i386.c (ix86_issue_rate): Pentium4, Nocona has issue rate of 2.

	* i386.c (ix86_issue_rate): Pentium4, Nocona has issue rate of 2.
	Core2, Corei7 and Haswell has issue rate of 4.
	(ix86_adjust_cost): Remove ATOM case; fix core2/corei7/Haswell case.

From-SVN: r203172

diff --git a/gcc/ChangeLog b/gcc/ChangeLog
index 93cd63d73b3d4f02ebfcaa1654d3c2cd4fd8dfcb..2d5c759c1c24461b27957c9e7c03d5e4af363560 100644 (file)
--- a/gcc/ChangeLog
+++ b/gcc/ChangeLog
@@ -1,3 +1,9 @@
+2013-10-03  Jan Hubicka  <jh@suse.cz>
+
+       * i386.c (ix86_issue_rate): Pentium4, Nocona has issue rate of 2.
+       Core2, Corei7 and Haswell has issue rate of 4.
+       (ix86_adjust_cost): Remove ATOM case; fix core2/corei7/Haswell case.
+
 2013-10-03  Jan Hubicka  <jh@suse.cz>
 
        * i386.c (ix86_option_override_internal): Do not enable

diff --git a/gcc/config/i386/i386.c b/gcc/config/i386/i386.c
index 09b0fc507703f7e2fea2061a3d08c23ade6103c9..1713ad6f06d55079ac25f7da212ad618ff526027 100644 (file)
--- a/gcc/config/i386/i386.c
+++ b/gcc/config/i386/i386.c
@@ -24418,17 +24418,14 @@ ix86_issue_rate (void)
     case PROCESSOR_SLM:
     case PROCESSOR_K6:
     case PROCESSOR_BTVER2:
+    case PROCESSOR_PENTIUM4:
+    case PROCESSOR_NOCONA:
       return 2;
 
     case PROCESSOR_PENTIUMPRO:
-    case PROCESSOR_PENTIUM4:
-    case PROCESSOR_CORE2:
-    case PROCESSOR_COREI7:
-    case PROCESSOR_HASWELL:
     case PROCESSOR_ATHLON:
     case PROCESSOR_K8:
     case PROCESSOR_AMDFAM10:
-    case PROCESSOR_NOCONA:
     case PROCESSOR_GENERIC:
     case PROCESSOR_BDVER1:
     case PROCESSOR_BDVER2:
@@ -24436,6 +24433,11 @@ ix86_issue_rate (void)
     case PROCESSOR_BTVER1:
       return 3;
 
+    case PROCESSOR_CORE2:
+    case PROCESSOR_COREI7:
+    case PROCESSOR_HASWELL:
+      return 4;
+
     default:
       return 1;
     }
@@ -24692,10 +24694,15 @@ ix86_adjust_cost (rtx insn, rtx link, rtx dep_insn, int cost)
     case PROCESSOR_BDVER3:
     case PROCESSOR_BTVER1:
     case PROCESSOR_BTVER2:
-    case PROCESSOR_ATOM:
     case PROCESSOR_GENERIC:
       memory = get_attr_memory (insn);
 
+      /* Stack engine allows to execute push&pop instructions in parall.  */
+      if (((insn_type == TYPE_PUSH || insn_type == TYPE_POP)
+          && (dep_insn_type == TYPE_PUSH || dep_insn_type == TYPE_POP))
+         && (ix86_tune != PROCESSOR_ATHLON && ix86_tune != PROCESSOR_K8))
+       return 0;
+
       /* Show ability of reorder buffer to hide latency of load by executing
         in parallel with previous instruction in case
         previous instruction is not needed to compute the address.  */
@@ -24722,6 +24729,29 @@ ix86_adjust_cost (rtx insn, rtx link, rtx dep_insn, int cost)
        }
       break;
 
+    case PROCESSOR_CORE2:
+    case PROCESSOR_COREI7:
+    case PROCESSOR_HASWELL:
+      memory = get_attr_memory (insn);
+
+      /* Stack engine allows to execute push&pop instructions in parall.  */
+      if ((insn_type == TYPE_PUSH || insn_type == TYPE_POP)
+         && (dep_insn_type == TYPE_PUSH || dep_insn_type == TYPE_POP))
+       return 0;
+
+      /* Show ability of reorder buffer to hide latency of load by executing
+        in parallel with previous instruction in case
+        previous instruction is not needed to compute the address.  */
+      if ((memory == MEMORY_LOAD || memory == MEMORY_BOTH)
+         && !ix86_agi_dependent (dep_insn, insn))
+       {
+         if (cost >= 4)
+           cost -= 4;
+         else
+           cost = 0;
+       }
+      break;
+
     case PROCESSOR_SLM:
       if (!reload_completed)
        return cost;