#include <immintrin.h>
#include "unistd.h"
#include <stdint.h>
#include <stdio.h>

#define FLUSH_ALIGN 64

// If intrinsincs not available
#define _mm_clflushopt(addr)              \
    asm volatile(".byte 0x66; clflush %0" \
                 : "+m"(*(volatile char *)addr));

#define _mm_clwb(addr)                     \
    asm volatile(".byte 0x66; xsaveopt %0" \
                 : "+m"(*(volatile char *)addr));
#define _mm_pcommit() \
    asm volatile(".byte 0x66, 0x0f, 0xae, 0xf8");

static void
flush_clflushopt(void *addr, size_t len)
{
    // printf("addr %p len %zu", addr, len);

    uintptr_t uptr;

    /*
     * Loop through cache-line-size (typically 64B) aligned chunks
     * covering the given range.
     */
    for (uptr = (uintptr_t)addr & ~(FLUSH_ALIGN - 1);
         uptr < (uintptr_t)addr + len; uptr += FLUSH_ALIGN)
    {
        // _mm_clflushopt((char *)uptr);
        _mm_clflushopt((char *)uptr);
    }
}