Add X86_TUNE_AVOID_LEA_FOR_ADDR

ix86_split_lea_for_addr transforms a single LEA instruction into a
series of MOV and ADD instructions.  For

lea 0x400(%edx, %ecx, 8), %edx

we get

mov %ecx, %edx
add %ecx, %edx
add %ecx, %edx
add %ecx, %edx
add %ecx, %edx
add %ecx, %edx
add %ecx, %edx
add %ecx, %edx
add $0x400, %edx

For -mtune=intel, we want to turn on X86_TUNE_OPT_AGU, but avoid
ix86_split_lea_for_addr to optimize for both Haswell and Silvermont.
This patch adds X86_TUNE_AVOID_LEA_FOR_ADDR and PROCESSOR_INTEL.
We keep PROCESSOR_INTEL the same as PROCESSOR_SILVERMONT, except that
X86_TUNE_AVOID_LEA_FOR_ADDR isn't turned on for PROCESSOR_INTEL.

	* config/i386/i386-c.c (ix86_target_macros_internal): Handle
	PROCESSOR_INTEL.  Treat like PROCESSOR_GENERIC.
	* config/i386/i386.c (intel_memcpy): New.  Duplicate slm_memcpy.
	(intel_memset): New.  Duplicate slm_memset.
	(intel_cost): New.  Duplicate slm_cost.
	(m_INTEL): New macro.
	(processor_target_table): Add "intel".
	(ix86_option_override_internal): Replace PROCESSOR_SILVERMONT
	with PROCESSOR_INTEL for "intel".
	(ix86_lea_outperforms): Support PROCESSOR_INTEL.  Duplicate
	PROCESSOR_SILVERMONT.
	(ix86_avoid_lea_for_addr): Check TARGET_AVOID_LEA_FOR_ADDR
	instead of TARGET_OPT_AGU.
	(ix86_issue_rate): Likewise.
	(ix86_adjust_cost): Likewise.
	(ia32_multipass_dfa_lookahead): Likewise.
	(swap_top_of_ready_list): Likewise.
	(ix86_sched_reorder): Likewise.
	* config/i386/i386.h (TARGET_INTEL): New.
	(TARGET_AVOID_LEA_FOR_ADDR): Likewise.
	(processor_type): Add PROCESSOR_INTEL.
	* config/i386/x86-tune.def: Support m_INTEL. Duplicate
	m_SILVERMONT.  Add X86_TUNE_AVOID_LEA_FOR_ADDR.


git-svn-id: svn+ssh://gcc.gnu.org/svn/gcc/trunk@206717 138bc75d-0d04-0410-961f-82ee72b054a4

5 files changed, 161 insertions, 32 deletions

diff --git a/gcc/ChangeLog b/gcc/ChangeLog
index 21b597144f4..df6e491f0ff 100644
--- a/gcc/ChangeLog
+++ b/gcc/ChangeLog
@@ -1,3 +1,29 @@
+2014-01-17  H.J. Lu  <hongjiu.lu@intel.com>
+
+	* config/i386/i386-c.c (ix86_target_macros_internal): Handle
+	PROCESSOR_INTEL.  Treat like PROCESSOR_GENERIC.
+	* config/i386/i386.c (intel_memcpy): New.  Duplicate slm_memcpy.
+	(intel_memset): New.  Duplicate slm_memset.
+	(intel_cost): New.  Duplicate slm_cost.
+	(m_INTEL): New macro.
+	(processor_target_table): Add "intel".
+	(ix86_option_override_internal): Replace PROCESSOR_SILVERMONT
+	with PROCESSOR_INTEL for "intel".
+	(ix86_lea_outperforms): Support PROCESSOR_INTEL.  Duplicate
+	PROCESSOR_SILVERMONT.
+	(ix86_avoid_lea_for_addr): Check TARGET_AVOID_LEA_FOR_ADDR
+	instead of TARGET_OPT_AGU.
+	(ix86_issue_rate): Likewise.
+	(ix86_adjust_cost): Likewise.
+	(ia32_multipass_dfa_lookahead): Likewise.
+	(swap_top_of_ready_list): Likewise.
+	(ix86_sched_reorder): Likewise.
+	* config/i386/i386.h (TARGET_INTEL): New.
+	(TARGET_AVOID_LEA_FOR_ADDR): Likewise.
+	(processor_type): Add PROCESSOR_INTEL.
+	* config/i386/x86-tune.def: Support m_INTEL. Duplicate
+	m_SILVERMONT.  Add X86_TUNE_AVOID_LEA_FOR_ADDR.
+
 2014-01-17  Marek Polacek  <polacek@redhat.com>
 
