Last weekend I attended the "Humanity+" conference in Melbourne
(http://hplusconf.com.au), held at RMIT. It consisted of an
eclectic mix of presentations by invited speakers, without
contributed papers or a published proceedings, though videos of the
talks will become available. The conference was under the
auspices of the Humanity+ organisation (http://humanityplus.org),
whose aim is to promote thinking about the "next steps" of
humanity. The main areas of focus appear to be biomedical and
bioengineering developments for longer and healthier life, leading
on to enhancements of the body, and artificial intelligence and
enhancements of the mind. The chair of Humanity+, Natasha
Vita-More, was one of the presenters. I went because I thought
the gerontologist Aubrey de Grey would be worth hearing, and because
the artist Stelarc was giving a presentation.
This conference was more optimistic than pessimistic. Climate
change and population pressures were there in the background, and
sustainability was a theme, but on the whole the intent was to look
beyond these problems to longer-term possible futures for
humanity. The organiser was Adam Ford, who has just become a
board member of Humanity+, and who has had a considerable
involvement in this general area.
Maybe 80 people attended, predominantly but by no means exclusively
male, and a mixture of young and old, with relatively few people in
the middle age range. I got the impression that almost everyone there
had a background in science, engineering or computing.
Aubrey de Grey was well worth hearing. His view on ageing is
that normal metabolic processes produce "damage" of various kinds,
such as junk inside cells that the body cannot dissolve. We
can tolerate a certain amount of such damage, but eventually it
starts to harm us. De Grey listed all the classes of damage
that are known (and indicated that no fundamentally new classes of
damage had come to light in the last 30 years), and indicated
plausible approaches to dealing with all of them. He mentioned
two specific projects at his laboratory dealing with junk inside the
cell, targeted at macular degeneration, which is a leading cause of
blindness, and at atherosclerosis, which is inflammation of the
walls of the arteries, heading to heart disease and strokes.
All of this comes under the heading of "regenerative medicine",
therapies to rejuvenate (that is, to make young again) systems in
the body by clearing out damage and taking the bodily systems back
some way towards the healthy young adult state. Once such
therapies are in place for all the major types of damage (which is
quite a few years away), de Grey thinks that we will be able to have
another 30 years of healthy middle age. These days 60 is the
new 50; with these therapies 80 or 90 would be the new 50. But
that is only the start. As techniques improve, clearing out a
greater proportion of damage, repeated rejuvenation would allow
enormous prolongation of healthy, active life, to ultimately maybe
1,000 years. This doesn't imply a cure for cancer, but it does
imply a method of avoiding cancer by manipulating telomeres (the
caps at the end of DNA strands).
All of this provoked a lot of discussion, and de Grey devoted his
second presentation to discussing objections to his program.
The diseases of ageing are not just a first world problem: de Grey
said that already two-thirds of the deaths in the world are due to
them. Of course if we do have the potential to live to 1,000
years there will have to be massive changes in society, but de Grey
pointed out that by the time such long life becomes feasible there
will have been massive changes in society anyway.
Incidentally de Grey is not a food faddist or anything of that
sort. He was asked about diet, and said that as long as one is
reasonably sensible about diet and exercise (and doesn't smoke),
things like the "paleo diet" and the like don't achieve much.
And he enjoyed a beer at the pub afterwards.
The other presentation that contained a road map for future
developments was that of Tim Josling on artificial
intelligence. He outlined the so-called hype cycle that tends
to apply to new technologies. Once a new technology becomes
known, at first there is a great deal of hype, resulting in wildly
inflated expectations. When the technology doesn't live up to
these, there is a "trough of disillusionment", and then after than
attitudes to the technology finally settle to a realistic view of
what it can achieve.
Artificial intelligence (AI) went through this cycle: after quite a
long initial period of hype the "AI winter" descended in the 1980s,
when funding dried up and AI was generally regarded to have
failed. In fact it developed quietly in various specialised
areas. Josling listed several techniques developed years or decades ago
that were impractical at the time but are now coming in to their own
as increased computer power has made them feasible.
