Maximum PC Processors RSS Feed

AMD Banks on Accelerated Processing Units

Gordon Mah Ung — Wed, 11 Nov 2009 20:00:00 -0600

AMD revealed new mobile and desktop platforms for the coming year, confirmed that it is launching a new dual GPU card next week codenamed “Hemlock,” and even gave the public a glimpse of its upcoming Fusion products that combines a traditional CPU and GPU in a monolithic die, at its annual briefing to financial analysts.

Meet the APU

AMD is dubbing its upcoming Fusion products as the “APU” or Accelerated Processor Unit, the first of which will be codenamed “Llano.” Llano will combine a DX11, gigaflop-capable, graphics core with a quad core processor on a single die. Interestingly, Llano will not be based on the company’s new Bulldozer core. AMD will instead use an improved 32nm version of the current Stars core which currently powers the Phenom II.

Llano will be used in upcoming desktop and mobile platforms. The bad news for Llano is that it will not see the light of day until 2011. Intel is expected to beat it to the punch with its CPU cum GPU late next year. AMD officials, however, pooh poohed Intel’s approach.

“Fusion is not a CPU with integrated graphics. The vision is to enable these new data parallel applications to be run on the most power efficient architecture available,” said AMD CEO Dirk Meyer. With the APU, code running on the graphics side is encouraged, Meyer said, whereas Intel continues to believe the parallel graphics core is an afterthought.

New Platforms

AMD said come 2010, its “Danube” platform is expected to take up the desktop replacement and thin and light categories of notebooks. Danube’s will feature the “Champlain” CPU with two to four cores, DDR3 support, an integrated DX10.1 core and with a discrete DX11 option. Ultrathin form factors will see the “Nile” platform with the new “Geneva” dual-core CPU, DDR3, integrated DX10.1 and a DX11 discrete option.

The real deal will not appear until 2011 when AMD expects to introduce its new “Sabine” platform. Sabine will be the first AMD notebook to use the new “Llano” APU. Thin and light users will get the new “Brazos” platform which features a dual-core APU dubbed “Ontario.” Unlike its quad-core sibling, Ontario will be based on the next-generation K11 / Bobcat CPU core that is the successor to today’s Stars core that powers the Phenom II and Athlon II. Mysteriously, AMD would not say what process technology would be used to build the Ontario APU or any of the Bobcat-based CPUs.

The next year will fairly steady for desktops. For enthusiasts, the new “Leo” platform will see AMD introduce its Hexa-core Thuban core with only an integrated DDR3 controller and a new RD890 chipset. Mainstream users will get the “Dorado” platform based on quad-core Athlon II CPUs running DDR3 and the RS880P chipset.

As with mobile, 2011 and the 32nm process will see a complete makeover. Mainstream desktop users will get the “Lynx” platform which will use the quad-core Llano APU. Enthusiasts will get the “Scorpius” platform which include an octo or quad-core CPU codenamed Zambezi. Zambezi will be based on the new Bulldozer core, use DDR3 and fit into – surprise an AM3 socket. Scorpius will be the sole platform not to feature graphics. AMD instead will depend on the traditional discrete graphics for enthusiats. The company, however, did say that an APU version of Bulldozer is in the works and could appear as early as 2012.

More about Bulldozer, Bobcat

AMD said it is ahead of schedule and is scheduled to release its next-generation Bulldozer and Bobcat cores on time. In fact, the company said it is expected to begin sampling Bulldozer, Bobcat and Fusion APU cores in the first half of 2010.

The bigger of the two is dubbed Bulldozer. Aimed at servers and enthusiasts, Bulldozer will be a modular design. Each module is a dual core with cores added to the die as needed for each product. Initially, a quad core and octo-core design will be produced. Of course, new instruction sets will be included as well as a new 128-bit floating point engine that’s optimized for the most comment floating point operations: multiply and accumulate. This far out AMD didn’t outline any clocks or cache amounts but seemed confident it would put it back in the game with Intel’s best.

As we said, Bulldozer will come in AM3 trim, but AMD officials would not commit to Bulldozer working in current AM3 boards this far out.

Bobcat is the mainstream and mobile version of the CPU. Also built in a modular fusion, AMD said it designed it for very low power consumption. Some versions will reach into the sub 1watt range which will open the CPU up to the mobile Internet devices and the Netbook formfactor. AMD said Bobcat will offer 90 percent of the performance of today’s mainstream CPUs with far lower power consumption and smaller die sizes. Bobcat is also a “synthesizable” design which is a departure for AMD. With synthesizable CPUs, engineers use software to design the circuits instead of creating each by hand. Similar to programming in C++ rather than machine code, AMD said there is roughly a 20 percent clock penalty by making Bobcat synthesizable but the power savings and the flexibility of it make it a “no brainer.”

AMD's Vision

In other updates from AMD, the company said it is de emphasizing CPUs in its branding which became confusing and instead will push a new Vision branding. Basic Vision is for looking at photos and video online, email, browsing and listening to music. Vision Premium is for those who convert videos to watch on portable media players, converting CDs to MP3, playing games or using a web came. Vision Ultimate will be for those who record live TV, playing graphics-rich online games, editing or mixing music, advanced photo editing or creating podcasts.

Finally, AMD execs confirmed that the company is prepared to launch its dual-GPU Hemlock video card as soon as next week. Hemlock is expected to be a dual-GPU version of the 5870 and is expected to sell at a premium price.

Cheap Chip! Athlon II X4 Breaks the $100 Quad-Core Barrier

Gordon Mah Ung — Wed, 16 Sep 2009 10:00:00 -0500

Even the Intel fanboys have to hand it to AMD once in a while. After Intel deftly dropped a Core i5 anvil on Phenom II’s head, AMD did a quick drop to floor and now fires back slo-mo style with its own chip: a $99 quad core.

Dubbed the Athlon II X4 620, this 2.6GHz quad core isn’t just leftover parts swept off the factory floor, either. The Athlon II X4 is based on the familiar K10 microarchitecture in the Phenom and Phenom II, but it’s actually a newer, smaller die. In fact, the new chip has less than half the transistors of a Phenom II X4 processor. Much of the shrinkage comes at the expense of cache. While the Phenom II packs 6MB of L3, the budget Athlon II X4 features none.

The TDP of the new Athlon II X4 chips (there are two, but only one is sub $100) is also considerably lower than the top-end Phenom II X4 965 Black Edition chip at 95 watts versus 140 watts. Other than the TDP and lack of L3 cache, the CPUs are essentially the same as their Phenom predecessors.

In fact, some Athlon II procs may actually be the same as Phenom II. Although the majority of Athlon IIs will be the smaller Propus cores, AMD will double-source the chips by taking some cores that might have been turned into Phenom II X4s and switching off the L3. Other than that, these chips will be virtually the same as a Propus—same TDP, same L2 cache, same clocks. While it might seem unusual, AMD says the practice is not unprecedented and happens quite often with budget CPUs. Because both the would-be Deneb and Propus cores are 45nm and essentially the same microarchitecture, it’s unlikely this will have any practical impact on the end user, the company says.

Still, the breakthrough here is not technology, but price. Up to now, the closest a budget user could get to a quad core was the stale Phenom X4 9650. At one time restricted to OEM sales, AMD has begun blowing these elderly parts out at about $110. The Phenom X4 9650 has 2MB of L3, but its slower Hyper Transport (3.6GHz vs. the Athlon II X4’s 4GHz) speed, lack of AM3 support (and thus DDR3), and its use of the older 65nm process technology make it a less attractive option.

In Intel land, the Athlon II X4’s main competition isn’t even close. Intel’s cheapest quad-core part today is the Core 2 Quad Q8200. Like the Athlon II X4, the Q8200’s low price is the result of a shrunken die size made possible by cutting cache. While the $220 Core 2 Quad Q9550 has 12MB of L2 cache, the $150 Core 2 Quad Q8200 has but 4MB of L2 cache.

Higher up the food chain, Intel made a significant technology and price breakthrough with the Core i5-750, but at $200 for the chip itself, it’s for folks with richer tastes. The extra $100 you can save with an Athlon II X4 is enough to buy an entry-level motherboard and the RAM to go with it.

To Quad or Not?

The budget buyer’s toughest question is whether to even opt for quad. Since price is the primary concern for the budget buyer, it’s worthwhile to consider all the various options in dual-core land. You could, for example, skip the Athlon II X4 620 in favor of the Athlon II X2 250. This would give you a 3GHz dual-core instead of the 2.6GHz quad-core and saves you about $13. Even cheaper, there’s AMD’s Athlon II X2 240, a 2.8GHz dual-core that’s listed at $60.

We didn’t run the performance numbers on these chips as we already know the answer: Which chip you buy should depend on what you do. Since the vast majority of games are not optimized for quad-core, a 3GHz dual-core will actually outperform a 2.6GHz quad core in gaming. The same can be said if you spend the bulk of your day in a browser or Microsoft Word: The two additional cores just don’t get you anything. On the other hand, if you encode media, edit photos, or you’re even an advanced Microsoft Excel user, a quad-core is well worth the dough. You don’t get double the performance everywhere, but for well-optimized apps, you could see substantial gains. How substantial? If an encoding job takes three hours on your 3GHz dual-core, it could take 1.6 hours on 2.6GHz quad core.

AMD’s new 45nm Propus core is at the heart of the new $99 Athlon II X4 quad-core.

Quad-cores will also pay dividends if you’re a heavy multitasker running more than one compute-intensive application at a time. Our final message to you is that a quad-core machine might actually get faster over time. That’s because apps are being continually upgraded and coding for four or more cores is a factor on most developers’ radar. That translates into faster performance on your quad core as the apps get updated.

