re PR rtl-optimization/57193 (suboptimal register allocation for SSE registers)

2018-02-09  Vladimir Makarov  <vmakarov@redhat.com>

	PR rtl-optimization/57193
	* ira-color.c (struct allocno_color_data): Add member
	conflict_allocno_hard_prefs.
	(update_conflict_allocno_hard_prefs): New.
	(bucket_allocno_compare_func): Add a preference based on
	conflict_allocno_hard_prefs.
	(push_allocno_to_stack): Update conflict_allocno_hard_prefs.
	(color_allocnos): Remove a dead code.  Initiate
	conflict_allocno_hard_prefs.  Call update_costs_from_prefs.

2018-02-09  Vladimir Makarov  <vmakarov@redhat.com>

	PR rtl-optimization/57193
	* gcc.target/i386/57193.c: New.

From-SVN: r257537

diff --git a/gcc/ChangeLog b/gcc/ChangeLog
index 4ac7fff372a918e646c3df7c63d5d734983c218b..043972eab936cead95fe835111fdb166fc10c417 100644 (file)
--- a/gcc/ChangeLog
+++ b/gcc/ChangeLog
@@ -1,3 +1,15 @@
+2018-02-09  Vladimir Makarov  <vmakarov@redhat.com>
+
+       PR rtl-optimization/57193
+       * ira-color.c (struct allocno_color_data): Add member
+       conflict_allocno_hard_prefs.
+       (update_conflict_allocno_hard_prefs): New.
+       (bucket_allocno_compare_func): Add a preference based on
+       conflict_allocno_hard_prefs.
+       (push_allocno_to_stack): Update conflict_allocno_hard_prefs.
+       (color_allocnos): Remove a dead code.  Initiate
+       conflict_allocno_hard_prefs.  Call update_costs_from_prefs.
+
 2018-02-09  Jakub Jelinek  <jakub@redhat.com>
 
        PR target/84226

diff --git a/gcc/ira-color.c b/gcc/ira-color.c
index 26b18f3b15de80f0f67f25435b0f285a5d70503f..7087fb99959d4c7944b2c6cbd93ddfda8294102b 100644 (file)
--- a/gcc/ira-color.c
+++ b/gcc/ira-color.c
@@ -112,6 +112,9 @@ struct allocno_color_data
      available for the allocno allocation.  It is number of the
      profitable hard regs.  */
   int available_regs_num;
+  /* Sum of frequencies of hard register preferences of all
+     conflicting allocnos which are not the coloring stack yet.  */
+  int conflict_allocno_hard_prefs;
   /* Allocnos in a bucket (used in coloring) chained by the following
      two members.  */
   ira_allocno_t next_bucket_allocno;
@@ -1435,6 +1438,36 @@ update_costs_from_copies (ira_allocno_t allocno, bool decr_p, bool record_p)
   update_costs_from_allocno (allocno, hard_regno, 1, decr_p, record_p);
 }
 
+/* Update conflict_allocno_hard_prefs of allocnos conflicting with
+   ALLOCNO.  */
+static void
+update_conflict_allocno_hard_prefs (ira_allocno_t allocno)
+{
+  int l, nr = ALLOCNO_NUM_OBJECTS (allocno);
+  
+  for (l = 0; l < nr; l++)
+    {
+      ira_object_t conflict_obj, obj = ALLOCNO_OBJECT (allocno, l);
+      ira_object_conflict_iterator oci;
+      
+      FOR_EACH_OBJECT_CONFLICT (obj, conflict_obj, oci)
+       {
+         ira_allocno_t conflict_a = OBJECT_ALLOCNO (conflict_obj);
+         allocno_color_data_t conflict_data = ALLOCNO_COLOR_DATA (conflict_a);
+         ira_pref_t pref;
+
+         if (!(hard_reg_set_intersect_p
+               (ALLOCNO_COLOR_DATA (allocno)->profitable_hard_regs,
+                conflict_data->profitable_hard_regs)))
+           continue;
+         for (pref = ALLOCNO_PREFS (allocno);
+              pref != NULL;
+              pref = pref->next_pref)
+           conflict_data->conflict_allocno_hard_prefs += pref->freq;
+       }
+    }
+}
+
 /* Restore costs of allocnos connected to ALLOCNO by copies as it was
    before updating costs of these allocnos from given allocno.  This
    is a wise thing to do as if given allocno did not get an expected
@@ -2223,7 +2256,7 @@ bucket_allocno_compare_func (const void *v1p, const void *v2p)
 {
   ira_allocno_t a1 = *(const ira_allocno_t *) v1p;
   ira_allocno_t a2 = *(const ira_allocno_t *) v2p;
-  int diff, freq1, freq2, a1_num, a2_num;
+  int diff, freq1, freq2, a1_num, a2_num, pref1, pref2;
   ira_allocno_t t1 = ALLOCNO_COLOR_DATA (a1)->first_thread_allocno;
   ira_allocno_t t2 = ALLOCNO_COLOR_DATA (a2)->first_thread_allocno;
   int cl1 = ALLOCNO_CLASS (a1), cl2 = ALLOCNO_CLASS (a2);
@@ -2253,6 +2286,11 @@ bucket_allocno_compare_func (const void *v1p, const void *v2p)
   a2_num = ALLOCNO_COLOR_DATA (a2)->available_regs_num;
   if ((diff = a2_num - a1_num) != 0)
     return diff;
+  /* Push allocnos with minimal conflict_allocno_hard_prefs first.  */
+  pref1 = ALLOCNO_COLOR_DATA (a1)->conflict_allocno_hard_prefs;
+  pref2 = ALLOCNO_COLOR_DATA (a2)->conflict_allocno_hard_prefs;
+  if ((diff = pref1 - pref2) != 0)
+    return diff;
   return ALLOCNO_NUM (a2) - ALLOCNO_NUM (a1);
 }
 
