Today we are going to benchmark inexpensive home multimedia systems that are not designed for active gaming. What's a typical portrait of such a system? We'll try to recreate it from scratch.

What typical tasks does a home computer perform, if it's not used for gaming or runs them very seldom? It's usually web surfing, email, and editing documents. But these tasks don't need a high speed computer, any modern system can cope with them. Quite possibly watching movies (or even encoding/transcoding video). This tasks does not require a top computer, but the slowest processors won't cope with it either. Besides, you will need a capacious hard drive: a movie in high resolution may take up several gigabytes. It makes sense to add a DVD recorder to the system -- it will come in handy for a media library. Perhaps our hypothetic user will also want to process photos from time to time. Hence: CPU, hard drive, DVD recorder. By the way, what about memory? Considering how much it costs now and how much of it new operating systems from Microsoft need (Vista and future Windows 7), we'd say that even a home computer should have 4 GB. It's less than $50 after all.

As we proceeded from prices in this article, our method for selecting components was simple: at first we took a look at Intel's offers in this segment, and then at what AMD offered for similar prices. Why in this order? It's elementary: because the Intel platform has always been more expensive. Besides, we decided to diversify our options, so both platforms are represented by two testbeds: in case of Intel we 'played' with combinations of motherboard / chipset, and in case of AMD -- new Phenom X3 and good old Athlon X2. There exist much more interesting combinations in this price range, of course. But as any real customer, we were limited by availability of products in a given store at a given day. However, in our point of view all these restrictions only add feasibility to our article.

Testbeds

* Local prices as of 30.03.2009 converted to USD.

Our tests are based on x64 CPU Performance Testing Methodology. The key peculiarity of this method is that all data types are reduced to one -- a relative integer score (performance of a given processor relative to Intel Core 2 Quad Q6600, performance of which is considered 100 points). But this time we had to customize both testbeds and tests: none of the graphics solutions here support DirectX 10, so Call of Juarez that requires DirectX 10 was out of the question. Besides, our game tests are not intended for integrated graphics, so another game test (World in Conflict) was excluded because three testbeds out of four demonstrated mind-boggling performance -- 0 fps. Considering 2-3 fps in Crysis and S.T.A.L.K.E.R., the gaming part of our method must be adapted for the new tasks literally 'on the fly'.

You can read about the changes next to the corresponding diagrams. The main consequence of all these changes is that scores in this article do not reflect performance relative to some reference point anymore, they are just a geomean of all test results in a corresponding group of tests. Moreover,if the average score looked like 0.0025, we moved the decimal point in all results several digits to the right, to fit the results within 10..100 -- they look better this way. There is one thing for you to remember: Scores in these diagrams are just abstract scores. They will do to compare performance of tested computers between each other, but they are not good for anything more (e.g. to use them outside this article). It's a pity, but it cannot be helped, if a method of testing is overhauled on-the-fly. We hope to announce a new test procedure in the nearest future, which will have lots of other improvements.

Professional tests

3D modeling and rendering

Bad luck for the system with Intel Pentium DC E5300 + Intel G31: it failed our tests in 3ds max and Maya (except for the render speed test). We took a screenshot of the error message in the video driver in Maya benchmark. 3ds max popped up the same message. Note the color palette of the screenshot: it's not a mistake, our display switched from 1280x1024x32 into 640x480 with 16 colors.

This glitch does not occur at once: both tests (3ds max and Maya) run for 20-30 minutes before it happens, but this effect is reproducible in 100% of cases. We ran tests more than ten times, but they always failed to complete.

The layout of forces was actually to be expected: the new Pentium DC E5xxx processors perform a tad better than the old Core 2 Duo E4xxx, similar to the first Phenoms in speed -- so Pentium DC E5300 has good chances to outperform a mid-speed triple-core processor from AMD. And it certainly does.

CAD/CAM

OpenGL in the Intel G31 chipset is quite slow and crashes often (Maya). We cannot find any other explanation why it lags behind the single-channel NVIDIA GeForce 7100 chipset (you may remember that table values for Pro/ENGINEER and SolidWorks mean seconds spent to complete the task, so lower values are better). However, it's AMD 740G that had a real 'benefit night' in this group of tests. No, image quality is all right, there were no freezes or crashes. But it's so slow!.. In some cases the graphics core in AMD 740G is outperformed by NVIDIA GeForce 7100 by more than three times!

