Hi Richard,

On 06/11/15 11:09, Richard Biener wrote:
On Fri, 6 Nov 2015, Richard Biener wrote:

The following patch makes the BB vectorizer not only handle BB heads
(until the first stmt with a data reference it cannot handle) but
arbitrary regions in a BB separated by such stmts.

This improves the number of BB vectorizations from 469 to 556
in a quick test on SPEC CPU 2006 with -Ofast on x86_64 and
1x400.perlbench 1x410.bwaves 1x416.gamess 1x450.soplex 1x453.povray
1x481.wrf failing both patched and unpatched (have to update my
config used for such experiments it seems ...)

Bootstrapped and tested on x86_64-unknown-linux-gnu, aarch64 cross built.

I'm currently re-testing for a cosmetic change I made when writing
the changelog.

I expected (and there are) some issues with compile-time.  Left
is unpatched and right is patched.

'403.gcc': 00:00:54 (54)                      | '403.gcc': 00:00:55 (55)
'483.xalancbmk': 00:02:20 (140)       | '483.xalancbmk': 00:02:24 (144)
'416.gamess': 00:02:36 (156)          | '416.gamess': 00:02:37 (157)
'435.gromacs': 00:00:18 (18)          | '435.gromacs': 00:00:19 (19)
'447.dealII': 00:01:31 (91)           | '447.dealII': 00:01:33 (93)
'453.povray': 00:04:54 (294)          | '453.povray': 00:08:54 (534)
'454.calculix': 00:00:34 (34)         | '454.calculix': 00:00:52 (52)
'481.wrf': 00:01:57 (117)                     | '481.wrf': 00:01:59 (119)

other benchmarks are unchanged.  I'm double-checking now that a followup
patch I have which re-implements BB vectorization dependence checking
fixes this (that's the only quadraticness I know of).
Fixes all but

'453.povray': 00:04:54 (294)          | '453.povray': 00:06:46 (406)

Note that povray is currently suffering from PR 68198

Kyrill


it even improves compile-time on some:

'464.h264ref': 00:00:26 (26)          | '464.h264ref': 00:00:21 (21)

it also increases the number of vectorized BBs to 722.

Needs some work still though.

Richard.

Richard.

2015-11-06  Richard Biener  <rguent...@suse.de>

        * tree-vectorizer.h (struct _bb_vec_info): Add region_begin/end
        members.
        (vect_stmt_in_region_p): Declare.
        * tree-vect-slp.c (new_bb_vec_info): Work on a region.
        (destroy_bb_vec_info): Likewise.
        (vect_bb_slp_scalar_cost): Use vect_stmt_in_region_p.
        (vect_get_and_check_slp_defs): Likewise.
        (vect_slp_analyze_bb_1): Refactor to make it work on sub-BBs.
        (vect_slp_bb): Likewise.
        * tree-vect-patterns.c (vect_same_loop_or_bb_p): Implement
        in terms of vect_stmt_in_region_p.
        (vect_pattern_recog): Iterate over the BB region.
        * tree-vect-stmts.c (vect_is_simple_use): Use vect_stmt_in_region_p.
        * tree-vectorizer.c (vect_stmt_in_region_p): New function.
        (pass_slp_vectorize::execute): Initialize all stmt UIDs to -1.

        * config/i386/i386.c: Include gimple-iterator.h.
        * config/aarch64/aarch64.c: Likewise.

        * gcc.dg/vect/bb-slp-38.c: New testcase.

