use cache line zero on architectures without nontemporal store

pystencils/astnodes.py

pystencils/backends/arm_instruction_sets.py

pystencils/backends/cbackend.py

pystencils/backends/ppc_instruction_sets.py

pystencils/backends/x86_instruction_sets.py

pystencils/cpu/vectorization.py

pystencils/include/arm_neon_helpers.h

pystencils/include/ppc_altivec_helpers.h

pystencils_tests/test_vectorization.py