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.

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;

gcc/builtins.h

@@ -110,8 +110,10 @@ extern void expand_builtin_update_setjmp_buf (rtx);
 extern tree mathfn_built_in (tree, enum built_in_function fn);
 extern tree mathfn_built_in (tree, combined_fn);
 extern tree mathfn_built_in_type (combined_fn);
-extern rtx builtin_strncpy_read_str (void *, HOST_WIDE_INT, scalar_int_mode);
-extern rtx builtin_memset_read_str (void *, HOST_WIDE_INT, scalar_int_mode);
+extern rtx builtin_strncpy_read_str (void *, void *, HOST_WIDE_INT,
+				     scalar_int_mode);
+extern rtx builtin_memset_read_str (void *, void *, HOST_WIDE_INT,
+				    scalar_int_mode);
 extern rtx expand_builtin_saveregs (void);
 extern tree std_build_builtin_va_list (void);
 extern tree std_fn_abi_va_list (tree);

gcc/config/i386/i386.c

@@ -23538,6 +23538,9 @@ ix86_run_selftests (void)
 #undef TARGET_ADDRESS_COST
 #define TARGET_ADDRESS_COST ix86_address_cost
 
+#undef TARGET_OVERLAP_OP_BY_PIECES_P
+#define TARGET_OVERLAP_OP_BY_PIECES_P hook_bool_void_true
+
 #undef TARGET_FLAGS_REGNUM
 #define TARGET_FLAGS_REGNUM FLAGS_REG
 #undef TARGET_FIXED_CONDITION_CODE_REGS

gcc/doc/tm.texi

@@ -6767,6 +6767,13 @@ in code size, for example where the number of insns emitted to perform a
 move would be greater than that of a library call.
 @end deftypefn
 
+@deftypefn {Target Hook} bool TARGET_OVERLAP_OP_BY_PIECES_P (void)
+This target hook should return true if when the @code{by_pieces}
+infrastructure is used, an offset adjusted unaligned memory operation
+in the smallest integer mode for the last piece operation of a memory
+region can be generated to avoid doing more than one smaller operations.
+@end deftypefn
+
 @deftypefn {Target Hook} int TARGET_COMPARE_BY_PIECES_BRANCH_RATIO (machine_mode @var{mode})
 When expanding a block comparison in MODE, gcc can try to reduce the
 number of branches at the expense of more memory operations.  This hook

gcc/doc/tm.texi.in

@@ -4588,6 +4588,8 @@ If you don't define this, a reasonable default is used.
 
 @hook TARGET_USE_BY_PIECES_INFRASTRUCTURE_P
 
+@hook TARGET_OVERLAP_OP_BY_PIECES_P
+
 @hook TARGET_COMPARE_BY_PIECES_BRANCH_RATIO
 
 @defmac MOVE_MAX_PIECES

gcc/expr.c

@@ -815,12 +815,27 @@ by_pieces_ninsns (unsigned HOST_WIDE_INT l, unsigned int align,
 		  unsigned int max_size, by_pieces_operation op)
 {
   unsigned HOST_WIDE_INT n_insns = 0;
+  scalar_int_mode mode;
+
+  if (targetm.overlap_op_by_pieces_p () && op != COMPARE_BY_PIECES)
+    {
+      /* NB: Round up L and ALIGN to the widest integer mode for
+	 MAX_SIZE.  */
+      mode = widest_int_mode_for_size (max_size);
+      if (optab_handler (mov_optab, mode) != CODE_FOR_nothing)
+	{
+	  unsigned HOST_WIDE_INT up = ROUND_UP (l, GET_MODE_SIZE (mode));
+	  if (up > l)
+	    l = up;
+	  align = GET_MODE_ALIGNMENT (mode);
+	}
+    }
 
   align = alignment_for_piecewise_move (MOVE_MAX_PIECES, align);
 
   while (max_size > 1 && l > 0)
     {
-      scalar_int_mode mode = widest_int_mode_for_size (max_size);
+      mode = widest_int_mode_for_size (max_size);
       enum insn_code icode;
 
