Print
Unless you're doing a lot of comparative tests of hard drives or SSDs, you probably won't be running drive benchmarks often. They're not that useful as diagnostic tools, either. Drive failures are sudden enough that running a benchmark might just push it over the edge if it's ready to fail.
Benchmarks can be useful in helping you decide when it's time to de-clutter your SSD. As SSDs get close to being full, performance may radically fall off. If the result of a storage benchmark is much slower than your baseline test—20% slower or more—it's time to clean the crud off your drive.
Given that you're not going to run disk benchmarks frequently, a free benchmark sounds like a good idea. The problem: most free storage benchmarks aren't all that robust. One popular test, CrystalDiskMark, is a synthetic test, but has been updated to work more effectively with SSDs and will even run on the Windows 8 developer preview.
This test is often run at trade shows by hard drive and SSD manufacturers.
There are more graphics benchmarks than you can shake a stick at, and many of them are free. Most of these have only marginal utility, because they don't always tell you how well your system might behave in an actual game. What is cool is that a benchmark, like the various versions of 3DMark, make it easy for you to compare your system with thousands of other systems, since they give you the option of collecting data online.
Benchmarks like 3DMark and Unigine Heaven are designed to completely thrash your graphics card. It's like the difference between putting your car on a dynamometer to get a theoretical idea of how well your car can perform and actually running it on a road course.
The free, basic version of 3DMark only gives you a score.
Heaven is similar in some ways to 3DMark, but based on an actual game engine.
On the other hand, no one game benchmark is perfect. They can only give you a rough idea of how well your system might do in a particular game or genre. So you really need to run game tests that reflect your tastes in gaming. Running first person shooter benchmarks won't help you determine how your system might run a real time strategy game, for example.
The other problem with game benchmarks is more subtle. Running one or two tests and looking at average frame rates doesn't always give you a good feel for how a game might play, as The Tech Report discovered. Game benchmarks that generate average frame rate results are useful for comparing different cards, but if you want to really dive in and see how a game runs, you may need to actually run that particular game.
The other problem is that most games don't have in-game benchmarks. Those that do are often simplistic, running a pre-collected bunch of frames and giving you an average frame rate. One step up is when the game test shows you minimum, maximum, and average frame rates. The best game benchmarks give you both a front end to launch the benchmark and graphical results. One example is the benchmark applet that ships with Metro 2033.
I wish every game shipped with a benchmark launcher like this.
The results screen for Metro 2033 gives you lots of information on the run.
The real issue, though, for the casual benchmarker, is that you often have to own the game to run the benchmark. If all you want to do is run a few tests to get a rough idea of how your system might perform, dropping $50 on a game just to run performance tests seems a little extreme—especially when you consider the technology in games varies considerably from one title to the next.
There are free, standalone game benchmarks available, however. Here are several good ones.
The Call of Pripyat test ships with a nice launcher and lets you easily tweak settings before you run it.
We can't finish our discussion on game benchmarking without talking about Fraps. Fraps is a tool that lets you benchmark any game. You run Fraps, set up recording parameters, then play the game. The problem with Fraps is that you often need to run through the game a number of times to get a repeatable result. But it's a useful tool if you've got the patience.
If you want to see how your system runs a particular application, you'll need to run that application. Many are available as demos, so you can often download them and see how well they run. The downside is that quite a few lack built-in benchmarks.
User communities are often helpful. If you're running a professional graphics application or high end image editing tool, user communities often have links to application tests you can run. Bear in mind that many of these take some work to run.
You can find a few benchmarks specifically designed for certain professional applications. SPEC, the Standard Performance Evaluation Corporation, offers a number of benchmarks for high end applications like 3DSMax, Solidworks, and Lightwave, but they all assume you actually have the application, and just supply scripts and data files. SPEC ViewPerf is an exception, and can demonstrate how your GPU and system might run a set of these pro apps, but the scenarios are a little artificial.