Incidentally Josling is more optimistic about the continuation of
Moore's Law (that the number of transistors on a chip doubles every
two years) than Herb Sutter (whom I mentioned in a previous post),
but it doesn't matter for Josling's argument whether increased
computing power arrives via Moore's Law in one box or via
networks, as Sutter expects.
Josling expects that more and more low-level white-collar jobs will
be cheaper to do by machines, on a relatively short time frame, and
he ended by posing the question: "Leisured aristocracy or unemployed
underclass?"
This sort of prophecy was made in my youth, and hasn't really come
to pass. However, the "acceptable" minimum rate of unemployment
has risen from 2% to 5% in my lifetime, and since the official
figures are constructed to be as low as possible, the true unemployment figure is
at least 10%. I also think that the availability of cheap
Third World workers has delayed the development of automation, but
that is beginning to come to an end. Eventually the machines
will be cheaper than even a Third World worker.
In the background of Josling's presentation is a concept known as
"The Singularity", and there was a panel discussion around this at
the conference. The Singularity is when machines become
smarter than we are; this may be a long way off, but it is hard to
argue convincingly that it can never happen. The Singularity is a sort
of "event horizon", as we cannot predict what would happen after that.
As far as raw processing power is concerned, by one estimate a
current desktop machine with a good graphics card has maybe 1/2000
of the raw power of a human brain. Networks of 2000 such
machines already exist. Though one of the panellists,
Colin Hales, indicated
that recent discoveries have indicated that the brain may have far
more power than the above estimate implies.
The work up until now has been in specialised domains, for example
making driverless trucks for mining sites. There was mention
of a possible approach to general artificial intelligence being
pioneered by Marcus Hutter at the Australian National
University. Josling indicated that the promising advances in
artificial intelligence involve various forms of machine learning
(and I got the impression that this applies to Hutter's work); this
led into a discussion of risks. If a machine has learnt from
experience rather than being explicitly programmed (and this already
happens in some areas) then we don't know in detail how it does what it does. If it does something unexpected and kills or injures
someone, it is not at all clear who should be held
accountable. One of the attendees, who works as a safety
engineer (I didn't catch his name) said that once a technology such
as that for driverless trucks is mature, it is more reliable than
having human drivers; it is the early period of introduction of such
technologies that is really dangerous. In this context, the
Google Car has driven itself autonomously around Los Angeles.
One of the panellists, James Newton-Thomas, who works with
autonomous mining equipment, indicated that the current approach is
to segregate the equipment behind physical barriers, as well as fitting independent safety systems.
A discussion that was only touched on at the conference was how to
make sure that a super-intelligent machine would be friendly towards
us, and there was some discussion about the relationship among
consciousness, intelligence and morality. There was also some
discussion about the uses to which governments and large
corporations would put super-intelligent machines. The
prospect of large-scale technological unemployment and the
thought-police-like powers already available via automated
surveillance and data mining are much more immediate concerns.
(To be continued...)
Tuesday, May 8, 2012
Monday, April 30, 2012
A Personal History of Computer Hardware
Reading Herb Sutter's comments on changes in computer hardware ("The
Free Lunch Is Over", from 2004
(http://www.gotw.ca/publications/concurrency-ddj.htm), and "Welcome
to the Jungle", from 2011
(http://herbsutter.com/welcome-to-the-jungle) led me to think about the computers I have engaged
with over the years.
