Implement -mmemcpy-strategy= and -mmemset-strategy= options

From-SVN: r201645

gcc/ChangeLog

+2013-08-09  Xinliang David Li  <davidxl@google.com>
+
+	* config/i386/stringop.def: New file.
+	* config/i386/stringop.opt: New file.
+	* config/i386/i386-opts.h: Include stringopt.def.
+	* config/i386/i386.opt: Include stringopt.opt.
+	* config/i386/i386.c (ix86_option_override_internal):
+	Override default size based stringop inline strategies
+	with options.
+	* config/i386/i386.c (ix86_parse_stringop_strategy_string):
+	New function.
+
 2013-08-09  Jan Hubicka  <jh@suse.cz>
 
 	 * ipa-ref.c (ipa_clear_stmts_in_references): Clear lto_stmt_uid, too.

gcc/config/i386/i386-opts.h

@@ -28,15 +28,17 @@ see the files COPYING3 and COPYING.RUNTIME respectively.  If not, see
 /* 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.  */

gcc/config/i386/i386.h

@@ -170,7 +170,7 @@ struct processor_costs {
   const int fsqrt;		/* cost of FSQRT instruction.  */
 				/* Specify what algorithm
 				   to use for stringops on unknown size.  */
-  struct stringop_algs memcpy[2], memset[2];
+  struct stringop_algs *memcpy, *memset;
   const int scalar_stmt_cost;   /* Cost of any scalar operation, excluding
 				   load and store.  */
   const int scalar_load_cost;   /* Cost of scalar load.  */

gcc/config/i386/i386.opt

@@ -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

gcc/config/i386/stringop.def

+/* 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)

gcc/config/i386/stringop.opt

+/* 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

gcc/doc/invoke.texi

@@ -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

gcc/testsuite/ChangeLog

+2013-08-09  Xinliang David Li  <davidxl@google.com>
+
+	* gcc.target/i386/memcpy-strategy-1.c: New test.
+	* gcc.target/i386/memcpy-strategy-2.c: Ditto.
+	* gcc.target/i386/memset-strategy-1.c: Ditto.
+	* gcc.target/i386/memcpy-strategy-3.c: Ditto.
+
 2013-08-09  Jan Hubicka  <jh@suse.cz>
 
 	* gcc.dg/tree-prof/crossmodule-indircall-1.c: New testcase.

gcc/testsuite/gcc.target/i386/memcpy-strategy-1.c

+/* { 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);
+}
+

gcc/testsuite/gcc.target/i386/memcpy-strategy-2.c

+/* { 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);
+}
+

gcc/testsuite/gcc.target/i386/memcpy-strategy-3.c

+/* { 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);
+}

gcc/testsuite/gcc.target/i386/memset-strategy-1.c

+/* { 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);
+}
+