 |
 |
 |
||
|
|
||||
 |
|
|
| Introduction and Specifications | |||||||
AMD has been fairly quiet as of late. A few months ago, we took a look at their initial Quad-FX platform and FX-70 series offerings. However, on the mainstream socket AM2 front, AMD hasn't made any real noise since the release of the Athlon 64 FX-62 way back in May of 2006. That's not to say AMD hasn't released any products since then. In fact, the company has launched a plethora of lower-clocked "Energy Efficient" processors for the platform and replaced the 125W Athlon 64 FX-62 with an 89W X2 5600+ at the same 2.8GHz and cache size. Frankly, enthusiasts waiting for a new flagship socket AM2 processor haven't had much to read about. Thankfully, there is news from the AMD home-front today. Today AMD is officially unveiling a new top-of-the-line socket AM2 processor, the Athlon 64 X2 6000+. The X2 6000+ sports a full 1MB of L2 cache per core and is clocked at a healthy 3.0GHz, just like the FX-74. Its cache configuration and clock speed should make the X2 6000+ the fastest desktop CPU to come out of AMD. So, what do you say we fire it up and see how it performs in comparison to the rest of today's high-end processor offerings?
We have posted a wealth of information regarding AMD's Athlon 64 processors and related core-logic chipsets over the last few months here at HotHardware.com. For some more background on the technologies employed by AMD's Athlon 64 processors and the AMD AM2 and Quad-FX platforms as a whole, we suggest taking a look at few of the related articles listed below. They contain detailed explanations of some of the features common to AMD's legacy products, compatible chipsets, and the enhancements make to various dual-core processors:
We cover some specifics regarding AMD's current dual-core socket AM2 processor offerings in our FX-62 and 5000+ evaluation, and cover many of the details regarding the nForce 600 family of chipsets in our evaluation of the nForce 680i SLI. And our Quad-FX platform and Quad-Father technology update articles have all of the details regarding Quad-FX and its related FX-70 series processors. We suggest perusing these articles if you're unfamiliar with AMD's technology. They'll lay the groundwork for the technology covered on the forthcoming pages. |
| Vital Signs and Overclocking |
Prior to benchmarking the new AMD Athlon 64 X2 6000+, we spent some time with CPU-Z to see if there was anything interesting to report in regard to the CPU's default configuration. We then took some notes regarding temperatures and overclocking.
CPU-Z: Athlon 64 X2 6000+ Other than the Athlon 64 X2 6000+'s clock speed, nothing much has changed since we last looked at the Socket AM2 Athlon 64 FX-62 a few months back. As you can see, the X2 6000+ processor is built using AMD's .09-micron manufacturing process and is clocked at 3.0GHz (15x200MHz), with 1MB of L2 cache per core, for a total of 2MB of L2 cache. There is also 128K of L1 cache (64K x 2) per execution core, for a total of 256K of L1 cache. A few months ago there were reports that AMD would only be releasing Athlon 64 X2 processors with 512K of L2 cache per core and that only the FX series would be outfitted with 1MB L2 cache compliments. Obviously, that strategy is no longer in effect. The FX brand, however, will be reserved for the Quad-FX platform for now and the X2 6000+ will remain the fastest socket AM2 processor for the time being.
Athlon 64 X2 6000+ Overclocked to 3.2GHz We also spent some time overclocking the Athlon 64 X2 6000+ and had some interesting results. To overclock the processors, we used AMD's stock aluminum / copper PIB cooler. We bumped the CPU voltage up by .1v and set the memory voltage to 2.4v. We left the processor's multiplier at its stock value of 15x and raised the HT speed until the test system was no longer stable. Ultimately, we were able to take the new Athlon 64 X2 6000+ to just under 3.2GHz with an HT clock of 214MHz. The 192MHz overclock equates to a 6.4% increase in clock speed, which is relatively small by today's standards. As we mentioned in our Quad-FX platform coverage a while back, it seems that AMD is getting close to hitting a clock speed ceiling with their 90nm SOI manufacturing process. Through all of our preliminary tests, we also monitored processor temperatures via Asus' PC Probe II software. While idling at stock speeds, we found that the Athlon 64 X2 6000+ processors' core temperature hovered around 48oC. And under load temperatures peaked at around 67oC. Overclocking the CPU to almost 3.2GHz didn't drastically effect temperatures, but we did see a max of about 72oC at one point, at least according to the Asus' health monitoring software. |
| Our Test Systems and SANDRA 2007 | |||||||||||||||||
How we configured our test systems: When configuring our test systems for this article, we first entered their respective system BIOSes and set each board to its "Optimized" or "High performance Defaults". We then saved the settings, re-entered the BIOS and set memory timings for DDR2-800 with 4,4,4,12 timings. The hard drives were then formatted, and Windows XP Professional (SP2) was installed. When the Windows installation was complete, we installed the drivers necessary for our components, and removed Windows Messenger from the system. Auto-Updating and System Restore were then disabled and we set up a 1024MB permanent page file on the same partition as the Windows installation. Lastly, we set Windows XP's Visual Effects to "best performance," installed all of our benchmarking software, defragged the hard drives, and ran all of the tests.
