Dual Processor vs Dual Core

 比较了AMD和Intel各自产品上的差别。其中的评论也有很好的参考意义。原文链接：http://www.pugetsystems.com/labs/articles/Dual-Processor-vs-Dual-Core-23

Introduction
	It has always been a frequent question -- "Will I benefit from multiple processors?" With the growing popularity of dual core processors, the topic is more important than ever! Will multiple processors or a dual core processor be beneficial to you, and what are the differences between them? These are the questions this article will attempt to lay to rest. A major question for some people getting ready to buy a high-end system is whether they want or need to have two processors available to them. For anyone doing video editing, multi-threaded applications, or a lot of multitasking the answer is a very clear 'yes'. Then the question becomes whether two separate processors (as in a dual Xeon or Opteron system) is the way to go, or whether a single dual core processor (like a Pentium D or Athlon64 X2) will do just as well. Dual CPU vs dual core -- which is better?!
Dual Core Defined
	As the tasks that computers can perform get more complicated, and as people desire to do more at once, computer manufacturers are trying hard to increase speed in order to keep up with demand. Having a faster CPU has been the traditional way to keep up, since a faster CPU can do a task then quickly switch and work on the next. However, due to size, complexity and heat issues it has become increasingly difficult to make CPUs faster. In order to continue to improve performance, another solution had to be found. Having two CPUs (and a motherboard capable of hosting them) is more expensive, so computer engineers came up with another approach: take two CPUs, smash them together onto one chip, and presto! The power of two CPUs, but only one socket on the motherboard. This keeps the price of the motherboards reasonable, and allows for the power of two CPUs (also known as cores) with a cost that is less than two separate chips. This, in a nut shell, is what the term "Dual Core" refers to - two CPUs put together on one chip. There are more subtle differences between brands (how they combined two cores onto one chip, and the speeds they run each core at) that can affect how much of a boost in performance you can get from having a dual core CPU. Additionally, different types of programs get differing benefits from having a dual core chip.
Thread Scheduling
	There is one more thing to keep in mind: how a computer knows when to use each core. There is a part of the Windows operating system called the 'scheduler' which tells the CPU what program to be running at any given time. This allows several programs to run at the same time, while the processor switches back and forth between them as needed. When a lot of programs are running, a computer can begin to seem slow, since Windows' scheduler is having to divert the computer's CPU resources in many directions. If a dual-core processor is present, the scheduler suddenly has twice as much CPU resource to work with. This would allow for things like being able to run one core specifically for a game, while using the other core to do "background" things that keep the rest of the system running. Sometimes both cores can even work on the same program (if it is designed to take advantage of more than one core - this is called being "multi-threaded"). However, it is important to note that if you are running a single program and it is not "multi-threaded", you will not see a benefit from more than one CPU or core.
Dual Core Implementation
	Because of the different ways AMD and Intel came into the dual-core market, each platform deals with the increased communication needs of their new processors differently. AMD claims that they have been planning the move to dual-core for several years now, since the first Athlon64s and Opterons were released. The benefit of this can be seen in the way that the two cores on their processors communicate directly -- the structure was already in place for the dual cores to work together. Intel, on the other hand, simply put two of their Pentium cores on the same chip, and if they need to communicate with each other it has to be done through the motherboard chipset. This is not as elegant a solution, but it does its job well and allowed Intel to get dual-core designs to the market quickly. In the future Intel plans to move to a more unified design, and only time can tell what that will look like. Intel did not increase the speed of their front-side-bus (the connection between the CPU and the motherboard) when they switched to dual-core, meaning that though the processing power doubled, the amount of bandwidth for each core did not. This puts a bit of a strain on the Intel design, and likely prevents it from being as powerful as it could be. To counteract this effect, Intel continues to use faster system memory to keep information supplied to the processor cores. As a side note, the highest-end Intel chip, the Pentium Extreme Edition 955, has a higher front-side-bus speed, as well as having a larger (2MB per core) cache