iXBT Labs - Computer Hardware in Detail

Platform

Video

Multimedia

Mobile

Other

Pentium E2140/2160 and Athlon X2 BE-2350

Low-Power CPU Benchmarks.

Stanislav Garmatyuk; July 27, 2007.

July 27, 2007



AMD and Intel recently introduced three new low cost processors. Intel decided to resurrect its Pentium brand for use on two new low-cost parts; the Intel Pentium E2140 and Pentium 2160. AMD, on the other hand, released a new Athlon part, the Athlon X2 BE-2350. Although these processors are positioned at somewhat different segments of the market, we believe it is still appropriate for these two processors to be compared against each other because they have a lot in common:

  • Neither the Pentium E2140, Pentium 2160, nor the Athlon X2 BE-2350 are high-end components. AMD and Intel both have processors in their lineups that are a lot faster.
  • All of these processors are available at similar price points
  • Both the Pentium E and Athlon BE series consume low amounts of power. This is for slightly different reasons, however. Intel's Pentium E series consumes low power because low power consumption is a general property of the core those processors are based on. The AMD BE series, on the other hand, has been developed specifically for lower power consumption.

As you may have already noticed, AMD has yet again changed its branding scheme for processors. The previous name-giving method made it nearly impossible to discern where the processor was getting its name from. In contrast, we believe this new branding scheme is much more logical and concise.

  • The "64" is gone from the "Athlon 64 X2" name, and now processors of this class are called simply "Athlon X2". This is reasonable since "Athlon" is a well known AMD brand, "X2" - specifies double-core architecture, while the 64-bit characteristic isn't something that needs to be given much emphasis anymore
  • The first letter (in our case "B"), most likely signifies a general performance class. In the future there will be processors lettered "G" (top-performance) and "L" (the present Sempron class).
  • The second letter in the marking describes the power consumption class. Processors consuming more than 65 W will have the letter "P" (full-scale, so to speak, "power"). Processors consuming 65 W will be denoted the letter "S". The most economic processors that consume less than 65 W will be given the letter "E".
  • The first digit in the marking describes the certain CPU family. One might guess that "family" somehow correlates to the core. However, at the present moment the reasoning behind the number is not entirely clear.
  • The next three digits, similar to Intel, designate the kind of performance class the processor is meant for. The performance class is a complex parameter based not only on core frequency, but also on bus frequency, on cache size and so on.

Keeping all of these naming characteristics, the Athlon X2 BE-2350 is a middle-range dual-core Athlon processor with low power consumption. The CPU's performance index rings in at 350. So far it's the highest index in the "BE" series.

The naming system is even simpler with the Intel Pentium E2140/2160 processors. They are, in fact, low-end Core 2 Duos that have been cut-down in terms of technical characteristics. Just like the Core 2 Duo E4xxx, they have an 800-MHz bus. The CPU frequency has been brought down even further, and cache has been cut in half. The reduction in cache means that the amount of L2 cache shared by both cores is only 1 megabyte.

There is one very important thing we did in this article. In our stance that we should tell our readers everything that happens during testing in our labs, we decided to publish the results of an unsuccessful benchmark run with the Athlon X2 BE-2350. What basically happened in the unsuccessful performance measurements of the Athlon X2 BE-2350 was our motherboard's BIOS wasn't correctly identifying the processor. Although the processor worked, it remained "unknown" to the system. To give an idea of how this type of situation affects performance, we decided to include its results marked on our charts as "Athlon X2 BE-2350 (UNN)". Naturally, we also published the proper benchmarks and have based all of our findings off of these benchmarks.

