On last.fm: Michael Jackson radio - Listen now!
BNET Business Network:
BNET
TechRepublic
ZDNet
TalkBack 16 of 35:
Next »
« Previous
what you think is speed may not be
Let's say you have a 1 GHz CPU and a 1.4 GHz CPU. Which is faster?

With only that much information, you can't tell.

Processor speeds refer to clock speed, or the speed at which the CPU can compute. What is critical is latch speed, which is (basically) the speed at which a CPU can fetch another instruction to do work. Assuming everything else is perfect for both CPUs:

The clock speed, or 'cycle' of the 1 GHz CPU is a billionth of a second, or a nanosecond.

Let's say the old 1 GHz CPU could latch an instruction in 1 nanosecond. That is pretty good. That means that your 1 GHz CPU can fetch the next instruction as soon as it is done with the current one. A lot of instructions take more than 1 cycle, so your 1 GHz CPU is actually doing a good job using its resources since it can work on another instruction immediately after finishing the current one.

Let's say that some chip-maker was having a rough time. Everyone else had 1.4 GHz chips coming out, so they needed to market one too, but they just can't get their latch speed fast enough. A cycle in a 1.4 GHz CPU is much shorter, about .7 nanoseconds, but their latches only can transmit an instruction in 1 nanosecond.

So... they bulid and market a CPU with a 1.4 GHz clocked processing core and a pipeline with 1 nanosecond latches. What happens?

The CPU can only accept a new instruction every .7 nanoseconds, but the instructions can only be delivered every 1 nanoseconds... so the CPU has to wait two clock cycles to get each instruction.

Let's presume you have a big program of 1 billion instructions.

The 1 GHz CPU with the 1 nanosecond latch speed will take 1 second to complete it. Remember, a nanosecond is a billionth of a second, and a Gigahert is one billion operation per second. So, your one billion instructions would executed one after the other, each immediately following the last.

What about the 1.4 GHz CPU?

Well, it can only get an instruction every 1.4 nanoseconds. Since the latch speed is slower than the processor core's clock the CPU can only get one instruction every two cycles.

The same bunch of instructions will take 1.4 seconds to run on the 1.4 GHz machine.

The CPU will latch an instruction, execute it, which takes .7 nanoseconds, wait one cycle, which takes .7 nanoseconds, and then can latch the next instruction.

This is an overly simplified example, assuming everything else in the computers is the same and can the instructions are fed in at infinite speed and blah, blah... but the fact remains that clock speed makes your processor WAIT faser, not necessarily WORK faster.

This being said... 1.4 GHz doesn't mean .4 GHz faster than 1 GHz. It basically just means one is different. Whether it is faster or not depends on MANY other things.

So... maybe these nice, new low-power chips have lower clock speeds, but they might be able to get the job done faster and with less power than their big brothers.
Posted by: deymious@...   Posted on: 08/23/05 You are currently: a Guest | Members login | Terms of Use

Alert moderator to an offensive message

Subscribe to this discussion via Email or RSS

The speed race is over. The power race is on.  DonnieBoy | 08/23/05
don't we all wish that...  ctk76 | 08/23/05
At last Intel started catching up  michael_t | 08/23/05
Overheating  dch48 | 08/23/05
Old Story  in-DUH-vidual | 08/23/05
Its true i reheated chineese food with it  BuckRogers_z | 08/24/05
RE: That's nice; now for speed?  Krazyken39 | 08/23/05
now for speed  linuxoverwindows | 08/23/05
Power consumption is of little interest to me  stan@... | 08/23/05
Re Power Consumption  joedokes | 08/23/05
Oh Really?  panzrwagn | 08/23/05
Really  stan@... | 08/24/05
The market's going away from your preference...  kjartan93 | 08/24/05
It usually does  stan@... | 08/24/05
Low power? So what  Raed009 | 08/23/05
what you think is speed may not be  deymious@... | 08/23/05
nice work...  linuxoverwindows | 08/23/05
Here Here  bka1959 | 08/23/05
Re: nice work  Ande_z | 08/24/05
It gets worse  CobraA1 | 08/23/05
Power vs Actual Work Done (i.e.SpecInt)  usr001 | 08/24/05
actually...  deymious@... | 09/18/05
Thank you  G Fedorchuk | 08/25/05
Intel: more power less enrgy  chanhqvo | 08/23/05
Roadmap and Apple  Mr_Dave | 08/23/05
I'll be Watching...  Jkirk3279 | 08/23/05
On sharing IBM technology...  flatliner | 08/23/05
Torvolds strikes again  Roger Ramjet | 08/24/05
New Architecture  Old Guy_z | 08/24/05
I agree speed race over  kokuryu | 08/24/05
RE: "I agree speed race over"  ajapierce | 08/24/05
Parasite-ware... good one  Mr_Dave | 08/24/05
Great for the Road... not so good for the ....  BuckRogers_z | 08/24/05
IDF shows INTEL is far far behind  sharikou | 08/26/05
Who cares?  Thore | 02/07/06

What do you think?

SponsoredWhite Papers, Webcasts, and Downloads

  • Smart Tech Expert advice on innovations in healthcare and the green technologies that make it happen. Find out more
  • Smart Business Discussion and advice on management issues that revolve around making your world smarter and more useful. More Smart Advice
  • Smart People The best and worst moves in the management and strategy trenches. Learn More