       unsigned int modesize = GET_MODE_SIZE (mode);
@@ -888,7 +903,8 @@ class pieces_addr
   void *m_cfndata;
 public:
   pieces_addr (rtx, bool, by_pieces_constfn, void *);
-  rtx adjust (scalar_int_mode, HOST_WIDE_INT);
+  rtx adjust (scalar_int_mode, HOST_WIDE_INT,
+	      by_pieces_prev * = nullptr);
   void increment_address (HOST_WIDE_INT);
   void maybe_predec (HOST_WIDE_INT);
   void maybe_postinc (HOST_WIDE_INT);
@@ -990,10 +1006,12 @@ pieces_addr::decide_autoinc (machine_mode ARG_UNUSED (mode), bool reverse,
    but we still modify the MEM's properties.  */
 
 rtx
-pieces_addr::adjust (scalar_int_mode mode, HOST_WIDE_INT offset)
+pieces_addr::adjust (scalar_int_mode mode, HOST_WIDE_INT offset,
+		     by_pieces_prev *prev)
 {
   if (m_constfn)
-    return m_constfn (m_cfndata, offset, mode);
+    /* Pass the previous data to m_constfn.  */
+    return m_constfn (m_cfndata, prev, offset, mode);
   if (m_obj == NULL_RTX)
     return NULL_RTX;
   if (m_auto)
@@ -1051,6 +1069,10 @@ class op_by_pieces_d
   unsigned int m_align;
   unsigned int m_max_size;
   bool m_reverse;
+  /* True if this is a stack push.  */
+  bool m_push;
+  /* True if targetm.overlap_op_by_pieces_p () returns true.  */
+  bool m_overlap_op_by_pieces;
 
   /* Virtual functions, overriden by derived classes for the specific
      operation.  */
@@ -1062,7 +1084,7 @@ class op_by_pieces_d
 
  public:
   op_by_pieces_d (rtx, bool, rtx, bool, by_pieces_constfn, void *,
-		  unsigned HOST_WIDE_INT, unsigned int);
+		  unsigned HOST_WIDE_INT, unsigned int, bool);
   void run ();
 };
 
@@ -1077,10 +1099,11 @@ op_by_pieces_d::op_by_pieces_d (rtx to, bool to_load,
 				by_pieces_constfn from_cfn,
 				void *from_cfn_data,
 				unsigned HOST_WIDE_INT len,
-				unsigned int align)
+				unsigned int align, bool push)
   : m_to (to, to_load, NULL, NULL),
     m_from (from, from_load, from_cfn, from_cfn_data),
-    m_len (len), m_max_size (MOVE_MAX_PIECES + 1)
+    m_len (len), m_max_size (MOVE_MAX_PIECES + 1),
+    m_push (push)
 {
   int toi = m_to.get_addr_inc ();
   int fromi = m_from.get_addr_inc ();
@@ -1109,6 +1132,8 @@ op_by_pieces_d::op_by_pieces_d (rtx to, bool to_load,
 
   align = alignment_for_piecewise_move (MOVE_MAX_PIECES, align);
   m_align = align;
+
+  m_overlap_op_by_pieces = targetm.overlap_op_by_pieces_p ();
 }
 
 /* This function returns the largest usable integer mode for LEN bytes
@@ -1145,6 +1170,9 @@ op_by_pieces_d::run ()
   scalar_int_mode mode = widest_int_mode_for_size (m_max_size);
   mode = get_usable_mode (mode, m_len);
 
+  by_pieces_prev to_prev = { nullptr, mode };
+  by_pieces_prev from_prev = { nullptr, mode };
+
   do
     {
       unsigned int size = GET_MODE_SIZE (mode);
@@ -1155,8 +1183,12 @@ op_by_pieces_d::run ()
 	  if (m_reverse)
 	    m_offset -= size;
 
-	  to1 = m_to.adjust (mode, m_offset);
-	  from1 = m_from.adjust (mode, m_offset);
+	  to1 = m_to.adjust (mode, m_offset, &to_prev);
+	  to_prev.data = to1;
+	  to_prev.mode = mode;
+	  from1 = m_from.adjust (mode, m_offset, &from_prev);
+	  from_prev.data = from1;
+	  from_prev.mode = mode;
 
 	  m_to.maybe_predec (-(HOST_WIDE_INT)size);
 	  m_from.maybe_predec (-(HOST_WIDE_INT)size);
@@ -1177,9 +1209,32 @@ op_by_pieces_d::run ()
       if (m_len == 0)
 	return;
 
