My benchmarking marathon last week seemed to generate more questions and requests for further benchmarking. A popular request from you, Constant Reader, was to see Windows Vista 32-bit benchmarked against Windows Vista 64-bit.
You asked, I delivered. Enjoy!
The Test System
To carry out this run of benchmarks I chose a base system that represents the sort of system that someone might want to have 4GB or more of RAM installed and therefore want to go the 64-bit route. I'm certain that my choice of system will generate a lot of feedback relating to its suitability.
Here’s the spec of that system:
- Phenom 9700 quad-core processor
- ATi Radeon 3850 graphics card with 256MB RAM
- ASUS M3A32-MVP Deluxe motherboard
- 2GB (2 x 1GB) Corsair Dominator CM2X1024-8500C5D RAM
- Western Digital Raptor 10,000RPM 150GB primary hard drive
- Western Digital Caviar 7,200RPM 500GB secondary hard drive
The following OS combinations were tested:
- Vista 32-bit RTM
- Vista 32-bit SP1
- Vista 64-bit RTM
- Vista 64-bit SP1
Each system was fully patched with all patches available from Windows Update.
Other noteworthy points:
- The only driver installed was the graphics card driver - Catalyst 8.2.
- No optimizations were carried out other than to process idle tasks and defrag the hard drive between each test.
- Windows Defender was left on for all tests.
- The Microsoft SP1 testing guidelines document was followed closely.
This time we’re going to use a purely synthetic benchmark - PassMark PerformanceTest 6.1.
Note: With PassMark ratings, the higher the number, the better the score.
Each test was run four times and the lowest score from each run was discarded. The remaining results were then averaged to produce a final PassMark rating.
Let's look at the average PassMark rating for the four different platforms:
- Vista 32-bit RTM PassMark rating: 1002.4
- Vista 32-bit SP1 PassMark rating: 972.3
- Vista 64-bit RTM PassMark rating: 1183.1
- Vista 64-bit SP1 PassMark rating: 1128.8
Vista 32-bit RTM left, Vista 32-bit SP1 right
Vista 64-bit RTM left, Vista 64-bit SP1 right
Taking a closer look at the PassMark PerformanceTest output shows an almost across the board improvement in performance when comparing 64-bit to 32-bit Vista (only the disk component of the test showed a decline in performance on 64-bit).
Some quick number crunching reveals some interesting data.
- Windows Vista 32-bit SP1 gets a PassMark rating that's 3.0% lower than Windows Vista 32-bit RTM.
- Windows Vista 64-bit SP1 gets a PassMark rating that's 4.6% lower than Windows Vista 64-bit RTM.
So far, we're seeing PassMark ratings that are in line with earlier benchmarking tests comparing Vista RTM with Vista SP1 - that is, the SP1 system returns a lower PassMark rating than RTM. OK, but this test was to compare 32-bit Vista against 64-bit Vista. Doing this gives us some very interesting results:
- Windows Vista 64-bit RTM gets a PassMark rating that's 18.0% higher than Windows Vista 32-bit RTM.
- Windows Vista 64-bit SP1 gets a PassMark rating that's 16.1% higher than Windows Vista 32-bit SP1.
Advantage Vista 64-bit.
Boot Up Times
For completeness I also measured the boot up time. I took this as the time from the boot loader to a usable desktop.
Average results were as follows:
- Vista 32-bit RTM Boot up time: 27 sec
- Vista 32-bit SP1 Boot up time: 31 sec
- Vista 64-bit RTM Boot up time: 44 sec
- Vista 64-bit SP1 Boot up time: 42 sec
Advantage Vista 32-bit.
The results from this set of benchmark runs have turned out to be quite clear. Let me summarize the results here:
- SP1 causes a drop in PassMark Performance ratings on both Vista 32-bit and Vista 64-bit.
- The drop in the PassMark Performance ratings is greater for 64-bit Vista than it is for 32-bit Vista.
- However, both RTM and SP1 versions of Windows Vista 64-bit show a much higher PassMark Performance rating Windows Vista 32-bit.
- Boot times for Vista 64-bit are longer than Vista 32-bit.
Later I hope to see which platform delivers the best frame rates in some of my favorite games.
<< Home >>