Also, Cinebench can test how your CPU and GPU work with Maxon's Cinema4D, but will also give you a clue as to how your system might perform with software 3D rendering in general.
The bottom line is that application benchmarks are complex and difficult, but the only way to test how your system might run an application critical to your work.
If you're not constantly comparing hardware, then benchmarks aren't something you'll run often. But there's a wealth of tools available to test the performance of your system. They're useful diagnostic tools, can help you hit a stable overclock and tell you when your system performance has deteriorated beyond acceptable parameters. Best of all, many of them are free as well as useful.
Comments are closed on this article
mattman059
October 16, 2011 at 8:59pm
" Perhaps you just got a new graphics card, or doubled your installed DRAM"
HOW DID YOU KNOW!!!!!
loyd
October 14, 2011 at 10:25am
I'm actually not familiar with Kombuster. But Furmark can actually push a graphics card beyond its rated parameters. So that test should be used with care.
akrazyassho
October 13, 2011 at 8:32pm
Question about the Heaven benchmark and tessellation in general. In the benchmark you can turn on and off tessellation, but there is a huge difference. Ex: the stones on the walls all come out to a certain height/ have a unque depth, but when you turn off tes. they are all flat walls/surfaces. My question is, that depth that the stones/rocks have, is that built into the benchmark or is that really the card deciding and rendering at its own free will due to tessellation??
loyd
October 14, 2011 at 10:23am
The answer is both. The programmer gives some hints as to how much tessellation should be generated. In the case of Heaven, the designers have given the user some control over this through tessellation levels. If you get past the performance test stuff, you'll see that "extreme" tessellation actually looks pretty bad, while moderate degrees of tessellation adds pleasing levels of geometric detail.
maleficarus™
October 13, 2011 at 3:28pm
Stress-testing is stupid! Why "bake" your CPU like that when it will never represent anything you will ever do in real world situations. Why not just toss your CPU in the oven for 30 mins at 350 degrees? Same silly logic...
steven4570
October 13, 2011 at 4:29pm
stress testing is more designed for testing an overclocks stability not really benchmarking, in that reguard it is very useful
xXSINS OF WARXx
October 13, 2011 at 4:26pm
Idk, why did Einstein come up with the mathematical equation of e=mc^2? Why did NASA decide to send a rocket to the moon? Or why do numerous people around the globe try to break countless Guinness world records? The answer is simple; because we can. If we as a nation were to simply stop pushing the boundaries that life sets before us then the conveniences we so ignorantly take for granted would cease to exist and human nature will never continue to evolve; those types of infectious negative ideas will only plague our children…
maleficarus™
October 13, 2011 at 4:56pm
What kind of nonesense is this? Baking your CPU with prime95 or IBT is not only stupid, but useless as well. It does not in anyway shape or form represent anything we do on our PC's. Common sense logic dictates that if this isn't a real world representation, then it is not logical to do! Common sense people!!
We can all jump off a bridge. Does that mean we should because we can?
steven4570
October 16, 2011 at 6:06pm
i hate people who use the term"common sense logic" because in most cases they have no fucking clue what theyre talking about. Some systems if we change anytthing for what every reason, need to be tested for stability. one time i had stabiity issues with everything at stock speed on this one pc i built, turns out the default voltages in the outdated bios were wrong. it has its place, its not going to fry or die because of it, cpus like that will be working far longer than youll be using them ill guarantee.
pcfxer
October 13, 2011 at 5:38pm
You stress test for stability to simulate the life/usage of the CPU within a much shorter time span. For example; you want to know that your overclock will last for five years at five hours per day so you run a stress test for say one week at tewnty four hours per day. The goal is to design a test that will allow you to certify that your overclock is stable for normal usage.
AMD and Intel both do this on their CPUs. Automotive manufacturers do this as well; most iconicly Porsche did this with the Beetle. This is common practice in engineering.
maleficarus™
October 13, 2011 at 7:31pm
Yes at stock speeds. Not OC speeds that everyone uses for stress-testing. Not a single person uses prime95 stock do they? So your point is not valid at all...
