Intel's MMX Inside

The 57 instructions that make up MMX use a technique called Single Instruction, Multiple Data (SIMD) to deliver better performance by performing more tasks in parallel, or at the same time. Joanne Hasegawa, an Intel spokesperson, says MMX works because of the nature of most multimedia programming code.

"Multimedia and communications code tends to be small and repetitive," she says, "but there just seems to be so much of it." MMX lets the chip churn through more of these operations at once rather than serially, or one another. When the chip does more jobs at the same time, everything speeds up.

Intel says the performance boost will let its processors run several simultaneous, CPU-intensive multimedia tasks with more than enough power left over for additional applications. MMX is an attempt to keep the Intel-based PC in its position as the premier tool for running today's graphics-rich multimedia software and games. Other microprocessor companies such as Sun have added similar instructions to their architectures, but MMX appears to be the most ambitious such attempt to date.

MMX technology is based upon a careful analysis of multimedia applications. Intel engineers found that most video, music, image processing, and game applications shared several key features in the way they used a CPU's computing time. Chief among these was the large number of small, repetitive loops a program goes through to redraw screen elements or replay bits of sounds. MMX technology adds instructions to Intel chips to grant them special capabilities for dealing with these short, repetitive arithmetic operations.

In a graphics application, for instance, the individual pixels—the tiny dots that together make an image on a screen—usually are represented inside the computer as 8-bit numbers, or bytes. In a chip using MMX technology, eight of these bytes might be packed into one 64-bit number and moved together into the MMX area of the CPU. The necessary mathematical operations then are performed on all eight bytes at the same time.

The faster performance provided by this advanced number-crunching means developers can pump bigger data strings through the CPU in the time smaller strings now take. This ability leads not only to faster software, but to better software.

Intel's MMX Boosts Multimedia

Intel plans to roll out new versions of its flagship desktop chip later this year, featuring special multimedia extensions for zipping through graphics and sound-intensive tasks. Intel calls its "MMX" multimedia instruction set the most significant enhancement to the Intel chip architecture since the 386 CPU, which extended the 80x86 family to 32 bits.

While Intel's statement invites charges of public relations exaggeration, designers at software companies from Macromedia to Microsoft lining up to incorporate the new technology into their code. Users will get to see for themselves how speedy MMX really is by the fourth quarter of 1996. The first MMX-enhanced Pentium, code-named P55C, is set to begin shipping toward the end of the year, with large-volume shipments ramping up in 1997. Because MMX instructions must be built into the CPU, owners of existing 486s, or even Pentiums, won't be able to add MMX to their systems without upgrading the entire chip.

Intel acquires Xircom

The announcement came just before the release of its full-year 2000 results and as Nasdaq-listed Californian-based Xircom released Q1 2001 results.

The all-cash deal is expected to be completed in the first quarter of this year, after which Xircom will become a wholly owned subsidiary of the Network Communications Group. Xircom's board of directors has approved the $25 per share agreement and recommended stockholders accept the offer.

Mark Christensen, Intel vice-president and general manager network comms, said: "The acquisition provides Intel with an award-winning line- up of products and technologies in the fast growing mobile computing area.

"Xircom's strengths in small form factor design, combined with our silicon expertise, will allow us to provide customers with news and innovative solutions for linking mobile computing devices to corporate wired and wireless networks."

Xircom's Q1 saless were down 3.22% to $120.1m, with net income, excluding acquisition-related costs, of $200,000, compared to $15.3m, although when those costs are included it made a loss of $2.5m.

The combined strengths of Intel and Xircom will be a tremendous benefit. Customers will have access to a more complete line of products and will benefit from the innovation our companies will apply to mobile computing and wireless network.

Intel's 65W Quad-Cores

Core 2 isn't going to be phased out soon, we're unlikely to see many more releases under that moniker. Last month, specifications were leaked for a potential Core 2 Duo E8700, a 3.5GHz offering, which we could probably expect to be the final C2D Dual-Core chip, although nothing's ever really set in stone. On the Quad-Core side of things, Intel helped pad their line-up with the help of three new models, launched late last month.

