[nextpage title=”Introduction”]
Dual-core technology is finally a reality and the tendency is that all mainstream CPUs to become dual-core in a near future. But will average users really benefit from it? In this review we’ve got two CPUs running at the same clock rate, Athlon 64 3800+ and Athlon 64 X2 4600+ (both running at 2.4 GHz), and could see if there is a real performance gain for regular users. We also checked Athlon 64 FX-60 performance, which is a dual-core Athlon 64 FX running at 2.6 GHz.
One of the greatest advantages of dual-core CPUs is that they don’t need a new motherboard. Both Athlon 64 X2 and dual-core Athlon 64 FX use the socket 939 standard, so you can replace your current socket 939 CPU directly into a dual-core AMD CPU.
Figure 1: Athlon 64 X2 4600+ and Athlon 64 3800+
Both Athlon 64 X2 4600+ and Athlon 64 FX-60 are recognized as two CPUs by Windows, as you can see on Figures 3 and 4.
Figure 3: How Athlon 64 X2 4600+ is recognized on Windows.
Figure 4: How Athlon 64 FX-60 is recognized on Windows.
With a dual-core CPU you will have, in fact, two CPUs inside your PC. That’s why we are running this test: to check how much is the performance gain for a regular user. For more in-depth information about AMD dual-core technology, read our article Dual Core AMD Processors.
[nextpage title=”Introduction (Cont’d)”]
There are two main differences between Athlon 64 X2 and dual-core versions of Athlon 64 FX. First, they have different L2 cache sizes. While each Athlon 64 X2 core has a 512 KB L2 memory cache, each core of dual-core Athlon 64 FX has a 1 MB L2 memory cache. Another difference between them is the fact that Athlon 64 FX has its clock multiplier unlocked, i.e., you can increase its clock multiplier in order to achieve a higher clock rate.
Athlon 64 X2 4600+ runs at 2.4 GHz, the same clock rate as Athlon 64 3800+, multiplying its base clock of 200 MHz by 12. Athlon 64 FX-60 runs at 2.6 GHz, multiplying its base clock of 200 MHz by 13.
Figure 5: Athlon 64 X2 4600+ specs.
Figure 6: Athlon 64 FX-60 specs.
We didn’t compare these CPUs with Intel counterparts (namely Pentium D and Pentium Extreme Edition) because unfortunately Intel didn’t provide us samples for reviewing.
[nextpage title=”How We Tested”]
During our benchmarking sessions, we used the configuration listed below. Between our benchmarking sessions the only variable was the processor being tested.
Hardware Configuration
- Motherboard: MSI K8N Diamond Plus (BIOS 1.12, December 22nd, 2005).
- Memory: Two Corsair CMX1024-3500LLPRO modules with 1 GB each, installed on DDR Dual Channel configuration (2-3-2-6 timings).
- Hard Drive: Samsung SpinPoint SP0411N (7,200 rpm, 40 GB, ATA-133).
- Video Card: XFX GeForce 7800 GTX.
- Video resolution: 1024x768x32@85Hz.
- Power Supply: OCZ ModStream 520 W.
Software Configuration
- Windows XP Professional installed using NTFS
- Service Pack 2
- DirectX 9.0c
Driver Versions
- NVIDIA video driver version: 84.21
- NVIDIA nForce 4 SLI X16 driver version: 7.15
- All motherboard drivers were installed (SiliconImage SiI3132, Marvell Yukon, Sound Blaster Audigy, etc)
Used Software
- SYSmark2004 – Patch 2
- PCMark05 Professional 1.1.0
- Cinebench 9.5
- 3DMark06 Professional 1.0.2
- Quake 4 – Patch 1.2
We adopted a 3% error margin; thus, differences below 3% cannot be considered relevant. In other words, products with a performance difference below 3% should be considered as having similar performance.
[nextpage title=”Overall Performance: SYSmark2004″]
We measured the overall performance of the CPUs included in this review using SYSmark2004, which is a program that simulates the use of real-world applications. Thus, we consider this the best software to measure, in practical terms, the system performance.