We began our testing with SiSoftware's SANDRA XI, the System ANalyzer, Diagnostic and Reporting Assistant. We ran six of the built-in subsystem tests that partially comprise the SANDRA XI suite with the Athlon 64 X2 6000+ (CPU, Multimedia, Multi-Core Efficiency, Memory, Cache, and Memory Latency). All of the scores reported below were taken with the processors running at their default clock speeds of 3.0GHz.
The results reported by the various SANDRA test modules fell right in line with our expectations. The Athlon 64 X2 6000+ outperformed all other AMD dual-core processors, but it couldn't quite keep up with the higher-clocked Core 2 and Xeon processors. Memory bandwidth and memory latency proved to be strong points for the CPU, as it racked up over 8.5GB/s in SANDRA's buffered memory bandwidth test, and posted the lowest latencies with block sizes up to 1MB. Once block sizes exceeded 1MB, the Core 2's larger 4MB cache allowed it to take the lead. |
| PCMark05: CPU and Memory | |||||
For our next round of synthetic benchmarks, we ran the CPU and memory performance modules built into Futuremark's PCMark05 suite.
"The CPU test suite is a collection of tests that are run to isolate the performance of the CPU. The CPU Test Suite also includes multithreading: two of the test scenarios are run multithreaded; the other including two simultaneous tests and the other running four tests simultaneously. The remaining six tests are run single threaded. Operations include, File Compression/Decompression, Encryption/Decryption, Image Decompression, and Audio Compression" - Courtesy FutureMark Corp.
PCMark05's multi-threaded CPU benchmark had the new Athlon 64 X2 6000+ finishing just ahead of the Athlon 64 FX-62, but the Quad-FX platform and Intel's dual- and quad-core Core 2 processors both outpaced the AM2-based processors.
"The Memory test suite is a collection of tests that isolate the performance of the memory subsystem. The memory subsystem consists of various devices on the PC. This includes the main memory, the CPU internal cache (known as the L1 cache) and the external cache (known as the L2 cache). As it is difficult to find applications that only stress the memory, we explicitly developed a set of tests geared for this purpose. The tests are written in C++ and assembly. They include: Reading data blocks from memory, Writing data blocks to memory performing copy operations on data blocks, random access to data items and latency testing." - Courtesy FutureMark Corp.
The performance deltas separating AMD's socket AM2 dual-core processors (the FX-62 and 6000+) and Intel's Core 2 processors in PCMark05's memory performance module were relatively small in comparison to the previous results. The Intel CPU's still came out on top though. The Quad-FX platform, however, put up comparatively lower scores here due to its non-unified memory architecture. To improve the Quad-FX platform's memory performance, it should be running under 64-bit environment with proper support for NUMA, namely XP-64 or Vista. |
| Office XP and Photoshop 7 | ||||
PC World Magazine's Worldbench 5.0 is a Business and Professional application benchmark. The tests consist of a number of performance modules that each utilize one, or a group of popular applications to gauge performance.
Below we have the results from WB 5.0's Office XP SP2 and Photoshop 7 performance modules, recorded in seconds. Lower times indicate better performance here, so the shorter the bar the better.
In both of the WorldBench modules we tested, the new Athlon 64 X2 6000+ performed at right about the same level as the similarly clocked Quad-FX Athlon 64 FX-74 system. These tests don't benefit from the additional two execution cores on the Quad-FX platform, hence the similar performance between the 6000+ and FX-74. Intel's Core 2 and Extreme processors once again posted the best scores, however, besting AMD's fastest AMD processor by margins of 9 to 54 seconds depending on the individual test and comparison made. |
| LAME MT and Sony Vegas | ||||||||
In our custom LAME MT MP3 encoding test, we convert a large WAV file to the MP3 format, which is a very popular scenario that many end users work with on a day-to-day basis to provide portability and storage of their digital audio content.
