Core 2 Duo has been one of the most important launches for Intel in quite some time, really taking back the Desktop market by storm. Yet, even when I was in Germany at a pre-launch briefing of Conroe/Core 2 Duo, Intel suggested that quad core wasn't far off either. In fact, the computer being used for the PowerPoint presentation, was in fact Kentsfield – Intel's code name for its quad core processor. Not particuarly good use of resources, but an excellent demonstration of the state of play.
November has come around, and true to Intel's word, quad-core is here. It seems like only yesterday we were marvelling at the first dual-core solutions, so to have a “quad-core” processor in front of me, seems almost surreal. However, in actuality, this isn't as much of a technological feat as you might think. Eighty cores, as demonstrated at IDF
Intel has basically taken two Core 2 Duo dies and just put them in to one package. I think Intel realises that this is cheating a little and that's why the product name is Core 2 Extreme QX6700, which apart from the subtle “Q”, doesn't mention quad anywhere in the name. This is an Extreme Edition processor, so is naturally expensive, initially priced at $999. This isn't far off the current price of an Core 2 Extreme X6800 (£643), so in comparison, it's pretty good value.
Technically speaking, the fact the cores are in the same package is irrelevant. In order for data to be communicated between the two dies, the data needs to go through the North Bridge, via the Front Side Bus. Essentially, it means the performance will be identical to having two separate processors in two separate sockets.
Intel's approach does have its benefits though. For one, by having all four cores in the same package, there is only one heatsink. Any boards that currently support Core 2 Duo, will support Kentsfield as well. In saying that, we had to update the BIOS on our Gigabyte 965P motherboard, in order to get it to boot. It also makes designing a decent motherboard a lot easier and means we can expect to see quad-core hitting the MicroATX platform
Friday, February 6, 2009
Intel Core 2 Duo 'Conroe' E6400, E6600, E6700, X6800
Without a doubt, Core 2 Duo or "Conroe" as it is code-named has been one of the most anticipated product launches in the hardware community for quite some time. Everybody has been waiting to see if Intel can claim back the performance crown and push under the rug the disappointment that was the NetBurst architecture. The string of Pentium 4/NetBurst products that Intel released had so many faults that I won't embarrass Intel by listing them. Put simply, NetBurst never reached the potential Intel believed it was capable of. However, financially it did very well as Intel is incredibly good at marketing, while AMD seems happy to sit by as the underdog expecting PC enthusiasts to do all its advertising for it.
On a number of occasions I've had the opportunity to play with Pentium M on desktop motherboards and it has been the closest experience yet to re-creating my Mendocino Celeron A overclocking days. So naturally, I have been looking to Conroe with anticipation.
Conroe is nothing like any previous Pentium 4 products. In fact, it's based on the mobile Core Duo design which is in itself based on Pentium M, which is based on Pentium 3 architecture. So Intel has actually done a bit of a U-turn.
Compared to Pentium 4, Core Duo (not to be confused with Core 2 Duo) offers low power consumption, low waste heat and high performance per clock. This is almost an exact opposite to the Pentium 4 which used so much power that the ATX specification had to be modified to add more 12V rails, and produced so much heat that they often throttled and made reaching 4GHz almost impossible. Not only this, but clock for clock performance wasn't stellar – hence the need for higher clock speeds in the first place. The resultant disparity between AMDs and Intel's clock speed was one of the primary reasons for AMD introducing PR ratings (eg. 5000+) so that consumers didn't feel like they were getting a raw deal.
AMD's biggest selling point has been its on die memory controller. This has had a lot of knock on effects (such as almost identical performance from motherboard to motherboard), but the main effect is a huge reduction in memory latency as communication is no longer passed through the north bridge. This, in combination with HyperTransport reduced the bottleneck of the front side bus. Memory performance affects system performance significantly, so Intel processors were suffering in this area a lot.
Intel's solution to this is several minor improvements to the Core architecture in order to reduce this memory latency and increase overall system performance. Most of these optimisations are quite minor, but put together add up to more than the sum of their parts. Quite frankly, how Intel has improved their architecture so much is largely irrelevant - performance figures tell us all we need to know.
Possibly the biggest improvement is an added pipeline. Where as Core Duo can complete three instructions per cycle, Core 2 Duo can now complete four which an obvious increase in processing power and efficiency.
To help reduce bottlenecks, the front side bus has been increased to 1,066MHz from the 800Mhz that all but a few of the Extreme Edition processors used. This is at a base frequency of 266MHz, quad pumped.
If it wasn't completely obvious, the "Duo" portion of the name indicates that these are dual-core processors. Unlike previous Pentium D processors, these use a shared Level 2 cache (2MB or 4MB depending on the processor). This can be dynamically allocated depending on the task being run. For instance, if running an application that isn't multi-threaded (i.e. can't take advantage of a second core), then the primary core would get the full 4MB of Level 2 cache. Having more Level 2 cache means that fewer requests need to be made to the system memory – one of the biggest causes of latency.
On a number of occasions I've had the opportunity to play with Pentium M on desktop motherboards and it has been the closest experience yet to re-creating my Mendocino Celeron A overclocking days. So naturally, I have been looking to Conroe with anticipation.
Conroe is nothing like any previous Pentium 4 products. In fact, it's based on the mobile Core Duo design which is in itself based on Pentium M, which is based on Pentium 3 architecture. So Intel has actually done a bit of a U-turn.
Compared to Pentium 4, Core Duo (not to be confused with Core 2 Duo) offers low power consumption, low waste heat and high performance per clock. This is almost an exact opposite to the Pentium 4 which used so much power that the ATX specification had to be modified to add more 12V rails, and produced so much heat that they often throttled and made reaching 4GHz almost impossible. Not only this, but clock for clock performance wasn't stellar – hence the need for higher clock speeds in the first place. The resultant disparity between AMDs and Intel's clock speed was one of the primary reasons for AMD introducing PR ratings (eg. 5000+) so that consumers didn't feel like they were getting a raw deal.
AMD's biggest selling point has been its on die memory controller. This has had a lot of knock on effects (such as almost identical performance from motherboard to motherboard), but the main effect is a huge reduction in memory latency as communication is no longer passed through the north bridge. This, in combination with HyperTransport reduced the bottleneck of the front side bus. Memory performance affects system performance significantly, so Intel processors were suffering in this area a lot.
Intel's solution to this is several minor improvements to the Core architecture in order to reduce this memory latency and increase overall system performance. Most of these optimisations are quite minor, but put together add up to more than the sum of their parts. Quite frankly, how Intel has improved their architecture so much is largely irrelevant - performance figures tell us all we need to know.
Possibly the biggest improvement is an added pipeline. Where as Core Duo can complete three instructions per cycle, Core 2 Duo can now complete four which an obvious increase in processing power and efficiency.
To help reduce bottlenecks, the front side bus has been increased to 1,066MHz from the 800Mhz that all but a few of the Extreme Edition processors used. This is at a base frequency of 266MHz, quad pumped.
If it wasn't completely obvious, the "Duo" portion of the name indicates that these are dual-core processors. Unlike previous Pentium D processors, these use a shared Level 2 cache (2MB or 4MB depending on the processor). This can be dynamically allocated depending on the task being run. For instance, if running an application that isn't multi-threaded (i.e. can't take advantage of a second core), then the primary core would get the full 4MB of Level 2 cache. Having more Level 2 cache means that fewer requests need to be made to the system memory – one of the biggest causes of latency.
Intel Core 2 Duo Mobile Processor Review - T7600
A month ago we showed you exclusive testing results (here) of the new Intel Core 2 Duo T7400 “Merom†CPU . While those initial results showed good improvements in floating point operation, a quick test revealed that battery life (here) showed that our testing platform was still not ready for prime time as the T7400 should have battery performance by design.
The Core 2 Duo T7600 we are looking at today is a production sample (read: very likely the same quality and performance you will get at a retailer) clocked at 2.33 GHz, slightly faster than the 2.16 GHz on the T7400 sample we tested a month ago. And what a difference a month makes! Intel has made the improvements where it counts -- lower power consumption which translates into better battery life!
Intel has done it! While in our early look at the T7400 showed rather poor battery performance the T7600 we have tested today, which is heading into production, has made drastic improvements. We can now say without a doubt that Intel's latest mobile CPU has nailed the holy grail in mobile computing - it performs faster, consumes less power, and generates less heat. What else is there to say besides that?
Now with power and heat issues all sorted out, there's no reason why you shouldn't consider the Core 2 Duo in your next laptop. With price points as low as $209 for the T5500 up to the T7600 at $637, there’s a Core 2 Duo mobile CPU to suit all budgets and designs. It really looks like Intel has another hit CPU on their hands and with all the design innovations from laptop vendors, it's hard not to be a little excited when looking forward. It's definitely a good time to be looking into a notebook computer and Intel has given us many reasons to with their Core 2 Duo CPUs!
So in the end, we're giving this CPU an Editor's Choice Award. The latest Core 2 Duo mobile CPU is cooler, faster, and runs longer than the older Core Duo. Not only that, it has technology improvements under the hood like a larger level 2 cache (4MB) and 64-bit extensions to support 64-bit OSes like the upcoming Windows Vista. If you've had reservations before about getting a laptop, the Core 2 Duo should have you convinced. Intel's track record in this arena is strong, and their latest CPU just solidifies their lead.
The Core 2 Duo T7600 we are looking at today is a production sample (read: very likely the same quality and performance you will get at a retailer) clocked at 2.33 GHz, slightly faster than the 2.16 GHz on the T7400 sample we tested a month ago. And what a difference a month makes! Intel has made the improvements where it counts -- lower power consumption which translates into better battery life!
Intel has done it! While in our early look at the T7400 showed rather poor battery performance the T7600 we have tested today, which is heading into production, has made drastic improvements. We can now say without a doubt that Intel's latest mobile CPU has nailed the holy grail in mobile computing - it performs faster, consumes less power, and generates less heat. What else is there to say besides that?
Now with power and heat issues all sorted out, there's no reason why you shouldn't consider the Core 2 Duo in your next laptop. With price points as low as $209 for the T5500 up to the T7600 at $637, there’s a Core 2 Duo mobile CPU to suit all budgets and designs. It really looks like Intel has another hit CPU on their hands and with all the design innovations from laptop vendors, it's hard not to be a little excited when looking forward. It's definitely a good time to be looking into a notebook computer and Intel has given us many reasons to with their Core 2 Duo CPUs!
So in the end, we're giving this CPU an Editor's Choice Award. The latest Core 2 Duo mobile CPU is cooler, faster, and runs longer than the older Core Duo. Not only that, it has technology improvements under the hood like a larger level 2 cache (4MB) and 64-bit extensions to support 64-bit OSes like the upcoming Windows Vista. If you've had reservations before about getting a laptop, the Core 2 Duo should have you convinced. Intel's track record in this arena is strong, and their latest CPU just solidifies their lead.
Intel Conroe Core 2 Duo/Extreme Processors
Intel's new Core 2 architecture builds on the foundations laid down by the Core micro-architecture which debuted on Intel's current range of dual-core mobile CPUs. Again, those unfamiliar to the new terminology may know them as Yonah.
Let's be clear about this. Intel, by moving away from NetBurst and the ultra-high clockspeeds required for the Pentium 4 series to be competitive against AMD's Athlon 64 series, has decided that a new micro-architecture was required that would provide both excellent performance and be energy-efficient, too. That, then, spelt an end to the Pentium 4 as Intel's consumer CPU of choice. It's still around, of course, but Core 2 Duo/Extreme is now positioned as Intel's performance CPU.
The following table details the range of Core 2-based CPUs Intel will be offering right off the bat, along with a Pentium Extreme Edition 965 and Athlon 64 FX-62 for reference. We'll then discuss the reasons behind why Core 2 is destined to give AMD a very hard time.
Models
Intel is initially launching Core 2 Duo at a starting speed-grade of 1.83GHz. This model, designated E6300, will be equipped with 2MiB of L2 cache and falls under the codename of Allendale. We expect Intel to release a lower-clocked version in the near future. Other than a lower clock speed and 2MiB L2 cache, the E6300 is, for all intents and purposes, architecturally identical to the rest of the Duo range; it's no Celeron model. That's especially gratifying with respect to its relatively low price.
The range is headlined by the Intel Core 2 Extreme X6800, which operates at 2.93GHz and, like Extreme Editions before, is multiplier-unlocked. Deep-walleted enthusiasts will have some fun with this one.
Let's digest the information above, particularly the architectural elements, with some insightful commentary.
Architecture analysis
Here's what makes the Core 2 Duo tick, folks.
Dual-core support
Intel Core 2 Duo-based CPUs will harness two execution cores based on a single piece of silicon. The cores communicate with the rest of the system via a single bus, which will be clocked in at 1066MHz and offer around 8.5GB/s CPU-to-MCH bandwidth. Initial Core 2 Duo CPUs will be manufactured on Intel's proven 65nm process. Projections state that 45nm production will begin in Q2 2007. Core 2 Duo supports a 14-stage execution pipeline, down (read better) from the 31 present on the Prescott-based Pentium 4.
Wide Dynamic Execution
Current x86 processors can deliver 3 instructions per clock cycle. Core 2 Duo, however, has been architected to fetch, dispatch, execute and retire up to four full instructions simultaneously, offering a 33% boost over, say, a Pentium 4 CPU. Allied to this, Core 2 Duo also supports what Intel terms Macro-Fusion, which can combine certain common x86 instructions (pairs, say, compare and conditional jump) into a single instruction (micro-op) for execution, thereby reducing overall processing time. Processing efficiency is the name of the game here.
Intel Smart Memory Access and Advanced Smart Cache
Higher-end Core 2 Duo CPUs will be equipped with 4MiB of on-chip L2 cache, minimising the need to run back to system memory for frequently used data. Unlike the present Pentium 4 micro-architecture, Core 2 Duo's two cores will share the cache amongst each other. Intel's engineering team has found that forcing the cores to individually allocate and use cache is more efficient than allotting a fixed, per-core amount. By varying the amount of cache split over the two cores Intel hopes that cache misses, the bane of modern CPUs in terms of execution efficiency, will be further reduced.
Core 2 Duo also supports what Intel terms Smart Memory Access. Put simply, and falling under the banner of memory disambiguation, it's a form of out-of-order, built-in intelligence that predicts and loads the upcoming instruction data before current store instructions have been processed. Intel has designed algorithms that can accurately predict whether a load can be processed before the store, thereby, again, potentially saving overall execution time.
Coupled with a heavily optimised cache, and thinking about it how it all fits together, the Core 2 Duo's memory access latency will be better than the present Pentium 4's, for the reasons discussed above. Intel has toyed with the idea of integrating a memory controller right on the CPU die itself, a la AMD, but reckons that Core 2 Duo's intelligent architecture masks latency well enough for it to do without. We'll put this assertion to the test in our ScienceMark 2.0 memory latency analysis.
Advanced Media Boost
Increasing efficiency with Streaming SIMD (Single Instruction Multiple Data) Extentions, Core 2 Duo CPUs are able to process a 128-bit instruction in a single clock cycle, rather than requiring the incumbent two clocks that current generations employ.
Intelligent Power Capability
Intel has designed Core 2 Duo not only to perform well on a clock-for-clock basis but also to be energy-efficient whilst doing so. This is precisely where its mobile heritage shines through. Intelligent, which seems to be the watchword for Core 2 Duo, management monitors core usage and application requirements such that it can power-gate parts of the CPU when not in use; there's little need for two cores running at full power in single-threaded applications, for example. Intel reckons that it has improved the physical requirements of power-gating enough for it to offer better power consumption than previous generations'.
Intel indicates that all Core 2 Duo models (barring Extreme) will harness a 65W TDP; half that of the Pentium Extreme Edition 965 CPU. The Core 2 Duo Extreme, however, ships with a slightly higher 75W TDP.
Further, Conroe will ship with an integrated digital thermal sensor. The sensor is embedded on the die itself and will give more-accurate readings. Incidentally, the 965 Express chipset family supports Intel Quiet System Technology, which intelligently manages processor and system fan-speeds in relation to core temperature, ensuring the fan(s) are spun just fast enough to keep the processor from throttling.
Virtualisation Technology, 64-bit processing
Virtualisation Technology offers hardware-isolated virtual partitions that allow the user to run multiple operating systems on one PC, and 64-bit processing (EMT64), along with Execute Disable Bit, is carried over from the Pentium 4 line of CPUs.
Let's be clear about this. Intel, by moving away from NetBurst and the ultra-high clockspeeds required for the Pentium 4 series to be competitive against AMD's Athlon 64 series, has decided that a new micro-architecture was required that would provide both excellent performance and be energy-efficient, too. That, then, spelt an end to the Pentium 4 as Intel's consumer CPU of choice. It's still around, of course, but Core 2 Duo/Extreme is now positioned as Intel's performance CPU.
The following table details the range of Core 2-based CPUs Intel will be offering right off the bat, along with a Pentium Extreme Edition 965 and Athlon 64 FX-62 for reference. We'll then discuss the reasons behind why Core 2 is destined to give AMD a very hard time.
Models
Intel is initially launching Core 2 Duo at a starting speed-grade of 1.83GHz. This model, designated E6300, will be equipped with 2MiB of L2 cache and falls under the codename of Allendale. We expect Intel to release a lower-clocked version in the near future. Other than a lower clock speed and 2MiB L2 cache, the E6300 is, for all intents and purposes, architecturally identical to the rest of the Duo range; it's no Celeron model. That's especially gratifying with respect to its relatively low price.
The range is headlined by the Intel Core 2 Extreme X6800, which operates at 2.93GHz and, like Extreme Editions before, is multiplier-unlocked. Deep-walleted enthusiasts will have some fun with this one.
Let's digest the information above, particularly the architectural elements, with some insightful commentary.
Architecture analysis
Here's what makes the Core 2 Duo tick, folks.
Dual-core support
Intel Core 2 Duo-based CPUs will harness two execution cores based on a single piece of silicon. The cores communicate with the rest of the system via a single bus, which will be clocked in at 1066MHz and offer around 8.5GB/s CPU-to-MCH bandwidth. Initial Core 2 Duo CPUs will be manufactured on Intel's proven 65nm process. Projections state that 45nm production will begin in Q2 2007. Core 2 Duo supports a 14-stage execution pipeline, down (read better) from the 31 present on the Prescott-based Pentium 4.
Wide Dynamic Execution
Current x86 processors can deliver 3 instructions per clock cycle. Core 2 Duo, however, has been architected to fetch, dispatch, execute and retire up to four full instructions simultaneously, offering a 33% boost over, say, a Pentium 4 CPU. Allied to this, Core 2 Duo also supports what Intel terms Macro-Fusion, which can combine certain common x86 instructions (pairs, say, compare and conditional jump) into a single instruction (micro-op) for execution, thereby reducing overall processing time. Processing efficiency is the name of the game here.
Intel Smart Memory Access and Advanced Smart Cache
Higher-end Core 2 Duo CPUs will be equipped with 4MiB of on-chip L2 cache, minimising the need to run back to system memory for frequently used data. Unlike the present Pentium 4 micro-architecture, Core 2 Duo's two cores will share the cache amongst each other. Intel's engineering team has found that forcing the cores to individually allocate and use cache is more efficient than allotting a fixed, per-core amount. By varying the amount of cache split over the two cores Intel hopes that cache misses, the bane of modern CPUs in terms of execution efficiency, will be further reduced.