I had fleeting encounters with computers as a university student; this was at a time when a whole university had just a handful of computers. My first real engagement with computers was in the late 1960s when I got a summer job at a computing laboratory run by CSIRO, the Commonwealth (of Australia) Scientific and Industrial Research Organisation. The machine was a Control Data 3200, which had (I think) 32,000 24-bit words of memory. That is 96 kilobytes (though the byte wasn't in use then), less than one thousandth of the memory of any video card today, let alone the memory of a whole computer. It occupied the whole of a large room, being made of discrete transistors (not integrated circuits, i.e. "chips"). Input was by punched card, one card per line of program; you put the bundle of cards in a box, and waited some hours for the program to be run, since the computer required specialised human operators. Then you looked at the printed output, found the missing comma in your program and tried again. The machine had four magnetic tape units (one tape held about 5 megabytes), and there was a monstrous line printer. I think there was also a pen plotter, though I didn't use it. As a great privilege I got to go once or twice into the machine room and actually sit at the console and type commands.
Despite all the obvious differences, the basic architecture of both the hardware and the software was remarkably similar to that which prevailed across the whole of Sutter's "Free lunch" period, 1975-2005. There was a single processing unit, a quantity of memory (RAM), and slower but more capacious external storage, in this case provided by the magnetic tape drives. I did some programming in assembly language, and the underlying operations that the machine carried out (load, store, add, shift, jump, and so forth) are still there, though the way these operations are carried out inside the CPU has become much more complex and there are new types of operation (I don't think there were any stack manipulation instructions then, let alone vector instructions). The higher-level language was Fortran, and far as I remember the cycle of compile (separately for each "compilation unit"), link, load, run was the same as that still used today with languages like C++.
I went to England for further study, and encountered my first "departmental" computer, meaning that it belonged to the Mathematics Department, not the University as a whole. It was a PDP-8 computer, the size of a bar fridge, it had (I think) the equivalent of 8 kilobytes of memory, and the program was input via paper tape. I took a course on Lisp using this machine; it was the first interactive language I encountered, where I could change things on the fly. Around this time I visited a friend at Cambridge University and encountered for the first time the arrangement of numerous terminals connected to a single computer. By this time integrated circuits were being used, though the single-chip microprocessor didn't arrive until a little later. Also hard drives were arriving, though they were the size of washing machines or bigger.
My working life was spent in University mathematics departments, so computers were always there, though often just in the background. The system of numerous terminals connected to a single computer, probably in another building, remained dominant for quite some time. For a while the terminals were teletypes; they physically typed onto paper. The Control key on computer keyboards dates from the teletype era: it was used to control the teletype by, for example, advancing the paper a line (control-J), or ringing the bell on the teletype (control-G). The resulting non-printing "control characters" are still used in computer text files. In the 1960s a character set only held 64 characters including the control characters; there was only room for UPPER CASE letters. When character sets with 128 characters (7 bits) came into use, lower case letters became available, and computer output became much more readable.
The teletypes gave way to the ubiquitous green-screen monitors, 80 characters across and 24 or 25 lines deep. What look like descendants of these can still be seen in shop checkout counters.
At some point the mathematics typesetting program TeX arrived, and we all became amateur typesetters. Before that, mathematical typing was done by administrative staff, and it was a specialised skill, using IBM golfball typewriters. TeX allowed the production of better-looking results than any typewriter could achieve, but it wasn't easy to use, and really only people from mathematics and related disciplines took to it. It was and is open-source software and remains the standard method of producing mathematical documents.
The next big change was the spread of personal computers. The first one of these I got to use was an Apple II that belonged to a friend. I went round to his place, and he sat me down in front of the machine and then went out to do some errand. I knew that in principle I couldn't harm the computer just by pressing keys, but I was still a bit nervous (it was expensive). I touched a key, there was a loud bang, and the computer stopped working. The machine was full of plug-in cards, and it turned out that a sharp protrusion on one card had managed to eat its way into a capacitor on a neighbouring card, resulting in a destructive short circuit.
The first computer that I owned myself (1985) was a Commodore 64; the name indicated that it had 64 kilobytes of memory in its small plastic box, that is two thirds of the memory of the room-filling machine of the late 1960s. It also had an inbuilt sound synthesiser chip, and it was the only computer I have ever used that had a genuine random number generator. Usually there is a pseudo-random number generator, a small program that generates a determinate sequence of numbers once the starting point is set, but the Commodore 64 could read the analogue noise generator circuit in the sound chip, which gave genuine physically-based random numbers. The Commodore was much cheaper than the Apple, but it didn't have a floppy disk drive, only a very slow unit that stored data on audio cassettes. It has been said that the Commodore 64 was the last computer that one person could understand all of; it even came with a circuit diagram.
