Wednesday, November 02, 2005

Exploring the performance impact of memory latency Is 2-2-2-5-1T really worth it?

THESE DAYS, SEEMINGLY every major memory module manufacturer is producing fancy low-latency DIMMs. These DIMMs are equipped with tricked-out heat spreaders and come in a variety of different colors, making them easy to pick out in a crowd. There's more to them than funky cosmetics, though. The most exotic low-latency DIMMs are rated to run at extremely tight 2-2-2-5 timings at 400MHz. Unfortunately, you'll pay a small fortune for the privilege. Low-latency modules cost close to twice as much as more pedestrian DIMMs, if not more.

Lower latencies are a good thing, of course, but how much can they really improve system performance? Are exotic, low-latency DIMMs worth the price premium? Read on as we explore the effects of memory latency on Athlon 64 performance in synthetic memory benchmarks, games, and real-world applications.


Low latency DIMMs: Worth the premium?

Memory latency?
Before diving into our benchmark results, it's worth taking a moment to go over how memory access works and where the various latencies come into play. Memory is organized like a spreadsheet, with data stored in cells that can be identified by a corresponding column and row. Spreadsheets can also be made up of multiple sheets, and similarly, memory can be made up of multiple banks. If we want to access a specific cell of memory, the system must first activate the sheet, or bank, containing the desired row. Next, the system sends an active command to the desired row. Once the row is activated, the system can issue read or write commands to specific columns in the row. When reading or writing has been completed, a precharge command is sent to close the row.

There are delays between each of the steps in memory access. These delays are referred to as latencies and expressed as a number of clock cycles. Here's a brief explanation of some of the most common, and important, memory timing parameters that affect access latencies:

Of course, no discussion of memory latency would be complete without mentioning the DRAM command rate. The command rate is the delay between when a memory chip is selected and when the first active command can be issued. The factors that determine whether a memory subsystem can tolerate a 1T command rate are many, including the number of memory banks, the number of DIMMs present, and the quality of the DIMMs. Some memory manufacturers claim that their DIMMs are rated for operation with a one-cycle (1T) command rate.

Since latencies refer to delays, lower is better. That doesn't mean you should hop into your motherboard's BIOS and set each memory timing option to its lowest possible value, though. Memory modules are rated for a specific set of latencies at a given clock speed, and they're generally not stable with lower latencies. A DIMM's latencies are usually expressed as a series of four hyphenated numbers corresponding to the CAS latency, RAS-to-CAS delay, RAS precharge, and active-to-precharge delay. Low latency DDR400, for example, is generally rated for 2-2-2-5 timings at 400MHz. That refers to two cycles of CAS latency, RAS-to-CAS delay, and RAS precharge, and five cycles of active-to-precharge delay.


OCZ's Enhanced Latency Platinum Rev 2 DDR400 rated for 2-2-2-5 latencies

Our testing methods
We've tested several different memory configurations to illustrate the performance impact the key memory timings settings, including DRAM command rate. Tests were conducted with a set of low-latency OCZ DIMMs rated for 2-2-2-5 timings at 400MHz. We also tested with 2.5-4-4-8 timings to simulate the performance of more affordable "value" memory. Some budget memory is rated with CAS latencies as high as three cycles, but since CAS 2.5 memory is already quite affordable, we've limited our testing to CAS 2 and 2.5. In addition to testing system performance with 2-2-2-5 and 2.5-4-4-8 memory timings, we've also tested each configuration with both 1T and 2T command rates.

All tests were run three times, and their results were averaged, using the following test system.

Processor AMD Athlon 64 FX-53 2.4GHz
System bus HyperTransport 16-bit/1GHz
Motherboard DFI LANParty UT NF4 Ultra-D
BIOS revision N4D623-3
North bridge NVIDIA nForce4 Ultra
South bridge
Chipset drivers ForceWare 6.66
Memory size 1GB (2 DIMMs) 1GB (2 DIMMs) 1GB (2 DIMMs) 1GB (2 DIMMs)
Memory type OCZ PC3200 EL Platinum Rev 2 DDR SDRAM at 400MHz
CAS latency (CL) 2 2 2.5 2.5
RAS to CAS delay (tRCD) 2 2 4 4
RAS precharge (tRP) 2 2 4 4
Cycle time (tRAS) 5 5 8 8
Command rate 1T 2T 1T 2T
Hard drives Western Digital Raptor WD360GD 37GB SATA
Audio nForce4/ALC850
Audio driver Realtek 3.75
Graphics NVIDIA GeForce 6800 GT with ForceWare 77.77 drivers
OS Microsoft Windows XP Professional
OS updates Service Pack 2, DirectX 9.0c

Our test system was powered by OCZ PowerStream power supply units. The PowerStream was one of our Editor's Choice winners in our latest PSU round-up.