However, we didn't ponder long over this mystery -- it's good to have good memory. In fact, AMD inherited graphics from ATI, probably the same concerns the driver team. And we already wrote about 'phenomenal' performance of non-professional graphics cards from ATI in professional applications using OpenGL API. It's a pity the situation hasn't improved for three years -- our today's tests prove that the problem is most likely in software, not hardware.

Compiling

The first announcement: this is a new compile test. The source code is the same, just as the compiler, but the choice of options and some project improvements allow to use all processor cores. As a result, compile time is much shorter now, and this benchmark has become more dependent on a processor.

Surprisingly, it didn't help AMD Phenom at all -- this processor is outperformed by the dual-core Pentium DC as well as by the older dual-core processor from AMD -- Athlon X2. In other respects, this situation was to be expected, Intel G31 defeats GeForce 7100 -- the compile test has always been indifferent to large cache and fast memory, so GeForce 7100 with its single-channel memory controller couldn't compete with the Intel chipset.

Professional photo processing

There are no miracles in this test either, we all know that Adobe Photoshop has been favoring Intel since Pentium 4. Phenom X3 outperforms Athlon X2, because our Adobe Photoshop test can use all cores, and Phenom X3 has more of them.

Scientific applications

Mathematic packages suddenly turned out to be sensitive to memory speed (how else can we explain that G31 is so much faster than GeForce 7100?) And Athlon X2 6000 defeats Phenom X3 8450 not only in MATLAB (as we expected), but also in Maple and in one of Mathematica tests.

Web server

The web server test unexpectedly turns out less sensitive to the number of channels in a memory controller, even in its multi-threaded part (PHP Calculator). Other results are not surprising.

Total professional score

Intel Pentium DC E5300 + Intel G31 gets no professional score and no USD-per-point value because it failed to pass all tests. So it was not possible to calculate these parameters. However, the Intel platform in combination with NVIDIA GeForce 7100 still wins the professional run with an imposing advantage. It's all clear why: AMD platform shows terrible results in CAD/CAM tests because of low OpenGL performance of AMD 740G (we still insist that the problem is in the drivers, not in hardware), plus mediocre results in Adobe Photoshop (even the triple-core Phenom cannot compete with the dual-core Pentium!) But let's not forget that the professional group of tests in this article is not very important, as we test home systems.

Non-professional tests

Archiving

The archiving test is quite predictable -- it favors large cache, fast memory, and high frequencies. So the winners rank by these parameters.

Encoding

It's a natural situation: both systems with Pentium DC E5300 take the lead, Athlon X2 outperforms Phenom X3 owing to its clock rate.

Games

Here is another addition: we supplemented our game section with tests in low resolutions (800x600) and mid/low graphics settings. There are six games in this group of tests: Call of Duty 2, DOOM 3, Far Cry (the first part), Serious Sam 2, and the newest game -- S.T.A.L.K.E.R., but also in 800x600 with DX7 lighting. Why do we need these tests? The answer is to test performance of the integrated graphics solutions. If you take a look at results of the tested platforms in the usual game section of our test method, you will get it at once: they are not informative. What's the difference between 5 and 7 fps? It's too small -- you cannot play games in both cases! Besides, no one plays Crysis or CoD 4 with Intel G31 or AMD 740G -- they are not designed for it. However, why not test such platforms with games, which you can play? We decided to give it a try. It's up to you to say whether our decision is correct or not.

The unfortunate couple of Pentium DC E5300 + Intel G31 is unlucky again in game tests: it failed four tests from the old part of our test procedure and even one test from the new part, specifically crafted for systems with integrated graphics. The graphics core G31 puts up especially interesting performance in the old S.T.A.L.K.E.R. test and in new Serious Sam 2 test. Logs of test results show stunning data: 120 fps, 160 fps! A miracle? Alas, no: having run the tests once again, we saw that while incredible fps values were registered in logs, but the test showed an absolutely black screen instead of a dynamic 3D scene. The other tests had a different reaction. For example, that's what Call of Duty 4 demonstrates.

