DSE: Use the constant store source if possible

RTL DSE tracks redundant constant stores within a basic block.  When RTL
loop invariant motion hoists a constant initialization out of the loop
into a separate basic block, the constant store value becomes unknown
within the original basic block.  When recording store for RTL DSE, check
if the source register is set only once to a constant by a non-partial
unconditional load.  If yes, record the constant as the constant store
source.  It eliminates unrolled zero stores after memset 0 in a loop
where a vector register is used as the zero store source.

gcc/

	PR rtl-optimization/105638
	* df-core.cc (df_find_single_def_src): Moved and renamed from
	find_single_def_src in loop-iv.cc.  Change the argument to rtx
	and use rtx_equal_p.  Return null for partial or conditional
	defs.
	* df.h (df_find_single_def_src): New prototype.
	* dse.cc (record_store): Use the constant source if the source
	register is set only once.
	* loop-iv.cc (find_single_def_src): Moved to df-core.cc.
	(replace_single_def_regs): Replace find_single_def_src with
	df_find_single_def_src.

gcc/testsuite/

	PR rtl-optimization/105638
	* g++.target/i386/pr105638.C: New test.

diff --git a/gcc/df-core.cc b/gcc/df-core.cc
index a901b84878f73a4e9b65b4dce6ecc3b9420d1c40..e3a56bf6a9ff6ef942908c7db3620060d4d26831 100644 (file)
--- a/gcc/df-core.cc
+++ b/gcc/df-core.cc
@@ -2009,6 +2009,47 @@ df_reg_used (rtx_insn *insn, rtx reg)
   return df_find_use (insn, reg) != NULL;
 }
 
+/* If REG has a single definition, return its known value, otherwise return
+   null.  */
+
+rtx
+df_find_single_def_src (rtx reg)
+{
+  rtx src = NULL_RTX;
+
+  /* Don't look through unbounded number of single definition REG copies,
+     there might be loops for sources with uninitialized variables.  */
+  for (int cnt = 0; cnt < 128; cnt++)
+    {
+      df_ref adef = DF_REG_DEF_CHAIN (REGNO (reg));
+      if (adef == NULL || DF_REF_NEXT_REG (adef) != NULL
+         || DF_REF_IS_ARTIFICIAL (adef)
+         || (DF_REF_FLAGS (adef)
+             & (DF_REF_PARTIAL | DF_REF_CONDITIONAL)))
+       return NULL_RTX;
+
+      rtx set = single_set (DF_REF_INSN (adef));
+      if (set == NULL || !rtx_equal_p (SET_DEST (set), reg))
+       return NULL_RTX;
+
+      rtx note = find_reg_equal_equiv_note (DF_REF_INSN (adef));
+      if (note && function_invariant_p (XEXP (note, 0)))
+       return XEXP (note, 0);
+      src = SET_SRC (set);
+
+      if (REG_P (src))
+       {
+         reg = src;
+         continue;
+       }
+      break;
+    }
+  if (!function_invariant_p (src))
+    return NULL_RTX;
+
+  return src;
+}
+
 \f
 /*----------------------------------------------------------------------------
    Debugging and printing functions.

diff --git a/gcc/df.h b/gcc/df.h
index bd329205d08c55623540e05fa9e5d937c2321373..71e249ad20a5b6db2a92d9eddbba58d28230b893 100644 (file)
--- a/gcc/df.h
+++ b/gcc/df.h
@@ -991,6 +991,7 @@ extern df_ref df_find_def (rtx_insn *, rtx);
 extern bool df_reg_defined (rtx_insn *, rtx);
 extern df_ref df_find_use (rtx_insn *, rtx);
 extern bool df_reg_used (rtx_insn *, rtx);
+extern rtx df_find_single_def_src (rtx);
 extern void df_worklist_dataflow (struct dataflow *,bitmap, int *, int);
 extern void df_print_regset (FILE *file, const_bitmap r);
 extern void df_print_word_regset (FILE *file, const_bitmap r);

diff --git a/gcc/dse.cc b/gcc/dse.cc
index 30c11cee0348e70e06e378c40ea1cfe87c3017b8..994c60dc189774d01191aea6b0b4ca67394c74d3 100644 (file)
--- a/gcc/dse.cc
+++ b/gcc/dse.cc
@@ -1508,6 +1508,14 @@ record_store (rtx body, bb_info_t bb_info)
 