memory and the ability to use Hyperthreading (which all non-Extreme Edition Pentium D processors lack). This makes it a very tempting choice for those wanting to overcome some of the design handicaps of Intel's dual-core solution. AMD, on the other hand, does not use a front-side-bus in the traditional sense. They use a technology called HyperTransport to communicate with the chipset and system memory, and they have also moved the memory controller from the chipset to the CPU. By having the memory controller directly on the processor, AMD has given their platform a large advantage, especially with the move to dual-core. The latest generation of AMD single-core processors can use single- or dual-channel PC3200 memory, but it is interesting to note that even though dual-channel operation doubles the memory speed, it does not double the actual memory performance for single-core processors. It appears that dual-channel memory just provides significanly more bandwidth than a single processor core can use. However, with dual-core processors all that extra bandwidth can be put to good use, allowing the same technology already present in single-core chips to remain unchanged without causing the same sort of bottleneck Intel suffers from.
AMD Performance Comparison
	To compare performance differences here at Puget Custom Computers, we compile a selection of benchmarks taken from systems we have built in the past. This comes in very useful when looking to answer questions about performance, like we're doing here! We will tackle AMD first: This is a comparison of two systems with virtually identical hardware. The video card and hard drive used were the same brand and model. The amount of RAM is identical (2x 1GB PC3200) with the only difference being that the Opteron system used ECC memory. The real differences were just the motherboard and CPUs. For the Opteron system we have 2 model '248' processors running at 2.2Ghz each with 1MB of cache. They are running on a Tyan Thunder K8WE board, which uses an nVidia nForce Professional chipset. The single-CPU solution is an Athlon64 X2 4400+, with two cores each running at 2.2Ghz and each sporting a 1MB cache. This processor was installed in an Asus A8N-SLI Premium motherboard, utilizing an nVidia nForce4 SLI chipset. As you can see, graphics performance is very similar, with 3dMark05 scores only 1 point apart and less than 4% variation in the 3dMark'03 scores. Looking closer, we can also see that the important specific metrics in PCMark04 are very similar as well -- the biggest difference is seen in the additional overhead of ECC impacting the memory performance.All around, I would say that with the AMD platform there is little noticeable difference between dual-core and dual processors. Which is great news, because no matter which setup you choose you get the same power! For those with plenty of money to burn, it is also common for us to build a AMD Opteron system with a dual CPU motherboard, and using a dual core CPU in each socket. That gives a grand total of four functional CPU cores! This setup is especially desirable if you need to have multiple heavy duty applications open (CAD, video editing, and modeling come to mind) - just make sure you complement those processors with plenty of memory.
Intel Performance Comparison
	For Intel, we have compiled a comparison between a pair of Xeon 3.0Ghz CPUs with 1MB cache each and a single Pentium D 830. The Pentium D has two cores with each running at 3.0Ghz with 1MB of cache. Furthermore, both setups use an 800Mhz front-side-bus to communicate with the motherboard. Again, the motherboards themselves are different but each system has the same amount of memory (2GB) and similar video cards (GeForce 6800GT 256MB). There is a little more variation between these two systems because the memory is configured differently: the Xeon is using two sticks of 1GB PC3200, while the Pentium is using 4 sticks of 512MB PC2 5400. This gives the Pentium D a definite advantage in overall memory bandwidth available, but that is a very tangible benefit of using the Pentium D line. Intel has not yet, as of this writing, updated its Xeon processors and their chipsets to handle higher speed RAM. Here again we see fairly close performance in graphics, with the Xeon system in a very slight lead. In more performance-oriented tests, however, we see the Pentium system tending to pull ahead by a fair margin. This is most likely due to its significant memory speed advantage, but again this is a very valid and important result. The RAM that was used in the Pentium D system is standard for that platform, but even if we wanted to, we could not build a Xeon setup with the same speed of memory.So while the processors may be very comparable in performance the overall win definitely goes to the Pentium D dual-core platform.
Conclusion
	As you can see, the move to dual-core is definitely a win for consumers. Since they are more affordable than dual processor computers, but offer the same or better performance, they are becoming the standard for modern computer systems.