Quads Compared

CPU Specs

CPU	2.66GHz Core i7-920	2.66GHz Core i7-750	2.33GHz Core 2 Quad Q8200	3.4GHz Phenom II X4 965 BE	2.8GHz Athlon II X4 630	2.6GHz Athlon II X4 620
Socket	LGA1366	LGA1156	LGA775	AM3	AM3	AM3
Price (Volume)	$284	$199	$163	$245	$122	$99
Price (Street)	$280	N/A	$150	$256	$122	$99
TDP	130Watts	95 Watts	95 Watts	140 Watts	95 Watts	95 Watts
Codename	Bloomfield	Lynnfield	Yorkfield	Deneb	Propus*	Propus*
QPI/HT	4.8GT/s	4.8GT/s	N/A	4GHz	4GHz	4GHz
Core Clock	2.66GHz	2.66GHz	2.33GHz	3.4GHz	2.8GHz	2.6GHz
Turbo Boost (Max 1 Core)	2.93GHz	3.2GHz	N/A	N/A	N/A	N/A
HyperThreading?	Yes	No	N/A	N/A	N/A	N/A
Cores/Threads	4/8	4/4	4/4	4/4	4/4	4/4
L1 Cache	256KB	256KB	256KB	512KB	512KB	512KB
L2 Cache	1MB	1MB	4MB	2MB	2MB	2MB
L3 Cache	8MB	8MB	N/A	6MB	N/A	N/A
Die Size (mm^2)	263	296	164	258	169	169
Transistor Count (million)	731	774	456	758	300	300
Process (nm)	45	45	45	45	45	45
Memory Controller	Tri Channel	Dual Channel	N/A	Dual Channel	Dual Channel	Dual Channel

* Some Athlon II X4s will use Deneb cores with L3 cache disabled.

Next up, the performance tests and benchmarks.

Performance

We don’t want to telegraph the winner of this budget grudge-match, but the Athlon II X4 accomplishes what AMD wanted: It’s not the fastest game in town, nor the sexiest, but it’s certainly the cheapest and it can hold its own against the current offerings of Intel. Of course, that’s if you factor in price as a big component. We can tell you this: There isn’t one single thing the Athlon II X4 is faster at than the Core i5. Not one. However, the Athlon II X4 is half the price, and in this economy, well, that can mean a lot.

Ménage à Quad

Three cheap chips do battle in the benchmark arena

For our benchmark analysis we looked at three of the relevant CPUs: Intel’s $150 Core 2 Quad Q8200, AMD’s $99 Athlon II X4 620, and Intel’s $200 Core i5-750. All three platforms used an EVGA GeForce GTX 280 card, Windows Vista Home Premium in 64-bit flavor, and a 150GB Western Digital Raptor drive. We used an Asus Maximus II Formula board with 4GB of DDR2/1066 for the Core 2 Quad, a Gigabyte GA-MA790FXT-UDF5P with 4GB of DDR3/1333 for the Athlon II X4, and a Gigabyte GA-P55-UD6 for the Core i5-750 processor. Our benchmark suite ran the gamut, from bandwidth-intensive to compute-limited to real-world performance tests.

First: There’s simply no comparison between the Core i5 and either the Core 2 Quad or Athlon II X4. There’s not a single benchmark among those we ran where the Core 2 Quad or Athlon II could outgun the Core i5. The Core i5 is easily faster than those two chips by double-digit percentages, generally around 30 percent faster. But you knew that. After all, it costs twice as much as the Athlon II and about 25 percent more than the Core 2 Quad.

Between the Core 2 Quad and Athlon II X4, it’s an interesting mix. Generally, the Athlon II X4 is significantly faster in encoding than the Core 2 Quad. But in gaming, it’s significantly slower. However, that’s based on running the game at low resolution and with features turned off to take the GPU out of the equation. At normal resolutions or with a dual-GPU setup, you’d likely see little difference between the two chips.

Considering the Athlon II X4’s advantage in encoding tasks we’re going to declare it the winner. Even taking into account that it was slower in our two photo-oriented tasks: ProShow Producer and Photoshop CS3, we still think the Athlon II X4 has the edge. Besides, it’s 50 percent cheaper than the Core 2 Quad. And at half the price of the Core i5, this one is an easy win for AMD.

BENCHMARKS

CPU	2.6GHz Athlon II X4 620	2.33GHz Core 2 Quad Q8200	2.66GHz Core i5-750*
MainConcept Reference 1.0 (sec)	1772	1976	1337
Premiere Pro CS3 (sec)	899	888	620
Cinebench 10 64-bit	9941	10184	14442
Handbrake (sec)	1559	1681	1198
PCMark Vantage 64-bit Overall	5792	5299	7208
POV Ray 3.7	2334	2191	2773
Photoshop CS3 (sec)	165	146	128
ProShow Producer (sec)	1224	997	700
Everest 5.0 RAM Read (MB/s)	8544	7511	12867
Everest 5.0 RAM Write (MB/s)	6960	7059	9881
Everest 5.0 RAM Copy (MB/s)	10028	7397	14684
Everest 5.0 RAM Latency (ns)	52.5	66.7	31
Sandra RAM Bandwidth (GB/s)	12.3	7.2	16.8
Fritz Chess Benchmark	12.93	13.79	17.38
3DMark Vantage Overall	13727	14260	14947
3DMark Vantage GPU	11371	11840	12249
3DMark Vantage CPU	36269	36863	44066
Valve Particle Test (fps)	71	81	124
Valve Map Compilation (sec)	157	163	121
Crysis (fps)	83.1	99.5	147
Resident Evil 5(fps)	70.7	70.3	109
World in Conflict (fps)	137	155	266
WinRar 3.20 RAW (sec)	1067	1110	706

* Bold score denotes the winner, but only between the Core 2 Quad and Athlon II X4. The Core i5 trounces both the Athlon II X4 and Core 2 Quad in every benchmark but we included it for reference.

Intel's Core i5 Analyzed and Tested (150+ Benchmarks)

Gordon Mah Ung — Tue, 08 Sep 2009 10:00:00 -0500

Intel’s latest troika of new CPUs brings Nehalem goodness to the masses

Nehalem for everyone! That simple sentence best explains Intel’s brand-new series of CPUs, which is sure to please budget users everywhere while confounding power users.

Why would a new CPU that gives you the best bang for the buck in town be greeted nervously? Because Intel’s new CPU brings with it a new socket as well as a new infrastructure. This new infrastructure is essentially a fork in the road that forces users to make a difficult choice: Save money today but get locked out of the high-end, or splurge today knowing that the budget CPU is damn near as good as the top-end part.

For the details on Intel’s new budget monster, savor our full report, consume the specs, and then digest the benchmarks to see just which path your next PC should take.

Meet Lynnfield

We normally don’t use a CPU’s code-name once its real name is known, but to help keep your head from popping off over Intel’s confusing naming scheme we’re going to rely on some code-names here for clarity.

Intel’s newest CPU family is code-named Lynnfield. The lineup includes the 2.93GHz Core i7-870, the 2.83GHz Core i7-860, and the 2.66GHz Core i5-750. Lynnfield chips use essentially the same microarchitecture as Intel’s original Core i7 CPUs, which were code-named Bloomfield, but the new CPUs are incompatible with existing Core i7 motherboards. That’s right, you could walk into a store and buy a Core i7 CPU that will not work with the Core i7 motherboard you just bought. Likewise, the Core i7 heatsink cooler you bought may not work with a new Core i7, either.

Despite its smaller size, Intel’s new Lynnfield Core i7/Core i5 CPU (right) actually features an increased transistor count of 774 million and a larger die size of 296 square millimeters, compared with the 731-million-tranny Bloomfield Core i7 (left) and its 263 square-millimeter die.

Socket Switcheroo

The most notable difference in this new crop of Core i7s is the socket. For Lynnfield, Intel is introducing the LGA1156 socket. This socket is, as stated, incompatible with the current LGA1366 motherboards and CPUs. To irk you even more, even the heatsink cooler mounting holes are incompatible, so you probably couldn’t use an LGA1366 cooler, even if you happened to have one. And even more annoying to enthusiasts, LGA775 coolers are also incompatible. Earlier this year, Intel execs told Maximum PC that LGA775 cooler compatibility was being considered for the new chip, but obviously the company has since ruled that out. To break it down: LGA1366 uses a 12cm gap, LGA1156 uses an 11cm gap, and LGA775 uses a 10cm gap. Yes, one centimeter difference and you have to dustbin your pricey high-rise cooler even though it’s capable of handling the thermals of the new chip.

We asked Intel if it was doing this just to piss people off and the company said no, it did it for legitimate engineering reasons. Intel actually lowered the height of the new direct socket load mechanism that clamps the CPU in place, which required moving the mounting holes out. Existing heatsinks capable of the thermal load should work, Intel said, so long as consumers obtain updated mounting brackets from the cooler maker. We have to also note that very new high-end coolers are coming with mounts for LGA1156 too. Still, make sure that if the box says Core i7, support for LGA1156 is included.

Although Intel wouldn’t confirm this, we’ve been told by high-end system builders that certain LGA1366 motherboards and coolers would flex enough to create a gap between cooler and CPU. The new design presumably fixes that problem.

Sockets Compared

Lynnfield Socket

Bloomfield Socket

The new budget Core i5/Core i7 CPUs use a new LGA1156 socket design (top image), which is incompatible with existing LGA1366 Core i7 motherboards and coolers (bottom image). The design eliminates traces for the third memory controller, but builds in wires that will accommodate forthcoming CPUs with integrated graphics cores.

Memory Loss

Enthusiasts will also question the move from tri-channel DDR3 to dual-channel DDR3—why go back if wider is better? Intel’s decision is based on pragmatism and cost. The tri-channel circuitry in the CPU doesn’t add much cost to the processor, but it’s not cheap to implement when building a motherboard. Those added traces from the socket to the RAM slots mean more layers and pricier boards. That’s one of the contributing factors to excessively priced X58 boards this past year.

