iXBT Labs - Computer Hardware in Detail






AMD Athlon II X4 620 Processor

<< Previous page

     Next page >>


The benchmarking procedure (the list of software and test conditions) is described in this article. To make the diagrams easier to read, results are represented in percents (100% stands for the result of Intel Core 2 Quad Q9300 in each test). The detailed results in absolute values are published in this Microsoft Excel spreadsheet. Test results were obtained with DDR2 memory, unless stated otherwise.

3D visualization

Our constant readers may already know that this group of tests including interactive operations with 3D models in corresponding applications practically does not use four cores. As a result, the best choice here is the triple-core processor, as its large cache allows to outperform its equally-clocked colleagues in the series.

3D rendering

Each core is accounted for in rendering in the same applications. But cache size is not so important, because data have to be taken from memory. As a result, the new product looks very good. Besides, we have an impression (not only in this test) that the memory controller in Athlon II has also been tuned for DDR3 mode. It may affect test results in the nominal mode only in rare cases. But we notice its effect in such nuances as operating stability with harder timings or capacity to withstand higher memory frequencies. On the other hand, if we take a look at test results of the prev-gen Phenom, the progress does not look very big (considering the 100-MHz difference), if we don't take into account the difference in manufacturing costs and the fact that the new quad-core processors are actually represented by the cheapest model.

Science & engineering computation

Scientific applications value cache even more than the first group of programs, and multiple cores are not always effective again. So the triple-core processor takes up the lead here. This very processor provides maximum performance for its price in Maple, MATLAB, and Mathematica.

So what can we advise to people who use 3D Modeling packages (we've divided their performance aspects into three groups)? The practical conclusion is banal: you'd better get an expensive quad-core processor (Phenom II X4 810 or even a medium model from series 900), if you use your computer for modeling and for final rendering. Such processors will demonstrate high results in rendering. And what concerns interactive operations, responsiveness of a system starts to depend on a graphics card from a certain level of CPU speed. So a powerful quad-core processor won't be a bottleneck, because its cores are fast enough to execute badly-parallelized fragments of code in these applications. But the contrary is true as well -- if you have a weaker graphics card than we use in our testbed (it often happens with budget PCs), the first diagram will be even flatter. Situation with rendering won't change, so the gap between Model 620 and the leader will become smaller.


Memory exchange efficiency takes the first place among parameters that affect test results here, and only the Q8200 has nothing to boast here. As cache plays an important role here as well, the budget product from AMD manages to break away from its predecessor only with DDR3 memory. But in this case it even outperforms the modern triple-core processor with its large cache. That is it's a situation, when an additional core makes up for the shortage of 6MB cache (all other things being equal). And the 810 illustrates a banal fact that it's better be both wealthy and healthy.

Image editing

These are boring results, because they are even: only Phenom X4 9850 lags behind the others, but you will hardly notice this slower response in real life. In order to detect differences in our tests, we use very large data volumes to be processed by a script in a graphics editor in batch mode. But it's an unexpected result from the reviewer's point of view. We actually see that the lack or presence of L3 cache as well as similar manipulations with the fourth core have no noticeable effect. How can it be? That's the average situation in modern applications working with bitmap graphics. So if you are interested in details, pay attention to detailed results. They show that ACDSee votes for the triple-core processor, Paint.NET and Photoshop prefer quad-core processors, demonstrating surprising indifference to cache size. The Q8200 has the highest total score owing to Paint Shop Pro and Photo Impact.

Write a comment below. No registration needed!

<< Previous page

Next page >>

blog comments powered by Disqus

  Most Popular Reviews More    RSS  

AMD Phenom II X4 955, Phenom II X4 960T, Phenom II X6 1075T, and Intel Pentium G2120, Core i3-3220, Core i5-3330 Processors

Comparing old, cheap solutions from AMD with new, budget offerings from Intel.
February 1, 2013 · Processor Roundups

Inno3D GeForce GTX 670 iChill, Inno3D GeForce GTX 660 Ti Graphics Cards

A couple of mid-range adapters with original cooling systems.
January 30, 2013 · Video cards: NVIDIA GPUs

Creative Sound Blaster X-Fi Surround 5.1

An external X-Fi solution in tests.
September 9, 2008 · Sound Cards

AMD FX-8350 Processor

The first worthwhile Piledriver CPU.
September 11, 2012 · Processors: AMD

Consumed Power, Energy Consumption: Ivy Bridge vs. Sandy Bridge

Trying out the new method.
September 18, 2012 · Processors: Intel
  Latest Reviews More    RSS  

i3DSpeed, September 2013

Retested all graphics cards with the new drivers.
Oct 18, 2013 · 3Digests

i3DSpeed, August 2013

Added new benchmarks: BioShock Infinite and Metro: Last Light.
Sep 06, 2013 · 3Digests

i3DSpeed, July 2013

Added the test results of NVIDIA GeForce GTX 760 and AMD Radeon HD 7730.
Aug 05, 2013 · 3Digests

Gainward GeForce GTX 650 Ti BOOST 2GB Golden Sample Graphics Card

An excellent hybrid of GeForce GTX 650 Ti and GeForce GTX 660.
Jun 24, 2013 · Video cards: NVIDIA GPUs

i3DSpeed, May 2013

Added the test results of NVIDIA GeForce GTX 770/780.
Jun 03, 2013 · 3Digests
  Latest News More    RSS  

Platform  ·  Video  ·  Multimedia  ·  Mobile  ·  Other  ||  About us & Privacy policy  ·  Twitter  ·  Facebook

Copyright © Byrds Research & Publishing, Ltd., 1997–2011. All rights reserved.