Core 2 Duo E6700 and Core 2 Extreme X6800 Review

[nextpage title=”Introduction”]

Core 2 is the new desktop CPU family from Intel, based on the new Core microarchitecture. For desktops Core 2 comes in two flavors: Core 2 Duo, which replaces Pentium D, and Core 2 Extreme, which replaces Pentium Extreme Edition. Core 2 desktop version was formerly known as Conroe and in this review we will check the performance of two models, Core 2 Duo E6700, which runs at 2.66 GHz, and Core 2 Extreme X6800, which runs at 2.93 GHz. We will compare them to the most high-end CPUs from AMD to date, including Athlon 64 X2 5000+ and Athlon 64 FX-62. Who has the fastest desktop CPU, Intel or AMD? Read on.

Attention: This review has some innacurate results, please read our most recent review for more accurate results.

Pay attention to not confuse Core 2 Duo with Core Duo. Core Duo is the commercial name for a Pentium M manufactured using 65 nm process, codenamed Yonah, while Core 2 Duo is the commercial name for the CPU codenamed Merom (for laptops) or Conroe (for desktops), which uses the new Intel Core microarchitecture.

You can check the CPUs Intel sent us on Figures 1 and 2. Since they were engineering samples, they didn’t have their final markings on them. Instead they had an “Intel Confidential” marking. In Figure 2, you can see their bottom side. They use the standard socket LGA775 used by current Pentium 4 and Pentium D CPUs, the only difference you can see is the number and location of the capacitors found in the middle. We added our Pentium 4 550 (3.4 GHz) on the photo so you can see this.

Figure 1: Core 2 Extreme X6800 and Core 2 Duo E6700 engineering samples.

Figure 2: Core 2 Extreme X6800, Core 2 Duo E6700 and Pentium 4 550 (3.4 GHz).

Keep using socket LGA775 was a great move from Intel. Socket LGA775 motherboards launched before Core 2 CPUs were available may be compatible with them. There are two requirements: first, the motherboard must be capable of supplying the voltage required by the new CPU; and second, the motherboard must be capable of supplying the external clock rate (FSB) required by the new CPU. Unfortunately only newer motherboards are capable of supplying the voltage required by Core 2 CPUs.

Internally, however, Core 2 CPUs have nothing to do with Pentium 4 or Pentium D. While Pentium 4 and Pentium D are based on Intel’s 7th generation microarchitecture – also known as NetBurst – Core 2 is based on a new architecture, called Core, which is based on Pentium M’s (which is based on Pentium III’s – as you will see in the next page, Core 2 CPUs report their Family ID as being “6”, the same one as Pentium Pro, Pentium II and Pentium III). Please read our Inside Intel Core Microarchitecture tutorial to learn everything you need to know about this new architecture.

Since they use a totally different internal architecture, you cannot compare clock rates used by Core 2 CPUs with the ones used by other CPUs like Pentium 4 or Pentium D. Core 2 CPUs may be faster using a lower clock rate as they internally process things differently. In fact, we will check this aspect on our review. Here is a problem for the Average Joe. Even though Intel started identifying their CPUs by model numbers a while ago, people still tend to compare CPUs by their clock rates. It will be hard for us to say to which previous Intel CPU or to which AMD CPU each Core 2 model is comparable by just looking to their specs.

Let’s now take a closer look at Core 2 technical specs.

[nextpage title=”Specs”]

The main specifications for the reviewed Core 2 CPUs include:

• Core microarchitecture
• Dual-core technology
• 1,066 MHz external clock rate (266 MHz x 4)
• 4 MB unified L2 memory cache
• Intel Virtualization Technology
• Execute Disable Bit
• Intel EM64T Technology
• Intelligent Power Capability

Some things pop right on our face. The first one is the total lack of Hyper-Threading technology, which seems to be an exclusive feature of Pentium 4 and Pentium Extreme Edition CPUs. This technology emulates two CPUs per core, so a compatible operating system like Windows XP or Linux would recognize a standard Pentium 4 as two CPUs and a Pentium Extreme Edition as four CPUs (two per core) – Pentium D also lacks this feature. If Intel will add this feature back on Core 2 family is still a mystery.

The second thing is the amazing amount of L2 memory cache present on the reviewed models (keep in mind that Intel will probably release models using less memory cache). Intel decided to use a unified L2 cache, contrasted to a per-core approach like Pentium D, Pentium Extreme Edition, Athlon 64 X2 and dual-core Athlon 64 FX. According to Intel their approach provides a higher performance, as each core can use data that is already on the unified cache but was loaded from the main memory by the other core. Also, the cores can negotiate how much memory cache each one will use at a given moment. The division between them doesn’t need to be 50%-50%. At a given moment one core may be using 75% of the memory cache and the other one, 25%. On the separated approach the division is always 50%-50%, meaning that one core can have unused cache at the same time that the other core has ran out of cache, and this core cannot simply “borrow” memory cache from the other core like on the unified approach.
 