We do not preclude that having played with options, we could have made the games run with G31. However, we decided that the game was not worth the candle. When we selected test options for both game parts, we used logic and common sense in the first place. Logic and common sense seemed like a more imposing foundation for a test procedure than specifics of the Intel G31/G33 graphics core. Especially considering that neither AMD 740G nor NVIDIA GeForce 7100 had any problems with completing all graphics tests (you may remember that AMD 740G suffers from serious performance drops sometimes, but it can complete any test and show a correct screen).

Non-professional photo processing

Phenom has never been very good at photo processing in non-professional applications, so we were not surprised by results of the X3 8450. Athlon X2 6000 performs well here, considering the age of this architecture. That's another group of tests absolutely indifferent to the fact that the NVIDIA chipset has only one channel.

Total non-professional score

AMD expectedly shoots forward in the non-professional group of tests: unlike professional 3D applications, games run very well on AMD 740G. The combination of Pentium DC E5300 and Intel G31 again lacks the total score, because it failed several tests due to problems with the graphics system. However, results of the G31 in games are mostly far from impressive, even when it copes with the load. Thus, even though the combination of Pentium DC E5300 + GeForce 7100 is the champion in absolute performance here, it cannot be a champion in price/performance (it's the most expensive system of all we tested here). However, the most interesting fact lies ahead: it's not Phenom that wins in the AMD platform! The best solution in absolute performance and a price/performance ratio is actually Athlon X2 6000 + AMD 740G! We should do justice to Phenom, it's a fast processor for games. But in other respects (archiving, media encoding, photo processing), the overhauled Athlon X2 6000 is much faster, even though it has only two cores versus three.

Conclusions

The platform from Intel is an apparent winner: the difference between 1.28 and 1.15 USD per point is about 11%. On the other hand, we can remove results in 'heavy' professional applications and leave only the non-professional group of tests. In this case the AMD platform will be victorious (by less than 1%). So, it was very interesting to perform these tests, we got curious results. There were several surprises: before our tests we thought that the winner would be Intel Pentium DC E5300 + Intel G31, because it's the cheapest solution, and it's equipped with a dual-channel memory controller, unlike the single-channel NVIDIA GeForce 7100 chipset. We were even ready (if it's a winner) to criticize it for the lack of DVI support, which is a good feature for a home multimedia system. But it turns out that two channels prove their worth only in a limited number of applications, and Intel G31 has many problems with its integrated graphics system even without DVI -- frankly speaking, we cannot remember any other cases, when a platform simply failed so many tests. Competition between similarly-priced Phenom X3 and Athlon X2 processors in the class of inexpensive multimedia systems is no less captivating. But to tell the truth, we expected the outcome in this case.

What concerns recommendations, they are quite traditional: the more interesting our test results are, the more difficult to formulate them. Our favorites are obvious: Athlon X2 6000 + AMD 740G and Pentium DC E5300 + GeForce 7100 (we even risked an assumption that the other combinations -- Athlon X2 + AMD 740G and Pentium DC + GeForce 7100 -- could be no less interesting). There is no universal answer as to which combination to choose: it all depends on personal software preferences. That is, if you work much with photos, you will certainly appreciate the speed of Intel's platform. If you play lots of games -- you should pay your attention to AMD's platform (in this very case even Phenom X3 will be a good choice). All platforms have some drawbacks: inadequate OpenGL drivers in AMD, generic problems with graphics and no DVI in Intel (mauvais ton for a modern integrated chipset), single-channel memory controller in NVIDIA, which restrictions will become more pronounced with a powerful processor. But it would have been naive to expect a Low-End chipset to have no drawbacks at all -- it's the wrong price range.

P.S. In the process of running tests and writing this article we found an interesting newer AMD 780V-based motherboard in the same price range. We were tempted to add it to the article, of course, but then decided against it: what if another motherboard gets cheaper after additional tests -- for example, models with Intel G41 or GeForce 9300? One could rewrite this article forever. This situation reminded us once again that price comparisons have several drawbacks that cannot be avoided.