These home computers had some of the attributes of a video game console and certainly helped the evolution of computers into multi-media machines.
In 1989 the Internet proper arrived in Australia with a satellite link from Australia to the mainland U.S. via Hawaii, and the establishment of what was called AARNET by a consortium of Australian universities and the CSIRO. Previously there had been more local Australian networks, with international email available, though not easy to use. A lot of the network developments happened in University computer science departments, with mathematics, physics and engineering departments not far behind. General use outside Universities didn't start in Australia until about 1993.
At home I bought an Atari, also in 1989; I was getting involved in electronic music, and the Atari was well adapted for that. Meantime at work workstations had arrived, desktop computers in their own right, with much better displays than the old terminals, and networked together. A little later I got a Sun desktop computer at work. It had 4 megabytes of memory (I think), but by default it only had an 80 megabyte hard drive. This was nowhere near enough, and I got an additional 600 megabyte disk drive, which cost over $2000. Twenty years later, a drive with 1,000 times the capacity costs around one twentieth of the price, not allowing for inflation. I don't think anyone foresaw this extraordinary increase in hard drive capacity.
The Sun workstation had an additional piece of hardware that could be used as a sound card, though it was actually a general scientific data collector. It contained a so-called DSP (Digital Signal Processor) chip, that for certain purposes was much faster than the main processor. DSP chips are still used in specialised applications, including sound cards.
After that the World Wide Web appeared, via the Mosaic browser. The IBM PC and clones gradually become dominant; at work they were connected to a central server, and were more likely to run Linux than Windows. I also used a PC at home; I changed to the Macintosh in 2006.
A computing-related development that came at work shortly before I retired was the establishment of an "access grid room", essentially a well-equipped and well-connected video conferencing room allowing the sharing of specialised mathematics courses between universities. Another development late in my working life, and one related to Sutter's comments, was the building of super-computer class machines by hooking together a network of 100 or more PCs. Smaller versions of these clusters were within the reach of individual University departments or research centres. I didn't have an excuse to seek access to them.
The electronic computer was born a little before I was, but stored program machines did not arrive until after I was born, the earliest electronic computers not being stored-program. The transistor was also born shortly after I was, so the twin revolutions of computing as we know it and of micro-electronics have taken place in my lifetime.
I had fleeting encounters with computers as a university student; this was at a time when a whole university had just a handful of computers. My first real engagement with computers was in the late 1960s when I got a summer job at a computing laboratory run by CSIRO, the Commonwealth (of Australia) Scientific and Industrial Research Organisation. The machine was a Control Data 3200, which had (I think) 32,000 24-bit words of memory. That is 96 kilobytes (though the byte wasn't in use then), less than one thousandth of the memory of any video card today, let alone the memory of a whole computer. It occupied the whole of a large room, being made of discrete transistors (not integrated circuits, i.e. "chips"). Input was by punched card, one card per line of program; you put the bundle of cards in a box, and waited some hours for the program to be run, since the computer required specialised human operators. Then you looked at the printed output, found the missing comma in your program and tried again. The machine had four magnetic tape units (one tape held about 5 megabytes), and there was a monstrous line printer. I think there was also a pen plotter, though I didn't use it. As a great privilege I got to go once or twice into the machine room and actually sit at the console and type commands.
