 |
 |
 |
||
|
|
||||
 |
|
|
| Introduction and Related Information | |||||||
|
Over the last year or so, since Intel's Core microarchitecture and Conroe core were ready to be unveiled at the Intel Developers Forum in early March '06, Intel has been more open and has allowed the media a view into more details regarding upcoming products much earlier than they had before. You don't have to take our word for it, however. Simply look around at all of the early performance previews out of IDF, and the steady flow of announcements regarding Intel's 45nm manufacturing process, metal gate transistors, the Terascale project, Larrabee, Penryn, Nehalem, and a number of other projects, and it becomes readily apparent that Intel wants to get the word out regarding their future products early and often.
Today's news falls into the category of an early announcement as well; a sneak peek, so to speak. In the coming weeks - sometime later this summer - Intel will be officially launching a whole line of desktop processors that feature 1333MHz front side bus frequencies, which is a healthy boost from the current desktop standard of 1066MHz. We've actually got one of these new 1333MHz FSB-equipped chips in house, the Core 2 Duo E6750, and while we can't disclose all of the details regarding this processor just yet, we can talk about its performance and overclockability. And that's is exactly what we're going to do here today, but first let's get some of the particulars out of the way.
We've posted a wealth of information related to Intel's Core microarchitecture and Core 2 Duo and Extreme family of processors here at HotHardware.com. For more background on the technologies employed by the Core microarchitecture and Intel's platform as a whole, we suggest taking a look at few of these related articles. They contain detailed explanations of some of the features common to Intel's legacy products, compatible chipsets, and the new Core 2 Duo and Core 2 Extreme processors:
We cover some specifics regarding Intel's 65nm manufacturing process in our 955XE / i975X evaluation and outline Intel's AMT (Active Management Technology) and IVT (Intel Virtualization Technology), among other things inherent to the Core microarchitecture, in our Core 2 Duo E6700 & Extreme X6800 Evaluation . The other articles listed above will also give you some background as to how the Core 2 has matured, leading up to today. Beyond the increase in FSB speed, there really isn't too much more to know about the E6750, other than the fact that the chip is based on a new stepping and revision of the Conroe core and that it will require a motherboard and chipset capable of supporting the new 1333MHz FSB, i.e. Intel Bearlake (P3x, G3x) or NVIDIA's nForce 6. |
| Vital Signs and Overclocking |
|
As you probably expect, the Core 2 Duo E6750 looks just like any other Core 2 Duo CPU thanks to the processor's integrated heat spreader. But the underside too looks just like the first batch of Conroe-based processors that hit the market last year.
The Core 2 Duo E6750 uses Intel's LGA775 (Land Grid Array) packaging, just like all of Intel's desktop processors for the past three years, and while built using Intel's 65nm manufacturing process, underneath that IHS lies a new revision of the Conroe core.
As you can see in the CPU-Z screenshots above, this particular processors has a core clock speed of 2.6GHz, with a default multiplier of 8 and an actual front side bus frequency of 333MHz (1333MHz quad-pumped). This is particularly important because Intel's previous generation of chipsets do not officially support an FSB frequency that high, even though most of them are capable of running in that range through overclocking. With this new line of processors, Intel is hoping to speed up the adoption of their new P3x and G3x desktop chipsets Also of note according to CPU-Z are the new E6750's revision and stepping. The version of Conroe at the heart of the E6750 is stepping B revision G0. If you recall, the first Conroe-based processors to hit the market had a stepping of 5 and a revision code of B1. We asked for details on what specifically had been changed in the new stepping / revision, but have not gotten an answer just yet. If Intel discloses the changes, we'll be sure to update the article and let you know.
As is typically the case, we like to overclock every new processor to land in the lab to see just how much clock speed headroom it has. In our initial look at Conroe, we were able to take a Core 2 Extreme X6800 processor up to about 3.5GHz using nothing but a slight bump in voltage and the stock air cooler, which is nothing to scoff at. This time around, however, our results were nothing short of spectacular. By bumping the processor's core voltage to 1.45v and increasing the front side bus speed via our Asus P5K Deluxe motherboard's BIOS, we were able to take the Core 2 Duo E6750 up from its default clock speed of 2.6GHz to an impressive 3.92GHz (multiplier=8x / Front Side Bus Frequency=490MHz. This was done using the stock Intel CPU cooler on an open-air test bench. At that speed, the CPU completed a Cinebench rendering pass in just 18 seconds and it blew past the Core 2 Extreme X6800 in SANDRA's Processor Arithmetic benchmark. We should also note that throughout all of our overclocking experiments, the CPU barely hit 48°C and it seemed to heat up and cool down very quickly. We've only spent a limited amount of time with this chip and haven't experimented with multiple motherboards just yet, so we're not certain these temperature readings are accurate, but this early data suggests that this new revision of Conroe runs quite cool and has excellent overclocking potential. |
| 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 upcoming Core 2 Duo E6750 finished just slightly ahead of the similarly clocked Core 2 Duo E6700 in PCMark05's CPU performance test. The processors higher front side bus frequency doesn't allow it to catch the faster Core 2 Extreme X6800, and the quad-core QX6800 is simply in a league of its own.