As for the external bus, Core 2 family keeps using the same idea that was introduced with the very first Pentium 4 CPU: quad data rate (QDR), i.e., the CPU transfers externally four data per clock cycle. Because of this the CPU external clock rate is said to be four times its actual clock rate. These Core 2 CPUs, for example, have an external bus of 266 MHz but transferring four data per clock cycle, thus Intel label their external bus as being of 1,066 MHz.

So Core 2 Duo E6700 achieves its 2.66 GHz internal clock rate by multiplying its 266 MHz external clock rate by 10 and Core 2 Extreme X6800 achieves its 2.93 GHz internal clock rate by multiplying its 266 MHz clock rate by 11.

These CPUs also incorporates dual-core technology, meaning that internally they have two complete CPUs. SMP-compatible operating systems like Windows XP and Linux will recognize two CPUs. SMP stands for Symmetric Multi Processing and is the ability of a system to use more than one CPU.

On Figures 3 and 4 you see CPU ID results taken with CPU-Z for the reviewed CPUs. As you can see, they report as being “Family 6”, i.e., Intel 6th generation, the same family as Pentium Pro, Pentium II, Pentium III and Pentium M. It is really funny to see a new CPU family with a CPU ID Family ID lower than the previous family (Pentium 4 and Pentium D reports Family ID as 7). The clock rates are being erroneously reported as 1,6 GHz due to Enhanced SpeedStep Technology.

Figure 3: Core 2 Duo E6700.

Figure 4: Core 2 Extreme X6800.

Intelligent Power Capability is an enhancement over Enhanced SpeedStep Technology that we have explained in details in our Inside Intel Core Microarchitecture tutorial.

To learn more about the other features listed above, just click on the links provided to read our tutorials on them.

Another very important difference between Core 2 and Pentium 4 families is the amount of dissipated power. We will talk more about this in the next page.

[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
Athlon 64 3800+	1	2.4 GHz	*	512 KB	Socket 939 (DDR)	89 W
Athlon 64 X2 4600+	2	2.4 GHz	*	512 KB x 2	Socket 939 (DDR)	110 W
Athlon 64 X2 5000+	2	2.6 GHz	*	512 KB x 2	Socket AM2 (DDR2)	89 W
Athlon 64 FX-60	2	2.6 GHz	*	1 MB x 2	Socket 939 (DDR)	110 W
Athlon 64 FX-62	2	2.8 GHz	*	1 MB x 2	Socket AM2 (DDR2)	125 W
Pentium 4 550	1	3.4 GHz	800 MHz (200 MHz x 4)	1 MB	Socket LGA775 (DDR2)	115 W
Core 2 Duo E6700	2	2.66 GHz	1,066 MHz (266 MHz x 4)	4 MB	Socket LGA775 (DDR2)	65 W
Core 2 Extreme X6800	2	2.93 GHz	1,066 MHz (266 MHz x 4)	4 MB	Socket LGA775 (DDR2)	75 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.

Thanks to Core microarchitecture –an enhancement over Pentium M’s – Core 2 family dissipates a lot less power, meaning less heat (TDP stands for Thermal Design Power). As you can see on the table above, Core 2 Duo and Core 2 Extreme dissipate less power than all other CPUs included in our review. It is amazing to see how a dual-core CPU, which has two complete CPUs inside, can dissipate less power than a single-core Pentium 4. You can claim that they run at lower clock rates, however keep in mind that they have four times the amount of memory cache found on Pentium 4, which by itself would increase the CPU power dissipation a lot.

Unfortunately Intel didn’t provide us Pentium D and Pentium Extreme Edition samples for reviewing. A pity.

[nextpage title=”How We Tested”]

During our benchmarking sessions, we used the configuration listed below. Between our benchmarking sessions the only variable was the processor being tested and the motherboard, as socket AM2 CPUs require a new motherboard.
 