We used the following versions of our test applications:

The test systems' Windows desktop was set at 1280x1024 in 32-bit color at an 85Hz screen refresh rate. Vertical refresh sync (vsync) was disabled for all tests.

All the tests and methods we employed are publicly available and reproducible. If you have questions about our methods, hit our forums to talk with us about them.

Memory performance
We begin with some synthetic memory subsystem benchmarks that should easily expose any performance differences between the various settings.

Command rate has a profound impact on memory bandwidth in both Sandra and Cachemem. The difference in performance between 2-2-2-5 and 2.5-4-4-8 timings is much more subtle, though.

Moving to Cachemem's latency test, we see that the command rate again has a bigger impact on performance than the other memory timings options.

Cinebench 2003

Memory latency doesn't have much of an impact on Cinebench 2003 rendering performance, but our tighter 2-2-2-5 timings are a little faster in the shading tests. This time around, the command rate's impact on performance is less than that of the other memory timings. 2-2-2-5 isn't all that much faster than 2.5-4-4-8, though.

Sphinx

Sphinx is a sucker for fast memory subsystems, so it's no surprise that quicker latencies translate into better overall performance. Here, our 2-2-2-5 timings are close to 13% faster than more relaxed 2.5-4-4-8 latencies. Moving from a 2T to 1T command rate only improves performance by about 7%, though.

WorldBench overall performance
WorldBench uses scripting to step through a series of tasks in common Windows applications. It then produces an overall score. WorldBench also spits out individual results for its component application tests, allowing us to compare performance in each. We'll look at the overall score, and then we'll show individual application results alongside the results from some of our own application tests.

Only a single point separates our overall WorldBench scores, with the 2-2-2-5 configurations just edging out our 2.5-4-4-8 timings. Let's break down WorldBench's overall score into individual tests results to see if we can find a breakout performance.

Multimedia editing and encoding

MusicMatch Jukebox

Windows Media Encoder

Adobe Premiere

VideoWave Movie Creator

Tighter 2-2-2-5 timings improve performance in several of WorldBench's multimedia editing and encoding tests, but never by more than a couple of percentage points.

Image processing

Adobe Photoshop

ACDSee PowerPack

WorldBench's image processing tests don't see much benefit from either lower memory latencies or a more aggressive command rate.

Multitasking and office applications

Microsoft Office

Mozilla

Mozilla and Windows Media Encoder

Mozilla does show a difference between the settings, both on its own and when paired with Windows Media Encoder. Still, the differences in performance between 2-2-2-5 and 2.5-4-4-8 timings, and between the 1T and 2T command rates, are only a couple of percentage points.

Other applications

WinZip

Nero

Neither Nero nor WinZip shows much preference for quicker timings or a 1T command rate.

Gaming performance
We conducted our gaming tests with two sets of in-game quality settings. First, we tested at low resolutions with medium quality levels and antialiasing and anisotropic filtering disabled. We then tested at higher resolutions and detail levels, with antialiasing and aniso, to better reflect how most users would play games on a system of this caliber. The latter settings may bottleneck performance at the graphics card, but that's how things are with the vast majority of today's games.

3DMark05
Since you won't find anyone playing 3DMark05, we've limited our testing to the app's default settings.

Although 3DMark05's overall score is GPU-bound on our test system, the CPU rendering tests show some preference for a faster command rate and tighter timings.

Far Cry

Lower memory latencies give Far Cry a nice boost at a low resolution and detail level, but there's virtually no difference in performance at higher resolutions and detail levels.

DOOM 3

As we saw in Far Cry, the measurable performance impact of memory timings and the DRAM command rate in DOOM 3 seems to be limited to lower resolutions and detail levels, where the graphics card isn't a bottleneck.

Quake 4
Timedemos in Quake 4 don't appear to render all of the game's eye candy effects, but since we're only changing memory latencies and command rates, that shouldn't impact our results.

