Changeset 862 for XIOS/trunk/src/transformation/axis_algorithm_interpolate.cpp

Timestamp:

06/09/16 11:32:27 (8 years ago)

Author:

mhnguyen

Message:

Chaning the way to process transformation to improve the performance.
Instead of exchanging global index and weights on full GRID, each process only
sends and receives the global index and weights on each ELEMENT, which can reduce
the message size of DHT.

+) Domain and axis now have their own exchange function to transfer global index and weight
+) Generic transformation now plays the role of "synthesizer" for all elements
+) Grid transformation now plays the role of transformation mapping, e.x: exchange final global index and weight
among processes.

Test
+) On Curie
+) Pass on all basic tests
+) Dynamic interpolation on axis hasn't been tested (and it seems to need more change to make it rework)

File:

• XIOS/trunk/src/transformation/axis_algorithm_interpolate.cpp (modified) (2 diffs)

XIOS/trunk/src/transformation/axis_algorithm_interpolate.cpp

@@ -265 +265 @@
     CDomain* dom = domListP[0];
     size_t vecAxisValueSize = dom->i_index.numElements();
+    int niGlobDom = dom->ni_glo.getValue();
     vecAxisValue.resize(vecAxisValueSize);
     if (transPosition_.empty())
@@ -271 +272 @@
       for (size_t idx = 0; idx < vecAxisValueSize; ++idx)
       {
-        transPosition_[idx].resize(2);
-        transPosition_[idx][0] = (dom->i_index)(idx);
-        transPosition_[idx][1] = (dom->j_index)(idx);
+        transPosition_[idx].resize(1);
+        transPosition_[idx][0] = (dom->i_index)(idx) + niGlobDom * (dom->j_index)(idx);
+//        transPosition_[idx][0] = (dom->i_index)(idx);
+//        transPosition_[idx][1] = (dom->j_index)(idx);
       }
     }