vect: Cost adjacent vector loads/stores together [PR111784]

As comments[1][2], this patch is to change the costing way
on some adjacent vector loads/stores from costing one by
one to costing them together with the total number once.

It helps to fix the exposed regression PR111784 on aarch64,
as aarch64 specific costing could make different decisions
according to the different costing ways (counting with total
number vs. counting one by one).  Based on a reduced test
case from PR111784, only considering vec_num can fix the
regression already, but vector loads/stores in regard to
ncopies are also adjacent accesses, so they are considered
as well.

btw, this patch leaves the costing on dr_explicit_realign
and dr_explicit_realign_optimized alone to make it simple.
The costing way change can cause the differences for them
since there is one costing depending on targetm.vectorize.
builtin_mask_for_load and it's costed according to the
calling times.  IIUC, these two dr_alignment_support are
mainly used for old Power? (only having 16 bytes aligned
vector load/store but no unaligned vector load/store).

[1] https://gcc.gnu.org/pipermail/gcc-patches/2023-September/630742.html
[2] https://gcc.gnu.org/pipermail/gcc-patches/2023-September/630744.html

	PR tree-optimization/111784

gcc/ChangeLog:

	* tree-vect-stmts.cc (vectorizable_store): Adjust costing way for
	adjacent vector stores, by costing them with the total number
	rather than costing them one by one.
	(vectorizable_load): Adjust costing way for adjacent vector
	loads, by costing them with the total number rather than costing
	them one by one.

diff --git a/gcc/tree-vect-stmts.cc b/gcc/tree-vect-stmts.cc
index 337b24c51f953667ad4146002052ce40f34b7529..99ba75e98c0d185edd78c7b8b9947618d18576cc 100644 (file)
--- a/gcc/tree-vect-stmts.cc
+++ b/gcc/tree-vect-stmts.cc
@@ -8626,6 +8626,9 @@ vectorizable_store (vec_info *vinfo,
       alias_off = build_int_cst (ref_type, 0);
       stmt_vec_info next_stmt_info = first_stmt_info;
       auto_vec<tree> vec_oprnds (ncopies);
+      /* For costing some adjacent vector stores, we'd like to cost with
+        the total number of them once instead of cost each one by one. */
+      unsigned int n_adjacent_stores = 0;
       for (g = 0; g < group_size; g++)
        {
          running_off = offvar;
@@ -8683,10 +8686,7 @@ vectorizable_store (vec_info *vinfo,
                         store to avoid ICE like 110776.  */
                      if (VECTOR_TYPE_P (ltype)
                          && known_ne (TYPE_VECTOR_SUBPARTS (ltype), 1U))
-                       vect_get_store_cost (vinfo, stmt_info, 1,
-                                            alignment_support_scheme,
-                                            misalignment, &inside_cost,
-                                            cost_vec);
+                       n_adjacent_stores++;
                      else
                        inside_cost
                          += record_stmt_cost (cost_vec, 1, scalar_store,
@@ -8743,11 +8743,18 @@ vectorizable_store (vec_info *vinfo,
            break;
        }
 
-      if (costing_p && dump_enabled_p ())
-       dump_printf_loc (MSG_NOTE, vect_location,
-                        "vect_model_store_cost: inside_cost = %d, "
-                        "prologue_cost = %d .\n",
-                        inside_cost, prologue_cost);
+      if (costing_p)
+       {
+         if (n_adjacent_stores > 0)
+           vect_get_store_cost (vinfo, stmt_info, n_adjacent_stores,
+                                alignment_support_scheme, misalignment,
+                                &inside_cost, cost_vec);
+         if (dump_enabled_p ())
+           dump_printf_loc (MSG_NOTE, vect_location,
+                            "vect_model_store_cost: inside_cost = %d, "
+                            "prologue_cost = %d .\n",
+                            inside_cost, prologue_cost);
+       }
 
       return true;
     }
@@ -8854,6 +8861,9 @@ vectorizable_store (vec_info *vinfo,
     {
       gcc_assert (!slp && grouped_store);
       unsigned inside_cost = 0, prologue_cost = 0;
+      /* For costing some adjacent vector stores, we'd like to cost with
+        the total number of them once instead of cost each one by one. */
+      unsigned int n_adjacent_stores = 0;
       for (j = 0; j < ncopies; j++)
        {
          gimple *new_stmt;
@@ -8919,10 +8929,7 @@ vectorizable_store (vec_info *vinfo,
 
          if (costing_p)
            {
-             for (i = 0; i < vec_num; i++)
-               vect_get_store_cost (vinfo, stmt_info, 1,
-                                    alignment_support_scheme, misalignment,
-                                    &inside_cost, cost_vec);
+             n_adjacent_stores += vec_num;
              continue;
            }
 