 	PR c/58346
diff --git a/gcc/config/i386/i386-c.c b/gcc/config/i386/i386-c.c
index 9686382af48..ce9ba95ede6 100644
--- a/gcc/config/i386/i386-c.c
+++ b/gcc/config/i386/i386-c.c
@@ -174,6 +174,7 @@ ix86_target_macros_internal (HOST_WIDE_INT isa_flag,
     /* use PROCESSOR_max to not set/unset the arch macro.  */
     case PROCESSOR_max:
       break;
+    case PROCESSOR_INTEL:
     case PROCESSOR_GENERIC:
       gcc_unreachable ();
     }
@@ -276,6 +277,7 @@ ix86_target_macros_internal (HOST_WIDE_INT isa_flag,
       def_or_undef (parse_in, "__tune_slm__");
       def_or_undef (parse_in, "__tune_silvermont__");
       break;
+    case PROCESSOR_INTEL:
     case PROCESSOR_GENERIC:
       break;
     /* use PROCESSOR_max to not set/unset the tune macro.  */
diff --git a/gcc/config/i386/i386.c b/gcc/config/i386/i386.c
index d3e4d5f654c..8993331f4d3 100644
--- a/gcc/config/i386/i386.c
+++ b/gcc/config/i386/i386.c
@@ -1747,6 +1747,83 @@ struct processor_costs slm_cost = {
   1,					/* cond_not_taken_branch_cost.  */
 };
 
+static stringop_algs intel_memcpy[2] = {
+  {libcall, {{11, loop, false}, {-1, rep_prefix_4_byte, false}}},
+  {libcall, {{32, loop, false}, {64, rep_prefix_4_byte, false},
+             {8192, rep_prefix_8_byte, false}, {-1, libcall, false}}}};
+static stringop_algs intel_memset[2] = {
+  {libcall, {{8, loop, false}, {15, unrolled_loop, false},
+             {2048, rep_prefix_4_byte, false}, {-1, libcall, false}}},
+  {libcall, {{24, loop, false}, {32, unrolled_loop, false},
+             {8192, rep_prefix_8_byte, false}, {-1, libcall, false}}}};
+static const
+struct processor_costs intel_cost = {
+  COSTS_N_INSNS (1),			/* cost of an add instruction */
+  COSTS_N_INSNS (1) + 1,		/* cost of a lea instruction */
+  COSTS_N_INSNS (1),			/* variable shift costs */
+  COSTS_N_INSNS (1),			/* constant shift costs */
+  {COSTS_N_INSNS (3),			/* cost of starting multiply for QI */
+   COSTS_N_INSNS (3),			/*				 HI */
+   COSTS_N_INSNS (3),			/*				 SI */
+   COSTS_N_INSNS (4),			/*				 DI */
+   COSTS_N_INSNS (2)},			/*			      other */
+  0,					/* cost of multiply per each bit set */
+  {COSTS_N_INSNS (18),			/* cost of a divide/mod for QI */
+   COSTS_N_INSNS (26),			/*			    HI */
+   COSTS_N_INSNS (42),			/*			    SI */
+   COSTS_N_INSNS (74),			/*			    DI */
+   COSTS_N_INSNS (74)},			/*			    other */
+  COSTS_N_INSNS (1),			/* cost of movsx */
+  COSTS_N_INSNS (1),			/* cost of movzx */
+  8,					/* "large" insn */
+  17,					/* MOVE_RATIO */
+  4,					/* cost for loading QImode using movzbl */
+  {4, 4, 4},				/* cost of loading integer registers
+					   in QImode, HImode and SImode.
+					   Relative to reg-reg move (2).  */
+  {4, 4, 4},				/* cost of storing integer registers */
+  4,					/* cost of reg,reg fld/fst */
+  {12, 12, 12},				/* cost of loading fp registers
+					   in SFmode, DFmode and XFmode */
+  {6, 6, 8},				/* cost of storing fp registers
+					   in SFmode, DFmode and XFmode */
+  2,					/* cost of moving MMX register */
+  {8, 8},				/* cost of loading MMX registers
+					   in SImode and DImode */
+  {8, 8},				/* cost of storing MMX registers
+					   in SImode and DImode */
+  2,					/* cost of moving SSE register */
+  {8, 8, 8},				/* cost of loading SSE registers
+					   in SImode, DImode and TImode */
+  {8, 8, 8},				/* cost of storing SSE registers
+					   in SImode, DImode and TImode */
+  5,					/* MMX or SSE register to integer */
+  32,					/* size of l1 cache.  */
+  256,					/* size of l2 cache.  */
+  64,					/* size of prefetch block */
+  6,					/* number of parallel prefetches */
+  3,					/* Branch cost */
+  COSTS_N_INSNS (8),			/* cost of FADD and FSUB insns.  */
+  COSTS_N_INSNS (8),			/* cost of FMUL instruction.  */
+  COSTS_N_INSNS (20),			/* cost of FDIV instruction.  */
+  COSTS_N_INSNS (8),			/* cost of FABS instruction.  */
+  COSTS_N_INSNS (8),			/* cost of FCHS instruction.  */
+  COSTS_N_INSNS (40),			/* cost of FSQRT instruction.  */
+  intel_memcpy,
+  intel_memset,
+  1,					/* scalar_stmt_cost.  */
+  1,					/* scalar load_cost.  */
+  1,					/* scalar_store_cost.  */
+  1,					/* vec_stmt_cost.  */
+  1,					/* vec_to_scalar_cost.  */
+  1,					/* scalar_to_vec_cost.  */
+  1,					/* vec_align_load_cost.  */
+  2,					/* vec_unalign_load_cost.  */
+  1,					/* vec_store_cost.  */
+  3,					/* cond_taken_branch_cost.  */
+  1,					/* cond_not_taken_branch_cost.  */
+};
+
 /* Generic should produce code tuned for Core-i7 (and newer chips)
    and btver1 (and newer chips).  */
 