The benchmarks are divided into two groups:
- Internet Content Creation: Simulates the authoring of a website containing text, images, videos and animations. The following programs are used: Adobe After Effects 5.5, Adobe Photoshop 7.01, Adobe Premiere 6.5, Discreet 3ds Max 5.1, Macromedia Dreamweaver MX, Macromedia Flash MX, Microsoft Windows Media Encoder 9, McAfee VirusScan 7.0 and Winzip 8.1.
- Office Productivity: Simulates the use of an office suite, i.e., simulates sending e-mails, word processing, spreadsheets, presentations, etc. The following programs are used: Adobe Acrobat 5.05, Microsoft Office XP SP2, Internet Explorer 6.0 SP1, NaturallySpeaking 6, McAfee VirusScan 7.0 and Winzip 8.1.
This software delivers several results, all of them using a specific SYSmark2004 unit. First we have a SYSmark2004 overall score. Then we have a group result for each batch listed above. And for each batch, we have specific results: 3D Creation, 2D Creation and Web Publication for Internet Content Creation and Communication, Document Creation and Data Analysis for Office Productivity.
We were eager to know what performance gain an average user would have by using a dual-core Athlon 64 instead of a single-core one. The results you can see on the chart below.
The performance gain has surprised us. We thought that dual-core technology would improve only very specific applications like 3D rendering, but Athlon 64 X2 4600+ achieved an overall result 19.49% higher than Athlon 64 3800+ (both runs at 2.4 GHz), running regular programs. It is very interesting to note that this improvement was basically on the Internet Content Creation batch, where Athlon 64 X2 4600+ was 40.99% faster than Athlon 64 3800+. On Office Productivity both CPUs achieved the same performance.
The most benefited application segments were Web Publication (50.00%), 3D Creation (38.46%), 2D Creation (36.30%) and Document Creation (11.22%).
With Athlon 64 FX-60 we could see the benefits of a bigger L2 memory cache (1 MB per core, against 512 KB per core on Athlon 64 X2) and a clock 200 MHz higher (2.6 GHz). It achieved an overall performance 13.30% higher than Athlon 64 X2 4600+ and 35.38% higher than Athlon 64 3800+. For Internet Content Creation it was 11.18% faster than Athlon 64 X2 4600+ and 56.76% faster than Athlon 64 3800+, while for Office Productivity it was 15.61% faster than these two CPUs.
Compared to Athlon 64 X2 4600+, Athlon 64 FX-60 most benefited application segments were Document Creation (17.11%), Web Publication (14.34%) and 3D Creation (10.76%). And compared to Athlon 64 3800+, the most benefited application segments were Web Publication (71.51%), 3D Creation (53.37%), 2D Creation (46.98%) and Document Creation (30.24%).
[nextpage title=”Processing Performance: PCMark05 Professional”]
PCMark05 Professional measures the system performance by running several tests. We selected two batches for our comparisons, System and CPU.
The System batch performs the following tests: HDD XP Startup, Physics and 3D, 2D Transparent Window, 3D Pixel Shader, Web Page Rendering, File Decryption, 2D Graphics Memory – 64 lines, HDD General Usage and three multithreading tests.
The CPU batch performs the following tests: File Compression, File Decompression, File Encryption, File Decryption, Image Decompression, Audio Compression and two multithreading tests.
The results are given in a PCMark05 specific unit.
On System batch Athlon 64 X2 4600+ was 31.77% faster than Athlon 64 3800+, while Athlon 64 FX-60 was only 4.97% faster than Athlon 64 X2 4600+ but 38.31% faster than Athlon 64 3800+.
On CPU batch Athlon 64 X2 4600+ was 40.60% faster than Athlon 64 3800+, while Athlon 64 FX-60 was 8.43% faster than Athlon 64 X2 4600+ and 52.45% faster than Athlon 64 3800+.
[nextpage title=”Rendering Performance: Cinebench 9.5″]
Cinebench 9.5 is based on the 3D software, Cinema 4d. It is very useful to measure the performance gain given by having more than one CPU installed on the system when rendering heavy 3D images.
This software provides five results, Rendering 1 CPU, which measures the rendering performance using just one CPU, Rendering x CPUs, which measures the rendering performance using all CPUs available on the system, Cinema 4D shading, OpenGL Software Lighting and OpenGL Hardware Lighting. Since we were interested in measuring the rendering performance, we are going to compare the “Rendering x CPUs” results from all CPUs (“Rendering 1 CPU” in the case of Athlon 64 3800+).
