New parameters to control stringop expansion libcall strategy

Xinliang David Li davidxl@google.com
Thu Aug 8 06:17:00 GMT 2013


Updated patch attached (fixed header, buffer overflow, and warning -->
error problems).

Ok for trunk?

thanks,

David

On Wed, Aug 7, 2013 at 6:04 PM, Joseph S. Myers <joseph@codesourcery.com> wrote:
> On Wed, 7 Aug 2013, Xinliang David Li wrote:
>
>> > Why the exception?  This should only be used on the host, not the target.
>>
>> Sorry, I copied the boiler-plate header from i386.h -- is it wrong there too?
>
> tm.h gets included in target code because we haven't finished separating
> target macros used on the target from those used on the host.
>
> --
> Joseph S. Myers
> joseph@codesourcery.com
-------------- next part --------------
Index: config/i386/stringop.def
===================================================================
--- config/i386/stringop.def	(revision 0)
+++ config/i386/stringop.def	(revision 0)
@@ -0,0 +1,37 @@
+/* Definitions for stringop strategy for IA-32.
+   Copyright (C) 2013 Free Software Foundation, Inc.
+
+This file is part of GCC.
+
+GCC is free software; you can redistribute it and/or modify
+it under the terms of the GNU General Public License as published by
+the Free Software Foundation; either version 3, or (at your option)
+any later version.
+
+GCC is distributed in the hope that it will be useful,
+but WITHOUT ANY WARRANTY; without even the implied warranty of
+MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+GNU General Public License for more details.
+
+You should have received a copy of the GNU General Public License 
+along with GCC; see the files COPYING3.  If not,
+see <http://www.gnu.org/licenses/>.  */
+
+DEF_ENUM
+DEF_ALG (no_stringop, no_stringop)
+DEF_ENUM
+DEF_ALG (libcall, libcall)
+DEF_ENUM
+DEF_ALG (rep_prefix_1_byte, rep_byte)
+DEF_ENUM
+DEF_ALG (rep_prefix_4_byte, rep_4byte)
+DEF_ENUM
+DEF_ALG (rep_prefix_8_byte, rep_8byte)
+DEF_ENUM
+DEF_ALG (loop_1_byte, byte_loop)
+DEF_ENUM
+DEF_ALG (loop, loop)
+DEF_ENUM
+DEF_ALG (unrolled_loop, unrolled_loop)
+DEF_ENUM
+DEF_ALG (vector_loop, vector_loop)
Index: config/i386/stringop.opt
===================================================================
--- config/i386/stringop.opt	(revision 0)
+++ config/i386/stringop.opt	(revision 0)
@@ -0,0 +1,31 @@
+/* Definitions for stringop option handling for IA-32.
+   Copyright (C) 2013 Free Software Foundation, Inc.
+
+This file is part of GCC.
+
+GCC is free software; you can redistribute it and/or modify
+it under the terms of the GNU General Public License as published by
+the Free Software Foundation; either version 3, or (at your option)
+any later version.
+
+GCC is distributed in the hope that it will be useful,
+but WITHOUT ANY WARRANTY; without even the implied warranty of
+MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+GNU General Public License for more details.
+
+You should have received a copy of the GNU General Public License
+along with GCC; see the files COPYING3.  If not,
+see <http://www.gnu.org/licenses/>.  */
+
+Enum(stringop_alg) String(rep_byte) Value(rep_prefix_1_byte)
+
+#undef DEF_ENUM
+#define DEF_ENUM EnumValue
+
+#undef DEF_ALG
+#define DEF_ALG(alg, name) Enum(stringop_alg) String(name) Value(alg)
+
+#include "stringop.def"
+
+#undef DEF_ENUM
+#undef DEF_ALG
Index: config/i386/i386-opts.h
===================================================================
--- config/i386/i386-opts.h	(revision 201581)
+++ config/i386/i386-opts.h	(working copy)
@@ -28,15 +28,17 @@ see the files COPYING3 and COPYING.RUNTI
 /* Algorithm to expand string function with.  */
 enum stringop_alg
 {
-   no_stringop,
-   libcall,
-   rep_prefix_1_byte,
-   rep_prefix_4_byte,
-   rep_prefix_8_byte,
-   loop_1_byte,
-   loop,
-   unrolled_loop,
-   vector_loop
+#undef DEF_ENUM
+#define DEF_ENUM
+
+#undef DEF_ALG
+#define DEF_ALG(alg, name) alg, 
+
+#include "stringop.def"
+last_alg
+
+#undef DEF_ENUM
+#undef DEF_ALG
 };
 