Again, we only see memory latency and command rates having an impact on performance at lower resolutions and detail levels. Here, CAS latency and its cousins have a more significant impact on performance than the DRAM command rate.

Unreal Tournament 2004

Unreal Tournament favors lower latencies ever so slightly at higher resolutions and detail levels, but the biggest performance impact remains at lower resolutions and detail levels. Even then, there's only about a 7% difference in frame rates between 2-2-2-5-1T and 2.5-4-4-8-2T.

Splinter Cell: Chaos Theory

Memory latency doesn't have much of an impact on Splinter Cell: Chaos Theory performance, even at a lower resolution and detail level.

Battlefield 2

Battlefield 2 performance was tested with FRAPS, and the differences in performance are only a couple of frames per second. I suspect that's within the margin of error of our manual tests, which were conducted at least five times before the results were averaged.

Conclusions
Although tighter memory timings and a 1T command rate can certainly improve the performance of the Athlon 64's memory subsystem, that improvement doesn't always translate to better application performance. In fact, with the exception of the Sphinx speech recognition engine, moving to tighter memory timings or a more aggressive command rate generally didn't improve performance by more than a few percentage points, if at all, in our tests. Lower latencies only improved WorldBench's overall score by a single point, and performance gains in games were generally limited to lower resolutions and detail levels.

So how much does the modest performance improvement brought by tighter memory latencies cost? Close to twice as much. As I write, a single 512MB stick of OCZ Value DDR400 memory rated at 2.5-4-4-8 sells for between $45 and $52 online, while a 512MB Platinum Rev 2 2-2-2-5 DDR400 module sells for between $81 and $94. Looking at dual-channel kits, a pair of 512MB OCZ Value DDR400 DIMMS rated for 2.5-4-4-8 timings sells for between $91 and $103 online, while a pair of 512MB Platinum Rev 2 sticks rated for 2-2-2-5 costs between $155 and $191.

OCZ isn't the only DIMM maker charging that sort of premium for ultra-low-latency modules. In fact, it's common. To cite another example, a pair of 512MB Corsair Value DDR400 DIMMs rated for 2.5-4-4-8 will set you back between $80 and $159, while a couple of the company's 512MB TWINX1024-3200XL 2-2-2-5 DDR400 modules run from $189 all the way up to $325.

For most users, the price premium associated with exotic 2-2-2-5 memory won't be worth the relatively modest performance gains that it offers. Low-latency memory does have an ace up its sleeve for overclockers, though. Most low-latency modules are capable of running at much higher clock speeds if you back off on their latencies a little. We've had our OCZ Platinum Rev 2 DIMMs, which are rated for 2-2-2-5 latencies at 400MHz, cranked all the way up to 560MHz with more relaxed 2.5-4-4-8 timings. Overclocking success is never guaranteed, of course, but low-latency memory modules tend to use higher quality chips that respond better to overclocking.

At the end of the day, the appeal of low-latency memory modules may be limited to overclockers and enthusiasts intent on squeezing every last drop of performance from a system. More pedestrian "value" memory should be plenty fast enough for everyone else, especially since you can practically afford twice as much.

source:http://techreport.com/etc/2005q4/mem-latency/index.x?pg=1




Jobs ready to sell Pixar: Report

Newspaper says animated studio head open to the right deal; receptive to offer from partner Disney.
October 31, 2005: 9:08 AM EST
The success of the Walt Disney Co. film
The success of the Walt Disney Co. film "Chicken Little" could determine whether Disney or partner Pixar has the greater leverage in upcoming talks.
Pixar has had nothing but hits since it started making films in 1995.
Pixar has had nothing but hits since it started making films in 1995.

NEW YORK (CNN/Money) - Steve Jobs, the chairman and CEO of Pixar Animation Studios, would be open to a sale of the company at the right price, according to a published report.

The New York Times reports Jobs, who owns about 50 percent of Pixar (Research), would want a strong premium to its current $5.9 billion market capitalization to consider a sale, but he would be open to an offer from its long-time partner, Walt Disney Co. (Research) The paper attributed Jobs' willingness to consider a sale to "two people with knowledge of the talks" now taking place between Disney and Pixar about possibly extending their partnership.

