[gcc(refs/users/aoliva/heads/testme)] Introduce -finline-memset-loops

[Alexandre Oliva <aoliva@gcc.gnu.org>]

https://gcc.gnu.org/g:3f62b511ae76889c9fd92d799f502c206d975eb5

commit 3f62b511ae76889c9fd92d799f502c206d975eb5
Author: Alexandre Oliva <oliva@adacore.com>
Date:   Thu Dec 22 21:28:44 2022 -0300

    Introduce -finline-memset-loops
    
    try_store_by_multiple_pieces was added not long ago, enabling
    variable-sized memset to be expanded inline when the worst-case
    in-range constant length would, using conditional blocks with powers
    of two to cover all possibilities of length and alignment.
    
    This patch extends the memset expansion to start with a loop, so as to
    still take advantage of known alignment even with long lengths, but
    without necessarily adding store blocks for every power of two.
    
    This makes it possible for any memset call to be expanded, even if
    storing a single byte per iteration.  Surely efficient implementations
    of memset can do better, with a pre-loop to increase alignment, but
    that would likely be excessive for inline expansions of memset.
    
    Still, in some cases, users prefer to inline memset, even if it's not
    as performant, or when it's known to be performant in ways the
    compiler can't tell, to avoid depending on a C runtime library.
    
    With this flag, global or per-function optimizations may enable inline
    expansion of memset to be selectively requested, while the
    infrastructure for that may enable us to introduce per-target tuning
    to enable such looping even advantageous, even if not explicitly
    requested.
    
    
    for  gcc/ChangeLog
    
            * builtins.cc (try_store_by_multiple_pieces): Support starting
            with a loop.
            * common.opt (finline-memset-loops): New.
            * doc/invoke.texi (-finline-memset-loops): Add.
    
    for  gcc/testsuite/ChangeLog
    
            * gcc.dg/torture/inline-mem-set-1.c: New.

Diff:
---
 gcc/builtins.cc                                 | 50 +++++++++++++++++++++++--
 gcc/common.opt                                  |  4 ++
 gcc/doc/invoke.texi                             | 13 ++++++-
 gcc/testsuite/gcc.dg/torture/inline-mem-set-1.c | 14 +++++++
 4 files changed, 77 insertions(+), 4 deletions(-)

diff --git a/gcc/builtins.cc b/gcc/builtins.cc
index af45829875e..865d7a6d7a2 100644
--- a/gcc/builtins.cc
+++ b/gcc/builtins.cc
@@ -4361,9 +4361,37 @@ try_store_by_multiple_pieces (rtx to, rtx len, unsigned int ctz_len,
   if (max_bits >= 0)
     xlenest += ((HOST_WIDE_INT_1U << max_bits) * 2
 		- (HOST_WIDE_INT_1U << ctz_len));
+  bool max_loop = false;
   if (!can_store_by_pieces (xlenest, builtin_memset_read_str,
 			    &valc, align, true))
-    return false;
+    {
+      if (!flag_inline_memset_loops)
+	return false;
+      while (--max_bits >= sctz_len)
+	{
+	  xlenest = ((HOST_WIDE_INT_1U << max_bits) * 2
+		     - (HOST_WIDE_INT_1U << ctz_len));
+	  if (can_store_by_pieces (xlenest + blksize,
+				   builtin_memset_read_str,
+				   &valc, align, true))
+	    {
+	      max_loop = true;
+	      break;
+	    }
+	  if (!blksize)
+	    continue;
+	  if (can_store_by_pieces (xlenest,
+				   builtin_memset_read_str,
+				   &valc, align, true))
+	    {
+	      blksize = 0;
+	      max_loop = true;
+	      break;
+	    }
+	}
+      if (!max_loop)
+	return false;
+    }
 
   by_pieces_constfn constfun;
   void *constfundata;
@@ -4405,6 +4433,7 @@ try_store_by_multiple_pieces (rtx to, rtx len, unsigned int ctz_len,
      the least significant bit possibly set in the length.  */
   for (int i = max_bits; i >= sctz_len; i--)
     {
+      rtx_code_label *loop_label = NULL;
       rtx_code_label *label = NULL;
       blksize = HOST_WIDE_INT_1U << i;
 
@@ -4423,14 +4452,24 @@ try_store_by_multiple_pieces (rtx to, rtx len, unsigned int ctz_len,
       else if ((max_len & blksize) == 0)
 	continue;
 