 /* Available call abi.  */
Index: config/i386/i386.c
===================================================================
--- config/i386/i386.c	(revision 201582)
+++ config/i386/i386.c	(working copy)
@@ -158,7 +158,7 @@ struct processor_costs ix86_size_cost =
 };
 
 /* Processor costs (relative to an add) */
-static const
+static
 struct processor_costs i386_cost = {	/* 386 specific costs */
   COSTS_N_INSNS (1),			/* cost of an add instruction */
   COSTS_N_INSNS (1),			/* cost of a lea instruction */
@@ -228,7 +228,7 @@ struct processor_costs i386_cost = {	/*
   1,					/* cond_not_taken_branch_cost.  */
 };
 
-static const
+static
 struct processor_costs i486_cost = {	/* 486 specific costs */
   COSTS_N_INSNS (1),			/* cost of an add instruction */
   COSTS_N_INSNS (1),			/* cost of a lea instruction */
@@ -300,7 +300,7 @@ struct processor_costs i486_cost = {	/*
   1,					/* cond_not_taken_branch_cost.  */
 };
 
-static const
+static
 struct processor_costs pentium_cost = {
   COSTS_N_INSNS (1),			/* cost of an add instruction */
   COSTS_N_INSNS (1),			/* cost of a lea instruction */
@@ -370,7 +370,7 @@ struct processor_costs pentium_cost = {
   1,					/* cond_not_taken_branch_cost.  */
 };
 
-static const
+static
 struct processor_costs pentiumpro_cost = {
   COSTS_N_INSNS (1),			/* cost of an add instruction */
   COSTS_N_INSNS (1),			/* cost of a lea instruction */
@@ -449,7 +449,7 @@ struct processor_costs pentiumpro_cost =
   1,					/* cond_not_taken_branch_cost.  */
 };
 
-static const
+static
 struct processor_costs geode_cost = {
   COSTS_N_INSNS (1),			/* cost of an add instruction */
   COSTS_N_INSNS (1),			/* cost of a lea instruction */
@@ -520,7 +520,7 @@ struct processor_costs geode_cost = {
   1,					/* cond_not_taken_branch_cost.  */
 };
 
-static const
+static
 struct processor_costs k6_cost = {
   COSTS_N_INSNS (1),			/* cost of an add instruction */
   COSTS_N_INSNS (2),			/* cost of a lea instruction */
@@ -593,7 +593,7 @@ struct processor_costs k6_cost = {
   1,					/* cond_not_taken_branch_cost.  */
 };
 
-static const
+static
 struct processor_costs athlon_cost = {
   COSTS_N_INSNS (1),			/* cost of an add instruction */
   COSTS_N_INSNS (2),			/* cost of a lea instruction */
@@ -666,7 +666,7 @@ struct processor_costs athlon_cost = {
   1,					/* cond_not_taken_branch_cost.  */
 };
 
-static const
+static
 struct processor_costs k8_cost = {
   COSTS_N_INSNS (1),			/* cost of an add instruction */
   COSTS_N_INSNS (2),			/* cost of a lea instruction */
@@ -1267,7 +1267,7 @@ struct processor_costs btver2_cost = {
   1,					/* cond_not_taken_branch_cost.  */
 };
 
-static const
+static
 struct processor_costs pentium4_cost = {
   COSTS_N_INSNS (1),			/* cost of an add instruction */
   COSTS_N_INSNS (3),			/* cost of a lea instruction */
@@ -1338,7 +1338,7 @@ struct processor_costs pentium4_cost = {
   1,					/* cond_not_taken_branch_cost.  */
 };
 
-static const
+static
 struct processor_costs nocona_cost = {
   COSTS_N_INSNS (1),			/* cost of an add instruction */
   COSTS_N_INSNS (1),			/* cost of a lea instruction */
@@ -1411,7 +1411,7 @@ struct processor_costs nocona_cost = {
   1,					/* cond_not_taken_branch_cost.  */
 };
 
-static const
+static
 struct processor_costs atom_cost = {
   COSTS_N_INSNS (1),			/* cost of an add instruction */
   COSTS_N_INSNS (1) + 1,		/* cost of a lea instruction */
@@ -1558,7 +1558,7 @@ struct processor_costs slm_cost = {
 };
 