-      /* NB: widest_int_mode_for_size checks SIZE > 1.  */
-      mode = widest_int_mode_for_size (size);
-      mode = get_usable_mode (mode, m_len);
+      if (!m_push && m_overlap_op_by_pieces)
+	{
+	  /* NB: Generate overlapping operations if it is not a stack
+	     push since stack push must not overlap.  Get the smallest
+	     integer mode for M_LEN bytes.  */
+	  mode = smallest_int_mode_for_size (m_len * BITS_PER_UNIT);
+	  mode = get_usable_mode (mode, GET_MODE_SIZE (mode));
+	  int gap = GET_MODE_SIZE (mode) - m_len;
+	  if (gap > 0)
+	    {
+	      /* If size of MODE > M_LEN, generate the last operation
+		 in MODE for the remaining bytes with ovelapping memory
+		 from the previois operation.  */
+	      if (m_reverse)
+		m_offset += gap;
+	      else
+		m_offset -= gap;
+	      m_len += gap;
+	    }
+	}
+      else
+	{
+	  /* NB: widest_int_mode_for_size checks SIZE > 1.  */
+	  mode = widest_int_mode_for_size (size);
+	  mode = get_usable_mode (mode, m_len);
+	}
     }
   while (1);
 
@@ -1190,6 +1245,12 @@ op_by_pieces_d::run ()
 /* Derived class from op_by_pieces_d, providing support for block move
    operations.  */
 
+#ifdef PUSH_ROUNDING
+#define PUSHG_P(to)  ((to) == nullptr)
+#else
+#define PUSHG_P(to)  false
+#endif
+
 class move_by_pieces_d : public op_by_pieces_d
 {
   insn_gen_fn m_gen_fun;
@@ -1199,7 +1260,8 @@ class move_by_pieces_d : public op_by_pieces_d
  public:
   move_by_pieces_d (rtx to, rtx from, unsigned HOST_WIDE_INT len,
 		    unsigned int align)
-    : op_by_pieces_d (to, false, from, true, NULL, NULL, len, align)
+    : op_by_pieces_d (to, false, from, true, NULL, NULL, len, align,
+		      PUSHG_P (to))
   {
   }
   rtx finish_retmode (memop_ret);
@@ -1294,7 +1356,8 @@ class store_by_pieces_d : public op_by_pieces_d
  public:
   store_by_pieces_d (rtx to, by_pieces_constfn cfn, void *cfn_data,
 		     unsigned HOST_WIDE_INT len, unsigned int align)
-    : op_by_pieces_d (to, false, NULL_RTX, true, cfn, cfn_data, len, align)
+    : op_by_pieces_d (to, false, NULL_RTX, true, cfn, cfn_data, len,
+		      align, false)
   {
   }
   rtx finish_retmode (memop_ret);
@@ -1349,7 +1412,7 @@ store_by_pieces_d::finish_retmode (memop_ret retmode)
 
 int
 can_store_by_pieces (unsigned HOST_WIDE_INT len,
-		     rtx (*constfun) (void *, HOST_WIDE_INT, scalar_int_mode),
+		     by_pieces_constfn constfun,
 		     void *constfundata, unsigned int align, bool memsetp)
 {
   unsigned HOST_WIDE_INT l;
@@ -1396,7 +1459,7 @@ can_store_by_pieces (unsigned HOST_WIDE_INT len,
 		  if (reverse)
 		    offset -= size;
 
-		  cst = (*constfun) (constfundata, offset, mode);
+		  cst = (*constfun) (constfundata, nullptr, offset, mode);
 		  if (!targetm.legitimate_constant_p (mode, cst))
 		    return 0;
 