Despite all the obvious differences, the basic architecture of both the hardware and the software was remarkably similar to that which prevailed across the whole of Sutter's "Free lunch" period, 1975-2005. There was a single processing unit, a quantity of memory (RAM), and slower but more capacious external storage, in this case provided by the magnetic tape drives. I did some programming in assembly language, and the underlying operations that the machine carried out (load, store, add, shift, jump, and so forth) are still there, though the way these operations are carried out inside the CPU has become much more complex and there are new types of operation (I don't think there were any stack manipulation instructions then, let alone vector instructions). The higher-level language was Fortran, and far as I remember the cycle of compile (separately for each "compilation unit"), link, load, run was the same as that still used today with languages like C++.
I went to England for further study, and encountered my first "departmental" computer, meaning that it belonged to the Mathematics Department, not the University as a whole. It was a PDP-8 computer, the size of a bar fridge, it had (I think) the equivalent of 8 kilobytes of memory, and the program was input via paper tape. I took a course on Lisp using this machine; it was the first interactive language I encountered, where I could change things on the fly. Around this time I visited a friend at Cambridge University and encountered for the first time the arrangement of numerous terminals connected to a single computer. By this time integrated circuits were being used, though the single-chip microprocessor didn't arrive until a little later. Also hard drives were arriving, though they were the size of washing machines or bigger.
My working life was spent in University mathematics departments, so computers were always there, though often just in the background. The system of numerous terminals connected to a single computer, probably in another building, remained dominant for quite some time. For a while the terminals were teletypes; they physically typed onto paper. The Control key on computer keyboards dates from the teletype era: it was used to control the teletype by, for example, advancing the paper a line (control-J), or ringing the bell on the teletype (control-G). The resulting non-printing "control characters" are still used in computer text files. In the 1960s a character set only held 64 characters including the control characters; there was only room for UPPER CASE letters. When character sets with 128 characters (7 bits) came into use, lower case letters became available, and computer output became much more readable.
The teletypes gave way to the ubiquitous green-screen monitors, 80 characters across and 24 or 25 lines deep. What look like descendants of these can still be seen in shop checkout counters.
At some point the mathematics typesetting program TeX arrived, and we all became amateur typesetters. Before that, mathematical typing was done by administrative staff, and it was a specialised skill, using IBM golfball typewriters. TeX allowed the production of better-looking results than any typewriter could achieve, but it wasn't easy to use, and really only people from mathematics and related disciplines took to it. It was and is open-source software and remains the standard method of producing mathematical documents.
The next big change was the spread of personal computers. The first one of these I got to use was an Apple II that belonged to a friend. I went round to his place, and he sat me down in front of the machine and then went out to do some errand. I knew that in principle I couldn't harm the computer just by pressing keys, but I was still a bit nervous (it was expensive). I touched a key, there was a loud bang, and the computer stopped working. The machine was full of plug-in cards, and it turned out that a sharp protrusion on one card had managed to eat its way into a capacitor on a neighbouring card, resulting in a destructive short circuit.
The first computer that I owned myself (1985) was a Commodore 64; the name indicated that it had 64 kilobytes of memory in its small plastic box, that is two thirds of the memory of the room-filling machine of the late 1960s. It also had an inbuilt sound synthesiser chip, and it was the only computer I have ever used that had a genuine random number generator. Usually there is a pseudo-random number generator, a small program that generates a determinate sequence of numbers once the starting point is set, but the Commodore 64 could read the analogue noise generator circuit in the sound chip, which gave genuine physically-based random numbers. The Commodore was much cheaper than the Apple, but it didn't have a floppy disk drive, only a very slow unit that stored data on audio cassettes. It has been said that the Commodore 64 was the last computer that one person could understand all of; it even came with a circuit diagram.
These home computers had some of the attributes of a video game console and certainly helped the evolution of computers into multi-media machines.
In 1989 the Internet proper arrived in Australia with a satellite link from Australia to the mainland U.S. via Hawaii, and the establishment of what was called AARNET by a consortium of Australian universities and the CSIRO. Previously there had been more local Australian networks, with international email available, though not easy to use. A lot of the network developments happened in University computer science departments, with mathematics, physics and engineering departments not far behind. General use outside Universities didn't start in Australia until about 1993.
