Cool and cheap screamers from Intel and AMD

The game is changing dramatically, however, with Intel’s introduction of its new Core 2 Duo processors and AMD’s retaliatory moves. Now, we have some excellent dual-core CPU options that combine solid performance with very low power use at prices around the $200 mark. What’s more, because they have relatively modest clock speeds, they may have the potential to overclock like Floyd Landis in Stage 17. From Intel, there’s the Core 2 Duo E6300, with 2MB of cache and microarchitectural roots in Intel’s mobile products group. From AMD, there’s the CPU with the longest name ever, the Athlon 64 X2 3800+ Energy Efficient Small Form Factor. You may use extra energy spitting out that massive moniker, but the chip promises to conserve thanks to its astounding 35W power rating.

We’ve tested these cool, cheap screamers against a range of today’s best processors to see whether one of them might be the right choice for your next PC build. Also, we’ve taken a little extra time to explore power use, overclocking, and the impact on the Core 2 processors of dropping from 4MB to 2MB of L2 cache. Keep reading to see what we found.

The chips

The first of our two contestants is the Core 2 Duo E6300, the humblest of Intel’s new Core 2 processors. Unlike its fancier big brothers, the E6300 has only 2MB of L2 cache to share between its two execution cores. You’ll find plenty of sources that will tell you the code name for these 2MB Core 2 Duo processors is “Allendale,” but Intel says otherwise. These CPUs are still code-named “Conroe,” which makes sense since they’re the same physical chips with half of their L2 cache disabled. Intel may well be cooking up a chip code-named Allendale with 2MB of L2 cache natively, but this is not that chip.

Whatever the name, the E6300 shares its faster siblings’ 65nm fab process and 1066MHz front-side bus speed, but it runs at a relatively relaxed 1.86GHz clock frequency. The E6300 also has the same 65W thermal design power (TDP) rating as the rest of the desktop Core 2 Duo family, despite its much lower clock rate. The Core 2 Duo E6700, for instance, runs at 2.67GHz and fits into the same 65W thermal envelope. In practice, I would expect most Core 2 Duo E6300s to use less power than an E6700, although power use will vary from chip to chip because Intel sets stock voltages for each processor at the factory.

Regardless, the Core 2 Duo line’s 65W TDP compares quite favorably to the Pentium D 805’s 95W rating or the Pentium D 950’s considerable 130W TDP.

If you really want to go low on the power, though, our second contender may be an even better fit. AMD uses a more conservative formula to estimate thermal design power than Intel, and even so, the Athlon 64 X2 3800+ Energy Efficient Small Form Factor carries a TDP rating of only 35W. As you might have gathered, this puppy is intended for use in low-power, low-noise systems such as home theater PCs.

In fact, we should come clean. Our efforts to compare this processor to the Core 2 Duo E6300 may not be entirely apt. AMD offers two other versions of the Athlon 64 X2 3800+ for its Socket AM2 infrastructure that might be a closer match for the E6300. The plain ol’ Athlon 64 X2 3800+ comes with a TDP of 89W, while the Energy Efficient (but not Small Form Factor) version has a 65W TDP. AMD makes these different power grades of its processors by tweaking the way that the chips are fabricated, and it charges more for the lower power versions.

Heck, the, err, A64 X2 3800+ EE SFF is almost certainly the same chip as the Turion 64 X2, but with different packaging and pinout. It’s possible that Intel might eventually release a similar low-power version of the Core 2 Duo that’s based on the “Merom” mobile variant of the Core 2.

Fortunately, the performance of all three flavors of the Athlon 64 X2 3800+ products should be virtually identical, so our performance numbers should be relevant for any of them. All three are 90nm chips that run at 2GHz with 512KB of L2 cache per core.

The new math
Back when we reviewed the high-end versions of the Core 2, AMD had pledged to cut prices to maintain a price-performance ratio similar to Intel’s, but we didn’t yet know exactly how those prices would look. Now the price cuts have come, and they’re deep. Here’s how things stack up.

Intel’s introductory prices for the Core 2 were very reasonable, and AMD really took the axe to its price structure in response. For our purposes, though, these price lists are a little bit iffy. The E6300, for example, is selling at online vendors for between $220 and $230, well above its $183 list price, probably because supply of these chips is still spotty. Meanwhile, the price of the Athlon 64 X2 3800+ EE SFF is not listed at AMD’s website, and the chips themselves aren’t yet showing up at online retailers. AMD says initial supplies of the EE SFF were all snapped up by a major PC manufacturer, but it expects to see processors selling individually by later this month. When that happens, I wouldn’t be surprised to see the EE SFF end up in the same $220-230 range as the Core 2 Duo E6300.