Core 2 Duo also supports what Intel terms Smart Memory Access. Put simply, and falling under the banner of memory disambiguation, it's a form of out-of-order, built-in intelligence that predicts and loads the upcoming instruction data before current store instructions have been processed. Intel has designed algorithms that can accurately predict whether a load can be processed before the store, thereby, again, potentially saving overall execution time.
Coupled with a heavily optimised cache, and thinking about it how it all fits together, the Core 2 Duo's memory access latency will be better than the present Pentium 4's, for the reasons discussed above. Intel has toyed with the idea of integrating a memory controller right on the CPU die itself, a la AMD, but reckons that Core 2 Duo's intelligent architecture masks latency well enough for it to do without. We'll put this assertion to the test in our ScienceMark 2.0 memory latency analysis.
Advanced Media Boost
Increasing efficiency with Streaming SIMD (Single Instruction Multiple Data) Extentions, Core 2 Duo CPUs are able to process a 128-bit instruction in a single clock cycle, rather than requiring the incumbent two clocks that current generations employ.
Intelligent Power Capability
Intel has designed Core 2 Duo not only to perform well on a clock-for-clock basis but also to be energy-efficient whilst doing so. This is precisely where its mobile heritage shines through. Intelligent, which seems to be the watchword for Core 2 Duo, management monitors core usage and application requirements such that it can power-gate parts of the CPU when not in use; there's little need for two cores running at full power in single-threaded applications, for example. Intel reckons that it has improved the physical requirements of power-gating enough for it to offer better power consumption than previous generations'.
Intel indicates that all Core 2 Duo models (barring Extreme) will harness a 65W TDP; half that of the Pentium Extreme Edition 965 CPU. The Core 2 Duo Extreme, however, ships with a slightly higher 75W TDP.
Further, Conroe will ship with an integrated digital thermal sensor. The sensor is embedded on the die itself and will give more-accurate readings. Incidentally, the 965 Express chipset family supports Intel Quiet System Technology, which intelligently manages processor and system fan-speeds in relation to core temperature, ensuring the fan(s) are spun just fast enough to keep the processor from throttling.
Virtualisation Technology, 64-bit processing
Virtualisation Technology offers hardware-isolated virtual partitions that allow the user to run multiple operating systems on one PC, and 64-bit processing (EMT64), along with Execute Disable Bit, is carried over from the Pentium 4 line of CPUs.
Intel Core 2 (Conroe) Performance Review
It has finally happened, Intel will be putting to rest the long standing Pentium branding for their next generation of desktop microprocessors in favor of a totally new line-up simply called Core. However, this isn't just a re-branding exercise for Intel. The Core processors mark Intel's first true major revamp of microprocessor technology since their launch of the NetBurst microarchitecture with the Willamette core Pentium 4 back in the year 2000 and before you know it, we're already at Core 2. Now we're getting ahead of ourselves. Considering the major gear shift at Intel to bring about this day, let's take a brief recap on the chain of events that have lead to the development of the new Core processors.
AMD's sharp rise in market share from their hugely successful Athlon XP, Athlon 64 and dual-core Athlon 64 X2 processors in the past two years has been a rude awakening for Intel. AMD was even making inroads into the server market with their Opteron products and went as bold as to openly challenge Intel's dual-core Xeon on both performance and power consumption fronts in 2005 - a challenge which Intel chose to ignore resulting in defacto bragging rights for AMD for a period of time.
Intel of course has not been sitting idle all this while and we've seen a huge effort in promoting their next generation microarchitecture over the past year, which was basically Intel telling the world 'Wait and see, we'll be back and then we will rock!'. Intel officially unveiled the revolutionary Core microarchitecture early this year at IDF Spring 2006 in San Francisco and wet our lips with a preview of the enhanced power saving features (if not the performance) with the launch of the Core Duo (codenamed Yonah) dual-core mobile processor.
AMD's sharp rise in market share from their hugely successful Athlon XP, Athlon 64 and dual-core Athlon 64 X2 processors in the past two years has been a rude awakening for Intel. AMD was even making inroads into the server market with their Opteron products and went as bold as to openly challenge Intel's dual-core Xeon on both performance and power consumption fronts in 2005 - a challenge which Intel chose to ignore resulting in defacto bragging rights for AMD for a period of time.
Intel of course has not been sitting idle all this while and we've seen a huge effort in promoting their next generation microarchitecture over the past year, which was basically Intel telling the world 'Wait and see, we'll be back and then we will rock!'. Intel officially unveiled the revolutionary Core microarchitecture early this year at IDF Spring 2006 in San Francisco and wet our lips with a preview of the enhanced power saving features (if not the performance) with the launch of the Core Duo (codenamed Yonah) dual-core mobile processor.
Intel Core 2 Duo, 2.40 GHz E6600
Intel's launch of the Core 2 Duo has come and gone, and now, for the most part, the entire range of speeds are available in stores (the 4 big ones of course - Newegg, mWave, ZZF, and TigerDirect). Availability still seems a bit scarce at this moment, and prices will range so shop around. Of course, Intel will likely come up with product in no time, as they are known to do after launching new processors (just don't ask them to do the same with chipsets! But that's for another story).
If you're wondering why this review is late - well there are a few reasons really. First of all, Intel actually pulled back Core 2 Duo from its original release date of July 27th, I guess to get the jump on AMD's planned price drops. So really we're not that far off the original release date ;)
We also had to put together an AMD test system ourselves, because AMD often has problems producing enough CPU's to meet the demands of OEM, retail, and media. I set out to put together the fastest AM2 system I could buy today (ridiculously expensive FX chips notwithstanding). That ended up being an Athlon64 X2 4600+. That's right - the 5000+ and 4800+ parts were nowhere to be seen, even though they launched last May. The retail channel is just starting to get 4800+'s in stock, so the 5000+'s can't be far behind. To round out our AMD system, we went with an Asus motherboard based on NVIDIA's 570 Ultra chipset. Unfortunately I ended up buying my X2 just before the price drops occured... So I paid about $550 USD, while they are now going for around $255-260. Ugh.
Finally, I had major issues with the beta BIOS on the Intel test motherboard. For some reason, the board would no longer POST either of the Core 2 processors after having a Pentium-D installed in it. No matter what I tried, it wouldn't do it. I only had one option - wait for Core 2 to officially launch, and use a production BIOS. Finally, all testing is complete, and I'm ready to report about Core 2 Duo and Core 2 Extreme.
The codenames for the new desktop parts are "Conroe" "Conroe XE" and the lesser-known "Allendale". For the retail market, they are called "Core 2 Duo" and "Core 2 Extreme", even though this is actually their first CPU based on Core, desktop or otherwise.
Conroe and Allendale are identical, except Allendale comes with half the amount of L2 cache - 2MB instead of 4MB. Conroe XE is identical to Conroe, except that it has an unlocked multiplier.
The two Allendale based processors are the E6300, which runs at 1.86 GHz, and the E6400, which runs at 2.13 GHz. The Conroe parts are the E6600 and E6700 which run at 2.40 GHz and 2.67 GHz respectively. Finally, there is the Conroe XE based Core 2 Extreme, which is identical to all other Conroe processors in every way - it's just clocked higher and has an unlocked multiplier. The top Core 2 Extreme (and Intel's top processor of all) is the X6800, which runs at 2.93 GHz.
All of the aforementioned processors run on a quad-pumped 1066 MHz FSB.
The mobile part is codenamed "Merom" and was quietly launched alongside Conroe. It too is called "Core 2 Duo" and "Core 2 Solo" in retail; frontside bus is limited to 667 MHz on these low power-using parts, rather than 1066 MHz. Confused? No kidding.
If you're wondering why this review is late - well there are a few reasons really. First of all, Intel actually pulled back Core 2 Duo from its original release date of July 27th, I guess to get the jump on AMD's planned price drops. So really we're not that far off the original release date ;)
We also had to put together an AMD test system ourselves, because AMD often has problems producing enough CPU's to meet the demands of OEM, retail, and media. I set out to put together the fastest AM2 system I could buy today (ridiculously expensive FX chips notwithstanding). That ended up being an Athlon64 X2 4600+. That's right - the 5000+ and 4800+ parts were nowhere to be seen, even though they launched last May. The retail channel is just starting to get 4800+'s in stock, so the 5000+'s can't be far behind. To round out our AMD system, we went with an Asus motherboard based on NVIDIA's 570 Ultra chipset. Unfortunately I ended up buying my X2 just before the price drops occured... So I paid about $550 USD, while they are now going for around $255-260. Ugh.
Finally, I had major issues with the beta BIOS on the Intel test motherboard. For some reason, the board would no longer POST either of the Core 2 processors after having a Pentium-D installed in it. No matter what I tried, it wouldn't do it. I only had one option - wait for Core 2 to officially launch, and use a production BIOS. Finally, all testing is complete, and I'm ready to report about Core 2 Duo and Core 2 Extreme.
The codenames for the new desktop parts are "Conroe" "Conroe XE" and the lesser-known "Allendale". For the retail market, they are called "Core 2 Duo" and "Core 2 Extreme", even though this is actually their first CPU based on Core, desktop or otherwise.
Conroe and Allendale are identical, except Allendale comes with half the amount of L2 cache - 2MB instead of 4MB. Conroe XE is identical to Conroe, except that it has an unlocked multiplier.
The two Allendale based processors are the E6300, which runs at 1.86 GHz, and the E6400, which runs at 2.13 GHz. The Conroe parts are the E6600 and E6700 which run at 2.40 GHz and 2.67 GHz respectively. Finally, there is the Conroe XE based Core 2 Extreme, which is identical to all other Conroe processors in every way - it's just clocked higher and has an unlocked multiplier. The top Core 2 Extreme (and Intel's top processor of all) is the X6800, which runs at 2.93 GHz.
All of the aforementioned processors run on a quad-pumped 1066 MHz FSB.
The mobile part is codenamed "Merom" and was quietly launched alongside Conroe. It too is called "Core 2 Duo" and "Core 2 Solo" in retail; frontside bus is limited to 667 MHz on these low power-using parts, rather than 1066 MHz. Confused? No kidding.
Intel Core 2 Extreme QX6700 - Quad-Core Power for Desktops
Intel's Core 2 Duo processor family bearing the new Core microarchitecture broke new grounds when it was launched a scant four months ago, catapulting Intel back into the driver's seat of the microprocessor industry, a 'show hand' that arch-rival AMD has yet to deliver a response till date. Despite the rave journalistic buzz however, the Core 2 Duo is still a dual-core processor and dual-core processors themselves aren't anything new (Intel's Pentium D and AMD's Athlon 64 X2 have been around since early 2005), not to mention that three and a half months is hardly enough time for the Core 2 Duo to really penetrate the retail channels.
The news that have been most anticipated within tech circles however, has been the talk of Intel's upcoming quad-core part, codenamed Kentsfield. During the recent IDF Fall 2006, Intel confirmed the launch and we were even given the opportunity for a hands-on performance preview, which you can check out here . Today, Kentsfield becomes official. Quad-core processing has indeed arrived in the consumer space as Intel increases its leadership position even more.
The official name of the Kentsfield series will be Core 2 Quad in the mainstream segment and the Core 2 Extreme in the enthusiast segment. The first Kentsfield processor to be available at launch will start with the top-end 2.66GHz Core 2 Extreme QX6700 priced at US$999, which is the same as the 2.93GHz Core 2 Extreme X6800 during its launch. The QX6700 will be followed by the mainstream 2.4GHz Core 2 Quad Q6600, tentatively set to be released first quarter of 2007 and rumored to be priced around US$851. Whether the corresponding Core 2 Duo processors will receive price cuts remain to be seen as nothing has been announced yet.
This naming convention is based on the fact that the Kentsfield processors are in the same generation as the dual-core Conroe and Allendale - hence, 'Core 2' designates the processor series and the 'Duo' or 'Quad' suffix designating the number of cores. What may be initially confusing however is that both Conroe and Kentsfield enthusiast parts will be named Core 2 Extreme. For these processors, the CPU model numbers give away its pedigree. Those with a 'Q' prefix are quad-core models, eg. Core 2 Extreme QX6700
The news that have been most anticipated within tech circles however, has been the talk of Intel's upcoming quad-core part, codenamed Kentsfield. During the recent IDF Fall 2006, Intel confirmed the launch and we were even given the opportunity for a hands-on performance preview, which you can check out here . Today, Kentsfield becomes official. Quad-core processing has indeed arrived in the consumer space as Intel increases its leadership position even more.
The official name of the Kentsfield series will be Core 2 Quad in the mainstream segment and the Core 2 Extreme in the enthusiast segment. The first Kentsfield processor to be available at launch will start with the top-end 2.66GHz Core 2 Extreme QX6700 priced at US$999, which is the same as the 2.93GHz Core 2 Extreme X6800 during its launch. The QX6700 will be followed by the mainstream 2.4GHz Core 2 Quad Q6600, tentatively set to be released first quarter of 2007 and rumored to be priced around US$851. Whether the corresponding Core 2 Duo processors will receive price cuts remain to be seen as nothing has been announced yet.
This naming convention is based on the fact that the Kentsfield processors are in the same generation as the dual-core Conroe and Allendale - hence, 'Core 2' designates the processor series and the 'Duo' or 'Quad' suffix designating the number of cores. What may be initially confusing however is that both Conroe and Kentsfield enthusiast parts will be named Core 2 Extreme. For these processors, the CPU model numbers give away its pedigree. Those with a 'Q' prefix are quad-core models, eg. Core 2 Extreme QX6700
Intel Core 2 Duo Merom Notebooks
Every few months computer technology moves forward. Usually it’s only a small jump, such as a latest iteration of a graphics architecture, but sometimes it’s a significant one, such as the recent introduction of Intel’s Core 2 Duo desktop processor, known internally by Intel as Conroe.
Conroe’s arrival was very important as it represented the first time that Intel had brought the fruits of its new ‘Performance per Watt’ architecture direction to the desktop. Intel has been moving in this direction for some time, ever since it realised that even as its ‘NetBurst’ Pentium 4 architecture was running out of steam, its Pentium M ‘Banias’ mobile chip was going great guns.
As such it turned to the Banias design team, based in Haifa, Israel, to create an architecture that was efficient and able to scale, qualities that Pentium 4 did not possess. Last year, I was lucky enough to be taken on a press tour of Intel in Israel, and met some of the team responsible for Banias, Dothan and Yonah. It was clear then that all of these were leading up to the processor released today, known then only as Merom. Though it was the last to appear on the market, Merom is actually the processor on which its desktop and workstation counterparts, Conroe (Core 2 Duo) and Woodcrest (Xeon) are based.
This design architecture, which Spode talked about here is known as the Core architecture. Rather confusingly though, Core Duo, which is Yonah, is not actually Core architecture – it’s was essentially a dual-core version of Pentium M.
Core architecture, with its various improvements and enhancements, actually begins with the Core 2 Duo, which in Conroe guise, has already appeared on the desktop.
The reason for this is that Intel previous mobile chip, Yonah or Core Duo was so good that it didn’t need to rush it to market. However, Intel definitely needed to bring Conroe to the market as for a long time been lagging behind AMD.
So how does the mobile version of Core 2 Duo (Merom) actually differ from the desktop version (Conroe)? Actually, the differences are relatively minor – though as it’s essentially the same chip that’s not really surprising. This means that it sports all the excellent features that made Conroe so powerful. This includes the Wide Dynamic Execution consisting of an increase in pipelines from three to four and the use of the Macro-Fusion technique that combines common pairs of instructions into a single instruction. Perhaps most crucially Merom employs all of the power management saving tricks that the Core architecture is designed for, such as putting many parts of the CPU to sleep when they’re not required. This enables it to have a lower Thermal Design Power (TDP) figure of 34W, compared to 65W for Conroe, which is the essential figure for a mobile CPU. Other differences are that Merom runs at a lower Front Side Bus of 667MHz, (versus 1,066MHz).
Conroe’s arrival was very important as it represented the first time that Intel had brought the fruits of its new ‘Performance per Watt’ architecture direction to the desktop. Intel has been moving in this direction for some time, ever since it realised that even as its ‘NetBurst’ Pentium 4 architecture was running out of steam, its Pentium M ‘Banias’ mobile chip was going great guns.
As such it turned to the Banias design team, based in Haifa, Israel, to create an architecture that was efficient and able to scale, qualities that Pentium 4 did not possess. Last year, I was lucky enough to be taken on a press tour of Intel in Israel, and met some of the team responsible for Banias, Dothan and Yonah. It was clear then that all of these were leading up to the processor released today, known then only as Merom. Though it was the last to appear on the market, Merom is actually the processor on which its desktop and workstation counterparts, Conroe (Core 2 Duo) and Woodcrest (Xeon) are based.
This design architecture, which Spode talked about here is known as the Core architecture. Rather confusingly though, Core Duo, which is Yonah, is not actually Core architecture – it’s was essentially a dual-core version of Pentium M.
Core architecture, with its various improvements and enhancements, actually begins with the Core 2 Duo, which in Conroe guise, has already appeared on the desktop.
The reason for this is that Intel previous mobile chip, Yonah or Core Duo was so good that it didn’t need to rush it to market. However, Intel definitely needed to bring Conroe to the market as for a long time been lagging behind AMD.
So how does the mobile version of Core 2 Duo (Merom) actually differ from the desktop version (Conroe)? Actually, the differences are relatively minor – though as it’s essentially the same chip that’s not really surprising. This means that it sports all the excellent features that made Conroe so powerful. This includes the Wide Dynamic Execution consisting of an increase in pipelines from three to four and the use of the Macro-Fusion technique that combines common pairs of instructions into a single instruction. Perhaps most crucially Merom employs all of the power management saving tricks that the Core architecture is designed for, such as putting many parts of the CPU to sleep when they’re not required. This enables it to have a lower Thermal Design Power (TDP) figure of 34W, compared to 65W for Conroe, which is the essential figure for a mobile CPU. Other differences are that Merom runs at a lower Front Side Bus of 667MHz, (versus 1,066MHz).
Intel Tips Its 3G Processor Strategy
CANNES, France - Intel Corp. disclosed details of its next-generation communications processor strategy, code-named Hermon, which is targeted at single- and dual-mode wideband CDMA phones.
Intel executives said Wednesday (Feb. 25) at the 3GSM World Congress here that the single-chip device incorporates an XScale MSA architecture processor, on-chip StrataFlash memory, W-CDMA and GPRS baseband logic on a 0.13-micron process.
Intel plans to announce full details of the product in the next six months, and expects both mass-market cellphones and smartphones to appear by 2005. Reference designs based on Hermon are expected by the end of the year.
"The fully scalable system-on-chip device incorporates a number of key mobile technologies, such as our Quick Capture and Clear Connect solutions, which will allow handsets to track multiple basestations, thus leading to fewer dropped calls, yet draws on our existing XScale communications processor," said Gadi Singer, vice president and co-general manager of Intel's cellular and hand held group.
