION (long_long_unsigned_type_node); + + accum_iter_precision += loop_precision; + + if (i == 0 + || (loop_precision >= max_accum_precision + && loop_precision >= TYPE_PRECISION (iter_type))) + iter_type_precision = loop_precision; + else if (TYPE_PRECISION (iter_type) < max_accum_precision) + iter_type_precision + = MIN (1 << ceil_log2 (accum_iter_precision), + max_accum_precision); + + if (iter_type_precision) + iter_type = build_nonstandard_integer_type + (iter_type_precision, 1); + } } else if (iter_type != long_long_unsigned_type_node) { |