Showing 17 comments

• 
  fellix 1 comment collapsed Collapse Expand

  Have considered turning off HyperThreading on the Xeon setup for more accurate comarison with the P-D system?

  • A Like
  • Reply

  • 03/28/2006 03:19 AM
  • 0 Like
  • F
• 
  Jon Bach , Puget Systems founder and president. 1 comment collapsed Collapse Expand

  That would just decrease the performance of the Xeons, making them fall further behind. The point behind hyperthreading is to maximize the throughput of the CPU by reducing the possible bottleneck in and out of the CPU, if I understand correctly. Another indicator that Intel has a bottleneck of data I/O to the CPU.

  • A Like
  • Reply

  • 03/28/2006 03:30 AM
  • 0 Like
  • F
• 
  Jon Bach , Puget Systems founder and president. 1 comment collapsed Collapse Expand

  BTW, it has been great to see the popularity of this article...from *just about* everywhere! As of 10am today:
  
  del.ico.us: 255 visitors ,
  Slashdot: 0 visitors (story rejected)

  • A Like
  • Reply

  • 03/30/2006 04:31 AM
  • 0 Like
  • F
• 
  PCC-Wilson 1 comment collapsed Collapse Expand

  Hmm...I wonder why slashdot rejected the story? Too good for them? :thumbsdown

  • A Like
  • Reply

  • 03/30/2006 05:18 AM
  • 0 Like
  • F
• 
  PCC-Richard 1 comment collapsed Collapse Expand

  I just think that slashdot general posts more complex articles. This was written more for the layman.

  • A Like
  • Reply

  • 03/31/2006 03:09 AM
  • 0 Like
  • F
• 
  Geoff 1 comment collapsed Collapse Expand

  Isn't there a fundamental problem with the memory benches (and subsequently others) here in that the dual-core solution has two memory channels, both filled, but the dual-processor solution has *four* memory channels, only two of which are being used? The dual-processor should rock compared to the dual-core in this category at least.

  • A Like
  • Reply

  • 04/03/2006 06:58 AM
  • 0 Like
  • F
• 
  PCC-William 1 comment collapsed Collapse Expand

  Geoff, your are correct! Several readers have pointed this out to me since we launched the article, but unfortunately the benchmarks we have available are all based on systems that have long since been shipped out to the customer. That particular build was intended, as the customer requested, to have 'growing room' for extra RAM. I failed to notice this as I was selecting benchmarks to use for the article.
  
  I will be checking to see if there are any other similar systems we have benchmarks on file for, but as I recall that was the only dual-dual-core-opteron in that speed range that we have done. If I am able to come up with some better comparisons, and if they differ significantly (as I suspect), then I will see if we can update the article accordingly.

  • A Like
  • Reply

  • 04/03/2006 09:21 AM
  • 0 Like
  • F
• 
  Rhinoman 1 comment collapsed Collapse Expand

  In the comparsion both the single processor and dual core are at the same speed(3.0 Ghz). The problem being that what you get in Dual-Core is slower then single XEON (2.8 Ghz vrs 3.8 Ghz). In fact we have clients asking if they should by Dual Processor system at 3.8 GHZ or Dual - Dual-Core system at 2.8 GHZ? What are these comparison like?

  • A Like
  • Reply

  • 04/03/2006 11:10 PM
  • 0 Like
  • F
• 
  Jon Bach , Puget Systems founder and president. 1 comment collapsed Collapse Expand

  Well, since his article showed that dual-core is comparable in speed to dual-CPU, that would mean that a dual-CPU system at a full GHZ faster would be....well....faster! Seems like this article shows that it is not a difficult comparison, but rather a very straight forward one.

  • A Like
  • Reply

  • 04/04/2006 01:25 AM
  • 0 Like
  • F
• 
  mharr 1 comment collapsed Collapse Expand

  However, it is important to note that if you are running a single program and it is not "multi-threaded", you will not see a benefit from more than one CPU or core.
  
  Is this true? I am under the impression that a user will see some performance increase from a dual-processor system, even if a single primary application does not use or is not designed to use multiple processors, at least on Windows NT-class machines (NT/2000/XP/2003).
  
  While the application is using just one of the processors, the Windows OS will perform its OS "stuff" on the other "unused", leaving less task-switching and interference for the primary application. That could, for a heavy application (database, CAD, game) have a noticable performance increase.
  
  I remember testing this back in the day of Pentium Pro dual processor servers (200 mhz), using SQL Server. Although we limited SQL Server to 1 processor (due to licensing, buying only a 1 processor license), we saw 15-20% performance gain on a dual processor system. Later, testing a web server (IIS on Win2k) on hyperthreaded machine, we saw 10-15% performance increase (IIS default web site at that time could only run on on process, one processor).
  
  So I think that just having an extra processor to let Windows offload its overhead onto, will make noticable difference in heavy applications.
  
  Mark

  • A Like
  • Reply

  • 04/04/2006 01:38 AM
  • 0 Like
  • F
• 
  PCC-William 1 comment collapsed Collapse Expand

  Rhinoman,
  
  It looks like you are talking about the dual-core Xeons compared to a 2x single-core Xeon. Yes, in that case, the dual-core Xeons are not available in as high of speeds as the single core are. However, the comparison I made was between two Xeons and a dual-core Pentium 4. The reason I went with this comparison was that most people don't seem to be very interested in two dual-core Xeons (they tend to run very hot and are quite expensive). In fact, to my knowledge, we have yet to sell a dual-core Xeon. However, anyone who might have been thinking about a two cpu Xeon setup would be interested (or so I hoped) to know that a dual-core Pentium with the same clock speed beat out a pair of Xeons. Sadly, I can't really provide benchmarks to directly answer the question you brought up, since we have had no systems come through with dual-core-Xeons.
  