 /* Generic64 should produce code tuned for Nocona and K8.  */
-static const
+static
 struct processor_costs generic64_cost = {
   COSTS_N_INSNS (1),			/* cost of an add instruction */
   /* On all chips taken into consideration lea is 2 cycles and more.  With
@@ -1637,7 +1637,7 @@ struct processor_costs generic64_cost =
 };
 
 /* core_cost should produce code tuned for Core familly of CPUs.  */
-static const
+static
 struct processor_costs core_cost = {
   COSTS_N_INSNS (1),			/* cost of an add instruction */
   /* On all chips taken into consideration lea is 2 cycles and more.  With
@@ -1719,7 +1719,7 @@ struct processor_costs core_cost = {
 
 /* Generic32 should produce code tuned for PPro, Pentium4, Nocona,
    Athlon and K8.  */
-static const
+static
 struct processor_costs generic32_cost = {
   COSTS_N_INSNS (1),			/* cost of an add instruction */
   COSTS_N_INSNS (1) + 1,		/* cost of a lea instruction */
@@ -2926,6 +2926,149 @@ ix86_debug_options (void)
 
   return;
 }
+
+static const char *stringop_alg_names[] = {
+#define DEF_ENUM
+#define DEF_ALG(alg, name) #name,
+#include "stringop.def"
+#undef DEF_ENUM
+#undef DEF_ALG
+};
+
+/* Parse parameter string passed to -mmemcpy-strategy= or -mmemset-strategy=.
+   The string is of the following form (or comma separated list of it):
+
+     strategy_alg:max_size:[align|noalign]
+
+   where the full size range for the strategy is either [0, max_size] or
+   [min_size, max_size], in which min_size is the max_size + 1 of the
+   preceding range.  The last size range must have max_size == -1.
+
+   Examples:
+
+    1.
+       -mmemcpy-strategy=libcall:-1:noalign
+
+      this is equivalent to (for known size memcpy) -mstringop-strategy=libcall
+
+
+   2.
+      -mmemset-strategy=rep_8byte:16:noalign,vector_loop:2048:align,libcall:-1:noalign
+
+      This is to tell the compiler to use the following strategy for memset
+      1) when the expected size is between [1, 16], use rep_8byte strategy;
+      2) when the size is between [17, 2048], use vector_loop;
+      3) when the size is > 2048, use libcall.  */
+
+struct stringop_size_range
+{
+  int min;
+  int max;
+  stringop_alg alg;
+  bool noalign;
+};
+
+static void
+ix86_parse_stringop_strategy_string (char *strategy_str, bool is_memset)
+{
+  const struct stringop_algs *default_algs;
+  stringop_size_range input_ranges[MAX_STRINGOP_ALGS];
+  char *curr_range_str, *next_range_str;
+  int i = 0, n = 0;
+
+  if (is_memset)
+    default_algs = &ix86_cost->memset[TARGET_64BIT != 0];
+  else
+    default_algs = &ix86_cost->memcpy[TARGET_64BIT != 0];
+
+  curr_range_str = strategy_str;
+
+  do
+    {
+      int mins, maxs;
+      stringop_alg alg;
+      char alg_name[128];
+      char align[16];
+      next_range_str = strchr (curr_range_str, ',');
+      if (next_range_str)
+        *next_range_str++ = '\0';
+
+      if (3 != sscanf (curr_range_str, "%20[^:]:%d:%10s",
+                       alg_name, &maxs, align))
+        {
+          error ("Wrong arg %s to option %s", curr_range_str,
+                 is_memset ? "-mmemset_strategy=" : "-mmemcpy_strategy=");
+          return;
+        }
+
+      if (n > 0 && (maxs < (mins = input_ranges[n - 1].max + 1) && maxs != -1))
+        {
+          error ("Size ranges of option %s should be increasing",
+                 is_memset ? "-mmemset_strategy=" : "-mmemcpy_strategy=");
+          return;
+        }
+
+      for (i = 0; i < last_alg; i++)
+        {
+          if (!strcmp (alg_name, stringop_alg_names[i]))
+            {
+              alg = (stringop_alg) i;
+              break;
+            }
+        }
+
+      if (i == last_alg)
+        {
+          error ("Wrong stringop strategy name %s specified for option %s",
+                 alg_name,
+                 is_memset ? "-mmemset_strategy=" : "-mmemcpy_strategy=");
+          return;
+        }
+
+      input_ranges[n].min = mins;
+      input_ranges[n].max = maxs;
+      input_ranges[n].alg = alg;
+      if (!strcmp (align, "align"))
+        input_ranges[n].noalign = false;
+      else if (!strcmp (align, "noalign"))
+        input_ranges[n].noalign = true;
+      else
+        {
+          error ("Unknown alignment %s specified for option %s",
+                 align, is_memset ? "-mmemset_strategy=" : "-mmemcpy_strategy=");
+          return;
+        }
+      n++;
+      curr_range_str = next_range_str;
+    }
+  while (curr_range_str);
+
+  if (input_ranges[n - 1].max != -1)
+    {
+      error ("The max value for the last size range should be -1"
+             " for option %s",
+             is_memset ? "-mmemset_strategy=" : "-mmemcpy_strategy=");
+      return;
+    }
+
+  if (n > MAX_STRINGOP_ALGS)
+    {
+      error ("Too many size ranges specified in option %s",
+             is_memset ? "-mmemset_strategy=" : "-mmemcpy_strategy=");
+      return;
+    }
+
+  /* Now override the default algs array.  */
+  for (i = 0; i < n; i++)
+    {
+      *const_cast<int *>(&default_algs->size[i].max) = input_ranges[i].max;
+      *const_cast<stringop_alg *>(&default_algs->size[i].alg)
+          = input_ranges[i].alg;
+      *const_cast<int *>(&default_algs->size[i].noalign)
+          = input_ranges[i].noalign;
+    }
+}
+
 

