What does it mean if your Measured integer speed declines?

Jim Milks
Jim Milks
Joined: 19 Jun 06
Posts: 116
Credit: 529,852
RAC: 0
Topic 192822

The title says it all. My MacBook has seen its Measured integer speed recently decline from >4000 to 3939.2 whereas the measured floating point speed has remained constant. Should I be worried? Or could updating BOINC (as I did two or three months ago) cause the appearance of a decline?

roadrunner_gs
roadrunner_gs
Joined: 7 Mar 06
Posts: 94
Credit: 3,369,656
RAC: 0

What does it mean if your Measured integer speed declines?

You are complaining about a loss of 1.5 %.
That amount is considered statistical dispersion or tolerance.

Jim Milks
Jim Milks
Joined: 19 Jun 06
Posts: 116
Credit: 529,852
RAC: 0

RE: You are complaining

Message 68027 in response to message 68026

Quote:
You are complaining about a loss of 1.5 %.
That amount is considered statistical dispersion or tolerance.

My previous measured integer speed was actually between 4000 and 4100, so the actual loss is ~3 to 4%. I'm not sure what you mean by statistical dispersion or tolerance--my field of study (old field succession) doesn't require that knowledge. :-) My main concern is if this loss means something is going wrong with my computer. If so, I'd like to correct any problems before the computer crashes. After all, my dissertation is on this particular computer.

Astro
Astro
Joined: 18 Jan 05
Posts: 257
Credit: 1,000,560
RAC: 0

The benchmarks are run each

The benchmarks are run each time you change Boinc versions, and then every 5 days after that. small fluctuations are normal. The benchmark measures in cpu time, so other running processes shouldn't affect it greatly. Try running the benchmark manually (advanced - rerun benchmarks), you'll see that they're close, but generally not the same on every run.

Now, if you see your benchmarks cut in half, then overheating maybe be happening and your cpu frequency may be being cut in half by ondie thermal diode, Or cool'n'quiet "like" program (energy saving software)

Dave Burbank
Dave Burbank
Joined: 30 Jan 06
Posts: 275
Credit: 1,548,376
RAC: 0

RE: RE: You are

Message 68029 in response to message 68027

Quote:
Quote:
You are complaining about a loss of 1.5 %.
That amount is considered statistical dispersion or tolerance.

My previous measured integer speed was actually between 4000 and 4100, so the actual loss is ~3 to 4%. I'm not sure what you mean by statistical dispersion or tolerance--my field of study (old field succession) doesn't require that knowledge. :-) My main concern is if this loss means something is going wrong with my computer. If so, I'd like to correct any problems before the computer crashes. After all, my dissertation is on this particular computer.

It's not a big deal at all... your measured speed will change a bit every time the benchmark is run. 100 points is nothing in the grand scheme of things.

There are 10^11 stars in the galaxy. That used to be a huge number. But it's only a hundred billion. It's less than the national deficit! We used to call them astronomical numbers. Now we should call them economical numbers. - Richard Feynman

Comment viewing options

Select your preferred way to display the comments and click "Save settings" to activate your changes.