Also apply the insn to prefetch ratio heuristic to loops with known trip count.

2010-05-17  Changpeng Fang  <changpeng.fang@amd.com>

	* doc/invoke.texi: Update documentation for min-insn-to-prefetch-ratio.
	* tree-ssa-loop-prefetch.c (is_loop_prefetching_profitable): Also apply
	the insn to prefetch ratio heuristic to loops with known trip count.

From-SVN: r159515

gcc/ChangeLog

 2010-05-17  Changpeng Fang  <changpeng.fang@amd.com>
 
+	* doc/invoke.texi: Update documentation for min-insn-to-prefetch-ratio.
+	* tree-ssa-loop-prefetch.c (is_loop_prefetching_profitable): Also apply
+	the insn to prefetch ratio heuristic to loops with known trip count.
+
+2010-05-17  Changpeng Fang  <changpeng.fang@amd.com>
+
 	* tree-ssa-loop-prefetch.c (PREFETCH_MOD_TO_UNROLL_FACTOR_RATIO): New.
 	(schedule_prefetches): Do not generate a prefetch if the unroll factor
 	is far from what is required by the prefetch.

gcc/doc/invoke.texi

@@ -8518,8 +8518,7 @@ The size of L2 cache, in kilobytes.
 
 @item min-insn-to-prefetch-ratio
 The minimum ratio between the number of instructions and the
-number of prefetches to enable prefetching in a loop with an
-unknown trip count.
+number of prefetches to enable prefetching in a loop.
 
 @item prefetch-min-insn-to-mem-ratio
 The minimum ratio between the number of instructions and the

gcc/tree-ssa-loop-prefetch.c

@@ -1603,17 +1603,9 @@ is_loop_prefetching_profitable (unsigned ahead, HOST_WIDE_INT est_niter,
       return false;
     }
 
-  /* Profitability of prefetching is highly dependent on the trip count.
-     For a given AHEAD distance, the first AHEAD iterations do not benefit
-     from prefetching, and the last AHEAD iterations execute useless
-     prefetches.  So, if the trip count is not large enough relative to AHEAD,
-     prefetching may cause serious performance degradation.  To avoid this
-     problem when the trip count is not known at compile time, we
-     conservatively skip loops with high prefetching costs.  For now, only
-     the I-cache cost is considered.  The relative I-cache cost is estimated
-     by taking the ratio between the number of prefetches and the total
-     number of instructions.  Since we are using integer arithmetic, we
-     compute the reciprocal of this ratio.
+  /* Prefetching most likely causes performance degradation when the instruction
+     to prefetch ratio is too small.  Too many prefetch instructions in a loop
+     may reduce the I-cache performance.
      (unroll_factor * ninsns) is used to estimate the number of instructions in
      the unrolled loop.  This implementation is a bit simplistic -- the number
      of issued prefetch instructions is also affected by unrolling.  So,
@@ -1623,12 +1615,21 @@ is_loop_prefetching_profitable (unsigned ahead, HOST_WIDE_INT est_niter,
      original loop * unroll_factor (at least the induction variable increases
      and the exit branches will get eliminated), so it might be better to use
      tree_estimate_loop_size + estimated_unrolled_size.  */
-  if (est_niter < 0)
+  insn_to_prefetch_ratio = (unroll_factor * ninsns) / prefetch_count;
+  if (insn_to_prefetch_ratio < MIN_INSN_TO_PREFETCH_RATIO)
     {
-      insn_to_prefetch_ratio = (unroll_factor * ninsns) / prefetch_count;
-      return insn_to_prefetch_ratio >= MIN_INSN_TO_PREFETCH_RATIO;
+      if (dump_file && (dump_flags & TDF_DETAILS))
+        fprintf (dump_file,
+		 "Not prefetching -- instruction to prefetch ratio (%d) too small\n",
+		 insn_to_prefetch_ratio);
+      return false;
     }
 
+  /* Could not do further estimation if the trip count is unknown.  Just assume
+     prefetching is profitable. Too aggressive???  */
+  if (est_niter < 0)
+    return true;
+
   if (est_niter < (HOST_WIDE_INT) (TRIP_COUNT_TO_AHEAD_RATIO * ahead))
     {
       if (dump_file && (dump_flags & TDF_DETAILS))