"Andre Vieira (lists)" <andre.simoesdiasvie...@arm.com> writes:
> Hi,
>
> This patch replaces the uses of simd_clone_subparts with
> TYPE_VECTOR_SUBPARTS and removes the definition of the first.
>
> gcc/ChangeLog:
>
> * omp-sind-clone.cc (simd_clone_subparts): Remove.
> (simd_clone_init_simd_arrays): Replace simd_clone_subparts with
> TYPE_VECTOR_SUBPARTS.
> (ipa_simd_modify_function_body): Likewise.
> * tree-vect-stmts.cc (simd_clone_subparts): Remove.
> (vectorizable_simd_clone_call): Replace simd_clone_subparts
> with TYPE_VECTOR_SUBPARTS.
>
> diff --git a/gcc/omp-simd-clone.cc b/gcc/omp-simd-clone.cc
> index
> 0949b8ba288dfc7e7692403bfc600983faddf5dd..48b480e7556d9ad8e5502e10e513ec36b17b9cbb
> 100644
> --- a/gcc/omp-simd-clone.cc
> +++ b/gcc/omp-simd-clone.cc
> @@ -255,16 +255,6 @@ ok_for_auto_simd_clone (struct cgraph_node *node)
> return true;
> }
>
> -
> -/* Return the number of elements in vector type VECTYPE, which is associated
> - with a SIMD clone. At present these always have a constant length. */
> -
> -static unsigned HOST_WIDE_INT
> -simd_clone_subparts (tree vectype)
> -{
> - return TYPE_VECTOR_SUBPARTS (vectype).to_constant ();
> -}
> -
> /* Allocate a fresh `simd_clone' and return it. NARGS is the number
> of arguments to reserve space for. */
>
> @@ -1027,7 +1017,7 @@ simd_clone_init_simd_arrays (struct cgraph_node *node,
> }
> continue;
> }
> - if (known_eq (simd_clone_subparts (TREE_TYPE (arg)),
> + if (known_eq (TYPE_VECTOR_SUBPARTS (TREE_TYPE (arg)),
> node->simdclone->simdlen))
> {
> tree ptype = build_pointer_type (TREE_TYPE (TREE_TYPE (array)));
> @@ -1039,7 +1029,7 @@ simd_clone_init_simd_arrays (struct cgraph_node *node,
> }
> else
> {
> - unsigned int simdlen = simd_clone_subparts (TREE_TYPE (arg));
> + poly_uint64 simdlen = TYPE_VECTOR_SUBPARTS (TREE_TYPE (arg));
> unsigned int times = vector_unroll_factor (node->simdclone->simdlen,
> simdlen);
> tree ptype = build_pointer_type (TREE_TYPE (TREE_TYPE (array)));
> @@ -1225,9 +1215,9 @@ ipa_simd_modify_function_body (struct cgraph_node *node,
> iter, NULL_TREE, NULL_TREE);
> adjustments->register_replacement (&(*adjustments->m_adj_params)[j],
> r);
>
> - if (multiple_p (node->simdclone->simdlen, simd_clone_subparts
> (vectype)))
> + if (multiple_p (node->simdclone->simdlen, TYPE_VECTOR_SUBPARTS
> (vectype)))
> j += vector_unroll_factor (node->simdclone->simdlen,
> - simd_clone_subparts (vectype)) - 1;
> + TYPE_VECTOR_SUBPARTS (vectype)) - 1;
> }
> adjustments->sort_replacements ();
>
> diff --git a/gcc/tree-vect-stmts.cc b/gcc/tree-vect-stmts.cc
> index
> df6239a1c61c7213ad3c1468723bc1adf70bc02c..c85b6babc4bc5bc3111ef326dcc8f32bb25333f6
> 100644
> --- a/gcc/tree-vect-stmts.cc
> +++ b/gcc/tree-vect-stmts.cc
> @@ -3964,16 +3964,6 @@ vect_simd_lane_linear (tree op, class loop *loop,
> }
> }
>
> -/* Return the number of elements in vector type VECTYPE, which is associated
> - with a SIMD clone. At present these vectors always have a constant
> - length. */
> -
> -static unsigned HOST_WIDE_INT
> -simd_clone_subparts (tree vectype)
> -{
> - return TYPE_VECTOR_SUBPARTS (vectype).to_constant ();
> -}
> -
> /* Function vectorizable_simd_clone_call.
