Core 2 Duo (Conroe) the new king

[Fionavar]

Intels solution was the Itanium was it not?

 

Yes I believe you are correct. The problem is that Intel has yet to migrate well in performance winthin a 64-bit world. This was, imo, the reason/place the Opteron architecture displayed AMD was more than simply an enthusiast's market.

[alanschu]

I preferred AMD's approach as it would be easier to integrate 64-bit chips, as they still had excellent 32-bit support. Given the installed base of 32-bit architecture, it's not surprising it has not been a speedy transition to 64-bit.

[Bokishi]

Quad core is coming at the end of the year.

[angshuman]

Intels solution was the Itanium was it not?

Itanium was targeted at a very different market segment (although it may not have started life that way). The mid-range and high-end server market had been using 64-bit machines for ages: Sun Ultra SPARC, IBM P-series, DEC Alpha etc. Itanium was Intel/HP's attempt to play in this segment. Machines built around these processors usually had Multi-Chip Modules (in which each chip is sometimes multi-core e.g. IBM Power5), fancy interconnection networks (e.g. Alpha), huge caches (20-30MB is not uncommon on an Itanium system), loads of memory bandwidth, NUMA, etc. etc.

 

However, these servers were usually too expensive for small businesses. Therefore, Intel had always had a market for the Xeon line: relatively low-end 32-bit server parts. AMD was technically the first to step up the ante in this particular low-end server segment and introduce the Opteron as the first 64-bit x86 server processor. Intel's "reply" to this was the 64-bit Xeon, not the Itanium.

Edited August 3, 2006 by angshuman

[Alec]

Intels solution was the Itanium was it not?

<{POST_SNAPBACK}>

 

Wasn't Xeon the 64 bit Intel?

Yeah, but AMD started using only 64 bit CPU and dumped the 32 bit ones. Intel kept using 32 bit (even now) and kept 64 bit only for professional or business use, I think.

[alanschu]

Intels solution was the Itanium was it not?

Itanium was targeted at a very different market segment (although it may not have started life that way). The mid-range and high-end server market had been using 64-bit machines for ages: Sun Ultra SPARC, IBM P-series, DEC Alpha etc. Itanium was Intel/HP's attempt to play in this segment. Machines built around these processors usually had Multi-Chip Modules (in which each chip is sometimes multi-core e.g. IBM Power5), fancy interconnection networks (e.g. Alpha), huge caches (20-30MB is not uncommon on an Itanium system), loads of memory bandwidth, NUMA, etc. etc.

 

However, these servers were usually too expensive for small businesses. Therefore, Intel had always had a market for the Xeon line: relatively low-end 32-bit server parts. AMD was technically the first to step up the ante in this particular low-end server segment and introduce the Opteron as the first 64-bit x86 server processor. Intel's "reply" to this was the 64-bit Xeon, not the Itanium.

<{POST_SNAPBACK}>

 

I know the Itanium wasn't meant to compete with AMD's 64-bit solution. I was unaware that the Xeon was an attempt to "reply" to the Opteron though.

[angshuman]

For those among us that are planning to build a Conroe system, here's some useful information. It seems there are a bunch of ASUS P5W "Conroe-ready" motherboards in the market that aren't really Conroe ready since they have on older BIOS. If you already have a Pentium4 that you can plug in to flash the BIOS it's a non-issue, but if you are building a new Conroe system from scratch this may cause some headaches.

 

http://www.theinquirer.net/default.aspx?article=33523

[Diamond]

For those among us that are planning to build a Conroe system, here's some useful information. It seems there are a bunch of ASUS P5W "Conroe-ready" motherboards in the market that aren't really Conroe ready since they have on older BIOS. If you already have a Pentium4 that you can plug in to flash the BIOS it's a non-issue, but if you are building a new Conroe system from scratch this may cause some headaches.

 

http://www.theinquirer.net/default.aspx?article=33523

<{POST_SNAPBACK}>

Damn, where have you been earlier?

[Meshugger]

I'm glad that i don't plan to upgrade until later this fall.

[Gorth]

Quad core is coming at the end of the year.

