[PATCH] Optimize guard update copy

[Richard Guenther]

Hi!

This patch removes number four of the copies done for guard update.
Basically, additionally to the three copies I mentioned in the previous
mail, we're doing one extra during the RemoteView expressionApply of the
data-parallel assignment we're doing for the guard domains. Ugh. Fixed by
manually sending/receiving from/to the views.  Doesn't work for Cheetah,
so conditionalized on POOMA_MPI.

Tested as usual, ok to apply?

Richard.


2003Dec30  Richard Guenther <address@hidden>

        * src/Engine/MultiPatchEngine.cpp: optimize remote to local and
        local to remote copy in guard update.

===== MultiPatchEngine.cpp 1.6 vs 1.7 =====
--- 1.6/r2/src/Engine/MultiPatchEngine.cpp      Tue Dec  9 12:16:07 2003
+++ 1.7/r2/src/Engine/MultiPatchEngine.cpp      Thu Dec 18 16:41:50 2003
@@ -34,6 +34,7 @@
 #include "Engine/CompressedFraction.h"
 #include "Array/Array.h"
 #include "Tulip/ReduceOverContexts.h"
+#include "Tulip/SendReceive.h"
 #include "Threads/PoomaCSem.h"
 #include "Domain/IteratorPairDomain.h"

@@ -261,6 +262,40 @@
 //
 //-----------------------------------------------------------------------------

+/// Guard layer assign between non-remote engines, just use the
+/// ET mechanisms
+
+template <int Dim, class T, class Tag>
+static inline
+void simpleAssign(const Array<Dim, T, Tag>& lhs,
+                 const Array<Dim, T, Tag>& rhs,
+                 const Interval<Dim>& domain)
+{
+  lhs(domain) = rhs(domain);
+}
+
+/// Guard layer assign between remote engines, use Send/Receive directly
+/// to avoid one extra copy of the data.
+
+template <int Dim, class T, class Tag>
+static inline
+void simpleAssign(const Array<Dim, T, Remote<Tag> >& lhs,
+                 const Array<Dim, T, Remote<Tag> >& rhs,
+                 const Interval<Dim>& domain)
+{
+  if (lhs.engine().owningContext() == rhs.engine().owningContext())
+    lhs(domain) = rhs(domain);
+  else {
+    typedef typename NewEngine<Engine<Dim, T, Tag>, Interval<Dim> >::Type_t 
ViewEngine_t;
+    if (lhs.engine().engineIsLocal())
+      Receive<ViewEngine_t>::receive(ViewEngine_t(lhs.engine().localEngine(), 
domain),
+                                    rhs.engine().owningContext());
+    else if (rhs.engine().engineIsLocal())
+      SendReceive::send(ViewEngine_t(rhs.engine().localEngine(), domain),
+                       lhs.engine().owningContext());
+  }
+}
+
 template <int Dim, class T, class LayoutTag, class PatchTag>
 void Engine<Dim, T, MultiPatch<LayoutTag,PatchTag> >::
 fillGuardsHandler(const WrappedInt<true> &) const
@@ -293,8 +328,12 @@
       Array<Dim, T, PatchTag> lhs(data()[dest]), rhs(data()[src]);

       // Now do assignment from the subdomains.
-
+      // Optimized lhs(p->domain_m) = rhs(p->domain_m);
+#if POOMA_MPI
+      simpleAssign(lhs, rhs, p->domain_m);
+#else
       lhs(p->domain_m) = rhs(p->domain_m);
+#endif

       ++p;
     }