Fix RNG vectorization for LB

Reported by @RudolfWeeber. Not sure why it wasn't caught by the pycodegen nightly job. Added new tests to lbmpy in lbmpy!82 (merged).

Forgotten type check in _print_Function:

  File "pystencils/pystencils/backends/cbackend.py", line 673, in _print_Function
    (isinstance(arg, TypedSymbol) and arg.dtype.is_int())
AttributeError: 'VectorType' object has no attribute 'is_int'

Generation of invalid tail loops when assume_sufficient_line_padding=False:

_data_pdfs_tmp_20_30_10[ctr_0] = _mm256_add_pd(_mm256_add_pd(_mm256_add_pd(_mm256_add_pd(_mm256_add_pd(_mm256_add_pd(_mm256_add_pd(_mm256_add_pd(_mm256_add_pd(_mm256_mul_pd(xi_88,_mm256_set_pd(0.142857142857143,0.142857142857143,0.142857142857143,0.142857142857143)),_mm256_mul_pd(xi_89,_mm256_set_pd(0.2,0.2,0.2,0.2))),_mm256_mul_pd(xi_91,_mm256_set_pd(-1.0,-1.0,-1.0,-1.0))),_mm256_mul_pd(xi_92,_mm256_set_pd(0.0857142857142857,0.0857142857142857,0.0857142857142857,0.0857142857142857))),_mm256_set_pd(xi_108*-0.5,xi_108*-0.5,xi_108*-0.5,xi_108*-0.5)),_mm256_set_pd(xi_112*0.0238095238095238,xi_112*0.0238095238095238,xi_112*0.0238095238095238,xi_112*0.0238095238095238)),_mm256_set_pd(xi_95*0.1,xi_95*0.1,xi_95*0.1,xi_95*0.1)),_mm256_set_pd(xi_98*0.0428571428571429,xi_98*0.0428571428571429,xi_98*0.0428571428571429,xi_98*0.0428571428571429)),_mm256_set_pd(_data_pdfs_20_30_10[ctr_0],_data_pdfs_20_30_10[ctr_0],_data_pdfs_20_30_10[ctr_0],_data_pdfs_20_30_10[ctr_0])),_mm256_set_pd(forceTerm_0,forceTerm_0,forceTerm_0,forceTerm_0));

Generation of partially-vectorized code with assume_inner_stride_is_one=False in conjunction with the random number generator:

const double xi_22 = -xi_64 + xi_66;                                                                                                                             
const float64x2_t xi_26 = vaddq_f64(random_1_1,vdupq_n_f64(-0.5)); 

pystencils/backends/cbackend.py

@@ -192,7 +192,9 @@ class CBackend:
     def __init__(self, sympy_printer=None, signature_only=False, vector_instruction_set=None, dialect='c'):
         if sympy_printer is None:
             if vector_instruction_set is not None:
-                self.sympy_printer = VectorizedCustomSympyPrinter(vector_instruction_set)
+                self.vector_sympy_printer = VectorizedCustomSympyPrinter(vector_instruction_set)
+                self.scalar_sympy_printer = CustomSympyPrinter()
+                self.sympy_printer = self.vector_sympy_printer
             else:
                 self.sympy_printer = CustomSympyPrinter()
         else:
@@ -259,6 +261,12 @@ class CBackend:
         prefix = "\n".join(node.prefix_lines)
         if prefix:
             prefix += "\n"
+        if self._vector_instruction_set and hasattr(node, 'instruction_set') and node.instruction_set is None:
+            # the tail loop must not be vectorized
+            self.sympy_printer = self.scalar_sympy_printer
+            code = f"{prefix}{loop_str}\n{self._print(node.body)}"
+            self.sympy_printer = self.vector_sympy_printer
+            return code
         return f"{prefix}{loop_str}\n{self._print(node.body)}"
 
     def _print_SympyAssignment(self, node):
@@ -670,7 +678,7 @@ class VectorizedCustomSympyPrinter(CustomSympyPrinter):
                 else:
                     is_boolean = get_type_of_expression(arg) == create_type("bool")
                     is_integer = get_type_of_expression(arg) == create_type("int") or \
-                        (isinstance(arg, TypedSymbol) and arg.dtype.is_int())
+                        (isinstance(arg, TypedSymbol) and not isinstance(arg.dtype, VectorType) and arg.dtype.is_int())
                     instruction = 'makeVecConstBool' if is_boolean else \
                                   'makeVecConstInt' if is_integer else 'makeVecConst'
                     return self.instruction_set[instruction].format(self._print(arg), **self._kwargs)