Index: gcc/tree-vectorizer.h
===================================================================
*** gcc/tree-vectorizer.h.orig  2015-11-05 09:52:00.640227178 +0100
--- gcc/tree-vectorizer.h       2015-11-05 13:20:58.385786476 +0100
*************** nested_in_vect_loop_p (struct loop *loop
*** 390,395 ****
--- 390,397 ----
   typedef struct _bb_vec_info : public vec_info
   {
     basic_block bb;
+   gimple_stmt_iterator region_begin;
+   gimple_stmt_iterator region_end;
   } *bb_vec_info;
#define BB_VINFO_BB(B) (B)->bb
*************** void vect_pattern_recog (vec_info *);
*** 1085,1089 ****
--- 1087,1092 ----
   /* In tree-vectorizer.c.  */
   unsigned vectorize_loops (void);
   void vect_destroy_datarefs (vec_info *);
+ bool vect_stmt_in_region_p (vec_info *, gimple *);
#endif /* GCC_TREE_VECTORIZER_H */
Index: gcc/tree-vect-slp.c
===================================================================
*** gcc/tree-vect-slp.c.orig    2015-11-05 09:52:00.640227178 +0100
--- gcc/tree-vect-slp.c 2015-11-06 10:22:56.707880233 +0100
*************** vect_get_and_check_slp_defs (vec_info *v
*** 209,215 ****
     unsigned int i, number_of_oprnds;
     gimple *def_stmt;
     enum vect_def_type dt = vect_uninitialized_def;
-   struct loop *loop = NULL;
     bool pattern = false;
     slp_oprnd_info oprnd_info;
     int first_op_idx = 1;
--- 209,214 ----
*************** vect_get_and_check_slp_defs (vec_info *v
*** 218,226 ****
     bool first = stmt_num == 0;
     bool second = stmt_num == 1;
- if (is_a <loop_vec_info> (vinfo))
-     loop = LOOP_VINFO_LOOP (as_a <loop_vec_info> (vinfo));
-
     if (is_gimple_call (stmt))
       {
         number_of_oprnds = gimple_call_num_args (stmt);
--- 217,222 ----
*************** again:
*** 276,286 ****
            from the pattern.  Check that all the stmts of the node are in the
            pattern.  */
         if (def_stmt && gimple_bb (def_stmt)
!           && ((is_a <loop_vec_info> (vinfo)
!              && flow_bb_inside_loop_p (loop, gimple_bb (def_stmt)))
!             || (is_a <bb_vec_info> (vinfo)
!                 && gimple_bb (def_stmt) == as_a <bb_vec_info> (vinfo)->bb
!                 && gimple_code (def_stmt) != GIMPLE_PHI))
             && vinfo_for_stmt (def_stmt)
             && STMT_VINFO_IN_PATTERN_P (vinfo_for_stmt (def_stmt))
          && !STMT_VINFO_RELEVANT (vinfo_for_stmt (def_stmt))
--- 272,278 ----
            from the pattern.  Check that all the stmts of the node are in the
            pattern.  */
         if (def_stmt && gimple_bb (def_stmt)
!           && vect_stmt_in_region_p (vinfo, def_stmt)
             && vinfo_for_stmt (def_stmt)
             && STMT_VINFO_IN_PATTERN_P (vinfo_for_stmt (def_stmt))
          && !STMT_VINFO_RELEVANT (vinfo_for_stmt (def_stmt))
*************** vect_detect_hybrid_slp (loop_vec_info lo
*** 2076,2091 ****
      stmt_vec_info structs for all the stmts in it.  */
static bb_vec_info
! new_bb_vec_info (basic_block bb)
   {
     bb_vec_info res = NULL;
     gimple_stmt_iterator gsi;
res = (bb_vec_info) xcalloc (1, sizeof (struct _bb_vec_info));
     res->kind = vec_info::bb;
     BB_VINFO_BB (res) = bb;
! for (gsi = gsi_start_bb (bb); !gsi_end_p (gsi); gsi_next (&gsi))
       {
         gimple *stmt = gsi_stmt (gsi);
         gimple_set_uid (stmt, 0);
--- 2068,2088 ----
      stmt_vec_info structs for all the stmts in it.  */
static bb_vec_info
! new_bb_vec_info (gimple_stmt_iterator region_begin,
!                gimple_stmt_iterator region_end)
   {
+   basic_block bb = gsi_bb (region_begin);
     bb_vec_info res = NULL;
     gimple_stmt_iterator gsi;
res = (bb_vec_info) xcalloc (1, sizeof (struct _bb_vec_info));
     res->kind = vec_info::bb;
