WIP: Assembly

Adds the functionality to directly show the assembly output of the generated code.

Further, the base pointer specification is revealed to the user which is helpful to minimize register spilling in some cases.

pystencils/backends/cbackend.py

@@ -628,6 +628,20 @@ class VectorizedCustomSympyPrinter(CustomSympyPrinter):
         return result
 
     def _print_Add(self, expr, order=None):
+        def visit(summands):
+            if len(summands) == 2:
+                sign = summands[0].sign * summands[1].sign
+                func = self.instruction_set['-' + suffix] if sign == -1 else self.instruction_set['+' + suffix]
+                return func.format(summands[0].term, summands[1].term)
+            else:
+                elements = len(summands) // 2
+                if len(summands[:elements]) < 2:
+                    func = self.instruction_set['-' + suffix] \
+                        if summands[0].sign == -1 else self.instruction_set['+' + suffix]
+                    return func.format(summands[0].term, visit(summands[elements:]))
+                else:
+                    func = self.instruction_set['+' + suffix]
+                    return func.format(visit(summands[:elements]), visit(summands[elements:]))
         try:
             result = self._scalarFallback('_print_Add', expr)
         except Exception:
@@ -662,10 +676,13 @@ class VectorizedCustomSympyPrinter(CustomSympyPrinter):
             summands.insert(0, self.SummandInfo(1, "0"))
 
         assert len(summands) >= 2
-        processed = summands[0].term
-        for summand in summands[1:]:
-            func = self.instruction_set['-' + suffix] if summand.sign == -1 else self.instruction_set['+' + suffix]
-            processed = func.format(processed, summand.term)
+        if len(summands) < 10:
+            processed = summands[0].term
+            for summand in summands[1:]:
+                func = self.instruction_set['-' + suffix] if summand.sign == -1 else self.instruction_set['+' + suffix]
+                processed = func.format(processed, summand.term)
+        else:
+            processed = visit(summands)
         return processed
 
     def _print_Pow(self, expr):