Free Trial

Safari Books Online is a digital library providing on-demand subscription access to thousands of learning resources.

  • Create BookmarkCreate Bookmark
  • Create Note or TagCreate Note or Tag
  • PrintPrint

Exercises

1.What kind of storage devices are used in computer systems?
2.What is the difference between persistent storage and volatile storage?
3.Describe a couple of persistent- and volatile storage devices.
4.What is a storage hierarchy? Why is it used in computer systems? How is it organized?
5.Where CPU register allocation to data is concerned, who manages the CPU register-set, user or the system?
6.What is a data cache? Why are data caches used in operating systems?
7.How are data items in a cache addressed by users?
8.What are the three widely used cache organizations? What are their advantages and shortcomings?
9.What are the advantages of set-associative cache organization over direct-mapped- and fully-associative cache organizations?
10.What are the two cache-write strategies? How do they differ from one another? What are their pros and cons?
11.What is a prefetch? What is a demand fetch? How do they differ from each other?
12.Explain fetch-, placement-, and replacement rules of cache management. What is the difference between fetch-, placement-, and replacement rules?
13.Describe two shortcomings of the FIFO replacement scheme?
14.Explain the clock replacement scheme, and its pros and cons.
15.What is cache coherence problem?
16.What is the difference between write-invalidate and write-update coherence protocols?
17.Explain snoopy coherence protocol. What are its shortcomings?
18.What is the difference between delayed write and asynchronous write? Give an example of a situation in which (i) a delayed write and (ii) an asynchronous write is useful.
19.Suppose we have a processor with a hardware cache memory. Suppose a program is run by the CPU and this produces 500,000 memory references, out of which 475,000 hit the cache memory. Suppose average memory access time is 70 ns and cache access time 20 ns, of which 10 ns are for lookup. Suppose the system follows the write-through policy.
  1. What is the hit ratio?

  2. What is the average memory reference time as seen by the CPU if (i) all the memory references are read, (ii) 80% of the memory references are read, and (iii) 90% of the memory references are read?

20.Consider a typical storage hierarchy in a computer system. The hierarchy comprises a hardware cache (top level), a bank of main memory (intermediate level) and a disk (bottom level). Suppose the average memory access time is 70 ns and cache access time 20 ns, of which 10 ns are for lookup. The disk access takes 25 ms on the average. The computer system produces a hit ratio of 0.95 for the hardware cache and 0.75 for the main memory. What is the effective read access time for a word in the system?
21.What is the difference between a cache and a buffer?


  

You are currently reading a PREVIEW of this book.

                                                                                                                    

Get instant access to over $1 million worth of books and videos.

  

Start a Free 10-Day Trial


  
  • Safari Books Online
  • Create BookmarkCreate Bookmark
  • Create Note or TagCreate Note or Tag
  • PrintPrint