Generate offset adjusted operation for op_by_pieces operations

Add an overlap_op_by_pieces_p target hook for op_by_pieces operations
between two areas of memory to generate one offset adjusted operation
in the smallest integer mode for the remaining bytes on the last piece
operation of a memory region to avoid doing more than one smaller
operations.

Pass the RTL information from the previous iteration to m_constfn in
op_by_pieces operation so that builtin_memset_[read|gen]_str can
generate the new RTL from the previous RTL.

Tested on Linux/x86-64.

gcc/

	PR middle-end/90773
	* builtins.c (builtin_memcpy_read_str): Add a dummy argument.
	(builtin_strncpy_read_str): Likewise.
	(builtin_memset_read_str): Add an argument for the previous RTL
	information and generate the new RTL from the previous RTL info.
	(builtin_memset_gen_str): Likewise.
	* builtins.h (builtin_strncpy_read_str): Update the prototype.
	(builtin_memset_read_str): Likewise.
	* expr.c (by_pieces_ninsns): If targetm.overlap_op_by_pieces_p()
	returns true, round up size and alignment to the widest integer
	mode for maximum size.
	(pieces_addr::adjust): Add a pointer to by_pieces_prev argument
	and pass it to m_constfn.
	(op_by_pieces_d): Add m_push and m_overlap_op_by_pieces.
	(op_by_pieces_d::op_by_pieces_d): Add a bool argument to
	initialize m_push.  Initialize m_overlap_op_by_pieces with
	targetm.overlap_op_by_pieces_p ().
	(op_by_pieces_d::run): Pass the previous RTL information to
	pieces_addr::adjust and generate overlapping operations if
	m_overlap_op_by_pieces is true.
	(PUSHG_P): New.
	(move_by_pieces_d::move_by_pieces_d): Updated for op_by_pieces_d
	change.
	(store_by_pieces_d::store_by_pieces_d): Updated for op_by_pieces_d
	change.
	(can_store_by_pieces): Use by_pieces_constfn on constfun.
	(store_by_pieces): Use by_pieces_constfn on constfun.  Updated
	for op_by_pieces_d change.
	(clear_by_pieces_1): Add a dummy argument.
	(clear_by_pieces): Updated for op_by_pieces_d change.
	(compare_by_pieces_d::compare_by_pieces_d): Likewise.
	(string_cst_read_str): Add a dummy argument.
	* expr.h (by_pieces_constfn): Add a dummy argument.
	(by_pieces_prev): New.
	* target.def (overlap_op_by_pieces_p): New target hook.
	* config/i386/i386.c (TARGET_OVERLAP_OP_BY_PIECES_P): New.
	* doc/tm.texi.in: Add TARGET_OVERLAP_OP_BY_PIECES_P.
	* doc/tm.texi: Regenerated.

gcc/testsuite/

	PR middle-end/90773
	* g++.dg/pr90773-1.h: New test.
	* g++.dg/pr90773-1a.C: Likewise.
	* g++.dg/pr90773-1b.C: Likewise.
	* g++.dg/pr90773-1c.C: Likewise.
	* g++.dg/pr90773-1d.C: Likewise.
	* gcc.target/i386/pr90773-1.c: Likewise.
	* gcc.target/i386/pr90773-2.c: Likewise.
	* gcc.target/i386/pr90773-3.c: Likewise.
	* gcc.target/i386/pr90773-4.c: Likewise.
	* gcc.target/i386/pr90773-5.c: Likewise.
	* gcc.target/i386/pr90773-6.c: Likewise.
	* gcc.target/i386/pr90773-7.c: Likewise.
	* gcc.target/i386/pr90773-8.c: Likewise.
	* gcc.target/i386/pr90773-9.c: Likewise.
	* gcc.target/i386/pr90773-10.c: Likewise.
	* gcc.target/i386/pr90773-11.c: Likewise.
	* gcc.target/i386/pr90773-12.c: Likewise.
	* gcc.target/i386/pr90773-13.c: Likewise.
	* gcc.target/i386/pr90773-14.c: Likewise.

