Multicore processors – they’re “becoming the norm” in such things as smartphones and data centers, since, among other reasons, “extra processing power is good news for developers.”

That’s according to industry observer Tim Kridel, who notes that yes, like with so much else in this world, “there’s a catch: The real-world performance gains are often held back by old ways of thinking about coding, a caveat summed up in the oft-overlooked Amdahl’s Law.”

Okay, we’ve given you enough time: Remember Amdahl’s Law yet? No, that’s Moore’s Law you’re thinking of. And let’s not even mention Murphy’s Law. We’ll give you a bit more time.

Kridel recently spoke with University of Wisconsin Professor Mark Hill on Amdahl’s Law, how it affects multicore performance, why parallelism is key to unlocking multicore’s benefits and why the computing world could use a new Moore’s Law.

Hill told of an encounter he had with IBM (News - Alert) researcher Thomas Puzak, who said that “everybody knows Amdahl’s Law but quickly forgets it,” according to Kridel, and how “harsh” it is: “If you’re 99 percent parallel and 1 percent serial, and you have 256 cores, how much faster do you think you can go? You’d think you get a speed-up of maybe 250 out of 256. The answer is a speed-up of 72. That 1 percent has already cost you that much.”

Hence, as Kridel said, Hill called for “a growing need for dramatic increases in parallelism,” since “you’re going to take old software and get dramatic parallelism because it’s going to get that sequential component down.”

Obviously there are challenges to developers when writing parallel-centric software, Kridel said, noting that a change in mindset is a factor as well. “It’s a pretty huge hurdle,” Hill agreed, saying that yeah, there have been people writing parallel software in niche domains such as supercomputers, “but most developers don’t have experience with it. If you think of software as a numerical recipe -- you do this, you do that -- parallel computing is like a bunch of numerical recipes operating at the same time. That can be conceptually a lot more difficult.”

But the need doesn’t change. As Kridel says, “enterprises want data centers that aren’t electricity hogs, and smartphones that can last an entire workday before they need a charge.” Hill agrees that this means there will be “a lot more pressure for the code to be more efficient.”

In 2009 TMC had the news of the release of an IDC (News - Alert) report titled “The Diminishing Returns of Moore's Law: Multicore Is Not the Panacea for Increasing Performance It Should Be,” which looked at the proliferation of multicore processors and the effect they have on software performance.

“Forget scalable computing, the explosion of logical processors could lead to scalable computers,” said Brett Waldman, research analyst, Enterprise Virtualization Software at the time. “The lack of application development tools to efficiently program applications for parallel execution will drive the demand for greater virtualization management tools to solve the underutilization problem of multicore servers that is right around the corner.”