Core 2 Extreme QX6700 Review

[nextpage title=”Introduction”]

During last IDF we had the chance of making a short review on Intel’s first quad-core CPU, Core 2 Extreme QX6700 (codenamed Kentsfield) – which runs at 2.66 GHz. This time we got one sample from Intel and were able to run several programs and compare its performance with other CPUs from Intel and from AMD. Does quad-core CPUs really improve PC performance? Check it out.

Figure 1: Core 2 Extreme QX6700 engineering sample.

We have already written a full article on how Intel’s quad-core technology works. We recommend you to read this article before going further.

As mentioned, Core 2 Extreme QX6700 has four cores and runs internally at 2.66 GHz. As you can see the only difference on its name is the letter “Q”, standing for quad-core. Newer quad-core CPUs to be released in the beginning of 2007 will be called Core 2 Quad.

Internally this CPU has two Core 2 Duo chips. So you can think of Core 2 Extreme QX6700 as being two Core 2 Duo E6700 chips. Since it has two separated chips inside, its 8 MB L2 memory cache isn’t unified as it occurs with Core 2 Duo processors. In fact it has two 4 MB L2 memory caches, the first one is shared by cores 1 and 2 and the second one is shared by cores 3 and 4.

Externally it keeps using socket LGA775 and 1,066 MHz front side bus (FSB), so you can install Core 2 Extreme QX6700 on any socket LGA775 motherboard that supports Core 2 Duo CPUs (however a BIOS upgrade may be necessary).

The system recognizes Core 2 Extreme QX6700 as four independent CPUs. Keep in mind that each CPU core is a real physical CPU and not a simulation like Hyper-Threading technology. By the way, Core 2 CPUs don’t have Hyper-Threading technology; this technology – at least so far – is exclusive of NetBurst microarchitecture, which is used by Pentium 4 and Pentium D (dual-core version of Pentium 4) processors. Core 2 CPUs use a new microarchitecture, called Core microarchitecture, which is based on Pentium M’s (which, in turn, is based on Pentium III’s).

Figure 2: Windows correctly recognizes Core 2 Extreme QX6700 as four CPUs.

Figure 3: Four CPUs available on task manager.

Figure 4: All Core 2 Extreme QX6700 specs on CPU-Z.

[nextpage title=”CPUs Included In Our Review”]

We summarized below all CPUs included in this review with their main specs.

CPU	Cores	Internal Clock	External Clock	L2 Memory Cache	Platform	TDP
Core 2 Extreme QX6700	4	2.66 GHz	1,066 MHz (266 MHz x 4)	4 MB x 2	Socket LGA775	130 W
Core 2 Extreme X6800	2	2.93 GHz	1,066 MHz (266 MHz x 4)	4 MB	Socket LGA775	75 W
Core 2 Duo E6700	2	2.66 GHz	1,066 MHz (266 MHz x 4)	4 MB	Socket LGA775	65 W
Pentium 4 550	1	3.4 GHz	800 MHz (200 MHz x 4)	1 MB	Socket LGA775	115 W
Pentium 4 640	1	3.2 GHz	800 MHz (200 MHz x 4)	1 MB	Socket LGA775	84 W
Athlon 64 X2 5000+	2	2.6 GHz	*	512 KB x 2	Socket AM2	89 W

* Since AMD64 CPUs have their memory controller embedded in the CPU, the datapath between the CPU and the memory controller uses the CPU internal clock rate instead of an external clock rate as it happens on Intel CPUs. To communicate with components outside the CPU, AMD64 CPUs have two busses, the memory bus and the HyperTransport bus. The memory bus run up to DDR400 or DDR2-800 depending on the platform (socket 939 or socket AM2, respectively) and the HyperTransport bus of the listed CPUs works at 1,000 MHz transferring two 16-bit data per clock cycle (also labeled as “2,000 MHz”), achieving a 4,000 MB/s transfer rate on each direction. A 800 MHz external bus on Intel CPUs can provide a maximum theoretical transfer rate of 6,400 MB/s while a 1,066 MHz external bus can provide up to 8,528 MB/s. Direct comparison of this particular spec between Intel and AMD CPUs is really tricky as Intel external bus is used for both accessing the main RAM memory and other components – the video card in particular –, while on AMD64 CPUs two separated paths are used. Also, on Intel CPUs the same datapath is used for transferring data in and out, while HyperTransport bus provides two separated paths for input and output.