Should you be concerned about shifting down to dual-channel? Generally, no. For the most part, only the most memory-bandwidth-intensive apps will actually see any performance hit. The fantastic latency and overall bandwidth capacity of the Nehalem design is more than adequate for today’s applications. This doesn’t mean it’s a non-issue. The vast majority of Lynnfield motherboards we’ve seen are opting for four-DIMM slots. That means a maximum of 8GB using affordable 2GB DIMMs (4GB DIMMs are currently cost-prohibitive). The only board we’ve seen with more DIMM slots is Gigabyte’s GA-P55-UD6, which features six, for a total of 12GB, using 2GB DIMMs. The memory controller in Lynnfield tops out at 16GB, while Bloomfield maxes out at 24GB. Realistically, 24GB of RAM is way overkill for 99 percent of us. Our experience has shown us that most apps do not consume that much RAM; 4GB to 6GB is the sweet spot today.

PCI-E at the Core

Another significant change for Lynnfield is that PCI-E comes directly off the CPU core. In X58/Bloomfield, X48/Core 2 Quad, and 790FX/Phenom II, PCI Express is external to the CPU, residing in the north-bridge chipset. Data is pumped out to the chipset where it must then be directed to the PCI-E slots that connect to the GPUs. As you can imagine, the extra hop creates a latency issue—that’s eliminated with Lynnfield. Lower latency is better, right? Yes and no. While latency is better on Lynnfield, the CPUs feature but a single x16 PCI-E 2.0 lane in the chip. That’s fine for a single GPU, but multi-GPU configurations will have to split the bandwidth. That means an SLI or CrossFire X rig will run both cards in x8 mode. Remember, however, that we’re talking x8 at PCI-E 2.0 speeds, which is 8GB/s for each card. From what we’ve seen and from what vendors have told us, only at the highest resolutions with antialiasing do you see any impact.

But, you say, what about tri-SLI? That, too, can be theoretically supported. Even though Lynn-field supports but a single x16 PCI-E 2.0 lane, additional PCI-E lanes are added through the P55 chipset—at the cost of latency. Previous designs that had PCI-E plumbed from both the north bridge and south bridge were dinged for doing just this. Some vendors are working around the lack of bandwidth by adding Nvidia’s nForce 200 chip to their boards. The nForce 200 doesn’t magically add bandwidth but it does manage the available bandwidth across multiple slots. Thus, a board vendor could add three or even four x16 PCI-E slots and have the nForce 200 chip manage the load for multi-GPU configurations. This would eliminate the need to have the GPUs feed off of the higher-latency connection in the chipset.

CrossFire X support is a given in the vast majority of P55 motherboards. And SLI will be as well for the board vendors who pay Nvidia to “certify” that their boards are SLI-ready. Fortunately, the big names are already onboard with that, including Asus, Gigabyte, MSI, EVGA, and even Intel.

If you’re wondering why Intel doesn’t just fix the lack of bandwidth by adding additional PCI-E lanes in the CPU, consider this: Intel would have to add additional traces from the CPU and the socket, and even Intel is loathe to introduce yet another new socket standard so soon. The company also doesn’t think it’s worth it as anyone who truly wants full dual-x16 GPU support should really be buying X58: Remember, folks, Lynnfield and P55 are for the “mainstream.”

The Lynnfield LGA1156 again rejiggers the design of the modern CPU. With the Athlon 64 and the Core i7, the memory controller was moved from the north bridge directly into the CPU core. With Lynnfield, the PCI-Express ports are now handled directly by the CPU as well. Furthermore, relatively low-speed data from the hard drives and USB ports flows though a single DMI link at 2GB/s with Lynnfield.

P55: Downsizing the Chipset

In the old days, new core-logic chipsets were almost as exciting as a new CPU. Not so today. With X58 and Bloomfield, the chipset got fired from its job of managing the memory controller. With Lynnfield, it even loses its responsibilities for managing PCI-E, as both features are now integral to the CPU itself. Today, the chipset is nothing more than a glorified south bridge, managing USB, SATA, PCI, PS/2, and other decidedly unsexy items. The P55 might have been sexier if it had USB 3.0 or SATA 6 functionality, but that won’t appear until next year. And even if it had those features, it’s pretty clear where the P55 stands: Its desk has been moved to the basement and its red Swingline stapler has been confiscated.

Tweakability

There was some initial confusion when Bloomfield was introduced. Early reports had it that the memory multipliers were unlocked on the high-end Extreme versions of the CPU, but locked on the lower-end versions. It turned out that was only the case for samples first sent to the press and system vendors. Retail versions of the lower-end Bloomfields were unlocked as well, making it possible for users to set the RAM at speeds higher than the rated DDR3/1066. This time around, there’s no such confusion. All three new Lynnfields feature unlocked memory multipliers and the chips are actually officially rated for operation at DDR3/1333, with higher speeds obtainable through “overclocking.” Of course, the chips are upwardly clock-locked, so you can’t simply set your $200 Core i5 to run at 4GHz by changing the multiplier.

Though open about memory locks, Intel has been cagier about Turbo mode. With Bloomfield, Intel never revealed to consumers the top clock speeds the CPUs could hit under Turbo mode, but with Lynnfield, it’s now publicizing the top speed that a single core can hit. The Core i7-870, for example, can top out at 3.6GHz by overclocking individual cores based on the thermals and power consumption of the chip. That’s actually far greater than the Bloomfield modes can top out at on default. The take-away is that, with the months it has had to tinker with Lynnfield, Intel has improved Turbo mode (now officially Turbo Boost). However, the feature is locked. Only on the Extreme parts will users be able to tinker with Turbo beyond the default caps.

The Big Decision

All this techno-speak is meaningless if the processor doesn’t perform as expected. We don’t want to give away everything here but let’s just say we’re not disappointed. Lynnfield is everything you’d expect of a new iteration of Nehalem and Intel’s now-very-mature 45m process. As such, overclocking, is also fruitful. By simply boosting the base clock of the cheapie $200 Core i5-750, we were able to take it from 2.66GHz to a very stable 3.5GHz without any additional voltage on our very first attempt using a Gigabyte GA-P55-UD6 board.

System builders have been equally impressed with these budget parts and have achieved overclocking results every bit as good as, if not better than, the most expensive Core i7-975 Extreme Edition parts.

That brings us to the main question: Why even build a Bloomfield LGA1366 at this point if building a Lynnfield system will save you at least $100 on the board and a little on the RAM, and even more money if you opt for the ultra-budget Core i5-750?

Here’s that fork in the road: Lynnfield is cheaper and gets you 90 percent the performance of a Bloomfield system, but early next year Intel will introduce a CPU code-named Gulftown, aka Core i9. Core i9 adds two more physical cores to the CPU and will likely be the first consumer hexacore CPU. With Hyper-Threading, that’s 12 threads available to the OS and enough to make the most jaded enthusiast perk up. Core i9, however, will only be available on the Bloomfield/LGA1366 platform. If you were to build a Lynnfield LGA1156 box there’d be no six-core for you! At least, not at this point. Intel said it has no plans for an LGA1156 hexacore. You see the dilemma. Save money now and build a really kick-ass LGA1156 or spend the extra $200 to build an LGA1366 that has an easy upgrade path to six cores with Hyper-Threading. It’s not an easy choice to make under normal circumstances, but in this economic climate, it’s even harder—that $200 goes a long way toward a better GPU, better PSU, more RAM, or a bigger hard drive. The choice, however, is up to you.

Next, the CPU buyers guide and benchmarks!

CPU Buyers Guide

What’s the best budget chip available today for those interested in getting good performance on the cheap? We’ll walk you through the top five chips and tell you which one to buy.

CPU Specs

CPU	Core i7-920	Core i7-870	Core i7-860	Core i5-750	Core 2 Quad Q9550/Q9550s	Phenom II X4 965 BE
Socket	LGA1366	LGA1156	LGA1156	LGA1156	LGA775	AM3
Price (Volume)	$284	$562	$284	$196	$266 / $320	$245
Price (Street)	$280	N/A	N/A	N/A	$220 / $350	$245
TDP	130Watts	95Watts	95Watts	95Watts	95Watts / 65Watts	140Watts
Codename	Bloomfield	Lynnfield	Lynnfield	Lynnfield	Yorkfield	Deneb
QPI/HT	4.8GT/s	4.8GT/s	4.8GT/s	4.8GT/s	N/A	4GHz
Core Clock	2.66GHz	2.93GHz	2.8GHz	2.66GHz	2.83GHz	3.4GHz
Turbo Boost (Max 1 Core)	2.93GHz	3.6GHz	3.46GHz	3.2GHz	N/A	N/A
HyperThreading?	Yes	Yes	Yes	No	No	N/A
Cores/Threads	4/8	4/8	4/8	4/4	4/4	4/4
L1 Cache	256KB	256KB	256KB	256KB	256KB	512KB
L2 Cache	1MB	1MB	1MB	1MB	12MB	2MB
L3 Cache	8MB	8MB	8MB	8MB	N/A	6MB
Die Size (mm^2)	263	296	296	296	214	258
Transistor Count (million)	731	774	774	771	820	758
Process (nm)	45	45	45	45	45	45

AMD 3.4GHz Phenom II X4 965 BE

It’s bad news for AMD’s recently released quad-core. Its best and brightest could never compete with the Core i7-920 in performance, but it certainly outgunned it in price. Now with Intel’s LGA1156 Lynnfields here, it can’t even compete on price. As of this writing, the Phenom II X4 965 Black Edition had a list price of $245. The Core i5-750 has a list price of $200 and it mercilessly punts the Phenom II X4 965 BE up and down the field. Only in the mostly-single threaded Photoshop CS3 and POV Ray 3.7 did the Phenom’s 700MHz advantage put it over the top. Against the Hyper-Threaded Core i7’s though, the virtual cores vaulted the Nehalems over the Phenom II X4 965 everywhere. The good news for the Phenom II X4 965 is that it isn’t dead ass last. That falls to its old nemesis, the 2.83GHz Core 2 Quad Q9550. There, the Phenom II X4 965 BE serves space-cold revenge to the only chip here not to sport an on-die memory controller. Yeah, so you Intel fan boys say so what? Core 2 is an end of life CPU big whoop, but you gotta take your victories as you can get them.

