Fix compiling for linux arm64 (#650)

* Enable MK64 build option for torch

* Fix HMAS type error (present on arm64)

* Align memory pool and fix empty macro

* Experimental: Add 4096 memory alignment

* Add alignment for ALIGNED8 macro

* Use memset over deprecated bzero

* Ensure OPENGLES flag can be used in CMakeLists.txt

* Diagnostic: align ship2_window_i8 to rule out odd-alignment crash

---------

Co-authored-by: MegaMech <MegaMech@users.noreply.github.com>

include/macros.h

@@ -63,18 +63,25 @@
 
 // Align to 8-byte boundary for DMA requirements
 #ifdef __GNUC__
-#define ALIGNED8
+#define ALIGNED8 __attribute__((aligned(8)))
 #else
 #define ALIGNED8
 #endif
 
 // Align to 16-byte boundary for audio lib requirements
 #ifdef __GNUC__
-#define ALIGNED16
+#define ALIGNED16 __attribute__((aligned(16)))
 #else
 #define ALIGNED16
 #endif
 
+// Align to 4096-byte boundary for 64-bit page requirements
+#ifdef __GNUC__
+#define ALIGNED4096 __attribute__((aligned(4096)))
+#else
+#define ALIGNED4096
+#endif
+
 // Fixed point macros
 #define FTOFIX(f) ((s32) ((f) * 65536.0))
 #define ITOFIX(i) ((s32) ((i) << 16))

include/stubs.h

@@ -1,7 +1,6 @@
 #include <libultraship.h>
 
 #ifdef _WIN32
-#define bzero(b, len) (memset((b), '\0', (len)), (void) 0)
 #define bcopy(b1, b2, len) (memmove((b2), (b1), (len)), (void) 0)
 #endif