@@ -1426,7 +1489,7 @@ can_store_by_pieces (unsigned HOST_WIDE_INT len,
 
 rtx
 store_by_pieces (rtx to, unsigned HOST_WIDE_INT len,
-		 rtx (*constfun) (void *, HOST_WIDE_INT, scalar_int_mode),
+		 by_pieces_constfn constfun,
 		 void *constfundata, unsigned int align, bool memsetp,
 		 memop_ret retmode)
 {
@@ -1454,7 +1517,7 @@ store_by_pieces (rtx to, unsigned HOST_WIDE_INT len,
    Return const0_rtx unconditionally.  */
 
 static rtx
-clear_by_pieces_1 (void *, HOST_WIDE_INT, scalar_int_mode)
+clear_by_pieces_1 (void *, void *, HOST_WIDE_INT, scalar_int_mode)
 {
   return const0_rtx;
 }
@@ -1490,7 +1553,8 @@ class compare_by_pieces_d : public op_by_pieces_d
   compare_by_pieces_d (rtx op0, rtx op1, by_pieces_constfn op1_cfn,
 		       void *op1_cfn_data, HOST_WIDE_INT len, int align,
 		       rtx_code_label *fail_label)
-    : op_by_pieces_d (op0, true, op1, true, op1_cfn, op1_cfn_data, len, align)
+    : op_by_pieces_d (op0, true, op1, true, op1_cfn, op1_cfn_data, len,
+		      align, false)
   {
     m_fail_label = fail_label;
   }
@@ -5676,7 +5740,8 @@ emit_storent_insn (rtx to, rtx from)
 /* Helper function for store_expr storing of STRING_CST.  */
 
 static rtx
-string_cst_read_str (void *data, HOST_WIDE_INT offset, scalar_int_mode mode)
+string_cst_read_str (void *data, void *, HOST_WIDE_INT offset,
+		     scalar_int_mode mode)
 {
   tree str = (tree) data;
 

gcc/expr.h

@@ -107,7 +107,15 @@ enum block_op_methods
   BLOCK_OP_NO_LIBCALL_RET
 };
 
-typedef rtx (*by_pieces_constfn) (void *, HOST_WIDE_INT, scalar_int_mode);
+typedef rtx (*by_pieces_constfn) (void *, void *, HOST_WIDE_INT,
+				  scalar_int_mode);
+
+/* The second pointer passed to by_pieces_constfn.  */
+struct by_pieces_prev
+{
+  rtx data;
+  scalar_int_mode mode;
+};
 
 extern rtx emit_block_move (rtx, rtx, rtx, enum block_op_methods);
 extern rtx emit_block_move_hints (rtx, rtx, rtx, enum block_op_methods,

gcc/target.def

@@ -3642,6 +3642,15 @@ move would be greater than that of a library call.",
         enum by_pieces_operation op, bool speed_p),
  default_use_by_pieces_infrastructure_p)
 
+DEFHOOK
+(overlap_op_by_pieces_p,
+ "This target hook should return true if when the @code{by_pieces}\n\
+infrastructure is used, an offset adjusted unaligned memory operation\n\
+in the smallest integer mode for the last piece operation of a memory\n\
+region can be generated to avoid doing more than one smaller operations.",
+ bool, (void),
+ hook_bool_void_false)
+
 DEFHOOK
 (compare_by_pieces_branch_ratio,
  "When expanding a block comparison in MODE, gcc can try to reduce the\n\

gcc/testsuite/g++.dg/pr90773-1.h

@@ -0,0 +1,14 @@
+class fixed_wide_int_storage {
+public:
+  long val[10];
+  int len;
+  fixed_wide_int_storage ()
+    {
+      len = sizeof (val) / sizeof (val[0]);
+      for (int i = 0; i < len; i++)
+	val[i] = i;
+    }
+};
+
+extern void foo (fixed_wide_int_storage);
+extern int record_increment(void);

gcc/testsuite/g++.dg/pr90773-1a.C

@@ -0,0 +1,13 @@
+// { dg-do compile }
+// { dg-options "-O2" }
+// { dg-additional-options "-mno-avx -msse2 -mtune=skylake" { target { i?86-*-* x86_64-*-* } } }
+
+#include "pr90773-1.h"
+
+int
+record_increment(void)
+{
+  fixed_wide_int_storage x;
+  foo (x);
+  return 0;
+}