The real bad news for AMD is that it’s not expected to get its next-generation Bulldozer core out now until 2011 so it can build it on a 32nm process. With Core i5 pushing the $200 range and Core i3 around the corner and expected to push into the ultra-budget range, there’s going to be very little maneuvering room for AMD’s rather dated design.

Still, there is place for the Phenom II X4 965 BE: existing upgrades. The processor will drop into a large assortment of existing AM2+ boards (you should check your mobo maker’s web site first for support) and even though it’s slower than a Core i5/i7, it’s a hell of a lot cheaper and easier to remove your current Athlon 64 X2 part and drop in the Phenom II X4 965 BE. Once you do that, you can thumb your nose at the Intel boys who have to replace their LGA775 boards and likely do an OS reinstall to upgrade to Core i5 and Core i7. Heck, there’s even rumors of a six-core AM3 part which would likely drop into modern AM2+ board so there’s some solace for AMD fans even if the performance isn’t there.

Intel 2.83GHz Core 2 Quad Q9550

We’ve said for months that Core 2 was a lame duck and it gets even lamer with the introduction of the LGA1156 parts. The Core 2 can’t compete with its Nehalem brethren on any front. Even the lowly – and cheaper Core i5-750 – gives the Core 2 Quad Q9550 such a bad beat down, that AMD would likely feel bad for it. And as we said, even the Phenom II X4 965 BE mostly smokes the Core 2 Quad. Sure, the Core 2 Quad surprisingly outperforms the Phenom II X4 965 BE in a couple of places, but it’s still the loser. We could have reached for the highest bin Core 2 Quad, the 3GHz Q9650, but at $319 on the street and list, it makes no sense.

Hell, even at the street price of $220, it’s hard to justify the Core 2 Quad Q9550 over a new Core i5 rig. Even AMD’s Phenom II has a better roadmap as the company will support it through at least through 2010 with newer, faster CPUs. The same can’t be said of Intel which is unlikely to introduce faster Core 2 parts. There is still a place for Core 2 though: If your box is rolling a dual-core and the LGA775 board supports 45nm quads, it would be dumb not to get one more upgrade out of it. Outside of that, it’s clear Core 2’s glory days are long, long gone.

Intel 2.66GHz Core i5-750

Of the troika of new chips, Intel’s Core i5-750 is likely to be the big hit. With wholesale prices of $200, the average joe or jane can now build a Nehalem-based system for almost as much as a Core 2 or Phenom II box. The key price differentiator is the motherboards. Board’s we’ve seen will likely top out about $225 but many will dip into the $150 range. That makes it significantly different from when Intel’s Core i7-920 launched. Sure it was only $280 (and still a year later) but the boards for the processor all pushed the $300 mark. Even today, it’s hard to get an LGA1366 board for $250.

In performance, the lower clocked Core i5 schools Core 2 Quad Q9550 as well as the Phenom II X4 BE. The Phenom II X4’s massive clock difference actually gets close to the Core i5 in a few benchmarks and surpasses it in two but the cheap Lynnfield is clearly the winner. Against the Core i7, as expected, the Core i5 loses but for many, giving up 10 percent to 25 percent in performance is worth it to save, oh, $300 over the price of the top-end Core i7-870. The performance delta between the i5 and i7 is the greatest in multi-threaded apps. In gaming and apps not optimized for quad cores, they’re a lot closer.

In the final analysis, the Core i5 falls right where Intel’s bewildering branding scheme puts it: faster than Core 2 and Phenom II but slower than i7 and really damned cheap to boot too. Buy this chip is the vast majority of your applications are not optimized for quad-core or more. If, however, your work counts on an increased amount of cores, go the extra mileage for a Core i7 with Hyper-Threading.

Intel 2.8GHz Core i7-860

If you use the Goldilocks formula, this new quad-core, Hyper-Threaded CPU is “just right.” It’s just the right blend of performance to price. At $266 for a 2.83GHz, its most natural enemy is the Core i7-920 in LGA1366. The 920’s primary advantage is increased bandwidth thanks to its tri-channel DDR3 support. But since the vast majority of apps really don’t need that much bandwidth, the 860 is generally faster by five percent thanks to its 5 percent clock advantage. That’s pretty much what we saw in our tests too – about five percent difference in the vast majority of the tests in favor of the 2.8GHz 860. And of course, the 860 also gets a boost from its increased Turbo Boost clocks. A stock 920 will only Turbo as high as 2.93GHz under some loads. The 860 will max out at 3.46GHz under some loads. Why is the Turbo higher on the 860? The 920 was a first generation Nehalem processor and Intel played it very conservatively with the Turbo. With the 860, the company feels more comfortable pushing it higher.

So what should you buy? Both procs are priced the same at $266, but each has its strengths. The 920 has true dual x16 PCI-E 2.0 support thanks to the X58 chipset and discrete PCI-E as well as tri-channel DDR3. Frankly, we think both of those features are pretty minor reasons to choose 920. The main reason to pick a 920 is the upgrade path. In a few months, Intel will introduce a 32nm-based six-coire processor codenamed Gulftown. With Hyper-Threading, you get 12 threads as well as any goodness Intel can squeeze out of the new 32nm process (both the 860 and 920 are 45nm parts). A rig built on 860 will also not see Gulftown and probably will not see a six-core part for quite some time if ever. Again, Intel intends for LGA1156 to be for the mainstream and the 99 percent of mainstream users don’t need 12-threads for their apps nor will they pay out $1,000 for a Gulftown CPU.

That takes us back to the Core i7-860 part. If you save possibly $150 to $200 by building an 860 rig, that can be put toward a faster GPU, a bigger hard driver or a larger monitor. In this economic climate, that’s pretty appealing and really the pick of the litter if you ask us.

Intel 2.93GHz Core i7-870

In this comparison of five CPUs, the 870 was head and shoulders the fastest CPU. Generally, we saw a 5 percent advantage in the 870 – just what you would expect from a 5 percent clock advantage. We did see some interesting results though. The multi-threaded Cinebench 10 actually saw the 870 with a 13 percent higher score. World in Conflict also saw the 870 run away with a 24 percent higher frame rate than the 860. So here’s the real question: Would you pay nearly 100 percent more for that? For most folks, probably not. At $555 for the Core i7-870 and $266 for the Core i7-860, it just makes a hell of a lot sense to give up some of that performance to put towards something else in your machine. And if you really are into being on the ragged edge of performance, it makes a lot more sense to jump in with both feet for an LGA1366 platform and the promise of a six-core upgrade in a few month. So we’re a little ambivalent about the Core i7-870. But make no bones about it, the Core i7-870 is the king of the CPUs that battled today, it’s just not really a “budget” CPU is it?

Intel 2.66GHz Core i7-920

If you haven’t figured it out by now, Intel’s 920 is the chip all three LGA1156 Lynnfield’s were gunning for. A huge hit among the performance budget shoppers, it overclocked well and got you into the Core i7 club without paying through the nose.

With its three new siblings here, the 920 is mostly pushed to the back in performance and pricing competitiveness. The other chips run at higher clocks, automatically Turbo Boost to higher levels and can save you from $150 to $200 in associated building costs. So why bother with the 920? There is still some magic to this old favorite. In this roundup, the 920 was generally in third or second place in the vast majority of the tests. And in some benches, the 920 interestingly bubbled up to the top. Even though its superior tri-channel doesn’t always pay off, it apparently does in Photoshop CS3 where the 920 took top honors and we suspect its superior bandwidth helps keep it in hunt elsewhere too. We had heard early rumors that Intel would axe the 920 once the LGA1156 procs were out but the company has since told us it had no plans to discontinue 920 right now. That’s a good decision too. While LGA1136 is definitely an exclusive club, there’s no reason for Intel to make it even harder to get in. If your only choice to getting an LGA1366 platform was to shell out $500 for a Core i7-950 or $1,000 for a Core i7-975 Extreme Edition, very few people would choose that route.

Of course, the biggest reason to buy 920 is for the path to the Core i9 “Gulftown” CPU that Intel will introduce in a few months. Ideally, you could build a 920 box and use it for a year or so until the Gulftown derivatives drop down enough to become “budget” chips themselves.

The Benchmarks

To run our test, we tried to balance each particular CPU’s platform as closely as possible but given the differences in each chip’s requirements that’s almost impossible. We used the same make and model Western Digital Raptor 150GB drive for all four builds, the same 64-bit Windows Vista Home Premium SP2 build, the same make/model/clocked EVGA GeForce GTX280 and the same drivers. Windows 7 was available at the time of our reviews but we felt it would be best to use Vista as drivers were readily available for it.

The only real differences, of course, were the motherboards and RAM configurations. Although the Core i7-920 does unofficially support higher clocked RAM, we stuck with the official DDR3/1066, but 6GB of it. For the dual-channel Phenom II X4 and Core i5/i7, we used 4GB of DDR3/1333. For the dual-channel Core 2 Quad, we used the far more common DDR2/1066 as the vast majority of Core 2 Quad folks are running DDR2. For motherboards, we used three Gigabyte boards: the new GA-P55-UD6 for the LGA1156 procs, a GA-EX58-UDR3 for the LGA1136, and a GA-MA790GPT-UD3H for the Phenom II. For the Core 2, we relied on an Asus Maximus II Formula.

