Why HPC? Weather Prediction is One of the Many Whys

16 April 2012

Inevitably, when I speak about HPC (supercomputing [petaflops and exaflops], visualization systems, Infinite Computing, etc.), I am asked the following question: Why? (i.e. Why as in why do we need so many flops?) My response always starts with “weather forecasting…” with an emphasis on forecasting such things as hurricanes and tornadoes. Accurate storm predictions can save lives.

The following is a headline from the Friday, 13 April 02012, Arizona Republic: Saturday storms ‘life threatening’.

“We’re quite sure tomorrow will be a very busy and dangerous day in terms of large swathes of central and southern plains.” — National Weather Service (NOAA.gov) via the Arizona Republic

Various news sources reported the following.

National Weather Service’s Storm Prediction Center in Norman, Okla., which specializes in tornado forecasting, took the unusual step of warning people more than 24 hours in advance of a possible “high-end, life-threatening event.”

The predictions ended up being extremely accurate: Tornadoes hit the midwest part of the United States hard on Saturday and Sunday.

The accuracy of weather forecasting is important because it can save lives. But right now the accuracy is critically important because of the need to establish trust among the populous.

Advertisements

SKA Radio Telescope I Get, But Why Megadata?

12 April 2012

DOME: IBM and ASTRON’s Exascale Computer for SKA Radio Telescope contains a picture that in turn contains the word megadata. My last posting focused on an article that used the word nanodata. I just didn’t get what nanodata meant, but I sort of understand megadata. The following is a quote from the SingularityWeblog.com posting:

The SKA is an international consortium to build the world’s largest and most sensitive radio telescope. Scientists estimate that the processing power required to operate the telescope will be equal to 100 million of today’s fastest desktop computers.

I understand the use of megadata to describe lots of data, but I would have used yottadata.

Borrowing from Pink Floyd’s “Comfortably Numb”… Is there anybody out there?


Ubiquitous Sensing I Get, But What’s Nanodata?

11 April 2012

The Computing Trend that Will Change Everything had the sub-title “Computing isn’t just getting cheaper. It’s becoming more energy efficient. That means a world populated by ubiquitous sensors and streams of nanodata.

Ubiquitous sensors imply streams of data. That I get. But what’s nanodata?

Harvesting background energy flows, including ambient light, motion, or heat, opens up the possibility of mobile sensors operating indefinitely with no external power source, and that means an explosion of available data.

An “explosion of data” implies to me yottadata (as in yottagoo). Again, what’s nanodata?

According the MIT Technology Review article, nanodata is “customized fine-grained data describing in detail the characteristics of individuals, transactions, and information flows.” To me it seems as if nanodata is a form of metadata (i.e. data about data).

I still don’t get the term nanodata, but I consider that okay. Bottom-line: It’s possible ubiquitous sensors is our future and that implies infinite data being piped into an Infinite Computing environment.


20 Petaflops Coming Soon

31 March 2012

[1 April 02012]
Three years ago, on 1 April 02009, I gave a talk titled 20 Petaflops by 02012. [Yes, I used a 5-digit year.] First quarter of 02012 has ended and as far as I know our computing world has not hit 20 petaflops, but the next TOP500 list doesn’t come out until June. Regardless, I am 99.999% confident that 20 petaflops in 02012 is going to happen primarily because of what IBM announced four months ago.

[25 November 2011]
IBM issued a press release titled IBM Announces Supercomputer to Propel Sciences Forward having the sub-title Blue Gene/Q tackles major challenges of the day, delivers up to 100 petaflops at peak performance.

“When it is fully deployed in 2012 at Lawrence Livermore National Laboratory (LLNL), the system, named ‘Sequoia’, is expected to achieve 20 petaflops at peak performance, marking it as one of the fastest supercomputers in the world.”

IBM.com::IBM Announces Supercomputer to Propel Sciences Forward

[11 November 2011]
The TOP500.org issued the following press release: Japan’s K Computer Tops 10 Petaflop/s to Stay Atop TOP500 List. Japan’s K computer was benchmarked at 10.51 petaflops.

[1 April 2009]
AzGrid::Talk::20 Petaflops in 02012

Two years earlier I gave a talk sub-titled Computing in the 21st Century. During that talk I stated the following: “The next era of computing is the era of High-Performance (Productivity) Computing (HPC).” In addition, during the talk I indicated that peta-scale computing was scheduled to occur in 02008. TOP500.org posted the following on 18 June 02008: “With the publication of the latest edition of the TOP500 list of the world’s most powerful supercomputers today (Wednesday, June 18), the global high performance computing community has officially entered a new realm–a supercomputer with a peak performance of more than 1 petaflop/s [1.026 petaflops]

[4 April 2007]
AzGrid::Talk::The Next Era of Computing


Infinite Computing Deprecates the Delete Function

26 March 2012

On 26 March 02012 I discovered that Facebook has a Usenet page, so I “Liked” it. My curiosity prompted me to do some Usenet searching and I found a net.music posting that I made almost 30 years ago on 5/8/01982. http://goo.gl/16mNL

Quoting Voltaire: “Doubt is not a pleasant condition, but certainty is absurd.”

