debian hardinfo benchmarks

[klx300r]

Maybe I misunderstood the processor part of the Hardinfo benchmark, but isn't it a CPU test (which in today reads: Core) by design? If you want a view of real life effects of single or multiple cores you would use other tests, like indeed the Blender benchmark?



...which won't affect anything at all, the 3D acceleration is purely a GUI thing in Blender.

grandma, for the 10'th time, Hardinfo is NOT MULTI THREADED so knowing that the benchmark figures are misleading..period. :smack:
our friend Piru knows this and chooses to not correct the graphs for some 'strange' reason.

as for Blender results you see the difference that using 1 thread as compared to both right? having 3D acceleration should slightly improve the render times as they definitely won't get worse

[drHirudo]

That sounds interesting. I wouldn't mind seeing that.

Yet another interesting calculation would be:

How long you need to keep your X1000 on for it to "pay the difference in initial cost", compared to f.ex. earlier higher end A1 models (other OS4 choices), Mac Mini (what it was ported for but not released), higher end PowerMacs (including G5) and PowerBooks (what OS4 could run on "relatively easily")

Also could throw in "same spec" X86 as that's what some people will start demanding right away :lol:

I bought my microA1 back in January 2005. Works flawlessly till now. Thats 89 months. Oh well, I had to buy $3 battery and replace it two months ago.


Bought in July 2011 Dell Inspiron laptop. It broke in December and in February 2012 I returned it back and had to pay extra to get another laptop from another brand.

So far the ALL the Amiga hardware I have performs good. That includes the old machines.

[Jupp3]

having 3D acceleration should slightly improve the render times as they definitely won't get worse

Well, if you have GUI running, then you might see few (low) percent decrease in rendering times, as it might waste some CPU time drawing the GUI (which could be used rendering).

But it's been long time since I did some benchmarks, but isn't it possible to run blender from command line without a gui, and tell it to render specific (given from command line) scene?

That way it won't use gfx card at all, so you can see if you can get few percent faster renders :lol:

Doing:
blender -b scene.blend -f 1

Will render the specified frame (1) of the given scene to /tmp/0001.png

With -t you can specify amount of threads (how many cores will be used)

[takemehomegrandma]

grandma, for the 10'th time, Hardinfo is NOT MULTI THREADED

Wasn't that *exactly* what I just said? :confused: It was what I meant, anyway...

our friend Piru knows this and chooses to not correct the graphs for some 'strange' reason.

Given the above, everything *is already correct*, modifying the data would be tampering with the results! If you want to measure the CPU's SMP capabilities you would have to use other benchmarks, like blender (or numerous others)! It seems you don't understand the benchmark...?

as for Blender results you see the difference that using 1 thread as compared to both right?

Yes? :confused:

having 3D acceleration should slightly improve the render times as they definitely won't get worse

Since none of the benchmarks are using GPU for rendering (it's supposed to be a benchmark of the *CPU*), it won't get any better either...

[klx300r]

...

Given the above, everything *is already correct*, modifying the data would be tampering with the results! If you want to measure the CPU's SMP capabilities you would have to use other benchmarks, like blender (or numerous others)! It seems you don't understand ..

Who is talking about changing data & tampering??? Again as I stated too many times, a simple line stating that the X1000 results are based on only 1 thread will suffice.
Not noting that simple fact is simply wrong/ misleading/ inaccurate/ trolling.

[takemehomegrandma]

a simple line stating that the X1000 results are based on only 1 thread will suffice.

Why? The benchmark (and the results) can only be 1 thread, right?

[fishy_fiz]

That sounds interesting. I wouldn't mind seeing that.

Yet another interesting calculation would be:

How long you need to keep your X1000 on for it to "pay the difference in initial cost", compared to f.ex. earlier higher end A1 models (other OS4 choices), Mac Mini (what it was ported for but not released), higher end PowerMacs (including G5) and PowerBooks (what OS4 could run on "relatively easily")

Also could throw in "same spec" X86 as that's what some people will start demanding right away :lol:

Ivy Bridge cpus use less power than either. Theyre actually being aimed at netbook use such is their power consumption (or lack of). AMD cpus of course are a different story despite being lower performing.

[jorkany]

Why? The benchmark (and the results) can only be 1 thread, right?

I wonder if he would be so obsessive about unnecessary labeling if the X1000 had been a better performer?

[Terminills]

I wonder if he would be so obsessive about unnecessary labeling if the X1000 had been a better performer?

My money is on no.

[kickstart]

@takehomegrandma

You have too many patience with some people.

[dammy]

My money is on no.

+1

[klx300r]

Why? The benchmark (and the results) can only be 1 thread, right?

why does it say so somewhere ? if it was made clear this was the case then there would be no doubt, right?

[klx300r]

I wonder if he would be so obsessive about unnecessary labeling if the X1000 had been a better performer?

I just would like a test to be factual. If the benchmarks used multi threads those graphs would look quite different, but then again, this thread wasnt started to outline facts and truths right :rolleyes:

[klx300r]

@takehomegrandma

You have too many patience with some people.

I must have patience with grandma as I work with elderly people all the time:razz:

[Hammer]

Ivy Bridge cpus use less power than either. Theyre actually being aimed at netbook use such is their power consumption (or lack of). AMD cpus of course are a different story despite being lower performing.

Beyond 4Ghz for both Ivybridge and Bulldozer, the AMD Bulldozer can still tangle with Intel Ivybridge . http://forums.anandtech.com/showthread.php?t=2243073

When all threads can be used, Bulldozer does a good job of making up for the lost single threaded performance. Scaling for FX outshines the i7 3770k by a significant margin. Most notably with techarp's x264 HD, where my FX 8150 @ 4.9 Ghz beats a 5.0 Ghz 2600k, and narrowly loses to a 4.9 Ghz 3770k. (Check source 19)

In TrueCrypt 7.1a we see a 4.9 Ghz FX 8150 performing slightly better than its 22nm 3770k intel counterpart at 4.7 Ghz.

In 7-Zip we see the FX 8150 jumping 2.7 % percent ahead of its 3770k counterpart at the same 4.9 Ghz clock for Compression, but falling behind 2.7% with decompression.

The temperature of a 3770k is also seen to sky-rocket up to 78C during a SuperPi 32m test, while my FX 8150 doest hit above 59C

[Rob]

@Kesa

This thread is good news to Hyperion. There is nothing wrong in OS4 regarding raw CPU performance.

MorphOS is faster than OS4 on Pegasos II so there is the potential for OS4 to ring more out of the X1000 than it currently does.