@@ -1942,6 +2019,7 @@ const struct processor_costs *ix86_cost = &pentium_cost;
 #define m_CORE_ALL (m_CORE2 | m_NEHALEM  | m_SANDYBRIDGE | m_HASWELL)
 #define m_BONNELL (1<<PROCESSOR_BONNELL)
 #define m_SILVERMONT (1<<PROCESSOR_SILVERMONT)
+#define m_INTEL (1<<PROCESSOR_INTEL)
 
 #define m_GEODE (1<<PROCESSOR_GEODE)
 #define m_K6 (1<<PROCESSOR_K6)
@@ -2401,6 +2479,7 @@ static const struct ptt processor_target_table[PROCESSOR_max] =
   {"haswell", &core_cost, 16, 10, 16, 10, 16},
   {"bonnell", &atom_cost, 16, 15, 16, 7, 16},
   {"silvermont", &slm_cost, 16, 15, 16, 7, 16},
+  {"intel", &intel_cost, 16, 15, 16, 7, 16},
   {"geode", &geode_cost, 0, 0, 0, 0, 0},
   {"k6", &k6_cost, 32, 7, 32, 7, 32},
   {"athlon", &athlon_cost, 16, 7, 16, 7, 16},
@@ -3112,7 +3191,7 @@ ix86_option_override_internal (bool main_args_p,
       {"atom", PROCESSOR_BONNELL, CPU_ATOM, PTA_BONNELL},
       {"silvermont", PROCESSOR_SILVERMONT, CPU_SLM, PTA_SILVERMONT},
       {"slm", PROCESSOR_SILVERMONT, CPU_SLM, PTA_SILVERMONT},
-      {"intel", PROCESSOR_SILVERMONT, CPU_SLM, PTA_NEHALEM},
+      {"intel", PROCESSOR_INTEL, CPU_SLM, PTA_NEHALEM},
       {"geode", PROCESSOR_GEODE, CPU_GEODE,
 	PTA_MMX | PTA_3DNOW | PTA_3DNOW_A | PTA_PREFETCH_SSE | PTA_PRFCHW},
       {"k6", PROCESSOR_K6, CPU_K6, PTA_MMX},
@@ -17941,7 +18020,7 @@ ix86_lea_outperforms (rtx insn, unsigned int regno0, unsigned int regno1,
   /* For Silvermont if using a 2-source or 3-source LEA for
      non-destructive destination purposes, or due to wanting
      ability to use SCALE, the use of LEA is justified.  */
-  if (ix86_tune == PROCESSOR_SILVERMONT)
+  if (ix86_tune == PROCESSOR_SILVERMONT || ix86_tune == PROCESSOR_INTEL)
     {
       if (has_scale)
 	return true;
@@ -18077,7 +18156,7 @@ ix86_avoid_lea_for_addr (rtx insn, rtx operands[])
   int ok;
 
