Tell me more ×
Super User is a question and answer site for computer enthusiasts and power users. It's 100% free, no registration required.
up vote 12 down vote favorite
2

Possible Duplicate:
What are the technologies that make a single processor core faster than a single processor core of the same frequency that was released years ago?

How come, for example, a 2.66GHz dual core i5 will be faster than a 2.66 core 2 duo? Is this because of newer instructions that can process information in less ticks?

share|improve this question
Wow both breakthroughs and david's are great answers...I dont know which to pick as correct :P – agz Jan 30 at 2:42

marked as duplicate by techie007, Dennis, Tog, Keltari, Kez Jan 30 at 10:47

This question has been asked before and already has an answer. If those answers do not fully address your question, please ask a new question.

2 Answers

up vote 15 down vote accepted

It's not because of newer instructions usually. It's just because the processor requires fewer instruction cycles to execute the same instructions. This can be for a large number of reasons:

  1. Large caches mean less time wasted waiting for memory.

  2. More execution units means less time waiting to start operating on an instruction.

  3. Better branch prediction means less time wasted speculatively executing instructions that never actually need to be executed.

  4. Execution unit improvements mean less time waiting for instructions to complete.

  5. Shorter pipelines means pipelines fill up faster.

And so on.

share|improve this answer
I believe the Core architecture has a 14-15 stage pipeline (ref), and the Nehalem/Sandy Bridge has roughly a 14-17 stage pipeline (ref). – Breakthrough Jan 30 at 0:10
Shorter piplines are easier to keep full and reduce the penalties of pipeline flushes. Longer pipelines generally permit higher clock speeds. – David Schwartz Jan 30 at 0:11
That's what I mean, I think the pipeline depth itself has remained the same or has increased. Also in the Intel 64 and IA-32 SW Dev Manuals, the last mention of a pipeline change is in Vol. 1, Ch. 2.2.3/2.2.4 (the Intel Core/Atom microarchitectures). – Breakthrough Jan 30 at 0:13
The effort to raise clock speeds has resulted in longer pipelines. That got ridiculous (as many as 31 stages!) towards the end of the NetBurst era. These days, it's a delicate engineering decision with advantages and disadvantages both ways. – David Schwartz Jan 30 at 0:19
up vote 12 down vote

The absolute definitive reference is the Intel 64 and IA-32 Architectures Software Developer Manuals. They detail the changes between architectures, and they're a great resource to understand the x86 architecture.

I would recommend that you download the combined volumes 1 through 3C (first download link on that page). Volume 1 Chapter 2.2 has the information you want.

Some general differences I see listed in that chapter, going from the Core to the Nehalem/Sandy Bridge microarchitectures are:

  • improved branch prediction, quicker recovery from misprediction
  • HyperThreading Technology
  • integrated memory controller, new cache hirearchy
  • faster floating-point exception handling (Sandy Bridge only)
  • LEA bandwidth improvement (Sandy Bridge only)
  • AVX instruction extensions (Sandy Bridge only)

The complete list can be found in the link provided above (Vol. 1, Ch. 2.2).

share|improve this answer

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