-1
$\begingroup$

I find this question while solving some government job question bank. If someone could provide the answer along with a little explanation it would be very helpful.

Ques:- If the Intel Pentium processors, was not made compatible to programs written for its predecessor, it could have been designed to be a faster processor.

  1. The statement is true
  2. The statement is false
  3. The speed cannot be predicted
  4. Speed has nothing to do with the compatibility

(I did not find any tag as microprocessor or something so i have to keep it under the tag computer architecture, sorry for that, but i did not have sufficient reputation to create a tag.)

$\endgroup$
  • 1
    $\begingroup$ Your question is unclear. Please, define what you mean by "faster". Please, define what you mean by "could be designed". Are you looking for some hypothetical theoretical maximum? Also, this doesn't sound like a Computer Science question, more like Computer Engineering one. And what are your constraints? How much money are you allowed to spend on the design? How much time can it take? How big can the processor be? How hot can it? How expensive is the resulting product allowed to be? $\endgroup$ – Jörg W Mittag Jun 9 at 5:53
  • $\begingroup$ @JörgWMittag as i have mentioned this is a question from one of the entrance exam, so i have just pasted it as it is. By faster, it means "faster" in terms of processing speed, "could be designed" is a case, which is asked whether it will be true or false, if the given condition is satisfied, or it does not depend upon the given condition, I does not find any community named Computer Engineering and i know microprocessors is a part of computer science so i have posted the question here, The question also does not require any constraints. $\endgroup$ – Atul Kumar Jun 9 at 6:37
  • $\begingroup$ @JörgWMittag the question is simple, a condition is given based on which whether it is possible to achieve certain improvement or not is asked, $\endgroup$ – Atul Kumar Jun 9 at 6:39
  • 1
    $\begingroup$ Being unable to find an appropriate tag is usually a sign that a question is off-topic. To me, questions about whether a specific design requirement affected the performance of a specific CPU isn't really a question about computer science. $\endgroup$ – David Richerby Jun 9 at 8:22
1
$\begingroup$

Let me ask you a similar question. If car X, which is automatic, didn't have to support manual gear, then it could have been designed faster:

  1. The statement is true
  2. The statement is false
  3. The speed cannot be predicted
  4. Speed has nothing to do with the compatibility

What do you think?


Let me mention in passing two relevant points from the world of computers:

  • Intel did design a Pentium-replacement with a completely new architecture, Itanium. It wasn't successful, for various reasons. One of them was lack of compatibility.

  • All problematic aspects of Windows are often blamed on backward compatibility.

$\endgroup$
  • $\begingroup$ I would argue the failure of Itanium is attributable to a) over-estimating the intelligence of compilers, b) completely getting blindsided by the shift from "Moar FLOPS at all cost" to "More efficient FLOPS, both in terms of money and energy". I read an article once that mentioned in passing that the original Itanium spent on some select SPEC benchmarks up to 80% of cycles speculatively executing instructions that were then thrown away. That is a 400% (or 5x) overhead in first getting energy into the CPU (electrical power) and then getting it out again (HVAC). $\endgroup$ – Jörg W Mittag Jun 9 at 15:00
  • $\begingroup$ Interestingly, the Pentium4 was a dead-end for the exact same reason(s). $\endgroup$ – Jörg W Mittag Jun 9 at 15:01

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.