   /* Check we need to optimize.  */
-  if (!TARGET_OPT_AGU || optimize_function_for_size_p (cfun))
+  if (!TARGET_AVOID_LEA_FOR_ADDR || optimize_function_for_size_p (cfun))
     return false;
 
   /* Check it is correct to split here.  */
@@ -25200,6 +25279,7 @@ ix86_issue_rate (void)
     case PROCESSOR_PENTIUM:
     case PROCESSOR_BONNELL:
     case PROCESSOR_SILVERMONT:
+    case PROCESSOR_INTEL:
     case PROCESSOR_K6:
     case PROCESSOR_BTVER2:
     case PROCESSOR_PENTIUM4:
@@ -25541,6 +25621,7 @@ ix86_adjust_cost (rtx insn, rtx link, rtx dep_insn, int cost)
       break;
 
     case PROCESSOR_SILVERMONT:
+    case PROCESSOR_INTEL:
       if (!reload_completed)
 	return cost;
 
@@ -25609,6 +25690,7 @@ ia32_multipass_dfa_lookahead (void)
     case PROCESSOR_HASWELL:
     case PROCESSOR_BONNELL:
     case PROCESSOR_SILVERMONT:
+    case PROCESSOR_INTEL:
       /* Generally, we want haifa-sched:max_issue() to look ahead as far
 	 as many instructions can be executed on a cycle, i.e.,
 	 issue_rate.  I wonder why tuning for many CPUs does not do this.  */
@@ -25830,7 +25912,7 @@ swap_top_of_ready_list (rtx *ready, int n_ready)
   int clock2 = -1;
   #define INSN_TICK(INSN) (HID (INSN)->tick)
 
-  if (ix86_tune != PROCESSOR_SILVERMONT)
+  if (ix86_tune != PROCESSOR_SILVERMONT && ix86_tune != PROCESSOR_INTEL)
     return false;
 
   if (!NONDEBUG_INSN_P (top))
@@ -25904,7 +25986,8 @@ ix86_sched_reorder (FILE *dump, int sched_verbose, rtx *ready, int *pn_ready,
 
   /* Do reodering for BONNELL/SILVERMONT only.  */
   if (ix86_tune != PROCESSOR_BONNELL
-      && ix86_tune != PROCESSOR_SILVERMONT)
+      && ix86_tune != PROCESSOR_SILVERMONT
+      && ix86_tune != PROCESSOR_INTEL)
     return issue_rate;
 