Our testing methods
You’ll notice the presence of a CPU marked “Core 2 4MB 1.86GHz” in our results. That’s actually a Core 2 Extreme X6800 chip that I’ve clocked down to the same speed as the Core 2 Duo E6300. I wanted to see how the move from 4MB of L2 cache to 2MB impacts performance, so I set up this clock-for-clock comparison against the E6300.

Please note that the two Pentium D 900-series processors in our test are actually a Pentium Extreme Edition 965 chip that’s been set to the appropriate core and bus speeds and had Hyper-Threading disabled in order to simulate the actual products. Similarly, our Socket AM2 versions of the Athlon 64 X2 4800+, 4600+, and 4200+ are actually the Athlon 64 FX-62 and X2 5000+ clocked down to the appropriate speeds, and the Core 2 Duo E6600 is actually an underclocked Core 2 Extreme X6800. The performance of our “simulated” processor models should be identical to the actual products.

Also, I’ve placed asterisks next to the memory clock speeds of the Socket AM2 test systems in the table below. Due to limitations in AMD’s memory clocking scheme, a couple of these systems couldn’t set their memory clocks to exactly 800MHz.

As ever, we did our best to deliver clean benchmark numbers. Tests were run at least three times, and the results were averaged.

Our test systems were configured like so:

Thanks to Corsair and Crucial for providing us with memory for our testing. Both of them provide products and support that are far and away superior to generic, no-name memory.

Also, all of our test systems were powered by OCZ GameXStream 700W power supply units. Thanks to OCZ for providing these units for our use in testing.

The test systems’ Windows desktops were set at 1280×1024 in 32-bit color at an 85Hz screen refresh rate. Vertical refresh sync (vsync) was disabled.

We used the following versions of our test applications:

• SiSoft Sandra 2007.5.10.98 64-bit
• CPU-Z 1.33
• Compiled binary of C Linpack port from Ace’s Hardware
• POV-Ray for Windows 3.6.1 64-bit
• SMPOV 4.6
• Cinebench 9.5 64-bit Edition
• LAME MT 3.97a 64-bit
• Windows Media Encoder 9 x64 Edition
• Sphinx 3.3
• picCOLOR 4.0 build 561 64-bit
• The Elder Scrolls IV: Oblivion 1.1
• Battlefield 2 1.22
• Quake 4 1.2 with trq4demo5
• FEAR 1.03
• Unreal Tournament 2004 v3369 and 3369 64-bit Edition with trdemo1
• 3DMark06 1.0.2
• WorldBench 5.0

The tests and methods we employ are generally publicly available and reproducible. If you have questions about our methods, hit our forums to talk with us about them.

Memory performance

The two processors line up just about as one might expect in this memory bandwidth benchmark. Like the other Athlon 64 processors, the EE SFF benefits from not having to traverse a front-side bus in order to reach main memory. Meanwhile, the difference between the Core 2 Duo E6300 and its equivalent with 4MB of L2 cache is virtually nil.

Our relatively unoptimized version of Linpack shows us the size and performance of the various parts of the memory hierarchy on each chip, out to 2MB matrix sizes. Because it can dynamically repartition its L2 cache between its two cores, the E6300’s effective cache size in this test looks to be about 2MB. The EE SFF has individual 512K L2 caches dedicated to each core, so its effective L2 cache size here is much smaller.

The integrated memory controller on the Athlon 64 confers an advantage to the EE SFF, but it’s not as great as expected because the Core 2 Duo includes a number of optimizations to mask memory access latencies, including out-of-order loads and stores and a sophisticated algorithm for recognizing access patterns and speculatively pre-fetching data into the L2 cache.

Let’s have a look at how the memory access latencies look across a broader range of conditions.

The EE SFF gets to main memory faster, but it does have to go there more often due to its smaller L2 cache.

Gaming performance

Quake 4
We tested Quake 4 by running our own custom timedemo with and without its multiprocessor optimizations enabled. These can be switched on in the game console by setting the “r_usesmp” variable to “1”.

We’re testing at lower resolutions and lower graphical detail settings in order to ease any GPU bottlenecks that might mask the performance differences between the CPUs. At higher graphical detail settings or with a less powerful graphics card, of course, the graphics subsystem might become the primary performance limiter.