The 3G platform will use TTPCom's protocol and applications software, extending the relationship between the companies on GSM/GPRS designs. The first customer for the new communications processor is expected to be Taiwanese group Asustek, which is developing a range of smartphones based on Hermon and Intel's Bulverde applications processor.
Singer said Bulverde has been sampled by numerous phone designers, some who will be introducing devices by the end of 2004. He would not say whether any are top mobile phone manufacturers.
Paul Otellini, Intel's president and COO, hinted at Hermon development during a keynote address here. He did unveil a three-radio reference design for cellphones offering 802.11b, Bluetooth and GSM/GPRS capabilities. It will run on the latest version of the Bulverde applications processor, wireless MMX and an XScale communications processor. The phone will support leading operating systems, including Microsoft, Symbian, Linux, Java and PalmOS.
It will also play MP3 music files with PC-quality sound, and incorporates a 1.3-megapixel digital camera.
Otellini reiterated Intel's commitment to the wireless broadband, particularly emerging WiMax technology, and said the company will have silicon for the expanded wireless network by the end of the year. Basestations and customer premises equipment are expected to be available by the middle of 2005.
He also forecast in a glitzy demononstation here that WiMax capability would be built into notebook computers by 2006, followed by handsets by 2007. The huge bandwidth increase provided by WiMax, compared to Wi-Fi, over much greater distances could set up a battle with operators of 3G networks.
Intel's mantra remains that "the wireless industry is evolving from a web of independent networks into a single, integrated wireless network with multiple standards, where no single standard will be sufficient."
Intel executives said Wednesday (Feb. 25) at the 3GSM World Congress here that the single-chip device incorporates an XScale MSA architecture processor, on-chip StrataFlash memory, W-CDMA and GPRS baseband logic on a 0.13-micron process.
Intel plans to announce full details of the product in the next six months, and expects both mass-market cellphones and smartphones to appear by 2005. Reference designs based on Hermon are expected by the end of the year.
"The fully scalable system-on-chip device incorporates a number of key mobile technologies, such as our Quick Capture and Clear Connect solutions, which will allow handsets to track multiple basestations, thus leading to fewer dropped calls, yet draws on our existing XScale communications processor," said Gadi Singer, vice president and co-general manager of Intel's cellular and hand held group.
The 3G platform will use TTPCom's protocol and applications software, extending the relationship between the companies on GSM/GPRS designs. The first customer for the new communications processor is expected to be Taiwanese group Asustek, which is developing a range of smartphones based on Hermon and Intel's Bulverde applications processor.
Singer said Bulverde has been sampled by numerous phone designers, some who will be introducing devices by the end of 2004. He would not say whether any are top mobile phone manufacturers.
Paul Otellini, Intel's president and COO, hinted at Hermon development during a keynote address here. He did unveil a three-radio reference design for cellphones offering 802.11b, Bluetooth and GSM/GPRS capabilities. It will run on the latest version of the Bulverde applications processor, wireless MMX and an XScale communications processor. The phone will support leading operating systems, including Microsoft, Symbian, Linux, Java and PalmOS.
It will also play MP3 music files with PC-quality sound, and incorporates a 1.3-megapixel digital camera.
Otellini reiterated Intel's commitment to the wireless broadband, particularly emerging WiMax technology, and said the company will have silicon for the expanded wireless network by the end of the year. Basestations and customer premises equipment are expected to be available by the middle of 2005.
He also forecast in a glitzy demononstation here that WiMax capability would be built into notebook computers by 2006, followed by handsets by 2007. The huge bandwidth increase provided by WiMax, compared to Wi-Fi, over much greater distances could set up a battle with operators of 3G networks.
Intel's mantra remains that "the wireless industry is evolving from a web of independent networks into a single, integrated wireless network with multiple standards, where no single standard will be sufficient."
Intel Buys Mobile Linux Developer OpenedHand
OpenedHand developers will join Intel's Open Source Technology Center, where they will focus on optimizing the Moblin software stack for Atom. Moblin, which stands for mobile Linux, is an open source project established by Intel. The initiative seeks to produce tools and software for MIDs, TV set-top boxes, personal navigation devices, personal media players, and ultra-light laptops.
"Intel will continue supporting open source projects currently led by OpenedHand staff, such as Clutter and Matchbox projects, and, in most cases, will accelerate these projects as they become an integral part of Moblin," OpenedHand said Tuesday in announcing the acquisition. Clutter is a graphics library for creating hardware-accelerated user interfaces, and Matchbox is a window manager used in Internet devices, such as Nokia's Internet Tablet and FIC's Neo smartphone.
Intel is not alone in targeting MIDs, smartphones, and other emerging devices for accessing the Web. Graphics chipmaker Nvidia is competing with Tegra, an all-in-one integrated graphics systems on a chip. Nvidia is particularly interested in the smartphone market, which is also being targeted by Texas Instruments, Qualcomm, Broadcom, and Samsung Electronics.
Intel's major competitor for manufacturers building mini-notebooks, ultra-light devices with screens less than 10 inches, is VIA Technologies, which makes the Nano CPU. Nvidia is working with Via to combine Nano with Tegra into a smartphone hardware platform.
Intel has said that demand for its Atom processor is "better than anticipated." Demand, in fact, is so good that media reports have said that the chipmaker is falling behind in meeting orders. Intel, however, has not acknowledged any problems. "Demand is very good, better than expected, and we're working with our customers to meet that demand," a spokesman told InformationWeek.
"Intel will continue supporting open source projects currently led by OpenedHand staff, such as Clutter and Matchbox projects, and, in most cases, will accelerate these projects as they become an integral part of Moblin," OpenedHand said Tuesday in announcing the acquisition. Clutter is a graphics library for creating hardware-accelerated user interfaces, and Matchbox is a window manager used in Internet devices, such as Nokia's Internet Tablet and FIC's Neo smartphone.
Intel is not alone in targeting MIDs, smartphones, and other emerging devices for accessing the Web. Graphics chipmaker Nvidia is competing with Tegra, an all-in-one integrated graphics systems on a chip. Nvidia is particularly interested in the smartphone market, which is also being targeted by Texas Instruments, Qualcomm, Broadcom, and Samsung Electronics.
Intel's major competitor for manufacturers building mini-notebooks, ultra-light devices with screens less than 10 inches, is VIA Technologies, which makes the Nano CPU. Nvidia is working with Via to combine Nano with Tegra into a smartphone hardware platform.
Intel has said that demand for its Atom processor is "better than anticipated." Demand, in fact, is so good that media reports have said that the chipmaker is falling behind in meeting orders. Intel, however, has not acknowledged any problems. "Demand is very good, better than expected, and we're working with our customers to meet that demand," a spokesman told InformationWeek.
Intel Details Larrabee Processor Architecture
Intel describes aspects of its Larrabee microarchitecture, including the design of an x86 processing core developed specifically for the chip. The chip maker explains why its engineers believe the Larrabee processor will usher in a new era of parallel software programming.
Intel is offering the first in-depth look at its "Larrabee" processor and the chip maker plans to offer the microprocessor to address a range of graphics and visual applications using x86 processing cores instead of more traditional GPUs.
In a paper, "Larrabee: A Many-Core x86 Architecture for Visual Computing," Intel engineers offered several new details about the forthcoming Larrabee graphics processing unit, including the fact that Intel derived the instructional pipeline for the individual x86 cores from the company's Pentium chip.
In addition, Larrabee will support Microsoft's DirectX and OpenGL APIs, which Intel hopes will motivate a legion of software developers to create new visual- and graphics-intensive applications while taking advantage of the traditional Intel Architecture found in Larrabee's x86 cores.
The first of the Larrabee chips, which are destined for the high-end PCs that use discrete graphics cards, will not arrive until 2009 or 2010, although Intel is expected to release samples starting in late 2008. Larrabee is described as a "many-core" processor, which means that it's likely to contain 10 or more individual x86 CPU cores within the silicon package. (Intel's upcoming Nehalem processors are likely to have up to eight cores.)
While Intel engineers have spoken about Larrabee and its place within high-performance computing, the paper makes clear that the first of the Larrabee processors are designed for the gaming market, where the chip will compete against high-end GPU offerings from ATI—owned by Advanced Micro Devices—and Nvidia. The fact that Intel is supporting the industry-standard DirectX and OpenGL APIs shows that the chip maker is looking to encourage developers to create new gaming applications on its architecture.
Intel is also betting that Larrabee will usher in a new era of parallel computing by offering developers a way to create highly specialized applications, such as games that require visual computing or scientific software applications that require intensive graphics capabilities, using the familiar x86 instructional set along with the C and C++ programming languages.
Nvidia, with its Tesla 10 series GPGPU (general processing GPU), is requiring developers to learn a new programming language called CUDA (Compute Unified Device Architecture), which allows the GPU to be programmed like a CPU.
For its part, AMD and its ATI graphics division are embracing CL, an open-source programming language. AMD is also moving toward combining the CPU and GPU on the same piece of silicon as part of its Accelerated Computing program.
In short, Intel is looking to combine the throughput capabilities of a CPU with the parallel programming abilities found in graphics processors.
"What the graphics and general data parallel application market needs is an architecture that provides the full programming abilities of a CPU, the full capabilities of a CPU together with the parallelism that is inherent in graphics processors," said Larry Seiler, a senior principal engineer with Intel. "Larrabee provides [that] and it's a practical solution to the limitations of current graphics processors."
This development could lead to a new way of looking at the capabilities of CPUs and GPUs in the commercial market.
"What stands out is that Intel views the CPU as the best GPU," said John Spooner, an analyst with Technology Business Research.
"Intel is able to apply x86 to rendering graphics rather than adopting a new or different architecture, which is clearly directly opposite of Nvidia's view of the world," Spooner added. "These companies are sure to engage in a public jousting match over whose architecture is better. The one that comes out on top, though, will be determined by performance and how well accepted the architecture is by developers."
At the heart of Larrabee is a series of simple x86 cores that are built with short instructional pipelines derived from the Pentium chip. The chip will also include what Intel describes as a vector processing units, which enhance the performance of graphics and video applications.
The Larrabee architecture will support four execution threads with each core and each thread supporting a register set, which helps with memory. In this setup, Larrabee offers a simple, efficient in-order instructional pipeline but maintains some of the benefits of an out-of-order pipeline, which helps when running applications designed to run in parallel. The short pipelines on Larrabee will allow for faster access to the Level 1 cache with each core.
All the Larrabee x86 cores—at this point Intel gave no guidance as to how many cores Larrabee will use—will share part of a large L2 cache, which will be partitioned among the different cores and allow for high bandwidth and data sharing.
The entire Larrabee chip architecture will be built on what Intel called a "bidirectional ring network," which should also allow faster communication between each of the individual x86 cores.
Intel is offering the first in-depth look at its "Larrabee" processor and the chip maker plans to offer the microprocessor to address a range of graphics and visual applications using x86 processing cores instead of more traditional GPUs.
In a paper, "Larrabee: A Many-Core x86 Architecture for Visual Computing," Intel engineers offered several new details about the forthcoming Larrabee graphics processing unit, including the fact that Intel derived the instructional pipeline for the individual x86 cores from the company's Pentium chip.
In addition, Larrabee will support Microsoft's DirectX and OpenGL APIs, which Intel hopes will motivate a legion of software developers to create new visual- and graphics-intensive applications while taking advantage of the traditional Intel Architecture found in Larrabee's x86 cores.
The first of the Larrabee chips, which are destined for the high-end PCs that use discrete graphics cards, will not arrive until 2009 or 2010, although Intel is expected to release samples starting in late 2008. Larrabee is described as a "many-core" processor, which means that it's likely to contain 10 or more individual x86 CPU cores within the silicon package. (Intel's upcoming Nehalem processors are likely to have up to eight cores.)
While Intel engineers have spoken about Larrabee and its place within high-performance computing, the paper makes clear that the first of the Larrabee processors are designed for the gaming market, where the chip will compete against high-end GPU offerings from ATI—owned by Advanced Micro Devices—and Nvidia. The fact that Intel is supporting the industry-standard DirectX and OpenGL APIs shows that the chip maker is looking to encourage developers to create new gaming applications on its architecture.
Intel is also betting that Larrabee will usher in a new era of parallel computing by offering developers a way to create highly specialized applications, such as games that require visual computing or scientific software applications that require intensive graphics capabilities, using the familiar x86 instructional set along with the C and C++ programming languages.
Nvidia, with its Tesla 10 series GPGPU (general processing GPU), is requiring developers to learn a new programming language called CUDA (Compute Unified Device Architecture), which allows the GPU to be programmed like a CPU.
For its part, AMD and its ATI graphics division are embracing CL, an open-source programming language. AMD is also moving toward combining the CPU and GPU on the same piece of silicon as part of its Accelerated Computing program.
In short, Intel is looking to combine the throughput capabilities of a CPU with the parallel programming abilities found in graphics processors.
"What the graphics and general data parallel application market needs is an architecture that provides the full programming abilities of a CPU, the full capabilities of a CPU together with the parallelism that is inherent in graphics processors," said Larry Seiler, a senior principal engineer with Intel. "Larrabee provides [that] and it's a practical solution to the limitations of current graphics processors."
This development could lead to a new way of looking at the capabilities of CPUs and GPUs in the commercial market.
"What stands out is that Intel views the CPU as the best GPU," said John Spooner, an analyst with Technology Business Research.
"Intel is able to apply x86 to rendering graphics rather than adopting a new or different architecture, which is clearly directly opposite of Nvidia's view of the world," Spooner added. "These companies are sure to engage in a public jousting match over whose architecture is better. The one that comes out on top, though, will be determined by performance and how well accepted the architecture is by developers."
At the heart of Larrabee is a series of simple x86 cores that are built with short instructional pipelines derived from the Pentium chip. The chip will also include what Intel describes as a vector processing units, which enhance the performance of graphics and video applications.
The Larrabee architecture will support four execution threads with each core and each thread supporting a register set, which helps with memory. In this setup, Larrabee offers a simple, efficient in-order instructional pipeline but maintains some of the benefits of an out-of-order pipeline, which helps when running applications designed to run in parallel. The short pipelines on Larrabee will allow for faster access to the Level 1 cache with each core.
All the Larrabee x86 cores—at this point Intel gave no guidance as to how many cores Larrabee will use—will share part of a large L2 cache, which will be partitioned among the different cores and allow for high bandwidth and data sharing.
The entire Larrabee chip architecture will be built on what Intel called a "bidirectional ring network," which should also allow faster communication between each of the individual x86 cores.
Intel Details Atom Processor For MIDs
It seems we can't go a week right now without Intel stumping up details of yet another even less power-hungry processor. We already saw leaks of Diamondville details, but now Intel has made them official, under the name of Atom.
Confusing matters slightly, there's actually two processor ranges, previously codenamed Diamondville and Silverthorne, that will come under the Atom banner. These are intended for sub-notebooks and Mobile Internet Devices (MIDs), respectively, so will have fairly different applications.
Atom chips will, as we know, be manufactured on the 45nm hi-k metal gate technology introduced with Penryn. Those destined for MIDs will have clock speeds ranging up to 1.8GHz and TDPs from an incredible 0.6W to 2.5W with idle power consumption is touted at as low as 30mW, a far cry from the 35W power draw of similarly clocked notebook Core 2 chips.
Previously codenamed Menlow, the Centrino Atom platform, in which these CPUs will be embedded, is set to offer support for WiMAX, WiFi and 3G/HSDPA, fitting in with the moniker of being an Internet device. Hopefully this should lead to devices like the Sony Vaio VGN-UX1XN but without the limitations, such as abysmal battery life.
It will still be a while after the announcement of the processors before we see MIDs using them, which is a shame because, now we have the details, the desire to get my grubby mitts on a system has increased tenfold.
Confusing matters slightly, there's actually two processor ranges, previously codenamed Diamondville and Silverthorne, that will come under the Atom banner. These are intended for sub-notebooks and Mobile Internet Devices (MIDs), respectively, so will have fairly different applications.
Atom chips will, as we know, be manufactured on the 45nm hi-k metal gate technology introduced with Penryn. Those destined for MIDs will have clock speeds ranging up to 1.8GHz and TDPs from an incredible 0.6W to 2.5W with idle power consumption is touted at as low as 30mW, a far cry from the 35W power draw of similarly clocked notebook Core 2 chips.
Previously codenamed Menlow, the Centrino Atom platform, in which these CPUs will be embedded, is set to offer support for WiMAX, WiFi and 3G/HSDPA, fitting in with the moniker of being an Internet device. Hopefully this should lead to devices like the Sony Vaio VGN-UX1XN but without the limitations, such as abysmal battery life.
It will still be a while after the announcement of the processors before we see MIDs using them, which is a shame because, now we have the details, the desire to get my grubby mitts on a system has increased tenfold.
AMD64 3200+ Venice S939
As said in the intro, AMD recently released their Venice and San Diego core processors. The primary differences between the two, is that the Venice uses 512Kb L2 Cache, and the San Diego uses 1024Kb L2 Cache. Venice is for the casual mainstream computer user, while San Diego will be, or hopes to be, the hardcore gamers core of choice.
Both Cores, use a 90nanometer process, as all the current AMD chips being produced will. AMD recently got rid of the 130nm cores, and because of this, the potential of the chip is better.. lower temperatures and higher overlocks. Even the Winchester core at 90nm, couldn't handle higher frequencies, which held some overclockers back, and this is where Venice could make it's mark.
So what does the Venice bring to the table, to make it better than the Winnie? AMD added the SSE3 Instruction set to both the Venice and San Diego, which should help out in some areas, primarily media and development, but not gaming. It should be mentioned that this is not a simple copy/paste, so to speak, of the SSE3 instructions from the Prescott Intel chips. Prescott has a few more instructions in the set, that are used towards their Hyper-Threading technology. So if you were considering an Intel due to the Hyper-Threading factor, then the addition of SSE3 to the Venice/Sandy shouldn't sway you.
Another feature added, is a better memory controller. An issue with the controller on the Winchester chips, was that if you used 4 Single-Sided sticks of memory, it would force you to use 2T timings, which held back performance. This has been fixed on the new cores.
Lastly, another thing that makes the Venice so great, is that it runs using a relatively low 66W of power, meaning lower temps, and higher overclocks. In the review, I am going to benchmark the stock chip, and then see how far I can push the overclock. The Venice comes in four flavours, the 3000+, 3200+, 3500+ and finally the 3800+. I'll be taking a look at the 3200+, which comes in at a stock speed of 2.0GHz.
Processor
AMD 64 3200+ S939 "Venice" Core (512k L2 Cache)
Motherboard
DFI LanParty NF4 UT Ultra-D
Power Supply
Ultra X-Finity 600W
Memory
512 * 2 Samsung DDR400 (3-3-3-8)
Hard Disks
200GB * 2 Western Digital 8MB Cache160GB Western Digital 8MB Cache
Sound Card
Phillips PSC724 Ultimate Edge 5.1
Video Card
BFG 6800 GT OC 256MB
Etcetera
Running Windows XP Professional with SP2.Video drivers are Omega Drivers 1.6693 versions.Using 5/10 BIOS flash.