>
> Check if STMT_INFO performs a function call that can be vectorized
> @@ -4251,7 +4241,7 @@ vectorizable_simd_clone_call (vec_info *vinfo,
> stmt_vec_info stmt_info,
> slp_node);
> if (arginfo[i].vectype == NULL
> || !constant_multiple_p (bestn->simdclone->simdlen,
> - simd_clone_subparts (arginfo[i].vectype)))
> + TYPE_VECTOR_SUBPARTS (arginfo[i].vectype)))
> return false;
> }
>
> @@ -4349,15 +4339,19 @@ vectorizable_simd_clone_call (vec_info *vinfo,
> stmt_vec_info stmt_info,
> case SIMD_CLONE_ARG_TYPE_VECTOR:
> atype = bestn->simdclone->args[i].vector_type;
> o = vector_unroll_factor (nunits,
> - simd_clone_subparts (atype));
> + TYPE_VECTOR_SUBPARTS (atype));
> for (m = j * o; m < (j + 1) * o; m++)
> {
> - if (simd_clone_subparts (atype)
> - < simd_clone_subparts (arginfo[i].vectype))
> + poly_uint64 atype_subparts = TYPE_VECTOR_SUBPARTS (atype);
> + poly_uint64 arginfo_subparts
> + = TYPE_VECTOR_SUBPARTS (arginfo[i].vectype);
> + if (known_lt (atype_subparts, arginfo_subparts))
> {
> poly_uint64 prec = GET_MODE_BITSIZE (TYPE_MODE (atype));
> - k = (simd_clone_subparts (arginfo[i].vectype)
> - / simd_clone_subparts (atype));
> + if (!constant_multiple_p (atype_subparts,
> + arginfo_subparts, &k))
> + gcc_unreachable ();
> +
Very minor, but I think it's conceptually cleaner to use the
constant_multiple_p as the if condition, rather than known_lt.
Then...
> gcc_assert ((k & (k - 1)) == 0);
> if (m == 0)
> {
> @@ -4387,8 +4381,9 @@ vectorizable_simd_clone_call (vec_info *vinfo,
> stmt_vec_info stmt_info,
> }
> else
> {
> - k = (simd_clone_subparts (atype)
> - / simd_clone_subparts (arginfo[i].vectype));
> + if (!constant_multiple_p (arginfo_subparts,
> + atype_subparts, &k))
> + gcc_unreachable ();
...make this else conditional on constant_multiple_p too,
with a new final else that contains gcc_unreachable.
> gcc_assert ((k & (k - 1)) == 0);
> vec<constructor_elt, va_gc> *ctor_elts;
> if (k != 1)
> @@ -4522,7 +4517,7 @@ vectorizable_simd_clone_call (vec_info *vinfo,
> stmt_vec_info stmt_info,
> if (vec_dest)
> {
> gcc_assert (ratype
> - || known_eq (simd_clone_subparts (rtype), nunits));
> + || known_eq (TYPE_VECTOR_SUBPARTS (rtype), nunits));
> if (ratype)
> new_temp = create_tmp_var (ratype);
> else if (useless_type_conversion_p (vectype, rtype))
> @@ -4536,13 +4531,13 @@ vectorizable_simd_clone_call (vec_info *vinfo,
> stmt_vec_info stmt_info,
>
> if (vec_dest)
> {
> - if (!multiple_p (simd_clone_subparts (vectype), nunits))
> + if (!multiple_p (TYPE_VECTOR_SUBPARTS (vectype), nunits))
> {
> unsigned int k, l;
> poly_uint64 prec = GET_MODE_BITSIZE (TYPE_MODE (vectype));
> poly_uint64 bytes = GET_MODE_SIZE (TYPE_MODE (vectype));
> k = vector_unroll_factor (nunits,
> - simd_clone_subparts (vectype));
> + TYPE_VECTOR_SUBPARTS (vectype));
> gcc_assert ((k & (k - 1)) == 0);
> for (l = 0; l < k; l++)
> {
> @@ -4568,10 +4563,12 @@ vectorizable_simd_clone_call (vec_info *vinfo,
> stmt_vec_info stmt_info,
> vect_clobber_variable (vinfo, stmt_info, gsi, new_temp);
> continue;
> }
> - else if (!multiple_p (nunits, simd_clone_subparts (vectype)))
> + else if (!multiple_p (nunits, TYPE_VECTOR_SUBPARTS (vectype)))
> {
> - unsigned int k = (simd_clone_subparts (vectype)
> - / simd_clone_subparts (rtype));
> + unsigned int k;
> + if (!constant_multiple_p (TYPE_VECTOR_SUBPARTS (vectype),
> + TYPE_VECTOR_SUBPARTS (rtype), &k))
> + gcc_unreachable ();
Suggest using vector_unroll_factor here too.
Thanks,
Richard
> gcc_assert ((k & (k - 1)) == 0);
> if ((j & (k - 1)) == 0)
> vec_alloc (ret_ctor_elts, k);
> @@ -4579,7 +4576,7 @@ vectorizable_simd_clone_call (vec_info *vinfo,
> stmt_vec_info stmt_info,
> {
> unsigned int m, o;
> o = vector_unroll_factor (nunits,
> - simd_clone_subparts (rtype));
> + TYPE_VECTOR_SUBPARTS (rtype));
> for (m = 0; m < o; m++)
> {
> tree tem = build4 (ARRAY_REF, rtype, new_temp,
