Gadget and Gizmo

Adding more processing cores has emerged as the primary way of boosting performance of server and PC chips, but the benefits will be greatly diminished if the industry can't overcome certain hardware and programming challenges, participants at the Multicore Expo in Santa Clara, California, said this week.

Most software today is still written for single-core chips and will need to be rewritten or updated to take advantage of the increasing number of cores that Intel, Sun Microsystems and other chip makers are adding to their products, said Linley Gwennap, president and principal analyst at The Linley Group.

[ Related: Intel wants developers to think parallel | Keep up with app dev issues and trends with InfoWorld's Fatal Exception and Strategic Developer blogs. ]

Off-the-shelf applications will often run faster on CPUs with up to four processor cores, but beyond that performance levels off and may even deteriorate as more cores are added, he said. A recent report from Gartner also highlighted the problem.

Chip makers and system builders have begun efforts to educate developers and provide them with better tools for multicore programming. A year ago, Intel and Microsoft said they would invest million to open two research centers at U.S. universities devoted to tackling the problem. The lack of multicore programming tools for mainstream developers is perhaps the biggest challenge the industry faces today, Gwennap said.

Writing applications in a way that lets different parts of a computing task, such as solving a math problem or rendering an image, be divided up and executed simultaneously across multiple cores is not new. But this model, often called parallel computing, has been limited so far mainly to specialized, high-performance computing environments.

But in recent years, Intel and AMD have been adding cores as a more power-efficient way to boost chip performance, a marked change from their traditional practice of increasing clock speed. Intel is building eight cores into its upcoming Nehalem-EX chips, and AMD is designing 12-core chips for servers. They are also adding multi-threading capabilities, which allow each of the cores to work on multiple lines of code at the same time.

That means mainstream applications have to be written in a different way to take advantage of the additional cores available. The work is hard to do and creates the potential for new types for software bugs. One of the most common is "race conditions," where the output of a calculation depends on the various elements of a task being completed in a certain order. If they are not, errors can result.

A few parallel programming tools are available, such as Intel's Parallel Studio for C and C++. Other vendors in the space are Codeplay, Polycore Software and Clik Arts. There is also a new C-based parallel programming model called OpenCL, being developed by The Khronos Group and backed by Apple, Intel, AMD, Nvidia and others.

But many of the tools available are still works in progress, participants at the Multicore Expo said. Software compilers need to be able to identify code that can be parallelized, and then do the job of parallelizing it without manual intervention from programmers, said Shay Gal-on, director of software engineering at EEMBC, a nonprofit organization that develops benchmarks for embedded chips.

Despite the lack of tools, some software vendors have found it relatively easy to create parallel code for simple computing jobs, like image and video processing, Gwennapp said. Adobe has rewritten Photoshop in a way that can assign duties like magnification and image filtering to specific x86 cores, improving performance by three to four times, he said.

"If you are doing video or graphics, you can take different sets of pixels and assign them to different CPUs. You can get a lot of parallelism that way," he said. But for more complex tasks, it is difficult to find a single approach for identifying a sequence of computations that can be parallelized and then dividing them up.

While the programming side may present the biggest challenge, there are also hardware changes that need to be made, to overcome issues such as memory latency and slow bus speeds. "As you add more and more CPUs on the chip, you need the memory bandwidth to back it up," Gwennap said.

Sharing a single memory cache or data bus among multiple cores can create a bottleneck, meaning the extra cores will be largely wasted. "By the time you get to six or eight CPUs, they spend all their time talking to each other and not moving forward to getting any work done," he said.

The onus may ultimately lie with developers to bridge the gap between hardware and software to write better parallel programs. Many coders are not up to speed on the latest developments in hardware design, Gal-on said. They should open up data sheets and study chip architectures to understand how their code can perform better, he said.

Datacenter construction requires a massive investment in time and cash before a facility is completed.

It's no wonder, then, that companies who have embarked on building a new datacenter have not halted their projects. In interviews with more than a dozen companies, each with 0 million in IT investments, Joseph Pucciarelli, program director of technology financing and executive strategies for market researcher IDC (a sister brand of CIO and InfoWorld), found that not one planned on scaling back their projects.

[ Find out how the economic downturn is affecting the IT industry in InfoWorld's special report. | Keep up on the latest tech news headlines at InfoWorld News, or subscribe to the Today's Headlines newsletter. ]

"You are talking projects that have been in the works for years," Pucciarelli says. "These are complex multicycle construction efforts."

Yet, the future is a different matter, he says. Economic uncertainty has caused many companies to review plans to expand IT infrastructure. In the past six month, new orders for datacenter construction have essentially halted, Pucciarelli says. "Everyone is waiting to see in which direction this period of economic volatility is going to pan out."

Datacenters typically require three years or more to finish and cost tens of millions to hundreds of millions of dollars. Just planning a project can take from two to four years, the analyst says. One of the 14 companies he interviewed in February has embarked on a 0 million ERP project, which the firm aims to continue.

"They're doing it because they are going to get all the cost benefits of a new IT infrastructure," he says.

Tata Communications is another company that plans to continue building datacenters. The communications and managed service provider processes around 7 billion voice minutes a year and has datacenters in the United States, the United Kingdom, Singapore, and India, its home country. It's planning to construct new facilities in South Africa and China, says Abid Qadiri, vice president of datacenter services for the company.

The economic downturn has caused many companies to focus on cutting the costs of managing their data, making outsourcing attractive, he says.

"The current environment, looking at it from the cost perspective, has actually increased the incentive to outsource datacenters," Qadiri says. "Companies are asking questions that they might not have normally asked. Such as, 'Are datacenters our business?'"

Tata Communications currently has datacenter facilities taking up almost 1 million square feet of space, and plans to invest more than billion to expand their capabilities to serve customers' data requirements.

The trend toward outsourcing is unclear, says IDC's Pucciarelli. While CIOs are tasked with maintaining the same level of IT service at a reduced overhead, many CFOs are less than enamored of outsourcing as the solution. Their three top concerns are continuity, security, and value, and not all are adequately addressed by outsourcing, the analyst says.

In 2008, for example, more than half of companies interviewed in a recent IBM report had suffered an outage due to operational or power issues. Long outages dramatically affect businesses and is a major fear of people considering outsourcing, Pucciarelli says.

"When you interview a person who has had a datacenter issue, where it went down for days, it is an emotionally scarring issue," he says.

Outsourcing is not the only solution. As companies consolidate during the economic downturn, they will typically merge data center operations into their newest facilities, Pucciarelli says. Over the next few years, the analyst expects many facilities to be put up for sale.

CIO.com is an InfoWorld affiliate.