Above the following benchmark graph, and throughout most of the tests in this review, we’ve included Task Manager plots showing CPU utilization. These plots were captured on the Pentium Extreme Edition 965, and they should offer some indication of how much impact multithreading has on the operation of each application. Single-threaded apps may sometimes show up as spread across multiple processors in Task Manager, but the total amount of space below all four lines shouldn’t equal more than the total area of one square if the test is truly single-threaded. Anything significantly more than that is probably an indication of some multithreaded component in the execution of the test. Because WorldBench’s tests are entirely scripted, however, we weren’t able to capture Task Manager plots for them, as you’ll notice later.

NVIDIA’s video drivers are now multithreaded, so we should see some amount of multithreading action happening in any application that uses the GPU for 3D graphics, even if the game is only single-threaded.

The E6300 edges out the EE SFF by a hair. Both processors can run Quake 4 at more than acceptable frame rates, though. The move from 2MB of cache to 4MB makes a measurable difference, but not a substantial one.

The Elder Scrolls IV: Oblivion
We tested Oblivion by manually playing through a specific point in the game five times for each CPU while recording frame rates using the FRAPS utility. Each gameplay sequence lasted 60 seconds. This method has the advantage of simulating real gameplay quite closely, but it comes at the expense of precise repeatability. We believe five sample sessions are sufficient to get reasonably consistent and trustworthy results. In addition to average frame rates, we’ve included the low frames rates, because those tend to reflect the user experience in performance-critical situations. In order to diminish the effect of outliers, we’ve reported the median of the five low frame rates we encountered.

We set Oblivion’s graphical quality settings to “Medium,” 800×600 resolution, with HDR lighting enabled. Our Oblivion test is a quick run around the Imperial City Arboretum.

Again, the EE SFF winds up just below the E6300, and again, the margin between them is fairly small.

F.E.A.R.
We used F.E.A.R.’s built-in “test settings” benchmark to get these results. The game’s “Computer” and “Graphics” performance options were both set to “High.”

Battlefield 2
We used FRAPS to capture BF2 frame rates just as we did with Oblivion. Graphics quality options were set to BF2’s canned “High” quality profile. This game has a built-in cap at 100 frames per second, and we intentionally left that cap enabled so we could offer a faithful look at real-world performance.

Unreal Tournament 2004
We used a more traditional recorded timedemo for testing UT2004, but we tried out two versions of the game, the original 32-bit flavor and the 64-bit version.

The Core 2 Duo E6300 maintains its advantage over the X2 3800+ EE SFF—until we reach UT2004, where its relatively low clock frequency and 2MB L2 cache combine to make it relinquish the lead by an eyelash. If the E6300 had a larger cache, it would outpace the EE SFF here.

Whatever the outcome, though, both of these processors are quite fast enough to run today’s games. Given what we’ve seen in the tests above, I’d pick the E6300 as a better bet to run tomorrow’s more CPU-intensive games smoothly. The gap between the two CPUs isn’t huge, though.

3DMark06
3DMark06 combines the results from its graphics and CPU tests in order to reach an overall score. Here’s how the processors did overall and in each of those tests.

The GeForce 7900 GTX graphics cards in our test rigs become a serious limitation in 3DMark06, so the CPUs are left to distinguish themselves in 3DMark’s CPU-specific tests. There, the E6300 pulls ahead of the EE SFF.

WorldBench overall performance
WorldBench’s overall score is a pretty decent indication of general-use performance for desktop computers. This benchmark uses scripting to step through a series of tasks in common Windows applications and then produces an overall score for comparison. WorldBench also records individual results for its component application tests, allowing us to compare performance in each. We’ll look at the overall score, and then we’ll show individual application results alongside the results from some of our own application tests.

The gap between the E6300 and the Athlon 64 X2 3800+ EE SFF grows wider in WorldBench. On the Core 2 Duo, moving up from a 2MB cache to a 4MB cache is only worth one more point, or less than one percent of overall performance in WorldBench.

Audio editing and encoding

LAME MP3 encoding
LAME MT is, as you might have guessed, a multithreaded version of the LAME MP3 encoder. LAME MT was created as a demonstration of the benefits of multithreading specifically on a Hyper-Threaded CPU like the Pentium 4. (Of course, multithreading works even better on dual-core processors.) You can download a paper (in Word format) describing the programming effort.