Both Cores, use a 90nanometer process, as all the current AMD chips being produced will. AMD recently got rid of the 130nm cores, and because of this, the potential of the chip is better.. lower temperatures and higher overlocks. Even the Winchester core at 90nm, couldn't handle higher frequencies, which held some overclockers back, and this is where Venice could make it's mark.
So what does the Venice bring to the table, to make it better than the Winnie? AMD added the SSE3 Instruction set to both the Venice and San Diego, which should help out in some areas, primarily media and development, but not gaming. It should be mentioned that this is not a simple copy/paste, so to speak, of the SSE3 instructions from the Prescott Intel chips. Prescott has a few more instructions in the set, that are used towards their Hyper-Threading technology. So if you were considering an Intel due to the Hyper-Threading factor, then the addition of SSE3 to the Venice/Sandy shouldn't sway you.
Another feature added, is a better memory controller. An issue with the controller on the Winchester chips, was that if you used 4 Single-Sided sticks of memory, it would force you to use 2T timings, which held back performance. This has been fixed on the new cores.
Lastly, another thing that makes the Venice so great, is that it runs using a relatively low 66W of power, meaning lower temps, and higher overclocks. In the review, I am going to benchmark the stock chip, and then see how far I can push the overclock. The Venice comes in four flavours, the 3000+, 3200+, 3500+ and finally the 3800+. I'll be taking a look at the 3200+, which comes in at a stock speed of 2.0GHz.
Processor
AMD 64 3200+ S939 "Venice" Core (512k L2 Cache)
Motherboard
DFI LanParty NF4 UT Ultra-D
Power Supply
Ultra X-Finity 600W
Memory
512 * 2 Samsung DDR400 (3-3-3-8)
Hard Disks
200GB * 2 Western Digital 8MB Cache160GB Western Digital 8MB Cache
Sound Card
Phillips PSC724 Ultimate Edge 5.1
Video Card
BFG 6800 GT OC 256MB
Etcetera
Running Windows XP Professional with SP2.Video drivers are Omega Drivers 1.6693 versions.Using 5/10 BIOS flash.
AMD64 3700+ San Diego S939 2.2GHz
Here at the Techgage labs, on the border of sanity, we have a brand new Athlon 3700+ San Diego in for review. If you have found your way to our little corner of the 'net, I am certain that AMD needs no introduction. But, for all of you techies out there that have been living under a rock or in Siberia, AMD is the premiere gaming CPU of choice for anyone "in the know".
This is a debatable statement at best so through out the review, we will see what this chip has to offer. I have owned a 3500+ Winchester core before this. so I am excited to see what the difference an extra 512 of L2 will help out. It's been a while since we have taken a look at a CPU so let's get into the meat of this review.
About Advanced Micro Devices
Founded in 1969 and based in Sunnyvale, California, AMD provides microprocessors, Flash memory devices, and silicon-based solutions for our customers in the communications and computer industries worldwide.
However, our focus goes beyond integrated circuits and transistors. AMD is committed to helping our customers — and their customers — take advantage of the phenomenal capacity of silicon to add value and help differentiate their offerings. To that end, AMD products are developed with customer needs always in mind and not for the sake of innovation alone. Stated more plainly, it means that AMD exists to provide real solutions for real customer problems that exist in the real world today.
Earlier this year, AMD released their Venice and San Diego core processors. The primary differences between the two, is that the Venice uses 512Kb L2 Cache, and the San Diego uses 1024Kb L2 Cache. Venice is for the casual mainstream computer user, while San Diego could be the hardcore gamers core of choice.
Both Cores, use a 90nanometer process, as all the current AMD chips being produced will. AMD recently got rid of the 130nm cores, and because of this, the potential of the chip is better.. lower temperatures and higher overclocks. Even the Winchester core at 90nm, couldn't handle higher frequencies, which held some overclockers back, and this is where Venice could make it's mark.
So what does the Venice bring to the table, to make it better than the Winnie? AMD added the SSE3 Instruction set to both the Venice and San Diego, which should help out in some areas, primarily media and development, but not gaming. It should be mentioned that this is not a simple copy/paste, so to speak, of the SSE3 instructions from the Prescott Intel chips. Prescott has a few more instructions in the set, that are used towards their Hyper-Threading technology. So if you were considering an Intel due to the Hyper-Threading factor, then the addition of SSE3 to the Venice/Sandy shouldn't sway you.
This is a debatable statement at best so through out the review, we will see what this chip has to offer. I have owned a 3500+ Winchester core before this. so I am excited to see what the difference an extra 512 of L2 will help out. It's been a while since we have taken a look at a CPU so let's get into the meat of this review.
About Advanced Micro Devices
Founded in 1969 and based in Sunnyvale, California, AMD provides microprocessors, Flash memory devices, and silicon-based solutions for our customers in the communications and computer industries worldwide.
However, our focus goes beyond integrated circuits and transistors. AMD is committed to helping our customers — and their customers — take advantage of the phenomenal capacity of silicon to add value and help differentiate their offerings. To that end, AMD products are developed with customer needs always in mind and not for the sake of innovation alone. Stated more plainly, it means that AMD exists to provide real solutions for real customer problems that exist in the real world today.
Earlier this year, AMD released their Venice and San Diego core processors. The primary differences between the two, is that the Venice uses 512Kb L2 Cache, and the San Diego uses 1024Kb L2 Cache. Venice is for the casual mainstream computer user, while San Diego could be the hardcore gamers core of choice.
Both Cores, use a 90nanometer process, as all the current AMD chips being produced will. AMD recently got rid of the 130nm cores, and because of this, the potential of the chip is better.. lower temperatures and higher overclocks. Even the Winchester core at 90nm, couldn't handle higher frequencies, which held some overclockers back, and this is where Venice could make it's mark.
So what does the Venice bring to the table, to make it better than the Winnie? AMD added the SSE3 Instruction set to both the Venice and San Diego, which should help out in some areas, primarily media and development, but not gaming. It should be mentioned that this is not a simple copy/paste, so to speak, of the SSE3 instructions from the Prescott Intel chips. Prescott has a few more instructions in the set, that are used towards their Hyper-Threading technology. So if you were considering an Intel due to the Hyper-Threading factor, then the addition of SSE3 to the Venice/Sandy shouldn't sway you.
AMD Introduces New Prices for Athlon Processors
IBM announced the completion of its approximately US $845 million (approximately 5 billion Swedish Kronor) tender offer for the shares of Telelogic, a provider of software to develop technical systems and enterprise architecture. The tender offer, announced on June 11, 2007, was finalized after IBM obtained acceptance from 98.7% of stock ownership in Telelogic as well as satisfaction of other conditions of the offer, including necessary worldwide regulatory approvals. Headquartered in Malmo, Sweden, and Irvine, California, Telelogic has more than 8,000 customers worldwide and operations in 22 countries around the world. In India, Telelogic has a headcount of approx. 300 who will be integrated into IBM India towards the end of 2008. According to Ken King, vice president and Telelogic integration executive, IBM Software, with the acquisition closure, Telelogic now becomes 'an IBM company'. "The integrated product and technology roadmap will illustrate incremental value to our systems and IT customers across Telelogic and Rational. India has a unique advantage with this acquisition as we gain not just from the business perspective, but also from the strong skill-set that Telelogic has here." Together, IBM, Telelogic, and business partners will now be able to deliver high-quality systems to the market faster while reducing costs. Customers will benefit from the combined technologies and services of both companies, providing them a wide range of software and system development capabilities, along with support from a worldwide sales and services organization. "Telelogic is an important element of our software and systems development and delivery strategy," said Dr. Daniel Sabbah, general manager, IBM Rational Software. "Software is at the heart of embedded devices and systems. This IBM technology has important implications for society." Telelogic will report into the IBM Rational Software unit. In consonance with IBM's software strategy, Telelogic clients' and partners' investments in existing IBM and Telelogic technologies will be preserved, allowing customers to take advantage of the broader set of capabilities without the need to replace existing systems, the company said. Since 1995, IBM has invested more than $18 billion on public acquisitions, making it the most acquisitive company in the technology industry, based on volume of transactions. Other strategic acquisitions in support of IBM s software and systems development and delivery strategy include BuildForge (build and release management), SystemCorp (project and portfolio management) and Watchfire (Web application security).
Managing Data Storage by Support Services
Data Storage exponential data growth, you need to find efficient, cost-effective ways to make the most of your critical storage infrastructure. And with the complexity of today's storage technology and the ever-mounting demands on your internal resources, it's tougher than ever to do it alone. With the technology storage industry at the cusp of strong growth, as never before, data storage environment poses multiple challenges that directly impacts bottom-line business results.
More data is captured and stored by businesses now than ever before. A typical business today stores 10 times more data than in 2000. Gartner report estimates that storage requirements will have increased by a factor of 30 by 2012. Challenges like soaring storage costs. Tighter regulations governing data retention, access and privacy. Data center power, cooling and space limitations. Scarce technical expertise. The constant threat of natural and manmade disasters. The complexities of managing multivendor storage solutions are present. This can be addressed by end-to-end support services, Multivendor hardware/software support, Integrated remote support technologies, Comprehensive installation and implementation support lastly a full suite of flexible, scalable services to boost ongoing storage performance and availability. Companies are moving from Direct Attached Storage (DAS) to networked storage with the adoption of Fiber Channel (FC) Storage Area Network (SAN) technologies. The major benefits associated with this move are: higher availability, scalability, minimal interference with LAN traffic, increased management efficiency and utilization levels of about 90%, resulting in lower Total Cost of Ownership (TCO) and higher Return on Investment (ROI). As the economy improved from the recession of 2000, and the demand for storing increasingly large volumes of data, companies are beginning to spend on IT infrastructure and storage. In this way, businesses need to start rethinking the way they go about storing their data in order to enhance analytics, improve business processes and give themselves the best possible competitive advantage.
More data is captured and stored by businesses now than ever before. A typical business today stores 10 times more data than in 2000. Gartner report estimates that storage requirements will have increased by a factor of 30 by 2012. Challenges like soaring storage costs. Tighter regulations governing data retention, access and privacy. Data center power, cooling and space limitations. Scarce technical expertise. The constant threat of natural and manmade disasters. The complexities of managing multivendor storage solutions are present. This can be addressed by end-to-end support services, Multivendor hardware/software support, Integrated remote support technologies, Comprehensive installation and implementation support lastly a full suite of flexible, scalable services to boost ongoing storage performance and availability. Companies are moving from Direct Attached Storage (DAS) to networked storage with the adoption of Fiber Channel (FC) Storage Area Network (SAN) technologies. The major benefits associated with this move are: higher availability, scalability, minimal interference with LAN traffic, increased management efficiency and utilization levels of about 90%, resulting in lower Total Cost of Ownership (TCO) and higher Return on Investment (ROI). As the economy improved from the recession of 2000, and the demand for storing increasingly large volumes of data, companies are beginning to spend on IT infrastructure and storage. In this way, businesses need to start rethinking the way they go about storing their data in order to enhance analytics, improve business processes and give themselves the best possible competitive advantage.
Intel G35 Express Chipset Processors
The Intel® G35 Express Chipset continues the Intel® chipset legacy and extends it to new levels with purpose-built capabilities designed specifically to address the key needs of the enthusiast home user.The Intel G35 Express Chipset continues the Intel chipset legacy and extends it to new levels with purpose-built capabilities designed specifically to address the key needs of the home user. With advancements in graphics, video, and system responsiveness, the Intel G35 Express Chipset allows your PC to be the center of home computing, communication, and entertainment.Desktop PC platforms based on the Intel G35 Express Chipset, combined with either the Intel Core 2 Duo or Intel Core 2 Quad processor, and with support for next-generation 45nm Intel® Core™2 processor family, deliver innovative capabilities and usages for digital home consumers and new levels of 3D and media performance while enabling lower power and quieter systems.
Intel Launches Quad-core Products for Servers
To provide energy efficient performance, coupled with enhanced virtualization capabilities, Intel India has unveiled quad-core processors, which are specifically designed for Multi-Processor (MP) servers.
The 6 Quad-core Xeon 7300 series processors can deliver more performance per watt over the company's previous generation dual-core products. Commenting on the new launch, R. Ravindran, director (sales) of Intel South Asia said, "With the Xeon 7300 series, Intel is delivering new levels of performance and performance per watt, and driving the Intel Core microarchitecture into such innovative systems as 4 socket, 16 core blades that use less energy than our older models." For channel customers looking for complete platforms based on these new processors, Intel offers the Intel S7000FC4UR server platform. Many software vendors are also supporting Xeon 7300, which include BEA, Microsoft, Oracle, SAP, and VMware. The 7300 series and Intel 7300 chipset offer up to four times the memory capacity of Intel's previous MP platforms. With the introduction of the Xeon 7300, users can pool their Intel Core microarchitecture based server resources, whether they are single-, dual- , or multi-processor based, into a server infrastructure that can improve usage models like failover, load balancing, disaster recovery, or server maintenance. More than 50 system manufacturers, including HCL, Wipro, Dell, Egenera, Fujitsu, Fujitsu-Siemens, Hitachi, HP, IBM, NEC, Sun, Supermicro, and Unisys, will announce the Xeon 7300 series processors. Depending on the speeds, features, and amount ordered the pricing of these new quad-core processors ranges from USD 856 to USD 2,301 in quantities of 1,000.
The 6 Quad-core Xeon 7300 series processors can deliver more performance per watt over the company's previous generation dual-core products. Commenting on the new launch, R. Ravindran, director (sales) of Intel South Asia said, "With the Xeon 7300 series, Intel is delivering new levels of performance and performance per watt, and driving the Intel Core microarchitecture into such innovative systems as 4 socket, 16 core blades that use less energy than our older models." For channel customers looking for complete platforms based on these new processors, Intel offers the Intel S7000FC4UR server platform. Many software vendors are also supporting Xeon 7300, which include BEA, Microsoft, Oracle, SAP, and VMware. The 7300 series and Intel 7300 chipset offer up to four times the memory capacity of Intel's previous MP platforms. With the introduction of the Xeon 7300, users can pool their Intel Core microarchitecture based server resources, whether they are single-, dual- , or multi-processor based, into a server infrastructure that can improve usage models like failover, load balancing, disaster recovery, or server maintenance. More than 50 system manufacturers, including HCL, Wipro, Dell, Egenera, Fujitsu, Fujitsu-Siemens, Hitachi, HP, IBM, NEC, Sun, Supermicro, and Unisys, will announce the Xeon 7300 series processors. Depending on the speeds, features, and amount ordered the pricing of these new quad-core processors ranges from USD 856 to USD 2,301 in quantities of 1,000.
AMD Intros GPU
AMD has introduced the ATI Radeon E2400, a high-performance graphic processing unit to deliver the latest 2D, 3D and multimedia graphics performance.
The new graphics technology is backed by a planned five-year availability and long-term support offering reliability for a variety of applications on operating systems featuring Microsoft DirectX 10 and OpenGL 2.0. "With the input of major original equipment manufacturers and platform developers, we have designed the ATI Radeon E2400 from the start to deliver high graphics performance while meeting the unique requirements of the embedded market," said Richard Jaenicke, director of embedded graphics for AMD. Built on 65nm process technology, the ATI Radeon E2400 includes AMD's Unified Shader Architecture with support for Microsoft DirectX 10, allowing customers to develop advanced content for many applications. The device package incorporates 128MB of on-chip GDDR3 memory for graphic-intensive applications, eliminating the space, effort, and cost of external memory designs. For designs that require a low profile solution in space-constrained environments, AMD offers the ATI Radeon E2400 MXM-II module based on the open standard MXM-II specifications. The ATI Radeon E2400 is scheduled to ship this month in production quantities. AMD will showcase the product both at Embedded World 2008 (February 26-28, 2008) in Nuremberg, Germany, and at Embedded Systems Conference Silicon (April 14-18, 2008) in San Jose, California.
The new graphics technology is backed by a planned five-year availability and long-term support offering reliability for a variety of applications on operating systems featuring Microsoft DirectX 10 and OpenGL 2.0. "With the input of major original equipment manufacturers and platform developers, we have designed the ATI Radeon E2400 from the start to deliver high graphics performance while meeting the unique requirements of the embedded market," said Richard Jaenicke, director of embedded graphics for AMD. Built on 65nm process technology, the ATI Radeon E2400 includes AMD's Unified Shader Architecture with support for Microsoft DirectX 10, allowing customers to develop advanced content for many applications. The device package incorporates 128MB of on-chip GDDR3 memory for graphic-intensive applications, eliminating the space, effort, and cost of external memory designs. For designs that require a low profile solution in space-constrained environments, AMD offers the ATI Radeon E2400 MXM-II module based on the open standard MXM-II specifications. The ATI Radeon E2400 is scheduled to ship this month in production quantities. AMD will showcase the product both at Embedded World 2008 (February 26-28, 2008) in Nuremberg, Germany, and at Embedded Systems Conference Silicon (April 14-18, 2008) in San Jose, California.
Intel Pentium Extreme Edition
Get advanced performance for high-end gaming and the most demanding power applications. The Intel Pentium 4 Processor with HT Technology Extreme Edition is designed specifically for those who know their technology and crave high performance.FeaturesHyper-Threading Technology Streaming SIMD extensions 3 Intel Extended Memory 64 Technology Execute Disable Bit capability 1MB L2 Advanced Transfer Cache for each core Specifications General Product Type Processor Expansion / Connectivity Compatible Slots 1 x processor - LGA775 Socket Miscellaneous Package Type Intel Boxed Processor Type / Form Factor Intel Pentium Extreme Edition Dual-Core 840 Processor Qty 1 Clock Speed 3.2 GHz Bus Speed 800 MHz Processor Socket LGA775 Socket Cache Memory Type Advanced Transfer Cache Installed Size L2 cache - 2 MB What is a PowerLeap adapter? This device from PowerLeap allows socket 7 and socket 5 motherboards to have clock multiplier speeds up to 6.0x, even if you original motherboard has a maximum multiplier that is lower. Additionally, this adapter will also provide you with the proper split voltages for all AMD, CYRIX and Intel MMX processor to work on your system. Once the Powerleap adapter is installed you are only limited by your BIOS.Because my original motherboard does not support AMD Processors or 6.0x clock multipliers I needed to use the PowerLeap adapter in my tests. But as you can see below this combination has given me a dramatic increase in speed over my original Pentium 133 that came with my system.
Intel 5000P Chipset Processors
Intel's new server chipsets for the Dual-Core Intel® Xeon® processor 5000 series enable Intel® dual-processor (DP) balanced server platforms that are efficient, dependable, and responsive.
Intel® dual-core processor-based platforms help businesses better utilize assets with effective virtualization and increase density in their data centers through optimized power and thermal features.
With the Intel 5000P or Intel 5000V chipset and Dual-Core Intel Xeon processor 5000 series, system designers can offer new platforms that help IT services move ahead with increased productivity, higher throughput, and faster time-to-solution.
The Intel® 5000P chipset, the next generation Intel® dual-processor (DP) server chipset technology, offers increased graphics performance, reduced power consumption, and improved platform reliability and system manageability
Intel® dual-core processor-based platforms help businesses better utilize assets with effective virtualization and increase density in their data centers through optimized power and thermal features.
