From: Richard Sandiford Date: Thu, 14 Nov 2019 15:12:58 +0000 (+0000) Subject: Support vectorisation with mixed vector sizes X-Git-Url: https://git.libre-soc.org/?a=commitdiff_plain;h=df7c22831f1e48dba49479c5960c1c180d8eab2c;p=gcc.git Support vectorisation with mixed vector sizes After previous patches, it's now possible to make the vectoriser support multiple vector sizes in the same vector region, using related_vector_mode to pick the right vector mode for a given element mode. No port yet takes advantage of this, but I have a follow-on patch for AArch64. This patch also seemed like a good opportunity to add some more dump messages: one to make it clear which vector size/mode was being used when analysis passed or failed, and another to say when we've decided to skip a redundant vector size/mode. 2019-11-14 Richard Sandiford gcc/ * machmode.h (opt_machine_mode::operator==): New function. (opt_machine_mode::operator!=): Likewise. * tree-vectorizer.h (vec_info::vector_mode): Update comment. (get_related_vectype_for_scalar_type): Delete. (get_vectype_for_scalar_type_and_size): Declare. * tree-vect-slp.c (vect_slp_bb_region): Print dump messages to say whether analysis passed or failed, and with what vector modes. Use related_vector_mode to check whether trying a particular vector mode would be redundant with the autodetected mode, and print a dump message if we decide to skip it. * tree-vect-loop.c (vect_analyze_loop): Likewise. (vect_create_epilog_for_reduction): Use get_related_vectype_for_scalar_type instead of get_vectype_for_scalar_type_and_size. * tree-vect-stmts.c (get_vectype_for_scalar_type_and_size): Replace with... (get_related_vectype_for_scalar_type): ...this new function. Take a starting/"prevailing" vector mode rather than a vector size. Take an optional nunits argument, with the same meaning as for related_vector_mode. Use related_vector_mode when not auto-detecting a mode, falling back to mode_for_vector if no target mode exists. (get_vectype_for_scalar_type): Update accordingly. (get_same_sized_vectype): Likewise. * tree-vectorizer.c (get_vec_alignment_for_array_type): Likewise. From-SVN: r278240 --- diff --git a/gcc/ChangeLog b/gcc/ChangeLog index 41c94140b1a..680aa85121a 100644 --- a/gcc/ChangeLog +++ b/gcc/ChangeLog @@ -1,3 +1,31 @@ +2019-11-14 Richard Sandiford + + * machmode.h (opt_machine_mode::operator==): New function. + (opt_machine_mode::operator!=): Likewise. + * tree-vectorizer.h (vec_info::vector_mode): Update comment. + (get_related_vectype_for_scalar_type): Delete. + (get_vectype_for_scalar_type_and_size): Declare. + * tree-vect-slp.c (vect_slp_bb_region): Print dump messages to say + whether analysis passed or failed, and with what vector modes. + Use related_vector_mode to check whether trying a particular + vector mode would be redundant with the autodetected mode, + and print a dump message if we decide to skip it. + * tree-vect-loop.c (vect_analyze_loop): Likewise. + (vect_create_epilog_for_reduction): Use + get_related_vectype_for_scalar_type instead of + get_vectype_for_scalar_type_and_size. + * tree-vect-stmts.c (get_vectype_for_scalar_type_and_size): Replace + with... + (get_related_vectype_for_scalar_type): ...this new function. + Take a starting/"prevailing" vector mode rather than a vector size. + Take an optional nunits argument, with the same meaning as for + related_vector_mode. Use related_vector_mode when not + auto-detecting a mode, falling back to mode_for_vector if no + target mode exists. + (get_vectype_for_scalar_type): Update accordingly. + (get_same_sized_vectype): Likewise. + * tree-vectorizer.c (get_vec_alignment_for_array_type): Likewise. + 2019-11-14 Richard Sandiford * tree-vect-stmts.c (vectorizable_call): Require the types diff --git a/gcc/machmode.h b/gcc/machmode.h index 6750833c2fe..a507ed66c3f 100644 --- a/gcc/machmode.h +++ b/gcc/machmode.h @@ -258,6 +258,9 @@ public: bool exists () const; template bool exists (U *) const; + bool operator== (const T &m) const { return m_mode == m; } + bool operator!