From patchwork Sat Dec 29 16:57:18 2012
Content-Type: text/plain; charset="utf-8"
MIME-Version: 1.0
Content-Transfer-Encoding: 7bit
Subject: [RFC,x86] Changes for AVX and AVX2 processors
Date: Sat, 29 Dec 2012 06:57:18 -0000
From: Vladimir Yakovlev <vbyakovl23@gmail.com>
X-Patchwork-Id: 208675
Message-Id: <CAK1BsWo-iWDNcukpNqKsp7OrpE+k9riZV0=9Z3FxuGK+4DW24w@mail.gmail.com>
To: Uros Bizjak <ubizjak@gmail.com>
Cc: gcc-patches@gcc.gnu.org

I did changes. Please take a look.

2012/12/29, Uros Bizjak <ubizjak@gmail.com>:
> On Sat, Dec 29, 2012 at 6:26 AM, Vladimir Yakovlev <vbyakovl23@gmail.com>
> wrote:
>
>> processor_alias_table contains the same processor type for all
>> "corei7", "corei7-avx", "core-avx-i" and "core-avx2". At least, it has
>> consequence on checking x86_avx256_split_unaligned_load &
>> ix86_tune_mask: for all these processors it results the same. Moreover
>> we cannot turn new features on for AVX/AVX2 using
>> initial_ix86_tune_features.
>
> corei7, corei7-avx and core-avx-i are all based on sandybridge (=
> PROCESSOR_COREI7) architecture. The only problematic entry is
> core-avx2, which should be based on new architecture. I propose
> PROCESSOR_HASWELL, in the same way as we have PROCESSOR_NOCONA.
>
> Uros.
>


diff --git a/gcc/config/i386/i386-c.c b/gcc/config/i386/i386-c.c
index 08e1afe..2d8abd5 100644
--- a/gcc/config/i386/i386-c.c
+++ b/gcc/config/i386/i386-c.c
@@ -142,11 +142,7 @@ ix86_target_macros_internal (HOST_WIDE_INT isa_flag,
       def_or_undef (parse_in, "__corei7");
       def_or_undef (parse_in, "__corei7__");
       break;
-    case PROCESSOR_CORE_AVX:
-      def_or_undef (parse_in, "__core_avx");
-      def_or_undef (parse_in, "__core_avx__");
-      break;
-    case PROCESSOR_CORE_AVX2:
+    case PROCESSOR_HASWELL:
       def_or_undef (parse_in, "__core_avx2");
       def_or_undef (parse_in, "__core_avx2__");
       break;
@@ -240,10 +236,7 @@ ix86_target_macros_internal (HOST_WIDE_INT isa_flag,
     case PROCESSOR_COREI7:
       def_or_undef (parse_in, "__tune_corei7__");
       break;
-    case PROCESSOR_CORE_AVX:
-      def_or_undef (parse_in, "__tune_core_avx__");
-      break;
-    case PROCESSOR_CORE_AVX2:
+    case PROCESSOR_HASWELL:
       def_or_undef (parse_in, "__tune_core_avx2__");
       break;
     case PROCESSOR_ATOM:
diff --git a/gcc/config/i386/i386.c b/gcc/config/i386/i386.c
index 10411da..4adbef6 100644
--- a/gcc/config/i386/i386.c
+++ b/gcc/config/i386/i386.c
@@ -1732,9 +1732,8 @@ 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_CORE_AVX (1<<PROCESSOR_CORE_AVX)
-#define m_CORE_AVX2 (1<<PROCESSOR_CORE_AVX2)
-#define m_CORE_ALL (m_CORE2 | m_COREI7 | m_CORE_AVX | m_CORE_AVX2)
+#define m_HASWELL (1<<PROCESSOR_HASWELL)
+#define m_CORE_ALL (m_CORE2 | m_COREI7  | m_HASWELL)
 #define m_ATOM (1<<PROCESSOR_ATOM)
 