   /* Nothing to do if ready list contains only 1 instruction.  */
diff --git a/gcc/config/i386/i386.h b/gcc/config/i386/i386.h
index 3199b41292d..580a3196b27 100644
--- a/gcc/config/i386/i386.h
+++ b/gcc/config/i386/i386.h
@@ -308,6 +308,7 @@ extern const struct processor_costs ix86_size_cost;
 #define TARGET_HASWELL (ix86_tune == PROCESSOR_HASWELL)
 #define TARGET_BONNELL (ix86_tune == PROCESSOR_BONNELL)
 #define TARGET_SILVERMONT (ix86_tune == PROCESSOR_SILVERMONT)
+#define TARGET_INTEL (ix86_tune == PROCESSOR_INTEL)
 #define TARGET_GENERIC (ix86_tune == PROCESSOR_GENERIC)
 #define TARGET_AMDFAM10 (ix86_tune == PROCESSOR_AMDFAM10)
 #define TARGET_BDVER1 (ix86_tune == PROCESSOR_BDVER1)
@@ -429,6 +430,8 @@ extern unsigned char ix86_tune_features[X86_TUNE_LAST];
 #define TARGET_FUSE_ALU_AND_BRANCH \
 	ix86_tune_features[X86_TUNE_FUSE_ALU_AND_BRANCH]
 #define TARGET_OPT_AGU ix86_tune_features[X86_TUNE_OPT_AGU]
+#define TARGET_AVOID_LEA_FOR_ADDR \
+	ix86_tune_features[X86_TUNE_AVOID_LEA_FOR_ADDR]
 #define TARGET_VECTORIZE_DOUBLE \
 	ix86_tune_features[X86_TUNE_VECTORIZE_DOUBLE]
 #define TARGET_SOFTWARE_PREFETCHING_BENEFICIAL \
@@ -2184,6 +2187,7 @@ enum processor_type
   PROCESSOR_HASWELL,
   PROCESSOR_BONNELL,
   PROCESSOR_SILVERMONT,
+  PROCESSOR_INTEL,
   PROCESSOR_GEODE,
   PROCESSOR_K6,
   PROCESSOR_ATHLON,
diff --git a/gcc/config/i386/x86-tune.def b/gcc/config/i386/x86-tune.def
index ec96a4b2617..f5affe6cdaf 100644
--- a/gcc/config/i386/x86-tune.def
+++ b/gcc/config/i386/x86-tune.def
@@ -40,16 +40,16 @@ see the files COPYING3 and COPYING.RUNTIME respectively.  If not, see
 
 /* X86_TUNE_SCHEDULE: Enable scheduling.  */
 DEF_TUNE (X86_TUNE_SCHEDULE, "schedule",
-          m_PENT | m_PPRO | m_CORE_ALL | m_BONNELL | m_SILVERMONT | m_K6_GEODE
-          | m_AMD_MULTIPLE | m_GENERIC)
+          m_PENT | m_PPRO | m_CORE_ALL | m_BONNELL | m_SILVERMONT | m_INTEL 
+	  | m_K6_GEODE | m_AMD_MULTIPLE | m_GENERIC)
 
 /* X86_TUNE_PARTIAL_REG_DEPENDENCY: Enable more register renaming
    on modern chips.  Preffer stores affecting whole integer register
    over partial stores.  For example preffer MOVZBL or MOVQ to load 8bit
    value over movb.  */
 DEF_TUNE (X86_TUNE_PARTIAL_REG_DEPENDENCY, "partial_reg_dependency",
-          m_P4_NOCONA | m_CORE_ALL | m_BONNELL | m_SILVERMONT | m_AMD_MULTIPLE
-          | m_GENERIC)
+          m_P4_NOCONA | m_CORE_ALL | m_BONNELL | m_SILVERMONT | m_INTEL
+	  | m_AMD_MULTIPLE | m_GENERIC)
 
 /* X86_TUNE_SSE_PARTIAL_REG_DEPENDENCY: This knob promotes all store
    destinations to be 128bit to allow register renaming on 128bit SSE units,
@@ -58,8 +58,8 @@ DEF_TUNE (X86_TUNE_PARTIAL_REG_DEPENDENCY, "partial_reg_dependency",
    SPECfp regression, while enabling it on K8 brings roughly 2.4% regression
    that can be partly masked by careful scheduling of moves.  */
 DEF_TUNE (X86_TUNE_SSE_PARTIAL_REG_DEPENDENCY, "sse_partial_reg_dependency",
-          m_PPRO | m_P4_NOCONA | m_CORE_ALL | m_BONNELL | m_SILVERMONT | m_AMDFAM10
-          | m_BDVER | m_GENERIC)
+          m_PPRO | m_P4_NOCONA | m_CORE_ALL | m_BONNELL | m_SILVERMONT
+	  | m_INTEL | m_AMDFAM10 | m_BDVER | m_GENERIC)
 