Benchmark Test Setup

CPU	Core i7-920	Core i7-870	Core i7-860	Core i5-750	Core 2 Quad Q9550/Q9550s	Phenom II X4 965 BE
RAM Mode	Triple	Dual	Dual	Dual	Dual	Dual Unganged
RAM Size	6GB	4GB	4GB	4GB	4GB	4GB
RAM Speed	DDR3/1066	DDR3/1333	DDR3/1333	DDR3/1333	DDR2/1066	DDR3/1333
RAM Latency	7-7-7-20-1T	9-9-9-24-1T	9-9-9-24-1T	9-9-9-24-1T	5-5-5-18-2T	9-9-9-25-1T
Hard Drive	WD 150 Raptor	WD 150 Raptor	WD 150 Raptor	WD 150 Raptor	WD 150 Raptor	WD 150 Raptor
OS	Vista HP 64-bit SP2	Vista HP 64-bit SP2	Vista HP 64-bit SP2	Vista HP 64-bit SP2	Vista HP 64-bit SP2	Vista HP 64-bit SP2
GPU	Geforce GTX 295	Geforce GTX 295	Geforce GTX 295	Geforce GTX 295	Geforce GTX 295	Geforce GTX 295
GPU Clocks 3D	670/1458 /1215	670/1458 /1215	670/1458 /1215	670/1458 /1215	670/1458 /1215	670/1458 /1215
Motherboard	Gigabyte GA-MA790 FXT-UD5P	Gigabyte GA-P55 -UD3	Gigabyte GA-P55 -UD3	Gigabyte GA-P55 -UD3	Asus Maximum II Formula	Gigabyte GA-EX58 -UD3R

BENCHMARKS

CPU	Core i7-920	Core i7-870	Core i7-860	Core i5-750	Core 2 Quad Q9550/Q9550s	Phenom II X4 965 BE
MainConcept Reference 1.0	1235	1115	1170	1337	1644	1388
MainConcept Refernece 1.0 Pro AVC	696	635	664	769	986	840
Premiere Pro CS3	671	610	630	620	741	733
Cinebench 10 64-bit	16140	18275	16085	14442	12280	14083
Handbrake iPod Classic	994	939	993	1198	1366	1220
PCMark Vantage 64-bit Overall	6929	7536	7299	7208	6241	6824
POV Ray 3.7	3470	3888	3702	2773	2669	3045
Photoshop CS3	116	119	126	128	132	123
ProShow Producer	636	640	617	700	862	911
Everest 5.0 RAM Read (MB/s)	14387	12997	13641	12867	7807	8154
Everest 5.0 RAM Write (MB/s)	11639	10811	10992	9881	7085	6794
Everest 5.0 RAM Copy (MB/s)	15790	15414	15393	14684	7455	10246
Everest 5.0 RAM Latency (ns)	61	53	52	31	64	54.3
Sandra RAM Bandwidth (GB/s)	22.4	16.7	17.2	16.8	7.2	12.7
Fritz Chess Benchmark	21.4	23.94	22.38	17.38	16.97	17.04
3DMark Vantage Overall	15008	15002	14985	14947	14681	14544
3DMark Vantage GPU	12306	12231	12247	12249	12013	11978
3DMark Vantage CPU	44002	46815	45525	44066	40644	40679
Valve Particle Test	143	159	151	124	99	95
Valve Map Compilation	146	128	133	121	129	125
Crysis	146	156	150	147	119	104
Resident Evil 5 Fixed DX9	114	115	118	109	85	89
Resident Evil 5 Fixed DX10	117.7	106.5	119.7	109.4	83.8	89.2
Resident Evil 5 Variable DX9	145.8	155.9	147.2	155.4	133.7	140.3
Resident Evil 5 Variable DX10	150.4	155	157.8	160	133.9	140.2
World in Conflict	221	282	227	266	159	160
WinRar 3.20	581	588	594	706	868	805

Best scores in bold.

Next, our detailed benchmark analysis.

Benchmark Analysis

Sisoft Sandra RAM

(higher is better)

Sisoftware’s Sandra RAM benchmark lets the Core i7-920 strut its tri-channel DDR3 stuff. Keep in mind, we tested the Core i7-920 at its officially rated speed of DDR3/1066 vs. DDR3/1333 for the five other parts here. That extra bandwidth of the 920, in fact, may help it keep pace with the newer processors despite a general clock deficit. Still, as we’ve said, the vast majority of folks just don’t need that bandwidth.

WinRar 3.20

(lower is better)

Now that we’ve said don’t pay attention to bandwidth, here’s a test that does actually show how much it can help. We used WinRar 3.20 to compress a folder of RAW files shot with a Canon EOS 5D. The files, pretty much, are near uncompressible so we thought it would be a good way to stretch the processors. The Core i7-920 just edges out the Core i7-870 despite a 266MHz gap between the two chips.

World in Conflict

(higher is better)

We ran World In Conflict at low resolutions to take the GPU out of the equation for performance. Some have questioned this but it tells you what you would get if you had the fastest GPU in ze vorld. The results were a bit odd but we saws the Core i7-870 up front and then the budget Core i5-750 next in line. Huh? Why would the results be so whacky? We have two theories: Turbo Boost can play havoc with unpredictability. Afterall, it automatically overclocks individual cores for a given thermal load and power consumption load so it’s possible the Turbo Boost for the 750 just kicked up into high gear in the most single-threaded game. Our other theory is that the oddly super low latency that the 750 exhibitied may have contributed to its scores. The other conclusion you can draw from this is that the Phenom II and Core 2 Quad should have just stayed off the field.

Crysis

(higher is better)

We used the same low quality and low resolution mode for our Crysis runs to show you just what kind of frame rates you’ll get in four years when the newest GPUs finally make Crysis its bitch. If you happened to still be running the same rig in 2013, here’s how your CPU would shape up. Unlike some of the multi-threaded benchmarks, we actually saw very predictable results with the most expensive 870 on top, the budget builder’s favorite, the 860, in second, and the 750 and 920 pretty even.

Valve Particle Test

(higher is better)

Valve’s Particle Test is a quad-core optimized test that measures CPU performance. Here, our results were predictable with the Lynnfields seemingly scaling with clock speeds. The surprise again is how well the 920 does which can only be attributed to its third-channel of DDR3.

Proshow Producer

(lower is better)

Our Proshow Producer benchmark hammers all cores available and again, there’s that pesky Turbo Boost messing with us. The Core i7-870 should have been the fastest, but the Core i7-860 just edges past all contenders. If you’ve wondered if Hyper-Threading pays off? Yes. Notice the roughly 10 percent gain the 2.66GHz 920 has against the 2.66GHz 750. That’s generally what we’ve seen from Hyper-Threading in other benchmarks. One other conclusion: Core 2 Quad and Phenom II X4, why are you here again?

OLPC Switches to VIA Processors

Pulkit Chandna — Mon, 20 Apr 2009 20:20:59 -0500

The One Laptop per Child project has chosen Via’s low-wattage C7-M processor for a revised version of its XO laptop. The inexpensive XO laptop currently ships with AMD’s Geode LX processor, but AMD has decided to retire the processor. OLPC has made it clear that the Via-powered XO laptop - which the OLPC has dubbed “Generation 1.5” – will not be a major hardware refresh.

"The design goal is to provide an overall update of the system within the same ID and external appearance," OLPC’s VP of hardware development, John Watlington, announced on Friday. The revised version, which is due in November, will feature 1GB DDR2 SDRAM (currently 256MB) and up to 8GB flash storage (currently 1GB). OLPC will abandon the x-86 processor platform and adopt an ARM-based processor in its stead as part of its Generation 2.0 refresh.

Socket AM3 Arrives -- AMD Releases Five New CPUs that Support DDR3

Gordon Mah Ung — Mon, 09 Feb 2009 12:00:00 -0600

Who says AMD moves too slowly? Just a month after releasing its well regarded Phenom II mid-range CPUs, the company is back with no fewer than five new P-II chips and its new AM3 socket that support DDR3. We give you the skinny on AMD’s latest quad and tri-cores and help you sort through AMD’s bewildering array of CPU choices.

War. What is it good for? Absolutely nothing. Well, except when it’s a CPU war. In that case, it’s good for consumers. Really good for us. With the unveiling of five new AMD’s latest Phenom II CPUs supporting DDR3, it’s pretty clear that the CPU war that started with the unveiling of the Phenom II in January is escalating.

AMD’s new lineup includes the 2.6GHz Phenom II X4 for $175, the 2.8GHz Phenom II X3 720 Black Edition at $145, and the 2.6GHz Phenom II X3 710 for $125. AMD’s two other new chips: the 2.6GHz Phenom II X4 910 and the 2.5GHz Phenom II X4 805. The 910 and 805 are OEM only CPUs and pricing was not released but you can expect that gray-markets will carry them and that the prices will follow the numbers. The 805, for example, should be slightly cheaper than the $175 810 and the 910 should be cheaper than the $195 Phenom II X4 920.

Lost in the numbers? So where we. AMD’s lineup is so bewildering to us today that we had build a spread sheet just to sort it out!

There are five prominent things to note with the new CPUs: They all support AM3, the HyperTransport speeds are higher, the L3 cache size is different, the tri-cores are back and the thermals are lower. We’ll address these in order.

AM3 socket

AM3 is AMD’s new socket standard that is built to support DDR3. The good news is that AM3 CPUs feature both DDR2 and DDR3 controllers. This means you can install an AM3 CPU in an AM2+ (and even some AM2) motherboards. You cannot, however, install an AM2+ CPU in an AM3 board. To prevent damage, the AM3 sockets have two fewer pins so you can’t even physically insert an AM2+ CPU in the socket. All Phenom II CPUs except for the two original launch CPUs should be AM3-based.

Can you spot the two fewer pins on the AM3 CPU on the right vs. the AM2+ CPU on the left?

Why didn’t AMD make the two original chips (the Phenom II X4 940 and 920) AM3 too? The company said it wanted to get them out as soon as possible and ditching AM3 support a cut quite a bit of engineering time off. We can understand that but it’s only been a month since the 940 and 920 were unveiled so couldn’t it have waited just a little longer so as not to confuse the hell out f people and piss off 940 and 920 owners? Apparently not. In fact, we’ve been told by AMD officials that the 940 and 920 actually had the AM3 controllers in them but they not turned on. If we ever get the time, we’ll have to snip the pins off a Socket AM2+ 920 and see what happens when it’s inserted into an AM3 motherboard.