Unfortunately Intel didn’t provide us a Pentium D or a Pentium Extreme Edition samples for reviewing. Also we had to send the Athlon 64 FX-62 we had back to AMD (they only lend us the CPUs, we have to send them back after publishing the review). We asked AMD to send us Athlon FX-62 again for this new review and we got no answer from them. A pity.

By the way, the present review is far more accurate than our previous review on Core 2 Extreme X6800 and Core 2 Duo E6700 CPUs. You may find several discrepancies between the two. In such cases, please consider the results from the present review and discard the results we published before.

We changed all our methodology entirely in order to present values closer to reality. We have changed five points: the amount of memory (2 GB against 1 GB), the video card (GeForce 7950 GX2 against GeForce 7800 GTX), the hard disk drive (80 GB SATA-300 against 40 GB ATA-133), the power supply (Antec Neo HE 550 against OCZ ModStream 520 W) and the programs we used (we included far more programs now).

We would like to thank all our readers (and also Intel) that pointed out that something was wrong with our previous review, with numbers lower than other websites were getting. Even though the numbers were correct for the hardware parts we used, we surely had to use more high-end parts for making the review closer to reality. It is obvious that no one buying a high-end Core 2 will use a 40 GB ATA-133 HDD, for example.

[nextpage title=”How We Tested”]

During our benchmarking sessions, we used the configuration listed below. Between our benchmarking sessions the only variable was the CPU being tested and the motherboard, when we benchmarked the CPU from AMD.
 
Hardware Configuration

• Motherboard (Intel): Intel D975XBX2 (BX97520J.86A.1024.2006.0814.1142 BIOS)
• Motherboard (AMD): ASUS M2N32 SLI Deluxe (0117, April 18th, 2006)
• Memory: 2 GB DDR2-1066/PC2-8500 with 5-5-5-15 timings, two Patriot PDC21G8500ELK modules (512 MB each) and two Corsair CM2X512-8500C5 modules (512 MB each).
• Hard Disk Drive: Samsung HD080HJ (SATA-300, 7,200 rpm, 8 MB buffer).
• Video Card: XFX GeForce 7950 GX2 M570 1GB DDR3 XXX (PV-T71U-ZDD9) (factory-overclocked).
• Video resolution: 1024x768x32@85Hz.
• Power Supply: Antec Neo HE 550.

Software Configuration

• Windows XP Professional installed using NTFS
• Service Pack 2
• DirectX 9.0c

Driver Versions

• NVIDIA video driver version: 91.47
• Intel Inf chipset driver version (Intel): 8.0.1.1002
• nForce 590 SLI driver version (AMD): 9.35
• Audio driver version (Intel): Sigmatel 5.10.5143
• Audio driver version (AMD): SoundMax 5.10.1.4490
• LAN driver version (Intel): Intel Pro/1000 9.5.12.0
• RAID driver version (Marvell, Intel): 1.1.0.38-beta
• RAID driver version (Intel): 5.5.0.1035
• RAID driver version (SiliconImage, AMD): 1.0.0.9

Used Software

• SYSmark2004 – Patch 2
• PCMark05 Professional 1.1.0
• GamingHeaven Photoshop Benchmark V2
• Cinebench 9.5
• 3DMark06 Professional 1.0.2
• Far Cry – Patch 1.4
• F.E.A.R. – Patch 1.08
• Quake 4 – Patch 1.2
• Battlefield 2142 – Patch 1.01

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=”SYSmark2004″]

SYSmark2004 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.

For a better visualization, we separated the results into three graphs: overall score, Internet Content Creation score and Office Productivity score.

SYSmark2004 – Overall Score	Score	Difference
Core 2 Extreme X6800 (2.93 GHz)	347	2.36%
Core 2 Extreme QX6700 (2.66 GHz)	339
Core 2 Duo E6700 (2.66 GHz)	331	2.42%
Athlon 64 X2 5000+ (2.6 GHz)	260	30.38%
Pentium 4 550 (3.4 GHz)	195	73.85%
Pentium 4 640 (3.2 GHz)	186	82.26%

Core 2 Extreme X6800 was the CPU that achieved the highest overall performance on SYSmark2004, probably because some applications don’t take advantage of having more than two CPUs installed on the system. For this kind of application the CPU with the highest clock rate will be the fastest one. However, since the performance difference between Core 2 Extreme X6800 and Core 2 Extreme QX6700 was below 3%, we have to consider them to have the same performance level on this score.