@@ -9012,11 +9019,18 @@ vectorizable_store (vec_info *vinfo,
          STMT_VINFO_VEC_STMTS (stmt_info).safe_push (new_stmt);
        }
 
-      if (costing_p && dump_enabled_p ())
-       dump_printf_loc (MSG_NOTE, vect_location,
-                        "vect_model_store_cost: inside_cost = %d, "
-                        "prologue_cost = %d .\n",
-                        inside_cost, prologue_cost);
+      if (costing_p)
+       {
+         if (n_adjacent_stores > 0)
+           vect_get_store_cost (vinfo, stmt_info, n_adjacent_stores,
+                                alignment_support_scheme, misalignment,
+                                &inside_cost, cost_vec);
+         if (dump_enabled_p ())
+           dump_printf_loc (MSG_NOTE, vect_location,
+                            "vect_model_store_cost: inside_cost = %d, "
+                            "prologue_cost = %d .\n",
+                            inside_cost, prologue_cost);
+       }
 
       return true;
     }
@@ -9235,6 +9249,9 @@ vectorizable_store (vec_info *vinfo,
              || memory_access_type == VMAT_CONTIGUOUS_REVERSE);
 
   unsigned inside_cost = 0, prologue_cost = 0;
+  /* For costing some adjacent vector stores, we'd like to cost with
+     the total number of them once instead of cost each one by one. */
+  unsigned int n_adjacent_stores = 0;
   auto_vec<tree> result_chain (group_size);
   auto_vec<tree, 1> vec_oprnds;
   for (j = 0; j < ncopies; j++)
@@ -9396,9 +9413,7 @@ vectorizable_store (vec_info *vinfo,
 
          if (costing_p)
            {
-             vect_get_store_cost (vinfo, stmt_info, 1,
-                                  alignment_support_scheme, misalignment,
-                                  &inside_cost, cost_vec);
+             n_adjacent_stores++;
 
              if (!slp)
                {
@@ -9568,6 +9583,11 @@ vectorizable_store (vec_info *vinfo,
 
   if (costing_p)
     {
+      if (n_adjacent_stores > 0)
+       vect_get_store_cost (vinfo, stmt_info, n_adjacent_stores,
+                            alignment_support_scheme, misalignment,
+                            &inside_cost, cost_vec);
+
       /* When vectorizing a store into the function result assign
         a penalty if the function returns in a multi-register location.
         In this case we assume we'll end up with having to spill the
@@ -10275,6 +10295,9 @@ vectorizable_load (vec_info *vinfo,
       unsigned HOST_WIDE_INT
        elsz = tree_to_uhwi (TYPE_SIZE_UNIT (TREE_TYPE (vectype)));
       unsigned int n_groups = 0;
+      /* For costing some adjacent vector loads, we'd like to cost with
+        the total number of them once instead of cost each one by one. */
+      unsigned int n_adjacent_loads = 0;
       for (j = 0; j < ncopies; j++)
        {
          if (nloads > 1 && !costing_p)
@@ -10288,10 +10311,7 @@ vectorizable_load (vec_info *vinfo,
                     avoid ICE, see PR110776.  */
                  if (VECTOR_TYPE_P (ltype)
                      && memory_access_type != VMAT_ELEMENTWISE)
-                   vect_get_load_cost (vinfo, stmt_info, 1,
-                                       alignment_support_scheme, misalignment,
-                                       false, &inside_cost, nullptr, cost_vec,
-                                       cost_vec, true);
+                   n_adjacent_loads++;
                  else
                    inside_cost += record_stmt_cost (cost_vec, 1, scalar_load,
                                                     stmt_info, 0, vect_body);
@@ -10385,11 +10405,19 @@ vectorizable_load (vec_info *vinfo,
                                          false, &n_perms);
        }
 
