He has joined the choir invisible
He has gone to meet his maker
It is an ex-donkey
2721 posts • joined 24 Apr 2007
He has joined the choir invisible
He has gone to meet his maker
It is an ex-donkey
was my immediate thought.
Terry Pratchett, you are a wise man, and clearly we all live on the discworld/
you will imagine to hear it say
"More powerrr, we need more powerrrr!"
Not the frothy kind! Distill the stuff I say. A glass of single malt to my fond memories of Scotty saying
Ye cannae break the laws of physics capt'n!
I will wait to see the scientific paper on this. A problem with these tests is that it mixes hardware and software performance measurement. Gaining speed by increasing communication bandwidth (and decreasing latency, for preference) just get the "duh" response it deserves.
The only ways to see if two algorithms differ is to (i) do a proper complexity analysis (computing time and memory/bandwidth use) to see how it should scale theoretically (both in terms of data size and number of processors), and (ii) time optimized versions on the same hardware (or different sets of hardware), using a variable number of processors or nodes.
Oh really. I do not need spectacular visual effects on my desktop, unless I am playing a computer game, or running scientific visualization software. My OS should not try to dazzle me, I need to get work done. The best OS is the one you hardly notice. This may involve smart use of visual effects. Some visual effects I find useful (compiz-fusion has some things I find very handy, in particular in the area of switching desktops and looking for the right open app), but most are just battery-draining eye candy. It is telling that the spectacular visual effects are mentioned before the streamlined navigation (which is useful). I want substance, not bling.
I agree up to a point. Languages do need to change, and they are in fact changing. OpemMP is a sort of "bolt-on" solution for C(++) which allows the compiler to treat for loops as for-all statements, and provides various other mechanisms for syncing. A functional approach such as in Erlang is often proposed. I do have some doubts that we can solve all sorts of problems merely with new languages. We need to learn new ways of thinking about these problems. A good language can inspire new ways of thinking, of course.
I have to disagree a bit here. Parallel computing is great, but at the same time it is hard work, and it is only useful in particular, data and compute intensive tasks. Memory access bottlenecks have been reduced greatly by getting rid of the front-side bus (guess why Opterons are so popular in HPC), but they are still very much present in GPUs, in particular in communication between GPU and main memory. There are improvements in tooling, but they are too often over-hyped. Besides, as with all optimization, you need understanding of the hardware.
Parallel computing is at the forefront of computer science research, and new (wait-free) algorithms are being published in scientific journals, as are improvements in compilers, languages and other tools.
Throughout its early history, physics simulation with its emphasis on matrix-vector work dominated the HPC field. Now a much larger variety of code is being parallelized. People are finding out the hard way that parallel algorithm design is a lot harder than sequential programming.
As I like to tell my students: parallel computing provides much faster ways of making your program crash.
Let me guess, they can easily parallelize adding two arrays together, or doing matrix vector stuff optimally. This covers some very important bases, but some parallel code needs to be rethought rather than just recompiled when porting to a very different architecture.
We have code which does not use matrix-vector stuff, and works best (40x speed up on 64 cores) on fairly coarse grained, shared memory, parallel architectures. We still have not managed to make a distributed memory version (working on it), and are struggling with an OpenCL version for GPUs (working on it with GPU gurus).
Every time I have heard people claim to have tools that take all the hard work out of parallel programming, they show me examples like "add these 10^9 numbers to another bunch of 10^9 numbers". These tools can indeed take a lot of the hard work out of parallel computing, but not all, by quite a long way.
I thought the Unseen University had prior art on that. Go ahead Apple, sue UU, they have a pond full of people who tried to sue them.
Doffs hat to TP
Wasn't stage five "Light fuse"
or for a more emotional (i.e., high blood-pressure) pitch, Steve Balmer
Not sure about that. quite a few people (myself included) drop the default browser in Android for something with more functionality. My HTC Desire's default browser had no tabs, I tried firefox on Android briefly but was not impressed, and run Dolphin now. There may be better browsers out there for Android, but I rather like Dolphin, so won't change now.
They just made a few extra to hit this number
Few people can say their knitwear was used by NASA, someone give her medal!
I can essentially live with the so-so resolution, I cannot do without an nVidia GPU to run many of our CUDA programs. A fairly portable 14" with a pretty nifty CUDA punch goes a long way to ticking all the boxes for my work.
Did he have to stun them in order to get them to attend?
Sorry, couldn't resist
"Apple will also take heart from the fact that, as of yet, there are no reports of Windows Phone fanatics in China offering to exchange organs, or even their virginity, for a handset."
This could mean people are less enthusiastic for Windows Phone, it could mean the Windows phones are sufficiently cheap to be affordable without such extreme measures, or it could mean a certain proportion of the populace needs their brain seen to (or a combination of the three).