Hardware Configuration

• Socket 939 Motherboard: MSI K8N Diamond Plus (BIOS 1.12, December 22nd, 2005).
• Socket AM2 Motherboard: ASUS M2N32-SLI De Luxe
• Socket LGA775 Motherboard: Intel D975XBX
• Memory: Two Corsair CMX1024-3500LLPRO modules with 1 GB each, installed on DDR Dual Channel configuration (2-3-2-6 timings) for socket 939 CPUs.
• Memory: Four Corsair CM2X512-8500 modules with 512 MB each, installed on DDR2 Dual Channel configuration (using 4-4-4-12 timings) for socket AM2 and socket LGA775 CPUs.
• Hard Drive: Maxtor DiamondMax 9 Plus (7,200 rpm, 40 GB, ATA-133).
• Video Card: XFX GeForce 7800 GTX.
• Video resolution: 1024x768x32@85Hz.
• Power Supply: OCZ ModStream 520 W.

Software Configuration

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

Driver Versions

• NVIDIA video driver version: 84.21
• NVIDIA nForce 4 SLI X16 driver version: 7.15
• Intel Inf driver version: 8.0.1002
• All motherboard drivers were installed

Used Software

• SYSmark2004 – Patch 2
• PCMark05 Professional 1.1.0
• Cinebench 9.5
• 3DMark06 Professional 1.0.2
• Quake 4 – Patch 1.2

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=”Overall Performance: SYSmark2004″]

We measured the overall performance of the CPUs included in this review using SYSmark2004, which 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.

The results you can see on the chart below.

Core 2 Duo E6700 (2.4 GHz) achieved an overall SYSmark2004 score similar to Athlon 64 FX-62 (2.8 GHz) and 7.58% higher than Athlon 64 FX-60 (2.6 GHz), 9.23% higher than Athlon 64 X2 5000+ (2.6 GHz), 21.89% higher than Athlon 64 X2 4600+ (2.4 GHz), 45.64% higher than Athlon 64 3800+ (2.4 GHz) and 54.35% higher than Pentium 4 550 (3.4 GHz).

Core 2 Extreme E6800 (2.93 GHz) achieved an overall SYSmark2004 score 8.10% higher than Core 2 Duo E6700 (2.66 GHz), 10.04% higher than Athlon 64 FX-62 (2.8 GHz), 16.29% higher than Athlon 64 FX-60 (2.6 GHz), 18.08% higher than Athlon 64 X2 5000+ (2.6 GHz), 31.76% higher than Athlon 64 X2 4600+ (2.4 GHz), 57.44% higher than Athlon 64 3800+ (2.4 GHz) and 66.85% higher than Pentium 4 550 (3.4 GHz).

On Internet Content Creation batch, however, Core 2 Duo E6700 achieved the same performance level of Athlon 64 X2 4600+, losing to other dual-core CPUs from AMD we reviewed: Athlon 64 FX-62 was 21.31% faster, Athlon 64 FX-60 was 14.10% and Athlon 64 X2 5000+ was 11.80% faster.

On this same batch Core 2 Extreme achieved the same performance level of Athlon 64 FX-60, losing to Athlon 64 FX-62, which was 3.93% faster, and beating Athlon 64 X2 5000+ by only 4.40% and Athlon 64 X2 4600+ by 13.74%. It was also 16.72% faster than Core 2 Duo E6700 on this batch.

Office productivity, on the other hand, is where Core 2 made AMD CPUs to eat dust – probably propelled by their 4 MB L2 memory cache. The MINIMUM performance difference between Core 2 CPUs and other CPUs included in our review was 100%, meaning they were at least twice faster.

Here Core 2 Duo E6700 was 102.86% faster than Athlon 64 FX-62, 113.00% faster than Athlon 64 FX-60, 114.07% faster than Athlon 64 X2 5000+, 146.24% faster than Athlon 64 X2 4600+, 147.67% faster than Athlon 64 3800+ and 161.96% faster than Pentium 4 550.

On this same batch Core 2 Extreme X6800 was 23.24% faster than its brother Core 2 Duo E6700, being 150.00% faster than Athlon 64 FX-62, 162.50% faster than Athlon 64 FX-60, 163.82% faster than Athlon 64 X2 5000+, 203.47% faster than Athlon 64 X2 4600+, 205.23% faster than Athlon 64 3800+ and 224.07% faster than Pentium 4 550.

Results from individual benchmarks you can see on the above graph. In summary these new Intel CPUs lost to AMD dual-core CPUs on multimedia applications but won on office applications. Very interesting.

[nextpage title=”Processing Performance: 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.

On System batch Core 2 Duo E6700 was faster than competing CPUs from AMD: 7.37% faster than Athlon 64 FX-62, 11.52% faster than Athlon 64 FX-60, 13.45% faster than Athlon 64 X2 5000+, 17.06% faster than Athlon 64 X2 4600+ and 54.25% faster than Athlon 64 3800+. It was also 55.01% faster than Pentium 4 550.