With the Intel 5000P or Intel 5000V chipset and Dual-Core Intel Xeon processor 5000 series, system designers can offer new platforms that help IT services move ahead with increased productivity, higher throughput, and faster time-to-solution.
The Intel® 5000P chipset, the next generation Intel® dual-processor (DP) server chipset technology, offers increased graphics performance, reduced power consumption, and improved platform reliability and system manageability
Intel Core 2 Extreme quad-core processor
When more is better-with four processing cores the Intel Core 2 Extreme processor delivers unrivaled¹ performance for the latest, greatest generation of multi-threaded games and multimedia apps.Now with a new version based on Intel's cutting edge 45nm technology utilizing hafnium-infused circuitry to deliver even greater performance and power efficiency. The Intel® Core™2 Extreme processor QX9770 running at 3.2 GHz delivers the best possible experience for today's most demanding users.
12 MB of total L2 cache
1600 MHz front side bus
Intel® Network Processors
Built on a high-performance fully programmable architecture, Intel network processors offer the speed, flexibility, and ease-of-use/reuse you need to accelerate time-to-market, extend time-in-market, and to enable a broad range of services from the customer premises to the core of the network. Network processors optimized for home, small-to-medium enterprise, and networked embedded applications. Flexible wire-speed processing for OC-3 to OC-12 multiservice network applications.
The Intel® IXC1100 control plane processor extends the benefits of Intel XScale® technology, including its rich set of development tools, to meet the processing needs of multi-service switches, VoIP media gateways, wireless infrastructure and other networking equipment.The information on this page is provided for the benefit of customers with existing designs.
12 MB of total L2 cache
1600 MHz front side bus
Intel® Network Processors
Built on a high-performance fully programmable architecture, Intel network processors offer the speed, flexibility, and ease-of-use/reuse you need to accelerate time-to-market, extend time-in-market, and to enable a broad range of services from the customer premises to the core of the network. Network processors optimized for home, small-to-medium enterprise, and networked embedded applications. Flexible wire-speed processing for OC-3 to OC-12 multiservice network applications.
The Intel® IXC1100 control plane processor extends the benefits of Intel XScale® technology, including its rich set of development tools, to meet the processing needs of multi-service switches, VoIP media gateways, wireless infrastructure and other networking equipment.The information on this page is provided for the benefit of customers with existing designs.
Intel Intros 45nm Core 2 Duo Processor
Intel Corporation recently announced the 45-nanometer (nm) Intel Core 2 Duo Processor E8400 with 7-year lifecycle support for embedded applications. To enhance security in embedded solutions, the processor also supports Intel Trusted Execution Technology. Based on Intel's high-k metal gate transistor formula and manufactured on the company's 45nm process, the E8400 processor offers increased performance by doubling transistor density and increasing cache size up to 6 MB, which is a threefold enhancement over the previous-generation Intel Core 2 Duo E6400. The E8400 processor is available to customers today and costs US $183 in quantities of 1,000. A hardware extension to the E8400 processor, Intel Trusted Execution Technology brings hardware data security to the embedded market, making the dual-core processor ideal for military and government, mid-range network security appliances, and retail applications. This security technology is designed to guard data within tamper-resistant virtualized computing environments and to protect against software attacks, viruses and other threats. The 45nm processor includes a Super Shuffle Engine that enhances Intel Streaming SIMD Extensions (SSE) algorithms optimized for graphics and multimedia processing. The Super Shuffle Engine reduces latency and improves the speed of existing SSE instructions while enabling significant gains on the latest Intel Streaming SIMD Extensions 4 (SSE4) instruction set.
Friday, January 23, 2009
Intel Core 2 Quad Q6600
There's no doubt that 2006 was one of the most incredible years in technology in recent memory. There were scandals, impressive landscape-shifting mergers, strange new alliances and many new products and technologies unveiled. One launch that stands out in everyone's mind is Intel's Conroe last summer. We were teased with leaked benchmark results and other information months before the release and once the launch finally hit, we were all relieved to see that it actually lived up to the hype.
After a launch like this, we didn't think that a follow-up would arrive for a while. We were wrong. In the early fall, we first learned about Intel's quad-core CPU, which is essentially two Conroes under the same IHS. I admit, I didn't expect to actually see it so soon, but come November, it was publicly available for anyone to purchase. Intel's at the top of their game, and don't want to step down anytime soon.
When they first launched their QX6700, they held off launching the Q6600 until early January. We don't know the reason for the delay, but now the possibility of having your own quad-core machine without breaking the bank has finally arrived. Let's first get the basics out of the way.
Oh My Quad
The Q6600 is a 2.4GHz chip, like its little brother the E6600. Both CPUs are nearly identical and use the same die(s), except that the Q6600 has two of them. Essentially, everything is doubled. Twice the cores, twice the cache and twice the drool. Like the other Core 2 Duos, Core 2 Quads are based on a 65nm process, although the process requires a slightly higher stock voltage. Since both the Quads are so similar to the Duos, it's no surprise to see that the die size is simply doubled as well, resulting in 2 x 143mm^2.
When compared to the top of the line QX6700 chip, the specs are again identical except for the 2.66GHz clock speed. Other than that, the CPUs are the same, just binned differently. When comparing to the top end Core 2 Duo, the differences are a lot more meaningful. While the QX6700 retails for just under $1,000, so does the X6800. However, when considering the QX6700, you receive a lower clock speed in return for twice the cores. At that point, it's up to you whether you want or need the sheer clock speed or greater benefits for your multi-thread applications.
To help put everything into perspective, here's a simple graph showcasing all of Intel's current Core 2 offerings.
CPU Model
Clock Speed
FSB
L2 Cache
TDP
Cores
Pricing
Intel Core 2 Extreme QX6700 2.66GHz 1066MHz 4MB x 2 130w 4 $999
Intel Core 2 Extreme X6800 2.93GHz 1066MHz 4MB 75W 2 $999
Intel Core 2 Quad Q6600 2.40GHz 1066MHz 4MB x 2 105W 4 $851
Intel Core 2 Duo E6700 2.66GHz 1066MHz 4MB 65W 2 $530
Intel Core 2 Duo E6600 2.40GHz 1066MHz 4MB 65W 2 $316
Intel Core 2 Duo E6400 2.13GHz 1066MHz 2MB 65W 2 $224
Intel Core 2 Duo E6300 1.86GHz 1066MHz 2MB 65W 2 $183
Intel Core 2 Duo E4300 1.80GHz 800MHz 2MB 65W 2 $163
One interesting point to note is that even though the Q6600 is essentially 2 x E6600, the TDP is not doubled, but rather sits at a comfortable 105W. The higher clocked QX6700 is 130W, however, which is why we don't see a QX6800 instead. A TDP of 130W is high to begin with, but considering the much slower 820 D we reviewed less than a year ago also had a TDP of 130W, power consumption still hasn't entered uncharted territory, and there are thermal solutions available to deal with that kind of heat.
Below, you can see a highly detailed illustration of the quad-core's innards. In case you thought that two dies would be a tight squeeze, think again! Despite having four cores, there's still a reasonable amount of breathing room in there. For a more realistic view of the chip with the HS off, you can check out the picture provided by Intel
After a launch like this, we didn't think that a follow-up would arrive for a while. We were wrong. In the early fall, we first learned about Intel's quad-core CPU, which is essentially two Conroes under the same IHS. I admit, I didn't expect to actually see it so soon, but come November, it was publicly available for anyone to purchase. Intel's at the top of their game, and don't want to step down anytime soon.
When they first launched their QX6700, they held off launching the Q6600 until early January. We don't know the reason for the delay, but now the possibility of having your own quad-core machine without breaking the bank has finally arrived. Let's first get the basics out of the way.
Oh My Quad
The Q6600 is a 2.4GHz chip, like its little brother the E6600. Both CPUs are nearly identical and use the same die(s), except that the Q6600 has two of them. Essentially, everything is doubled. Twice the cores, twice the cache and twice the drool. Like the other Core 2 Duos, Core 2 Quads are based on a 65nm process, although the process requires a slightly higher stock voltage. Since both the Quads are so similar to the Duos, it's no surprise to see that the die size is simply doubled as well, resulting in 2 x 143mm^2.
When compared to the top of the line QX6700 chip, the specs are again identical except for the 2.66GHz clock speed. Other than that, the CPUs are the same, just binned differently. When comparing to the top end Core 2 Duo, the differences are a lot more meaningful. While the QX6700 retails for just under $1,000, so does the X6800. However, when considering the QX6700, you receive a lower clock speed in return for twice the cores. At that point, it's up to you whether you want or need the sheer clock speed or greater benefits for your multi-thread applications.
To help put everything into perspective, here's a simple graph showcasing all of Intel's current Core 2 offerings.
CPU Model
Clock Speed
FSB
L2 Cache
TDP
Cores
Pricing
Intel Core 2 Extreme QX6700 2.66GHz 1066MHz 4MB x 2 130w 4 $999
Intel Core 2 Extreme X6800 2.93GHz 1066MHz 4MB 75W 2 $999
Intel Core 2 Quad Q6600 2.40GHz 1066MHz 4MB x 2 105W 4 $851
Intel Core 2 Duo E6700 2.66GHz 1066MHz 4MB 65W 2 $530
Intel Core 2 Duo E6600 2.40GHz 1066MHz 4MB 65W 2 $316
Intel Core 2 Duo E6400 2.13GHz 1066MHz 2MB 65W 2 $224
Intel Core 2 Duo E6300 1.86GHz 1066MHz 2MB 65W 2 $183
Intel Core 2 Duo E4300 1.80GHz 800MHz 2MB 65W 2 $163
One interesting point to note is that even though the Q6600 is essentially 2 x E6600, the TDP is not doubled, but rather sits at a comfortable 105W. The higher clocked QX6700 is 130W, however, which is why we don't see a QX6800 instead. A TDP of 130W is high to begin with, but considering the much slower 820 D we reviewed less than a year ago also had a TDP of 130W, power consumption still hasn't entered uncharted territory, and there are thermal solutions available to deal with that kind of heat.
Below, you can see a highly detailed illustration of the quad-core's innards. In case you thought that two dies would be a tight squeeze, think again! Despite having four cores, there's still a reasonable amount of breathing room in there. For a more realistic view of the chip with the HS off, you can check out the picture provided by Intel
Intel Pentium 820 D 2.8GHz 90nm Dual Core
It wasn't too long ago that we were all asking the question, "Should I go dual core?" Times have proven that dual core is the future and has clear benefits, which turned that question into, "Which dual core should I get?" Even if you are buying the lowest dual core on the scale, you are essentially getting twice the computing power than from a single chip. As more and more applications take advantage of dual cores, it makes the buying decision easier. Of course, the ability to multi-task without slowing your OS down is another huge benefit.
Intel and AMD both have a great selection of dual core chips, for all wallet sizes. Intel dual cores almost always cost less than AMD's, which makes them look more attractive. Generally speaking though, tests have proven AMD dual cores better for gaming on high-end systems. But, if you are looking for a cheap solution to get yourself a dual core rig built, then Intels offerings are worth looking at.
Today's processor in question is the 820 D. It was the bottom of the barrel when it came to Intel DC's, until the lower clocked 805 D came out. But before we get into specifics and feature comparisons, let's delve a bit deeper into why dual cores are beneficial to you.
Features
PCs that have two CPU cores are not necessarily new, although it is for the consumer market. A few years ago, you would need two separate CPU's in the same machine. You can now have the same benefit but with only one CPU. There was a lot of speculation when dual cores came to be, but there's no denying just how beneficial they can be. Because you essentially have two CPU cores under the same IHS, multitasking proves less groggy with larger applications. As you open new instances of applications, the CPU will decide which core to use. The goal is to allow you to do more on your PC than with a single core, without having a sluggish experience.
Even though you have a dual core, things can still slow down your PC, but that primarily only happens with multiple intensive applications that are stressing the same components at once, such as ram or your hard drive. As a great example though, you could play a game and convert a video file at the same time and feel virtually no lag or slowdown. Try doing that on a single core and it will not be a fun experience. Because of these possibilities, it's no wonder why dual cores are growing in popularity.
Intel and AMD both have a great selection of dual core chips, for all wallet sizes. Intel dual cores almost always cost less than AMD's, which makes them look more attractive. Generally speaking though, tests have proven AMD dual cores better for gaming on high-end systems. But, if you are looking for a cheap solution to get yourself a dual core rig built, then Intels offerings are worth looking at.
Today's processor in question is the 820 D. It was the bottom of the barrel when it came to Intel DC's, until the lower clocked 805 D came out. But before we get into specifics and feature comparisons, let's delve a bit deeper into why dual cores are beneficial to you.
Features
PCs that have two CPU cores are not necessarily new, although it is for the consumer market. A few years ago, you would need two separate CPU's in the same machine. You can now have the same benefit but with only one CPU. There was a lot of speculation when dual cores came to be, but there's no denying just how beneficial they can be. Because you essentially have two CPU cores under the same IHS, multitasking proves less groggy with larger applications. As you open new instances of applications, the CPU will decide which core to use. The goal is to allow you to do more on your PC than with a single core, without having a sluggish experience.
Even though you have a dual core, things can still slow down your PC, but that primarily only happens with multiple intensive applications that are stressing the same components at once, such as ram or your hard drive. As a great example though, you could play a game and convert a video file at the same time and feel virtually no lag or slowdown. Try doing that on a single core and it will not be a fun experience. Because of these possibilities, it's no wonder why dual cores are growing in popularity.
Intel Core 2 Duo E6750 Preview
It hasn't been a full year since we saw Intel launch their Core 2 Duo processors, but we will soon be seeing a line-up refresh. This is one product that really needs no introduction, but seeing as this is a refresh, refreshing everyones minds seems appropriate. Intel launched the Core 2 Duo to much fanfare last July. Months prior to this, enthusiasts were drooling over leaks of performance reports, which fortunately, turned out to be right on the money.
The entire Conroe line-up is built on a 65nm process, with the mainstream products offering 4MB of L2 cache. Improved over the previous Pentium 4/Pentium D line-up was better power efficiency resulting in a lower TDP and better overall temperatures. This is appreciated, as two cores under the same IHS can potentially create an unwanted room heater.
All but the lowest end Core 2 Duos take advantage of a 1066FSB. This is where this refreshed line-up comes into play, as it ushers in 1333FSB computing. This noticeable speed bump is all done while retaining the same TDP.
All Conroe 1333FSB processors are identified by by a 50 at the end of the product name, hence E6750, which is effectively taking over the spot of the E6700. Nothing has changed except for the FSB and speeds, except the ratio of course, which had to be altered in order to compliment the upgraded frequency.
One thing that should be cleared up is that most overclocking enthusiasts have already accomplished the same speeds we are seeing today, with most being exceeded. In fact, there is nothing stopping anyone from popping in an E6600 and overclocking using a 333FSB and 8 multiplier. That would effectively give you the exact same speed as the E6750 we are taking a look at today.
You might be wondering where the benefit is, with this official speed bump. Primarily it will benefit those non-overclockers most. There is no comparison to equal processor speed at 1066FSB and 1333FSB. That added FSB frequency should make a much more noticeable performance difference than the CPU frequency boost itself.
The entire Conroe line-up is built on a 65nm process, with the mainstream products offering 4MB of L2 cache. Improved over the previous Pentium 4/Pentium D line-up was better power efficiency resulting in a lower TDP and better overall temperatures. This is appreciated, as two cores under the same IHS can potentially create an unwanted room heater.
All but the lowest end Core 2 Duos take advantage of a 1066FSB. This is where this refreshed line-up comes into play, as it ushers in 1333FSB computing. This noticeable speed bump is all done while retaining the same TDP.
All Conroe 1333FSB processors are identified by by a 50 at the end of the product name, hence E6750, which is effectively taking over the spot of the E6700. Nothing has changed except for the FSB and speeds, except the ratio of course, which had to be altered in order to compliment the upgraded frequency.
One thing that should be cleared up is that most overclocking enthusiasts have already accomplished the same speeds we are seeing today, with most being exceeded. In fact, there is nothing stopping anyone from popping in an E6600 and overclocking using a 333FSB and 8 multiplier. That would effectively give you the exact same speed as the E6750 we are taking a look at today.
You might be wondering where the benefit is, with this official speed bump. Primarily it will benefit those non-overclockers most. There is no comparison to equal processor speed at 1066FSB and 1333FSB. That added FSB frequency should make a much more noticeable performance difference than the CPU frequency boost itself.
Intel Core 2 Extreme QX6850 Quad-Core
When Intel launched their P35 chipset two months ago, it ushered in not only DDR3 support, but also native 1333FSB support. This wasn't much of a surprise, since DDR3-1333 is a standard, and it's common to want to run 1:1 ratios with the FSB and memory frequency. We saw this with 800FSB CPUs and DDR2-800 memory and also 1066FSB CPUs with DDR2-1066 memory. The next big thing from Intel will be 1333FSB Penryn, which we have taken a look at in depth in previous months. To tide us over until then, Intel is launching refreshing parts of their Core 2 line-up to include native 1333FSB processors.
We took a look at their second-to-top offering a few weeks ago, in the form of a 2.66GHz E6750. Although it's an incredible CPU for the money, we already knew what to expect since it was a 'mere' speed bump and retained identical TDPs. You could take any Core 2 Duo and clock it to 1333FSB and have the same performance, in reality.
As I mentioned in that review, though, the biggest reason you should look forward to these new launches is because of their price points. The 2.66GHz E6750 will retail for around $200, which is an incredible thought considering what prices were set at last year. $200 will now get you a very powerful processor that will not be the bottleneck in gaming or other activities. In years past, you almost had to hand over $1,000 for a new CPU if you wanted ultimate performance. The Core 2 series has well proved itself since launch however, with even the budget offerings giving any enthusiast the performance they crave.
Those who don't enjoy overclocking, or are skeptical of the activity, are in luck because of the fact that they can still have a great CPU and not skip a car payment. But, despite the fact that there are powerful CPUs out there for reasonable prices, the Extreme line exists for two types of people. Those who want a top of the line processor without overclocking, and those who want to get every last ounce out of their overclocking. Because Extreme CPUs are binned higher, it's not unusual to see the top overclocks performed with them.
The only downside, of course, is the price. One has to wonder if the premium nowadays is truly worth it, considering the performance of the budget offerings can still be considered extreme by todays standards. Nothing stops overclockers from achieving the same frequencies with ease, either. Still, those who refuse to overclock for the sake of stability or what-have-you, but still want the best performance available, can't go wrong.
That's where the QX6850 comes into play, a 3.0GHz Core 2 Extreme that offers four cores to computing enthusiasts. This is the fastest Core 2 processor ever released, and in turn the fastest processor the market has to offer. Price as expected, is $999 in quantities of 1,000. You should expect to see it retail for closer to ~$1,250 at your favorite e-tailer, or even higher though. It's like buying a Ferrari, where paying $50,000 over SRP is not uncommon. This is just on a far smaller scale.
Although we are taking a look at the top offering for the 1333FSB processors, there will be a total of five being released immediately, with availability in the coming weeks. Below you will find the completely up-to-date line-up.