     BB_VINFO_BB (res) = bb;
+   res->region_begin = region_begin;
+   res->region_end = region_end;
! for (gsi = region_begin; gsi_stmt (gsi) != gsi_stmt (region_end);
!        gsi_next (&gsi))
       {
         gimple *stmt = gsi_stmt (gsi);
         gimple_set_uid (stmt, 0);
*************** destroy_bb_vec_info (bb_vec_info bb_vinf
*** 2118,2124 ****
bb = BB_VINFO_BB (bb_vinfo); ! for (si = gsi_start_bb (bb); !gsi_end_p (si); gsi_next (&si))
       {
         gimple *stmt = gsi_stmt (si);
         stmt_vec_info stmt_info = vinfo_for_stmt (stmt);
--- 2115,2122 ----
bb = BB_VINFO_BB (bb_vinfo); ! for (si = bb_vinfo->region_begin;
!        gsi_stmt (si) != gsi_stmt (bb_vinfo->region_end); gsi_next (&si))
       {
         gimple *stmt = gsi_stmt (si);
         stmt_vec_info stmt_info = vinfo_for_stmt (stmt);
*************** destroy_bb_vec_info (bb_vec_info bb_vinf
*** 2126,2131 ****
--- 2124,2132 ----
         if (stmt_info)
           /* Free stmt_vec_info.  */
           free_stmt_vec_info (stmt);
+
+       /* Reset region marker.  */
+       gimple_set_uid (stmt, -1);
       }
vect_destroy_datarefs (bb_vinfo);
*************** vect_bb_slp_scalar_cost (basic_block bb,
*** 2247,2254 ****
          gimple *use_stmt;
          FOR_EACH_IMM_USE_STMT (use_stmt, use_iter, DEF_FROM_PTR (def_p))
            if (!is_gimple_debug (use_stmt)
!               && (gimple_code (use_stmt) == GIMPLE_PHI
!                   || gimple_bb (use_stmt) != bb
                    || !STMT_VINFO_VECTORIZABLE (vinfo_for_stmt (use_stmt))))
              {
                (*life)[i] = true;
--- 2248,2255 ----
          gimple *use_stmt;
          FOR_EACH_IMM_USE_STMT (use_stmt, use_iter, DEF_FROM_PTR (def_p))
            if (!is_gimple_debug (use_stmt)
!               && (! vect_stmt_in_region_p (vinfo_for_stmt (stmt)->vinfo,
!                                            use_stmt)
                    || !STMT_VINFO_VECTORIZABLE (vinfo_for_stmt (use_stmt))))
              {
                (*life)[i] = true;
*************** vect_bb_vectorization_profitable_p (bb_v
*** 2327,2366 ****
   /* Check if the basic block can be vectorized.  */
static bb_vec_info
! vect_slp_analyze_bb_1 (basic_block bb)
   {
     bb_vec_info bb_vinfo;
     vec<slp_instance> slp_instances;
     slp_instance instance;
     int i;
     int min_vf = 2;
-   unsigned n_stmts = 0;
! bb_vinfo = new_bb_vec_info (bb);
     if (!bb_vinfo)
       return NULL;
! /* Gather all data references in the basic-block. */
!
!   for (gimple_stmt_iterator gsi = gsi_start_bb (bb);
!        !gsi_end_p (gsi); gsi_next (&gsi))
!     {
!       gimple *stmt = gsi_stmt (gsi);
!       if (is_gimple_debug (stmt))
!       continue;
!       ++n_stmts;
!       if (!find_data_references_in_stmt (NULL, stmt,
!                                        &BB_VINFO_DATAREFS (bb_vinfo)))
!       {
!         /* Mark the rest of the basic-block as unvectorizable.  */
!         for (; !gsi_end_p (gsi); gsi_next (&gsi))
!           {
!             stmt = gsi_stmt (gsi);
!             STMT_VINFO_VECTORIZABLE (vinfo_for_stmt (stmt)) = false;
!           }
!         break;
!       }
!     }
/* Analyze the data references. */ --- 2328,2358 ----
   /* Check if the basic block can be vectorized.  */
static bb_vec_info
! vect_slp_analyze_bb_1 (gimple_stmt_iterator region_begin,
!                      gimple_stmt_iterator region_end,
!                      vec<data_reference_p> datarefs, int n_stmts)
   {
     bb_vec_info bb_vinfo;
     vec<slp_instance> slp_instances;
     slp_instance instance;
     int i;
     int min_vf = 2;
! if (n_stmts > PARAM_VALUE (PARAM_SLP_MAX_INSNS_IN_BB))
!     {
!       if (dump_enabled_p ())