 /* Override various settings based on options.  If MAIN_ARGS_P, the
    options are from the command line, otherwise they are from
@@ -4081,6 +4224,21 @@ ix86_option_override_internal (bool main
   /* Handle stack protector */
   if (!global_options_set.x_ix86_stack_protector_guard)
     ix86_stack_protector_guard = TARGET_HAS_BIONIC ? SSP_GLOBAL : SSP_TLS;
+
+  /* Handle -mmemcpy-strategy= and -mmemset-strategy=  */
+  if (ix86_tune_memcpy_strategy)
+    {
+      char *str = xstrdup (ix86_tune_memcpy_strategy);
+      ix86_parse_stringop_strategy_string (str, false);
+      free (str);
+    }
+
+  if (ix86_tune_memset_strategy)
+    {
+      char *str = xstrdup (ix86_tune_memset_strategy);
+      ix86_parse_stringop_strategy_string (str, true);
+      free (str);
+    }
 }
 
 /* Implement the TARGET_OPTION_OVERRIDE hook.  */
@@ -22964,6 +23122,7 @@ ix86_expand_movmem (rtx dst, rtx src, rt
     {
     case libcall:
     case no_stringop:
+    case last_alg:
       gcc_unreachable ();
     case loop_1_byte:
       need_zero_guard = true;
@@ -23154,6 +23313,7 @@ ix86_expand_movmem (rtx dst, rtx src, rt
     {
     case libcall:
     case no_stringop:
+    case last_alg:
       gcc_unreachable ();
     case loop_1_byte:
     case loop:
@@ -23365,6 +23525,7 @@ ix86_expand_setmem (rtx dst, rtx count_e
     {
     case libcall:
     case no_stringop:
+    case last_alg:
       gcc_unreachable ();
     case loop:
       need_zero_guard = true;
@@ -23542,6 +23703,7 @@ ix86_expand_setmem (rtx dst, rtx count_e
     {
     case libcall:
     case no_stringop:
+    case last_alg:
       gcc_unreachable ();
     case loop_1_byte:
     case loop:
Index: config/i386/i386.opt
===================================================================
--- config/i386/i386.opt	(revision 201582)
+++ config/i386/i386.opt	(working copy)
@@ -316,6 +316,14 @@ mstack-arg-probe
 Target Report Mask(STACK_PROBE) Save
 Enable stack probing
 
+mmemcpy-strategy=
+Target RejectNegative Joined Var(ix86_tune_memcpy_strategy)
+Specify memcpy expansion strategy when expected size is known
+
+mmemset-strategy=
+Target RejectNegative Joined Var(ix86_tune_memset_strategy)
+Specify memset expansion strategy when expected size is known
+
 mstringop-strategy=
 Target RejectNegative Joined Enum(stringop_alg) Var(ix86_stringop_alg) Init(no_stringop)
 Chose strategy to generate stringop using
Index: doc/invoke.texi
===================================================================
--- doc/invoke.texi	(revision 201581)
+++ doc/invoke.texi	(working copy)
@@ -652,6 +652,7 @@ Objective-C and Objective-C++ Dialects}.
 -mbmi2 -mrtm -mlwp -mthreads @gol
 -mno-align-stringops  -minline-all-stringops @gol
 -minline-stringops-dynamically -mstringop-strategy=@var{alg} @gol
+-mmemcpy-strategy=@var{strategy} -mmemset-strategy=@var{strategy} 
 -mpush-args  -maccumulate-outgoing-args  -m128bit-long-double @gol
 -m96bit-long-double -mlong-double-64 -mlong-double-80 @gol
 -mregparm=@var{num}  -msseregparm @gol
@@ -14651,6 +14652,24 @@ Expand into an inline loop.
 Always use a library call.
 @end table
 