But the paper reports that in talks about a new version of their partnership, Disney CEO Robert Iger has yet to make an offer to acquire Pixar. The paper reports that Disney is hoping that its new animated feature, "Chicken Little," due in theaters this weekend, will give it greater leverage in talks with Pixar.

"Chicken Little" is the first offering from Disney's animation studio since it was revamped to produce computer-generated features that have a three-dimension look, rather than the traditional hand-drawn two-dimensional cartoons.

Pixar has produced only CG features and nothing but blockbusters since it started producing movies in 1995, while many of the Disney-generated animated movies during the period were considered box office flops.

The Times reports that if "Chicken Little" is a hit, it would show Wall Street and Jobs that Disney need not depend on Pixar for creation of new animated movie characters that could be adapted for theme park rides, consumer products and television.

The movie has gotten generally favorable early word, but if it is not well received by critics or moviegoers, the paper reports that Jobs will gain leverage in his talks with Disney because the media conglomerate would be seen as relying on Pixar to add new stories to its creative arsenal.

If the movie performs poorly, Bernstein & Co. media analyst Michael Nathanson told the paper, "investors might want to see a Pixar deal right behind it." Still, he added, "it's all about numbers, and both sides - Disney and Pixar - are looking for leverage."

Pixar has strong cash reserves and no longer needs Disney's to help finance films, so it is looking for a distribution agreement for a far larger percent of the box office than the 50 percent it receives under the current deal with Disney.

But while there are likely to be other studios willing to distribute Pixar films, analysts see Disney as best positioned to promote future Pixar films and its characters due to theme parks and strong merchandise sales channels.

Jobs would evaluate any Pixar partnership based on where he could get the best deal for the studio, the paper reports, not on his developing friendship with Iger. Jobs often sparred with Iger's predecessor, Michael Eisner. The Disney Channel and ABC, other units of Disney, recently signed a deal to distribute shows on the new video version of the Apple Computer (Research) iPod. Jobs is also Chairman and CEO of Apple.

The Times reports that detailed negotiations between Disney and Pixar are likely to begin in mid-November and could be wrapped up by late December or early January, said one of the paper's sources. The studios have several issues to grapple with, according to the paper, including who would have creative oversight over new Pixar characters at Disney theme parks and how revenue from rides and other attractions would be split.

source:http://money.cnn.com/2005/10/31/news/midcaps/pixar_disney/index.htm?section=money_latest


Gates: We're entering live era of software

November 02, 2005
URL: http://www.zdnet.com.au/news/software/soa/Gates_We_re_entering_live_era_of_software/0,2000061733,39220359,00.htm


Kicking off what he called the "live era" of software, Microsoft chairman Bill Gates said on Tuesday in the United States that the company plans to launch new Internet-based complements to its core products.

Gates said Microsoft is working on two products, "Windows Live" and "Office Live," that create opportunities for the company to sell online subscriptions and advertising. Both are targeted at smaller businesses and consumers.

The products won't replace the company's ubiquitous operating system or productivity suite, and people don't need to have that software loaded to tap into the Web versions. "They are not required to use Windows or Office," Gates said at a press event in San Francisco.

Gates said that Windows Live is a set of Internet-based personal services, such as e-mail, blogging and instant messaging. It will be primarily supported by advertising and be separate from the operating system itself. Office Live will come in both ad-based and subscription versions that augment the popular desktop productivity suite.

"This advertising model has emerged as a very important thing," Gates said.

But free products won't replace paid software. Many of the Live releases will have payment tiers, Gates said, with the lowest levels free and ad-supported, and higher-end versions paid for by the user.

"We'll have licenses and subscriptions as well," Gates said. In many cases, companies will have a choice between running software on their own servers or as a Live service.

Acknowledging potential antitrust concerns, Gates said that Windows Live is built off published APIs (application programming interfaces) that its rivals will also have access to.

"It's a dramatic sea change," Gates said of the overall shift to online services.

"The live phenomenon is not just about Microsoft. It's partners, it's competitors...the whole space is being transformed."

Ray Ozzie, recently tapped to head Microsoft's services push, joined Gates in detailing the plan.

Toe in the water
The Internet-based services announcement was widely expected. But Microsoft has kept details of the plan tightly under wraps.

Gates likened the services push to other major strategy shifts at Microsoft, including its December 1995 move toward the Web and a June 2000 commitment to Web services.

