Re: RFC: Add ADDR_EXPR lowering (PR tree-optimization/66718)

[Richard Biener <rguenther at suse dot de>]

On July 3, 2015 4:06:26 PM GMT+02:00, Jakub Jelinek <jakub@redhat.com> wrote:
>On Fri, Jul 03, 2015 at 03:41:29PM +0200, Richard Biener wrote:
>> > The fallout (at least on x86_64) is surprisingly small, i.e. none,
>just
>> > gcc.dg/vect/pr59984.c test (using -fopenmp-simd) ICEs, but that is
>due
>> > to a bug in the vectorizer.  Jakub has a patch and knows the
>details.
>> > As the test shows, we're now able to vectorize ADDR_EXPR of
>non-invariants
>> > (that was the motivation of this pass).
>
>Here is the fix for that.
>
>The problem is that for simd clone calls, if they have void return
>type,
>STMT_VINFO_VECTYPE is NULL.  If vectorize_simd_clone_call succeeds,
>that is fine, but if it doesn't, we can fall into all the other
>vectorizable_* functions, and some of them compute some variables
>IMHO prematurely.  It doesn't make sense to compute nunits/ncopies
>etc. if stmt isn't even an assignment etc.
>So, this patch adjusts the few routines that had this problem,
>so that we check is_gimple_assign and gimple_assign_rhs_code or
>whatever
>is the quick GIMPLE test those functions use to find if stmt is of
>interest
>to them, and only when it is, compute whatever they need later.
>As NULL STMT_VINFO_VECTYPE can happen only for calls, all these
>functions
>don't ICE anymore.
>
>Ok for trunk if it passes bootstrap/regtest?

OK.

Thanks,
Richard.

>In the pr59984.c testcase, with Marek's patch and this patch, one loop
>in
>test is already vectorized (the ICE was on the other one), I'll work on
>recognizing multiples of GOMP_SIMD_LANE () as linear next, so that we
>vectorize also the loop with bar.  Without Marek's patch we weren't
>vectorizing any of the two loops.
>
>2015-07-03  Jakub Jelinek  <jakub@redhat.com>
>
>	PR tree-optimization/66718
>	* tree-vect-stmts.c (vectorizable_assignment, vectorizable_store,
>	vectorizable_load, vectorizable_condition): Move vectype,
>	nunits, ncopies computation after checking what kind of statement
>	stmt is.
>
>--- gcc/tree-vect-stmts.c.jj	2015-06-30 14:08:45.000000000 +0200
>+++ gcc/tree-vect-stmts.c	2015-07-03 14:06:28.843573210 +0200
>@@ -4043,13 +4043,11 @@ vectorizable_assignment (gimple stmt, gi
>   tree scalar_dest;
>   tree op;
>   stmt_vec_info stmt_info = vinfo_for_stmt (stmt);
>-  tree vectype = STMT_VINFO_VECTYPE (stmt_info);
>   loop_vec_info loop_vinfo = STMT_VINFO_LOOP_VINFO (stmt_info);
>   tree new_temp;
>   tree def;
>   gimple def_stmt;
>enum vect_def_type dt[2] = {vect_unknown_def_type,
>vect_unknown_def_type};
>-  unsigned int nunits = TYPE_VECTOR_SUBPARTS (vectype);
>   int ncopies;
>   int i, j;
>   vec<tree> vec_oprnds = vNULL;
>@@ -4060,16 +4058,6 @@ vectorizable_assignment (gimple stmt, gi
