atomicCAS for bool implementation

Question

I\'m trying to figure out is there a bug in the answer (now deleted) about the implementation of Cuda-like atomicCAS for bools. The code from the answe

Answer 1

Many many thanks to @RobertCrovella; the first code sample does contain a bug, the second does fix it, but is not thread-safe (see question comments for details). The thread-safe fix:

static __inline__ __device__ bool atomicCAS(bool *address, bool compare, bool val)
{
    unsigned long long addr = (unsigned long long)address;
    unsigned pos = addr & 3;  // byte position within the int
    int *int_addr = (int *)(addr - pos);  // int-aligned address
    int old = *int_addr, assumed, ival;

    bool current_value;

    do
    {
        current_value = (bool)(old & ((0xFFU) << (8 * pos)));

        if(current_value != compare) // If we expected that bool to be different, then
            break; // stop trying to update it and just return it's current value

        assumed = old;
        if(val)
            ival = old | (1 << (8 * pos));
        else
            ival = old & (~((0xFFU) << (8 * pos)));
        old = atomicCAS(int_addr, assumed, ival);
    } while(assumed != old);

    return current_value;
}