At home I bought an Atari, also in 1989; I was getting involved in electronic music, and the Atari was well adapted for that. Meantime at work workstations had arrived, desktop computers in their own right, with much better displays than the old terminals, and networked together. A little later I got a Sun desktop computer at work. It had 4 megabytes of memory (I think), but by default it only had an 80 megabyte hard drive. This was nowhere near enough, and I got an additional 600 megabyte disk drive, which cost over $2000. Twenty years later, a drive with 1,000 times the capacity costs around one twentieth of the price, not allowing for inflation. I don't think anyone foresaw this extraordinary increase in hard drive capacity.
The Sun workstation had an additional piece of hardware that could be used as a sound card, though it was actually a general scientific data collector. It contained a so-called DSP (Digital Signal Processor) chip, that for certain purposes was much faster than the main processor. DSP chips are still used in specialised applications, including sound cards.
After that the World Wide Web appeared, via the Mosaic browser. The IBM PC and clones gradually become dominant; at work they were connected to a central server, and were more likely to run Linux than Windows. I also used a PC at home; I changed to the Macintosh in 2006.
A computing-related development that came at work shortly before I retired was the establishment of an "access grid room", essentially a well-equipped and well-connected video conferencing room allowing the sharing of specialised mathematics courses between universities. Another development late in my working life, and one related to Sutter's comments, was the building of super-computer class machines by hooking together a network of 100 or more PCs. Smaller versions of these clusters were within the reach of individual University departments or research centres. I didn't have an excuse to seek access to them.
The electronic computer was born a little before I was, but stored program machines did not arrive until after I was born, the earliest electronic computers not being stored-program. The transistor was also born shortly after I was, so the twin revolutions of computing as we know it and of micro-electronics have taken place in my lifetime.
Thursday, April 19, 2012
There Is No Free Lunch in the Jungle
I have not normally been posting
on technical topics, and I am not a professional programmer. But I do spend a fair bit of time writing programs for artistic purposes. Professional programmers
won't find anything of technical interest.
Recently I came across two articles by Herb Sutter, entitled "The Free Lunch Is Over", from 2004 (http://www.gotw.ca/publications/concurrency-ddj.htm), and "Welcome to the Jungle", from 2011 (http://herbsutter.com/welcome-to-the-jungle). Together they chart fundamental changes in the way that computer hardware is organised, and the effect that this is having on computer programs and computer programmers. Sutter is a programming guru who works for Microsoft, and he is particularly interested in changes to programming techniques.
In "The Free Lunch Is Over", Sutter presciently pointed out that the era of ever faster and more powerful computer processors is ending. The free lunch was the continual increase in computer processor speeds, sustained over a very long period (Sutter says roughly 1975 to 2005, but 1975 is an approximate starting date for desktop computers; for bigger computers it surely extends further back). This meant that software developers didn't have to worry too much about inefficient software; it might be a bit slow today, but tomorrow's machines will run it fast enough. Sutter's article, which first appeared in 2004, pointed out that processor clock speed had started to level out. Since then, there has been almost no increase in clock speed, which has stagnated at something under 4 gigahertz; the obstacle is the amount of heat generated in the small space of the chip. Sutter's first era is the era of the free lunch of ever-increasing processor speeds
It is still possible to pack ever more transistors into a chip, so since 2005 there has been a proliferation of multi-core chips, where each "core" is equivalent to the whole processor of an earlier machine. Today typical desk-top machines have four cores, and even phones and tablets are beginning to have two cores. Different programs can run at the same time on different cores, but to really make use of the cores a single program has to utilise several cores simultaneously. This requires a big change on the part of programmers, who need to acquire new tools and a new mindset. Various approaches to what is variously called parallel programming, concurrency or multi-threading have been around for a long time, but now they suddenly become central. Sutter's second era is "multi-core", that of machines with a relatively small number of powerful cores. The first article takes us to this point.