Core 2 Extreme QX6700 achieved the same performance level of Core 2 Duo E6700, as both run at the same clock rate. Here we can also see how big is the performance difference between Intel dual-core CPUs against AMD dual-core CPUs (Core 2 Duo E6700 was 27% faster than Athlon X2 5000+ and both run at almost the same clock rate). On the above table you can see the performance difference; the numbers in the “difference” row refers to the performance difference from each CPU to Core 2 Extreme QX6700.

Difference	Internet Content Creation	3D Creation	2D Creation	Web Publication
Core 2 Extreme X6800 (2.93 GHz)	1.53%	-4.07%	6.01%	3.23%
Core 2 Duo E6700 (2.66 GHz)	8.16%	3.35%	13.21%	8.05%
Athlon 64 X2 5000+ (2.6 GHz)	35.67%	29.77%	44.23%	33.76%
Pentium 4 550 (3.4 GHz)	110.91%	90.05%	120.59%	123.66%
Pentium 4 640 (3.2 GHz)	126.34%	100.50%	145.90%	136.36%

On Internet Content Creation batch overall results Core 2 Extreme QX6700 achieved the same performance level as Core 2 Extreme X6800, but Core 2 Extreme X6800 was a little bit faster (4.07%) on 3D Creation batch, probably for the same reason explained above. On all other results inside Internet Content Creation Core 2 Extreme QX6700 was faster, though. On the table above you can see the performance difference from Core 2 Extreme QX6700 to each CPU included on our review.

Difference	Office Productivity	Communication	Document Creation	Data Analysis
Core 2 Extreme X6800 (2.93 GHz)	-5.70%	-3.75%	-8.06%	-5.54%
Core 2 Duo E6700 (2.66 GHz)	-2.75%	-5.52%	-1.44%	-1.36%
Athlon 64 X2 5000+ (2.6 GHz)	25.25%	0.00%	36.25%	43.56%
Pentium 4 550 (3.4 GHz)	44.19%	16.67%	75.38%	45.73%
Pentium 4 640 (3.2 GHz)	47.62%	17.56%	78.13%	54.26%

On Office Productivity batch, Core 2 Extreme QX6700 achieved a performance level lower than Core 2 Extreme X6800 for the reasons we have already explained. The reviewed CPU achieved the same performance level as Core 2 Duo E6700, which runs at the same clock rate (2.66 GHz) but on Communication batch, where E6700 was 5.52% faster than QX6700. On the table above you can see the performance difference from Core 2 Extreme QX6700 to each CPU included on our review.

[nextpage title=”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.

Some applications don’t take advantage of having more than two CPUs installed on the system, and PCMark05 system batch seems to be one of them. Here Core 2 Extreme QX6700 was 3.26% faster than Core 2 Duo E6700, but Core 2 Extreme X6800 was 3.02% faster than the reviewed CPU. These differences are low, though.

Compared to other CPUs, Core 2 Extreme QX6700 was 14.54% faster than Athlon 64 X2 5000+, 61.74% faster than Pentium 4 3.4 GHz and 65.26% faster than Pentium 4 3.2 GHz.

On PCMark05 CPU batch Core 2 Extreme QX6700 was the fastest CPU, as this batch seems to be using more than two CPUs for its tasks. Here the reviewed CPU was 13.18% faster than Core 2 Extreme X6800, 24.93% faster than Core 2 Duo E6700, 58.63% faster than Athlon 64 X2 5000+, 105.45% faster than Pentium 4 3.4 GHz and 114.30% faster than Pentium 4 3.2 GHz.

[nextpage title=”Photoshop CS2″]

The best way to measure performance is by using real programs. The problem, though, is creating a methodology using real software that provides accurate results. For Photoshop CS2 there is a methodology created by the folks at GamingHeaven that is very accurate. Their script applies a series of 12 filters to a sample image and we wrote down the time taken for each filter to run. At the end, we have the results for each individual filter and we simply added them up to give the total time taken to run the 12 filters from GamingHeaven batch. The results below are given in seconds, so the lower the number the better.

