fix win32 CPUProgram missing cache flush (tinygrad#9171)

* win32: fix missing inst cache flush, rename ptr->self.mem for consistency with posix code

* fix types, remove assert

* fix memory leak

* rm whitespace

Author: peppingdore

tinygrad/device.py

@@ -236,10 +236,13 @@ def __init__(self, name:str, lib:bytes):
       PAGE_EXECUTE_READWRITE = 0x40
       MEM_COMMIT =  0x1000
       MEM_RESERVE = 0x2000
-      ctypes.windll.kernel32.VirtualAlloc.restype = ctypes.c_uint64
-      ptr = ctypes.windll.kernel32.VirtualAlloc(ctypes.c_int(0), ctypes.c_int(len(lib)), MEM_COMMIT | MEM_RESERVE, PAGE_EXECUTE_READWRITE)
-      ctypes.memmove(ptr, lib, len(lib))
-      self.fxn = ctypes.CFUNCTYPE(None)(ptr)
+      ctypes.windll.kernel32.VirtualAlloc.restype = ctypes.c_void_p
+      self.mem = ctypes.windll.kernel32.VirtualAlloc(ctypes.c_void_p(0), ctypes.c_size_t(len(lib)), MEM_COMMIT | MEM_RESERVE, PAGE_EXECUTE_READWRITE)
+      ctypes.memmove(self.mem, lib, len(lib))
+      ctypes.windll.kernel32.GetCurrentProcess.restype = ctypes.c_void_p
+      proc = ctypes.windll.kernel32.GetCurrentProcess()
+      ctypes.windll.kernel32.FlushInstructionCache(ctypes.c_void_p(proc), ctypes.c_void_p(self.mem), ctypes.c_size_t(len(lib)))
+      self.fxn = ctypes.CFUNCTYPE(None)(self.mem)
     else:
       from mmap import mmap, PROT_READ, PROT_WRITE, PROT_EXEC, MAP_ANON, MAP_PRIVATE
       # On apple silicon with SPRR enabled (it always is in macos) RWX pages are unrepresentable: https://blog.svenpeter.dev/posts/m1_sprr_gxf/
@@ -268,6 +271,9 @@ def __call__(self, *bufs, vals=(), wait=False):
     if platform.machine() == "arm64" and OSX: args = args[:8] + [ctypes.c_int64(a) if isinstance(a, int) else a for a in args[8:]]
     return cpu_time_execution(lambda: self.fxn(*args), enable=wait)
 
+  def __del__(self):
+    if sys.platform == 'win32': ctypes.windll.kernel32.VirtualFree(ctypes.c_void_p(self.mem), ctypes.c_size_t(0), 0x8000) #0x8000 - MEM_RELEASE
+
 # **************** for Compiled Devices ****************
 
 class CompileError(Exception): pass