Earlier this summer I wrote about the upcoming Power7 processor, including some of the major features. The Cliff Notes:
- Four, six, or eight cores
- Four computing threads per core, for a total capacity of 32 computing threads per chip
- DDR3 memory
- Due out by mid-2010
Well, at the HotChips conference at Stanford University last week, IBM revealed some more details for the upcoming processor. Though I wasn’t at the show, I was able to talk to Ron Kalla from IBM, who along with Bill Starke was giving a presentation at the show about the processor.
Though Kalla wouldn’t reveal what frequency the chip will run at — which is the detail IBM has been most reluctant to part with — he did say that it will be lower than Power6. This presentation given by IBM indicates Power7 will run at 4.04GHz, but the range is still unclear.
“We did go to a lower frequency to get a better power optimization point,” he said.
As a result, he said, customers running Power7-based systems will have “basically identical power consumption” to those running Power6-based servers. IBM is pushing this talking point a lot, because it wants as many Power6 users as possible to upgrade to Power7, and this could be an incentive.
This marks a clear departure with IBM’s push behind Power6, which was centered around clock speed. Back then, IBM bragged that the chips were hitting close to 5GHz in the labs. But experts at the time questioned whether cycle speed was the ultimate and only attribute of a good processor.
“The industry, Intel, was going to get away from talking about clock speeds and start talking about heavy lifting, like multi-threading,” one analyst, Charles King, said.
“Is a four-gig Power6 processor possible? I’m sure they could do it,” another analyst, Clay Ryder, added. “But I’m not sure the market is leaning toward that.”
Now, power-performance is the new metric, rather than just simple clock speed. In addition, IBM wants to push Power Systems as a good solution for Web-serving applications that can handle many users at the same time. Many cores accommodating many virtual machines may be more beneficial to that end that super-high clock speeds.
Bob Cancilla, a former executive in the Rational division of IBM, has started a new blog up in representation of his new company, Reno-based application modernization provider Oxford International. Cancilla opened up his blog with a bang, saying that the IBM i operating system and the RPG programming language are in a state of deep decline with not a lot of support within the IBM organization.
But in addition to decrying the state of the platform, Cancilla offers up possibilities for keeping it alive. You’ll never guess what he suggests. Or maybe you will. That’s right, application modernization! The exact line of business that his new company is in.
Nevertheless, Cancilla has some interesting points about the IBM i platform along with some valuable insights having been there for four years. Here are a few of his suggestions:
Before joining IBM I was CTO for a major insurance company where I ran a development organization that did major in-house development. Our project funding was totally tied to current business objectives and funded by various departments or in certain cases approved by the steering committee by special corporate funding for projects that crossed organizational lines.
What I did not have was money to fund an IT technology project. Even our Y2K work had to be tied into business objectives.
I think that many of your are like I was and have to integrate your modernization initiatives into currently funded projects. I can tell you that my management would never have funded a major conversion initiative as a standalone project. The only way to fund modernization was to show a business need or financial benefit.
Bookmark this post. No, not the one you’re reading now. This one. Why? Because it’s a link to all the pertinent documentation for IBM i, and can serve as a handy reference guide for all the IBM System i administrators out there.
Dawn May, the IBM i technical lead and business architect, has started a blog called iCan, and one of her first posts is this reference guide. It includes links to the IBM i Information Center, the systems hardware info center, Redbooks, IBM i support page, the AS/400 online library, and more. Check it out.
A new blog by IBM i Chief Architect Steve Will and IBM i Product Manager Craig Johnson has debuted on the IBM Systems Magazine website. And Will starts off with a relatively simple explanation of Single Level Store (SLS), an important part of the IBM i architecture.
Will describes it as being an attribute of the system that assigns a specific address to every piece of data — a bookmark if you will — much as if it were in memory. The benefits?
Well, one of the most important things it means is that it saves you time and money. Why? Because, in the IBM i SLS environment, the operating system manages the placement of data on storage. This is second nature to an IBM i customer but is practically unbelievable to a user who’s only familiar with other types of operating systems. Managing which disk drives are connected to the system, how full they are and what data is stored on which disks is a complex task that must be done by technical professionals. This, of course, means that technical professionals must be hired to do the job. The vast majority of customers don’t need to worry about that sort of thing for their IBM i storage.
Will added that it made adoption of solid-state drives (SSDs), which became available for Power6-based IBM i machines this April, much easier. The integrated storage management of IBM i meant the operating system “automatically recognizes an SSD, knows that it has much faster access time than traditional disks and places highly used system objects on SSD, immediately improving performance on the system.”
A new book by financial journalist Erin Arvedlund says that Bernie Madoff ran his massive Ponzi schemes using nothing other than an AS/400. The book, called “Too Good to be True: The Rise and Fall of Bernie Madoff,” is out this month.
To be fair, this isn’t the first time the possibility has been mentioned. After doing a quick search, I found that Alex Woodie at IT Jungle wrote about it months ago after Fox Business News reported on it.