>   enum tree_code code;
>   tree vectype_in;
> 
>-  /* Multiple types in SLP are handled by creating the appropriate
>number of
>-     vectorized stmts for each SLP node. Hence, NCOPIES is always 1 in
>-     case of SLP.  */
>-  if (slp_node || PURE_SLP_STMT (stmt_info))
>-    ncopies = 1;
>-  else
>-    ncopies = LOOP_VINFO_VECT_FACTOR (loop_vinfo) / nunits;
>-
>-  gcc_assert (ncopies >= 1);
>-
>   if (!STMT_VINFO_RELEVANT_P (stmt_info) && !bb_vinfo)
>     return false;
> 
>@@ -4095,6 +4083,19 @@ vectorizable_assignment (gimple stmt, gi
>   if (code == VIEW_CONVERT_EXPR)
>     op = TREE_OPERAND (op, 0);
> 
>+  tree vectype = STMT_VINFO_VECTYPE (stmt_info);
>+  unsigned int nunits = TYPE_VECTOR_SUBPARTS (vectype);
>+
>+  /* Multiple types in SLP are handled by creating the appropriate
>number of
>+     vectorized stmts for each SLP node. Hence, NCOPIES is always 1 in
>+     case of SLP.  */
>+  if (slp_node || PURE_SLP_STMT (stmt_info))
>+    ncopies = 1;
>+  else
>+    ncopies = LOOP_VINFO_VECT_FACTOR (loop_vinfo) / nunits;
>+
>+  gcc_assert (ncopies >= 1);
>+
>   if (!vect_is_simple_use_1 (op, stmt, loop_vinfo, bb_vinfo,
> 			     &def_stmt, &def, &dt[0], &vectype_in))
>     {
>@@ -5006,7 +5007,6 @@ vectorizable_store (gimple stmt, gimple_
>   tree vec_oprnd = NULL_TREE;
>   stmt_vec_info stmt_info = vinfo_for_stmt (stmt);
>struct data_reference *dr = STMT_VINFO_DATA_REF (stmt_info), *first_dr
>= NULL;
>-  tree vectype = STMT_VINFO_VECTYPE (stmt_info);
>   tree elem_type;
>   loop_vec_info loop_vinfo = STMT_VINFO_LOOP_VINFO (stmt_info);
>   struct loop *loop = NULL;
>@@ -5020,7 +5020,6 @@ vectorizable_store (gimple stmt, gimple_
>   tree dataref_ptr = NULL_TREE;
>   tree dataref_offset = NULL_TREE;
>   gimple ptr_incr = NULL;
>-  unsigned int nunits = TYPE_VECTOR_SUBPARTS (vectype);
>   int ncopies;
>   int j;
>   gimple next_stmt, first_stmt = NULL;
>@@ -5039,28 +5038,6 @@ vectorizable_store (gimple stmt, gimple_
>   bb_vec_info bb_vinfo = STMT_VINFO_BB_VINFO (stmt_info);
>   tree aggr_type;
> 
>-  if (loop_vinfo)
>-    loop = LOOP_VINFO_LOOP (loop_vinfo);
>-
>-  /* Multiple types in SLP are handled by creating the appropriate
>number of
>-     vectorized stmts for each SLP node. Hence, NCOPIES is always 1 in
>-     case of SLP.  */
>-  if (slp || PURE_SLP_STMT (stmt_info))
>-    ncopies = 1;
>-  else
>-    ncopies = LOOP_VINFO_VECT_FACTOR (loop_vinfo) / nunits;
>-
>-  gcc_assert (ncopies >= 1);
>-
>-  /* FORNOW. This restriction should be relaxed.  */
>-  if (loop && nested_in_vect_loop_p (loop, stmt) && ncopies > 1)
>-    {
>-      if (dump_enabled_p ())
>-        dump_printf_loc (MSG_MISSED_OPTIMIZATION, vect_location,
>-                         "multiple types in nested loop.\n");
>-      return false;
>-    }
>-
>   if (!STMT_VINFO_RELEVANT_P (stmt_info) && !bb_vinfo)
