Tom's Hardware Wants You: CPU Tests For 2011

[robnic]

I think it would be a good idea to consider hyper-threading on and off separately, where appropriate.

It would be useful to know how much better (or worse!) a processor with (e.g.) 4 physical cores performs with 8 logical cores, as opposed to 4 logical cores.

This would be of particular interest to overclockers, as the cpu overclock limit is reduced when HT is on (obviously).

I suspect that applications that are not heavily multi-threaded will respond negatively to hyper-threading, so it would be useful for users to be able to weigh up the different options (i.e. HT on or off) when looking at your benchmarks.

 

[robnic]

There's something that I've been wanting to see in the mass-benchmark comparisons for a long time:

There are so many processors included in the comparison that the charts can be a bit overwheming. I think that there should be an alternative way to view this information that is more meaningful. Here is my suggestion:

Exploit the fact that there are many processors that are effectively the same thing (e.g. i7-920 and i7-940), i.e. the same architecture, clocked at different frequencies. So, why not display a graph with cpu frequency on the x-axis, score on the y-axis, and have one line/curve for each architecture, instead of for each cpu. Imagine it - this would reduce the number of lines to a minimum, and would make it obvious to the user which architectures are better for each test. Furthermore, it would make it more obvious whether or not cpu frequency has a significant effect on that particular benchmark.

This could be expanded by overclocking (or underclocking) the processors within some reasonable range (e.g. 2Ghz-4Ghz, or whatever the max of that particular architecture is) in order to extrapolate the results, in an overclocker-friendly fashion, so that people will be informed of the expected benefits (if any) of running their cpu at a particular frequency. This would result in each of the stock cpus being a point on a continuous line on the graph.

In the past, when researching which cpu to get, I have personally implemented this at home in a spreadsheet (using your charts as reference), and the results are fantastic, and very informative. Please consider implementing this as a additional feature, as I think people would find it very useful. To my knowledge, no-one else on the web does this at current.

 

[Guest]

I would like to see X-Plane by Laminar Research show up as a benchmark. The "fall" of MS Flight Simulator department, and the specific demands of X-Plane make it a choice that will probably prove a computer's worth in bridging gaming and productivity. X-Plane taxes every bottleneck, and if I am not mistaken, the graphics are OpenGL, which would prove hardware flexibility. Since X-Plane runs on 3 platforms (Mac, PC, and Linux) it could be the measure of hardware that can help make cross-platform comparisons really "apples-to-apples."

 

[youssef 2010]

ditch AVG and use bitdefender.Also, Use GTA IV

 

[Cryio]

Metro 2033, using an ATI GPU with the Advanced Physx On. Select a scene with heavy particle effects, smoke, and environmental destruction.

 

[Samy0806]

I would like to see Arcania: Gothic 4 used as a benchmark.It was just released in Europe(12 Oct) and will be released soon in USA(19 Oct).You should give it a try.

 

[ingalonzo]

I'd like to see Crysis and Far Cry 2 on benchmarks. Also Crysis 2 when it comes out.

 

[Guest]

I'd like to see the inclusion of the Atom chips, in particular the dual-core Atom's. They are pretty good for HTPC's, and entry level home PC's. It will be useful when trying to justify, or make an informed decision.

 

[Guest]

How about the standard wow=addict setup.

Wow running at ultra settings on main screen
vent/ or other crappy vox running
media monkey or itunes or other media playing so you don't have to listen on nerd rage on said crappy software

 

[earthwormsvx]

How about some of the number crunchers like Folding@Home or distributed.net? The latter can also be used to benchmark video cards using Cuda or Stream.

 

[quiq]

win/linux boot time
artlantis render (please!)

multitasking benchmarks !

everest/aida64 benchs
blender

 

[Guest]

EVE-Online on Multiple clients.

I know the marked for this is small but as there are no one that tests hardware for people that play multi client games like EVE-Online.

Most of the people there run multiple clients and it wood be good to see how a cpu spreads different clients on the cores.
How the frame rates affect running 2-6 clients, showing multiple windows spread over 2 screens or how long time it uses to alt tab between them.

 

[Guest]

I'd like to see some results from all Javascript Benchmarks found on http://dromaeo.com/

 

[09mlb86]

Crysis, World in Conflict (my i7/5870 lag on this game @ 1920 x 1200), Far Cry 2

Dirt 2 is a very good choice, that is another game i have to turn down my settings a bit...

Thanks for reading!

 

[someoneelse]

Multitasking benchmark that really tests

-something brutal that really weeds out low cache poor multithreaded chips like 4 differnt encodes (or 4 the same on 4 virtual machines)

virtual machine benchmark ( virtualbox )

Oh and has anyone mentioned Crysis yet?

 

[danny69t]

Nero Burning ROM 6 )

 

[oneblackened]

Some kind of Audio production benchmark - loading a lot of VST plugins (namely amp simulators, drum trigger sets like superiordrummer, etc)

 

[Guest]

I'd like to an audio program tested. I'm a music producer/audio engineer and use cubase 5. it can tax the hell out of a cpu once you start using plug ins. there are a TON of free plugs out there as well. I'd love to see how different cpu's stack up when using multiple cores running cubase. Other digital audio workstations pro-tools, logic, etc.. i recommend cubase because i haveve used them all and prefer that. Also because it is probably the most cpu intensive of all the DAW programs. I see some great ideas here n this is my 2 cents.

 

[sebastien]

Hello,

Ok we see that benchmarks should be game based. It is always a great welcome to see how a targeted CPU and/or GPU perform in that sector.

Although I am growing a bit wary. To me it sounds like CPU lines start to differ exponentially in architecture base generations after generations of CPUs whether Intel or AMD. This means that to keep everything compatible then hardware components play and may play a bigger role in coming generations; therefore, Intel and/or AMD may grow differently CPU architecture-wise and how they perform depending on the actual action (single threaded, multi threaded, games, video editing, VCC 3D and 2D).
I am actually on the market to build a new rig. I am a 3D modeler and animator for game segment. I primarily work with Autodesk products and adobe products.
I have no clue where the performance and reliability line is between actual CPU/GPU (mass market CPU versus (intel Xeon or AMD opteron) and (mass market GPU versus (Nvidia quadro or ATI V series).
For a more concrete example. I run on a core 2 duo 2.4 with 6 gigs and a GTX 8800 (Yes it is old, I know and will replace it before the end of this year " if my wallet says yes"). This rig is decent but not for mudbox nore going higher than 2 millions polygons in max.
Having a benchmark CPU and GPU and CPU/GPU for professional software would be simply a great RELIEF!!!
At this point I have no clue to whether stick with mass market CPU or go into server CPU and if then Xeon or Opteron????

All I want is to work smoothly and never encounter a BSOD or sudden software crash. I am very attracted by ECC tehnology and the ability to throw 16 gigs of memory along with a quadro 4000 or V8750.
While game benchmark would be great to see and follow, it says and serves too little for my needs.