+      if (max_loop && i == max_bits)
+	{
+	  loop_label = gen_label_rtx ();
+	  emit_label (loop_label);
+	  /* Since we may run this multiple times, don't assume we
+	     know anything about the offset.  */
+	  clear_mem_offset (to);
+	}
+
       /* Issue a store of BLKSIZE bytes.  */
+      bool update_needed = i != sctz_len || loop_label;
       to = store_by_pieces (to, blksize,
 			    constfun, constfundata,
 			    align, true,
-			    i != sctz_len ? RETURN_END : RETURN_BEGIN);
+			    update_needed ? RETURN_END : RETURN_BEGIN);
 
       /* Adjust REM and PTR, unless this is the last iteration.  */
-      if (i != sctz_len)
+      if (update_needed)
 	{
 	  emit_move_insn (ptr, force_operand (XEXP (to, 0), NULL_RTX));
 	  to = replace_equiv_address (to, ptr);
@@ -4438,6 +4477,11 @@ try_store_by_multiple_pieces (rtx to, rtx len, unsigned int ctz_len,
 	  emit_move_insn (rem, force_operand (rem_minus_blksize, NULL_RTX));
 	}
 
+      if (loop_label)
+	emit_cmp_and_jump_insns (rem, GEN_INT (blksize), GE, NULL,
+				 ptr_mode, 1, loop_label,
+				 profile_probability::likely ());
+
       if (label)
 	{
 	  emit_label (label);
diff --git a/gcc/common.opt b/gcc/common.opt
index d0371aec8db..5d28f054241 100644
--- a/gcc/common.opt
+++ b/gcc/common.opt
@@ -1874,6 +1874,10 @@ finline-atomics
 Common Var(flag_inline_atomics) Init(1) Optimization
 Inline __atomic operations when a lock free instruction sequence is available.
 
+finline-memset-loops
+Common Var(flag_inline_memset_loops) Init(0) Optimization
+Inline memset even if it requires loops.
+
 fcf-protection
 Common RejectNegative Alias(fcf-protection=,full)
 
diff --git a/gcc/doc/invoke.texi b/gcc/doc/invoke.texi
index dec0cdb9d35..063ae03b30e 100644
--- a/gcc/doc/invoke.texi
+++ b/gcc/doc/invoke.texi
@@ -548,7 +548,8 @@ Objective-C and Objective-C++ Dialects}.
 -fgcse-sm  -fhoist-adjacent-loads  -fif-conversion @gol
 -fif-conversion2  -findirect-inlining @gol
 -finline-functions  -finline-functions-called-once  -finline-limit=@var{n} @gol
--finline-small-functions -fipa-modref -fipa-cp  -fipa-cp-clone @gol
+-finline-memset-loops -finline-small-functions @gol
+-fipa-modref -fipa-cp  -fipa-cp-clone @gol
 -fipa-bit-cp  -fipa-vrp  -fipa-pta  -fipa-profile  -fipa-pure-const @gol
 -fipa-reference  -fipa-reference-addressable @gol
 -fipa-stack-alignment  -fipa-icf  -fira-algorithm=@var{algorithm} @gol
@@ -11961,6 +11962,16 @@ in its own right.
 Enabled at levels @option{-O1}, @option{-O2}, @option{-O3} and @option{-Os},
 but not @option{-Og}.
 
+@item -finline-memset-loops
+@opindex finline-memset-loops
+Expand @code{memset} calls inline, even when the length is variable or
+big enough as to require looping.  This may enable the compiler to take
+advantage of known alignment and length multipliers, but it will often
+generate code that is less efficient than performant implementations of
+@code{memset}, and grow code size so much that even a less performant
+@code{memset} may run faster due to better use of the code cache.  This
+option is disabled by default.
+
 @item -fearly-inlining
 @opindex fearly-inlining
 Inline functions marked by @code{always_inline} and functions whose body seems
diff --git a/gcc/testsuite/gcc.dg/torture/inline-mem-set-1.c b/gcc/testsuite/gcc.dg/torture/inline-mem-set-1.c
new file mode 100644
index 00000000000..73bd1025f19
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/torture/inline-mem-set-1.c
@@ -0,0 +1,14 @@
+/* { dg-do compile } */
+/* { dg-options "-finline-memset-loops -gno-record-gcc-switches -fno-lto" } */
+
+void *zero (unsigned long long (*p)[32], int n)
+{
+  return __builtin_memset (p, 0, n * sizeof (*p));
+}
+
+void *ones (char (*p)[128], int n)
+{
+  return __builtin_memset (p, -1, n * sizeof (*p));
+}
+
+/* { dg-final { scan-assembler-not "memset" } } */