Dual Core Processors Info

From Wikipedia

A dual-core CPU combines two independent processors and their respective caches and cache controllers onto a single silicon chip, or integrated circuit. IBM's POWER4 was the first microprocessor to incorporate 2 cores on a single die. Various dual-core CPUs are being developed by companies such as Motorola, Intel and AMD, and began to appear in consumer products in 2005. This is an initial step in the development of many core computer architectures.

Some people think a true dual-core processor has two cores on a die (and the die is wrapped in a package). Some other people (like Intel) think a dual-core also includes a processor which has one core on each die, and the two dies are on the same package that plugged in one socket on the motherboard. Some call the latter multichip module, double core, or twin core, instead of dual-core. And in the discussion of multicore, the meaning of 'processor', 'CPU', 'chip' depends on the context; each may mean a core, a die, or a package.



Diagram of a dual-core chip,
CPU-local Level 1 caches and
shared, on-chip Level 2 caches.

Advantages

  • Proximity of two CPU cores on the same die have the advantage that the cache coherency circuitry can operate at a much higher clock rate than is possible if the signals have to travel off-chip, so combining equivalent CPUs on a single die significantly improves the performance of cache snoop operations.
  • Assuming that the die can fit into the package, physically, the dual-core CPU designs require much less PCB space than multi-chip SMP designs.
  • A dual-core processor uses slightly less power than two coupled single-core processors, principally because of the increased power required to drive signals external to the chip and because the smaller silicon process geometry allows the cores to operate at lower voltages.
  • In terms of competing technologies for the available silicon die area, the dual-core design can make use of proven CPU core library designs and produce a product with lower risk of design error than devising a new wider core design. Also, adding more cache suffers from diminishing returns.

Disadvantages

  • Dual-core processors require operating system (OS) support to make optimal use of the second computing resource. Also, making optimal use of multiprocessing in a desktop context requires application software support.
  • The higher integration of the dual-core chip drives the production yields down and are more difficult to manage thermally than lower density single-chip designs.
  • From an architectural point of view, ultimately, single CPU designs may make better use of the silicon surface area than multiprocessing cores, so a development commitment to this architecture may carry the risk of obsolescence.
  • Scaling efficiency is largely dependent on the application or problem set. For example, applications that require processing large amounts of data with low computer-overhead algorithms may find this architecture has an I/O bottleneck, underutilizing the device.

Athlon 64 X2 4800+ Vs. Pentium 840 EE
from: Toms Hardware

Before we draw our conclusions about the overall performance of the two systems, let's go over once more how the stress test progressed during the 18 days.

At first, we used two platforms from AMD and Intel, both with an SLI configuration based on NVIDIA's nForce4 SLI chipset. Later, we had to replace the motherboard in the Intel system with one based on the Intel 955X chipset, which also meant that SLI operation was no longer possible. In order to make the test fair, we also removed the SLI configuration from the AMD system. We were then able to get results from both systems after 14 days of operation with four applications running simultaneously.

When multiple applications are running, the clear conclusion is that the Intel Pentium 840 Extreme Edition is superior to the AMD Athlon 64 X2 4800+. This result attained by Intel's dual-core processor is particularly attributable to hyperthreading (HT) - the division of the two cores into four virtual CPU units. This was underscored by the fact that when the HT function was turned off, the tables turned and the AMD Athlon 64 X2 4800+ surpassed its rival. Here, it is impossible to speak in terms of percentages, precisely because of the different load distributions.

We got a different picture, however, when we ran single applications on each system. Here, the AMD system performed distinctly better (by just about 30% on average) compared to the Intel system.

Thus, when making a purchasing decision, the question to ask is whether or not multiple applications will be running simultaneously. If the answer is yes, then the Intel Pentium 840 EE is your first choice. Otherwise, the AMD Athlon 64 X2 4800+ will give you much better performance for single applications.

In the end, we can conclude that the Intel Pentium 840 EE should be used with a motherboard that has the Intel 955X chipset. We do not recommend its use with a board with NVIDIA's nForce4 SLI chipset.

With the AMD platform you've only got one option, which fortunately is stable: to combine the AMD platform with a motherboard based on NVIDIA's nForce4 SLI chipset. The results of our stress test show that the nForce4 SLI chipset for the AMD platform has matured.

Here is a summary of lessons learned.

  1. Make sure your cooler can actually cool the CPU. It sounds so simple, but the variations on coolers, particularly for those that support the various models of Intel's Pentium Extreme CPUs, can be subtle but important. We had problems with using an under-sized cooler for our Pentium 840 EE. Use the largest cooler you can for this processor. The one designed for the 840 EE has a higher 3500 RPM and larger copper core than the ones designed for slower EE models.
  2. Not all DDR2-667 CL5.0 RAM chips work the same in these early pre-release test platforms. We had to replace our OCZ modules with ones from Crucial, because the memory timings of the nForce 4 chipsets for Intel were too fast for our test motherboards.
  3. With our tests so far, it seems that hyperthreading is better than having separate CPUs at distributing and balancing the load on the overall processor(s). We aren't sure if this is due to the design of the memory that we are using, the individual CPU controllers or bus architectures, or something else that we haven't tested. We are investigating this further.
  4. In our Far Cry tests, the AMD system with a single nVidia graphics card still beat the frame rates posted by the Intel system with dual SLI cards. These tests were conducted with running multiple applications concurrently, with the game running as the foreground task, and your mileage and frame rates may vary from ours.
  5. AMD's dual core systems are more reliable at this point in time, at least when we put the final AMD product up against the pre-release Intel products that we used. We had far more problems with the Intel setup than AMD. Whether this is the nature of the products we tested, the mistakes we made in configuration, the greater tolerance for error when assembling AMD-related support components, or our own comfort factor with AMD equipment, we can't really say. But it is something to keep in mind when you assemble your own dual-core systems.
  6. Be prepared to be at the hairy edge of reliability with Intel dual-core SLI systems for the near term. We realize that our Intel setups are pre-release, but still we had several issues with BIOS updates and other items that reduced overall system reliability. This is certainly something to watch for as the Intel systems get into general release.
  7. All was not rosy with AMD, however: our tests showed that it lagged behind Intel with respect to Divx compression. We still don't have a good answer for the cause of this difference, however. But if you do a lot of videos, stick with Intel for the time being.