Interesting

 

As someone whose last PC purchase is 3 years back and is considering a new PC within the next 12 months, can someone enlighten me what the difference is between dual processor, which is what I had in mind buying, and dual/quad core architecture (performance wise) ?

 

Seems like any computer you buy today has dual core cpus in them. Heck, even my laptop has a Centrino Duo cpu and 2gb memory in it

 

So, where do I get the most bang for my buck architecture wise, 2 cpus or multiple cores ? Will my old OS (Windows XP pro SR1) still run on say a quad core architecture ? Other pitfalls ? Should I wait more than 12 months before buying a new one

[angshuman]

Interesting 

 

As someone whose last PC purchase is 3 years back and is considering a new PC within the next 12 months, can someone enlighten me what the difference is between dual processor, which is what I had in mind buying, and dual/quad core architecture (performance wise) ?

 

Seems like any computer you buy today has dual core cpus in them. Heck, even my laptop has a Centrino Duo cpu and 2gb memory in it 

 

So, where do I get the most bang for my buck architecture wise, 2 cpus or multiple cores ? Will my old OS (Windows XP pro SR1) still run on say a quad core architecture ? Other pitfalls ? Should I wait more than 12 months before buying a new one

A "core" is essentially a full processor. Before the advent of multi-cores, if you wanted to have multiple processors in your system, one of the most popular options was Symmetric Multi-Processing (SMP), where you buy a motherboard with multiple sockets into which you can plug multiple physical chips, with each chip containing one processor and some cache memory. The chips would be connected to main memory via a system bus. Unfortunately, such configurations were primarily reserved for servers, and both multiple-socket motherboards as well as SMP-capable processors were (and still are) quite expensive.

 

Today's "multi-core" chips (formally called Chip Multi-Processors or CMP's) contain multiple processors (or "cores") and cache memories inside a single chip. The primary advantage to the end-user such as you and I is cost and simplicity. With a single-socket motherboard and at the price point of a single-chip system, you can get the performance of an SMP system. High-throughput servers can use CMP's with multi-socketed motherboards to create "SMP-of-CMP" systems.

 

As far as the Operating System and application softwares are concerned, there is very little difference between a dual-processor CMP ("dual-core") and a dual-processor SMP. There are performance issues, however.

• Communication Latency: On an SMP, the processors are physically separated over a large distance. On a CMP, they are much closer together, so communication latencies are much lower. However, Intel's original CMP implentations (Pentium D) were extremely hacked-up. Inter-processor communication first had to go off the chip, get onto the system bus and then re-enter the chip into the other core. This offset pretty much all of the performance benefits of a CMP. In fact, the second iteration of the Pentium D (Presler) was not a CMP at all - it was actually a multi-chip module (MCM): 2 distinct chips crammed into a single package and made to fit into a single Socket.
   
   
  
• Bandwidth: On a CMP, both cores have to share the same set of pins to get data on and off the chip to/from main memory. This could be devastating for bandwidth-intensive applications. In practice, there's not much of a difference between bandwidth contention of a CMP and an SMP on an antiquated Intel-style "shared-bus" platform, where both processors need to get onto the same bus to get to main memory regardless of whether they are on the same chip (CMP) or on multiple chips (SMP). AMD's Hyper Transport, however, is an entirely different animal. Multiple chips on an SMP will have access to a lot more bandwidth than multiple cores on a CMP. With both Intel and AMD planning to introduce Quad-Cores, my spider-sense tells me that bandwidth contention is likely to be a huge performance issue that is going to limit the peak performance of these systems.
   
   
  
• Cache Sharing: Local on-chip cache memory can be shared between the multiple cores of a CMP. This is extremely beneficial if the applications running on the different cores have different cache space requirements. This is impossible on an SMP. Unfortunately, this is also not exploited on either the Pentium D or the Athlon64 X2. The on-chip L2 caches are hard-partitioned between the two cores on both these processors. Conroe and Merom are the first CMPs to feature shared L2 caches, and this should have a significant impact on performance for some applications.
  