In the second article, Sutter considers that the "multi-core" era is already ending even before we have learnt to cope with it. The third era is that of "hetero-core", the era of heterogeneous cores, which according to Sutter started in 2011. As far as the actual hardware is concerned, the third era arrived when powerful graphics cards started to be fitted to home computers for computer games. These graphics cards contain a large number (for example 100) of very small specialised cores, originally only capable of processing pixels for display. These small cores have gradually become more general-purpose, and there has been considerable interest in scientific computing circles in harnessing their power for general-purpose computation, not just graphics. This interest is now going mainstream, but it brings with yet more challenges for programmers, as now, added to the already difficult challenge of adapting a program to make use of multiple cores, different parts of the one program may be running on cores with very different capabilities.
Sutter has the "hetero-core" era ending some time in the 2020s because he thinks that is when Moore's Law (that the number of transistors on a chip doubles every two years) will finally end. At that point our desktop and laptop and pocket computing devices will have as much power as they are going to get. Sutter thinks by then another trend will have already taken over, the availability of "hardware as a service": enormous clusters of computers available to be used over the Internet by anyone, for a fee. This provides still another challenge for programmers: a program will run partly on the by then 1,000 or more heterogeneous cores in the user's local machine (desktop, laptop, tablet or phone), and partly on a much bigger collection of cores available at the other end of a wi-fi link. Sutter considers that building larger and larger networks of computers will be, for the foreseeable future, much easier than cramming more and more transistors into a single chip or box, so growth in computing power will take place less in individual machines and more in the availability of networks of computers. As Sutter points out, already Amazon and others offer large clusters of computers for hire; he gives the example of a cluster with 30,000 virtual cores that was (virtually) put together for a pharmaceutical company who hired it for one day, at a cost of under $1500 per hour. The calculations would have taken years on a desktop computer.
Interesting times!
Recently I came across two articles by Herb Sutter, entitled "The Free Lunch Is Over", from 2004 (http://www.gotw.ca/publications/concurrency-ddj.htm), and "Welcome to the Jungle", from 2011 (http://herbsutter.com/welcome-to-the-jungle). Together they chart fundamental changes in the way that computer hardware is organised, and the effect that this is having on computer programs and computer programmers. Sutter is a programming guru who works for Microsoft, and he is particularly interested in changes to programming techniques.
In "The Free Lunch Is Over", Sutter presciently pointed out that the era of ever faster and more powerful computer processors is ending. The free lunch was the continual increase in computer processor speeds, sustained over a very long period (Sutter says roughly 1975 to 2005, but 1975 is an approximate starting date for desktop computers; for bigger computers it surely extends further back). This meant that software developers didn't have to worry too much about inefficient software; it might be a bit slow today, but tomorrow's machines will run it fast enough. Sutter's article, which first appeared in 2004, pointed out that processor clock speed had started to level out. Since then, there has been almost no increase in clock speed, which has stagnated at something under 4 gigahertz; the obstacle is the amount of heat generated in the small space of the chip. Sutter's first era is the era of the free lunch of ever-increasing processor speeds
It is still possible to pack ever more transistors into a chip, so since 2005 there has been a proliferation of multi-core chips, where each "core" is equivalent to the whole processor of an earlier machine. Today typical desk-top machines have four cores, and even phones and tablets are beginning to have two cores. Different programs can run at the same time on different cores, but to really make use of the cores a single program has to utilise several cores simultaneously. This requires a big change on the part of programmers, who need to acquire new tools and a new mindset. Various approaches to what is variously called parallel programming, concurrency or multi-threading have been around for a long time, but now they suddenly become central. Sutter's second era is "multi-core", that of machines with a relatively small number of powerful cores. The first article takes us to this point.