In this test Athlon 64 X2 4600+ was 84.81% faster than Athlon 64 3800+, while Athlon 64 FX-60 was 8.22% faster than Athlon 64 X2 4600+ and 100.00% faster than Athlon 64 3800+.
[nextpage title=”3D Performance: 3DMark06 Professional”]
3DMark06 is the latest version of 3DMark franchise, measuring Shader 3.0 (i.e., DirectX 9.0c) performance. We run this software on its default configuration (1280×1024 resolution with no image quality settings enabled), checking the CPU batch results for comparison.
To be honest, 3D performance nowadays depends much more on the video card used than on the system CPU. Even then the 3D overall performance of Athlon 64 X2 4600+ was 14.53% higher than the one achieved by Athlon 64 3800+. Athlon 64 FX-60 achieved a result similar to Athlon 64 X2 4600+.
When comparing the results for the CPU tests alone, the big surprise: Athlon 64 X2 4600+ was 92.41% faster than Athlon 64 3800+ and Athlon 64 FX-60 was 7.72% faster than Athlon 64 X2 4600+ and 107.27% faster than Athlon 64 3800+. Once again, this shows how the improvement on CPU performance won’t probably reflect on a higher 3D performance.
[nextpage title=”3D Performance: Quake 4″]
We ran Quake 4 multiplayer demo id_demo001 on 1024x768x32 with no image quality settings enabled. We run it four times and the results shown on the chart is an arithmetic average of the collected data. The results are in frames per second. For more information on how to use Quake 4 to benchmark a PC, read our tutorial on this subject.
On Quake 4 Athlon 64 X2 4600+ was 7.49% faster than Athlon 64 3800+ and Athlon 64 FX-60 was 8.16% faster than Athlon 64 X2 4600+ and 16.26% faster than Athlon 64 3800+.
[nextpage title=”Overclocking”]
Since Athlon 64 FX CPUs don’t have a clock multiplier lock, we were very curious in see the overclocking capacity of Athlon 64 FX-60. First we raised its clock multiplier from 13 to 14 and the CPU ran at 2.8 GHz just fine. That’s great news. We tried to increase its base clock (HTT clock) when it was set at 14x but it was almost impossible. The system hanged even with base clock rates as low as 209 MHz. We went back to 13x and increased the CPU base clock and we could go stable up to 218 MHz (2,834 MHz internally – a 9% increase over the standard clock rate). We didn’t play with voltage settings or any other fancy settings provided by the motherboard, so you may be able to achieve better results than we did.
Under these two overclocking situations we ran PCMark05 Professional to see which configuration would give us more performance improvement, see our chart below.
Putting our Athlon 64 FX-60 running at 2.8 GHz by increasing its clock multiplier from 13x to 14x improved its PCMark05 overall score by 4.92% and its PCMark05 CPU score by 7.27%. By keeping the CPU at 13x multiplier and increasing its base clock to 218 MHz, which made it run at 2.83 GHz internally, its PCMark05 overall score was increased by 6.47% and its PCMark05 CPU score was increased by 8.96%.
[nextpage title=”Conclusions”]
We were really impressed by Athlon 64 X2 performance, since we thought that only 3D rendering and other very CPU-intensive tasks would benefit from dual-core technology. However, this isn’t true. We could see an impressive performance gain by running daily applications.
It is true, however, that 3D rendering and video-related tasks will be the kind of application that will benefit more from dual-core technology, as our benchmarks has shown us.
The only problem we see for Athlon 64 X2 is its price. While Athlon 64 3800+ can be found listed between USD 284 and USD 385 on Shopping.com, Athlon 64 X2 4600+, which runs at the same clock rate, can be found between USD 547 and USD 665, the double. And you won’t get double the performance…
Athlon 64 FX-60 is a great product for the high-end enthusiast or gamer, however its price is really a pain: between USD 960 and USD 1,223. OUCH!
Unless you are a performance freak and have unlimited resources available, we would suggest you to hold on until the prices drop. While in our opinion dual-core technology will bring a true performance gain for the average user, its price is still too high for such performance increase. Since the tendency is that all mainstream CPUs will be dual-core in the near future, we suggest you to hold on until then.
Leave a Reply