2010-04-15 Thomas Schwinge <tschwinge@gnu.org>

[pf3gnuchains/gcc-fork.git] / gcc / tree-ssa-loop-prefetch.c

diff --git a/gcc/tree-ssa-loop-prefetch.c b/gcc/tree-ssa-loop-prefetch.c
index daf9956..4d85f54 100644 (file)
--- a/gcc/tree-ssa-loop-prefetch.c
+++ b/gcc/tree-ssa-loop-prefetch.c
@@ -225,6 +225,17 @@ struct mem_ref_group
 
 #define PREFETCH_ALL           (~(unsigned HOST_WIDE_INT) 0)
 
+/* Do not generate a prefetch if the unroll factor is significantly less
+   than what is required by the prefetch.  This is to avoid redundant
+   prefetches.  For example, if prefetch_mod is 16 and unroll_factor is
+   1, this means prefetching requires unrolling the loop 16 times, but
+   the loop is not going to be unrolled.  In this case (ratio = 16),
+   prefetching is not likely to be beneficial.  */
+
+#ifndef PREFETCH_MOD_TO_UNROLL_FACTOR_RATIO
+#define PREFETCH_MOD_TO_UNROLL_FACTOR_RATIO 8
+#endif
+
 /* The memory reference.  */
 
 struct mem_ref
@@ -717,7 +728,7 @@ prune_ref_by_group_reuse (struct mem_ref *ref, struct mem_ref *by,
       prefetch_before = (hit_from - delta_r + step - 1) / step;
 
       /* Do not reduce prefetch_before if we meet beyond cache size.  */
-      if (prefetch_before > abs (L2_CACHE_SIZE_BYTES / step))
+      if (prefetch_before > (unsigned) abs (L2_CACHE_SIZE_BYTES / step))
         prefetch_before = PREFETCH_ALL;
       if (prefetch_before < ref->prefetch_before)
        ref->prefetch_before = prefetch_before;
@@ -921,6 +932,12 @@ schedule_prefetches (struct mem_ref_group *groups, unsigned unroll_factor,
        if (!should_issue_prefetch_p (ref))
          continue;
 
+        /* The loop is far from being sufficiently unrolled for this
+           prefetch.  Do not generate prefetch to avoid many redudant
+           prefetches.  */
+        if (ref->prefetch_mod / unroll_factor > PREFETCH_MOD_TO_UNROLL_FACTOR_RATIO)
+          continue;
+
        /* If we need to prefetch the reference each PREFETCH_MOD iterations,
           and we unroll the loop UNROLL_FACTOR times, we need to insert
           ceil (UNROLL_FACTOR / PREFETCH_MOD) instructions in each
@@ -1586,17 +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,
@@ -1606,12 +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))