bswap: Fix up symbolic merging for xor and plus [PR103376]

On Mon, Nov 22, 2021 at 08:39:42AM -0000, Roger Sayle wrote:
> This patch implements PR tree-optimization/103345 to merge adjacent
> loads when combined with addition or bitwise xor.  The current code
> in gimple-ssa-store-merging.c's find_bswap_or_nop alreay handles ior,
> so that all that's required is to treat PLUS_EXPR and BIT_XOR_EXPR in
> the same way at BIT_IOR_EXPR.

Unfortunately they aren't exactly the same.  They work the same if always
at least one operand (or corresponding byte in it) is known to be 0,
0 | 0 = 0 ^ 0 = 0 + 0 = 0.  But for | also x | x = x for any other x,
so perform_symbolic_merge has been accepting either that at least one
of the bytes is 0 or that both are the same, but that is wrong for ^
and +.

The following patch fixes that by passing through the code of binary
operation and allowing non-zero masked1 == masked2 through only
for BIT_IOR_EXPR.

Thinking more about it, perhaps we could do more for BIT_XOR_EXPR.
We could allow masked1 == masked2 case for it, but would need to
do something different than the
  n->n = n1->n | n2->n;
we do on all the bytes together.
In particular, for masked1 == masked2 if masked1 != 0 (well, for 0
both variants are the same) and masked1 != 0xff we would need to
clear corresponding n->n byte instead of setting it to the input
as x ^ x = 0 (but if we don't know what x and y are, the result is
also don't know).  Now, for plus it is much harder, because not only
for non-zero operands we don't know what the result is, but it can
modify upper bytes as well.  So perhaps only if current's byte
masked1 && masked2 set the resulting byte to 0xff (unknown) iff
the byte above it is 0 and 0, and set that resulting byte to 0xff too.
Also, even for | we could instead of return NULL just set the resulting
byte to 0xff if it is different, perhaps it will be masked off later on.

2021-11-24  Jakub Jelinek  <jakub@redhat.com>

	PR tree-optimization/103376
	* gimple-ssa-store-merging.c (perform_symbolic_merge): Add CODE
	argument.  If CODE is not BIT_IOR_EXPR, ensure that one of masked1
	or masked2 is 0.
	(find_bswap_or_nop_1, find_bswap_or_nop,
	imm_store_chain_info::try_coalesce_bswap): Adjust
	perform_symbolic_merge callers.

	* gcc.c-torture/execute/pr103376.c: New test.

2 files changed, 41 insertions, 8 deletions

diff --git a/gcc/gimple-ssa-store-merging.c b/gcc/gimple-ssa-store-merging.c
index 1740c9e..35df0fe 100644
--- a/gcc/gimple-ssa-store-merging.c
+++ b/gcc/gimple-ssa-store-merging.c
@@ -434,14 +434,14 @@ find_bswap_or_nop_load (gimple *stmt, tree ref, struct symbolic_number *n)
   return true;
 }
 
-/* Compute the symbolic number N representing the result of a bitwise OR on 2
-   symbolic number N1 and N2 whose source statements are respectively
-   SOURCE_STMT1 and SOURCE_STMT2.  */
+/* Compute the symbolic number N representing the result of a bitwise OR,
+   bitwise XOR or plus on 2 symbolic number N1 and N2 whose source statements
+   are respectively SOURCE_STMT1 and SOURCE_STMT2.  CODE is the operation.  */
 
 gimple *
 perform_symbolic_merge (gimple *source_stmt1, struct symbolic_number *n1,
 			gimple *source_stmt2, struct symbolic_number *n2,
-			struct symbolic_number *n)
+			struct symbolic_number *n, enum tree_code code)
 {
   int i, size;
   uint64_t mask;
@@ -563,7 +563,9 @@ perform_symbolic_merge (gimple *source_stmt1, struct symbolic_number *n1,
 
       masked1 = n1->n & mask;
       masked2 = n2->n & mask;
-      if (masked1 && masked2 && masked1 != masked2)
+      /* For BIT_XOR_EXPR or PLUS_EXPR, at least one of masked1 and masked2
+	 has to be 0, for BIT_IOR_EXPR x | x is still x.  */
+      if (masked1 && masked2 && (code != BIT_IOR_EXPR || masked1 != masked2))
 	return NULL;
     }
   n->n = n1->n | n2->n;
@@ -769,7 +771,8 @@ find_bswap_or_nop_1 (gimple *stmt, struct symbolic_number *n, int limit)
 	    return NULL;
 
 	  source_stmt
-	    = perform_symbolic_merge (source_stmt1, &n1, source_stmt2, &n2, n);
+	    = perform_symbolic_merge (source_stmt1, &n1, source_stmt2, &n2, n,
+				      code);
 
 	  if (!source_stmt)
 	    return NULL;
@@ -943,7 +946,8 @@ find_bswap_or_nop (gimple *stmt, struct symbolic_number *n, bool *bswap,
 	      else if (!do_shift_rotate (LSHIFT_EXPR, &n0, eltsz))
 		return NULL;
 	      ins_stmt
-		= perform_symbolic_merge (ins_stmt, &n0, source_stmt, &n1, n);
+		= perform_symbolic_merge (ins_stmt, &n0, source_stmt, &n1, n,
+					  BIT_IOR_EXPR);
 
 	      if (!ins_stmt)
 		return NULL;
@@ -2881,7 +2885,7 @@ imm_store_chain_info::try_coalesce_bswap (merged_store_group *merged_store,
 	  end = MAX (end, info->bitpos + info->bitsize);
 
 	  ins_stmt = perform_symbolic_merge (ins_stmt, &n, info->ins_stmt,
-					     &this_n, &n);
+					     &this_n, &n, BIT_IOR_EXPR);
 	  if (ins_stmt == NULL)
 	    return false;
 	}
diff --git a/gcc/testsuite/gcc.c-torture/execute/pr103376.c b/gcc/testsuite/gcc.c-torture/execute/pr103376.c
new file mode 100644
index 0000000..22e2019
--- /dev/null
+++ b/gcc/testsuite/gcc.c-torture/execute/pr103376.c
@@ -0,0 +1,29 @@
+/* PR tree-optimization/103376 */
+
+long long a = 0x123456789abcdef0LL, f;
+int b, c, *d;
+
+__attribute__((noipa)) void
+foo (int x)
+{
+  asm volatile ("" : : "r" (x));
+}
+
+int
+main ()
+{
+  long long e;
+  e = a;
+  if (b)
+    {
+      foo (c);
+      d = (int *) 0;
+      while (*d)
+	;
+    }
+  f = a ^ e;
+  asm volatile ("" : "+m" (f));
+  if (f != 0)
+    __builtin_abort ();
+  return 0;
+}