logo

Windows is without a doubt the most popular operating system out there today. With the release of Windows 7 just around the corner I thought why not compare all three operating systems to each other. I’ve taken all three operating systems and put them through their paces in a rather large series of tests comparing everything from video rendering to CPU and memory performance. I’ve got some rather interesting results for you, not quite what I expected, and I’m sure not what most people expected either. Continue on to learn how these operating systems stack up to one another…

I’ll start off with the specs of my system for you.

CPU: Intel Q9650 (3ghz)

RAM: 8gigs OCZ Fatal1ty PC2-6400

Motherboard: EVGA NF-680i

Video Card: Sparkle Nvidia GTX260 (896mb ram) –Main Monitor 22” 1680×1050 Res

Video Card2: EVGA 8600GTS (for PhysX)

Video Card2: ECS Nvidia GTS250 –Dual 20” 1680×1050 Res

 

The operating systems are:

Vista Ultimate 64bit

Windows 7 Ultimate 64bit

Windows XP 32bit

 

We’ll start the testing off with Crystalmark 2004R3

I like to use Crystalmark because it basically tests all aspects of the system and then also gives you an overall Mark or Score for your system that you can then compare to others.

-Higher score is better

crystalmark

As we can see, XP scores better overall, but why?

here’s the individual testing results with all the scores:

crystalmark-vista crystalmark-w7 crystalmark-xp

In the OpenGL and CPU Intensive testing we see that Windows XP handles them much better than the other two operating systems. We know that early on there was a problem with OpenGL in Vista, and supposedly it was fixed, but obviously it appears there’s still some problems with both Vista and 7 in regards to OpenGl support.

The next test would be Super Pi Mod v1.5XS and the time to calculate Pi to 32 Million places.

-lower score of time is better

super pi

Surprisingly Windows 7 has the best time to complete the calculations, coming in a good 15 seconds faster than Xp and almost 20 faster than Vista.

 

The next test is a Video Conversion test, I’ve taken a .AVI video file and converted it to .WMV format. I used the same file I got from my WinX DVD Ripper Review a little while ago, the movie is The Hunger. For the test I used WinX Video Converter and didn’t change any settings, it was straight conversion from one format to the other.

The Clip is 1.1oGB in size with a length of 1:36:24 running time.

vid convert

-lower times are better

vid conversion

Windows XP has the best video conversion performance coming in six seconds faster than Windows 7 and 21 seconds faster than Vista. Really though six seconds isn’t much, and neither is the extra 21 seconds it took Vista. All of them performed the conversions fine, the movie looked perfect.

The next test I’ve got is 3dmark06.

We all know what this one is, so no explanation needed I think.

-higher scores are better.

3dmark06

Windows Xp has a nice lead over both of the other operating systems, not even close really. As we can see Vista would be the worst performance, with 7 coming in a close second.

So far three out of these four tests have gone to Windows Xp.

The next test I’ve got is Cinebench.

If you don’t know what Cinebench is, here’s a quote from their site:

CINEBENCH is a real-world test suite that assesses your computer’s performance capabilities. MAXON CINEBENCH runs several tests on your computer to measure the performance of the main processor and the graphics card under real-world circumstances.

The test procedure consists of two main components: The first test sequence is dedicated to the computer’s main processor. A 3D scene file is used to render a photoreaslistic image. The scene makes use of various CPU-intensive features such as reflection, ambient occlusion, area lights and procedural shaders. During the first run the benchmark only uses one CPU (or CPU core) to ascertain a reference value. On computers that have multiple CPUs or CPU cores and on those that simulate multiple CPUs (via HyperThreading or similar technolgies), MAXON CINEBENCH will run a second test using all available CPU power.

The second test measures graphics card performance and is run inside the 3D editor window. The project file used can test all graphics cards that support the OpenGL standard. In this scene, only the camera was animated. This scene places medium to low demands on graphics cards and tests the maximum speed with which the scene can be properly displayed.

 

-Higher scores are better

cinebench

Again we see Windows XP leading in the OpenGl testing, no surprise there, but it then falls behind Windows7, but not by much, in the other two tests. Vista just isn’t too good all around…

To finish off I’ve got several tests from SiSoft Sandra 2009 SP4. Sandra is a great suite of tools to really benchmark and test your system.

The first test is Processor Cache and Memory:

Processor Cache and Memory

Benchmark the processors’ caches and memory access (transfer speed).

Results Interpretation:

Cache/Memory Bandwidth (MB/s) – higher results are better, i.e. faster memory bandwidth.

Speed Factor (MB/s) – lower results are better, i.e. less difference between processor cache speed and memory speed.