On this same batch Core 2 Extreme X6800 was 5.57% faster than Core 2 Duo E6700 and 13.35% faster than Athlon 64 FX-62, 17.73% faster than Athlon 64 FX-60, 19.77% faster than Athlon 64 X2 5000+, 23.58% faster than Athlon 64 X2 4600+, 62.84% faster than Athlon 64 3800+ and 63.65% faster than Pentium 4 550.

On CPU batch Core 2 Duo E6700 was once again faster than competing CPUs from AMD: 17.27% faster than Athlon 64 FX-62, 26.58% faster than Athlon 64 X2 5000+, 27.18% faster than Athlon 64 FX-60, 37.90% faster than Athlon 64 X2 4600+ and 64.04% faster than Athlon 64 3800+. It was also 93.89% faster than Pentium 4 550.

On this same batch Core 2 Extreme X6800 was 9.71% faster than Core 2 Duo E6700, 28.65% faster than Athlon 64 FX-62, 38.87% faster than Athlon 64 X2 5000+, 39.53% faster than Athlon 64 FX-60, 51.29% faster than Athlon 64 X2 4600+, 79.97% faster than Pentium 4 550 and 112.71% faster than Athlon 64 3800+.

[nextpage title=”Rendering Performance: 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.

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 (“Rendering 1 CPU” in the case of Athlon 64 3800+ and Pentium 4 550).

Here the results were quite interesting. All dual-core CPUs from AMD included in our review were faster than Core 2 Duo E6700: Athlon 64 FX-62 was 28.67% faster, Athlon 64 FX-60 and Athlon 64 X2 5000+ were 19.28% faster, and Athlon 64 X2 4600+ was 10.21% faster.

Core 2 Extreme X6800, on the other hand, was faster than all CPUs included in our comparison: it was 15.49% faster than Athlon 64 FX-62, 24.59% faster than Athlon 64 FX-60 and Athlon 64 X2 5000+, 34.83% faster than Athlon 64 X2 4600+, 48.60% faster than Core 2 Duo E6700, 149.17% faster than Athlon 64 3800+ and 181.88% faster than Pentium 4 550.

[nextpage title=”3D Performance: 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.

To be honest, 3D performance nowadays depends much more on the video card used than on the system CPU. This is so true that Core 2 Duo E6700 (2.66 GHz), Athlon 64 X2 4600+ (2.4 GHz), Athlon 64 X2 5000+ (2.6 GHz) and Athlon 64 FX-60 (2.6 GHz) achieved the same performance level on this test. Athlon 64 FX-62 was, however, 4.08% faster than Core 2 Duo E6700. Core 2 Extreme X6800 was a little bit faster than competing dual-core CPUs from AMD (3.13% faster than Athlon 64 FX-62, 4.42% faster than Athlon 64 FX-60, 4.75% faster than Athlon 64 X2 5000+ and 5.72% faster than Athlon 64 X2 4600+) and 7.34% faster than Core 2 Duo E6700.

When comparing the results for the CPU tests alone, a surprise. Core 2 Duo E6700 was heavily beaten by competing dual-core CPUs from AMD: Athlon 64 FX-62 was 33.84% faster, Athlon 64 FX-60 was 23.48% faster, Athlon 64 X2 5000+ was 20.97% faster and Athlon 64 X2 4600+ was 14.63% faster. Core 2 Extreme X6800 was 61.64% faster than Core 2 Duo E6700 on this test.

On the other hand, Core 2 Extreme X6800 was far faster than dual-core CPUs from AMD: it was 20.78% faster than Athlon 64 FX-62, 30.91% faster than Athlon 64 FX-60, 33.63% faster than Athlon 64 X2 5000+ and 41.02% faster than Athlon 64 X2 4600+.

Once again, this shows how the improvement on CPU performance won’t probably reflect on a higher 3D performance (however, as we’ve seen from the overall score, dual-core will reflect on a higher 3D performance compared to single-core technology).

[nextpage title=”3D Performance: Quake 4″]

We ran Quake 4 multiplayer demo id_demo001 on 1024x768x32 with no image quality settings enabled. We run it four times and the results shown on the chart is an arithmetic average of the collected data. The results are in frames per second. For more information on how to use Quake 4 to benchmark a PC, read our tutorial on this subject.

On Quake 4, probably due to the larger L2 memory cache, Intel CPUs based on Core microarchitecture were faster than all other CPUs included in our comparison. Here Core 2 Duo E6700 was 17.40% faster than Athlon 64 FX-62, 30.32% faster than Athlon 64 X2 5000+, 30.86% faster than Athlon 64 FX-60, 41.54% faster than Athlon 64 X2 4600+, 52.14% faster than Athlon 64 3800+ and 72.78% faster than Pentium 4 550.