CPU Model
Clock Speed
FSB
L2 Cache
TDP
Cores
Intel Core 2 Extreme QX6850 3.0GHz 1333MHz 4MB x 2 130w 4
Intel Core 2 Extreme QX6800 2.93GHz 1066MHz 4MB x 2 130w 4
Intel Core 2 Quad Q6700 2.66GHz 1066MHz 4MB x 2 130w 4
Intel Core 2 Quad Q6600 2.40GHz 1066MHz 4MB x 2 105W 4
Intel Core 2 Duo E6850 3.0GHz 1333MHz 4MB 65W 2
Intel Core 2 Extreme X6800 2.93GHz 1066MHz 4MB 65W 2
Intel Core 2 Duo E6750 2.66GHz 1333MHz 4MB 65W 2
Intel Core 2 Duo E6700 2.60GHz 1066MHz 4MB 65W 2
Intel Core 2 Duo E6600 2.40GHz 1066MHz 4MB 65W 2
Intel Core 2 Duo E6550 2.33GHz 1333MHz 2MB 65W 2
Intel Core 2 Duo E6540 2.33GHz 1333MHz 2MB 65W 2
Intel Core 2 Duo E6400 2.13GHz 1066MHz 2MB 65W 2
Intel Core 2 Duo E6300 1.86GHz 1066MHz 2MB 65W 2
Intel Core 2 Duo E4500 2.2GHz 800MHz 2MB 65W 2
Intel Core 2 Duo E4400 2.0GHz 800MHz 2MB 65W 2
Intel Core 2 Duo E4300 1.80GHz 800MHz 2MB 65W 2
Compared to the previous top-end processor, the QX6850 has a 70MHz advantage. Though a non-impressive frequency boost, it should prove much faster than the QX6800 overall, thanks to the much-improved FSB frequency.
The first Extreme Quad-Core released late last year was the QX6700, clocking in at 2.66GHz. Because of this new launch, it is being re-released as the Q6700, meaning no unlocked multiplier. Its price will also be dropped, alongside the rest of the line-up.
Below is a table of just the new processors, with their prices in quantities of 1,000.
CPU Model
Clock Speed
FSB
L2 Cache
TDP
Cores
$1,000
Intel Core 2 Extreme QX6850 3.0GHz 1333MHz 4MB x 2 130w 4 $999
Intel Core 2 Quad Q6700 2.66GHz 1066MHz 4MB x 2 130w 4 $530
Intel Core 2 Duo E6850 3.0GHz 1333MHz 4MB 65W 2 $266
Intel Core 2 Duo E6750 2.66GHz 1333MHz 4MB 65W 2 $183
Intel Core 2 Duo E6550 2.33GHz 1333MHz 2MB 65W 2 $163
Also announced today is Intels first extreme mobile part, the X7800. Like the desktop counter-parts, this Extreme processor features an unlocked multiplier, so it's overclocking friendly. This dual-core CPU is clocked at 2.6GHz and features an 800MHz FSB and 4MB of L2 Cache. Like all other extreme offerings though, it doesn't come cheap, costing $851 to OEMs.
The 6x50 series will be available to consumers in two weeks time, through your favorite retailer or e-tailer. The X7800 mobile CPU is being sold to OEMs now, and should be available in various notebooks in the coming weeks.
With that, let's cover our testing methodology and then jump right into benchmarking.
We took a look at their second-to-top offering a few weeks ago, in the form of a 2.66GHz E6750. Although it's an incredible CPU for the money, we already knew what to expect since it was a 'mere' speed bump and retained identical TDPs. You could take any Core 2 Duo and clock it to 1333FSB and have the same performance, in reality.
As I mentioned in that review, though, the biggest reason you should look forward to these new launches is because of their price points. The 2.66GHz E6750 will retail for around $200, which is an incredible thought considering what prices were set at last year. $200 will now get you a very powerful processor that will not be the bottleneck in gaming or other activities. In years past, you almost had to hand over $1,000 for a new CPU if you wanted ultimate performance. The Core 2 series has well proved itself since launch however, with even the budget offerings giving any enthusiast the performance they crave.
Those who don't enjoy overclocking, or are skeptical of the activity, are in luck because of the fact that they can still have a great CPU and not skip a car payment. But, despite the fact that there are powerful CPUs out there for reasonable prices, the Extreme line exists for two types of people. Those who want a top of the line processor without overclocking, and those who want to get every last ounce out of their overclocking. Because Extreme CPUs are binned higher, it's not unusual to see the top overclocks performed with them.
The only downside, of course, is the price. One has to wonder if the premium nowadays is truly worth it, considering the performance of the budget offerings can still be considered extreme by todays standards. Nothing stops overclockers from achieving the same frequencies with ease, either. Still, those who refuse to overclock for the sake of stability or what-have-you, but still want the best performance available, can't go wrong.
That's where the QX6850 comes into play, a 3.0GHz Core 2 Extreme that offers four cores to computing enthusiasts. This is the fastest Core 2 processor ever released, and in turn the fastest processor the market has to offer. Price as expected, is $999 in quantities of 1,000. You should expect to see it retail for closer to ~$1,250 at your favorite e-tailer, or even higher though. It's like buying a Ferrari, where paying $50,000 over SRP is not uncommon. This is just on a far smaller scale.
Although we are taking a look at the top offering for the 1333FSB processors, there will be a total of five being released immediately, with availability in the coming weeks. Below you will find the completely up-to-date line-up.
CPU Model
Clock Speed
FSB
L2 Cache
TDP
Cores
Intel Core 2 Extreme QX6850 3.0GHz 1333MHz 4MB x 2 130w 4
Intel Core 2 Extreme QX6800 2.93GHz 1066MHz 4MB x 2 130w 4
Intel Core 2 Quad Q6700 2.66GHz 1066MHz 4MB x 2 130w 4
Intel Core 2 Quad Q6600 2.40GHz 1066MHz 4MB x 2 105W 4
Intel Core 2 Duo E6850 3.0GHz 1333MHz 4MB 65W 2
Intel Core 2 Extreme X6800 2.93GHz 1066MHz 4MB 65W 2
Intel Core 2 Duo E6750 2.66GHz 1333MHz 4MB 65W 2
Intel Core 2 Duo E6700 2.60GHz 1066MHz 4MB 65W 2
Intel Core 2 Duo E6600 2.40GHz 1066MHz 4MB 65W 2
Intel Core 2 Duo E6550 2.33GHz 1333MHz 2MB 65W 2
Intel Core 2 Duo E6540 2.33GHz 1333MHz 2MB 65W 2
Intel Core 2 Duo E6400 2.13GHz 1066MHz 2MB 65W 2
Intel Core 2 Duo E6300 1.86GHz 1066MHz 2MB 65W 2
Intel Core 2 Duo E4500 2.2GHz 800MHz 2MB 65W 2
Intel Core 2 Duo E4400 2.0GHz 800MHz 2MB 65W 2
Intel Core 2 Duo E4300 1.80GHz 800MHz 2MB 65W 2
Compared to the previous top-end processor, the QX6850 has a 70MHz advantage. Though a non-impressive frequency boost, it should prove much faster than the QX6800 overall, thanks to the much-improved FSB frequency.
The first Extreme Quad-Core released late last year was the QX6700, clocking in at 2.66GHz. Because of this new launch, it is being re-released as the Q6700, meaning no unlocked multiplier. Its price will also be dropped, alongside the rest of the line-up.
Below is a table of just the new processors, with their prices in quantities of 1,000.
CPU Model
Clock Speed
FSB
L2 Cache
TDP
Cores
$1,000
Intel Core 2 Extreme QX6850 3.0GHz 1333MHz 4MB x 2 130w 4 $999
Intel Core 2 Quad Q6700 2.66GHz 1066MHz 4MB x 2 130w 4 $530
Intel Core 2 Duo E6850 3.0GHz 1333MHz 4MB 65W 2 $266
Intel Core 2 Duo E6750 2.66GHz 1333MHz 4MB 65W 2 $183
Intel Core 2 Duo E6550 2.33GHz 1333MHz 2MB 65W 2 $163
Also announced today is Intels first extreme mobile part, the X7800. Like the desktop counter-parts, this Extreme processor features an unlocked multiplier, so it's overclocking friendly. This dual-core CPU is clocked at 2.6GHz and features an 800MHz FSB and 4MB of L2 Cache. Like all other extreme offerings though, it doesn't come cheap, costing $851 to OEMs.
The 6x50 series will be available to consumers in two weeks time, through your favorite retailer or e-tailer. The X7800 mobile CPU is being sold to OEMs now, and should be available in various notebooks in the coming weeks.
With that, let's cover our testing methodology and then jump right into benchmarking.
Intel Xeon X3210 2.13GHz Quad-Core B3-Revision
With last months launch of Intel's 6x50 series of processors also came price drops that everyone had been anticipating for months. Rumors were that you would be able to purchase a Quad-Core for close to $300, and to everyone's relief, it proved absolutely true. However, while most will run towards the Q6600, many will overlook the Xeon alternatives. While not normally clocked the same, they had price drops as well, and should not be ignored.
One of the more popular Xeon's that were noticed was the X3210, a Quad-Core clocked at 2.13GHz. While the clock speed leaves a bit to be desired for desktop users, it was hard to ignore the $250 price tag. This was at a time when Q6600s retailed for $280 - $300, so a small frequency drop could save you upwards of $30.
But, to say 'less expensive' almost seems silly. Just last year, an E6600 cost close to $400, while a Q6600 today retails for $300 or lower. It's a great time to be building a new computer, there's no doubt about that.
After last months price drops though, prices have fluctuated constantly. One day, the Q6600 might retail for $280 from your favorite e-tailer and then the next, you'll find it for $350. So needless to say, if you spot the CPU on the cheap, it's probably not the best idea to sit back and wait, if you want to secure it for the lowest price possible.
At the time of writing, US e-tailers are selling the Q6600 2.4GHz Quad-Core for an average price of $280.00, while the X3210 sits at closer to $260. At that point, if big overclocking is in the cards, then the Q6600 is well worth the extra $20, unless you happen to find a X3210 G0 revision. Ahh, revision hunting.
When Intel released G0 revision processors, it was a good day for enthusiasts. Every model seemed to overclock far beyond what was possible with previous revisions, so it's important to keep an eye out if overclocking is important to you. This is where things get tricky, however. If you are purchasing a processor from a random e-tailer, chances are good that it's a luck of the draw. However, you might be lucky enough to visit an e-tailer that will list the entire spec number.
One of the more popular Xeon's that were noticed was the X3210, a Quad-Core clocked at 2.13GHz. While the clock speed leaves a bit to be desired for desktop users, it was hard to ignore the $250 price tag. This was at a time when Q6600s retailed for $280 - $300, so a small frequency drop could save you upwards of $30.
But, to say 'less expensive' almost seems silly. Just last year, an E6600 cost close to $400, while a Q6600 today retails for $300 or lower. It's a great time to be building a new computer, there's no doubt about that.
After last months price drops though, prices have fluctuated constantly. One day, the Q6600 might retail for $280 from your favorite e-tailer and then the next, you'll find it for $350. So needless to say, if you spot the CPU on the cheap, it's probably not the best idea to sit back and wait, if you want to secure it for the lowest price possible.
At the time of writing, US e-tailers are selling the Q6600 2.4GHz Quad-Core for an average price of $280.00, while the X3210 sits at closer to $260. At that point, if big overclocking is in the cards, then the Q6600 is well worth the extra $20, unless you happen to find a X3210 G0 revision. Ahh, revision hunting.
When Intel released G0 revision processors, it was a good day for enthusiasts. Every model seemed to overclock far beyond what was possible with previous revisions, so it's important to keep an eye out if overclocking is important to you. This is where things get tricky, however. If you are purchasing a processor from a random e-tailer, chances are good that it's a luck of the draw. However, you might be lucky enough to visit an e-tailer that will list the entire spec number.
Intel Brands 'Nehalem' Processors as Intel Core
At the 2008 Intel Developer Forum, the IT community and PC enthusiasts will get a first look at the Intel Nehalem processor, which represents a whole new microarchitecture. Intel is also planning to brand its first "Nehalem" chips as Intel Core, and the first of these chips will appear in gaming PCs and high-end desktops.
Intel is planning to devote most of its energy at IDF on detailing the features behind its processor microarchitecture dubbed "Nehalem," including a new brand name for this upcoming family of desktop chips.
Intel is expected to officially brand the processors that will be built on the Nehalem architecture as Intel Core on Aug. 11. The first set of these microprocessors will be offered for gaming machines and high-end PCs, and the first processor will be an Extreme Edition chip called the Intel Core i7.
"The Core name is and will be our flagship PC processor brand going forward," said Sean Maloney, Intel's executive vice president and chief sales and marketing officer.
While Intel has focused most of its energy this year to bring its Atom processors to market to support whole new classes of devices, from low-cost "netbooks" to MIDs (Mobile Internet Devices), Nehalem is expected to be the biggest announcement the chip maker makes in 2008, and it will radically alter the company's approach to its chip microarchitecture.
Nehalem will allow Intel to create processors that can scale from two to eight cores. Each core supports two instructional threads that will then allow the chips to perform several tasks simultaneously. Intel will also introduce a new technology called QuickPath, a high-speed chip-to-chip interconnect technology that will allow the Nehalem family of processors to connect to another component or another chip on the motherboard.
Perhaps the greatest improvement with Nehalem is that Intel will integrate the memory controller—the part of the CPU that communicates with the DDR (double data rate) memory chips—into the processor die itself, which eliminates the traditional FSB (front side bus). This type of integration will allow for greater levels of performance without increasing the clock speed of the processor, which should also keep the thermal envelope the same as the previous generation.
"When you go to an integrated memory controller, you reduce a substantial portion of the memory latency between the processor, and the system memory and typically the initial access memory latency is a big determinant of performance," said Dean McCarron, founder of Mercury Research. "Typically, you can get a performance increase of anywhere between 10 and 25 percent when you fix that latency problem."
Advanced Micro Devices has been building processors with an integrated memory controller for a number of years now, and that chip design helped AMD close the gap between its processors and Intel's chips, McCarron said. Now, Intel is catching up and will eliminate one of the technological advantages AMD has enjoyed.
"When AMD introduced the integrated memory controller, it allowed them close the gap between them and Intel very rapidly," McCarron added. "With Intel doing this, the performance gains will probably not be as great as what happened with their competitor because Intel has fairly large caches, which cover up part of that problem. There is little question, however, that making this move results in substantially higher performance gains with no increase in clock rate, so you are getting more performance at the same clock speed."
Intel is planning to devote most of its energy at IDF on detailing the features behind its processor microarchitecture dubbed "Nehalem," including a new brand name for this upcoming family of desktop chips.
Intel is expected to officially brand the processors that will be built on the Nehalem architecture as Intel Core on Aug. 11. The first set of these microprocessors will be offered for gaming machines and high-end PCs, and the first processor will be an Extreme Edition chip called the Intel Core i7.
"The Core name is and will be our flagship PC processor brand going forward," said Sean Maloney, Intel's executive vice president and chief sales and marketing officer.
While Intel has focused most of its energy this year to bring its Atom processors to market to support whole new classes of devices, from low-cost "netbooks" to MIDs (Mobile Internet Devices), Nehalem is expected to be the biggest announcement the chip maker makes in 2008, and it will radically alter the company's approach to its chip microarchitecture.
Nehalem will allow Intel to create processors that can scale from two to eight cores. Each core supports two instructional threads that will then allow the chips to perform several tasks simultaneously. Intel will also introduce a new technology called QuickPath, a high-speed chip-to-chip interconnect technology that will allow the Nehalem family of processors to connect to another component or another chip on the motherboard.
Perhaps the greatest improvement with Nehalem is that Intel will integrate the memory controller—the part of the CPU that communicates with the DDR (double data rate) memory chips—into the processor die itself, which eliminates the traditional FSB (front side bus). This type of integration will allow for greater levels of performance without increasing the clock speed of the processor, which should also keep the thermal envelope the same as the previous generation.
"When you go to an integrated memory controller, you reduce a substantial portion of the memory latency between the processor, and the system memory and typically the initial access memory latency is a big determinant of performance," said Dean McCarron, founder of Mercury Research. "Typically, you can get a performance increase of anywhere between 10 and 25 percent when you fix that latency problem."
Advanced Micro Devices has been building processors with an integrated memory controller for a number of years now, and that chip design helped AMD close the gap between its processors and Intel's chips, McCarron said. Now, Intel is catching up and will eliminate one of the technological advantages AMD has enjoyed.
"When AMD introduced the integrated memory controller, it allowed them close the gap between them and Intel very rapidly," McCarron added. "With Intel doing this, the performance gains will probably not be as great as what happened with their competitor because Intel has fairly large caches, which cover up part of that problem. There is little question, however, that making this move results in substantially higher performance gains with no increase in clock rate, so you are getting more performance at the same clock speed."
Intel Adds Processors, Cuts Core 2 Quad, Xeon Prices
With the Intel Nehalem chip on its way, Intel is cutting the prices of some of its high-end desktop processors and adding some chips into its lineup. The new Intel chips include the Intel Core 2 Quad Q9650 processor for high-end and gaming desktop PCs.
Intel is slashing the prices on some of its high-end desktop PC and server processors and adding some new chips to its portfolio following the release of the chip maker’s naming scheme for Nehalem.
The changes to Intel’s chip pricing were officially released Aug. 10, and those changes include cutting the price of the high-end Intel Core 2 Quad Q9550 (2.83GHz) by 40 percent from $530 to $316. Intel also added a new Core 2 Quad chip into the mix called the Q9650 (3.0GHz) at a price of $530.
Other additions to the high-end lineup include the Intel Core 2 Quad Q9400 (2.66GHz) at a price of $266. All three of these desktop chips are built on the company’s 45-nanometer manufacturing process.
Intel also announced chip price cuts July 20.
The changes to Intel's processor listing come a day after the company released the new branding and naming scheme for the processors that will be built on Intel’s forthcoming Nehalem microarchitecture. Since Intel has said that the first of the Nehalem chips – the Core i7 – is destined for high-end PCs and gaming desktops, the changes allow Intel to drop the prices of some its older chips, while freeing up room in its pricing chart for its latest processors.
The Intel Developer Forum will kick off Aug. 19, and much of the discussion there will focus on Nehalem, which will allow Intel to build chips that scale for two to eight cores and have new features such as an integrated memory controller. By bringing the first of the Nehalem chips into the high-end PC space, it allows Intel to showcase the chips in a small, but influential part of the market before entering the mainstream.
The other part of the market that Nehalem processors are likely to show up first is in the single-socket server space, and Intel also made changes to its Xeon lineup. The chip maker added three new models, the Xeon X3370 (3.0GHz), the X3330 (2.66GHz) and the E3120 (3.16GHz). The prices for these chips are $530, $266, and $188 respectively.
Intel also cut the price of its Xeon X3360 (2.83) by 40 percent from $530 to $316. The X3370 now replaces this chip as the high-end of the single-socket server chip lineup.
Finally, Intel added two additional Core 2 Duo desktop chips into the lineup. These additions include the Core 2 Duo E8600 (3.33GHz) for $266 and the E7300 (2.66GHz) for $133.
All the new prices are calculated in 1,000-unit shipments.
Intel is slashing the prices on some of its high-end desktop PC and server processors and adding some new chips to its portfolio following the release of the chip maker’s naming scheme for Nehalem.