 /* X86_TUNE_SSE_SPLIT_REGS: Set for machines where the type and dependencies
    are resolved on SSE register parts instead of whole registers, so we may
@@ -84,13 +84,14 @@ DEF_TUNE (X86_TUNE_PARTIAL_FLAG_REG_STALL, "partial_flag_reg_stall",
 /* X86_TUNE_MOVX: Enable to zero extend integer registers to avoid
    partial dependencies.  */
 DEF_TUNE (X86_TUNE_MOVX, "movx",
-          m_PPRO | m_P4_NOCONA | m_CORE_ALL | m_BONNELL | m_SILVERMONT | m_GEODE
-          | m_AMD_MULTIPLE  | m_GENERIC)
+          m_PPRO | m_P4_NOCONA | m_CORE_ALL | m_BONNELL | m_SILVERMONT
+	  | m_INTEL | m_GEODE | m_AMD_MULTIPLE  | m_GENERIC)
 
 /* X86_TUNE_MEMORY_MISMATCH_STALL: Avoid partial stores that are followed by
    full sized loads.  */
 DEF_TUNE (X86_TUNE_MEMORY_MISMATCH_STALL, "memory_mismatch_stall",
-          m_P4_NOCONA | m_CORE_ALL | m_BONNELL | m_SILVERMONT | m_AMD_MULTIPLE | m_GENERIC)
+          m_P4_NOCONA | m_CORE_ALL | m_BONNELL | m_SILVERMONT | m_INTEL
+	  | m_AMD_MULTIPLE | m_GENERIC)
 
 /* X86_TUNE_FUSE_CMP_AND_BRANCH_32: Fuse compare with a subsequent
    conditional jump instruction for 32 bit TARGET.
@@ -124,7 +125,8 @@ DEF_TUNE (X86_TUNE_REASSOC_INT_TO_PARALLEL, "reassoc_int_to_parallel",
 /* X86_TUNE_REASSOC_FP_TO_PARALLEL: Try to produce parallel computations
    during reassociation of fp computation.  */
 DEF_TUNE (X86_TUNE_REASSOC_FP_TO_PARALLEL, "reassoc_fp_to_parallel",
-          m_BONNELL | m_SILVERMONT | m_HASWELL | m_BDVER1 | m_BDVER2 | m_GENERIC)
+          m_BONNELL | m_SILVERMONT | m_HASWELL | m_INTEL | m_BDVER1
+	  | m_BDVER2 | m_GENERIC)
 
 /*****************************************************************************/
 /* Function prologue, epilogue and function calling sequences.               */
@@ -143,7 +145,8 @@ DEF_TUNE (X86_TUNE_REASSOC_FP_TO_PARALLEL, "reassoc_fp_to_parallel",
    regression on mgrid due to IRA limitation leading to unecessary
    use of the frame pointer in 32bit mode.  */
 DEF_TUNE (X86_TUNE_ACCUMULATE_OUTGOING_ARGS, "accumulate_outgoing_args",
-	  m_PPRO | m_P4_NOCONA | m_BONNELL | m_SILVERMONT | m_AMD_MULTIPLE | m_GENERIC)
+	  m_PPRO | m_P4_NOCONA | m_BONNELL | m_SILVERMONT | m_INTEL
+	  | m_AMD_MULTIPLE | m_GENERIC)
 
 /* X86_TUNE_PROLOGUE_USING_MOVE: Do not use push/pop in prologues that are
    considered on critical path.  */
@@ -202,7 +205,8 @@ DEF_TUNE (X86_TUNE_PAD_RETURNS, "pad_returns",
 /* X86_TUNE_FOUR_JUMP_LIMIT: Some CPU cores are not able to predict more
    than 4 branch instructions in the 16 byte window.  */
 DEF_TUNE (X86_TUNE_FOUR_JUMP_LIMIT, "four_jump_limit",
-          m_PPRO | m_P4_NOCONA | m_BONNELL | m_SILVERMONT | m_ATHLON_K8 | m_AMDFAM10)
+          m_PPRO | m_P4_NOCONA | m_BONNELL | m_SILVERMONT | m_INTEL |
+	  m_ATHLON_K8 | m_AMDFAM10)
 
 /*****************************************************************************/
 /* Integer instruction selection tuning                                      */
@@ -224,17 +228,22 @@ DEF_TUNE (X86_TUNE_READ_MODIFY, "read_modify", ~(m_PENT | m_PPRO))
 