I believe that both AMD's HyperTransport as well as Intel's brain-damaged FSB have sufficient bandwidth to support dual cores. With 4 cores on a single chip, I'm not so sure. Intel's blazing Conroes will without doubt be gasping for data in quad-core form, unless you are dealing with an excellently-written application that manages to restrict a large part of its communication within the chip. AMD's platform probably has more room to play with, but the beauty of HyperTransport is lies in its scalability with multiple sockets, so if you have plenty of cash and want a lot of processors, it is better to go with more sockets than more cores-in-a-socket.

Edited August 10, 2006 by angshuman

[Gorth]

I believe that both AMD's HyperTransport as well as Intel's brain-damaged FSB have sufficient bandwidth to support dual cores. With 4 cores on a single chip, I'm not so sure. Intel's blazing Conroes will without doubt be gasping for data in quad-core form, unless you are dealing with an excellently-written application that manages to restrict a large part of its communication within the chip. AMD's platform probably has more room to play with, but the beauty of HyperTransport is lies in its scalability with multiple sockets, so if you have plenty of cash and want a lot of processors, it is better to go with more sockets than more cores-in-a-socket.

 

Thanks

 

Money is less an issue (within reason of course), so I might still keep an eye on SMP options when the time comes.

 

Yes, it's for hobby usage and no, it's not for gaming. At least, I've never heard of a game that could use dual processors...

[Delerius_Jedi]

Wow, these figures really do show that Intel has finally come around. One question, though; I'm building a Conroe system, but I'm on a budget and don't plan on overclocking, so I don't think I need the insanely highspeed Corsair memory.

 

What is the "normal" RAM to use with Conroe? DDR2-533?

[angshuman]

Corsair's "Value" range for has worked well for me (without overclocking, of course). I've only used DDR1, I don't know if they have an equivalent for DDR2. In general, you should be fine with brands like Corsair, Crucial, Kingston and OCZ. Take a look at the RAM timing numbers (e.g., 2-2-2-5) for the value-priced sticks from these brands, and buy the sticks with the lowest latencies that you can afford.

[LostStraw]

Unlike the previous Pentium 4 and Pentium D design, the Core 2 technology sees a greater benefit from memory running synchronous with the Front Side Bus (FSB). This means that for the Conroe CPUs with FSB of 1066Mhz (4x266Mhz) the ideal memory speed is PC2-4200. Using PC2-5300 actually decreases performance, only when going to PC2-6400 there is again a performance increase to be seen. While expensive DDR2 memory models with tighter timings do improve performance, the difference in real world games and applications is negligible

 

http://en.wikipedia.org/wiki/Intel_Core_2#Conroe

 

So, for not overclocking, DDR2-533 seems to be the best choice. Make sure to get a motherboard that supports 1066MHz QDR though, the 865PE chipset only supports 800MHz QDR for example.

 

Some conroe benchmarks with various kinds of memory:

http://www.madshrimps.be/?action=getarticle&articID=472

[mkreku]

A smart move would then be to wait for the second generation of motherboards from all the boardmakers, as their first tries seldom realize the potential in the new hardware.

<{POST_SNAPBACK}>

Patience, grasshoppers.

 

I read that Abit is soon releasing their new Intel-based Core 2 Duo compatible motherboards..

 

I think I will wait until early October before I settle for a motherboard. Hopefully, by then things will be clearer as to what the different manufacturers have to offer.

[SteveThaiBinh]

Well, I just ordered mine.

 

They're going like hotcakes over at Novatech. I would have liked to wait for the perfect motherboard, but I'll only be in the UK for a two week window in September and I want to get everything sorted out now. Besides, if I waited for the motherboard, I might end up waiting for a DirectX10 graphics card, and so on, and never actually buy the thing.

 

Reading the specifications for RAM is giving me a headache.

[metadigital]

My friend just bought a Core Duo x6700.

 

I told him that in 16 weeks (November) the new Core Duo Quad Cores will be out.

[Bokishi]

Quad Core FTW!

[kirottu]

There

[Bokishi]

Yes, 8 cores a year from now.

[alanschu]

Wow, if that isn't 8 times faster, I'll be surprised :D

[metadigital]

There