-      if (costing_p && dump_enabled_p ())
-       dump_printf_loc (MSG_NOTE, vect_location,
-                        "vect_model_load_cost: inside_cost = %u, "
-                        "prologue_cost = 0 .\n",
-                        inside_cost);
+      if (costing_p)
+       {
+         if (n_adjacent_loads > 0)
+           vect_get_load_cost (vinfo, stmt_info, n_adjacent_loads,
+                               alignment_support_scheme, misalignment, false,
+                               &inside_cost, nullptr, cost_vec, cost_vec,
+                               true);
+         if (dump_enabled_p ())
+           dump_printf_loc (MSG_NOTE, vect_location,
+                            "vect_model_load_cost: inside_cost = %u, "
+                            "prologue_cost = 0 .\n",
+                            inside_cost);
+       }
 
       return true;
     }
@@ -10694,6 +10722,9 @@ vectorizable_load (vec_info *vinfo,
       gcc_assert (grouped_load && !slp);
 
       unsigned int inside_cost = 0, prologue_cost = 0;
+      /* For costing some adjacent vector loads, we'd like to cost with
+        the total number of them once instead of cost each one by one. */
+      unsigned int n_adjacent_loads = 0;
       for (j = 0; j < ncopies; j++)
        {
          if (costing_p)
@@ -10725,9 +10756,7 @@ vectorizable_load (vec_info *vinfo,
                                          true);
                    }
                }
-             vect_get_load_cost (vinfo, stmt_info, 1, alignment_support_scheme,
-                                 misalignment, false, &inside_cost,
-                                 &prologue_cost, cost_vec, cost_vec, true);
+             n_adjacent_loads++;
              continue;
            }
 
@@ -10829,11 +10858,19 @@ vectorizable_load (vec_info *vinfo,
          *vec_stmt = STMT_VINFO_VEC_STMTS (stmt_info)[0];
        }
 
-      if (costing_p && dump_enabled_p ())
-       dump_printf_loc (MSG_NOTE, vect_location,
-                        "vect_model_load_cost: inside_cost = %u, "
-                        "prologue_cost = %u .\n",
-                        inside_cost, prologue_cost);
+      if (costing_p)
+       {
+         if (n_adjacent_loads > 0)
+           vect_get_load_cost (vinfo, stmt_info, n_adjacent_loads,
+                               alignment_support_scheme, misalignment, false,
+                               &inside_cost, &prologue_cost, cost_vec,
+                               cost_vec, true);
+         if (dump_enabled_p ())
+           dump_printf_loc (MSG_NOTE, vect_location,
+                            "vect_model_load_cost: inside_cost = %u, "
+                            "prologue_cost = %u .\n",
+                            inside_cost, prologue_cost);
+       }
 
       return true;
     }
@@ -11177,6 +11214,9 @@ vectorizable_load (vec_info *vinfo,
 
   poly_uint64 group_elt = 0;
   unsigned int inside_cost = 0, prologue_cost = 0;
+  /* For costing some adjacent vector loads, we'd like to cost with
+     the total number of them once instead of cost each one by one. */
+  unsigned int n_adjacent_loads = 0;
   for (j = 0; j < ncopies; j++)
     {
       /* 1. Create the vector or array pointer update chain.  */
@@ -11571,10 +11611,18 @@ vectorizable_load (vec_info *vinfo,
                  || memory_access_type == VMAT_CONTIGUOUS_REVERSE
                  || (memory_access_type == VMAT_CONTIGUOUS_PERMUTE
                      && (!grouped_load || first_stmt_info_p)))
-               vect_get_load_cost (vinfo, stmt_info, 1,
-                                   alignment_support_scheme, misalignment,
-                                   add_realign_cost, &inside_cost,
-                                   &prologue_cost, cost_vec, cost_vec, true);
+               {
+                 /* Leave realign cases alone to keep them simple.  */
+                 if (alignment_support_scheme == dr_explicit_realign_optimized
+                     || alignment_support_scheme == dr_explicit_realign)
+                   vect_get_load_cost (vinfo, stmt_info, 1,
+                                       alignment_support_scheme, misalignment,
+                                       add_realign_cost, &inside_cost,
+                                       &prologue_cost, cost_vec, cost_vec,
+                                       true);
+                 else
+                   n_adjacent_loads++;
+               }
            }
          else
            {
@@ -11745,6 +11793,11 @@ vectorizable_load (vec_info *vinfo,
       gcc_assert (memory_access_type == VMAT_CONTIGUOUS
                  || memory_access_type == VMAT_CONTIGUOUS_REVERSE
                  || memory_access_type == VMAT_CONTIGUOUS_PERMUTE);
+      if (n_adjacent_loads > 0)
+       vect_get_load_cost (vinfo, stmt_info, n_adjacent_loads,
+                           alignment_support_scheme, misalignment, false,
+                           &inside_cost, &prologue_cost, cost_vec, cost_vec,
+                           true);
       if (dump_enabled_p ())
        dump_printf_loc (MSG_NOTE, vect_location,
                         "vect_model_load_cost: inside_cost = %u, "