 /* X86_TUNE_USE_INCDEC: Enable use of inc/dec instructions.   */
 DEF_TUNE (X86_TUNE_USE_INCDEC, "use_incdec",
-          ~(m_P4_NOCONA | m_CORE_ALL | m_BONNELL | m_SILVERMONT | m_GENERIC))
+          ~(m_P4_NOCONA | m_CORE_ALL | m_BONNELL | m_SILVERMONT | m_INTEL
+	    | m_GENERIC))
 
 /* X86_TUNE_INTEGER_DFMODE_MOVES: Enable if integer moves are preferred
    for DFmode copies */
 DEF_TUNE (X86_TUNE_INTEGER_DFMODE_MOVES, "integer_dfmode_moves",
           ~(m_PPRO | m_P4_NOCONA | m_CORE_ALL | m_BONNELL | m_SILVERMONT
-          | m_GEODE | m_AMD_MULTIPLE | m_GENERIC))
+	    | m_INTEL | m_GEODE | m_AMD_MULTIPLE | m_GENERIC))
 
 /* X86_TUNE_OPT_AGU: Optimize for Address Generation Unit. This flag
    will impact LEA instruction selection. */
-DEF_TUNE (X86_TUNE_OPT_AGU, "opt_agu", m_BONNELL | m_SILVERMONT)
+DEF_TUNE (X86_TUNE_OPT_AGU, "opt_agu", m_BONNELL | m_SILVERMONT | m_INTEL)
+
+/* X86_TUNE_AVOID_LEA_FOR_ADDR: Avoid lea for address computation.  */
+DEF_TUNE (X86_TUNE_AVOID_LEA_FOR_ADDR, "avoid_lea_for_addr",
+	  m_BONNELL | m_SILVERMONT)
 
 /* X86_TUNE_SLOW_IMUL_IMM32_MEM: Imul of 32-bit constant and memory is
    vector path on AMD machines.
@@ -251,7 +260,7 @@ DEF_TUNE (X86_TUNE_SLOW_IMUL_IMM8, "slow_imul_imm8",
 /* X86_TUNE_AVOID_MEM_OPND_FOR_CMOVE: Try to avoid memory operands for
    a conditional move.  */
 DEF_TUNE (X86_TUNE_AVOID_MEM_OPND_FOR_CMOVE, "avoid_mem_opnd_for_cmove",
-	  m_BONNELL | m_SILVERMONT)
+	  m_BONNELL | m_SILVERMONT | m_INTEL)
 
 /* X86_TUNE_SINGLE_STRINGOP: Enable use of single string operations, such
    as MOVS and STOS (without a REP prefix) to move/set sequences of bytes.  */
@@ -268,15 +277,18 @@ DEF_TUNE (X86_TUNE_MISALIGNED_MOVE_STRING_PRO_EPILOGUES,
 
 /* X86_TUNE_USE_SAHF: Controls use of SAHF.  */
 DEF_TUNE (X86_TUNE_USE_SAHF, "use_sahf",
-          m_PPRO | m_P4_NOCONA | m_CORE_ALL | m_BONNELL | m_SILVERMONT | m_K6_GEODE
-          | m_K8 | m_AMDFAM10 | m_BDVER | m_BTVER | m_GENERIC)
+          m_PPRO | m_P4_NOCONA | m_CORE_ALL | m_BONNELL | m_SILVERMONT
+	  | m_INTEL | m_K6_GEODE | m_K8 | m_AMDFAM10 | m_BDVER | m_BTVER
+	  | m_GENERIC)
 
 /* X86_TUNE_USE_CLTD: Controls use of CLTD and CTQO instructions.  */
-DEF_TUNE (X86_TUNE_USE_CLTD, "use_cltd", ~(m_PENT | m_BONNELL | m_SILVERMONT | m_K6))
+DEF_TUNE (X86_TUNE_USE_CLTD, "use_cltd",
+	  ~(m_PENT | m_BONNELL | m_SILVERMONT | m_INTEL  | m_K6))
 
 /* X86_TUNE_USE_BT: Enable use of BT (bit test) instructions.  */
 DEF_TUNE (X86_TUNE_USE_BT, "use_bt",
-          m_CORE_ALL | m_BONNELL | m_SILVERMONT | m_AMD_MULTIPLE | m_GENERIC)
+          m_CORE_ALL | m_BONNELL | m_SILVERMONT | m_INTEL | m_AMD_MULTIPLE
+	  | m_GENERIC)
 
