On Fri, Oct 25, 2019 at 2:39 PM Richard Sandiford
<richard.sandif...@arm.com> wrote:
>
> This patch replaces vec_info::vector_size with vec_info::vector_mode,
> but for now continues to use it as a way of specifying a single
> vector size. This makes it easier for later patches to use
> related_vector_mode instead.
OK.
>
> 2019-10-24 Richard Sandiford <richard.sandif...@arm.com>
>
> gcc/
> * tree-vectorizer.h (vec_info::vector_size): Replace with...
> (vec_info::vector_mode): ...this new field.
> * tree-vect-loop.c (vect_update_vf_for_slp): Update accordingly.
> (vect_analyze_loop, vect_transform_loop): Likewise.
> * tree-vect-slp.c (can_duplicate_and_interleave_p): Likewise.
> (vect_make_slp_decision, vect_slp_bb_region): Likewise.
> * tree-vect-stmts.c (get_vectype_for_scalar_type): Likewise.
> * tree-vectorizer.c (try_vectorize_loop_1): Likewise.
>
> gcc/testsuite/
> * gcc.dg/vect/vect-tail-nomask-1.c: Update expected epilogue
> vectorization message.
>
> Index: gcc/tree-vectorizer.h
> ===================================================================
> --- gcc/tree-vectorizer.h 2019-10-25 13:26:59.093879082 +0100
> +++ gcc/tree-vectorizer.h 2019-10-25 13:27:19.317736181 +0100
> @@ -329,9 +329,9 @@ typedef std::pair<tree, tree> vec_object
> /* Cost data used by the target cost model. */
> void *target_cost_data;
>
> - /* The vector size for this loop in bytes, or 0 if we haven't picked
> - a size yet. */
> - poly_uint64 vector_size;
> + /* If we've chosen a vector size for this vectorization region,
> + this is one mode that has such a size, otherwise it is VOIDmode. */
> + machine_mode vector_mode;
>
> private:
> stmt_vec_info new_stmt_vec_info (gimple *stmt);
> Index: gcc/tree-vect-loop.c
> ===================================================================
> --- gcc/tree-vect-loop.c 2019-10-25 13:27:15.525762975 +0100
> +++ gcc/tree-vect-loop.c 2019-10-25 13:27:19.309736237 +0100
> @@ -1414,8 +1414,8 @@ vect_update_vf_for_slp (loop_vec_info lo
> dump_printf_loc (MSG_NOTE, vect_location,
> "Loop contains SLP and non-SLP stmts\n");
> /* Both the vectorization factor and unroll factor have the form
> - loop_vinfo->vector_size * X for some rational X, so they must have
> - a common multiple. */
> + GET_MODE_SIZE (loop_vinfo->vector_mode) * X for some rational X,
> + so they must have a common multiple. */
> vectorization_factor
> = force_common_multiple (vectorization_factor,
> LOOP_VINFO_SLP_UNROLLING_FACTOR
> (loop_vinfo));
> @@ -2341,7 +2341,7 @@ vect_analyze_loop (class loop *loop, loo
> " loops cannot be vectorized\n");
>
> unsigned n_stmts = 0;
> - poly_uint64 autodetected_vector_size = 0;
> + machine_mode autodetected_vector_mode = VOIDmode;
> opt_loop_vec_info first_loop_vinfo = opt_loop_vec_info::success (NULL);
> machine_mode next_vector_mode = VOIDmode;
> while (1)
> @@ -2357,7 +2357,7 @@ vect_analyze_loop (class loop *loop, loo
> gcc_checking_assert (first_loop_vinfo == NULL);
> return loop_vinfo;
> }
> - loop_vinfo->vector_size = GET_MODE_SIZE (next_vector_mode);
> + loop_vinfo->vector_mode = next_vector_mode;
>
> bool fatal = false;
>
> @@ -2366,7 +2366,7 @@ vect_analyze_loop (class loop *loop, loo
>
> opt_result res = vect_analyze_loop_2 (loop_vinfo, fatal, &n_stmts);
> if (mode_i == 0)
> - autodetected_vector_size = loop_vinfo->vector_size;
> + autodetected_vector_mode = loop_vinfo->vector_mode;
>
> if (res)
> {
> @@ -2401,21 +2401,21 @@ vect_analyze_loop (class loop *loop, loo
>
> if (mode_i < vector_modes.length ()
