i386-c.c (ix86_target_macros_internal): Separate PROCESSOR_COREI7_AVX out from PROCES...

2013-11-04  Wei Mi  <wmi@google.com>

        * gcc/config/i386/i386-c.c (ix86_target_macros_internal): Separate
        PROCESSOR_COREI7_AVX out from PROCESSOR_COREI7.
        * gcc/config/i386/i386.c (ix86_option_override_internal): Ditto.
        (ix86_issue_rate): Ditto.
        (ix86_adjust_cost): Ditto.
        (ia32_multipass_dfa_lookahead): Ditto.
        (ix86_sched_init_global): Ditto.
        (get_builtin_code_for_version): Ditto.
        * gcc/config/i386/i386.h (enum target_cpu_default): Ditto.
        (enum processor_type): Ditto.
        * gcc/config/i386/x86-tune.def (DEF_TUNE): Ditto.

From-SVN: r204367

diff --git a/gcc/ChangeLog b/gcc/ChangeLog
index 18db887..f858406 100644 (file)
--- a/gcc/ChangeLog
+++ b/gcc/ChangeLog
@@ -1,3 +1,17 @@
+2013-11-04  Wei Mi  <wmi@google.com>
+
+       * gcc/config/i386/i386-c.c (ix86_target_macros_internal): Separate
+       PROCESSOR_COREI7_AVX out from PROCESSOR_COREI7.
+       * gcc/config/i386/i386.c (ix86_option_override_internal): Ditto.
+       (ix86_issue_rate): Ditto.
+       (ix86_adjust_cost): Ditto.
+       (ia32_multipass_dfa_lookahead): Ditto.
+       (ix86_sched_init_global): Ditto.
+       (get_builtin_code_for_version): Ditto.
+       * gcc/config/i386/i386.h (enum target_cpu_default): Ditto.
+       (enum processor_type): Ditto.
+       * gcc/config/i386/x86-tune.def (DEF_TUNE): Ditto.
+
 2013-11-04  Vladimir Makarov  <vmakarov@redhat.com>
 
        PR rtl-optimization/58967

diff --git a/gcc/config/i386/i386-c.c b/gcc/config/i386/i386-c.c
index a6eaf8a..690169d 100644 (file)
--- a/gcc/config/i386/i386-c.c
+++ b/gcc/config/i386/i386-c.c
@@ -141,6 +141,10 @@ ix86_target_macros_internal (HOST_WIDE_INT isa_flag,
       def_or_undef (parse_in, "__corei7");
       def_or_undef (parse_in, "__corei7__");
       break;
+    case PROCESSOR_COREI7_AVX:
+      def_or_undef (parse_in, "__corei7_avx");
+      def_or_undef (parse_in, "__corei7_avx__");
+      break;
     case PROCESSOR_HASWELL:
       def_or_undef (parse_in, "__core_avx2");
       def_or_undef (parse_in, "__core_avx2__");
@@ -238,6 +242,9 @@ ix86_target_macros_internal (HOST_WIDE_INT isa_flag,
     case PROCESSOR_COREI7:
       def_or_undef (parse_in, "__tune_corei7__");
       break;
+    case PROCESSOR_COREI7_AVX:
+      def_or_undef (parse_in, "__tune_corei7_avx__");
+      break;
     case PROCESSOR_HASWELL:
       def_or_undef (parse_in, "__tune_core_avx2__");
       break;

diff --git a/gcc/config/i386/i386.c b/gcc/config/i386/i386.c
index 902e169..631f3b9 100644 (file)
--- a/gcc/config/i386/i386.c
+++ b/gcc/config/i386/i386.c
@@ -1833,8 +1833,9 @@ const struct processor_costs *ix86_cost = &pentium_cost;
 #define m_P4_NOCONA (m_PENT4 | m_NOCONA)
 #define m_CORE2 (1<<PROCESSOR_CORE2)
 #define m_COREI7 (1<<PROCESSOR_COREI7)
+#define m_COREI7_AVX (1<<PROCESSOR_COREI7_AVX)
 #define m_HASWELL (1<<PROCESSOR_HASWELL)
-#define m_CORE_ALL (m_CORE2 | m_COREI7  | m_HASWELL)
+#define m_CORE_ALL (m_CORE2 | m_COREI7  | m_COREI7_AVX | m_HASWELL)
 #define m_ATOM (1<<PROCESSOR_ATOM)
 #define m_SLM (1<<PROCESSOR_SLM)
 
