Dabble with the cost model

python/dune/perftool/sumfact/vectorization.py

@@ -54,20 +54,18 @@ def attach_vectorization_info(sf):
 
 
 def costmodel(sf):
-    # Penalize vertical vectorization
-    vertical_penalty = 1 + math.log(sf.vertical_width)
+    # Penalize vertical vectorization and scalar execution
+    verticality = sf.vertical_width
+    if isinstance(sf, SumfactKernel):
+        verticality = get_vcl_type_size(dtype_floatingpoint())
+    vertical_penalty = 1 + 0.5 * math.log(verticality, 2)
 
     memory_penalty = 1.0
     if isinstance(sf, VectorizedSumfactKernel):
-        memory_penalty = 1.0 + math.log(len(set(k.interface for k in sf.kernels)), 2)
-
-    # Penalize scalar sum factorization kernels
-    scalar_penalty = 1
-    if isinstance(sf, SumfactKernel):
-        scalar_penalty = get_vcl_type_size(dtype_floatingpoint())
+        memory_penalty = 1.0 + 0.25 * math.log(len(set(k.interface for k in sf.kernels)), 2)
 
     # Return total operations
-    return sf.operations * vertical_penalty * memory_penalty * scalar_penalty
+    return sf.operations * vertical_penalty * memory_penalty
 
 
 def explicit_costfunction(sf):
@@ -265,21 +263,27 @@ def level1_optimal_vectorization_strategy(sumfacts, width):
 
     # Find the minimum cost strategy between all the quadrature point tuples
     optimal_strategies = {qp: level2_optimal_vectorization_strategy(sumfacts, width, qp) for qp in quad_points}
-    qp = min(optimal_strategies, key=lambda qp: strategy_cost((qp, optimal_strategies[qp])))
 
     # If we are using the 'target' strategy, we might want to log some information.
     if get_form_option("vectorization_strategy") == "target":
         # Print the achieved cost and the target cost on the screen
         set_form_option("vectorization_strategy", "model")
+        qp = min(optimal_strategies, key=lambda qp: strategy_cost((qp, optimal_strategies[qp])))
         cost = strategy_cost((qp, optimal_strategies[qp]))
+
         print("The target cost was:   {}".format(get_form_option("vectorization_target")))
         print("The achieved cost was: {}".format(cost))
-        print("The optimal cost would be: {}".format(strategy_cost(level1_optimal_vectorization_strategy(sumfacts, width))))
+        optimum = level1_optimal_vectorization_strategy(sumfacts, width)
+        print("The optimal cost would be: {}".format(strategy_cost(optimum)))
         set_form_option("vectorization_strategy", "target")
         print("The score in 'target' logic was: {}".format(strategy_cost((qp, optimal_strategies[qp]))))
 
         # Print the employed vectorization strategy into a file
-        filename = "targetstrat_{}.log".format(int(float(get_form_option("vectorization_target"))))
+        suffix = ""
+        if get_global_context_value("integral_type") == "interior_facet":
+            suffix = "_dir{}_mod{}".format(get_global_context_value("facedir_s"),
+                                           get_global_context_value("facemod_s"))
+        filename = "targetstrat_{}{}.log".format(int(float(get_form_option("vectorization_target"))), suffix)
         with open(filename, 'w') as f:
             f.write("\n".join(stringify_vectorization_strategy((qp, optimal_strategies[qp]))))
 
@@ -291,6 +295,8 @@ def level1_optimal_vectorization_strategy(sumfacts, width):
         # TODO: Depending on the number of samples, we might need a file lock here.
         with open("mapping.csv", 'a') as f:
             f.write(" ".join((identifier, str(cost), short_stringify_vectorization_strategy((qp, optimal_strategies[qp])))) + "\n")
+    else:
+        qp = min(optimal_strategies, key=lambda qp: strategy_cost((qp, optimal_strategies[qp])))
 
     return qp, optimal_strategies[qp]