1 files changed, 28 insertions, 8 deletions

diff --git a/gcc/builtins.c b/gcc/builtins.c
index 8c5324b..2d6bf4a 100644
--- a/gcc/builtins.c
+++ b/gcc/builtins.c
@@ -128,7 +128,6 @@ static rtx expand_builtin_va_copy (tree);
 static rtx inline_expand_builtin_bytecmp (tree, rtx);
 static rtx expand_builtin_strcmp (tree, rtx);
 static rtx expand_builtin_strncmp (tree, rtx, machine_mode);
-static rtx builtin_memcpy_read_str (void *, HOST_WIDE_INT, scalar_int_mode);
 static rtx expand_builtin_memchr (tree, rtx);
 static rtx expand_builtin_memcpy (tree, rtx);
 static rtx expand_builtin_memory_copy_args (tree dest, tree src, tree len,
@@ -145,7 +144,6 @@ static rtx expand_builtin_stpcpy (tree, rtx, machine_mode);
 static rtx expand_builtin_stpncpy (tree, rtx);
 static rtx expand_builtin_strncat (tree, rtx);
 static rtx expand_builtin_strncpy (tree, rtx);
-static rtx builtin_memset_gen_str (void *, HOST_WIDE_INT, scalar_int_mode);
 static rtx expand_builtin_memset (tree, rtx, machine_mode);
 static rtx expand_builtin_memset_args (tree, tree, tree, rtx, machine_mode, tree);
 static rtx expand_builtin_bzero (tree);
@@ -3860,7 +3858,7 @@ expand_builtin_strnlen (tree exp, rtx target, machine_mode target_mode)
    a target constant.  */
 
 static rtx
-builtin_memcpy_read_str (void *data, HOST_WIDE_INT offset,
+builtin_memcpy_read_str (void *data, void *, HOST_WIDE_INT offset,
 			 scalar_int_mode mode)
 {
   /* The REPresentation pointed to by DATA need not be a nul-terminated
@@ -6373,7 +6371,7 @@ expand_builtin_stpncpy (tree exp, rtx)
    constant.  */
 
 rtx
-builtin_strncpy_read_str (void *data, HOST_WIDE_INT offset,
+builtin_strncpy_read_str (void *data, void *, HOST_WIDE_INT offset,
 			  scalar_int_mode mode)
 {
   const char *str = (const char *) data;
@@ -6584,12 +6582,22 @@ expand_builtin_strncpy (tree exp, rtx target)
 
 /* Callback routine for store_by_pieces.  Read GET_MODE_BITSIZE (MODE)
    bytes from constant string DATA + OFFSET and return it as target
-   constant.  */
+   constant.  If PREV isn't nullptr, it has the RTL info from the
+   previous iteration.  */
 
 rtx
-builtin_memset_read_str (void *data, HOST_WIDE_INT offset ATTRIBUTE_UNUSED,
+builtin_memset_read_str (void *data, void *prevp,
+			 HOST_WIDE_INT offset ATTRIBUTE_UNUSED,
 			 scalar_int_mode mode)
 {
+  by_pieces_prev *prev = (by_pieces_prev *) prevp;
+  if (prev != nullptr && prev->data != nullptr)
+    {
+      /* Use the previous data in the same mode.  */
+      if (prev->mode == mode)
+	return prev->data;
+    }
+
   const char *c = (const char *) data;
   char *p = XALLOCAVEC (char, GET_MODE_SIZE (mode));
 
@@ -6601,16 +6609,28 @@ builtin_memset_read_str (void *data, HOST_WIDE_INT offset ATTRIBUTE_UNUSED,
 /* Callback routine for store_by_pieces.  Return the RTL of a register
    containing GET_MODE_SIZE (MODE) consecutive copies of the unsigned
    char value given in the RTL register data.  For example, if mode is
-   4 bytes wide, return the RTL for 0x01010101*data.  */
+   4 bytes wide, return the RTL for 0x01010101*data.  If PREV isn't
+   nullptr, it has the RTL info from the previous iteration.  */
 
 static rtx
-builtin_memset_gen_str (void *data, HOST_WIDE_INT offset ATTRIBUTE_UNUSED,
+builtin_memset_gen_str (void *data, void *prevp,
+			HOST_WIDE_INT offset ATTRIBUTE_UNUSED,
 			scalar_int_mode mode)
 {
   rtx target, coeff;
   size_t size;
   char *p;
 
+  by_pieces_prev *prev = (by_pieces_prev *) prevp;
+  if (prev != nullptr && prev->data != nullptr)
+    {
+      /* Use the previous data in the same mode.  */
+      if (prev->mode == mode)
+	return prev->data;
+
+      return simplify_gen_subreg (mode, prev->data, prev->mode, 0);
+    }
+
   size = GET_MODE_SIZE (mode);
   if (size == 1)
     return (rtx) data;