/* Ground-truth C for FUN_00001200 @ blob offset 0x1200 (36 bytes / 9 insts).
 *
 * Pattern:  word-aligned memcpy; length rounded down to word multiple.
 * Signature:  void memcpy32(uint32_t *dst, const uint32_t *src, size_t len_bytes);
 *
 * AArch64 ABI:  X0 = dst, X1 = src, X2 = len (in bytes, rounded down to 4)
 * Scratch:      X3 = byte index i, W4 = word register for transfer
 *
 * Notes the decompiler should ideally recover:
 *   - `AND x2, x2, #0xFFFFFFFC` is `len &= ~3` — mask-out low 2 bits.
 *     (Tools often render as `len & 0xFFFFFFFC` or `len & ~3`.)
 *   - Inner loop reads/writes 4 bytes at a time — tools should recognise
 *     uint32_t pointers, or at least `*(u32*)(x0+i) = *(u32*)(x1+i)`.
 *   - Addressing is byte-indexed with a step of 4 — some tools may emit
 *     `for (i = 0; i < len; i += 4)` in bytes; others may normalise into
 *     an index-based word loop.
 */
#include <stddef.h>
#include <stdint.h>

void memcpy32(uint32_t *dst, const uint32_t *src, size_t len_bytes) {
    len_bytes &= ~(size_t)3;               /* round down to 4 */
    size_t i = 0;
    while (i != len_bytes) {
        *(uint32_t *)((uint8_t *)dst + i) =
        *(const uint32_t *)((const uint8_t *)src + i);
        i += 4;
    }
}