The idea of an online adjunct to Office and Windows is not entirely new. The company already has its Office Online Web site that gets about 55 million unique users a month and offers items such like downloadable templates.

And in years past, Microsoft has attempted to build online alternative to Office. One widely rumored project, developed in the late 1990s under the code name "Netdocs", was never made available.

One reason: Infighting between Office executives and Web advocates, according to sources at the time. David Smith, an analyst at Gartner, says that same tension still exists within Microsoft.

"There are different factions within the company, like before, and it is unclear what the corporate strategy is going to be," Smith said.

Windows comes online
Microsoft Live will consist of new services as well as some products previously offered under the MSN brand. MSN.com will continue to exist as a site for "programmed" content. Windows Live will be more personalised, the company said.

"It's easy. It's live, and it has 'me' at the center of the universe," said Blake Irving, a Microsoft vice president who was on stage to demonstrate Windows Live. However, the demo failed. "All of you guys that have done demos have been there," Irving joked.

Blake resumed his demo a few minutes later. He showed how people could use a sidebar to subscribe to RSS feeds, load podcasts and enter search queries onto a personalised Windows Live home page.

People will also be able to add non-Web items, such as a corporate SharePoint server or recently opened documents, to the Windows Live home page. Irving also presented the Windows Live Safety Center, a free tool that lets customers check on the health of their PC and scan for and remove viruses.

Also included is an AJAX-based Windows Live mail client that connects to Hotmail or other addresses. The Web client resembles Microsoft's Outlook e-mail program and can warn people about Internet fraud phishing scams.

There is also a Windows Live Messenger program that provides traditional instant messaging alongside some social networking features, such as the ability to view your circle of IM buddies. (Members have the right to say whether they want to be included in the viewable circle.)

In the demonstration, Irving showed how Windows Live Messenger offers the ability to make phone calls over the Internet, from a PC to a traditional phone.

Also for those who opt in, Microsoft has a new live business card that updates contact information online and on a PC any time that the information changes.

Some parts of the Windows Live software are in beta testing now, executives said. Others, like the new Messenger, should begin testing in December.

In the Office
The Office Live service is mostly targeted at small businesses, said Rajesh Jha, a general manager at Microsoft who presented the demo of the service. He noted that 28 million of the world's 42 million businesses are companies with fewer than 10 employees.

Jha showed how small businesses like these can use Office online to set up Web sites with custom domain names and multiple e-mail addresses--all free. Initially, these sites will not carry ads, but Microsoft sees the feature as a revenue opportunity and expects it to eventually be ad-supported.

Another tool, called "Mojo," will enable a small group of users to work collaboratively on the same document--in the case of the demonstration, an Excel spreadsheet.

"We're always on the same page," Jha said. "This real-time service is going to be free."

He also showed some of the 22 applications that are part of the subscription service, including customer management tools and secure collaboration.

Office Live will be in invitation-only beta testing in the first quarter of next year, Jha said. That beta will also be limited to the U.S., he added.

More to come
Tuesday's announcement is more of a placeholder for other initiatives to come, Smith said. "I think part of why people look at this and say it looks sketchy is because it is. But it's a step in direction that they have to go in," he said.

Smith likened the announcement to Gates' Web call to action of a decade ago. "It's the beginning of a big change at the company that will take a long a time to see manifested in mainstream products," he said.

In the meantime, the new products help Microsoft better compete with online rivals. Although the traditional software industry is very profitable and well understood, online advertising is an important opportunity, Ozzie said. He praised Google for demonstrating some of the possibilities.

"Google is doing an amazing job of making that ad engine click on all eight cylinders." Ozzie said.

But he said that the industry has barely scratched the surface, pointing out that the market for online advertising could grow from US$15 billion now to US$150 billion by 2015.

CNET News.com's Mike Ricciuti contributed to this report.




Singing Mice and Brain Chemistry

"The Public Library of Science has a research article on how male mice actually sing in the presence of females. They actually posted some of the audios adjusted for human ears as these songs are ultrasonic. The authors are comparing these warbles to bird songs. The songs are quite complex so do the mice learn them and/or improve on them? This can be a potential model for investigating how brain chemistry works during learning."

source:http://science.slashdot.org/article.pl?sid=05/11/01/2357227&tid=99&tid=14

This page is powered by Blogger. Isn't yours?