ASUS Eee PC 1201N Netbook On Linux Update

[phoronix]

Phoronix: ASUS Eee PC 1201N Netbook On Linux Update

My sabbatical with Windows is coming to an end next week, but during the past three weeks I have been using the brand-new ASUS Eee PC 1201N exclusively. This ASUS netbook that packs an Intel Atom 330 dual-core processor, NVIDIA ION graphics, a nice 12" display that runs at 1366 x 768, and 2GB of RAM has been working out quite well...

http://www.phoronix.com/vr.php?view=Nzg2Ng

[portets43]

hahaha

that's one of the most minor quirks i've ever heard of in linux.

to windows 7 though; i expect it to perform very well in tests. resist flaming me, but it is great quality stuff.

microsoft makes excellent products. minus vista....

i just hate their company practices. HATE THEM

[kraftman]

hahaha

that's one of the most minor quirks i've ever heard of in linux.

to windows 7 though; i expect it to perform very well in tests. resist flaming me, but it is great quality stuff.

Testing defaults will only show Ubuntu isn't tweaked for performance in some areas. I can't say Win7 is a great quality stuff. I'd love to see how it performs in sysbench benchmarks (if they're available on this) and at least on some quad core CPU. It would probably squeal there.

[cl333r]

Testing defaults will only show Ubuntu isn't tweaked for performance in some areas. I can't say Win7 is a great quality stuff. I'd love to see how it performs in sysbench benchmarks (if they're available on this) and at least on some quad core CPU. It would probably squeal there.

I have on my computer XP, win7, Ubuntu etc.
I wanted to benchmark these OSes but not use anything that would involve drivers (eg. graphics driver, cause a lot boils down to the quality of drivers).
So I decided to create a simple (C++) test that would use the CPU and the RAM (allocating and initialising a lot of ints on the heap and testing their values).
And guess what, Ubuntu came out as the winner.

Ubuntu 32bit - 8 seconds.
WinXp 32bit = about 1 minute
Win7 (64bit but the .exe test was 32bit) = 13 seconds.

Under windows I compiled in Visual Studio with /O2, and under Ubuntu with gcc and -O2.
No, WinXP is not that slow, in this test winXP decided to use the "cache file" instead of the physical RAM for some reason, that's why it was sooo slow to complete, Win7 as you can see was "smarter", but still behind Ubuntu. I checked, the ints and pointers to ints all had same size.
Yes, it's just a glimpse/benchmark, but it's the most "neutral" one I could think of, and it's enough for me to have a general clue about what loads each system can sustain "by default".

Any benchmarks that involve (proprietary) drivers (on both OSes) that are developed primarily for windows with Linux as an afterthought I think don't deserve too much attention.

[thefirstm]

Don't forget to try 64-bit Ubuntu as well.

[loonyphoenix]

Any benchmarks that involve (proprietary) drivers (on both OSes) that are developed primarily for windows with Linux as an afterthought I think don't deserve too much attention.

Except to evaluate the drivers themselves, not the operating systems. That sort of information can be very useful, too.

Plus, finding out which tasks are not hindered by second-rate drivers can be useful too.

[Linuxhippy]

Its news like this, where I wonder wether the content is worth the key-presses you did :-(

[cl333r]

Its news like this, where I wonder wether the content is worth the key-presses you did :-(

No matter what you do there'll always be someone thinking this way and/or completely disagreeing with you. One can use your own words for your own post.

As to benchmarking 64 bit Ubuntu "against" 64 bit Windows (7) I found an issue: the availability of a final edition of 64 bit Visual Studio (and I didn't bother much searching how to create 64 bit code on windows with VStudio).
Why does it matter, well, for many reasons, in short, one needs to compare not only 64 bit OSes but also "true" 64 bit executables.

[thefirstm]

For alot of Windows applications, only 32-bit executables are (easily) available. On Ubuntu, most applications have native 64-bit executables in the repo. Therefore, testing 32-bit Windows executables against 64-bit Linux executables is actually fair, since most people are not going to be downloading the source for their Windows applications and recompiling them 64-bit.

[deanjo]

Yes, it's just a glimpse/benchmark, but it's the most "neutral" one I could think of, and it's enough for me to have a general clue about what loads each system can sustain "by default".

By running a 32 bit binary on windows 7 64 though you are not really benching it but the performance of wow64, windows 32-bit emulator.