Hardware and software

Testbed configuration

CPU Mainboard Memory Video
Pentium E2140 ASUS P5B Deluxe Corsair CM2X1024-6400C4 GeForce 8800 GTX
Pentium E2160 ASUS P5B Deluxe Corsair CM2X1024-6400C4 GeForce 8800 GTX
Core 2 Duo E4400 ASUS P5B Deluxe Corsair CM2X1024-6400C4 GeForce 8800 GTX
Core 2 Duo E6300 ASUS P5B Deluxe Corsair CM2X1024-6400C4 GeForce 8800 GTX
Core 2 Duo E6320 ASUS P5B Deluxe Corsair CM2X1024-6400C4 GeForce 8800 GTX
Core 2 Duo E6420 ASUS P5B Deluxe Corsair CM2X1024-6400C4 GeForce 8800 GTX
Athlon X2 BE-2350 ASUS M2N32-SLI Deluxe Corsair CM2X1024-6400C4 GeForce 8800 GTX
Athlon 64 X2 4400+ ASUS M2N32-SLI Deluxe Corsair CM2X1024-6400C4 GeForce 8800 GTX
Athlon 64 X2 5000+ ASUS M2N32-SLI Deluxe Corsair CM2X1024-6400C4 GeForce 8800 GTX
  • 2x1024MB RAM
  • Samsung HD401LJ (SATA) HDD
  • Boxed coolers
  • Cooler Master RS-A00-EMBA PSU
Processor Pentium E2140 Pentium E2160 Core 2 Duo E4400 Core 2 Duo E6300 Core 2 Duo E6320 Core 2 Duo E6420 Athlon X2 BE-2350 Athlon 64 X2 4400+ Athlon 64 X2 5000+
Process, nm 65 65 65 65 65 65 65 90 90
Core frequency, GHz 1.6 1.8 2.0 1.86 1.86 2.13 2.1 2.2 2.6
# of cores 2 2 2 2 2 2 2 2 2
L2 Cache*, KB 1024 1024 2048 2048 4096 4096 2x512 2x1024 2x512
Bus frequency**, MHz 800 (QP) 800 (QP) 800 (QP) 1066 (QP) 1066 (QP) 1066 (QP) 2x800 (DDR2) 2x800 (DDR2) 2x800 (DDR2)
Multiplier 8 9 10 7 7 8 10.5 11 13
Socket LGA775 LGA775 LGA775 LGA775 LGA775 LGA775 AM2 AM2 AM2
Heat emission***, W 65 65 65 65 65 65 45 89 89
AMD64/EM64T + + + + + + + + +
VT + + + + + +

* - "2 x ..." means per core
** - for AMD processors this is memory controller bus clock rate
*** - measured differently for Intel and AMD processors; impossible to compare directly.

Software

  1. Windows XP Professional x64 edition SP1
  2. 3ds max 9 x64 edition
  3. Maya 8.5 x64 edition
  4. Lightwave 3D 9 x64 edition
  5. MATLAB R2006a (7.2.0.32) x64 edition
  6. Pro/ENGINEER Wildfire 2.0
  7. SolidWorks 2005
  8. Photoshop CS2 (9.0)
  9. Visual Studio 2005 Professional
  10. Apache HTTP Server 2.2.4
  11. CPU RightMark 2005 Lite (1.3) x64 edition
  12. WinRAR 3.62
  13. 7-Zip 4.42 x64 edition
  14. FineReader 8.0 Professional
  15. LAME 3.97
  16. Monkey Audio 4.01
  17. OGG Encoder 2.83
  18. Windows Media Encoder 9 x64 edition
  19. Canopus ProCoder 2.01.30
  20. DivX 6.4
  21. Windows Media Video VCM 9
  22. x264 v.604
  23. XviD 1.1.2
  24. F.E.A.R. 1.08
  25. Half-Life 2 1.0
  26. Quake 4 1.3
  27. Call of Duty 2 1.2
  28. Serious Sam 2 2.07
  29. Supreme Commander 1.0.3220

Testing

A necessary foreword to the charts

We present the results of our tests in two unique ways due to our testing method. First of all, in the summary diagrams of this article all data types are reduced to one - relative integer points. What we mean by relative integer points is that the performance of all processors is relative to that of one processor, which in this case is the Intel Core 2 Duo E4300. The performance of the Core 2 Duo E4300 is rated at 100 points. Second, detailed results regarding the tests are available in a Microsoft Excel table. In the article itself only summary diagrams are given which are grouped together by benchmark classes. Nevertheless, when required, we will occasionally draw your attention to the expanded results which are located in the Excel file.

3-D modeling suites

So far the high-end Athlon X2 BE-2350 does not demonstrate any outstanding performance. It manages to outrun only the lower Pentium E2140 CPU. The Pentium E2160, which is, actually, a Core 2 Duo 4300 with half the L2 cache, is predictably behind the C2D E4300 in speed. You might ask: "How do we know that it's behind the C2D E4300 if that processor isn't even on the charts?" It is simple: in this version of our test method the C2D E4300 is the baseline CPU, therefore its performance is exactly at always 100 points everywhere. There is no need to display it on the charts.

CAD/CAE suites

In this category of applications the AMD K8 core still performs very well, despite its age. The BE-2350 performs quite well and ends up tying the Core 2 Duo E6320. While it's a serious loss to the Athlon 64 X2 4400+, it is clearly a result of not only a 100 MHz lower frequency, but also of a cut-down (2x512 KB) level-two cache.

Digital photo processing

Oddly enough, in this test the BE-2350's small cache is quite enough for it to get significantly closer to the Athlon 64 X2 4400+ in terms of performance. However, the Intel Core 2 performs much better with Photoshop than how it did in the previous test. For this reason, new AMD processor loses to the Pentium E2160 again.