+@item -mmemcpy-strategy=@var{strategy}
+@opindex mmemcpy-strategy=@var{strategy}
+Override the internal decision heuristic to decide if @code{__builtin_memcpy}
+should be inlined and what inline algorithm to use when the expected size
+of the copy operation is known. @var{strategy} 
+is a comma-separated list of @var{alg}:@var{max_size}:@var{dest_align} triplets. 
+@var{alg} is specified in @option{-mstringop-strategy}, @var{max_size} specifies
+the max byte size with which inline algorithm @var{alg} is allowed.  For the last
+triplet, the @var{max_size} must be @code{-1}. The @var{max_size} of the triplets
+in the list must be specified in increasing order.  The minimal byte size for 
+@var{alg} is @code{0} for the first triplet and @code{@var{max_size} + 1} of the 
+preceding range.
+
+@item -mmemset-strategy=@var{strategy}
+@opindex mmemset-strategy=@var{strategy}
+The option is similar to @option{-mmemcpy-strategy=} except that it is to control
+@code{__builtin_memset} expansion.
+
 @item -momit-leaf-frame-pointer
 @opindex momit-leaf-frame-pointer
 Don't keep the frame pointer in a register for leaf functions.  This
Index: testsuite/gcc.target/i386/memcpy-strategy-2.c
===================================================================
--- testsuite/gcc.target/i386/memcpy-strategy-2.c	(revision 0)
+++ testsuite/gcc.target/i386/memcpy-strategy-2.c	(revision 0)
@@ -0,0 +1,12 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -march=atom -mmemcpy-strategy=vector_loop:3000:align,libcall:-1:align" } */
+/* { dg-final { scan-assembler-times "movdqa" 8 { target { ! { ia32 } } } } } */
+/* { dg-final { scan-assembler-times "movdqa" 4 { target { ia32 } } } } */
+
+char a[2048];
+char b[2048];
+void t (void)
+{
+  __builtin_memcpy (a, b, 2048);
+}
+
Index: testsuite/gcc.target/i386/memset-strategy-1.c
===================================================================
--- testsuite/gcc.target/i386/memset-strategy-1.c	(revision 0)
+++ testsuite/gcc.target/i386/memset-strategy-1.c	(revision 0)
@@ -0,0 +1,10 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -march=atom -mmemset-strategy=libcall:-1:align" } */
+/* { dg-final { scan-assembler-times "memset" 2  } } */
+
+char a[2048];
+void t (void)
+{
+  __builtin_memset (a, 1, 2048);
+}
+
Index: testsuite/gcc.target/i386/memcpy-strategy-3.c
===================================================================
--- testsuite/gcc.target/i386/memcpy-strategy-3.c	(revision 0)
+++ testsuite/gcc.target/i386/memcpy-strategy-3.c	(revision 0)
@@ -0,0 +1,10 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -march=atom -mmemcpy-strategy=vector_loop:2000:align,libcall:-1:align" } */
+/* { dg-final { scan-assembler-times "memcpy" 2  } } */
+
+char a[2048];
+char b[2048];
+void t (void)
+{
+  __builtin_memcpy (a, b, 2048);
+}
Index: testsuite/gcc.target/i386/memcpy-strategy-1.c
===================================================================
--- testsuite/gcc.target/i386/memcpy-strategy-1.c	(revision 0)
+++ testsuite/gcc.target/i386/memcpy-strategy-1.c	(revision 0)
@@ -0,0 +1,12 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -march=atom -mmemcpy-strategy=vector_loop:-1:align" } */
+/* { dg-final { scan-assembler-times "movdqa" 8 { target { ! { ia32 } } } } } */
+/* { dg-final { scan-assembler-times "movdqa" 4 { target { ia32 } } } } */
+
+char a[2048];
+char b[2048];
+void t (void)
+{
+  __builtin_memcpy (a, b, 2048);
+}
+


More information about the Gcc-patches mailing list