gcc/testsuite/g++.dg/pr90773-1b.C

@@ -0,0 +1,5 @@
+// { dg-do compile }
+// { dg-options "-O2" }
+// { dg-additional-options "-mno-avx512f -march=skylake" { target { i?86-*-* x86_64-*-* } } }
+
+#include "pr90773-1a.C"

gcc/testsuite/g++.dg/pr90773-1c.C

@@ -0,0 +1,5 @@
+// { dg-do compile }
+// { dg-options "-O2" }
+// { dg-additional-options "-march=skylake-avx512" { target { i?86-*-* x86_64-*-* } } }
+
+#include "pr90773-1a.C"

gcc/testsuite/g++.dg/pr90773-1d.C

@@ -0,0 +1,19 @@
+// { dg-do run }
+// { dg-options "-O2" }
+// { dg-additional-options "-march=native" { target { i?86-*-* x86_64-*-* } } }
+// { dg-additional-sources "pr90773-1a.C" }
+
+#include "pr90773-1.h"
+
+void
+foo (fixed_wide_int_storage x)
+{
+  for (int i = 0; i < x.len; i++)
+    if (x.val[i] != i)
+      __builtin_abort ();
+}
+
+int main ()
+{
+  return record_increment ();
+}

gcc/testsuite/gcc.target/i386/pr90773-1.c

@@ -0,0 +1,17 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -mtune=generic" } */
+
+extern char *dst, *src;
+
+void
+foo (void)
+{
+  __builtin_memcpy (dst, src, 15);
+}
+
+/* { dg-final { scan-assembler-times "movq\[\\t \]+\\(%\[\^,\]+\\)," 1 { target { ! ia32 } } } } */
+/* { dg-final { scan-assembler-times "movq\[\\t \]+7\\(%\[\^,\]+\\)," 1 { target { ! ia32 } } } } */
+/* { dg-final { scan-assembler-times "movl\[\\t \]+\\(%\[\^,\]+\\)," 1 { target ia32 } } } */
+/* { dg-final { scan-assembler-times "movl\[\\t \]+4\\(%\[\^,\]+\\)," 1 { target ia32 } } } */
+/* { dg-final { scan-assembler-times "movl\[\\t \]+8\\(%\[\^,\]+\\)," 1 { target ia32 } } } */
+/* { dg-final { scan-assembler-times "movl\[\\t \]+11\\(%\[\^,\]+\\)," 1 { target ia32 } } } */

gcc/testsuite/gcc.target/i386/pr90773-10.c

@@ -0,0 +1,13 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -mtune=generic" } */
+
+extern char *dst;
+
+void
+foo (int c)
+{
+  __builtin_memset (dst, c, 5);
+}
+
+/* { dg-final { scan-assembler-times "movl\[\\t \]+.+, \\(%\[\^,\]+\\)" 1 } } */
+/* { dg-final { scan-assembler-times "movb\[\\t \]+.+, 4\\(%\[\^,\]+\\)" 1 } } */

gcc/testsuite/gcc.target/i386/pr90773-11.c

@@ -0,0 +1,13 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -mtune=generic" } */
+
+extern char *dst;
+
+void
+foo (int c)
+{
+  __builtin_memset (dst, c, 6);
+}
+
+/* { dg-final { scan-assembler-times "movl\[\\t \]+.+, \\(%\[\^,\]+\\)" 1 } } */
+/* { dg-final { scan-assembler-times "movw\[\\t \]+.+, 4\\(%\[\^,\]+\\)" 1 } } */

gcc/testsuite/gcc.target/i386/pr90773-12.c

@@ -0,0 +1,11 @@
+/* { dg-do compile { target { ! ia32 } } } */
+/* { dg-options "-O2 -mno-avx -msse2 -mtune=skylake" } */
+
+void
+foo (char *dst, char *src)
+{
+  __builtin_memcpy (dst, src, 255);
+}
+
+/* { dg-final { scan-assembler-times "movdqu\[\\t \]+\[0-9\]*\\(%\[\^,\]+\\)," 16 } } */
+/* { dg-final { scan-assembler-not "mov\[bwlq\]" } } */