Rather than run multiple parallel threads, LAME MT runs the MP3 encoder’s psycho-acoustic analysis function on a separate thread from the rest of the encoder using simple linear pipelining. That is, the psycho-acoustic analysis happens one frame ahead of everything else, and its results are buffered for later use by the second thread. The author notes, “In general, this approach is highly recommended, for it is exponentially harder to debug a parallel application than a linear one.”

We have results for two different 64-bit versions of LAME MT from different compilers, one from Microsoft and one from Intel, doing two different types of encoding, variable bit rate and constant bit rate. We are encoding a massive 10-minute, 6-second 101MB WAV file here, as we have done in many of our previous CPU reviews.

MusicMatch Jukebox

The competition remains close in our audio encoding tests, but the Core 2 Duo proves faster overall. The 4MB L2 cache doesn’t seem to help MP3 encoding with LAME at all.

Video editing and encoding

Windows Media Encoder x64 Edition Advanced Profile
We asked Windows Media Encoder to convert a gorgeous 1080-line WMV HD video clip into a 320×240 streaming format using the Windows Media Video 8 Advanced Profile codec.

Windows Media Encoder

Adobe Premiere

VideoWave Movie Creator

Nothing much changes when we move to video encoding. The Core 2 Duo takes three out of four tests by slim but significant margins.

Image processing

Adobe Photoshop

ACDSee PowerPack

picCOLOR
picCOLOR was created by Dr. Reinert H. G. Müller of the FIBUS Institute. This isn’t Photoshop; picCOLOR’s image analysis capabilities can be used for scientific applications like particle flow analysis. Dr. Müller has supplied us with new revisions of his program for some time now, all the while optimizing picCOLOR for new advances in CPU technology, including MMX, SSE2, and Hyper-Threading. Naturally, he’s ported picCOLOR to 64 bits, so we can test performance with the x86-64 ISA. Eight of the 12 functions in the test are multithreaded.

Scores in picCOLOR, by the way, are indexed against a single-processor Pentium III 1 GHz system, so that a score of 4.14 works out to 4.14 times the performance of the reference machine.

Core 2 processors excel in our image processing tests, and the E6300 is hanging with more expensive Athlon 64 models like the X2 4600+ in some cases.

Multitasking and office applications

MS Office

Mozilla

Mozilla and Windows Media Encoder

Here the E6300 really pads its lead in WorldBench by finishing well ahead of the EE SFF in the Mozilla and Mozilla-plus-Media Encoder tests.

Other applications

Sphinx speech recognition
Ricky Houghton first brought us the Sphinx benchmark through his association with speech recognition efforts at Carnegie Mellon University. Sphinx is a high-quality speech recognition routine. We use two different versions, built with two different compilers, in an attempt to ensure we’re getting the best possible performance.

WinZip

Nero

Sphinx is one of the few places where the difference between 2MB and 4MB cache sizes is really pronounced. Even with a smaller cache, though, the E6300 surpasses the fastest Athlon 64.

3D modeling and rendering

Cinebench 2003
Cinebench measures performance in Maxon’s Cinema 4D modeling and rendering app. This is the 64-bit version of Cinebench, primed and ready for these 64-bit processors.

The EE SFF pulls out a win in Cinebench’s rendering test.

The EE SFF picks up another win the OpenGL software test, but the E6300 proves faster in the other two Cinebench shading exercises.

POV-Ray rendering
POV-Ray just recently made the move to 64-bit binaries, and thanks to the nifty SMPOV distributed rendering utility, we’ve been able to make it multithreaded, as well. SMPOV spins off any number of instances of the POV-Ray renderer, and it will divvy up the scene in several different ways. For this scene, the best choice was to divide the screen horizontally between the different threads, which provides a fairly even workload.

We considered using the new beta of POV-Ray with native support for SMP, but it proved to be very, very slow. We’ll have to try it again once development has progressed further.

Here’s another rendering test, and another case where the EE SFF comes out on top.

SiSoft Sandra Mandelbrot
Next up is SiSoft’s Sandra system diagnosis program, which includes a number of different benchmarks. The one of interest to us is the “multimedia” benchmark, intended to show off the benefits of “multimedia” extensions like MMX and SSE/2. According to SiSoft’s FAQ, the benchmark actually does a fractal computation:

This benchmark generates a picture (640×480) of the well-known Mandelbrot fractal, using 255 iterations for each data pixel, in 32 colours. It is a real-life benchmark rather than a synthetic benchmark, designed to show the improvements MMX/Enhanced, 3DNow!/Enhanced, SSE(2) bring to such an algorithm.

