The following code will fail under valgrind like this: 
vex x86->IR: unhandled instruction bytes: 0xF 0x1 0x45 0xDE


#include <iostream>
#include <pthread.h>
// Compile and run:
// g++ -m64 sgdtq.cc -lpthread && valgrind  ./a.out
void *sgdtq(void *) {
 char ret_val[16] __attribute__((__aligned__(16)));
 // valgrind will fail here:
 __asm__ __volatile__("sgdtq %0" : "=m" (ret_val[6])::"memory");
 uint64_t id =  *reinterpret_cast<uint64_t *>(&ret_val[8]);
 std::cout << id << std::endl;
}

int main() {
 const int N = 100;
 pthread_t t[N];
 sgdtq(NULL);
 // start many threads. On a multi-cpu machine
 // this progam should print several different numbers.
 for (int i = 0; i < N; i++) {
   pthread_create(&t[i], 0, sgdtq, 0);
 }
 for (int i = 0; i < N; i++) {
   pthread_join(t[i], 0);
 }
}