Compiling

The compiling tests send both low-end Intel processors to the very bottom of the chart. If we talk of efficiency in terms of megahertz, though, then the Pentium E2160 doesn't look too bad. Despite a 17% lower frequency and equal cache size (except L2 scheme for BE-2350 is "2x512", whereas E2160 has a shared 1024 KB for all cores), it is only 3% behind in speed. However, this cache-hungry task doesn't leave any chances for processors with small cache to do well. The Pentium E2160 lags behind the Core 2 Duo E4300 by a whole 13 points (15%), while the Athlon X2 BE-2350 is surpassed by the Athlon 64 X2 4400+ by 14 points (16%). We reiterate, though, that there is no way to explain the latter. The only difference is probably caused by the 100 MHz difference in frequency.

Web-server

We get the impression that given same size of L2 cache (total, for AMD processors), Core 2 Duo in some cases loses on the architecture level. To the least what we can say is that the Athlon X2 BE-2350 manages to make better use of its megabyte of L2 cache than the Pentium E2xxx processors. There is, however, another hypothesis. Both cores have their own "threshold" of L2 cache, below which performance in some tasks begins to degrade catastrophically. Apparently, K8's threshold is lower than Core 2 Duo's. This, in particular, is confirmed by results of the Core 2 Duo E4300/4400.

Synthetics

Frequency rules performance here, so the outcome is rather predictable.

Data compression

The Pentium E2160's results are impressive; with half the cache of the Core 2 Duo E4300, it is able to outperform that same processor by six points! So far in our bewilderment we can only attribute this victory to new stepping technology, but the result is still unprecedented. The Athlon BE-2350, in comparison to Intel's low-end chip, is in its expected position; between the Pentium E2140 and 2160.

OCR

The Intel Core 2 Duo architecture is the performance leader in optical character recognition using FineReader-suite. This benchmark doesn't give much consideration to cache size. The victory of the Athlon 64 X2 5000+ over the Pentium E2140 only highlights that fact.

Audio encoding

This is simply an old and traditional test that we perform but don't comment on.

Video encoding

The shared 1 MB of L2 cache places the Core 2 Duo architecture in an uncomfortable situation. These video encoding benchmarks is another class of tasks, which is rather expansive and popular among home users, in which the Pentium Exxx processors occupy the bottom of the chart.

Games

The game results came out as expected. The Pentium E2160 is only seven points short of the Core 2 Duo E4300 baseline CPU, while the Athlon X2 BE-2350 positions itself between the Pentium E2140 and E2160.

Overall score



The overall results show the CPUs in a rare position, where depending on the class of applications, the top places are distributed quite diversely. In professional software applications, the Athlon X2 BE-2350 overcomes both of Intel's high-end chips by 3%, and low-end parts by 13%! However, in the "household" class of tasks, the Athlon X2 BE-2350 loses to the Pentium E2160, and not by a little, by 6%. The Overall score reduces the situation to a common denominator seen in many charts: the Athlon X2 BE-2350 turns out to be faster than the Pentium E2140, but it is still just below (one point) the performance of the Pentium E2160.

Supposed power consumption


At idle, the power consumption tests turn out to be quite in favor of the Core 2 Duo-based chips. However, power consumption of the Athlon X2 BE-2350 both in idle state and under 100% load is significantly better than that of all other Athlon 64 X2-s we have examined. Though it may not consume quite as little power as the "economical" Intel processors, many of which also have higher performance, the results still leave a pleasant impression.

Conclusion

No clear winner can be declared today. To be completely honest, all three of the processors performed exactly as we expected them to. The new Pentiums had the lowest power consumption levels, and although the Athlon X2 BE-2350 had lower power consumption levels than all other AMD processors, it still ended up with higher consumption than the Intel parts.

Given their characteristics, the Pentium E2xxx are fast enough. However, they are not performance champions and lose to the weakest of Core 2 Duo E4xxx-s. One thing that for us is unclear right now is if Intel calls this a Pentium, what will the new Celeron be like? 512 kilobyte shared L2? Judging from the test results, Intel's new core doesn't like small L2 caches at all.

Despite the hopes of some optimists, the Athlon X2 BE-2350 hasn't become the "killer" of low-end Core 2 Duo models. It just "gave a little beating" to the Pentium E2140 (in overall average score) and was glaringly close on the heels of the Pentium E2160. Its power consumption is higher than that of low-end Core 2 Duo parts, although it is significantly less than that of the regular Athlon 64 X2. As a result, it is reasonable to say not that AMD has "caught up with" Intel, but rather that it has significantly reduced the distance in the mid-range to entry-level performance segment.

As a whole - all three of these processors are quite successful and fast enough for their segment. So we give our congratulations to both lifelong competitors, Intel and AMD. Good luck, gentlemen. Keep it up.

Testbed memory modules were provided by
Corsair Memory

Write a comment below. No registration needed!


Article navigation:



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.