> && known_eq (GET_MODE_SIZE (vector_modes[mode_i]),
> - autodetected_vector_size))
> + GET_MODE_SIZE (autodetected_vector_mode)))
> mode_i += 1;
>
> if (mode_i == vector_modes.length ()
> - || known_eq (autodetected_vector_size, 0U))
> + || autodetected_vector_mode == VOIDmode)
> {
> if (first_loop_vinfo)
> {
> loop->aux = (loop_vec_info) first_loop_vinfo;
> if (dump_enabled_p ())
> {
> + machine_mode mode = first_loop_vinfo->vector_mode;
> dump_printf_loc (MSG_NOTE, vect_location,
> - "***** Choosing vector size ");
> - dump_dec (MSG_NOTE, first_loop_vinfo->vector_size);
> - dump_printf (MSG_NOTE, "\n");
> + "***** Choosing vector mode %s\n",
> + GET_MODE_NAME (mode));
> }
> return first_loop_vinfo;
> }
> @@ -8238,12 +8238,9 @@ vect_transform_loop (loop_vec_info loop_
> dump_printf (MSG_NOTE, "\n");
> }
> else
> - {
> - dump_printf_loc (MSG_NOTE, vect_location,
> - "LOOP EPILOGUE VECTORIZED (VS=");
> - dump_dec (MSG_NOTE, loop_vinfo->vector_size);
> - dump_printf (MSG_NOTE, ")\n");
> - }
> + dump_printf_loc (MSG_NOTE, vect_location,
> + "LOOP EPILOGUE VECTORIZED (MODE=%s)\n",
> + GET_MODE_NAME (loop_vinfo->vector_mode));
> }
>
> /* Loops vectorized with a variable factor won't benefit from
> @@ -8294,14 +8291,14 @@ vect_transform_loop (loop_vec_info loop_
> unsigned int ratio;
> while (next_i < vector_modes.length ()
> && !(constant_multiple_p
> - (loop_vinfo->vector_size,
> + (GET_MODE_SIZE (loop_vinfo->vector_mode),
> GET_MODE_SIZE (vector_modes[next_i]), &ratio)
> && eiters >= lowest_vf / ratio))
> next_i += 1;
> }
> else
> while (next_i < vector_modes.length ()
> - && maybe_lt (loop_vinfo->vector_size,
> + && maybe_lt (GET_MODE_SIZE (loop_vinfo->vector_mode),
> GET_MODE_SIZE (vector_modes[next_i])))
> next_i += 1;
>
> Index: gcc/tree-vect-slp.c
> ===================================================================
> --- gcc/tree-vect-slp.c 2019-10-25 13:27:15.525762975 +0100
> +++ gcc/tree-vect-slp.c 2019-10-25 13:27:19.313736209 +0100
> @@ -274,7 +274,7 @@ can_duplicate_and_interleave_p (vec_info
> {
> scalar_int_mode int_mode;
> poly_int64 elt_bits = elt_bytes * BITS_PER_UNIT;
> - if (multiple_p (vinfo->vector_size, elt_bytes, &nelts)
> + if (multiple_p (GET_MODE_SIZE (vinfo->vector_mode), elt_bytes, &nelts)
> && int_mode_for_size (elt_bits, 0).exists (&int_mode))
> {
> tree int_type = build_nonstandard_integer_type
> @@ -474,7 +474,7 @@ vect_get_and_check_slp_defs (vec_info *v
> }
> if ((dt == vect_constant_def
> || dt == vect_external_def)
> - && !vinfo->vector_size.is_constant ()
> + && !GET_MODE_SIZE (vinfo->vector_mode).is_constant ()
> && (TREE_CODE (type) == BOOLEAN_TYPE
> || !can_duplicate_and_interleave_p (vinfo, stmts.length (),
> TYPE_MODE (type))))
> @@ -2339,8 +2339,11 @@ vect_make_slp_decision (loop_vec_info lo
> FOR_EACH_VEC_ELT (slp_instances, i, instance)
> {
> /* FORNOW: SLP if you can. */
> - /* All unroll factors have the form vinfo->vector_size * X for some
> - rational X, so they must have a common multiple. */
> + /* All unroll factors have the form:
> +
> + GET_MODE_SIZE (vinfo->vector_mode) * X
> +
> + for some rational X, so they must have a common multiple. */
> unrolling_factor
> = force_common_multiple (unrolling_factor,
> SLP_INSTANCE_UNROLLING_FACTOR (instance));
> @@ -3096,7 +3099,7 @@ vect_slp_bb_region (gimple_stmt_iterator
>
> vec_info_shared shared;
>
> - poly_uint64 autodetected_vector_size = 0;
> + machine_mode autodetected_vector_mode = VOIDmode;
> while (1)
> {
> bool vectorized = false;
> @@ -3109,7 +3112,7 @@ vect_slp_bb_region (gimple_stmt_iterator
