Support Windows on ARM64

When I was working on !321 (merged), it occured to me that Windows also runs on ARM64 nowadays. So here is a patch to make pystencils run there. It only required some minor workarounds, including one for the lack of inline assembly in MSVC on ARM64 (which makes cacheline clearing impossible). ARM64 implies Neon, and MSVC does not support SVE -- this make the CPU capability detection as easy as on macOS on ARM64.

pystencils/include/arm_neon_helpers.h

@@ -36,13 +36,13 @@ inline int32x4_t makeVec_s32(int a, int b, int c, int d)
 #endif
 
 inline void cachelineZero(void * p) {
-#ifndef _MSC_VER
+#if !defined(_MSC_VER) || defined(__clang__)
 	__asm__ volatile("dc zva, %0"::"r"(p):"memory");
 #endif
 }
 
 inline size_t _cachelineSize() {
-#ifndef _MSC_VER
+#if !defined(_MSC_VER) || defined(__clang__)
 	// check that dc zva is permitted
 	uint64_t dczid;
 	__asm__ volatile ("mrs %0, dczid_el0" : "=r"(dczid));