Each of these new models belong to the "S" series, although I don't believe that the letter represents an actual word. In addition, each of the new chips are absolutely identical to their non-"S" counterparts, aside from the lower TDP. At the top-end, the Q9550s is Intel's only 65W offering that includes 12MB of L2 Cache. This chip, like the original, settles in nicely at 2.83GHz.

That's not the CPU we're investigating today, however. Rather, we have both the Q9400S and Q8200S, two different processors that cater to two different crowds. The mid-range Q9400S runs at 2.66GHz and includes 6MB of L2 Cache, while the Q8200S (and non-"S") currently remains as Intel's lowest-end desktop Quad-Core offering, at 2.33GHz with 4MB of L2 Cache. All three of the new models continue to run with a 1333MHz front-side bus.

Intel's 65W Quad-Cores - A Closer Look

So, what's the reason for a launch of 65W Quad-Core parts at this point in time? It's difficult to assume, but it could be that since the Core i7 launch, the company hasn't released much in the way of processors, so the timing might have seemed right. To add to it, we can no longer go a single day without hearing about the effects of global warming and the shape of the environment, so the "S"-line might intrigue crowds who are passionate about those issues.

There is one caveat, though - the price. in our news a few weeks ago, these models are going to see limited adoption solely because of their premium pricing, and even Intel themselves acknowledge this. People that purchase these are those who are either building SFF (Small Form-Factor) PCs and want a fast CPU with great thermals, or those who are simply looking for the fastest CPU with the lowest power consumption possible.

Intel notes that all three of these models have been available as off-roadmap chips to OEMs for some time, and that won't change. It's only now that they've begun offering them to regular consumers, and while it's still catering to a very specific audience, it's a nice move.

Quad-Core CPU Name	Cores	Clock	Cache	QPI/FSB	TDP	1Ku Price
Intel Core i7-965 Extreme Edition	4	3.20GHz	8MB	3200MHz	150W	$999
Intel Core i7-940	4	2.93GHz	8MB	2400MHz	130W	$562
Intel Core i7-920	4	2.66GHz	8MB	2400MHz	130W	$284
Intel Core 2 Extreme QX9775	4	3.20GHz	2 x 6MB	1600MHz	150W	$1,499
Intel Core 2 Extreme Q9650	4	3.00GHz	2 x 6MB	1333MHz	130W	$316
Intel Core 2 Quad Q9550S	4	2.83GHz	2 x 6MB	1333MHz	65W	$369
Intel Core 2 Quad Q9550	4	2.83GHz	2 x 6MB	1333MHz	95W	$266
Intel Core 2 Quad Q9400S	4	2.66GHz	2 x 3MB	1333MHz	65W	$320
Intel Core 2 Quad Q9400	4	2.66GHz	2 x 3MB	1333MHz	95W	$213
Intel Core 2 Quad Q9300	4	2.50GHz	2 x 3MB	1333MHz	95W	$266
Intel Core 2 Quad Q8200S	4	2.33GHz	2 x 2MB	1333MHz	65W	$245
Intel Core 2 Quad Q8200	4	2.33GHz	2 x 2MB	1333MHz	95W	$163

As seen in the table above, the pricing premiums are rather stark. Where the Q8200 is concerned, we can see a 50% ($82) increase, while at the top-end, the Q9550 sees a 38.7% ($103) bump. There's an obvious price to be paid for fine-tuned products, but it's still too bad to see increases like these. If it was a more modest bump, we'd likely see far greater adoption.

One thing that should be stressed though, is that while the new models will naturally draw less power over time, when compared to non models, thermals will alo see an improvement. With less voltage being required to run to the CPU, the temperatures will drop, which is one of the reasons the "S"-line is perfectly-suited for SFF PC builders.

Intel Reveals Westmere 32nm Roadmap

That announcement was a precursor to a media briefing that was held this afternoon, where all of the focus was directed towards the company's "Tick" phase. As a quick recap, Intel abides by a Tick/Tock methodology, where the Tock is a brand-new micro-architecture, such as Nehalem, while Tick is a revision, which, up to now, has always involved a brand-new process.