JCGPZ9
October 13, 2011 at 10:10pm
Actually I do when trying out a new thermal paste or heatsink. It's a great way to put sress on the CPU while still monitoring it.
Coldrage
October 14, 2011 at 11:56am
maleficarus™ way to make yourself look like a total tool.
I'm using a Q6600 @ 4.0 GHz since august 2007 and fold every day with it, stressed tested it countless times and it is still going strong.
CPU's these days are well designed to deal with heat.
Putting a CPU in an oven is just a terrible analogy.Folding as I speak with all 4 cores at 60c
As previously said, benchmarking is an excellent way to measure the performance of a piece of hardware, it sets the bar for what you can expect in real world applications and how it will perform.
Not sure if troll or just stupid.
onisuriyuuu
October 25, 2011 at 9:39pm
He kinda is a little of both. Obviously I am forced to run at stock froob.
My I-5 -2500k Is on a P8H67? forgot the model. And limited to a multiplier of 33 not 55 -> ie: 4-5GHZ. versus my 3.4GHZ.
I Dare you to find a way to increase the clock even higher (without turbo) to a multiplier of ... 40's with this board, i will pay you a brand new i7-2300k.
Note: My clock is even bellow stock clock..... The stock is 34 multiplier, my clock is 33 just a bit under the clock by about .... 50 mhz
Its impossible. So its best to know my heat limits when I try to use the most of what my clock has to offer me. And guess what.
My Temp is 55C at all 4 cores at 100 percent usage. ALSO Many times the insane multitasking that I do my CPU usage often does go upbound to 100 percent usage DAILY for hours on end. Why? Tell that to my 80 open tabs, my Photoshop, MMORPG's, ESET Nod 32 Scans, Maleware Byte Scans, Skype (amazingly takes 25% CPU for the insane convo's i get)
ON THE OTHER HAND. My GPU which I had to watch intently Heated up to around 60's Celcius which is highly... dangerous on my part, Because the closer it gets to 80 C the slower it gets, and also the more wear and also 80c is the failure point anyways. SO Benchmarking allowed me to see my Maximum sustained tempature and estimated fluxuations within the tempeture based on ambient tempatrue, it allows me to clock my GPU to get the most out of it without totally blowing it to pieces for running it for longer periods.... Obviously Things don't cool down at 100% it gets hotter and hotter and hotter as the ambient tempature increases from your mini heater of a computer, untill the room gets to a point the computer can hit 80c ..... But that will never happen because I have central Air and my room is well circulated. However If i was in someplace like pueto rico..... my computer is going to be HOT HOT HOT. litterally, and maybe melt a little.
i5-2500k, Frio Cooler ( Cold like a fridge :O )
Radeon 5570 (win exp: 6.7 on 7.9 ) Going to upgrade this soon My CPU is cooler than it....
Corsair 800w
8GB Vengance D3 Ram running dual ch 1333mhz (board limited would have been 1600mz)
Segate 1TB 5900rpm Storage Drive.
Samsung Display? 1600x 1200 its... so... clear, and so big. Guessing around just under 30 in
And other Misc Accessories Like my Mamba Mouse, and smaller hard drives not note worthy ex 250GB
Other than any typo's i might have put or nonsense sentence at 1:00 AM in the morning, please tell me or ask any other questions, and I will be gladly to clarify anything.
triclops41
October 13, 2011 at 1:06pm
Lloyd, can you comment on why you don't linke Kombuster or Furmark for benchmarking?
onisuriyuuu
October 25, 2011 at 9:42pm
Quite honestly His theory is that You can push your GPU too far (obviously the benchmark is made to push your hardware not find a place that feels comfortable) and do some severe permanent damage and possibly void your waranty if pushed out of manufacture regulated Over clocks. ( My Radeon has a factory overclock, however if i go beyond this I can void the waranty )