The benchmark is multi-threaded for up to 64 CPUs maximum on SMP systems. This works by interlacing, i.e. each thread computes the next column not being worked on by other threads. Sandra creates as many threads as there are CPUs in the system and assigns [sic] each thread to a different CPU.

We’re using the 64-bit port of Sandra. The “Integer x16” version of this test uses integer numbers to simulate floating-point math. The floating-point version of the benchmark takes advantage of SSE2 to process up to eight Mandelbrot iterations at once.

Core 2 processors just tear through this one with their wide execution units, and the E6300 is no exception.

Power consumption
We took our power readings at the wall outlet using an Extech 380803 power meter. Only the PC was plugged into the watt meter; the system’s monitor and speakers, for instance, were not. The “idle” readings were taken at the Windows desktop, while the “load” readings were taken using SMPOV and the 64-bit version of the POV-Ray renderer to load up the CPUs. In all cases, we asked SMPOV to use the same number of threads as there were CPU front ends in Task Manager—so four for the Extreme Edition 965, two for the Core 2 and Athlon 64 X2 processors. The test rigs were all equipped with OCZ GameXStream 700W power supply units.

The graph below for idle power use has results with and without “power management.” By “power management,” we mean the dynamic clock speed and voltage throttling technologies from Intel and AMD, known as SpeedStep and Cool’n’Quiet, respectively. The Intel processors also have an enhanced halt state known as C1E. A processor’s halt state is invoked by the OS whenever the system is able to sit idle for a moment. The C1E halt state in the Intel processors ramps down the CPU clock speed and voltage in order to save power, so even without SpeedStep, the CPU’s idle power use is reduced. Keep that in mind when considering the “No power management” results for the Intel processors at idle.

Interestingly, we found that the Core 2’s C1E state doesn’t lower CPU voltage. The CPU multiplier drops to 6.0, bringing the clock speed down to 1.6GHz, but voltage appears to remain unchanged. Turning on SpeedStep, however, drops the CPU’s core voltage, allowing for even lower idle power use.

Another tricky part about power consumption testing is getting good numbers for our “simulated” CPU speed grades. In order to make it work, you have to set the proper CPU core voltage, not just the right clock speeds. I made an attempt at simulating the Athlon 64 X2 models 4800+, 4600+, and 4200+ and the Pentium D 950/960 by setting the CPU voltages manually, but I’ve put an asterisk next to those CPUs in our results as a reminder that they’re simulated. I didn’t even bother including some simulated CPU models because of the difficulty involved and a few questionable results.

For the Athlon 64 X2 4800+, I set the voltage at 1.35V. The X2 4600+ and 4200+ were set to 1.3V. The “power management” idle scores were simply taken from chips with the same cache size (the FX-62 and 5000+, respectively), because all of these processors share the same 1 GHz/1.1V idle with Cool’n’Quiet.

The Pentium D 950 and 960 were trickier, since each Pentium D’s voltage needs are programmed at the factory. In this case, I stuck with the default of 1.312V for both speed grades. On an 800MHz bus, the Pentium D 950 and 950 both clocked down to 2.4 GHz at idle via the C1E halt mechanism. The Extreme Edition 965 clocked down to 3.2 GHz at idle.

Wow, that’s close. System power consumption at idle and under load is practically the same between the Athlon 64 X2 3800+ EE SFF-based system and the Core 2 Duo E6300-based one. The systems based on both chips draw quite a bit less power under load than most in the field, although the Core 2 Duo E6700 system is only 3W away from them.

That comparison pits the chips against one another with the E6300 on an Intel 975X-based motherboard and the EE SFF on an nForce 590 SLI motherboard. Both of those motherboards—and the core-logic chipsets on them—are enthusiast-class products that include support for dual graphics slots and a host of high-end features. The nForce 590 SLI, in particular, is a fairly power-hungry two-chip design with 16-lane PCI Express for graphics connections coming off of each chip.

I was also able to test several of the Athlon 64 X2 processors on a much simpler motherboard, the Asus M2NPV-VM. This mobo conforms to the Micro ATX form factor and uses the GeForce 6150/nForce 430 chipset combo with only a single graphics slot. I’d expect to see the EE SFF taking up residence on a lot of boards like this one. We don’t yet have a comparable motherboard for the Core 2 Duo, unfortunately.