In the second article, Sutter considers that the "multi-core" era is already ending even before we have learnt to cope with it. The third era is that of "hetero-core", the era of heterogeneous cores, which according to Sutter started in 2011. As far as the actual hardware is concerned, the third era arrived when powerful graphics cards started to be fitted to home computers for computer games. These graphics cards contain a large number (for example 100) of very small specialised cores, originally only capable of processing pixels for display. These small cores have gradually become more general-purpose, and there has been considerable interest in scientific computing circles in harnessing their power for general-purpose computation, not just graphics. This interest is now going mainstream, but it brings with yet more challenges for programmers, as now, added to the already difficult challenge of adapting a program to make use of multiple cores, different parts of the one program may be running on cores with very different capabilities.
Sutter has the "hetero-core" era ending some time in the 2020s because he thinks that is when Moore's Law (that the number of transistors on a chip doubles every two years) will finally end. At that point our desktop and laptop and pocket computing devices will have as much power as they are going to get. Sutter thinks by then another trend will have already taken over, the availability of "hardware as a service": enormous clusters of computers available to be used over the Internet by anyone, for a fee. This provides still another challenge for programmers: a program will run partly on the by then 1,000 or more heterogeneous cores in the user's local machine (desktop, laptop, tablet or phone), and partly on a much bigger collection of cores available at the other end of a wi-fi link. Sutter considers that building larger and larger networks of computers will be, for the foreseeable future, much easier than cramming more and more transistors into a single chip or box, so growth in computing power will take place less in individual machines and more in the availability of networks of computers. As Sutter points out, already Amazon and others offer large clusters of computers for hire; he gives the example of a cluster with 30,000 virtual cores that was (virtually) put together for a pharmaceutical company who hired it for one day, at a cost of under $1500 per hour. The calculations would have taken years on a desktop computer.
Interesting times!
Thursday, February 2, 2012
Red Brick Group Show, Ballarat
The Red Brick Gallery and Emporium in Ballarat is holding a group show, with lots of people involved. I have put in two prints from my Shaping Evolution series. The Gallery is run by two energetic artists, Steph Wallace and Marcia King, and has shown a lot of work by local artists/craftspeople.
Where: Red Brick Gallery, 218A Skipton St, Ballarat VIC 3350. (Near the corner with South St.)
Tel: 0402 416 097.
Opening: Friday February 3rd, 6.00-8.00pm.
Exhibition dates: February 3rd – February 16th, 2012.
Gallery hours: Tues – Sun, 10am – 5pm.
Info: www.http://redbrickgallery.com.au/.
Where: Red Brick Gallery, 218A Skipton St, Ballarat VIC 3350. (Near the corner with South St.)
Tel: 0402 416 097.
Opening: Friday February 3rd, 6.00-8.00pm.
Exhibition dates: February 3rd – February 16th, 2012.
Gallery hours: Tues – Sun, 10am – 5pm.
Info: www.http://redbrickgallery.com.au/.
Thursday, January 26, 2012
"Art Sparks" Creative Gathering, Ballarat
This is an initiative by Amy Tsilemanis to bring together people interested in the arts in Ballarat. The next gathering is on Tuesday 31st of January at Linda Franklin's South Street Art Studio.There will be a vegetarian feast, and then five artists, including me, will be performing or showing work. They range over music, storytelling and visual art; I will play a couple of my abstract videos. A good chance to meet and talk with people. The five featured artists are Al Wunder, Yasmin Cole, Gordon Monro, Anne Langdon and Janette Wotherspoon.
Where: South Street Art Studio, 410 South Street, Ballarat VIC 3350. (This is the old church on the corner with Errard St.)
Tel: 0438 826 500.
When: Tuesday 31st of January 201, 6.30 - 9.30pm.
Cost: Suggested: gold coin donation.
Info: On Facebook - search for "Art Sparks in Ballarat" and "South Street Art Studio".
Where: South Street Art Studio, 410 South Street, Ballarat VIC 3350. (This is the old church on the corner with Errard St.)
Tel: 0438 826 500.
When: Tuesday 31st of January 201, 6.30 - 9.30pm.
Cost: Suggested: gold coin donation.
Info: On Facebook - search for "Art Sparks in Ballarat" and "South Street Art Studio".
Subscribe to:
Posts (Atom)