For those in need of having their brain seen to, I hear prof Gumby is a very well-known brain specialist (or was that bwain specialist?)
Wasn't that what the computer really said?
"Please be careful with it Bond!"
I bet Simon Travaglia would like these. Paint the green button red and vice versa.
I have heard of this mythical beast, apparently hailing from Bonnie Scotland as well, but, much the cardiologist's delight, never encountered it in the wild. Should this not be researched?
Physicists (and not just physicists) always want more compute power than currently available.
Being rich guys who cannot renounce citizenship without losing their jobs.
Tribute to the Goodies? Like a trandem (three-seater bike) as replacement for the three-man Soyuz capsule
A few bottles of Château de Chasselas from the four Yorkshiremen? To wash down the spam?
You could go further back.
could I build a Kim cluster? Might even catch up with a 80486 if you put together a few hundred.
Interesting developments, in particular the having multiple MPI tasks able to run simultaneously on a single Kepler chip. Great added flexibility.
I understand the why, it is just of no use to me. Others will probably be very happy with the machines
I will aim at a much cheaper, only slightly heavier 13.3" or 14" notebook with nVidia 520 or 540 graphics so I can run CUDA and openCL stuff (there are a few very nice ones from Asus, Samsung, and even Dell). The whole idea of an ultrabook is hobbled by the insistence on Intel graphics. For the prices they are asking they could put in a decent graphics chipset. Until Intel supports CUDA (i.e. when hell freezes over) I will steer clear of any machine with only Intel graphics.
Now there is an excuse for a HUGE monitor (or two, or three) if ever I heard one.
Seriously, nice toolkits are coming out for this kind of work. Much needed too, as parallel computing allows you to get things wrong MUCH quicker.
Some will say it is because the Merkin goverment wants to spy on them
Others will say it is because many American drivers cannot even handle a stick-shift.
Which is it?
Still like blowing things up though
And after a PhD you become Dr. Knob?
I would be willing to try the chips (and other AMD/Radeon graphics), and the newer Linux drivers. Only problem is we would have to port quite a bit of stuff from CUDA to OpenCL (which might be a good idea anyway, similar performance and no vendor lock in).
Regarding the binary nVidia drivers, I have no problems there. I rather like the fact that after inserting a new nVidia card in my PC to replace the old nVidia card, Linux runs without any adaptation, whereas Windows needs a new driver.
I must be allowed to keep up with the register anywhere, even whilst walking across the <SPLAT>
What, and miss out on free drinks and food, and any vendor freebees?
Think like a BOFH:
1. Go to the conference
2. Head for the bar
3. Wheedle/bribe/blackmail vendor into inviting you to another conference for free
4. goto 1
They are really getting the excitement in space exploration back to (near) Apollo levels.
Unless you purchase the extra extended warranty, which extends for a further 74 milliseconds for a mere 25% surcharge!!
Only while stocks last!
Or "Budget Suites in SPAAAAAAAAAAAACE!!"
You do not have to sit through them. Using the DVDs as frisbees can bring hours of healthy entertainment. Experiments microwave ovens are encouraged.
Not long, rest assured, not long
You are right when talking about looking through CDs and glass blackened with soot. There are however perfectly safe solutions. My Thousand Oaks glass objective solar filter works fine on my 8" scope. I watched and photographed the solar eclipse in 1999 with that scope, and the previous transit of Venus in 2004. Baader Solar film is perfectly safe, if attached correctly in front of the objective lens. All eyepiece filters are an absolute menace. I have recently made a solar filter out of it for my kids 4.5" F/4.4 Newtonian, and my eldest son and I had a nice view of sunspots through it. All harmful UV is blocked, and the total energy levels remain quite low.
Projection is actually dangerous in most reflectors, and certainly Maksutovs, Schmidt Cassegrains, and other scopes with fast primary mirrors, as the secondary can shatter under thermal stress, and even in fast refractors I would prefer a filter as the thermal stresses might cause eyepieces to shatter. In slow refractors projection is fine, especially as multiple can watch simultaneously.
"88 percent of respondents said they are willing to seek professional help to treat smut addicition, but would prefer to do it online;"
Well obviously they prefer to do it online, that was exactly the problem, wasn't it?
I have installed Dolphin as my default browser (after trying and not liking firefox on android). No worries on that front
It is SOOOOO tempting to suggest any orangutans on facebook would be in the upper quartile of users intelligence-wise .
But we must resist such temptations, must we not
says it all!
Mimmoths preferably pronounced to sound like Inspector Clouseau trying to say "mammoth", has my vote
Am I alone in reading Mammuthus creticus as Mammuthus cretinus
Time to head home