Photoshop CS2 doesn’t seem to take advantage of having more than two CPUs (i.e., more than two cores) on your system, as the CPU with the highest clock rate achieved the best results: Core 2 Extreme X6800 was 3.01% faster than Core 2 Extreme QX6700 – not a big difference, though. Core 2 Extreme QX6700 achieved the same performance level as Core 2 Duo E6700, as they run under the same clock rate. The reviewed CPU was 27.05% faster than Athlon 64 X2 5000+, 32.88% faster than Pentium 4 3.4 GHz and 36.90% faster than Pentium 4 3.2 GHz.

[nextpage title=”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. Rendering is one area in which having more than one CPU helps considerably, because usually, rendering software recognizes several CPUs – Cinebench, for instance, can use up to 16 CPUs.

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. Keep in mind that even though the Pentium 4 CPUs we included in our review have only one core, they have Hyper-Threading technology, which simulates two CPUs.

Here Core 2 Extreme QX6700 was faster than all other CPUs we included in our comparison: 47.03% faster than Core 2 Extreme X6800, 61.10% faster than Core 2 Duo E6700, 82.36% faster than Athlon 64 X2 5000+, 295.48% faster than Pentium 4 3.4 GHz and 322.19% faster than Pentium 4 3.2 GHz.

[nextpage title=”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.

Here Core 2 Extreme QX6700 was the fastest CPU, being 8.61% faster than Core 2 Extreme X6800, 11.14% faster than Core 2 Duo E6700, 19.65% faster than Athlon 64 X2 5000+, 85.66% faster than Pentium 4 3.4 GHz and 96.65% faster than Pentium 4 3.2 GHz.

Analyzing only the CPU score from 3DMark06, Core 2 Extreme QX6700 was also the fastest CPU, being 54.58% faster than Core 2 Extreme X6800, 68.44% faster than Core 2 Duo E6700, 95.31% faster than Athlon 64 X2 5000+, 286.29% faster than Pentium 4 3.4 GHz and 305.07% faster than Pentium 4 3.2 GHz.

[nextpage title=”Far Cry”]

Far Cry is a heavy game based on the Shader 3.0 (DirectX 9.0c) programming model. We’ve updated the game to version 1.4. To measure the performance we run four times the demo created by German magazine PC Games Hardware (PCGH) and the results presented below are an arithmetic average of the collected data. We used HardwareOC Far Cry Benchmark 1.3.1 utility to help us collecting the data.

We ran this game in two scenarios, both at 1600×1200. The first one, which we called “low”, was with no anti-aliasing, anisotropic filtering set to one and maximum details. The second one, which we called “high”, was with 8x anti-aliasing, 16x anisotropic filtering and ultra details. The results below are given in frames per second.

Far Cry seems not to use the extra CPUs brought by Core 2 Extreme QX6700. Here the dual-core CPU with the highest clock rate achieved the best performance: Core 2 Extreme X6800 was 4.51% faster than the reviewed CPU, which achieved the same performance level as Core 2 Duo E6700, as they both run at the same clock rate. The reviewed CPU was 46.73% faster than Athlon 64 X2 5000+, 114.92% faster than Pentium 4 3.4 GHz and 124.97% faster than Pentium 4 3.2 GHz.

Even though Far Cry runs faster on dual-core CPUs, this isn’t true with quad-core CPUs. Here Core 2 Extreme X6800 was once again faster as it runs at a higher clock rate – it was 4.89% faster than Core 2 Extreme QX6700. The reviewed CPU was 3.03% slower than Core 2 Duo E6700 and 36.16% faster than Athlon 64 X2 5000+, 105.88% faster than Pentium 4 3.4 GHz and 155.03% faster than Pentium 4 3.2 GHz under our “high” configuration.

[nextpage title=”F.E.A.R.”]

F.E.A.R. is a heavy game and we used its internal benchmarking module. We upgraded it to version 1.08 and measured performance in two scenarios, both at 1600×1200 with “computer settings” at “maximum”. The first one, we called “low”, was with “graphics card” set at “low”, and the second one, we called “high”, was with “graphics card” set at “maximum”. Let’s take a look at the results, given in frames per second.

Here Core 2 Extreme QX6700 achieved the same performance level as Core 2 Extreme X6800 and Athlon 64 X2 5000+, being 3.02% faster than Core 2 Duo E6700, 59.90% faster than Pentium 4 3.4 GHz and 63.30% faster than Pentium 4 3.2 GHz.