 #define m_GEODE (1<<PROCESSOR_GEODE)
@@ -2438,8 +2437,6 @@ 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 avx  */
-  {&core_cost, 16, 10, 16, 10, 16},
   /* Core avx2  */
   {&core_cost, 16, 10, 16, 10, 16},
   {&generic32_cost, 16, 7, 16, 7, 16},
@@ -2469,7 +2466,6 @@ static const char *const cpu_names[TARGET_CPU_DEFAULT_max] =
   "nocona",
   "core2",
   "corei7",
-  "coreavx",
   "coreavx2",
   "atom",
   "geode",
@@ -2912,17 +2908,17 @@ 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_FXSR},
-      {"corei7-avx", PROCESSOR_CORE_AVX, CPU_COREI7,
+      {"corei7-avx", PROCESSOR_COREI7, 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_CORE_AVX, CPU_COREI7,
+      {"core-avx-i", PROCESSOR_COREI7, 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
 	| PTA_RDRND | PTA_F16C | PTA_FXSR | PTA_XSAVE | PTA_XSAVEOPT},
-      {"core-avx2", PROCESSOR_CORE_AVX2, CPU_COREI7,
+      {"core-avx2", PROCESSOR_HASWELL, CPU_COREI7,
 	PTA_64BIT | PTA_MMX | PTA_SSE | PTA_SSE2 | PTA_SSE3
 	| PTA_SSSE3 | PTA_SSE4_1 | PTA_SSE4_2 | PTA_AVX | PTA_AVX2
 	| PTA_CX16 | PTA_POPCNT | PTA_AES | PTA_PCLMUL | PTA_FSGSBASE
@@ -24069,8 +24065,7 @@ ix86_issue_rate (void)
     case PROCESSOR_PENTIUM4:
     case PROCESSOR_CORE2:
     case PROCESSOR_COREI7:
-    case PROCESSOR_CORE_AVX:
-    case PROCESSOR_CORE_AVX2:
+    case PROCESSOR_HASWELL:
     case PROCESSOR_ATHLON:
     case PROCESSOR_K8:
     case PROCESSOR_AMDFAM10:
@@ -24327,8 +24322,7 @@ ia32_multipass_dfa_lookahead (void)
 
     case PROCESSOR_CORE2:
     case PROCESSOR_COREI7:
-    case PROCESSOR_CORE_AVX:
-    case PROCESSOR_CORE_AVX2:
+    case PROCESSOR_HASWELL:
     case PROCESSOR_ATOM:
       /* Generally, we want haifa-sched:max_issue() to look ahead as far
 	 as many instructions can be executed on a cycle, i.e.,
@@ -24873,8 +24867,7 @@ ix86_sched_init_global (FILE *dump ATTRIBUTE_UNUSED,
     {
     case PROCESSOR_CORE2:
     case PROCESSOR_COREI7:
-    case PROCESSOR_CORE_AVX:
-    case PROCESSOR_CORE_AVX2:
+    case PROCESSOR_HASWELL:
       /* Do not perform multipass scheduling for pre-reload schedule
          to save compile time.  */
       if (reload_completed)
@@ -28719,11 +28712,7 @@ get_builtin_code_for_version (tree decl, tree *predicate_list)
 	      arg_str = "corei7";
 	      priority = P_PROC_SSE4_2;
 	      break;
-	    case PROCESSOR_CORE_AVX:
-	      arg_str = "core_avx";
-	      priority = P_PROC_SSE4_2;
-	      break;
-	    case PROCESSOR_CORE_AVX2:
+	    case PROCESSOR_HASWELL:
 	      arg_str = "core_avx2";
 	      priority = P_PROC_SSE4_2;
 	      break;
diff --git a/gcc/config/i386/i386.h b/gcc/config/i386/i386.h
index d3ee8b0..ee21c47 100644
--- a/gcc/config/i386/i386.h
+++ b/gcc/config/i386/i386.h
@@ -248,8 +248,7 @@ 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_CORE_AVX (ix86_tune == PROCESSOR_CORE_AVX)
-#define TARGET_CORE_AVX2 (ix86_tune == PROCESSOR_CORE_AVX2)
+#define TARGET_HASWELL (ix86_tune == PROCESSOR_HASWELL)
 #define TARGET_GENERIC32 (ix86_tune == PROCESSOR_GENERIC32)
 #define TARGET_GENERIC64 (ix86_tune == PROCESSOR_GENERIC64)
 #define TARGET_GENERIC (TARGET_GENERIC32 || TARGET_GENERIC64)
@@ -605,8 +604,7 @@ enum target_cpu_default
   TARGET_CPU_DEFAULT_nocona,
   TARGET_CPU_DEFAULT_core2,
   TARGET_CPU_DEFAULT_corei7,
-  TARGET_CPU_DEFAULT_core_avx,
-  TARGET_CPU_DEFAULT_core_avx2,
+  TARGET_CPU_DEFAULT_haswell,
   TARGET_CPU_DEFAULT_atom,
 
   TARGET_CPU_DEFAULT_geode,
@@ -2099,8 +2097,7 @@ enum processor_type
   PROCESSOR_NOCONA,
   PROCESSOR_CORE2,
   PROCESSOR_COREI7,
-  PROCESSOR_CORE_AVX,
-  PROCESSOR_CORE_AVX2,
+  PROCESSOR_HASWELL,
   PROCESSOR_GENERIC32,
   PROCESSOR_GENERIC64,
   PROCESSOR_AMDFAM10,