Secondary storage Consider a long sequence of accesses to a disk with 8 ms avera

Question

Secondary storage Consider a long sequence of accesses to a disk with 8 ms average seek time, 3 ms average rotational delay, and a data transfer rate of 60 Mbytes/sec The average size of a block being accessed is 64 Kbytes Assume that each data block is stored in contiguous sectors. Assuming that the blocks are randomly located on the disk, estimate the average percentage of the total time occupied by seek operations and rotational delays Input/Output The input status bit in an interface circuit is cleared as soon as the input data register is read Why is this important? A computer spends 80% of its time executing user-code and 20% of its time performing input/output operations If you regard I/O as an unnecessary' overhead, the efficiency of the computer is 80/(80 + 20) = 80 percent. Suppose that CPU performance is increasing at a compound rate of 40 percent per year and that the performance of I/O systems is increasing at a compound rate of 10 percent per year. In another two years, a new computer can be bought with both faster processing power and I/O performance How efficient would the new computer be in two years' time? Give a critique of the following statement: "Using a faster processor chip results in a corresponding increase in performance of a computer even if the main memory speed remains the same "

Explanation / Answer

2) input status bit is nothing but a signal to show a program that there is an input required to this program is waiting to be read. Once it is read, the status bit should be cleared for a program to process the input. it is important that this bit is cleared once the input is read so that the hardware can move on to the process or next input.

3) processing increase in each year + current performance -= 80 + 40 + 40 = 160

ip/op performance increase in each year + current performance =20 + 10 + 10 = 40

the increase in total performance = 160 / 160+40 = 80/100 = 80%

it performs 80% more than current performance. i.e double the performance of now

4)  the limitations found in a memory systems can be overcome by architectural designs inside the faster processors which can handle or mask those limitations in various ways. This means that your faster processor will be able to hide memory weaknesses in such a way as to render buying the faster memory almost useless. if the processor is weak and the memory is vast, the memory is useful only when the datas are high enough to handle. If the processor is faster and newer it can handle the situation using cache memories also. it makes the system work more efficiently.

Related Questions

Navigate

• Browse (All)
• Browse S
• Subjects

---

---

Integrity-first tutoring: explanations and feedback only — we do not complete graded work. Learn more.