Q2. (8 Pts: 1 pt. each, 15 minutes] Indicate whether the following statements are true or false, device qualifier may be called on the host or the 1. [] Functions annotated

with the device 2. [ ] Page faults cannot be handled by software because the overhead is too large. 3. [ ] Virtual memory space has to be bigger than the physical memory space. 4. [] You can have a miss in the TLB, a hit in the page table, and a miss in the cache for a single memory access. 5. [ ] Shared memory in CUDA is accessible to both the host and GPU 6. [] In the case of warp divergence; all possible execution paths are run by all threads in a warp serially so that thread instructions do not diverge. 7. ] All thread blocks involved in the same computation use the same kernel 8. [] Is it possible to multiply two 1024X1024 matrices using a tiled matrix multiplication code with 1,024 thread blocks on a device of block size of 512 threads. Note that each thread in a thread block calculates one element of the result matrix.