>     return false;
> 
>@@ -5086,6 +5063,32 @@ vectorizable_store (gimple stmt, gimple_
>     return false;
> 
>   gcc_assert (gimple_assign_single_p (stmt));
>+
>+  tree vectype = STMT_VINFO_VECTYPE (stmt_info);
>+  unsigned int nunits = TYPE_VECTOR_SUBPARTS (vectype);
>+
>+  if (loop_vinfo)
>+    loop = LOOP_VINFO_LOOP (loop_vinfo);
>+
>+  /* Multiple types in SLP are handled by creating the appropriate
>number of
>+     vectorized stmts for each SLP node. Hence, NCOPIES is always 1 in
>+     case of SLP.  */
>+  if (slp || PURE_SLP_STMT (stmt_info))
>+    ncopies = 1;
>+  else
>+    ncopies = LOOP_VINFO_VECT_FACTOR (loop_vinfo) / nunits;
>+
>+  gcc_assert (ncopies >= 1);
>+
>+  /* FORNOW. This restriction should be relaxed.  */
>+  if (loop && nested_in_vect_loop_p (loop, stmt) && ncopies > 1)
>+    {
>+      if (dump_enabled_p ())
>+        dump_printf_loc (MSG_MISSED_OPTIMIZATION, vect_location,
>+                         "multiple types in nested loop.\n");
>+      return false;
>+    }
>+
>   op = gimple_assign_rhs1 (stmt);
>   if (!vect_is_simple_use (op, stmt, loop_vinfo, bb_vinfo, &def_stmt,
> 			   &def, &dt))
>@@ -5834,7 +5837,6 @@ vectorizable_load (gimple stmt, gimple_s
>   struct loop *containing_loop = (gimple_bb (stmt))->loop_father;
>   bool nested_in_vect_loop = false;
>struct data_reference *dr = STMT_VINFO_DATA_REF (stmt_info), *first_dr
>= NULL;
>-  tree vectype = STMT_VINFO_VECTYPE (stmt_info);
>   tree elem_type;
>   tree new_temp;
>   machine_mode mode;
>@@ -5844,7 +5846,6 @@ vectorizable_load (gimple stmt, gimple_s
>   tree dataref_ptr = NULL_TREE;
>   tree dataref_offset = NULL_TREE;
>   gimple ptr_incr = NULL;
>-  int nunits = TYPE_VECTOR_SUBPARTS (vectype);
>   int ncopies;
>   int i, j, group_size = -1, group_gap_adj;
>   tree msq = NULL_TREE, lsq;
>@@ -5872,6 +5873,37 @@ vectorizable_load (gimple stmt, gimple_s
>   int gather_scale = 1;
>   enum vect_def_type gather_dt = vect_unknown_def_type;
> 
>+  if (!STMT_VINFO_RELEVANT_P (stmt_info) && !bb_vinfo)
>+    return false;
>+
>+  if (STMT_VINFO_DEF_TYPE (stmt_info) != vect_internal_def)
>+    return false;
>+
>+  /* Is vectorizable load? */
>+  if (!is_gimple_assign (stmt))
>+    return false;
>+
>+  scalar_dest = gimple_assign_lhs (stmt);
>+  if (TREE_CODE (scalar_dest) != SSA_NAME)
>+    return false;
>+
>+  code = gimple_assign_rhs_code (stmt);
>+  if (code != ARRAY_REF
>+      && code != BIT_FIELD_REF
>+      && code != INDIRECT_REF
>+      && code != COMPONENT_REF
>+      && code != IMAGPART_EXPR
>+      && code != REALPART_EXPR
>+      && code != MEM_REF
>+      && TREE_CODE_CLASS (code) != tcc_declaration)
>+    return false;
>+
>+  if (!STMT_VINFO_DATA_REF (stmt_info))
>+    return false;
>+
>+  tree vectype = STMT_VINFO_VECTYPE (stmt_info);