HyperTransport Speeds

The newest Phenom II all sport 4GHz HyperTransport speeds. The original Phenom II X4 940 and 920 only ran at 3.6GHz HyperTransport speeds. Why? Again, AMD said it need to cut a few corners to get the 940 and 920 out as soon as possible and limiting the speeds to 3.6GHz help it do that. The company notes that it’s not like the CPUs are saturating the bandwidth anyway so it should have no real impact on performance. We, frankly, haven’t noticed that much of a difference either and we have to note that only the original Phenom X4 9950 and Phenom X4 8850 sported the 4GHz HyperTransport speeds. All others were lower.

If you’re really interested in how AMD’s Phenom’s look from an HT speed context here’s our chart sorted by HyperTransport speeds:

Cache

AMD is now also resorting to smaller cache versions to differentiate its models. This is an old technique long used by Intel and AMD and helps maximize the yields. If a CPU has a bit of defective cache, Intel or AMD turn off that portion and sell it as a lower model which is why these new chips often have the same die size as the larger L2/L3 chips. As the process matures and the yields get good enough that all of the cache is good, the companies have been known to actually produce smaller cache versions to even further maximize the yield. Generally, the largest cache models cost the most. For AMD’s Phenom II lineup, a 9XX denotes the larger 6MB L3, while an 8XX denotes 4MB of L3 cache.

Again, here’s the view of AMD’s Phenom CPUs from an L3 cache perspective:

Tri-cores

Like the cache, AMD is also maximizing its yields by taking quad-core procs that have one bad core and selling them as tri-cores. Initially, enthusiasts scoffed at the idea of a quad-core minus one, but they’ve gradually been accepted. AMD has also had some success by putting the tri-cores against Intel’s dual cores. For the most part, three execution cores will indeed give you better performance in multi-threaded applications and multi-tasking than dual-cores. Here’s a break down of the X3’s by clock speed.

TDP

The final difference with these new chips is the thermal or TDP ratings. The original Phenom II X4 940 and 920 both had enthusiast-class TDP ratings of 125 watts. As more mainstream parts, all five new CPUs run are rated to disperse about 95 watts of heat under full load. It appears that AMD is now pushing 125 watts as its maximum TDP for desktop parts. Only one chip, the original Phenom X4 9950, hits 140 watts. All others are 125 watts or lower. Again, here’s a view from the TDP perspective.

We can’t touch on this CPU launch without tackling the big question: DDR3.

And you can’t tackle DDR3 without openly wondering why the hell is AMD so slow in adopting new memory standards? We find this to be especially ironic because it was AMD that made DDR what it is today.

Years ago, Intel decided that a fast, serialized, memory standard would benefit PCs. The solution to this was Rambus’ Direct RDRAM memory. Intel bet it all on RDRAM and restricted the Pentium 4’s chipsets to Direct RDRAM only. The problem is the RAM maker’s didn’t want RDRAM due to the licensing fees that they would have to pay Rambus. But what could they do if Intel made the CPUs and chipsets for it?

AMD saw it’s opening and led memory makers in a mutiny against Intel by supporting DDR with Athlon. The mutiny was successful, Direct RDRAM was tossed under the bus and Intel embraced DDR with a bear hug. Although we now believe the industry and the media (including Maximum PC) made a mistake by not moving to Direct RDRAM, or at least, something similar to it, DDR was the standard.

So how the hell did AMD turn from the darling of the memory industry into a perceived drag ass? DDR2 was adopted by Intel two years before AMD introduced AM2. And Intel’s DDR3 chipset has been around since late 2007.

We’ve long had a pet theory that moving the memory controller into the CPU has taken some flexibility out of memory choices. The original Athlon 64 was hard wired to only run DDR. Likewise, AM2 Athlon 64s and Phenoms could only run DDR2. AMD’s solution to supporting both DDR2 and DDR3 is to build a memory controller that supports both types of RAM into the AM3 procs.

AMD’s official explanation for its seemingly slow memory updates is that it only adopts new memory standards when its cost effective and when people actually want it. Hence, even with AM3, the company is still pooh poohing DDR3. AMD says it still believes the vast majority would rather have the cost savings of DDR2 over DDR3.

DDR2’s cost performance over DDR3 isn’t what it once was though. A year ago, 2GB of DDR3 would fetch several hundred dollars. Today, you can buy 4GB of Crucial DDR3/1066 for $79. Change your selection to 4GB of Crucial DDR2/800 and it would cost you $38. So DDR2 does cost 100 percent more, but we’re talking 80 bucks here folks for 4GB of RAM.

Finally there’s price.

AMD’s pricing on its CPUs has been a great deal for consumers. It is a bit confusing though. At first glance, you’d think it was 22 CPUs spread out in a price band from $225 to $101. But two of those chips are OEM only. Another four are aimed at servers and media center PCs and another four are for business desktops.

Performance

How we tested

We used an MSI DKA790GX board outfitted with 4GB of Patriot DDR2/1066, a PC Power and Cooling 1200 Watt PSU, a GeForce 8800GTX and 150GB WD Raptor drive to test the three AMD procs. As a comparison, we used a 2.83GHz Core 2 Quad Q9550 in a Gigabyte GA-X48-GQ6 with 4GB of DDR3/1333 with a WD Raptor 150 and GeForce 8800GTX. For the Core i7-920, we used an Intel DX58SO with 3GB of DDR3/1066, GeForce 8800GTX and WD Raptor 150 drive. All configurations used Windows Vista Home Premium in 64-bit flavor.

The results were mostly what we expected. Performance against its sibling, the 3GHz Phenom II X4 940 was what you would think a CPU with 400MHz fewer clock cycles would score. We did see some unexpected results though. The AM3 Phenom II X4 810 part slightly outscored the Phenom II X4 940 in several of the memory benchmarks. We didn’t expect this given that we were running it in the same board with the same RAM and with same RAM speeds and timing set. This is either a hiccup in our test or an errant setting from our earlier test of the 940. We unfortunately didn’t have time to go back and rerun our tests with the 940. It is also possible that AMD has taken the extra few months it had with the newer AM3 parts to tweak the memory controller.

Between the Intel and AMD chips there was no comparison but that’s no surprise. AMD doesn’t expect the 810 to take on the 2.83GHz Core 2 Quad Q9550. Instead, AMD believes the CPU is better matched against the budget 2.33GHz Core 2 Quad Q8200 part. The $163 Q8200 has 2MB less L2 cache than the Q9550 and runs about 500MHz slower. We didn’t have Intel’s ultra budget part handy to test but subtract 500MHz from the Q9550’s scores and take away a small bit for the cache and both parts are likely competitive with each other.

The $284 Core i7-920, of course, is the fastest of the bunch but it’s also more expensive to buy and build a machine around.
Realistically, this comes down to Phenom II vs. Core 2. There, it’s a competitive crowd as Intel has as many or more CPUs than AMD does. There is only one advantage an AMD builder would have over an Intel machine: future upgrades.

Intel is pretty set to push the superior performing Core i7 as the platform of the future and is unlikely to spend the money and engineering to say, qualify a 3.5GHz CPU for the Core 2 platform. AMD, on the other hand, is committed to AM3 for now. That means it’s possible we’ll see a 3.4GHz or 3.6GHz Phenom II down the road. And even if that chip comes out in AM3 the backwards compatibility with AM2+ means those people won’t get left behind either.

While Core 2 Quad certainly has some legs left in it, those with an eye towards future upgrades should look to Core i7 if they want performance. And if they just want a good performing budget chip, AMD’s Phenom II is actually looking like a more stable platform over Core 2 right now. We’re not at all saying that Core 2 is dead, especially since in many ways, it still far outperforms all of AMD’s CPUs, but in six or nine months, Core 2 will feel stale as only Core i7 and Phenom II will get performance upgrades.

Ultimate Core i7 Overclocking Guide -- We Push Nehalem to its Limits

Gordon Mah Ung — Thu, 05 Feb 2009 12:00:00 -0600

Here’s everything you need to know about overclocking Intel’s new CPU

Overclocking can kill your CPU. It can corrupt your OS, melt your motherboard, and cause you to lose a month’s work or more. Despite those dire orange-alert warnings, however, overclocking has moved on from the Nerd’s Only Club to become practically a mainstream hobby in the last few years.

So why overclock if the risks are so great? For some folks, it’s about bragging rights. Like drag-strip racers who burn up an engine just to set a quarter-mile record, there’s a small community who will overclock a CPU to the brink of destruction just to run a benchmark and take a screen shot of the result.

The bulk of overclockers, however, are more concerned with the cost dividends. If you can take a $300 CPU and make it as fast or faster than one that costs $1,000, the money you save can go toward other components in your system. For these folks, it’s like getting a free high-end videocard.

Whether you’re a cheapskate or a drag racer, you’ll find that Intel’s new Core i7 CPU is unlike any previous Intel CPU, and overclocking this beast requires more tinkering than you might expect. Follow along as we explore what it takes to push this chip hard.

A Brave New World -- The crumbling of the front-side-bus wall means a wholesale change in how you overclock Intel’s top parts

Veteran Intel overclockers know that little about the process changed since the beginning. Like the basics of flying (stick, rudder, ball), all you had to worry about with an Intel processor was the front-side bus, clock multiplier, and core voltage.
Not so with Core i7. With Intel retiring the front-side bus, you’ll need to brush up on your overclocking skills and concepts if you want to get the highest-performing overclock out of the Godzilla of CPUs.

The Base Clock

If you haven’t kept up on current events, you need to know that Intel eliminated the front-side-bus architecture that has connected the CPU to the core-logic chipset since 1978. The memory controller, which used to sit in the chipset, is now integrated directly into the CPU.