The changes to Intel’s chip pricing were officially released Aug. 10, and those changes include cutting the price of the high-end Intel Core 2 Quad Q9550 (2.83GHz) by 40 percent from $530 to $316. Intel also added a new Core 2 Quad chip into the mix called the Q9650 (3.0GHz) at a price of $530.
Other additions to the high-end lineup include the Intel Core 2 Quad Q9400 (2.66GHz) at a price of $266. All three of these desktop chips are built on the company’s 45-nanometer manufacturing process.
Intel also announced chip price cuts July 20.
The changes to Intel's processor listing come a day after the company released the new branding and naming scheme for the processors that will be built on Intel’s forthcoming Nehalem microarchitecture. Since Intel has said that the first of the Nehalem chips – the Core i7 – is destined for high-end PCs and gaming desktops, the changes allow Intel to drop the prices of some its older chips, while freeing up room in its pricing chart for its latest processors.
The Intel Developer Forum will kick off Aug. 19, and much of the discussion there will focus on Nehalem, which will allow Intel to build chips that scale for two to eight cores and have new features such as an integrated memory controller. By bringing the first of the Nehalem chips into the high-end PC space, it allows Intel to showcase the chips in a small, but influential part of the market before entering the mainstream.
The other part of the market that Nehalem processors are likely to show up first is in the single-socket server space, and Intel also made changes to its Xeon lineup. The chip maker added three new models, the Xeon X3370 (3.0GHz), the X3330 (2.66GHz) and the E3120 (3.16GHz). The prices for these chips are $530, $266, and $188 respectively.
Intel also cut the price of its Xeon X3360 (2.83) by 40 percent from $530 to $316. The X3370 now replaces this chip as the high-end of the single-socket server chip lineup.
Finally, Intel added two additional Core 2 Duo desktop chips into the lineup. These additions include the Core 2 Duo E8600 (3.33GHz) for $266 and the E7300 (2.66GHz) for $133.
All the new prices are calculated in 1,000-unit shipments.
Intel Core 2 Duo E8400 3.0GHz - Wolfdale Arrives
In the summer of 2006, Intel released their 65nm Conroe-based processors, and to say they won the hearts of many would be an understatement. It was one product-launch that Intel didn't want to hit lightly, especially since AMD were actively taking from their customer base - on the enthusiast side, most notably. When said and done, Intel did accomplish what they planned to do. They put the industry through a blender and showed us how to be excited about processors again.
Although frequencies with Conroe were not as high as what we were used to seeing from Intel, the folks in Santa Clara proved that a high frequency didn't mean much if the processor itself was inefficient. Indeed, a 2.4GHz Conroe Dual-Core proved just how much better an efficient processor could be, and it quickly became the most common processor choice for the enthusiast.
The following summer, follow-up processors were released, including the E6750 Dual-Core which we evaluated at the time. Besides speed bumps, those processors didn't bring much to the table in way of new features, except for native 1333FSB support. Instead, the processor we are taking a look at today is one of the few new models that effectively replace the Conroe-based chips that we came to love so dearly in summer of '06.
I won't delve deep into how 45nm improves on 65nm, as I explained all of that in our QX9650 review, but I will touch on things briefly. One large benefit that comes with all die shrinks is better power efficiency and lower temperatures. Chips have the capability to run just as fast, if not faster, than their predecessors, all while running cooler and drawing less power. It's a win/win situation.
But with 45nm, Intel introduced more than just a die shrink. The biggest feature that most people will be interested in is the SSE4 instruction set. It affects media-buffs only - those who encode videos - but the performance gains are so evident, that developers of such applications are bound to begin supporting it sooner than later. The speed increases could be as large as 2x, even though it's difficult to believe.
Other improvements include increased L2 cache, half-multipliers (eg, 9.5x), a faster front-side-bus, improved Super Shuffle Engine, Smart Cache (to improve how split loads are accessed and stored) and so many transistors on a single die, it can give people headaches to think about it!
The obvious downside of the QX9650 launch in November was the fact that no other processors complimented it. Therefore, it was QX9650 or bust - until now that is. During CES earlier this month, Intel officially announced their 45nm launch plans, which include the desktop side, server and also mobile. We found out at that time that the Quad-Core models (Q9300 - Q9550) were pushed back to sometime in Q1. Although a solid date was never settled on, original road maps showed January as the scheduled launch. However, the rumor is that due to poor performing Phenom Quad-Core sales, Intel decided to hold off on the launch to help push remaining 65nm models to consumers first.
So how does the road map stand now that some time has past? Although Intel announced near-immediate availability of all 45nm desktop Dual-Cores at CES, only the E8400 has shown up on e-tailers. One popular e-tailer has the other models listed for availability in April. How true that is, I'm unsure, but it's strange given the fact that they were supposed to be available by now.
Processor Name
Cores
Clock
Cache
FSB
TDP
1Ku Price
Available
Intel Core 2 Extreme QX9775
4
3.20GHz
2 x 6MB
1600MHz
150W
$1,499
Q1 2008
Intel Core 2 Extreme QX9770
4
3.20GHz
2 x 6MB
1600MHz
136W
$1,399
Q1 2008
Intel Core 2 Extreme QX9650
4
3.0GHz
2 x 6MB
1333MHz
130W
$999
Now
Intel Core 2 Quad Q9550
4
2.86GHz
2 x 6MB
1333MHz
95W
$530
Q1 2008
Intel Core 2 Quad Q9450
4
2.66GHz
2 x 6MB
1333MHz
95W
$316
Q1 2008
Intel Core 2 Quad Q9300
4
2.5GHz
2 x 3MB
1333MHz
95W
$266
Q1 2008
Intel Core 2 Duo E8500
2
3.16GHz
6MB
1333MHz
65W
$266
Jan 2008
Intel Core 2 Duo E8400
2
3.00GHz
6MB
1333MHz
65W
$183
Now
Intel Core 2 Duo E8200
2
2.66GHz
6MB
1333MHz
65W
$163
Jan 2008
Intel Core 2 Duo E8190
2
2.66GHz
6MB
1333MHz
65W
$163
Jan 2008
The biggest downside to the road map is that the Q9xxx are not available. Once they are, they are no doubt going to sell like hotcakes, given the improvements over the previous generation and the fact that the prices do not increase. The upside, though, is that even though the E8400 is the lone desktop Dual-Core to be available right now, we can be happy that it is the model most people would be after.
What makes the E8400 such a great choice is the fact that it's affordable, at $220USD on average, and has a nice clock speed. Let's face it... where overclocking is not concerned, having a 3.0GHz CPU looks better to the ego than say, 2.66GHz. It's all about the smooth frequencies, baby.
Although frequencies with Conroe were not as high as what we were used to seeing from Intel, the folks in Santa Clara proved that a high frequency didn't mean much if the processor itself was inefficient. Indeed, a 2.4GHz Conroe Dual-Core proved just how much better an efficient processor could be, and it quickly became the most common processor choice for the enthusiast.
The following summer, follow-up processors were released, including the E6750 Dual-Core which we evaluated at the time. Besides speed bumps, those processors didn't bring much to the table in way of new features, except for native 1333FSB support. Instead, the processor we are taking a look at today is one of the few new models that effectively replace the Conroe-based chips that we came to love so dearly in summer of '06.
I won't delve deep into how 45nm improves on 65nm, as I explained all of that in our QX9650 review, but I will touch on things briefly. One large benefit that comes with all die shrinks is better power efficiency and lower temperatures. Chips have the capability to run just as fast, if not faster, than their predecessors, all while running cooler and drawing less power. It's a win/win situation.
But with 45nm, Intel introduced more than just a die shrink. The biggest feature that most people will be interested in is the SSE4 instruction set. It affects media-buffs only - those who encode videos - but the performance gains are so evident, that developers of such applications are bound to begin supporting it sooner than later. The speed increases could be as large as 2x, even though it's difficult to believe.
Other improvements include increased L2 cache, half-multipliers (eg, 9.5x), a faster front-side-bus, improved Super Shuffle Engine, Smart Cache (to improve how split loads are accessed and stored) and so many transistors on a single die, it can give people headaches to think about it!
The obvious downside of the QX9650 launch in November was the fact that no other processors complimented it. Therefore, it was QX9650 or bust - until now that is. During CES earlier this month, Intel officially announced their 45nm launch plans, which include the desktop side, server and also mobile. We found out at that time that the Quad-Core models (Q9300 - Q9550) were pushed back to sometime in Q1. Although a solid date was never settled on, original road maps showed January as the scheduled launch. However, the rumor is that due to poor performing Phenom Quad-Core sales, Intel decided to hold off on the launch to help push remaining 65nm models to consumers first.
So how does the road map stand now that some time has past? Although Intel announced near-immediate availability of all 45nm desktop Dual-Cores at CES, only the E8400 has shown up on e-tailers. One popular e-tailer has the other models listed for availability in April. How true that is, I'm unsure, but it's strange given the fact that they were supposed to be available by now.
Processor Name
Cores
Clock
Cache
FSB
TDP
1Ku Price
Available
Intel Core 2 Extreme QX9775
4
3.20GHz
2 x 6MB
1600MHz
150W
$1,499
Q1 2008
Intel Core 2 Extreme QX9770
4
3.20GHz
2 x 6MB
1600MHz
136W
$1,399
Q1 2008
Intel Core 2 Extreme QX9650
4
3.0GHz
2 x 6MB
1333MHz
130W
$999
Now
Intel Core 2 Quad Q9550
4
2.86GHz
2 x 6MB
1333MHz
95W
$530
Q1 2008
Intel Core 2 Quad Q9450
4
2.66GHz
2 x 6MB
1333MHz
95W
$316
Q1 2008
Intel Core 2 Quad Q9300
4
2.5GHz
2 x 3MB
1333MHz
95W
$266
Q1 2008
Intel Core 2 Duo E8500
2
3.16GHz
6MB
1333MHz
65W
$266
Jan 2008
Intel Core 2 Duo E8400
2
3.00GHz
6MB
1333MHz
65W
$183
Now
Intel Core 2 Duo E8200
2
2.66GHz
6MB
1333MHz
65W
$163
Jan 2008
Intel Core 2 Duo E8190
2
2.66GHz
6MB
1333MHz
65W
$163
Jan 2008
The biggest downside to the road map is that the Q9xxx are not available. Once they are, they are no doubt going to sell like hotcakes, given the improvements over the previous generation and the fact that the prices do not increase. The upside, though, is that even though the E8400 is the lone desktop Dual-Core to be available right now, we can be happy that it is the model most people would be after.
What makes the E8400 such a great choice is the fact that it's affordable, at $220USD on average, and has a nice clock speed. Let's face it... where overclocking is not concerned, having a 3.0GHz CPU looks better to the ego than say, 2.66GHz. It's all about the smooth frequencies, baby.
AMD Phenom X3 8750 Triple-Core Processor Review
AMD announced the availability of three new AMD Phenom X3 triple-core processors that feature the latest B3 stepping. AMD first announced triple-core processors back in September 2007, but only just recently launched the AMD Phenom X3 8000 series last month. As the world's only triple-core x86 desktop processor, the Phenom X3 processors make for a very interesting product, but enthusiasts and consumers that follow processor launches had some concerns about the new triple-core processors. AMD states that the triple-core processors integrate three computational cores on a single die of silicon, but in reality it is a quad-core processor with one of the cores disabled. The initial batch of triple-core processors also suffered from the same TLB erratum that was found on the quad-cores since they made from the same B2 die steppings. When AMD announced the 50-series of quad-core processors they brought hope to AMD fans around the world as the TLB erratum was fixed thanks to a new and improved B3 stepping. AMD has finally brought the 'B3' stepping to the triple-cores and has announced three new AMD Phenom X3 triple-core processors that make up the new '50-series'. Without further ado here are the new AMD Phenom X3 processors and their price points.
• AMD Phenom X3 8750 triple-core processor - (2.4GHz) - $195
• AMD Phenom X3 8650 triple-core processor - (2.3GHz) - $165
• AMD Phenom X3 8450 triple-core processor - (2.1GHz) - $145
As you can see triple-core pricing starts at $145 for the 2.1GHz Phenom X3 8450 to $195 for the top end 2.4GHz Phenom X3 8750 triple-core processor. While these prices are very competitive, they are really close to that of the AMD Phenom X4 series. For example the AMD Phenom X4 9750 Quad-Core Processor is currently $214.99 shipped on our shopping service. Is it worth the extra $20 to get a quad-core or should one save the cash and go triple-core? You also have the2.2GHz Phenom X4 9550 for the same exact price of $195 plus shipping. If that question isn't tough keep in mind that Intel just cut prices this week, so now you have the 3GHz Intel E6850 for $183 and the 2.4GHz Intel Q6600 for $224.
The processor we will be looking at today is the AMD Phenom X3 8750 triple-core processor. The AMD Phenom X3 8750 is a 2.4GHz processor manufactured using AMD's 65nm Silicon on Insulator process technology. The chip has a Max TDP of 95W and has official support for a 1.8GHz memory controller and HT 3.0 frequency with Dual Dynamic Power Management technology. AMD informed Legit Reviews that they do have higher clock frequencies on the road map later this year as well as 65W Phenom X3 triple-core processors. The 65W triple-core processors will be aimed at HTPC users and those looking to build energy efficient computers. AMD will continue to expand and introduce new Phenom X3 processors in the months ahead, so expect to see and hear more about them!
• AMD Phenom X3 8750 triple-core processor - (2.4GHz) - $195
• AMD Phenom X3 8650 triple-core processor - (2.3GHz) - $165
• AMD Phenom X3 8450 triple-core processor - (2.1GHz) - $145
As you can see triple-core pricing starts at $145 for the 2.1GHz Phenom X3 8450 to $195 for the top end 2.4GHz Phenom X3 8750 triple-core processor. While these prices are very competitive, they are really close to that of the AMD Phenom X4 series. For example the AMD Phenom X4 9750 Quad-Core Processor is currently $214.99 shipped on our shopping service. Is it worth the extra $20 to get a quad-core or should one save the cash and go triple-core? You also have the2.2GHz Phenom X4 9550 for the same exact price of $195 plus shipping. If that question isn't tough keep in mind that Intel just cut prices this week, so now you have the 3GHz Intel E6850 for $183 and the 2.4GHz Intel Q6600 for $224.
The processor we will be looking at today is the AMD Phenom X3 8750 triple-core processor. The AMD Phenom X3 8750 is a 2.4GHz processor manufactured using AMD's 65nm Silicon on Insulator process technology. The chip has a Max TDP of 95W and has official support for a 1.8GHz memory controller and HT 3.0 frequency with Dual Dynamic Power Management technology. AMD informed Legit Reviews that they do have higher clock frequencies on the road map later this year as well as 65W Phenom X3 triple-core processors. The 65W triple-core processors will be aimed at HTPC users and those looking to build energy efficient computers. AMD will continue to expand and introduce new Phenom X3 processors in the months ahead, so expect to see and hear more about them!
AMD Phenom X4 9850 Processor Review - B3 Stepping
When the AMD Phenom series of processors launched back on November 19th, 2007 no one could have expected just how rough things were about to get for AMD. First, they sent out Phenom 9900 processors to the press that were was unable to keep up with the Intel Core 2 series of processors. Second, the Phenom 9700/9800/9900 processors that AMD sent out to the media were pulled at the last second and replaced with the lower clocked Phenom 9600 (2.3GHz) and Phenom 9500 (2.2GHz). Then after the Phenom series was lauched it got caught up in the TLB erratum 298 controversy and found itself plauged by benchmark problems. On top of all this AMD kept telling the media, who in turn told consumers, that everything was fine and AMD was on track to deliver the Phenom 9700 and 9800 later in Q1 with a new 3GHz model in Q2 of 2008.
AMD is committed to bring quad-core to the desktop market in Q4, and we are meeting that commitment with the launch of AMD Phenom quad-core processors 9500 and 9600 (2.2GHz and 2.3GHz) on Nov. 19th. AMD is going to initially introduce these two mainstream AMD Phenom quad-core processor models in order to satisfy customer demand in 2007. Since the October meeting, AMD has decided to launch our AMD Phenom 9700 (2.4GHz) quad core product in Q1 2008, along with our AMD Phenom 9900 (2.6 GHz) quad core processor. The launch of these two higher performance processors models will coincide with the introduction of related, significant performance enhancements in the platform; namely CrossFireX and our new enthusiast graphics product. Higher performance AMD Phenom processors will follow the introduction of the AMD Phenom 9700 and 9900 models, with a 3.0 GHz model in Q2 2008. AMD has a great history of delivering faster parts through a product’s lifecycle, and we are confident that this will remain true. - AMD PR 11/14/2007
The past four months could not have gone by fast enough for Advanced Micro Devices (AMD), but there does seem to be a new hope for Phenom as the latest revision of the core (stepping B3) fixes the TLB erratum along with many other erratums that were on the list. The TLB fix is now done at the silicon level, so the performance hit users were seeing with the BIOS workaround should be gone. AMD has now stopped production on the older core steppings as a result of this change. If you see a Phenom 9500 or Phenom 9600 in a system or for sale at a retailer you know that the procesor is a B1 or B2 stepping that has the TLB issue. All of the new Phenom B3 steppings will be named with the nomenclature of what AMD is calling the '50 series' of processors. The four new AMD Phenom X4 processors that AMD is announcing today are the 9550 (2.2GHz), 9650 (2.3GHz), 9750 (2.4GHz) and 9850 Black Edition (2.5GHz). AMD has told us to expect the new 50-series processors to perform the same, clock-for-clock as older revision (B2) processors operating in a platform that is not implementing the TLB erratum fix. For example, the 2.2GHz Phenom 9550 processor will replace the Phenom 9500 (B2) processor. AMD is basically 'fixing' Phenom and is making the model numbers clear to make sure consumers know what processors they are getting without having to open the retail box.
Our Phenom 9600 Black Edition on the left has been the fastest Phenom X4 processor that money could buy for a number of months now, but it is being replaced by the Phenom X4 9850 Black Edition processor that is seen above on the right. What is shocking is the fact that our Phenom X4 9850 Black Edition has a production date code of the tenth week of 2008. It is obvious that AMD was in a hurry to get these in our hand just days after these rolled off the production line.
The AMD Phenom X4 9850 that we will be benchmarking today is a 2.5GHz processor manufactured using AMD's 65nm Silicon on Insulator process technology. The chip has a Max TDP of 125W and it is a 'Black Edition', which means its multiplier is unlocked for better overclocking. Since the bus speed can't be raised that high on Phenom processors the best way to overclock is by increasing the multipler and the Black Edition was designed just for that. The one feature that is new and exclusive to just the AMD Phenom X4 9850 processor is a 2.0GHz memory controller.