> bb_vinfo->shared->save_datarefs ();
> else
> bb_vinfo->shared->check_datarefs ();
> - bb_vinfo->vector_size = GET_MODE_SIZE (next_vector_mode);
> + bb_vinfo->vector_mode = next_vector_mode;
>
> if (vect_slp_analyze_bb_1 (bb_vinfo, n_stmts, fatal)
> && dbg_cnt (vect_slp))
> @@ -3123,7 +3126,7 @@ vect_slp_bb_region (gimple_stmt_iterator
> unsigned HOST_WIDE_INT bytes;
> if (dump_enabled_p ())
> {
> - if (bb_vinfo->vector_size.is_constant (&bytes))
> + if (GET_MODE_SIZE (bb_vinfo->vector_mode).is_constant (&bytes))
> dump_printf_loc (MSG_OPTIMIZED_LOCATIONS, vect_location,
> "basic block part vectorized using %wu byte "
> "vectors\n", bytes);
> @@ -3137,18 +3140,18 @@ vect_slp_bb_region (gimple_stmt_iterator
> }
>
> if (mode_i == 0)
> - autodetected_vector_size = bb_vinfo->vector_size;
> + autodetected_vector_mode = bb_vinfo->vector_mode;
>
> delete bb_vinfo;
>
> if (mode_i < vector_modes.length ()
> && known_eq (GET_MODE_SIZE (vector_modes[mode_i]),
> - autodetected_vector_size))
> + GET_MODE_SIZE (autodetected_vector_mode)))
> mode_i += 1;
>
> if (vectorized
> || mode_i == vector_modes.length ()
> - || known_eq (autodetected_vector_size, 0U)
> + || autodetected_vector_mode == VOIDmode
> /* If vect_slp_analyze_bb_1 signaled that analysis for all
> vector sizes will fail do not bother iterating. */
> || fatal)
> Index: gcc/tree-vect-stmts.c
> ===================================================================
> --- gcc/tree-vect-stmts.c 2019-10-25 13:27:12.121787027 +0100
> +++ gcc/tree-vect-stmts.c 2019-10-25 13:27:19.313736209 +0100
> @@ -11212,11 +11212,10 @@ get_vectype_for_scalar_type_and_size (tr
> get_vectype_for_scalar_type (vec_info *vinfo, tree scalar_type)
> {
> tree vectype;
> - vectype = get_vectype_for_scalar_type_and_size (scalar_type,
> - vinfo->vector_size);
> - if (vectype
> - && known_eq (vinfo->vector_size, 0U))
> - vinfo->vector_size = GET_MODE_SIZE (TYPE_MODE (vectype));
> + poly_uint64 vector_size = GET_MODE_SIZE (vinfo->vector_mode);
> + vectype = get_vectype_for_scalar_type_and_size (scalar_type, vector_size);
> + if (vectype && vinfo->vector_mode == VOIDmode)
> + vinfo->vector_mode = TYPE_MODE (vectype);
> return vectype;
> }
>
> Index: gcc/tree-vectorizer.c
> ===================================================================
> --- gcc/tree-vectorizer.c 2019-10-21 07:41:32.997886232 +0100
> +++ gcc/tree-vectorizer.c 2019-10-25 13:27:19.317736181 +0100
> @@ -971,7 +971,7 @@ try_vectorize_loop_1 (hash_table<simduid
> unsigned HOST_WIDE_INT bytes;
> if (dump_enabled_p ())
> {
> - if (loop_vinfo->vector_size.is_constant (&bytes))
> + if (GET_MODE_SIZE (loop_vinfo->vector_mode).is_constant (&bytes))
> dump_printf_loc (MSG_OPTIMIZED_LOCATIONS, vect_location,
> "loop vectorized using %wu byte vectors\n", bytes);
> else
> Index: gcc/testsuite/gcc.dg/vect/vect-tail-nomask-1.c
> ===================================================================
> --- gcc/testsuite/gcc.dg/vect/vect-tail-nomask-1.c 2019-03-08
> 18:15:02.260871260 +0000
> +++ gcc/testsuite/gcc.dg/vect/vect-tail-nomask-1.c 2019-10-25
> 13:27:19.309736237 +0100
> @@ -106,4 +106,4 @@ main (int argc, const char **argv)
> }
>
> /* { dg-final { scan-tree-dump-times "LOOP VECTORIZED" 2 "vect" { target
> avx2_runtime } } } */
> -/* { dg-final { scan-tree-dump-times "LOOP EPILOGUE VECTORIZED \\(VS=16\\)"
> 2 "vect" { target avx2_runtime } } } */
> +/* { dg-final { scan-tree-dump-times "LOOP EPILOGUE VECTORIZED
> \\(MODE=V16QI\\)" 2 "vect" { target avx2_runtime } } } */