!       dump_printf_loc (MSG_MISSED_OPTIMIZATION, vect_location,
!                        "not vectorized: too many instructions in "
!                        "basic block.\n");
!       free_data_refs (datarefs);
!       return NULL;
!     }
!
!   bb_vinfo = new_bb_vec_info (region_begin, region_end);
     if (!bb_vinfo)
       return NULL;
! BB_VINFO_DATAREFS (bb_vinfo) = datarefs; /* Analyze the data references. */ *************** vect_slp_analyze_bb_1 (basic_block bb)
*** 2438,2445 ****
       }
/* Mark all the statements that we do not want to vectorize. */
!   for (gimple_stmt_iterator gsi = gsi_start_bb (BB_VINFO_BB (bb_vinfo));
!        !gsi_end_p (gsi); gsi_next (&gsi))
       {
         stmt_vec_info vinfo = vinfo_for_stmt (gsi_stmt (gsi));
         if (STMT_SLP_TYPE (vinfo) != pure_slp)
--- 2430,2437 ----
       }
/* Mark all the statements that we do not want to vectorize. */
!   for (gimple_stmt_iterator gsi = bb_vinfo->region_begin;
!        gsi_stmt (gsi) != gsi_stmt (bb_vinfo->region_end); gsi_next (&gsi))
       {
         stmt_vec_info vinfo = vinfo_for_stmt (gsi_stmt (gsi));
         if (STMT_SLP_TYPE (vinfo) != pure_slp)
*************** bool
*** 2509,2585 ****
   vect_slp_bb (basic_block bb)
   {
     bb_vec_info bb_vinfo;
-   int insns = 0;
     gimple_stmt_iterator gsi;
     unsigned int vector_sizes;
if (dump_enabled_p ())
       dump_printf_loc (MSG_NOTE, vect_location, "===vect_slp_analyze_bb===\n");
- for (gsi = gsi_start_bb (bb); !gsi_end_p (gsi); gsi_next (&gsi))
-     {
-       gimple *stmt = gsi_stmt (gsi);
-       if (!is_gimple_debug (stmt)
-           && !gimple_nop_p (stmt)
-           && gimple_code (stmt) != GIMPLE_LABEL)
-         insns++;
-       if (gimple_location (stmt) != UNKNOWN_LOCATION)
-       vect_location = gimple_location (stmt);
-     }
-
-   if (insns > PARAM_VALUE (PARAM_SLP_MAX_INSNS_IN_BB))
-     {
-       if (dump_enabled_p ())
-         dump_printf_loc (MSG_MISSED_OPTIMIZATION, vect_location,
-                        "not vectorized: too many instructions in "
-                        "basic block.\n");
-
-       return false;
-     }
-
     /* Autodetect first vector size we try.  */
     current_vector_size = 0;
     vector_sizes = targetm.vectorize.autovectorize_vector_sizes ();
while (1)
       {
!       bb_vinfo = vect_slp_analyze_bb_1 (bb);
!       if (bb_vinfo)
        {
!         if (!dbg_cnt (vect_slp))
!           {
!             destroy_bb_vec_info (bb_vinfo);
!             return false;
!           }
if (dump_enabled_p ())
!           dump_printf_loc (MSG_NOTE, vect_location, "SLPing BB\n");
vect_schedule_slp (bb_vinfo); if (dump_enabled_p ())
            dump_printf_loc (MSG_NOTE, vect_location,
!                            "BASIC BLOCK VECTORIZED\n");
destroy_bb_vec_info (bb_vinfo); ! return true;
        }
! destroy_bb_vec_info (bb_vinfo); vector_sizes &= ~current_vector_size;
!       if (vector_sizes == 0
!           || current_vector_size == 0)
!         return false;
! /* Try the next biggest vector size. */
!       current_vector_size = 1 << floor_log2 (vector_sizes);
!       if (dump_enabled_p ())
!         dump_printf_loc (MSG_NOTE, vect_location,
!                        "***** Re-trying analysis with "
!                        "vector size %d\n", current_vector_size);
       }
   }
--- 2501,2605 ----
   vect_slp_bb (basic_block bb)
   {
     bb_vec_info bb_vinfo;
     gimple_stmt_iterator gsi;
     unsigned int vector_sizes;
+   bool any_vectorized = false;
if (dump_enabled_p ())
       dump_printf_loc (MSG_NOTE, vect_location, "===vect_slp_analyze_bb===\n");
/* Autodetect first vector size we try. */
     current_vector_size = 0;