AMD is committed to bring quad-core to the desktop market in Q4, and we are meeting that commitment with the launch of AMD Phenom quad-core processors 9500 and 9600 (2.2GHz and 2.3GHz) on Nov. 19th. AMD is going to initially introduce these two mainstream AMD Phenom quad-core processor models in order to satisfy customer demand in 2007. Since the October meeting, AMD has decided to launch our AMD Phenom 9700 (2.4GHz) quad core product in Q1 2008, along with our AMD Phenom 9900 (2.6 GHz) quad core processor. The launch of these two higher performance processors models will coincide with the introduction of related, significant performance enhancements in the platform; namely CrossFireX and our new enthusiast graphics product. Higher performance AMD Phenom processors will follow the introduction of the AMD Phenom 9700 and 9900 models, with a 3.0 GHz model in Q2 2008. AMD has a great history of delivering faster parts through a product’s lifecycle, and we are confident that this will remain true. - AMD PR 11/14/2007
The past four months could not have gone by fast enough for Advanced Micro Devices (AMD), but there does seem to be a new hope for Phenom as the latest revision of the core (stepping B3) fixes the TLB erratum along with many other erratums that were on the list. The TLB fix is now done at the silicon level, so the performance hit users were seeing with the BIOS workaround should be gone. AMD has now stopped production on the older core steppings as a result of this change. If you see a Phenom 9500 or Phenom 9600 in a system or for sale at a retailer you know that the procesor is a B1 or B2 stepping that has the TLB issue. All of the new Phenom B3 steppings will be named with the nomenclature of what AMD is calling the '50 series' of processors. The four new AMD Phenom X4 processors that AMD is announcing today are the 9550 (2.2GHz), 9650 (2.3GHz), 9750 (2.4GHz) and 9850 Black Edition (2.5GHz). AMD has told us to expect the new 50-series processors to perform the same, clock-for-clock as older revision (B2) processors operating in a platform that is not implementing the TLB erratum fix. For example, the 2.2GHz Phenom 9550 processor will replace the Phenom 9500 (B2) processor. AMD is basically 'fixing' Phenom and is making the model numbers clear to make sure consumers know what processors they are getting without having to open the retail box.
Our Phenom 9600 Black Edition on the left has been the fastest Phenom X4 processor that money could buy for a number of months now, but it is being replaced by the Phenom X4 9850 Black Edition processor that is seen above on the right. What is shocking is the fact that our Phenom X4 9850 Black Edition has a production date code of the tenth week of 2008. It is obvious that AMD was in a hurry to get these in our hand just days after these rolled off the production line.
The AMD Phenom X4 9850 that we will be benchmarking today is a 2.5GHz processor manufactured using AMD's 65nm Silicon on Insulator process technology. The chip has a Max TDP of 125W and it is a 'Black Edition', which means its multiplier is unlocked for better overclocking. Since the bus speed can't be raised that high on Phenom processors the best way to overclock is by increasing the multipler and the Black Edition was designed just for that. The one feature that is new and exclusive to just the AMD Phenom X4 9850 processor is a 2.0GHz memory controller.
AMD Phenom 9600 Black Edition
Enthusiast products probably come under more scrutiny than most other products, and for good reason. When something is advertised to run faster, clock higher, or pretty much be the best of any product that is marketed, you expect it to be so. Even if the product is only that for a short time, you just expect great results.
There was a lot of hype surrounding the AMD Phenom processors long before they actually launched. There was also a great hope that AMD would be on the comeback trail and once again be competitive against Intel. Well, by now everyone knows that not only did the Phenom let us down as far being a competitive product when up against a similar Intel CPU, but the release of the first generation of Phenom CPU's had issues that caused grief among consumers.
Not long after the initial release of the Phenom CPUs, AMD introduced a Black Edition for overclockers. At least, that is what was assumed by many in the enthusiast crowd. To their credit, AMD was not charging any more for these (even if retailers were).
So what did the release of the Black Edition mean? It meant that you were getting a CPU that had unlocked multipliers which can be a true dream to those that like to just absolutely push their systems to the max. A low multiplier and a high front side bus or HTT is what overclockers dream of. But we want to make one thing clear from the beginning of this article. Phenom is not built for high HTT settings. Our overclocking endeavors were actually very frustrating because of this. With that in mind, it is obvious why AMD wanted to release this part with unlocked multipliers and why they are not charging any extra. If you want to overclock Phenom at all, your best bet is to be able to raise the multiplier. I know I am giving away the rest of the article here, but I think it is important to say this right up front. It is what it is!
It is really hard to figure out what to say to end this article. Most people will probably buy this CPU thinking that it will be an overclocking beast, and that they are guaranteed to get 3.0GHz out of it. If that is what you are thinking, you will be sorely displeased. Think about it, if 3.0GHz was automatic, why have we not seen any speed bumps for the Phenom actually released yet? Truth be told, AMD is having a hard time with these parts. The TLB problems have not helped, and being so sensitive to the higher bus speeds is certainly a hindrance to any serious overclocker. When it comes down to it, you should consider yourself lucky any time you get anything extra out of a CPU, and you can take that statement to the 10th degree for Phenom.
There was a lot of hype surrounding the AMD Phenom processors long before they actually launched. There was also a great hope that AMD would be on the comeback trail and once again be competitive against Intel. Well, by now everyone knows that not only did the Phenom let us down as far being a competitive product when up against a similar Intel CPU, but the release of the first generation of Phenom CPU's had issues that caused grief among consumers.
Not long after the initial release of the Phenom CPUs, AMD introduced a Black Edition for overclockers. At least, that is what was assumed by many in the enthusiast crowd. To their credit, AMD was not charging any more for these (even if retailers were).
So what did the release of the Black Edition mean? It meant that you were getting a CPU that had unlocked multipliers which can be a true dream to those that like to just absolutely push their systems to the max. A low multiplier and a high front side bus or HTT is what overclockers dream of. But we want to make one thing clear from the beginning of this article. Phenom is not built for high HTT settings. Our overclocking endeavors were actually very frustrating because of this. With that in mind, it is obvious why AMD wanted to release this part with unlocked multipliers and why they are not charging any extra. If you want to overclock Phenom at all, your best bet is to be able to raise the multiplier. I know I am giving away the rest of the article here, but I think it is important to say this right up front. It is what it is!
It is really hard to figure out what to say to end this article. Most people will probably buy this CPU thinking that it will be an overclocking beast, and that they are guaranteed to get 3.0GHz out of it. If that is what you are thinking, you will be sorely displeased. Think about it, if 3.0GHz was automatic, why have we not seen any speed bumps for the Phenom actually released yet? Truth be told, AMD is having a hard time with these parts. The TLB problems have not helped, and being so sensitive to the higher bus speeds is certainly a hindrance to any serious overclocker. When it comes down to it, you should consider yourself lucky any time you get anything extra out of a CPU, and you can take that statement to the 10th degree for Phenom.
Intel's New Core 2 Duo Processors Run Blazingly Fast
In our WorldBench 5 test suite, Intel's Core 2 Duo reference system outscored a matching system equipped with AMD's high-end Athlon 64 FX-62 chip by 17 percent. We also tested shipping PCs based on several chips in the Core 2 Duo family, including a water-cooled, overclocked ABS machine that posted a mark of 181 on our WorldBench 5 test--the highest WorldBench score we've ever seen. (See PC World's detailed test results and chart. For full reviews of five new Core 2 Duo-based systems, click the product names in the results chart.)
All of our Core 2 Duo configurations performed impressively, and the higher-end models in particular should allow power users to handle demanding multimedia work on their PCs more quickly and to perform multiple computing tasks at once more efficiently. Gaming, too, will receive an impressive boost from systems equipped with the new chips.
Though its new products are good news for users, things are different for some Intel employees, as the company announced the layoff of 1000 management employees.
The Core 2 Duo processor line ranges from the 1.86-GHz E6300 chip ($183) with 2MB of cache to the 2.93-GHz Core 2 Extreme X6800 chip ($999) with 4MB of cache; all have a 1066-MHz system bus. (Intel leaves the "Duo" designation off of its X6800 CPU.)
Though Core 2 Duo chips use the same Socket 775 interface as current Pentium 4 and Pentium D chips, they require new chip sets, so you'll have to get a new motherboard--you can't just pop a Core 2 Duo chip into your existing Intel-based PC and reap the tremendous performance gains. The Core 2 Duo reference systems we tested used a motherboard with Intel's 975X Express chip set (boards using the P965 Express chip set will also be available); nVidia and ATI have their own Core 2 Duo boards as well.
The new processors and systems will be on sale from various vendors beginning July 27, with some configurations of Core 2 Duo machines checking in at surprisingly reasonable prices.
Our motherboard Core 2 Duo test setup consisted of an Intel 975X Express board, 2GB of DDR2-667 memory, a pair of SATA hard drives configured in a striped array, and an nVidia GeForce 7800GT-based graphics card. We swapped first a 2.93-GHz Core 2 Extreme X6800 chip and then a 2.67-GHz Core 2 E6700 chip into that setup to generate scores we could compare directly to an otherwise identically configured system featuring AMD's new DDR2-capable AM2 platform and its top-of-the-line FX-62 processor.
Both of the Intel setups bested the AMD-based system on every test in our WorldBench 5 suite as well as on every one of our gaming tests (see chart below). The improvement on WorldBench 5's multitasking tests, which involve running a Web browsing session in Mozilla while encoding a file with Windows Media Encoder, was particularly dramatic. You'll also see notable gains in Photoshop and similar graphics applications.
In addition to our lab-built systems, we tested several vendor-supplied PCs. For example, Dell's $3985 XPS 700, a high-end system based on the 2.67-GHz Duo E6700 processor, came with 2GB of RAM, an nVidia GeForce 7950 GX2 Dual-GPU graphics board with 1GB of SDRAM, and two 320GB SATA hard drives in a Raid 0 array. That system (whose price includes a 24-inch wide-screen monitor) also earned a score of 153 on WorldBench 5, well ahead of the 142 posted by the previous top scorer, a 2.6-GHz AMD Athlon 64 FX-60-based Xi system.
Dell's $2350 XPS 410--a relatively mainstream system based on the midrange 2.4-GHz E6600 CPU--shipped with 2GB of RAM, an nVidia GeForce 7900GS graphics board, and two 320GB SATA drives configured in a Raid 0 array. That machine (whose price includes a 20-inch wide-screen LCD) earned a score of 138 on WorldBench 5, matching the score posted by AMD's high-end FX-62 chip on our motherboard test bed.
But even those notable scores paled in comparison to the performance of the overclocked system that ABS sent us. The $4199 water-cooled ABS Ultimate X9--which shipped with 2GB of RAM, a pair of Radeon X1900 Crossfire graphics boards, two superfast Western Digital 150GB SATA drives configured in a striped RAID array, and a Core 2 Extreme X6800 chip overclocked from 2.93 GHz to run at 3.5 GHz--turned in a WorldBench 5 score of 181. Obviously, this system is not a likely choice for typical buyers, but its score is by far the highest we've seen from a shipping system. And it may indicate how much headroom Intel's Core microarchitecture possesses.
All of our Core 2 Duo configurations performed impressively, and the higher-end models in particular should allow power users to handle demanding multimedia work on their PCs more quickly and to perform multiple computing tasks at once more efficiently. Gaming, too, will receive an impressive boost from systems equipped with the new chips.
Though its new products are good news for users, things are different for some Intel employees, as the company announced the layoff of 1000 management employees.
The Core 2 Duo processor line ranges from the 1.86-GHz E6300 chip ($183) with 2MB of cache to the 2.93-GHz Core 2 Extreme X6800 chip ($999) with 4MB of cache; all have a 1066-MHz system bus. (Intel leaves the "Duo" designation off of its X6800 CPU.)
Though Core 2 Duo chips use the same Socket 775 interface as current Pentium 4 and Pentium D chips, they require new chip sets, so you'll have to get a new motherboard--you can't just pop a Core 2 Duo chip into your existing Intel-based PC and reap the tremendous performance gains. The Core 2 Duo reference systems we tested used a motherboard with Intel's 975X Express chip set (boards using the P965 Express chip set will also be available); nVidia and ATI have their own Core 2 Duo boards as well.
The new processors and systems will be on sale from various vendors beginning July 27, with some configurations of Core 2 Duo machines checking in at surprisingly reasonable prices.
Our motherboard Core 2 Duo test setup consisted of an Intel 975X Express board, 2GB of DDR2-667 memory, a pair of SATA hard drives configured in a striped array, and an nVidia GeForce 7800GT-based graphics card. We swapped first a 2.93-GHz Core 2 Extreme X6800 chip and then a 2.67-GHz Core 2 E6700 chip into that setup to generate scores we could compare directly to an otherwise identically configured system featuring AMD's new DDR2-capable AM2 platform and its top-of-the-line FX-62 processor.
Both of the Intel setups bested the AMD-based system on every test in our WorldBench 5 suite as well as on every one of our gaming tests (see chart below). The improvement on WorldBench 5's multitasking tests, which involve running a Web browsing session in Mozilla while encoding a file with Windows Media Encoder, was particularly dramatic. You'll also see notable gains in Photoshop and similar graphics applications.
In addition to our lab-built systems, we tested several vendor-supplied PCs. For example, Dell's $3985 XPS 700, a high-end system based on the 2.67-GHz Duo E6700 processor, came with 2GB of RAM, an nVidia GeForce 7950 GX2 Dual-GPU graphics board with 1GB of SDRAM, and two 320GB SATA hard drives in a Raid 0 array. That system (whose price includes a 24-inch wide-screen monitor) also earned a score of 153 on WorldBench 5, well ahead of the 142 posted by the previous top scorer, a 2.6-GHz AMD Athlon 64 FX-60-based Xi system.
Dell's $2350 XPS 410--a relatively mainstream system based on the midrange 2.4-GHz E6600 CPU--shipped with 2GB of RAM, an nVidia GeForce 7900GS graphics board, and two 320GB SATA drives configured in a Raid 0 array. That machine (whose price includes a 20-inch wide-screen LCD) earned a score of 138 on WorldBench 5, matching the score posted by AMD's high-end FX-62 chip on our motherboard test bed.
But even those notable scores paled in comparison to the performance of the overclocked system that ABS sent us. The $4199 water-cooled ABS Ultimate X9--which shipped with 2GB of RAM, a pair of Radeon X1900 Crossfire graphics boards, two superfast Western Digital 150GB SATA drives configured in a striped RAID array, and a Core 2 Extreme X6800 chip overclocked from 2.93 GHz to run at 3.5 GHz--turned in a WorldBench 5 score of 181. Obviously, this system is not a likely choice for typical buyers, but its score is by far the highest we've seen from a shipping system. And it may indicate how much headroom Intel's Core microarchitecture possesses.
Intel Core 2 Extreme: 1333MHz PSB
In our Intel Core 2 (Conroe) Performance Review article, we briefly mentioned about the initial rumors of the Core 2 Extreme clocks. There was talk about it debuting at 3.33GHz on a 1333MHz PSB, but of course that didn't happen. While we're in no position to pout about the Core 2 Extreme X6800, especially after seeing its performance, we couldn't get rid of that nagging feeling that the X6800 just wasn't extreme enough since it was just a multiplier increment over the regular Core 2 Duo E6700.
We wanted to satisfy our curiosity as to how the Core 2 Extreme would perform if it did meet the speculated specifications on release. Our overclocking platform of choice - Gigabyte's GA-965P-DQ6. At the present moment, we find that many initial Core 2 motherboards' BIOS do not properly detect Core 2 processor capabilities, sometimes restricting multiplier selection and others lack the necessary voltage and tweaking selections. The GA-965P-DQ6 happens to be one of the better boards to support the unlocked X6800 and possess great voltage granularity, a perfect combination for our overclocking efforts.
To do this, we overclocked the Core 2 Extreme X6800 to the ideal 3.33GHz with a 1333MHz PSB using a 333x10 FSB to CPU multiplier ratio and then topped it off with DDR2-1066 memory.
Maximum Overclocking
Next, we did some real overclocking to see just how scalable the Core microarchitecture can be. Intel's Netburst has produced scalable processors with good overclockability, but are bogged down by high power consumption and operating temperatures. The Core 2 is almost a total opposite, starting at modest sub-2GHz speeds. The Core microarchitecture's short pipelines would have reduced the processors scalability in terms of frequency, but its ultra efficient power consumption and low thermals should give it plenty of room.
In our overclocking tests, we took the same Core 2 Extreme X6800 and went all out to see just how far we could push the processor on stock Intel air-cooling. That's right, we didn't use fancy third-party coolers for this nor did we rely on exotic cooling techniques. The standard Intel boxed processor cooler was used to realistically set a stage for overclocking bandwidth right out of the box.
Our result? A final clock of 3.60GHz at 360x10. Not exactly the best overclock on the Conroe core, but it nearly puts the Core 2 Extreme at the same speed of the Intel's Pentium Extreme Edition 965, which runs at 3.73GHz. In the end though, our overclocking effort was possibly limited by the older B1 stepping of our X6800. The newer B2 stepping on the retail processors seems to have better overclocking performance from what we've been able to gather. On the other hand, the GA-965P-DQ6 showed a great overclocking bandwidth, with the retail boards clocking up to 480MHz with ease. However, since we were testing the processor and not the motherboard, the 360x10 setting was more ideal than say 450x8 after taking into consideration memory limitations and keeping chipset voltage on the low.
We wanted to satisfy our curiosity as to how the Core 2 Extreme would perform if it did meet the speculated specifications on release. Our overclocking platform of choice - Gigabyte's GA-965P-DQ6. At the present moment, we find that many initial Core 2 motherboards' BIOS do not properly detect Core 2 processor capabilities, sometimes restricting multiplier selection and others lack the necessary voltage and tweaking selections. The GA-965P-DQ6 happens to be one of the better boards to support the unlocked X6800 and possess great voltage granularity, a perfect combination for our overclocking efforts.
To do this, we overclocked the Core 2 Extreme X6800 to the ideal 3.33GHz with a 1333MHz PSB using a 333x10 FSB to CPU multiplier ratio and then topped it off with DDR2-1066 memory.
Maximum Overclocking
Next, we did some real overclocking to see just how scalable the Core microarchitecture can be. Intel's Netburst has produced scalable processors with good overclockability, but are bogged down by high power consumption and operating temperatures. The Core 2 is almost a total opposite, starting at modest sub-2GHz speeds. The Core microarchitecture's short pipelines would have reduced the processors scalability in terms of frequency, but its ultra efficient power consumption and low thermals should give it plenty of room.
In our overclocking tests, we took the same Core 2 Extreme X6800 and went all out to see just how far we could push the processor on stock Intel air-cooling. That's right, we didn't use fancy third-party coolers for this nor did we rely on exotic cooling techniques. The standard Intel boxed processor cooler was used to realistically set a stage for overclocking bandwidth right out of the box.
Our result? A final clock of 3.60GHz at 360x10. Not exactly the best overclock on the Conroe core, but it nearly puts the Core 2 Extreme at the same speed of the Intel's Pentium Extreme Edition 965, which runs at 3.73GHz. In the end though, our overclocking effort was possibly limited by the older B1 stepping of our X6800. The newer B2 stepping on the retail processors seems to have better overclocking performance from what we've been able to gather. On the other hand, the GA-965P-DQ6 showed a great overclocking bandwidth, with the retail boards clocking up to 480MHz with ease. However, since we were testing the processor and not the motherboard, the 360x10 setting was more ideal than say 450x8 after taking into consideration memory limitations and keeping chipset voltage on the low.
Subscribe to:
Posts (Atom)