gcc/testsuite/gcc.target/i386/pr90773-13.c

@@ -0,0 +1,11 @@
+/* { dg-do compile { target { ! ia32 } } } */
+/* { dg-options "-O2 -mno-avx -msse2 -mtune=skylake" } */
+
+void
+foo (char *dst)
+{
+  __builtin_memset (dst, 0, 255);
+}
+
+/* { dg-final { scan-assembler-times "movups\[\\t \]+%xmm\[0-9\]+, \[0-9\]*\\(%\[\^,\]+\\)" 16 } } */
+/* { dg-final { scan-assembler-not "mov\[bwlq\]" } } */

gcc/testsuite/gcc.target/i386/pr90773-14.c

@@ -0,0 +1,13 @@
+/* { dg-do compile { target { ! ia32 } } } */
+/* { dg-options "-O2 -mno-avx -msse2 -mtune=generic" } */
+
+extern char *dst;
+
+void
+foo (void)
+{
+  __builtin_memset (dst, 1, 20);
+}
+
+/* { dg-final { scan-assembler-times "movups\[\\t \]+%xmm\[0-9\]+, \\(%\[\^,\]+\\)" 1 } } */
+/* { dg-final { scan-assembler-times "movl\[\\t \]+\\\$16843009, 16\\(%\[\^,\]+\\)" 1 } } */

gcc/testsuite/gcc.target/i386/pr90773-2.c

@@ -0,0 +1,20 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -mtune=generic" } */
+/* { dg-additional-options "-mno-avx -msse2" { target { ! ia32 } } } */
+/* { dg-additional-options "-mno-sse" { target ia32 } } */
+
+extern char *dst, *src;
+
+void
+foo (void)
+{
+  __builtin_memcpy (dst, src, 19);
+}
+
+/* { dg-final { scan-assembler-times "movdqu\[\\t \]+\\(%\[\^,\]+\\)," 1 { target { ! ia32 } } } } */
+/* { dg-final { scan-assembler-times "movl\[\\t \]+15\\(%\[\^,\]+\\)," 1 { target { ! ia32 } } } } */
+/* { dg-final { scan-assembler-times "movl\[\\t \]+\\(%\[\^,\]+\\)," 1 { target ia32 } } } */
+/* { dg-final { scan-assembler-times "movl\[\\t \]+4\\(%\[\^,\]+\\)," 1 { target ia32 } } } */
+/* { dg-final { scan-assembler-times "movl\[\\t \]+8\\(%\[\^,\]+\\)," 1 { target ia32 } } } */
+/* { dg-final { scan-assembler-times "movl\[\\t \]+12\\(%\[\^,\]+\\)," 1 { target ia32 } } } */
+/* { dg-final { scan-assembler-times "movl\[\\t \]+15\\(%\[\^,\]+\\)," 1 { target ia32 } } } */

gcc/testsuite/gcc.target/i386/pr90773-3.c

@@ -0,0 +1,23 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -mtune=generic" } */
+/* { dg-additional-options "-mno-avx -msse2" { target { ! ia32 } } } */
+/* { dg-additional-options "-mno-sse" { target ia32 } } */
+
+extern char *dst, *src;
+
+void
+foo (void)
+{
+  __builtin_memcpy (dst, src, 31);
+}
+
+/* { dg-final { scan-assembler-times "movdqu\[\\t \]+\\(%\[\^,\]+\\)," 1 { target { ! ia32 } } } } */
+/* { dg-final { scan-assembler-times "movdqu\[\\t \]+15\\(%\[\^,\]+\\)," 1 { target { ! ia32 } } } } */
+/* { dg-final { scan-assembler-times "movl\[\\t \]+\\(%\[\^,\]+\\)," 1 { target ia32 } } } */
+/* { dg-final { scan-assembler-times "movl\[\\t \]+4\\(%\[\^,\]+\\)," 1 { target ia32 } } } */
+/* { dg-final { scan-assembler-times "movl\[\\t \]+8\\(%\[\^,\]+\\)," 1 { target ia32 } } } */
+/* { dg-final { scan-assembler-times "movl\[\\t \]+12\\(%\[\^,\]+\\)," 1 { target ia32 } } } */
+/* { dg-final { scan-assembler-times "movl\[\\t \]+16\\(%\[\^,\]+\\)," 1 { target ia32 } } } */
+/* { dg-final { scan-assembler-times "movl\[\\t \]+20\\(%\[\^,\]+\\)," 1 { target ia32 } } } */
+/* { dg-final { scan-assembler-times "movl\[\\t \]+24\\(%\[\^,\]+\\)," 1 { target ia32 } } } */
+/* { dg-final { scan-assembler-times "movl\[\\t \]+27\\(%\[\^,\]+\\)," 1 { target ia32 } } } */