          if (tem && CONSTANT_P (tem))
            const_rhs = tem;
+         else
+           {
+             /* If RHS is set only once to a constant, set CONST_RHS
+                to the constant.  */
+             rtx def_src = df_find_single_def_src (rhs);
+             if (def_src != nullptr && CONSTANT_P (def_src))
+               const_rhs = def_src;
+           }
        }
     }
 

diff --git a/gcc/loop-iv.cc b/gcc/loop-iv.cc
index 0eafe7d2362d86c7e3986a30430428232eba636e..d639336445a4e9304e514d2893c3a950564c009f 100644 (file)
--- a/gcc/loop-iv.cc
+++ b/gcc/loop-iv.cc
@@ -1378,49 +1378,6 @@ simple_rhs_p (rtx rhs)
     }
 }
 
-/* If REGNO has a single definition, return its known value, otherwise return
-   null.  */
-
-static rtx
-find_single_def_src (unsigned int regno)
-{
-  rtx src = NULL_RTX;
-
-  /* Don't look through unbounded number of single definition REG copies,
-     there might be loops for sources with uninitialized variables.  */
-  for (int cnt = 0; cnt < 128; cnt++)
-    {
-      df_ref adef = DF_REG_DEF_CHAIN (regno);
-      if (adef == NULL || DF_REF_NEXT_REG (adef) != NULL
-         || DF_REF_IS_ARTIFICIAL (adef))
-       return NULL_RTX;
-
-      rtx set = single_set (DF_REF_INSN (adef));
-      if (set == NULL || !REG_P (SET_DEST (set))
-         || REGNO (SET_DEST (set)) != regno)
-       return NULL_RTX;
-
-      rtx note = find_reg_equal_equiv_note (DF_REF_INSN (adef));
-      if (note && function_invariant_p (XEXP (note, 0)))
-       {
-         src = XEXP (note, 0);
-         break;
-       }
-      src = SET_SRC (set);
-
-      if (REG_P (src))
-       {
-         regno = REGNO (src);
-         continue;
-       }
-      break;
-    }
-  if (!function_invariant_p (src))
-    return NULL_RTX;
-
-  return src;
-}
-
 /* If any registers in *EXPR that have a single definition, try to replace
    them with the known-equivalent values.  */
 
@@ -1433,7 +1390,7 @@ replace_single_def_regs (rtx *expr)
     {
       rtx x = *iter;
       if (REG_P (x))
-       if (rtx new_x = find_single_def_src (REGNO (x)))
+       if (rtx new_x = df_find_single_def_src (x))
          {
            *expr = simplify_replace_rtx (*expr, x, new_x);
            goto repeat;

diff --git a/gcc/testsuite/g++.target/i386/pr105638.C b/gcc/testsuite/g++.target/i386/pr105638.C
new file mode 100644 (file)
index 0000000..ff40a45
--- /dev/null
+++ b/gcc/testsuite/g++.target/i386/pr105638.C
@@ -0,0 +1,44 @@
+/* { dg-do compile { target { ! ia32 } } } */
+/* { dg-options "-std=gnu++20 -O2 -march=skylake" } */
+/* { dg-final { scan-assembler-not "vpxor" } } */
+
+#include <stdint.h>
+#include <vector>
+#include <tr1/array>
+
+class FastBoard {
+public:
+    typedef std::pair<int, int> movescore_t;
+    typedef std::tr1::array<movescore_t, 24> scoredlist_t;
+    
+protected:
+    std::vector<int> m_critical;
+
+    int m_boardsize;    
+};
+
+class FastState {
+public:        
+    FastBoard board;
+    
+    int movenum;              
+protected:
+    FastBoard::scoredlist_t scoredmoves;
+};
+
+class KoState : public FastState {
+private:         
+    std::vector<uint64_t> ko_hash_history;   
+    std::vector<uint64_t> hash_history;     
+};
+
+class GameState : public KoState {
+public:                    
+    void foo ();      
+private:
+    std::vector<KoState> game_history;                          
+};
+
+void GameState::foo() {
+    game_history.resize(movenum);
+}