     vector_sizes = targetm.vectorize.autovectorize_vector_sizes ();
+ gsi = gsi_start_bb (bb);
+
     while (1)
       {
!       if (gsi_end_p (gsi))
!       break;
!
!       gimple_stmt_iterator region_begin = gsi;
!       vec<data_reference_p> datarefs = vNULL;
!       int insns = 0;
!
!       for (; !gsi_end_p (gsi); gsi_next (&gsi))
        {
!         gimple *stmt = gsi_stmt (gsi);
!         if (is_gimple_debug (stmt))
!           continue;
!         insns++;
!
!         if (gimple_location (stmt) != UNKNOWN_LOCATION)
!           vect_location = gimple_location (stmt);
!
!         if (!find_data_references_in_stmt (NULL, stmt, &datarefs))
!           break;
!       }
!
!       /* Skip leading unhandled stmts.  */
!       if (gsi_stmt (region_begin) == gsi_stmt (gsi))
!       {
!         gsi_next (&gsi);
!         continue;
!       }
!
!       gimple_stmt_iterator region_end = gsi;
+ bool vectorized = false;
+       bb_vinfo = vect_slp_analyze_bb_1 (region_begin, region_end,
+                                       datarefs, insns);
+       if (bb_vinfo
+         && dbg_cnt (vect_slp))
+       {
          if (dump_enabled_p ())
!           dump_printf_loc (MSG_NOTE, vect_location, "SLPing BB part\n");
vect_schedule_slp (bb_vinfo); if (dump_enabled_p ())
            dump_printf_loc (MSG_NOTE, vect_location,
!                            "basic block part vectorized\n");
destroy_bb_vec_info (bb_vinfo); ! vectorized = true;
        }
+       else
+       destroy_bb_vec_info (bb_vinfo);
! any_vectorized |= vectorized; vector_sizes &= ~current_vector_size;
!       if (vectorized
!         || vector_sizes == 0
!         || current_vector_size == 0)
!       {
!         if (gsi_end_p (region_end))
!           break;
!
!         /* Skip the unhandled stmt.  */
!         gsi_next (&gsi);
!
!         /* And reset vector sizes.  */
!         current_vector_size = 0;
!         vector_sizes = targetm.vectorize.autovectorize_vector_sizes ();
!       }
!       else
!       {
!         /* Try the next biggest vector size.  */
!         current_vector_size = 1 << floor_log2 (vector_sizes);
!         if (dump_enabled_p ())
!           dump_printf_loc (MSG_NOTE, vect_location,
!                            "***** Re-trying analysis with "
!                            "vector size %d\n", current_vector_size);
! /* Start over. */
!         gsi = region_begin;
!       }
       }
+
+   return any_vectorized;
   }
Index: gcc/tree-vect-patterns.c
===================================================================
*** gcc/tree-vect-patterns.c.orig       2015-11-05 09:52:00.640227178 +0100
--- gcc/tree-vect-patterns.c    2015-11-05 13:25:46.060011765 +0100
*************** static bool
*** 107,133 ****
   vect_same_loop_or_bb_p (gimple *stmt1, gimple *stmt2)
   {
     stmt_vec_info stmt_vinfo = vinfo_for_stmt (stmt1);
!   loop_vec_info loop_vinfo = STMT_VINFO_LOOP_VINFO (stmt_vinfo);
!   bb_vec_info bb_vinfo = STMT_VINFO_BB_VINFO (stmt_vinfo);
!
!   if (!gimple_bb (stmt2))
!     return false;
!
!   if (loop_vinfo)
!     {
!       struct loop *loop = LOOP_VINFO_LOOP (loop_vinfo);
!       if (!flow_bb_inside_loop_p (loop, gimple_bb (stmt2)))
!       return false;
!     }
!   else
!     {
!       if (gimple_bb (stmt2) != BB_VINFO_BB (bb_vinfo)
!         || gimple_code (stmt2) == GIMPLE_PHI)
!       return false;
!     }
!
!   gcc_assert (vinfo_for_stmt (stmt2));
!   return true;
   }
/* If the LHS of DEF_STMT has a single use, and that statement is
--- 107,113 ----
   vect_same_loop_or_bb_p (gimple *stmt1, gimple *stmt2)
   {
     stmt_vec_info stmt_vinfo = vinfo_for_stmt (stmt1);
!   return vect_stmt_in_region_p (stmt_vinfo->vinfo, stmt2);
   }