 /*****************************************************************************/
 /* 387 instruction selection tuning                                          */
@@ -291,16 +303,16 @@ DEF_TUNE (X86_TUNE_USE_HIMODE_FIOP, "use_himode_fiop",
 /* X86_TUNE_USE_SIMODE_FIOP: Enables use of x87 instructions with 32bit
    integer operand.  */
 DEF_TUNE (X86_TUNE_USE_SIMODE_FIOP, "use_simode_fiop",
-          ~(m_PENT | m_PPRO | m_CORE_ALL | m_BONNELL
-            | m_SILVERMONT | m_AMD_MULTIPLE | m_GENERIC))
+          ~(m_PENT | m_PPRO | m_CORE_ALL | m_BONNELL | m_SILVERMONT
+	    | m_INTEL | m_AMD_MULTIPLE | m_GENERIC))
 
 /* X86_TUNE_USE_FFREEP: Use freep instruction instead of fstp.  */
 DEF_TUNE (X86_TUNE_USE_FFREEP, "use_ffreep", m_AMD_MULTIPLE)
 
 /* X86_TUNE_EXT_80387_CONSTANTS: Use fancy 80387 constants, such as PI.  */
 DEF_TUNE (X86_TUNE_EXT_80387_CONSTANTS, "ext_80387_constants",
-          m_PPRO | m_P4_NOCONA | m_CORE_ALL | m_BONNELL | m_SILVERMONT | m_K6_GEODE
-          | m_ATHLON_K8 | m_GENERIC)
+          m_PPRO | m_P4_NOCONA | m_CORE_ALL | m_BONNELL | m_SILVERMONT
+	  | m_INTEL | m_K6_GEODE | m_ATHLON_K8 | m_GENERIC)
 
 /*****************************************************************************/
 /* SSE instruction selection tuning                                          */
@@ -318,12 +330,14 @@ DEF_TUNE (X86_TUNE_GENERAL_REGS_SSE_SPILL, "general_regs_sse_spill",
 /* X86_TUNE_SSE_UNALIGNED_LOAD_OPTIMAL: Use movups for misaligned loads instead
    of a sequence loading registers by parts.  */
 DEF_TUNE (X86_TUNE_SSE_UNALIGNED_LOAD_OPTIMAL, "sse_unaligned_load_optimal",
-          m_NEHALEM | m_SANDYBRIDGE | m_HASWELL | m_AMDFAM10 | m_BDVER | m_BTVER | m_SILVERMONT | m_GENERIC)
+          m_NEHALEM | m_SANDYBRIDGE | m_HASWELL | m_AMDFAM10 | m_BDVER
+	  | m_BTVER | m_SILVERMONT | m_INTEL | m_GENERIC)
 
 /* X86_TUNE_SSE_UNALIGNED_STORE_OPTIMAL: Use movups for misaligned stores instead
    of a sequence loading registers by parts.  */
 DEF_TUNE (X86_TUNE_SSE_UNALIGNED_STORE_OPTIMAL, "sse_unaligned_store_optimal",
-          m_NEHALEM | m_SANDYBRIDGE | m_HASWELL | m_BDVER | m_SILVERMONT | m_GENERIC)
+          m_NEHALEM | m_SANDYBRIDGE | m_HASWELL | m_BDVER | m_SILVERMONT
+	  | m_INTEL | m_GENERIC)
 
 /* Use packed single precision instructions where posisble.  I.e. movups instead
    of movupd.  */
@@ -360,7 +374,7 @@ DEF_TUNE (X86_TUNE_INTER_UNIT_CONVERSIONS, "inter_unit_conversions",
 /* X86_TUNE_SPLIT_MEM_OPND_FOR_FP_CONVERTS: Try to split memory operand for
    fp converts to destination register.  */
 DEF_TUNE (X86_TUNE_SPLIT_MEM_OPND_FOR_FP_CONVERTS, "split_mem_opnd_for_fp_converts",
-          m_SILVERMONT)
+          m_SILVERMONT | m_INTEL)
 
 /* X86_TUNE_USE_VECTOR_FP_CONVERTS: Prefer vector packed SSE conversion
    from FP to FP.  This form of instructions avoids partial write to the