As we've known for a while, Intel's first 32nm processors are known as Westmere, which is a follow-up to Nehalem. However, there's a lot more to Westmere than just a die shrink, as Intel has made numerous changes to the architecture. No joke. Intel has either changed or added so much here, that Westmere could almost be considered to be a "Tock" phase. But, Westmere isn't really a brand new micro-architecture, but a revision to Nehalem, with many features tacked-on.

One of the main pieces of information most people are going to look for out of a media briefing like this is the roadmap update, and that's one thing we got. Although most of the talk was about Westmere, we're still far from done with the 45nm offerings, and many more are en route. Take the Lynnfield desktop chip, for example, which is likely to come out as Core i5, and also the mobile counterpart Clarksfield. Both of these chips will be Quad-Cores that feature 8 threads, just like Nehalem. Imagine that... eight threads on a notebook.

Both the desktop Lynnfield (LGA-1156) and mobile Clarksfield (mPGA-989) will become available sometime this year, with the 32nm parts to come later. What's most notable about the 32nm parts though, is the fact that initial models will deliver both a GPU and CPU inside of the same processor.

This is an area where we have to divulge a little more information, because this progression is far too important to just skip through. When launched, Intel will likely become the first to offer a GPU + CPU in one package, the result of which should be IGP graphics performance that is unparallelled to anything before it. It's really hard to conclude on that thinking without testing the processor out for ourselves, but placing a GPU so close to the CPU has got to be something that brings noticeable benefit.

The major changes don't end there, however... even our motherboards will undergo some alteration. Because of the die shrink, and the move of the memory controller onto the CPU, various components have been shifted around, as a result, the Southbridge has been removed entirely. The slide shown below gives an example of the new "2-Chip Solution".

Intel Core 2 Overclocking Basics

Intel's LGA 775 Core 2 series has been an extremely successful line of desktop processors. Most models are somewhat overclockable, and some are real overclocking monsters. Both Intel and nVidia have recently produced motherboard chipsets really conducive to overclocking. In the past, it was obvious that all but a handful of motherboard manufacturers considered overclocking as an annoyance, but today, nearly all motherboard manufacturers incorporate overclock-specific features into their motherboards and BIOS, and advertise their motherboards as overclock-friendly.

Depending on the BIOS, overall, the Core 2 is an easy overclocker. Gains are easily seen by merely raising the FSB to increase the CPU speed. There are certain models, or particular steppings of models, that aren't great overclockers, but if the CPU happens not to be a great overclocker, gains can also be seen by lowering the CPU multiplier to keep the processor running at or near stock speed, and just increasing the FSB, or Front Side Bus, though usually a better motherboard is required for significant performance increases using that method.

Even though overclocking has come a long way from hacked BIOS, pencil tracing, etc, it still isn't for the squeamish. You can still fry your CPU or motherboard, though it is much harder due to safety measures built into Intel processors and most motherboards. But with a little preparation and forethought, nearly anyone can successfully give their rig some extra oomph by a mild overclock, or make it really scream with a serious overclock. Read on to find out how!

This primer is directed towards the begin overclocker, or for the enthusiast recently introduced to LGA 775 Intel processors. It will cover the bare basics, and is in no way intended to teach someone to be an extreme overclocker, nor will the seasoned Core 2 overclocker likely learn much if at all from this article.

Intel Core i7 Processors

Core Frequencies - 3.2GHz (965), 2.93GHz (940), 2.66 (920) QPI Speed - 6.4GT/s (965), 4.8GT/s (940, 920) TDP (Thermal Design Power) - 130W Stepping - 4 Number of CPU Cores - 4 Shared L3 Cache - 8MB L2 Cache - 1MB (256K x 4) Processor input voltage (VID) - 1.160v .045-micron manufacturing process Shared Smart Cache Technology PECI Enabled Enhanced Intel SpeedStep Technology (EIST) Extended HALT State (C1E) Enabled Execute Disable Bit (XD) Enabled Intel 64 Technology Intel Virtualization Technology (VT)

Packaging - Flip Chip LGA1366 Total Die Size: Approximately 263mm2 Approximately 731M Transistors MSRP - $999 (965), $562 (940), $284 (920)