Code optimizations.

   - Reduce DCBZ and ICBI calls in memory copy and init functions.
   - Reduce strlen calls in trace.
   - Set thread to low priority while waiting on in-kernel barrier.

Change-Id: Ic9c23b1e26797ff393e5862819830de60554747e
Reviewed-on: http://gfw160.austin.ibm.com:8080/gerrit/871
Tested-by: Jenkins Server
Reviewed-by: Douglas R. Gilbert <dgilbert@us.ibm.com>
Reviewed-by: Daniel M. Crowell <dcrowell@us.ibm.com>
Reviewed-by: Brian H. Horton <brianh@linux.ibm.com>
Reviewed-by: A. Patrick Williams III <iawillia@us.ibm.com>

1 files changed, 2 insertions, 1 deletions

diff --git a/src/kernel/barrier.C b/src/kernel/barrier.C
index a5dadc63a..c0fea2fa4 100644
--- a/src/kernel/barrier.C
+++ b/src/kernel/barrier.C
@@ -31,7 +31,7 @@ void Barrier::wait()
     {
         size_t l_event = iv_event;
         iv_spinlock.unlock();
-        while(iv_event == l_event);
+        while(iv_event == l_event) { setThreadPriorityLow(); }
     }
     else
     {
@@ -39,4 +39,5 @@ void Barrier::wait()
         ++iv_event;
         iv_spinlock.unlock();
     }
+    setThreadPriorityHigh();
 }