I’m going to ignore Voltaire and say that I’m 99.999% certain that we have entered into the “era” of “Infinite Computing.” [I put quotes around “era” because to me an era has an endpoint.] To me infinite computing implies infinite storage and infinite storage deprecates the “delete” function. In other words, a bit, once posted, is never deleted. We can click the DELETE key over and over and over, but being certain that our bits have been deleted might be absurd.

About “Infinite Computing”

On 4 April 02007 I gave a talk titled The Next Era of Computing: Computing in the 21st Century. The talk included the following blurb.

The following is my one sentence description of the next era of computing: A grid-based cyber-infrastructure that provides infinite computational power, infinite storage, infinite bandwidth and infinite services (utilities).

The phrase Infinite Computing is used in the book Abundance: The Future is Better Than You Think (Copyright 02012 by Peter H. Diamandis and Steven Kotler).


Three Tweets by @compufoo

25 October 2010

On 25 October 02010, the @compufoo Twitter account had 515 tweets, 21 followers, and was following zero.

The @compufoo Twitter account was setup to support my “Computer Science For Non-CS Majors” class. I asked the students to follow @compufoo, but I did not require them to do so. More than half of the students were not Twitter users; consequently, only about half of the class started following @compufoo.

The following are the last three tweets tweeted by @compufoo prior to writing this blog posting.

[02010.10.25] Computing students should follow Dan Reed. RT @HPCDan HPC and the Excluded Middle http://bit.ly/dj0B8s

Dan Reed is a supercomputing guru. In 02006, President George W. Bush appointed Dan Reed to the President’s Council of Advisors on Science and Technology (PCAST).

[02010.10.25]“Dawn of a New Day” by Ray Ozzie http://goo.gl/ti6w via @robinwauters & @techcrunch

On 18 October 02010, Ray Ozzie — one of the creators of Lotus Notes — stepped down as Microsoft’s Chief Software Architect.

[02010.10.23]What will the Internet look like in 10 years? http://www.isoc.org/tools/blogs/scenarios/

The Internet Society (ISOC.org) is a non-profit that was founded in 01992 to “provide leadership in Internet related standards, education, and policy.”


KKK (Kapor, Kurzweil, Kay)

26 August 2010

02010.08.26: Day two of the Introduction to Computer Science class.

[Note: This posting uses 5-digit years.]

Rewind three weeks…

02010.08.03 at 2:10pm @mkapor tweeted:

I’m grouchy that so few people (except us old-timers) have even heard of Ted Nelson http://bit.ly/cGbsWC (Wikipedia bio)

Observe: Mitch Kapor hyperlinked into the Wikipedia.

02010:08.03 at 2:11pm @mkapor tweeted:

All of the web is in essence a pale shadow of just one of Ted Nelson’s dreams. Now do I have your attention?

Hmm… Who is Mitch Kapor?

2010.08.03 at 2:15pm @nanofoo in reply to @mkapor:

I’m going to make sure my CS1 students learn a bit about Ted Nelson this fall. They’ll come in knowing Gates & Jobs, but not Nelson.

@nanofoo never got reply from @mkapor, but @rossk did…

02010.08.03 at 2:48pm @rossk in reply to @mkapor:

where should the Nelson-newbie start?

02010.08.03 at 8:07pm@mkapor in reply to @rossk

Read “Computer Lib” by Nelson. Also see the Wired article on him for a dissenting view

Mitch Kapor did not provide his followers with hyperlinks, but here they are: Computer Lib/Dream Machine (dot-pdf) and Wired.com: The Curse of Xanadu


This posting uses 5-digit years and that is because I am a member of the Long Now Foundation. [Follow on Twitter @longnow.]

In 02002, Mitch Kapor made the first Long Bet (By 02029 no computer – or “machine intelligence” – will have passed the Turing Test.) with Ray Kurzweil. Hmm… Who is Ray Kurzweil? [Follow on Twitter @KurzweilAINews.]

02010.08.25 at 12:00pm @compufoo tweeted:

I agree with Ray Kurzweil that “exponential growth is the reality of information technology.” #future

I learned a lot from reading reading Ray Kurzweil’s The Singularity is Near.

In a nutshell, Kapor and Kurzweil are futurists whose last names start with the letter ‘K’. There another futurist whose last name starts with the letter ‘K’ and that is Alan Kay. In the Introduction to Computer Science we use the C++ programming language. C++ supports object oriented programming (OOP) and Alan Kay is considered one of the fathers of OOP.

Alan Kay was once quoted saying: “The best way to predict the future is to invent it.”

The following picture of the Foundation Building at Arizona State University was taken during early August of 02010.

"The best way to predict the future is to invent it." -- Alan Kay