Go into the BIOS on a Core i7 and you won’t see any reference to the front-side bus. Instead, it’s now the base clock or bclock. Some BIOSes also refer to this as the host clock or reference clock. On the current i7 procs, the base clock is 133MHz. While it’s not a front-side bus, most overclocking methods will require that you tweak the base clock just as you did with older FSB-based Intel chips and push it beyond 133MHz. One important thing to remember about the base clock is that it is the main reference clock for other components in the CPU— goosing this one setting will also overclock the RAM as well as the “uncore” (i.e., the L3 cache, memory controller, and Quick Path Interconnect, or QPI). We’ll get to more on this shortly.

Doing the Math

One thing that has not changed at all is the multiplier. The Core i7-965 Extreme Edition features a multiplier of 24 and is unlocked so you can move it up or down. The budget Core i7-920 features a multiplier of 20 and is upwardly locked so it will not move past 20. Experienced overclockers can grab a hall pass and skip to the next section, while those who have never done this before will need to stay in the classroom. As it was with the Core 2 and Pentium 4, the overall clock speed of the CPU is derived by multiplying the base clock (formerly the FSB) by the multiplier. For the 965, take 24 and multiply it by 133 to get 3200MHz or 3.2GHz. For the 920, take your multiplier of 20 and multiply by 133 to get 2667MHz or 2.66GHz.

Turbo Talk

One wrinkle to the multiplier is the new Turbo Mode. This mode essentially automatically overclocks a single core of the CPU under certain loads. If you have overclocked a Core i7-920 to 3.66GHz and then you switch on Turbo Mode, the CPU will actually run at 4.03GHz in single-threaded apps. Is it worth it? Frankly, we’re not sure. We are getting to the point where it’s pretty rare to be running performance-intensive single-threaded applications, so the performance boost will be minimal. You do get a 1x multiplier boost in dual-threaded apps so you most games would run at 3.83GHz. Sounds good right?

Our engineering sample Core i7-920 gave us results in line with what others have achieved with engineering sample parts as well as retail parts.

Unfortunately you can’t set your individual Turbo Mode settings on the cheap chips. Intel limits fine-grain Turbo Mode control to the Core i7-965 Extreme Edition. The pedestrian Core i7-920 and Core i7-940 are limited to a single multiplier increase for single-threaded apps, which is of marginal usefulness. It’s also clear that not all motherboard vendors think Turbo Mode is worthwhile. We’ve tested two different Asus boards that don’t implement Turbo Mode the same way Intel does. Instead of letting the user set the individual Turbo Mode settings on an Extreme Edition chip, your only option is to overclock all cores simultaneously.

Turbo Mode is something that should be evaluated based on your needs and the specifics of your overclock. For example, our case study actually found that a moderate overclock with Turbo Mode gave us better benchmark results than a higher-speed overclock without Turbo Mode.

Uncore: Separate but Connected

The Core i7 is a modular design with two main areas, the “core” and the “uncore”. Inside the chip, the actual execution cores that do the heavy lifting are treated as the “core.” The other parts, such as the integrated memory controller, L3 cache, and the Quick Path Interconnect are treated as the “uncore.” Since they’re separate entities, you can overclock the execution cores without overclocking the uncore to the same degree, in theory. This should let you hit higher speeds, since you wouldn’t be running the QPI, memory controller, or L3 quite as hard. In reality, however, it doesn’t work that way. Intel’s non-Extreme Edition Core i7 CPUs offer limited control over the uncore multiplier, so a boost to the base clock boosts the uncore speeds as well.

You need to set your Uncore multiplier to at least twice the multiplier for the system RAM. Also pay attention to the memory voltage. We had to run 1.66 volts for stable performance even at low RAM clock speeds. QPI also needed to be nudged up to 1.3 volts.

One thing to remember as you fumble around the BIOS is that the uncore must run at twice the speed of the system RAM. Here’s where it gets a little confusing. The speed of the uncore is determined by multiplying the uncore multiplier by the base clock. On a Core i7-920 chip, for example, the uncore defaults to 16. The uncore thus is 16 times 133 for a total uncore speed of 2,133MHz or 2.1GHz.

To figure out the RAM speed, you have to take the memory multiplier and multiply it by the base clock. In the case of a Core i7-920 chip, the default memory multiplier is 8. So to determine the main memory speed, multiply 8 by 133 for 1,066MHz. Why aren’t higher DDR3 speeds available? The highest official memory speed of the Core i7 is DDR3/1066. You can overclock your RAM to higher speeds, but depending on the motherboard, the only way to accomplish a memory overclock will be to crank up the base clock for the CPU—unless you own an Extreme Edition CPU.

The take away here is to remember to keep the uncore speed at twice the speed the RAM runs. If you plan to run DDR3/1600, you’ll need to run the uncore at 3,200MHz. On a Core i7-965, you can run that speed without overclocking. On a Core i7-920, you’ll have to overclock the base clock to get the RAM at that speed.

More about QPI

Another new element to the Core i7 is the Quick Path Interconnect that we mentioned earlier. This high-speed interface connects the processor (or processors, in a multi-proc machine) to the chipset. Intel currently has two QPI speed iterations. The Core i7-965 Extreme Edition runs at 6.4 gigatransfers per second and the non-Extreme chips, such as the Core i7-920 and Core-i7-940, run at 4.8GT/s.

The QPI is important to watch because ramping it up too far can kill your overclock. For example, pushing the base clock from its stock 133MHz to 200MHz on a Core i7-920 means that the QPI will default to 7.2GT/s. That’s quite bit more speed than the stock 4.8GT/s; however, we successfully tested a Core i7-920 running at 7.2GT/s and believe that’s still within the realm of viability.

The QPI speed of the Core i7-920 and Core i7-940 is derived by multiplying the base clock (133) by 36, which equals 4788 or 4.8GT/s. The Core i7-965 uses a default QPI multiplier of 48, but unlike the non-Extreme chips, the 965’s multiplier is not locked. If you believe your overclock is failing because you’ve cranked the QPI too far, you can try dropping the speed by changing the QPI multiplier. On some overclocking runs with a Core i7-965 Extreme Edition, we had to drop the QPI back from 7.68GT/s to 7.04GT/s to increase reliability. The bad news is that you can’t do this with the budget chips.

Turning off the CPU VR Current Limit Override in the BIOS prevents the CPU from throttling back the multipliers under the Turbo Mode. Notice the lack of Turbo Mode tuning versus that with an Extreme Edition installed.

Va Va Voltage

You probably learned as a three-year-old not to mess with electricity after that incident with the wall socket. The dangers of electricity haven’t changed, but to wring the greatest clock speed out of your CPU, you’re going to need to overvolt the suckah. Actually, it won’t be just the CPU—our highest reliable overclock was only achieved by upping voltage to the CPU and parts of the chipset.

How much is too much? The default core voltage of the three current Core i7’s is 1.2 volts. We were able to push voltage to 1.5 on a budget Core i7-920 and successfully make it through some torture testing, but in our opinion, that’s probably too much juice (at least with air cooling). Sure, it ran our stress tests for a reasonable amount of time, but we don’t think the chip will live for long. A more reasonable voltage is probably 1.4 volts (just slightly more than the maximum allowable of 1.375), but take that with a grain of salt, too. Because your CPU, motherboard, cooling, and PSU will be different, the amount of voltage you can add will likely vary from our scenario.

Another area you’ll have to overvolt is the QPI interface. You’ll likely have to increase the voltage from its stock 1.1 to 1.3 to get a reliable overclock. Some folks recommend running QPI voltage at or above the CPU’s core voltage, but we didn’t have to on our budget chip as it was happy with 1.3 volts. Our Extreme Edition, however, needed 1.5 volts to the QPI, which was equal to the CPU voltage. Finally, you’ll have to add voltage to your RAM to get it to higher speeds. There has been chatter that a RAM voltage exceeding 1.65 can destroy a CPU— fortunately, most of the high-performance DDR3 binned for Core i7 doesn’t seem to need more than 1.66 volts to run, which is certainly within reasonably safe limits.

Sometimes the highest clock isn’t the best for performance with Core i7. Using Turbo Mode, we saw a 3.66GHz chip perform as well as one running at 3.80GHz, and without the excess heat and voltage.

Cool Running

Overclocking and cooling go hand in hand. If you can keep the CPU cool, you’ll increase your overclocking limit. For the majority of our testing, we used a beefy ThermalRight 120. As good a reputation as this cooler has, it’s still just an air cooler. Water cooling is an even better choice for overclocking as it’s more efficient at removing heat from the core. Better still would be an exotic phase-change or Peltier unit that could bring the CPU temps far below zero degrees Celsius.

What’s a safe temperature for Core i7? That’s also open to debate. We had to dig around the Internet to find that all three Core i7s have a maximum recommended temp of 67.9 Celsius. That, however, is the maximum temperature taken on the outside of the heat spreader with a calibrated thermistor. In English, that means that if you’re being told that all four cores are running 82 C under full load, you’re probably OK for the short term—but your chip probably won’t last five years. It would be wise to aim for 80 C or lower, and even better to run in the 70 C range. Just remember that you may have to crank it all back in the summer.

Breaking It Down

If your head isn’t spinning by now, you’re in good shape, but most people, even somewhat seasoned overclockers, will want a stiff drink after trying to absorb this information. So let’s review.

You buy a new 2.66GHz Core i7-920—you just couldn’t splurge on the Core i7-965 Extreme Edition. You’ve got a reasonably chunky air cooler, a good-quality PSU, and you want to overclock that proc. What should you do? First, you need to start goosing up the base clock until you get a clock speed that seems reasonable for the CPU. So, let’s say you want to aim for a nice conservative 3.5GHz. Start by setting your base clock to a speed that will get your CPU in the region. Take it from 133MHz to, say, 160MHz. The target clock speed you’ll want is actually 175MHz for 3.5GHz, but we’ll start with 160MHz.