gcc/testsuite/gcc.target/i386/pr90773-4.c

@@ -0,0 +1,13 @@
+/* { dg-do compile { target { ! ia32 } } } */
+/* { dg-options "-O2 -mno-avx -msse2 -mtune=generic" } */
+
+extern char *dst;
+
+void
+foo (void)
+{
+  __builtin_memset (dst, 0, 31);
+}
+
+/* { dg-final { scan-assembler-times "movups\[\\t \]+%xmm\[0-9\]+, \\(%\[\^,\]+\\)" 1 } } */
+/* { dg-final { scan-assembler-times "movups\[\\t \]+%xmm\[0-9\]+, 15\\(%\[\^,\]+\\)" 1 } } */

gcc/testsuite/gcc.target/i386/pr90773-5.c

@@ -0,0 +1,13 @@
+/* { dg-do compile { target { ! ia32 } } } */
+/* { dg-options "-O2 -mno-avx -msse2 -mtune=generic" } */
+
+extern char *dst;
+
+void
+foo (void)
+{
+  __builtin_memset (dst, 0, 21);
+}
+
+/* { dg-final { scan-assembler-times "movups\[\\t \]+%xmm\[0-9\]+, \\(%\[\^,\]+\\)" 1 } } */
+/* { dg-final { scan-assembler-times "movq\[\\t \]+\\\$0+, 13\\(%\[\^,\]+\\)" 1 } } */

gcc/testsuite/gcc.target/i386/pr90773-6.c

@@ -0,0 +1,11 @@
+/* { dg-do compile { target { ! ia32 } } } */
+/* { dg-options "-O2 -mno-avx -msse2 -mtune=generic" } */
+
+void
+foo (char *dst, char *src)
+{
+  __builtin_memcpy (dst, src, 255);
+}
+
+/* { dg-final { scan-assembler-times "movdqu\[\\t \]+\[0-9\]*\\(%\[\^,\]+\\)," 16 } } */
+/* { dg-final { scan-assembler-not "mov\[bwlq\]" } } */

gcc/testsuite/gcc.target/i386/pr90773-7.c

@@ -0,0 +1,11 @@
+/* { dg-do compile { target { ! ia32 } } } */
+/* { dg-options "-O2 -mno-avx -msse2 -mtune=skylake" } */
+
+void
+foo (char *dst)
+{
+  __builtin_memset (dst, 0, 255);
+}
+
+/* { dg-final { scan-assembler-times "movups\[\\t \]+%xmm\[0-9\]+, \[0-9\]*\\(%\[\^,\]+\\)" 16 } } */
+/* { dg-final { scan-assembler-not "mov\[bwlq\]" } } */

gcc/testsuite/gcc.target/i386/pr90773-8.c

@@ -0,0 +1,13 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -mtune=generic" } */
+
+extern char *dst;
+
+void
+foo (void)
+{
+  __builtin_memset (dst, 0, 5);
+}
+
+/* { dg-final { scan-assembler-times "movl\[\\t \]+.+, \\(%\[\^,\]+\\)" 1 } } */
+/* { dg-final { scan-assembler-times "movb\[\\t \]+.+, 4\\(%\[\^,\]+\\)" 1 } } */

gcc/testsuite/gcc.target/i386/pr90773-9.c

@@ -0,0 +1,13 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -mtune=generic" } */
+
+extern char *dst;
+
+void
+foo (void)
+{
+  __builtin_memset (dst, 0, 6);
+}
+
+/* { dg-final { scan-assembler-times "movl\[\\t \]+.+, \\(%\[\^,\]+\\)" 1 } } */
+/* { dg-final { scan-assembler-times "movw\[\\t \]+.+, 4\\(%\[\^,\]+\\)" 1 } } */