In this test, we created our own 223MB WAV file (a never-ending Grateful Dead jam) and converted it to the MP3 format using the multi-thread capable LAME MT application in single and multi-thread modes. Processing times are recorded below. Once again, shorter times equate to better performance
LAME MT processes a maximum of two threads simultaneously, which explains why the dual-core Athlon 64 X2 6000+ and pseudo-quad-core Quad-FX Athlon 64 FX-74 platform performed similarly in this test. Once again though, Intel's Core 2 processors put up the best scores, significantly outpacing the Athlons in both the single and multi-threaded test configurations.
Sony's Vegas DV editing software is heavily multithreaded as it processes and mixes both audio and video streams. This is a new breed of digital video editing software that takes full advantage of current dual and multi-core processor architectures.
The Athlon 64 X2 6000+ completed the Sony Vegas rendering workload about half a minute faster than the Athlon 64 FX-62, but that was the only configuration it outperformed. Because this test is multi-threaded, the quad-core platforms put up the best scores, followed by Intel's dual-core Core 2 processors. |
| Kribibench v1.1 | ||||
For this next batch of tests, we ran Kribibench v1.1, a 3D rendering benchmark produced by the folks at Adept Development. Kribibench is an SSE aware software renderer where a 3D model is rendered and animated by the host CPU and the average frame rate is reported.
We used two of the included models with this benchmark: a "Sponge Explode" model consisting of over 19.2 million polygons and the test suite's "Ultra" model that is comprised of over 16 billion polys.
The Athlon 64 X2 6000+ put up some decent scores in the KribiBench benchmark, but it couldn't quite keep up with the Quad-FX or Core 2 platforms. The 6000+'s higher clock speed give it a marked advantage over AMD's previous flagship AM2 processor, the FX-62, Intel's core microarchitecture and the Quad-FX platform's psuedo quad-core configurations were significantly faster here. |
| Cinebench 9.5 and 3DMark06: CPU | ||||||||
The Cinebench 9.5 benchmark is an OpenGL 3D rendering performance test, based on the commercially available Cinema 4D application. Cinema 4D from Maxon is a 3D rendering and animation tool suite used by 3D animation houses and producers like Sony Animation and many others. And of course it's very demanding of system processor resources.
This is a multi-threaded, multi-processor aware benchmark that renders a single 3D scene and tracks the length of the entire process. The time it took each test system to render the entire scene is represented in the graph below (listed in seconds).
We had a four-way tie for second place in the single-threaded Cinebench test between the new Athlon 64 X2 6000+, FX-74, Core 2 Duo E6700, and Core 2 Extreme QX6700 processors. The first place position in the single-threaded test was reserved for the Core 2 Extreme X6800. The quad-core platforms put up the best scores in the multi-threaded tests, however.
3DMark06's built-in CPU test is a multi-threaded "gaming related" DirectX metric that's useful for comparing relative performance between similarly equipped systems. This test consists of two different 3D scenes that are generated with a software renderer that is dependent on the host CPU's performance. This means that the calculations normally reserved for your 3D accelerator are instead sent to the central processor. The number of frames generated per second in each test are used to determine the final score.
3DMark06's CPU performance module had the new Athlon 64 X2 6000+ finishing just ahead of the FX-62, but behind the rest of the competition. Because this is a multi-threaded benchmarks the quad-core offerings put up the best scores, followed for the Core 2 Duo E6700 and Core 2 Extreme X6800. |
| Quake 4: Low and High Resolutions | ||||
For our next set of tests, we benchmarked all of the test systems using a custom single-player Quake 4 timedemo. Here, we installed the game's official v1.3 point release which is SMP capable and ran the benchmark in two different configurations. First, we turned the resolution down to 640x480, and configured the game to run at its "Low-Quality" graphics setting. Although Quake 4 typically taxes today's high-end GPUs, when it's configured at these minimal settings, it is much more CPU and memory bandwidth-bound than anything else. Then we upped the resolution to 1600x1200 and enabled 4X anti-aliasing and anisotropic filtering to see how the platforms compared in a more taxing gaming environment.
We had a similar performance trend in both Quake 4 testing scenarios. Whether running at a low-res, low-quality setting, or a high-res, high-quality setting, the Athlon 64 X2 6000+'s performance fell right in the middle of the pack. It was clearly the fastest of the AMD-based configurations, but Intel's Core 2 offerings put up the best scores regardless of the test settings. |
| F.E.A.R.: Low and High Resolutions | ||||
For our last set of game tests, we moved on to more in-game benchmarking with F.E.A.R. When testing processors with F.E.A.R, we drop the resolution to 640x480, and reduce all of the in-game graphical options to their minimum values to isolate CPU and memory performance as much as possible. However, the in-game "effects" and "advanced computer options" settings, which control the level of detail for F.E.A.R.'s physics engine and particle system, are left at their maximum values, since these actually do place some load on the CPU rather than GPU. Like we did with Quake 4 on the previous page, we also ran a set of number with F.E.A.R. running at high-resolution with additional pixel processing enabled to asses performance in a typical high-end gaming scenario.