@@ -2299,6 +2300,8 @@ static const struct ptt processor_target_table[PROCESSOR_max] =
   {&core_cost, 16, 10, 16, 10, 16},
   /* Core i7  */
   {&core_cost, 16, 10, 16, 10, 16},
+  /* Core i7 avx  */
+  {&core_cost, 16, 10, 16, 10, 16},
   /* Core avx2  */
   {&core_cost, 16, 10, 16, 10, 16},
   {&generic_cost, 16, 10, 16, 10, 16},
@@ -2328,6 +2331,7 @@ static const char *const cpu_names[TARGET_CPU_DEFAULT_max] =
   "nocona",
   "core2",
   "corei7",
+  "corei7-avx",
   "core-avx2",
   "atom",
   "slm",
@@ -3016,12 +3020,12 @@ ix86_option_override_internal (bool main_args_p,
       {"corei7", PROCESSOR_COREI7, CPU_COREI7,
        PTA_64BIT | PTA_MMX | PTA_SSE | PTA_SSE2 | PTA_SSE3 | PTA_SSSE3
        | PTA_SSE4_1 | PTA_SSE4_2 | PTA_CX16 | PTA_POPCNT | PTA_FXSR},
-      {"corei7-avx", PROCESSOR_COREI7, CPU_COREI7,
+      {"corei7-avx", PROCESSOR_COREI7_AVX, CPU_COREI7,
        PTA_64BIT | PTA_MMX | PTA_SSE | PTA_SSE2 | PTA_SSE3
        | PTA_SSSE3 | PTA_SSE4_1 | PTA_SSE4_2 | PTA_AVX
        | PTA_CX16 | PTA_POPCNT | PTA_AES | PTA_PCLMUL
        | PTA_FXSR | PTA_XSAVE | PTA_XSAVEOPT},
-      {"core-avx-i", PROCESSOR_COREI7, CPU_COREI7,
+      {"core-avx-i", PROCESSOR_COREI7_AVX, CPU_COREI7,
        PTA_64BIT | PTA_MMX | PTA_SSE | PTA_SSE2 | PTA_SSE3
        | PTA_SSSE3 | PTA_SSE4_1 | PTA_SSE4_2 | PTA_AVX
        | PTA_CX16 | PTA_POPCNT | PTA_AES | PTA_PCLMUL | PTA_FSGSBASE
@@ -24807,6 +24811,7 @@ ix86_issue_rate (void)
 
     case PROCESSOR_CORE2:
     case PROCESSOR_COREI7:
+    case PROCESSOR_COREI7_AVX:
     case PROCESSOR_HASWELL:
       return 4;
 
@@ -25103,6 +25108,7 @@ ix86_adjust_cost (rtx insn, rtx link, rtx dep_insn, int cost)
 
     case PROCESSOR_CORE2:
     case PROCESSOR_COREI7:
+    case PROCESSOR_COREI7_AVX:
     case PROCESSOR_HASWELL:
       memory = get_attr_memory (insn);
 
@@ -25181,6 +25187,7 @@ ia32_multipass_dfa_lookahead (void)
 
     case PROCESSOR_CORE2:
     case PROCESSOR_COREI7:
+    case PROCESSOR_COREI7_AVX:
     case PROCESSOR_HASWELL:
     case PROCESSOR_ATOM:
     case PROCESSOR_SLM:
@@ -25821,6 +25828,7 @@ ix86_sched_init_global (FILE *dump ATTRIBUTE_UNUSED,
     {
     case PROCESSOR_CORE2:
     case PROCESSOR_COREI7:
+    case PROCESSOR_COREI7_AVX:
     case PROCESSOR_HASWELL:
       /* Do not perform multipass scheduling for pre-reload schedule
          to save compile time.  */
@@ -29672,6 +29680,10 @@ get_builtin_code_for_version (tree decl, tree *predicate_list)
              arg_str = "corei7";
              priority = P_PROC_SSE4_2;
              break;
+            case PROCESSOR_COREI7_AVX:
+              arg_str = "corei7-avx";
+              priority = P_PROC_SSE4_2;
+              break;
            case PROCESSOR_ATOM:
              arg_str = "atom";
              priority = P_PROC_SSSE3;

diff --git a/gcc/config/i386/i386.h b/gcc/config/i386/i386.h
index c979ee5..f07fd79 100644 (file)
--- a/gcc/config/i386/i386.h
+++ b/gcc/config/i386/i386.h
@@ -304,6 +304,7 @@ extern const struct processor_costs ix86_size_cost;
 #define TARGET_NOCONA (ix86_tune == PROCESSOR_NOCONA)
 #define TARGET_CORE2 (ix86_tune == PROCESSOR_CORE2)
 #define TARGET_COREI7 (ix86_tune == PROCESSOR_COREI7)
+#define TARGET_COREI7_AVX (ix86_tune == PROCESSOR_COREI7_AVX)
 #define TARGET_HASWELL (ix86_tune == PROCESSOR_HASWELL)
 #define TARGET_GENERIC (ix86_tune == PROCESSOR_GENERIC)
 #define TARGET_AMDFAM10 (ix86_tune == PROCESSOR_AMDFAM10)
@@ -613,6 +614,7 @@ enum target_cpu_default
   TARGET_CPU_DEFAULT_nocona,
   TARGET_CPU_DEFAULT_core2,
   TARGET_CPU_DEFAULT_corei7,
+  TARGET_CPU_DEFAULT_corei7_avx,
   TARGET_CPU_DEFAULT_haswell,
   TARGET_CPU_DEFAULT_atom,
   TARGET_CPU_DEFAULT_slm,
@@ -2229,6 +2231,7 @@ enum processor_type
   PROCESSOR_NOCONA,
   PROCESSOR_CORE2,
   PROCESSOR_COREI7,
+  PROCESSOR_COREI7_AVX,
   PROCESSOR_HASWELL,
   PROCESSOR_GENERIC,
   PROCESSOR_AMDFAM10,

diff --git a/gcc/config/i386/x86-tune.def b/gcc/config/i386/x86-tune.def
index 6e5d2fe..93977a9 100644 (file)
--- a/gcc/config/i386/x86-tune.def
+++ b/gcc/config/i386/x86-tune.def
@@ -300,12 +300,12 @@ 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_COREI7 | m_AMDFAM10 | m_BDVER | m_BTVER | m_SLM | m_GENERIC)
+          m_COREI7 | m_COREI7_AVX | m_AMDFAM10 | m_BDVER | m_BTVER | m_SLM | 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_COREI7 | m_BDVER | m_SLM | m_GENERIC)
+          m_COREI7 | m_COREI7_AVX | m_BDVER | m_SLM | m_GENERIC)
 
 /* Use packed single precision instructions where posisble.  I.e. movups instead
    of movupd.  */