Here Core 2 Extreme QX6700 achieved the same performance level as Core 2 Extreme X6800 and Core 2 Duo E6700, being 3.66% faster than Athlon 64 X2 5000+ and 8.97% faster than Pentium 4 3.4 GHz and Pentium 4 3.2 GHz. At this configuration the CPU doesn’t play a dramatic role.

[nextpage title=”Quake 4″]

We upgraded Quake 4 to version 1.3 and ran its multiplayer demo id_demo001 at 1600x1200x32 under two scenarios: first with image quality settings configured at “low” and then with image quality settings configured at “high”. You can check the results below, given in frames per second.

With low image quality settings, Core 2 Extreme X6800 was the fastest CPU, being 9.94% faster than Core 2 Extreme X6700. Here Core 2 E6700 was 4.76% faster than the reviewed CPU. Core 2 Extreme QX6700 was 25.99% faster than Athlon 64 X2 5000+, 66.52% faster than Pentium 4 3.4 GHz and 73.52% faster than Pentium 4 3.2 GHz.

With image quality set at “high” we achieved the same positions: Core 2 Extreme X6800 was the fastest CPU, being 11.34% faster than Core 2 Extreme X6700. Here Core 2 E6700 was 5.66% faster than the reviewed CPU. Core 2 Extreme QX6700 was 24.50% faster than Athlon 64 X2 5000+, 67.37% faster than Pentium 4 3.4 GHz and 72.86% faster than Pentium 4 3.2 GHz.

[nextpage title=”Battlefield 2142″]

Battlefield 2142 is the latest member of the Battlefield franchise. We updated this game to version 1.01. We created our own demo based on Sidi Power Plant map (click here to download the demo we created for this test), which provided a very consistent number of frames per second. We ran it and measured performance with FRAPS. Read our How to Use Battlefield 2142 to Benchmark your PC tutorial in order to learn the procedure we used here.

We ran this game at 1600×1200 in two scenarios, first with all its image quality settings set to low, and then with all its image quality settings set to high (anti-aliasing at 4x). 

You can see the results below, given in frames per second.

With image quality settings configured at “low”, there was no performance difference among the multi-core CPUs included in our review. Core 2 Extreme QX6700 was, however, 21.78% faster than Pentium 4 3.4 GHz and 24% faster than Pentium 4 3.2 GHz.

When we set all image quality settings to high, all CPUs achieved the same performance level, meaning that under this configuration Battlefield 2142 depends more on the installed video card than on the CPU.

[nextpage title=”Conclusions”]

Does quad-core improve the PC performance? Depends on the software you use.

While the performance under a lot of programs automatically increase when you use dual-core CPUs, the same isn’t true with quad-core. The program must be able to recognize more CPUs in order to make the system run faster.

If the programs you use aren’t optimized for quad-core, Core 2 Extreme X6800 is a better CPU, as it runs at a higher clock rate (2.93 GHz). As we’ve seen on our review, on such programs having a higher clock rate makes more difference than having more CPU cores.

Intel provided us a short list of applications that can, today, recognize more than two CPU cores:

• Adobe Photoshop CS2
• Adobe After Effects 7/8 
• Adobe Encore DVD 2.+ 
• Adobe Premiere Pro 2/3.0 
• Autodesk 3DSMAX 8 and 3DSMAX 9
• Cubase v4.5  
• DVD Shrink 3.2
• Maxon Cinema 4D
• Pinnacle Studio dv 10 
• Pov Ray 3.7 Beta
• Quicktime Pro 7.1
• Sony Vegas 7.0 
• TMPGEnc 2.524
• XMPEG with DIVX 6.2

As for games, this list was provided:

• Alan Wake
• Half-Life 2: Episode 2
• Splinter Cell: Double Agent
• Supreme Commander 
• Unreal Engine 3

As you can see, audio and video editing and 3D rendering are the kind of applications that can take advantage of quad-core technology right now. Of course the list of programs supporting more than two cores should increase from now on, especially with Intel releasing (and pushing) quad-core CPUs for the average user – called Core 2 Quad – in 2007.

In summary, Core 2 Extreme QX6700 is a great CPU if you run applications that can use more than two cores, especially audio and video editing and 3D rendering. If this isn’t the  kind of application you run the most, Core 2 Extreme X6800 continues to be the fastest CPU around.