Total system power draw for the EE SFF drops 20W at idle and 23W under load, simply by switching to a different motherboard. When coupled with the right mobo, the EE SFF’s power efficiency is outstanding.

Overclocking
My efforts to overclock the E6300 were limited by the fact that our Intel D975XBX motherboard refused to overclock the front-side bus (and thus the processor) by more than 25% of its rated speed. Still, with no increase in CPU voltage, I was able to get the E6300 to POST and run at 2.33GHz on a 1333MHz bus—on the very first try. Who knows how high this CPU might go on a different motherboard?

For this overclock, the PCI-E clock was locked at 100MHz. I had the memory dividers set up for 667MHz, which yielded 830MHz memory speeds with the overclocked bus. Although the RAM was running at a bit higher speed than stock, no change in memory timings was necessary to achieve stability.

As for the EE SFF, well, it’s a bit different story. AMD tweaks its manufacturing process in certain ways to make these low-power processors, and as I understand it, they are engaging in a tradeoff between transistor leakage and switching speed when they do so. As a result, the EE SFF is able to run with very low core voltages, but it’s not happy at high clock speeds. I was hoping to get it to 2.4GHz, which is the speed at which I run a much older Athlon 64 X2 3800+ in my own system, but the EE SFF wouldn’t POST at that speed. After some experimenting, I was able to get it stable at 2.33GHz (on a 233MHz HyperTransport link) with a minor bump in voltage. Even then, the system wouldn’t POST reliably, but it was stable enough to run a few tests. The system’s DDR2 memory was running at an effective 776MHz clock speed in this config, with PCI Express locked at 100MHz.

The Core 2 Duo’s clock-for-clock performance is very strong, so naturally a bump up in clock speed leads to big performance gains. When overclocked by just 25%, the E6300 challenges the Athlon 64 FX-62 in our gaming and audio encoding tests. We’ll have to try the E6300 on a different motherboard soon and see how high we can take it.

As for the EE SFF, I don’t think this is really an overclocker’s chip. It doesn’t have lots of headroom, and turning up the frequency and voltage compromises this CPU’s low-power character without delivering big returns.

Conclusions
Intel’s snazzy new CPU architecture again proves very potent. As you’ve witnessed, the Core 2 Duo E6300 generally got the better of this comparison in terms of performance. The E6300 is faster than the EE SFF—and, by extension, any of the three versions of the Athlon 64 X2 3800+—when running at stock speeds. When overclocked by an easily achievable 25% to 2.33GHz, this CPU can run with AMD’s fastest processor, the Athlon 64 FX-62. That’s pretty darned spiffy for a processor that lists for under $200.

The E6300 doesn’t draw much less power than the higher models of the Core 2 Duo, making it arguably less energy efficient than those chips. Still, the E6300 is easily more efficient than a Pentium D or a regular Athlon 64 X2.

Also, outside of a few exceptions, the E6300’s smaller L2 cache doesn’t handicap it significantly in terms of clock-for-clock performance compared to Core 2 Duo processors with 4MB of cache. What that says to me is that there’s no reason to fear grabbing a 2MB version of the Core 2 Duo if you plan to overclock. You’re not likely to miss the extra cache.

In short, if I were building a PC today and I could get my hands on an E6300, I’d grab it and go to town on the overclocking. The only reason I might hesitate would be worries about my motherboard taking the front-side bus beyond 1333MHz without problems. If you aren’t confident about taking the front-side bus into the stratosphere, the higher multiplier in the E6400 might be worth the extra money. Beyond that, the E6300 looks like a killer CPU for an enthusiast’s desktop PC.

The Athlon 64 X2 3800+ Energy Efficient Small Form Factor, meanwhile, has a different mission in life. It’s not bad on the desktop, with a WorldBench score better than a Pentium D 960 and decent performance in today’s games. But the EE SFF can’t keep up with the E6300 on the performance front, and it’s not much of an overclocker, either. Instead, the EE SFF would look most at home in the living room, on a low-power motherboard inside of a home theater PC case. With the right motherboard, its power consumption is ridiculously, wonderfully low. If you’re not looking to build a quiet, cool PC for some reason, though, you’re better off grabbing the 65W or 89W version of the Athlon 64 X2 3800+—or better yet, the Core 2 Duo E6300.