Core 2 Extreme X6800 was 6.61% faster than Core 2 Duo E6700, 25.15% faster than Athlon 64 FX-62, 38.93% faster than Athlon 64 X2 5000+, 39.50% faster than Athlon 64 FX-60, 50.89% faster than Athlon 64 X2 4600+, 62.19% faster than Athlon 64 3800+ and 84.19% faster than Pentium 4 550.

[nextpage title=”Memory Bandwidth: Sandra Lite 2007″]

We decided to include a memory bandwidth benchmark on this review because AMD64 CPUs have an embedded memory controller, so we were curious to see how it would perform against the memory controller located on the chipset we used, Intel 975X.

It is important for you to know that on Athlon 64 depending on the CPU model the memory bus won’t be running at full speed. Athlon 64 FX-62 has its memory bus truly running at 800 MHz (400 MHz x 2) but Athlon 64 X2 5000+ has its memory bus running at 742 MHz (371 MHz x 2).

On the graph below we also include the maximum theoretical performance for DDR2-800 memories running at single channel (6,400 MB/s) and at dual channel (12,800 MB/s). Since our memories on both platforms (Intel and AMD) were running at dual channel, in theory we had to achieve something near 12,800 MB/s. Let’s take a look.

Here we can see how using a memory controller embedded in the CPU is far more efficient than using the memory controller found on the chipset. Intel CPUs achieved a bandwidth 14.63% lower than the maximum rate for DDR2-800 SINGLE channel. As we had dual channel available, this results translates in a usage of only 42.69% of the available memory bandwidth.

Athlon 64 FX-62 achieved a memory transfer rate 10.20% greater than the one achieved by Athlon 64 X2 5000+, 59.61% greater than the one achieved by both Intel Core CPUs and 36.27% greater than the DDR2-800 standard transfer rate. Athlon 64 X2 5000+, which access memory at a lower clock rate, achieved a memory bandwidth 44.84% greater than the one achieved by both Intel Core CPUs.

Even with these great results for AMD, Athlon 64 FX-62 was able to use only 68.13% of the available bandwidth, so it seems that AMD still has some work to do on their memory controller.

[nextpage title=”Conclusions”]

Attention: This review has some innacurate results, please read our most recent review for more accurate results.

According to our tests the answer to the big question, “who was the best dual-core CPU, Intel or AMD?” is “It depends on the kind of application you are running”.

Amazingly enough comparing apples to apples it seems that AMD has better CPUs for multimedia and  3D applications, while the new Core family achieved a better performance in office-style applications and gaming.

We say “amazingly enough” because several years ago, during K6 times, 3D performance was AMD’s Achilles’ Heel, as they didn’t have a good math co-processor (FPU). It is really interesting to see how AMD was able to improve their CPUs, especially if we keep in mind that Intel is the one pushing and leading multimedia-oriented enhancements such as MMX/SSE. It is really funny to see how AMD has beaten Intel on their own technology.

But on other kinds of application, Intel made AMD to eat dust. On office-style applications – programs like WinZip, antivirus, Microsoft Office, Adobe Acrobat and web browsing – the new Intel CPUs based on the new Core microarchitecture achieved, on average, at least double the performance compared to competing dual-core CPUs from AMD. We could clearly see this on Sysmark 2004, which runs real-world programs. PCMark05, in a lesser scale, confirmed this tendency.

Even though both AMD and Intel CPUs achieved a similar performance on 3DMark06, Core-based CPUs were faster on Quake 4, probably because of the greater amount of L2 memory cache available. We can only confirm if the advantage of Intel Core 2 CPUs on office-style applications and Quake 4 is exclusively due to the higher amount of L2 memory cache or not when Intel releases versions of Core 2 using smaller caches.

As we mentioned earlier, a good feature of Core 2 CPUs is that they keep using socket LGA775, so you won’t need to replace your motherboard if you have a newer motherboard compatible with the external bus – a.k.a. FSB – and voltage of the chosen Core 2 model if you want to upgrade your CPU.

So, which CPU to buy? In our review Core 2 CPUs were faster on office-style applications and gaming, confining AMD to a niche market such as multimedia and 3D rendering. However, this conclusion isn’t final, as the reviewed models had 4 MB L2 memory cache and Intel will launch Core 2 Duo models with 2 MB L2 memory cache. As for the high-end models – i.e., the exact models we reviewed – you can follow this advice and Core 2 is, in fact, the best CPU for the average user. However for entry-level models using less memory cache we still need to review them to see how they look like compared to AMD counterparts.

Attention: This review has some innacurate results, please read our most recent review for more accurate results.