/* If the LHS of DEF_STMT has a single use, and that statement is
*************** vect_pattern_recog (vec_info *vinfo)
*** 3611,3643 ****
         loop = LOOP_VINFO_LOOP (loop_vinfo);
         bbs = LOOP_VINFO_BBS (loop_vinfo);
         nbbs = loop->num_nodes;
       }
     else
       {
!       bbs = &as_a <bb_vec_info> (vinfo)->bb;
!       nbbs = 1;
!     }
!
!   /* Scan through the loop stmts, applying the pattern recognition
!      functions starting at each stmt visited:  */
!   for (i = 0; i < nbbs; i++)
!     {
!       basic_block bb = bbs[i];
!       for (si = gsi_start_bb (bb); !gsi_end_p (si); gsi_next (&si))
!         {
!         if (is_a <bb_vec_info> (vinfo)
!             && (stmt = gsi_stmt (si))
              && vinfo_for_stmt (stmt)
              && !STMT_VINFO_VECTORIZABLE (vinfo_for_stmt (stmt)))
!          continue;
! /* Scan over all generic vect_recog_xxx_pattern functions. */
!           for (j = 0; j < NUM_PATTERNS; j++)
!             {
              vect_recog_func = vect_vect_recog_func_ptrs[j];
              vect_pattern_recog_1 (vect_recog_func, si,
                                    &stmts_to_replace);
!             }
!         }
       }
   }
--- 3591,3632 ----
         loop = LOOP_VINFO_LOOP (loop_vinfo);
         bbs = LOOP_VINFO_BBS (loop_vinfo);
         nbbs = loop->num_nodes;
+
+       /* Scan through the loop stmts, applying the pattern recognition
+        functions starting at each stmt visited:  */
+       for (i = 0; i < nbbs; i++)
+       {
+         basic_block bb = bbs[i];
+         for (si = gsi_start_bb (bb); !gsi_end_p (si); gsi_next (&si))
+           {
+             /* Scan over all generic vect_recog_xxx_pattern functions.  */
+             for (j = 0; j < NUM_PATTERNS; j++)
+               {
+                 vect_recog_func = vect_vect_recog_func_ptrs[j];
+                 vect_pattern_recog_1 (vect_recog_func, si,
+                                       &stmts_to_replace);
+               }
+           }
+       }
       }
     else
       {
!       bb_vec_info bb_vinfo = as_a <bb_vec_info> (vinfo);
!       for (si = bb_vinfo->region_begin;
!          gsi_stmt (si) != gsi_stmt (bb_vinfo->region_end); gsi_next (&si))
!       {
!         if ((stmt = gsi_stmt (si))
              && vinfo_for_stmt (stmt)
              && !STMT_VINFO_VECTORIZABLE (vinfo_for_stmt (stmt)))
!           continue;
! /* Scan over all generic vect_recog_xxx_pattern functions. */
!         for (j = 0; j < NUM_PATTERNS; j++)
!           {
              vect_recog_func = vect_vect_recog_func_ptrs[j];
              vect_pattern_recog_1 (vect_recog_func, si,
                                    &stmts_to_replace);
!           }
!       }
       }
   }
Index: gcc/config/i386/i386.c
===================================================================
*** gcc/config/i386/i386.c.orig 2015-11-05 09:52:42.239687133 +0100
--- gcc/config/i386/i386.c      2015-11-05 11:09:09.451774562 +0100
*************** along with GCC; see the file COPYING3.
*** 64,69 ****
--- 64,70 ----
   #include "context.h"
   #include "pass_manager.h"
   #include "target-globals.h"
+ #include "gimple-iterator.h"
   #include "tree-vectorizer.h"
   #include "shrink-wrap.h"
   #include "builtins.h"
Index: gcc/testsuite/gcc.dg/vect/bb-slp-38.c
===================================================================
*** /dev/null   1970-01-01 00:00:00.000000000 +0000
--- gcc/testsuite/gcc.dg/vect/bb-slp-38.c       2015-11-05 14:00:48.177644327 
+0100
***************
*** 0 ****
--- 1,44 ----
+ /* { dg-require-effective-target vect_int } */
+
+ #include "tree-vect.h"
+
+ extern void abort (void);
+
+ int a[8], b[8];
+ int x;
+
+ void __attribute__((noinline,noclone))
+ bar (void)