"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.
PCMark05's memory performance module does show that the E6750's 1333MHz front side bus frequency gives it a marked advantage over the similarly clocked E6700. Once again the chip wasn't able to catch the X6800, but the higher FSB does result in better memory performance overall. |
| Office XP and Photoshop | ||||
|
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.
There's not much to report in regard to Worldbench 5.0's Office XP and Photoshop tests. The Core 2 Duo E6750's higher-clocked FSB does allow it to nudge ahead of the Core 2 Duo E6700, but these tests aren't very bandwidth limited and scale proportionally with core clock speed. |
| 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.
The Core 2 Duo E6750 and E6700 finished right on top of each other in our custom LAME MT MP3 encoding benchmark in both the single- and multi-threaded version of the test. Technically, the E6700 finshed the MT test 1 second faster, but since this benchmark doesn't report fractional differences in the encoding time, that actual difference is likely to be less than 1 second, which falls well within the margin of error in this test.
The Core 2 Duo E6750's faster bus speed allowed it to finish our Sony Vegas video rendering benchmark about 5 seconds faster then the E6700. Once again though, the faster FSB doesn't give the chip enough of a boost to catch the X6800 and the quad-core QX6800 simply can't be touched. |
| 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.
We had another photo-finish in our Kribibench tests. While rendering and animating the 'sponge explode' model, the Core 2 Duo E6750 and E6700 finished with the exact same framerate of 5.38FPS. While rendering the more taxing 'ultra' model, the E6750 fell just slightly behind the E6700, but again the difference falls within the margin of error in this benchmark. |
| Cinebench and 3DMark06 | ||||||||
|
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.
Whether run in single- or multi-threaded mode, Cinebench 9.5 reported very similar results for the E6750 and E6700. Both processors rendered the scene in the same amount of time in the multi-threaded test and in the single-threaded test only 1 second separated the two processors.
It seems that 3DMark06's built-in CPU benchmark benefits from the additional memory bandwidth afforded by the E6750's higher-clocked front side bus. In this test, the Core 2 Duo E6750 finished 111 points ahead of the Core 2 Duo E6700, a difference of 4.7%. |
| Quake 4 and F.E.A.R. | ||||
|
For our last set of game tests, we moved on to some in-game benchmarking with Quake 4 and F.E.A.R. When testing processors and motherboards with Q4 or F.E.A.R, we drop the resolution 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, which control the level of detail for the games' physics engines and particle systems, are left at their maximum values, since these actually do place some load on the CPU rather than GPU.
Both Quake 4 and F.E.A.R. reported similar performance gains for the Core 2 Duo E6750. In both games, the E6750 finished roughly 5% ahead of the E6700. Once again, the difference wasn't enough to catch the higher clocked Core 2 Extreme X6800 but it did give the E6750 an marked edge over the Athlon 64 6000+ that the E6700 didn't enjoy. |
| 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 while running under load.
Before reading too far into these power consumption numbers, we need to clarify the results. The Core 2 Duo E6750 was tested on an Asus P5K Deluxe P35-chipset based motherboard that is chock full integrated peripherals. The remaining Core 2 processors were all tested on an Intel D975XBX2 motherboard which is based on the 975X Express chipset and isn't nearly as loaded at the P5K Deluxe. The P35 chipset has shown to consume more power than the 975X and the additional integrated peripherals on the P5K all need power as well. These differences account for the overall power consumption deltas represented above. Putting aside that information, we see the E6750 consumed 39 more watts under load than it did while idling. In comparison the E6700 consumed 34 more watts under load, and the X6800 45 more. So while the E6750 / P35 platform consumed more power as a whole, the processor itself was right on-par with the older E6700. |
| Summary and Conclusion | ||||
|
Performance Summary: Throughout our entire benchmark suite, the Core 2 Duo E6750 performed on-par or slightly faster than the similarly clocked Core 2 Duo E6700. The E6750's higher-clocked front side bus equated to more memory bandwidth in the synthetic tests, which resulted in performance gains of roughly 1% - 6% in our real-world tests.
Other than the chip's performance and overclockablity, there isn't much more we can report in regard to the Core 2 Duo E6750. Intel will be talking about pricing and availability sometime in the not too distant future. Our performance and overclocking data reveals some interesting information, however. As we've already mentioned the E6750's higher-clocked front side bus frequency resulted in more memory bandwidth which in turn resulted in somewhat higher performance overall versus the similarly clocked E6700. More interesting - at least in our opinion - is the E6750's new core revision and stepping, which resulted in massive overclocking headroom. Overclocking isn't a given of course, but if our sample is any indication of what retail-ready E6750's can do, these chips are going to be quite popular when they are released, as long as pricing is in line with Intel's current offerings.
|
;)
;)
;)
;)
;)
;)
;)
;)
;)
;)
;)
;)