Essential to the fraud was Madoff’s old clunker of a computer, an IBM AS/400 that he and select other employees could use to manipulate prices, the book says.
“Madoff and other employees on 17 punched in the stock prices on the IBM AS/400 and would just enter stock prices that would square with his fake returns,” Arvedlund says, after inexplicably telling us one page earlier that “no one touched” the computer but Madoff.
You’ll learn a lot by reading “Too Good to Be True.” One solemn message is that there are a lot of crooked rich people. Another is that there are a lot of dumb rich people, too.
My guess is that most readers of this blog would be less upset that an AS/400 was used in this scheme than the fact that the book author and reviewer referred to it as an “old clunker of a computer.” Either way, in her article, Woodie interviewed Rich Loeber, the president of Kisco Information Systems, which has Madoff associates in its marketing databases and may have sold software to Madoff. Loeber concluded that the AS/400 certainly can’t take the fall here.
“I don’t see how anyone can control how the hardware is used,” Loeber says. “Over the years, I’ve given this much thought and my final conclusion is that computers are morally neutral. How they are used is where the morals come in, and that is all controlled by people. I would not be surprised that AS/400s are used in all sorts of immoral ways, Madoff’s company just being one such example.”
My Midrange Meddle is still trying to drum up support for an iManifest-type group in Europe, the Middle East and Africa (EMEA) similar to the one that System i ISVs and resellers put together in Japan.
The idea of such a group is to get ISVs and resellers to rally around the IBM midrange platform. The iManifest in Japan currently has more than 70 System i vendors.
The slogan for the group is a take off a famous quote by John F. Kennedy, and it goes like this: “Ask not what IBM can do for you, ask what you can do for the IBM i community.” The folks at IBM, though not involved with the group, are supporting it, and even former IBMers like Frank Soltis are behind the effort.
The success of the impromptu group in Japan raised questions about whether the American System i community can get something similar off the ground. Though iSociety is still around, it hasn’t lived up to its original expectations.
Much in the way that Zend Technologies worked to get a PHP port to the System i platform, Timothy Prickett Morgan is suggesting that Ruby get a similar port.
Ruby and Rails run on Unix platforms, so it makes sense for IBM and the Ruby team to take all the learning they did to make PHP run in the PASE AIX runtime, hook into the DB2 for i database, and provide a bridge for 5250 applications to Ruby apps and apply it to Ruby and Rails. That’s easy to say, but perhaps harder to do. Ruby doesn’t seem to have a commercial champion, like PHP has in Zend.
At the end of last month, the two writers at iDevelop described their visit to Rochester, Minn., the technological home of the IBM System i platform, and a place close to the hearts of many System i enthusiasts.
There’s no doubt that many people in the System i industry have an emotional — might I even say spiritual — attraction to Rochester, and in particular its various big, blue buildings with names such as “Building 006″ and “Building 025.” Here’s an excerpt:
As big and blue as the buildings are, it’s the people at IBM in Rochester that make the trip truly worthwhile. There are great IBMers everywhere, but in Rochester there is always a feeling of being among kindred spirits like nowhere else we’ve been. Things are changing a little now that it’s all supposed to be about “Power Systems” but we suspect that many of the longtime IBMers in Rochester feel like we do–it’s really all about i.
And later, the writer talk about some of the things they might be doing off-campus:
We’ve already managed to spend some quality time with longtime friends, and the week has just begun. We have so much to look forward to–walking around Silverlake, visiting Andy’s (the local wine store), eating at John Hardy’s BBQ, watching the human foosball tournament at lunch time. … And most importantly of all, communing with many fellow fans of the greatest system a business can buy.
Tip: If you’re going to visit, go now. Better than in January when, as one commenter put it, the winds are howling and it feels like minus 70 degrees.
IBM has released a Redbook guide on the full convergence of its Power 520 and 550 servers, which now run IBM i (i5/OS), AIX and Linux. These models, announced in January 2008, came close to complete convergence that April. By last November, with the release of some system firmware, the convergence became complete.
The 644-page Redbook covers those completely converged models, starting with a broad look at the two systems and then delving into details. System i sysadmins will likely be most interested in a few System i-focused chapters: “IBM System i schematics for supported expansion units and towers,” “IBM i operating system and licensed program release level summary,” and “IBM i user license entitlement summary.”
IBM reported its second-quarter revenue for 2009 last week, and the news was mostly gloomy. The so-called “converged System p” platform decreased 13%, although believe it or not, that was the highlight of IBM’s system revenue numbers. The System z mainframe revenue tanked 39%, and the x86-based System x platform dropped 20%.
IBM isn’t the only company hit hard by these revenue figures, either. HP’s second-quarter results were similarly bad, with its servers and storage division down 28%. Dell hasn’t released its second-quarter results, but its first-quarter results saw a 29% drop in servers and networking.