+ {
+   x = 1;
+ }
+
+ void __attribute__((noinline,noclone))
+ foo(void)
+ {
+   a[0] = b[0];
+   a[1] = b[0];
+   a[2] = b[3];
+   a[3] = b[3];
+   bar ();
+   a[4] = b[4];
+   a[5] = b[7];
+   a[6] = b[4];
+   a[7] = b[7];
+ }
+
+ int main()
+ {
+   int i;
+   check_vect ();
+   for (i = 0; i < 8; ++i)
+     b[i] = i;
+   foo ();
+   if (a[0] != 0 || a[1] != 0 || a[2] != 3 || a[3] != 3
+       || a[4] != 4 || a[5] != 7 || a[6] != 4 || a[7] != 7)
+     abort ();
+   return 0;
+ }
+
+ /* { dg-final { scan-tree-dump "basic block vectorized" "slp2" { target 
vect_perm } } } */
+ /* { dg-final { scan-tree-dump-times "basic block part vectorized" 2 "slp2" { 
target vect_perm } } } */
Index: gcc/tree-vect-stmts.c
===================================================================
*** gcc/tree-vect-stmts.c.orig  2015-11-02 12:37:11.074249388 +0100
--- gcc/tree-vect-stmts.c       2015-11-05 13:29:21.413423692 +0100
*************** vect_is_simple_use (tree operand, vec_in
*** 8196,8207 ****
         dump_gimple_stmt (MSG_NOTE, TDF_SLIM, *def_stmt, 0);
       }
! basic_block bb = gimple_bb (*def_stmt);
!   if ((is_a <loop_vec_info> (vinfo)
!        && !flow_bb_inside_loop_p (as_a <loop_vec_info> (vinfo)->loop, bb))
!       || (is_a <bb_vec_info> (vinfo)
!         && (bb != as_a <bb_vec_info> (vinfo)->bb
!             || gimple_code (*def_stmt) == GIMPLE_PHI)))
       *dt = vect_external_def;
     else
       {
--- 8196,8202 ----
         dump_gimple_stmt (MSG_NOTE, TDF_SLIM, *def_stmt, 0);
       }
! if (! vect_stmt_in_region_p (vinfo, *def_stmt))
       *dt = vect_external_def;
     else
       {
Index: gcc/tree-vectorizer.c
===================================================================
*** gcc/tree-vectorizer.c.orig  2015-11-04 09:23:53.724687806 +0100
--- gcc/tree-vectorizer.c       2015-11-05 13:55:08.299817570 +0100
*************** vect_destroy_datarefs (vec_info *vinfo)
*** 350,355 ****
--- 350,382 ----
   }
+ /* Return whether STMT is inside the region we try to vectorize. */
+
+ bool
+ vect_stmt_in_region_p (vec_info *vinfo, gimple *stmt)
+ {
+   if (!gimple_bb (stmt))
+     return false;
+
+   if (loop_vec_info loop_vinfo = dyn_cast <loop_vec_info> (vinfo))
+     {
+       struct loop *loop = LOOP_VINFO_LOOP (loop_vinfo);
+       if (!flow_bb_inside_loop_p (loop, gimple_bb (stmt)))
+       return false;
+     }
+   else
+     {
+       bb_vec_info bb_vinfo = as_a <bb_vec_info> (vinfo);
+       if (gimple_bb (stmt) != BB_VINFO_BB (bb_vinfo)
+         || gimple_uid (stmt) == -1U
+         || gimple_code (stmt) == GIMPLE_PHI)
+       return false;
+     }
+
+   return true;
+ }
+
+
   /* If LOOP has been versioned during ifcvt, return the internal call
      guarding it.  */
*************** pass_slp_vectorize::execute (function *f
*** 692,697 ****
--- 719,732 ----
         scev_initialize ();
       }
+ /* Mark all stmts as not belonging to the current region. */
+   FOR_EACH_BB_FN (bb, fun)
+     {
+       for (gimple_stmt_iterator gsi = gsi_start_bb (bb); !gsi_end_p (gsi);
+          gsi_next (&gsi))
+       gimple_set_uid (gsi_stmt (gsi), -1);
+     }
+
     init_stmt_vec_info_vec ();
FOR_EACH_BB_FN (bb, fun)
Index: gcc/config/aarch64/aarch64.c
===================================================================
*** gcc/config/aarch64/aarch64.c.orig   2015-10-28 11:22:25.290823112 +0100
--- gcc/config/aarch64/aarch64.c        2015-11-06 10:24:21.539818027 +0100
***************
*** 52,57 ****
--- 52,58 ----
   #include "params.h"
   #include "gimplify.h"
   #include "dwarf2.h"
+ #include "gimple-iterator.h"
   #include "tree-vectorizer.h"
   #include "aarch64-cost-tables.h"
   #include "dumpfile.h"


Reply via email to