= (const T &m) const { return m_mode != m; } + private: machine_mode m_mode; }; diff --git a/gcc/tree-vect-loop.c b/gcc/tree-vect-loop.c index 213d620ed2c..e60c159d11a 100644 --- a/gcc/tree-vect-loop.c +++ b/gcc/tree-vect-loop.c @@ -2435,6 +2435,17 @@ vect_analyze_loop (class loop *loop, vec_info_shared *shared) res = vect_analyze_loop_2 (loop_vinfo, fatal, &n_stmts); if (mode_i == 0) autodetected_vector_mode = loop_vinfo->vector_mode; + if (dump_enabled_p ()) + { + if (res) + dump_printf_loc (MSG_NOTE, vect_location, + "***** Analysis succeeded with vector mode %s\n", + GET_MODE_NAME (loop_vinfo->vector_mode)); + else + dump_printf_loc (MSG_NOTE, vect_location, + "***** Analysis failed with vector mode %s\n", + GET_MODE_NAME (loop_vinfo->vector_mode)); + } loop->aux = NULL; if (res) @@ -2501,9 +2512,22 @@ vect_analyze_loop (class loop *loop, vec_info_shared *shared) } if (mode_i < vector_modes.length () - && known_eq (GET_MODE_SIZE (vector_modes[mode_i]), - GET_MODE_SIZE (autodetected_vector_mode))) - mode_i += 1; + && VECTOR_MODE_P (autodetected_vector_mode) + && (related_vector_mode (vector_modes[mode_i], + GET_MODE_INNER (autodetected_vector_mode)) + == autodetected_vector_mode) + && (related_vector_mode (autodetected_vector_mode, + GET_MODE_INNER (vector_modes[mode_i])) + == vector_modes[mode_i])) + { + if (dump_enabled_p ()) + dump_printf_loc (MSG_NOTE, vect_location, + "***** Skipping vector mode %s, which would" + " repeat the analysis for %s\n", + GET_MODE_NAME (vector_modes[mode_i]), + GET_MODE_NAME (autodetected_vector_mode)); + mode_i += 1; + } if (mode_i == vector_modes.length () || autodetected_vector_mode == VOIDmode) @@ -4898,13 +4922,14 @@ vect_create_epilog_for_reduction (stmt_vec_info stmt_info, halves against each other. */ enum machine_mode mode1 = mode; tree stype = TREE_TYPE (vectype); - unsigned sz = tree_to_uhwi (TYPE_SIZE_UNIT (vectype)); - unsigned sz1 = sz; + unsigned nunits = TYPE_VECTOR_SUBPARTS (vectype).to_constant (); + unsigned nunits1 = nunits; if (!slp_reduc && (mode1 = targetm.vectorize.split_reduction (mode)) != mode) - sz1 = GET_MODE_SIZE (mode1).to_constant (); + nunits1 = GET_MODE_NUNITS (mode1).to_constant (); - tree vectype1 = get_vectype_for_scalar_type_and_size (stype, sz1); + tree vectype1 = get_related_vectype_for_scalar_type (TYPE_MODE (vectype), + stype, nunits1); reduce_with_shift = have_whole_vector_shift (mode1); if (!VECTOR_MODE_P (mode1)) reduce_with_shift = false; @@ -4918,11 +4943,13 @@ vect_create_epilog_for_reduction (stmt_vec_info stmt_info, /* First reduce the vector to the desired vector size we should do shift reduction on by combining upper and lower halves. */ new_temp = new_phi_result; - while (sz > sz1) + while (nunits > nunits1) { gcc_assert (!slp_reduc); - sz /= 2; - vectype1 = get_vectype_for_scalar_type_and_size (stype, sz); + nunits /= 2; + vectype1 = get_related_vectype_for_scalar_type (TYPE_MODE (vectype), + stype, nunits); + unsigned int bitsize = tree_to_uhwi (TYPE_SIZE (vectype1)); /* The target has to make sure we support lowpart/highpart extraction, either via direct vector extract or through @@ -4947,15 +4974,14 @@ vect_create_epilog_for_reduction (stmt_vec_info stmt_info, = gimple_build_assign (dst2, BIT_FIELD_REF, build3 (BIT_FIELD_REF, vectype1, new_temp, TYPE_SIZE (vectype1), - bitsize_int (sz * BITS_PER_UNIT))); + bitsize_int (bitsize))); gsi_insert_before (&exit_gsi, epilog_stmt, GSI_SAME_STMT); } else { /* Extract via punning to appropriately sized integer mode vector. */ - tree eltype = build_nonstandard_integer_type (sz * BITS_PER_UNIT, - 1); + tree eltype = build_nonstandard_integer_type (bitsize, 1); tree etype = build_vector_type (eltype, 2); gcc_assert (convert_optab_handler (vec_extract_optab, TYPE_MODE (etype), @@ -4984,7 +5010,7 @@ vect_create_epilog_for_reduction (stmt_vec_info stmt_info, = gimple_build_assign (tem, BIT_FIELD_REF, build3 (BIT_FIELD_REF, eltype, new_temp, TYPE_SIZE (eltype), - bitsize_int (sz * BITS_PER_UNIT))); + bitsize_int (bitsize))); gsi_insert_before (&exit_gsi, epilog_stmt, GSI_SAME_STMT); dst2 = make_ssa_name (vectype1); epilog_stmt = gimple_build_assign (dst2, VIEW_CONVERT_EXPR, diff --git a/gcc/tree-vect-slp.c b/gcc/tree-vect-slp.c index 3885d9cbe4a..1e00db5a326 100644 --- a/gcc/tree-vect-slp.c +++ b/gcc/tree-vect-slp.c @@ -3203,7 +3203,12 @@ vect_slp_bb_region (gimple_stmt_iterator region_begin, && dbg_cnt (vect_slp)) { if (dump_enabled_p ()) - dump_printf_loc (MSG_NOTE, vect_location, "SLPing BB part\n"); + { + dump_printf_loc (MSG_NOTE, vect_location, + "***** Analysis succeeded with vector mode" + " %s\n", GET_MODE_NAME (bb_vinfo->vector_mode)); + dump_printf_loc (MSG_NOTE, vect_location, "SLPing BB part\n"); + } bb_vinfo->shared->check_datarefs (); vect_schedule_slp (bb_vinfo); @@ -3223,6 +3228,13 @@ vect_slp_bb_region (gimple_stmt_iterator region_begin, vectorized = true; } + else + { + if (dump_enabled_p ()) + dump_printf_loc (MSG_NOTE, vect_location, + "***** Analysis failed with vector mode %s\n", + GET_MODE_NAME (bb_vinfo->vector_mode)); + } if (mode_i == 0) autodetected_vector_mode = bb_vinfo->vector_mode; @@ -3230,9 +3242,22 @@ vect_slp_bb_region (gimple_stmt_iterator region_begin, delete bb_vinfo; if (mode_i < vector_modes.length () - && known_eq (GET_MODE_SIZE (vector_modes[mode_i]), - GET_MODE_SIZE (autodetected_vector_mode))) - mode_i += 1; + && VECTOR_MODE_P (autodetected_vector_mode) + && (related_vector_mode (vector_modes[mode_i], + GET_MODE_INNER (autodetected_vector_mode)) + == autodetected_vector_mode) + && (related_vector_mode (autodetected_vector_mode, + GET_MODE_INNER (vector_modes[mode_i])) + == vector_modes[mode_i])) + { + if (dump_enabled_p ()) + dump_printf_loc (MSG_NOTE, vect_location, + "***** Skipping vector mode %s, which would" + " repeat the analysis for %s\n", + GET_MODE_NAME (vector_modes[mode_i]), + GET_MODE_NAME (autodetected_vector_mode)); + mode_i += 1; + } if (vectorized || mode_i == vector_modes.length () diff --git a/gcc/tree-vect-stmts.c b/gcc/tree-vect-stmts.c index 80f59accad7..36f832bb522 100644 --- a/gcc/tree-vect-stmts.c +++ b/gcc/tree-vect-stmts.c @@ -11138,18 +11138,28 @@ vect_remove_stores (stmt_vec_info first_stmt_info) } } -/* Function get_vectype_for_scalar_type_and_size. +/* If NUNITS is nonzero, return a vector type that contains NUNITS + elements of type SCALAR_TYPE, or null if the target doesn't support + such a type. - Returns the vector type corresponding to SCALAR_TYPE and SIZE as supported - by the target. */ + If NUNITS is zero, return a vector type that contains elements of + type SCALAR_TYPE, choosing whichever vector size the target prefers. + + If PREVAILING_MODE is VOIDmode, we have not yet chosen a vector mode + for this vectorization region and want to "autodetect" the best choice. + Otherwise, PREVAILING_MODE is a previously-chosen vector TYPE_MODE + and we want the new type to be interoperable with it. PREVAILING_MODE + in this case can be a scalar integer mode or a vector mode; when it + is a vector mode, the function acts like a tree-level version of + related_vector_mode. */ tree -get_vectype_for_scalar_type_and_size (tree scalar_type, poly_uint64 size) +get_related_vectype_for_scalar_type (machine_mode prevailing_mode, + tree scalar_type, poly_uint64 nunits) { tree orig_scalar_type = scalar_type; scalar_mode inner_mode; machine_mode simd_mode; - poly_uint64 nunits; tree vectype; if (!is_int_mode (TYPE_MODE (scalar_type), &inner_mode) @@ -11189,10 +11199,11 @@ get_vectype_for_scalar_type_and_size (tree scalar_type, poly_uint64 size) if (scalar_type == NULL_TREE) return NULL_TREE; - /* If no size was supplied use the mode the target prefers. Otherwise - lookup a vector mode of the specified size. */ - if (known_eq (size, 0U)) + /* If no prevailing mode was supplied, use the mode the target prefers. + Otherwise lookup a vector mode based on the prevailing mode. */ + if (prevailing_mode == VOIDmode) { + gcc_assert (known_eq (nunits, 0U)); simd_mode = targetm.vectorize.preferred_simd_mode (inner_mode); if (SCALAR_INT_MODE_P (simd_mode)) { @@ -11208,9 +11219,19 @@ get_vectype_for_scalar_type_and_size (tree scalar_type, poly_uint64 size) return NULL_TREE; } } - else if (!multiple_p (size, nbytes, &nunits) - || !mode_for_vector (inner_mode, nunits).exists (&simd_mode)) - return NULL_TREE; + else if (SCALAR_INT_MODE_P (prevailing_mode) + || !related_vector_mode (prevailing_mode, + inner_mode, nunits).exists (&simd_mode)) + { + /* Fall back to using mode_for_vector, mostly in the hope of being + able to use an integer mode. */ + if (known_eq (nunits, 0U) + && !multiple_p (GET_MODE_SIZE (prevailing_mode), nbytes, &nunits)) + return NULL_TREE; + + if (!mode_for_vector (inner_mode, nunits).exists (&simd_mode)) + return NULL_TREE; + } vectype = build_vector_type_for_mode (scalar_type, simd_mode); @@ -11238,9 +11259,8 @@ get_vectype_for_scalar_type_and_size (tree scalar_type, poly_uint64 size) tree get_vectype_for_scalar_type (vec_info *vinfo, tree scalar_type) { - tree vectype; - poly_uint64 vector_size = GET_MODE_SIZE (vinfo->vector_mode); - vectype = get_vectype_for_scalar_type_and_size (scalar_type, vector_size); + tree vectype = get_related_vectype_for_scalar_type (vinfo->vector_mode, + scalar_type); if (vectype && vinfo->vector_mode == VOIDmode) vinfo->vector_mode = TYPE_MODE (vectype); return vectype; @@ -11273,8 +11293,13 @@ get_same_sized_vectype (tree scalar_type, tree vector_type) if (VECT_SCALAR_BOOLEAN_TYPE_P (scalar_type)) return truth_type_for (vector_type); - return get_vectype_for_scalar_type_and_size - (scalar_type, GET_MODE_SIZE (TYPE_MODE (vector_type))); + poly_uint64 nunits; + if (!multiple_p (GET_MODE_SIZE (TYPE_MODE (vector_type)), + GET_MODE_SIZE (TYPE_MODE (scalar_type)), &nunits)) + return NULL_TREE; + + return get_related_vectype_for_scalar_type (TYPE_MODE (vector_type), + scalar_type, nunits); } /* Function vect_is_simple_use. diff --git a/gcc/tree-vectorizer.c b/gcc/tree-vectorizer.c index d6de78350e6..7be81a0b27f 100644 --- a/gcc/tree-vectorizer.c +++ b/gcc/tree-vectorizer.c @@ -1359,7 +1359,7 @@ get_vec_alignment_for_array_type (tree type) poly_uint64 array_size, vector_size; tree scalar_type = strip_array_types (type); - tree vectype = get_vectype_for_scalar_type_and_size (scalar_type, 0); + tree vectype = get_related_vectype_for_scalar_type (VOIDmode, scalar_type); if (!vectype || !poly_int_tree_p (TYPE_SIZE (type), &array_size) || !poly_int_tree_p (TYPE_SIZE (vectype), &vector_size) diff --git a/gcc/tree-vectorizer.h b/gcc/tree-vectorizer.h index f6efed1f863..fadc4d89d16 100644 --- a/gcc/tree-vectorizer.h +++ b/gcc/tree-vectorizer.h @@ -335,8 +335,9 @@ public: /* Cost data used by the target cost model. */ void *target_cost_data; - /* If we've chosen a vector size for this vectorization region, - this is one mode that has such a size, otherwise it is VOIDmode. */ + /* The argument we should pass to related_vector_mode when looking up + the vector mode for a scalar mode, or VOIDmode if we haven't yet + made any decisions about which vector modes to use. */ machine_mode vector_mode; private: @@ -1624,8 +1625,9 @@ extern bool vect_can_advance_ivs_p (loop_vec_info); extern void vect_update_inits_of_drs (loop_vec_info, tree, tree_code); /* In tree-vect-stmts.c. */ +extern tree get_related_vectype_for_scalar_type (machine_mode, tree, + poly_uint64 = 0); extern tree get_vectype_for_scalar_type (vec_info *, tree); -extern tree get_vectype_for_scalar_type_and_size (tree, poly_uint64); extern tree get_mask_type_for_scalar_type (vec_info *, tree); extern tree get_same_sized_vectype (tree, tree); extern bool vect_get_loop_mask_type (loop_vec_info);