F.E.A.R. showed the new Athlon 64 X2 6000+ performing roughly on-par with the Core 2 Duo E6700. At lower resolution, the 6000+ actually finished a couple of frames per second ahead of the E6700. But at the higher resolution, which is essentially GPU bound, the E6700 jumped back ahead by 1 frame per second. |
| Power Consumption | ||||
We have one final data point we'd like to cover before bringing this article to a close. Our goal was to give you all an idea as to how much power each of the system configurations we tested used while idling and running under load.
Please keep in mind that we were testing total system power consumption here at the outlet, not just the power being drawn by the processors alone. In this test, we're showing you a ramp-up of power from idle on the desktop to full CPU load. We tested with a combination of Cinebench 9.5 and SANDRA XI running on the CPU.
The Athlon 64 X2 6000+ consumed roughly the same power as our Athlon 64 FX-62. While idling, the 6000+ actually drew 5 fewer watts than the FX-62 when using the same core logic chipset (NVIDIA's nForce 590 SLI) and under load is consumed roughly 6 more watts. Please also note that the RD580 chipset (ATI CrossFire Xpress 3200) consumes less power than the nForce 590 SLI, hence the two sets of power consumption scores for the FX-62. Had we also used the RD580 with the X2 6000+ processor its power consumption scores would likely scale down a bit as well. Despite offering higher performance, it's also worth noting that the Core 2 Duo E6700 and Core 2 Extreme X6800 processor both consumed less power than the 6000+, which is a testament to the efficiency of Intel's Core microarchitecture. When AMD finally makes the transition to 65nm with their higher-end processor offerings, power consumption between AMD and Intel at the high-end should get more competitive. |
| Our Summary and Conclusion | ||||||||||||||||||||||||
Performance Summary: The new AMD Athlon 64 X2 6000+ performed in-line with our expectations. As the highest clocked socket AM2 dual-core processor to date, the X2 6000+ was clearly faster than AMD's previous flagship AM2-based CPU, the Athlon 64 FX-62. And in some benchmarks, where the similarly clocked Quad-FX Athlon 64 FX-74's additional two execution cores weren't fully utilized, the Athlon 64 X2 6000+ performed on par with the FX-74 combo. Intel's Core 2 processors, however, outperformed the X2 6000+ virtually across the board.
AMD is officially launching three new processors today; the high-end Athlon 64 X2 6000+ we've focused on here, and two less expensive, energy efficient offerings, the 45W single-core Athlon 64 3800+ and 3500+. Official pricing (in 1KU quantities) and specifications for each of these processors are as follows:
We'll reserve comment on the energy efficient Athlon 64 3800+ and 3500+ processors until we get a chance to test them for ourselves, but performance should be in-line with AMD's similarly clocked single-core 90nm 3800+ and 3500+ processors, with power consumption that should reflect their relatively low 45W max power ratings. We will, however, offer judgment on the Athlon 64 X2 6000+... In comparison to all previous socket AM2 processor offerings, the Athlon 64 X2 6000+ is a solid product. Its higher clock speeds make it the fastest AM2 processor ever released, which also make it the fastest desktop CPU ever to come out of AMD's fabs. In the shadow of Intel's Core 2 Duo E6700 and Core 2 Extreme X6800 processors though, the new X2 6000+ isn't quite as impressive. The Core 2 Duos consumed less power overall and performed better in just about every benchmark. AMD has priced the 6000+ aggressively, which somewhat compensates for the Core 2's higher performance. The 6000+ is almost $500 cheaper than the Athlon 64 FX-62 was when it was launched, which markedly enhances its value proposition. And it's about $60 less expensive than the Core 2 Duo E6700. Ultimately, the Athlon 64 X2 6000+ isn't fast enough to wrestle the performance crown from Intel's high-end Core 2 Duo processors, but it does push AMD's performance up a rung on the ladder. At this point it's clear that it's going to take much higher frequencies, or rather a new architecture for AMD to overtake Intel again. For now, these new price points and speed bins will put AMD on somewhat equal footing, in terms of overall value.
|
;)
;)
;)
;)
;)
;)
;)
;)
;)
;)
;)
;)