@@ -2339,7 +2377,8 @@ delete_allocno_from_bucket (ira_allocno_t allocno, ira_allocno_t *bucket_ptr)
 /* Put allocno A onto the coloring stack without removing it from its
    bucket.  Pushing allocno to the coloring stack can result in moving
    conflicting allocnos from the uncolorable bucket to the colorable
-   one.  */
+   one.  Update conflict_allocno_hard_prefs of the conflicting
+   allocnos which are not on stack yet.  */
 static void
 push_allocno_to_stack (ira_allocno_t a)
 {
@@ -2369,15 +2408,19 @@ push_allocno_to_stack (ira_allocno_t a)
       FOR_EACH_OBJECT_CONFLICT (obj, conflict_obj, oci)
        {
          ira_allocno_t conflict_a = OBJECT_ALLOCNO (conflict_obj);
-         
+         ira_pref_t pref;
+
          conflict_data = ALLOCNO_COLOR_DATA (conflict_a);
-         if (conflict_data->colorable_p
-             || ! conflict_data->in_graph_p
+         if (! conflict_data->in_graph_p
              || ALLOCNO_ASSIGNED_P (conflict_a)
              || !(hard_reg_set_intersect_p
                   (ALLOCNO_COLOR_DATA (a)->profitable_hard_regs,
                    conflict_data->profitable_hard_regs)))
            continue;
+         for (pref = ALLOCNO_PREFS (a); pref != NULL; pref = pref->next_pref)
+           conflict_data->conflict_allocno_hard_prefs -= pref->freq;
+         if (conflict_data->colorable_p)
+           continue;
          ira_assert (bitmap_bit_p (coloring_allocno_bitmap,
                                    ALLOCNO_NUM (conflict_a)));
          if (update_left_conflict_sizes_p (conflict_a, a, size))
@@ -3048,21 +3091,12 @@ color_allocnos (void)
   setup_profitable_hard_regs ();
   EXECUTE_IF_SET_IN_BITMAP (coloring_allocno_bitmap, 0, i, bi)
     {
-      int l, nr;
-      HARD_REG_SET conflict_hard_regs;
       allocno_color_data_t data;
       ira_pref_t pref, next_pref;
 
       a = ira_allocnos[i];
-      nr = ALLOCNO_NUM_OBJECTS (a);
-      CLEAR_HARD_REG_SET (conflict_hard_regs);
-      for (l = 0; l < nr; l++)
-       {
-         ira_object_t obj = ALLOCNO_OBJECT (a, l);
-         IOR_HARD_REG_SET (conflict_hard_regs,
-                           OBJECT_CONFLICT_HARD_REGS (obj));
-       }
       data = ALLOCNO_COLOR_DATA (a);
+      data->conflict_allocno_hard_prefs = 0;
       for (pref = ALLOCNO_PREFS (a); pref != NULL; pref = next_pref)
        {
          next_pref = pref->next_pref;
@@ -3072,6 +3106,7 @@ color_allocnos (void)
            ira_remove_pref (pref);
        }
     }
+  
   if (flag_ira_algorithm == IRA_ALGORITHM_PRIORITY)
     {
       n = 0;
@@ -3134,6 +3169,7 @@ color_allocnos (void)
            {
              ALLOCNO_COLOR_DATA (a)->in_graph_p = true;
              update_costs_from_prefs (a);
+             update_conflict_allocno_hard_prefs (a);
            }
          else
            {

diff --git a/gcc/testsuite/ChangeLog b/gcc/testsuite/ChangeLog
index 64018db71656f90d5c7f1c0f9219517b48f4df26..9d80ab85aa487e912f597ed6d68e816e33f7c2b1 100644 (file)
--- a/gcc/testsuite/ChangeLog
+++ b/gcc/testsuite/ChangeLog
@@ -1,3 +1,8 @@
+2018-02-09  Vladimir Makarov  <vmakarov@redhat.com>
+
+       PR rtl-optimization/57193
+       * gcc.target/i386/57193.c: New.
+
 2018-02-09  Jakub Jelinek  <jakub@redhat.com>
 
        PR target/84226

diff --git a/gcc/testsuite/gcc.target/i386/pr57193.c b/gcc/testsuite/gcc.target/i386/pr57193.c
new file mode 100644 (file)
index 0000000..70e2612
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/pr57193.c
@@ -0,0 +1,16 @@
+/* { dg-do compile { target { ! ia32 } } } */
+/* { dg-options "-O2" } */
+/* { dg-final { scan-assembler-times "movdqa" 2 } } */
+
+#include <emmintrin.h>
+
+void test1(const __m128i* in1, const __m128i* in2, __m128i* out,
+           __m128i f, __m128i zero)
+{
+       __m128i c = _mm_avg_epu8(*in1, *in2);
+       __m128i l = _mm_unpacklo_epi8(c, zero);
+       __m128i h = _mm_unpackhi_epi8(c, zero);
+       __m128i m = _mm_mulhi_epu16(l, f);
+       __m128i n = _mm_mulhi_epu16(h, f);
+       *out = _mm_packus_epi16(m, n);
+}