>+  int nunits = TYPE_VECTOR_SUBPARTS (vectype);
>+
>   if (loop_vinfo)
>     {
>       loop = LOOP_VINFO_LOOP (loop_vinfo);
>@@ -5914,34 +5946,6 @@ vectorizable_load (gimple stmt, gimple_s
>       return false;
>     }
> 
>-  if (!STMT_VINFO_RELEVANT_P (stmt_info) && !bb_vinfo)
>-    return false;
>-
>-  if (STMT_VINFO_DEF_TYPE (stmt_info) != vect_internal_def)
>-    return false;
>-
>-  /* Is vectorizable load? */
>-  if (!is_gimple_assign (stmt))
>-    return false;
>-
>-  scalar_dest = gimple_assign_lhs (stmt);
>-  if (TREE_CODE (scalar_dest) != SSA_NAME)
>-    return false;
>-
>-  code = gimple_assign_rhs_code (stmt);
>-  if (code != ARRAY_REF
>-      && code != BIT_FIELD_REF
>-      && code != INDIRECT_REF
>-      && code != COMPONENT_REF
>-      && code != IMAGPART_EXPR
>-      && code != REALPART_EXPR
>-      && code != MEM_REF
>-      && TREE_CODE_CLASS (code) != tcc_declaration)
>-    return false;
>-
>-  if (!STMT_VINFO_DATA_REF (stmt_info))
>-    return false;
>-
>   elem_type = TREE_TYPE (vectype);
>   mode = TYPE_MODE (vectype);
> 
>@@ -7021,7 +7025,6 @@ vectorizable_condition (gimple stmt, gim
>   tree vec_dest = NULL_TREE;
>   tree cond_expr, then_clause, else_clause;
>   stmt_vec_info stmt_info = vinfo_for_stmt (stmt);
>-  tree vectype = STMT_VINFO_VECTYPE (stmt_info);
>   tree comp_vectype = NULL_TREE;
>   tree vec_cond_lhs = NULL_TREE, vec_cond_rhs = NULL_TREE;
>   tree vec_then_clause = NULL_TREE, vec_else_clause = NULL_TREE;
>@@ -7030,7 +7033,6 @@ vectorizable_condition (gimple stmt, gim
>   loop_vec_info loop_vinfo = STMT_VINFO_LOOP_VINFO (stmt_info);
>   tree def;
>   enum vect_def_type dt, dts[4];
>-  int nunits = TYPE_VECTOR_SUBPARTS (vectype);
>   int ncopies;
>   enum tree_code code;
>   stmt_vec_info prev_stmt_info = NULL;
>@@ -7042,15 +7044,6 @@ vectorizable_condition (gimple stmt, gim
>   vec<tree> vec_oprnds3 = vNULL;
>   tree vec_cmp_type;
> 
>-  if (slp_node || PURE_SLP_STMT (stmt_info))
>-    ncopies = 1;
>-  else
>-    ncopies = LOOP_VINFO_VECT_FACTOR (loop_vinfo) / nunits;
>-
>-  gcc_assert (ncopies >= 1);
>-  if (reduc_index && ncopies > 1)
>-    return false; /* FORNOW */
>-
>   if (reduc_index && STMT_SLP_TYPE (stmt_info))
>     return false;
> 
>@@ -7080,6 +7073,18 @@ vectorizable_condition (gimple stmt, gim
>   if (code != COND_EXPR)
>     return false;
> 
>+  tree vectype = STMT_VINFO_VECTYPE (stmt_info);
>+  int nunits = TYPE_VECTOR_SUBPARTS (vectype);
>+
>+  if (slp_node || PURE_SLP_STMT (stmt_info))
>+    ncopies = 1;
>+  else
>+    ncopies = LOOP_VINFO_VECT_FACTOR (loop_vinfo) / nunits;
>+
>+  gcc_assert (ncopies >= 1);
>+  if (reduc_index && ncopies > 1)
>+    return false; /* FORNOW */
>+
>   cond_expr = gimple_assign_rhs1 (stmt);
>   then_clause = gimple_assign_rhs2 (stmt);
>   else_clause = gimple_assign_rhs3 (stmt);
>
>
>	Jakub