Combined Index: is a composite figure representing the overall performance rating of the entire Cache-Memory performance in terms of MB/s. The value is the logarithmic average of all the results for the entire address space. (Higher is better, i.e. better performance)

Speed Factor: is a figure representing the speed differential between the CPU’s cache and memory. The value is the ratio of the fastest cache (i.e. L1) bandwidth to the main memory bandwidth. (Lower is better, i.e. the memory is not very much slower than CPU’s cache)

cache and memory

The results are a mixed bag with no real winner here in this test. Windows XP though appears to be the better performer but the results are very close for all of them.

 

Next up I’ve got CPU Arithmetic:

Processor Arithmetic

Benchmarks the ALU and FPU processor units. Shows how your processors handle arithmetic and floating point instructions in comparison to other typical processors.

Results Interpretation:

Dhrystone (MIPS) – higher results are better, i.e. better integer performance.

Whetstone (MFLOPS) – higher results are better, i.e. better floating-point performance.

 

CPU arithmetic

If anything we can see that Vista lags behind in two of tests, it would appear that XP performs a bit better really with more rounded performance results.

Many of us use our computers for multi-media so I think it’s very important to know how these operating system will perform, so the next test is CPU Multi-Media:

Processor Multi-Media

Benchmark the (W)MMX(2), SSE(2/3/4), AVX processor units. Shows how your processors handle multi-media instructions and data in comparison to other typical processors.

Such operations are used by more specialised software, e.g. image manipulation, video decoders/encoders, games.

Results Interpretatio :

Multi-Media Integer (Pixels/s) – higher results are better, i.e. better integer performance.

Multi-Media Single/Double Float (Pixels/s) – higher results are better, i.e. better floating-point performance.

 

cpu multimedia

Clearly for any Multi-Media you want Windows 7, Windows XP lags very far behind in all of the tests, but Vista come in a very close second place.

 

For the next test I’ve got a GPU centric one called Graphics (GPGPU) Bandwidth.

Graphics (GPGPU) Bandwidth

Benchmark the bandwidth of the memory of the graphics processors (GPGPUs) and the bandwidth of the bus that connects them to your computer.

Results Interpretation
Internal Memory Bandwidth (MB/s) – higher results are better, i.e. faster internal memory bandwidth.

Data Transfer Bandwidth (MB/s) – higher results are better, i.e. faster data transfer between the GPU and computer.

GPGPU Bandwidth

Very similar performance across all operating systems, so close that you’d never ‘feel’ the differences in the real world. So it’s safe to say that they’re all pretty much the same in terms of this test.

 

The next test would be memory bandwidth.

Memory Bandwidth

Benchmark the memory bandwidth of your computer.

Results Interpretation:

Integer Memory Bandwidth (MB/s) – higher results are better, i.e. faster memory bandwidth.

Float Memory Bandwidth (MB/s) – higher results are better, i.e. faster memory bandwidth

Memory bandwidth

And again we see that Windows Xp is the clear and balanced choice , but still the results are very close overall.

 

Next up we’ve got Memory Latency and you’d think with the same exact ram in there that this test might be close.

Memory Latency

Benchmark the latency (response time) of processors’ caches and memory

The latency of caches is measured in processor clocks (i.e. how many clocks it takes for the data to be ready) as it is dependent on the processor clock speed.

The latency of memory is measured in nanoseconds as it is typically independent on processor clock speed.

-lower scores are better

memory latency

We see that 7 and XP are almost equal, there’s really no difference between them, at least that you’d ever notice. Vista on the other hand doesn’t do too well here does it?

 

With dual and quad core processors being so popular, this test is also a fairly important one I think.

Multi-Core Efficiency

Benchmark the multi-core efficiency of the processors.

The ability of the cores to process data blocks and pass them to another core for processing (producer-consumer paradigm) of different sizes and different chain sizes is measured. The efficiency of the inter-connect between cores is thus benchmarked; however, the number of cores (and processors) also counts as more data buffers can be processed simultaneously (aka "in flight").

-higher is better for bandwidth

-lower is better for latency

Multicore effic

 

Windows 7 takes it here, but not by much. Oddly we see Vista with a much lower latency than the other two operating systems. Then again we are talking nanoseconds, so really there’s not much of a difference is there?

 

So with these results, what do you get from all of this?

To me, it looks as though Windows Xp is still the best choice for an operating system. Sure the others look nicer, but in terms of performance I think Xp is the one to go with on average. Yes Vista and 7 have DirectX 10, but how much of a difference does that really make? Vista and 7 have Aero, but again that just makes things look nice, they’re nice tweaks and little improvements to usability but in terms of performance it doesn’t do much except maybe hinder it.

Maybe I could turn Aero off and see what kind of results I get then? I’ve always wondered what kind of impact it has on the system.