We’ve read posts on the Internet of some people being able to reach a high clock speed without the need for additional voltage to the CPU, so you’ll want to see if your CPU is capable of it. If you want a good real-world test, run your favorite multithreaded encoder, such as HandBrake. Nero’s Recode is also multithreaded and will put a reasonable load on the CPU. If you want to really torture it, download Prime95 from www.mersenne.org. Unzip it and run Prime95.exe. Select In-place FFTs and make sure the number of threads is set to eight. By default, it should be eight for a Core i7. If it runs for, say, half an hour, you can aim higher. Add 5MHz to your overclock and try again. Go until it fails.

Extreme Edition CPUs feature unlocked QPI and memory ratios and even let you override the individual Turbo Mode settings and change how the CPU throttles under power loads to either let you run higher overclocks or nuke your CPU faster.

Now it’s time to add voltage. A good starting point is 1.35 or 1.375 volts. Since 1.375 is the maximum allowable voltage under spec, you’re actually still playing it very safe. While you’re there, you may want to add voltage to the QPI. So nudge it up from 1.1 volts to 1.3 volts. Some say that the QPI voltage should at least equal the core voltage, but that’s up to you. You should also add voltage to the RAM to get it to spec. If you’re using RAM rated for higher speeds, give the RAM the amount the maker suggests. The safe limit seems to be 1.66 volts.

Intel says it locked the QPI and memory multipliers on its budget chips but some motherboards appear to circumvent this. If your board does this or you’re running an Extreme Edition, which has unlocked QPI and memory multipliers, you can try backing down your uncore and RAM multiplier. Most BIOSes should correct the ratios for you, but remember that the uncore multiplier should be twice that of the RAM. So if the RAM multiplier is set to 10, set the uncore multiplier to 20. If you back the RAM multiplier down to six, you can set your uncore multiplier to 12.

Now reboot and rerun your stress tests. Keep repeating the steps we’ve outlined until you hit your target or hit a wall. Once you’re at your target, do a longer stress test with Prime95 to see if it is truly stable. You may have to add cooling or voltage to get it to run for several hours.

Remember, cooling and quality power matter. If you think you can do all this with a cheap power supply and straw heatsink, think again. Want to know how far can you get Intel’s cheapest Core i7 to overclock with air cooling? Read our case study to find out.

Case Study: Core i7-920

Can you make Intel’s cheapest i7 outperform the vaunted Core i7-965 Extreme Edition?

For our case study, we decided to stick with what the overwhelming majority of overclockers will select: Intel’s cheapo $285 2.66GHz Core i7-920. We paired this chip with an Intel DX58SO “Smackover” board, 6GB of Corsair Dominator DDR3/1600 RAM, an EVGA GTX 280 videocard, a WD 150GB Raptor, and a PC Power and Cooling Turbo-Cool 1200.

For cooling, we used a ThermalRight 120 and ran the board on a lab bench with three small fans for auxiliary cooling: an 8cm on the hard drive, an 8cm USB fan blowing on the RAM, and a 12cm fan directed at the voltage regulators and the heatsink.

We used Windows Vista Home Premium in 64-bit and ran a few benchmarks at the CPU’s stock 2.66GHz clock speed with the default Turbo Mode on. We then used the board’s OS-based overclocking tool for the majority of our overclocking attempts. Why? Normally we prefer the BIOS as we don’t want to deal with yet another app starting in Windows, but the Intel Desktop Control Center let us turn knobs and tweak settings without having to boot into the BIOS. This saved us invaluable time.

For stress-testing, we used a custom blend of Prime95 that Velocity Micro developed for overclock testing. We’ve long used the utility and have found it to push machines harder than any other test.

We know from previous experience that the Core i7 seems to need a minimum QPI voltage of 1.3 volts, so that’s where we started. We intentionally kept our RAM clock speeds down since we just wanted to see how far we could push the CPU, but we were surprised that we had to move the voltage to 1.66 volts to reach stability. After a day of testing and one OS reinstall, we decided that the best performance we could squeeze out of the Core i7-920 was 3.66GHz with Turbo Mode on. This was done with a base clock of 183MHz, the core voltage at 1.4 volts, the RAM at 1.66 volts, and the QPI at 1.3 volts for a QPI speed of 6.59GT/s.

With Turbo Mode, the default 20 multiplier occasionally reached 21 or 22 for an effective clock of 3.83GHz to 4.03GHz, which allowed us to achieve benchmark results on par with our higher overclock attempt: We topped our chip out at 3.8GHz with 1.5 volts but the CPU’s thermals were unacceptable, running into the mid 80s C. In our Lab in the winter, that’s fine, but we knew this overclock would never survive a real summer in a real home.

Our take away is that it should be very easy to push the 2.66GHz Core i7-920 by 1GHz, and more conservative overclocks of 3.5GHz or 3.4GHz should be extremely easy. But to expect a truly reliable overclock over 3.6GHz will require good-quality water cooling.

Core i7-920 Benchmarks

	2.66GHz (Turbo On)	3.66GHz (Turbo On)	3.66GHz (Turbo Off)	3.8GHz (Turbo Off)
Cinebench 64-bit 10 w/ 8-threads	16,097	21,474	21,013	21,640
Cinebench 64-bit 10 w/ thread	3,869	5,251	4,973	5204
ProShow Producer	11:43	8:05	9:40	8:45
3DMark Vantage Overall	14,720	15,010	14,963	14,984
3DMark Vantage GPU	12,099	12,133	12,133	12,129
3DMark Vantage CPU	42,042	51,987	49,860	51,012
Valve Particle Simulation	140	190	180	186
Main Concept Reference AVC Pro	11:57	9:13	9:16	8:57

Best scores are bolded.

How Reliable is Your Overclock?

If you’re ever in an online game where some dude brags that he’s running his blah, blah rig at blah, blah speed using special blah, blah tricks, take it with a pound of salt. Like the great fish that got away, people tend to inflate their overclocking achievements.

We were very happy with Intel’s Desktop Control Center as an OS-based overclocking tool but this 4GHz overclock was just wishful thinking.

Sometimes they don’t even know they’re exaggerating. If you think pushing a machine to 5GHz and running a game marks an overclocked rig as bullet proof, think again. The majority of today’s games barely push two threads, and even when they do, the CPU doesn’t do much. The truth is that much of the heavy lifting in games is done on the GPU, so you can’t use gaming as a true judge of a stable overclock.

Instead, try a multi-hour encode or transcode of a video using a multithreaded encoder like HandBrake. Even better, try a serious ball-buster like Prime95. This math-heavy prime-number hunter features a built-in torture test that is truly torturous. For the majority of our tests here, we used a custom-blend of Prime95 that we’ve found to put the heaviest load on overclocked CPUs. In our experience, the benchmark manages to properly put our overclocking hopes in their place by blue screening an unstable machine in mere minutes.

If your machine will withstand a couple of hours of Prime95, you’re doing good. If it’ll run over night, it’s bullet resistant. If it’ll run overnight in the middle of the summer, in an 80 degree room, well, you really have something to brag about.

Core i7 Budget Buyers, Beware

It got to be so easy to overclock Intel’s Core 2 line that a Mac user could one-mouse button the cheapest 10MHz Core 2 chip to 12GHz. That pretty much killed demand for Intel’s 3.2GHz Core 2 Extreme QX9770 CPU since the only difference was an unlocked multiplier and higher front-side bus (Intel’s insane pricing didn’t help, either.)

With the Core i7, Intel is being a far more aggressive in differentiating the Extreme chip. No longer is it just a multiplier lock. With the Core i7-920 and Core i7-940, you cannot set the individual Turbo Mode ratios. The thermal override switch and amperage override are also disabled. Finally, QPI ratios and memory ratios are similarly limited.

Does this make the Extreme Edition a chip that you must have? It depends. Swapping the Core i7-920 with a Core i7-965 Extreme Edition is like moving from a budget car to a luxury car built on the same platform. You’ll reach for a knob in the budget car that was there in the luxury car and find that it’s not there.

In our experience, it was easier to get the Core i7-965 to the limits imposed by our air cooling than it was with the budget CPU. While it took us an afternoon to get the Core i7-920 to a reliable 3.80GHz, we had the Core i7-965 Extreme Edition at 3.83GHz in a few minutes. By adding the Turbo Mode, we had the latter chip effectively running at 4GHz, and we’re certain higher speeds were attainable with better cooling. One thing to keep in mind though: While the Core i7-965 will likely reach higher speeds than the Core i7-920, it won’t give you the same amount of headroom. That is, you can get a 1GHz overclock with the Core i7-920 on air but you won’t be able to do the same with the Core i7-965 without water or something more exotic.

Is the 965 Extreme Edition a better overclocker? Certainly. Is it worth the extra $700? That’s a tough call and ultimately something only you and your bank account can answer.

The Best of the Best Just Got Better

Florence Ion — Thu, 29 Jan 2009 18:22:54 -0600

Stop the presses! (Ok, maybe not). We wanted to let you know that Best of the Best, our comprehensive list of our favorite PC hardware components, has just been updated and overhauled with new categories and parts that you’ll need to consider for your next PC build or upgrade.

In addition to three new processor categories (Extreme, $500, and $250), we’ve listed our pick for the top Core i7 motherboard. The budget through high-end GPU lineup as also been refreshed, and we now make two hard drive recommendations based on performance and capacity.

Check it out!

Intel to Cut Chip Prices Soon

Andy Salisbury — Wed, 14 Jan 2009 15:16:55 -0600

It looks like Intel’s pricing on their lower-end quad-core processors will be reportedly going down on January 18th. This comes in the wake of AMD’s latest 45-nm Phenom II and Shanghai Opteron chips.

AMD’s newest quad-core beast, the Phenom II Dragon processor has been garnering some pretty high acclaim as of late. Its even being featured in servers by Hewlett-Packard, Sun, Dell, IBM and Fujitsu.

The cuts are expected to be on only the quad-core processors, but it’s still very much a possibility that other chips could receive cuts.

Image Credit: Intel