Make a copy of strip mined loops with small number of iterations from profiling

[Roland Westrelin]

> Okay. Introduce the const variable (right at the method) for this, please? Some
> wording about how it is chosen would be nice, even if it says "this is a blind
> guess":
>   LoopStripMiningIter / 10

What about this (yes that magic constant was already used elsewhere)?

Roland.

diff --git a/src/share/vm/opto/c2_globals.hpp b/src/share/vm/opto/c2_globals.hpp
--- a/src/share/vm/opto/c2_globals.hpp
+++ b/src/share/vm/opto/c2_globals.hpp
@@ -741,6 +741,10 @@
           "Number of iterations in strip mined loop")                       \
           range(0, max_juint)                                               \
                                                                             \
+  product(intx, LoopStripMiningIterShortLoop, 0,                            \
+          "Loop with fewer iterations are not strip mined")                 \
+          range(0, max_juint)                                               \
+                                                                            \
   product(bool, LoopStripMiningCopyShort, true,                             \
           "Make a copy of loop with no strip mining when profiling shows "  \
           "they execute few iterations")                                    \
diff --git a/src/share/vm/opto/loopTransform.cpp b/src/share/vm/opto/loopTransform.cpp
--- a/src/share/vm/opto/loopTransform.cpp
+++ b/src/share/vm/opto/loopTransform.cpp
@@ -2792,7 +2792,7 @@
       cl->is_strip_mined() &&
       !cl->is_strip_mined_short_cloned() &&
       !cl->has_exact_trip_count() &&
-      cl->profile_trip_cnt() < LoopStripMiningIter / 10) {
+      cl->profile_trip_cnt() < LoopStripMiningIterShortLoop) {
     int nodes_left = phase->C->max_node_limit() - phase->C->live_nodes();
     if ((int)(2 * _body.size()) <= nodes_left) {
       int stride = cl->stride_con();
diff --git a/src/share/vm/opto/opaquenode.cpp b/src/share/vm/opto/opaquenode.cpp
--- a/src/share/vm/opto/opaquenode.cpp
+++ b/src/share/vm/opto/opaquenode.cpp
@@ -97,10 +97,11 @@
                       int stride = inner_cl->stride_con();
                       jlong scaled_iters_long = ((jlong)LoopStripMiningIter) * ABS(stride);
                       int scaled_iters = (int)scaled_iters_long;
+                      int short_scaled_iters = LoopStripMiningIterShortLoop* ABS(stride);
                       const TypeInt* inner_iv_t = phase->type(inner_iv_phi)->is_int();
                       jlong iter_estimate = (jlong)inner_iv_t->_hi - (jlong)inner_iv_t->_lo;
                       assert(iter_estimate > 0, "broken");
-                      if ((jlong)scaled_iters != scaled_iters_long || iter_estimate <= scaled_iters_long / 10) {
+                      if ((jlong)scaled_iters != scaled_iters_long || iter_estimate <= short_scaled_iters) {
                         // Remove outer loop and safepoint (too few iterations)
                         Node* outer_sfpt = le->in(0);
                         assert(outer_sfpt->Opcode() == Op_SafePoint, "broken outer loop");
diff --git a/src/share/vm/runtime/arguments.cpp b/src/share/vm/runtime/arguments.cpp
--- a/src/share/vm/runtime/arguments.cpp
+++ b/src/share/vm/runtime/arguments.cpp
@@ -2641,6 +2641,10 @@
     }
     LoopStripMiningIter = 0;
   }
+  if (FLAG_IS_DEFAULT(LoopStripMiningIterShortLoop)) {
+    // blind guess
+    LoopStripMiningIterShortLoop = LoopStripMiningIter / 10;
+  }
 #endif
   return status;
 }