  
  mharr,
  
  There will be some benefit from a second CPU or core in Windows, as you describe, so long as something else is going on in the background that needs CPU attention. There are cases where this seems to not be true, however. Gaming is a good example: in many benchmarks dual-core CPUs seem to do no better (occassionally even slightly worse) than single-cores with the same speed. Soon, however, gmaes will begin to be designed for multiple cores and we will surely see a large performance boost. Also, if you had something CPU intesive running in the background there could be a noticable difference. Really, it comes down to how you plan to use your system - which is great, because here at Puget you can get a computer custom-made to meet your needs!

  • A Like
  • Reply

  • 04/04/2006 02:54 AM
  • 0 Like
  • F
• 
  Rhinoman 1 comment collapsed Collapse Expand

  Well, since his article showed that dual-core is comparable in speed to dual-CPU, that would mean that a dual-CPU system at a full GHZ faster would be....well....faster! Seems like this article shows that it is not a difficult comparison, but rather a very straight forward one.
  
  That was not my intend question. The comparison I am looking for is Dual - DUAL-Core 2.8 Ghz compared to Dual-Processor 3.8 GHz. The PROBLEM is you can not order Dual-Cores at the same speed as Xeon single processor. And I am looking for comparision of DUAL-DUAL Core to Dual Processor.

  • A Like
  • Reply

  • 04/04/2006 03:03 AM
  • 0 Like
  • F
• 
  Jon Bach , Puget Systems founder and president. 1 comment collapsed Collapse Expand

  Sorry I misunderstood. I would still tend to take a simplistic view -- add up the GHz!
  
  Dual Dual-Core 2.8GHz -> 11.2 "effective" GHz
  Dual 3.8HGz -> 7.6 "effective" GHz
  
  It isn't as simple as that, but (and correct me if I'm wrong William!) our benchmarks seem to predict that to be pretty darn close.
  
  Of course, the CPU needs to be the bottleneck of whatever you're doing for the dual dual-cores to help, and as said above, you also need to make sure your applications are multi-threaded for best benefit.

  • A Like
  • Reply

  • 04/04/2006 03:18 AM
  • 0 Like
  • F
• 
  Rhinoman 1 comment collapsed Collapse Expand

  Sorry I misunderstood. I would still tend to take a simplistic view -- add up the GHz!
  
  Dual Dual-Core 2.8GHz -> 11.2 "effective" GHz
  Dual 3.8HGz -> 7.6 "effective" GHz
  
  It isn't as simple as that, but (and correct me if I'm wrong William!) our benchmarks seem to predict that to be pretty darn close.
  
  Of course, the CPU needs to be the bottleneck of whatever you're doing for the dual dual-cores to help, and as said above, you also need to make sure your applications are multi-threaded for best benefit.
  
  That is the problem! We have application that are multi-thread but also are very CPU intensive. Multi-threading helps you if you can split up the problem. But the shear GHz speed helps to finish the problem. We have
  some clients compare speeds with Dual-Core and the problem comes down to the speed of the CPU.

  • A Like
  • Reply

  • 04/04/2006 03:34 AM
  • 0 Like
  • F
• 
  PCC-William 2 comments collapsed Collapse Expand

  Rhinoman,
  
  Not to change the subject too much, but have you considered AMD processors? We have sold several dual socket dual-core Opteron rigs, and they perform marvelously well. And they come in almost the exact same clock speeds as the single-core line, so it is easy to look at benchmarks and see a direct comparison. Also, they scale up more easily than Xeons - you can get 4 or 8 socket dual-core configurations if you really need the extra horsepower. Just make sure that, if you go this way, you have 2 sticks of RAM for every physical cpu-socket (to ensure you get the most bandwidth available via dual-channel memory).

  • A Like
  • Reply

  • 04/04/2006 03:54 AM
  • 0 Like
  • F
• 
  cercle 1 comment collapsed Collapse Expand

  :confused:AMD,they use memory controler,and also real ! four core .Each core is connected to other's memory.Intel use a core of two plus another ,and no memory controler integrated to core.Until next version ,memory controler integrated,I look forward to a real four core,each able to use its total amount of memory,...20XX?:cool:

  • A Like
  • Reply

  • 08/05/2008 09:18 PM
  • in reply to PCC-William
  • 0 Like
  • F