1) it was written back before modern FPUs and SSE etc. nowadays doing square roots in hardware is faster, especially if you vectorize. but back in 1999 it wasn't.
...Unless you had an AMD K6-2 or K6/III which had 3DNow! which could do it in 1 to 3 clock cycles in hardware depending on the accuracy you needed.
Q3 ran a treat on my K6-2/500 with nVidia TNT2 Ultra. There were all kinds of 3DNow! optimisations in there.
... they fired all the Linux Emulation engineers before it went back into Solaris. It was a killer technology. You could run Oracle for RHEL on Solaris 10 on Opteron and you could run Windows programs on WINE compiled for Linux along side Solaris x86 and Java apps.
Too bad they continue to waste hundreds of millions of dollars on a dead-end CPU architecture (i.e. SPARC).
The application stack's all written in Java, right? So who the heck needs expensive SPARC when Opteron does the job faster at a fraction of the price?
Who needs Solaris when Linux is catching up so fast?
So what you're saying is that the new intel processors will be just like Sun's Niagara, announced 2 years ago, only with good floating-point and much higher clock speed.
Excellent.
AMD already has 4-core Opterons up its sleeve. I'm really looking forward to the next couple of years.
Last week I was remembering watching an episode of the now defunct BBC TV Programme called Tomorrow's World from the 80s in which they showed a 3.5" floppy being used to store music.
I was only about 10-12 years old at the time, but the gist of it was, they were "processing the audio signal using a computer to remove the unimportant information and store only the important information on the disk."
I seem to remember they had a man playing the trumpet in the studio and they recorded him playing. On the computer they showed the signal and maybe some Fourier Transforms of it to demonstrate what was being stored and discarded.
Then, of course, they played back the recording.
It recently occurred to me that it was a form of lossy audio compression, and very likely related to things like MP3 and Ogg/Vorbis.
If you're not getting reimbursed by your employer, you shouldn't be going to work, unless you're working for charity.
You should (if you're lucky) get enough to cover your work costs (transport, clothes etc.), pay your rent/morgage and buy enough food to eat. If you're luckier, you might have some disposable income.
I vowed never to work for an unreasonable employer ever again after I quite my part-time potato-arranging job at Safeway when I was 17. I've been lucky so far.
Perhaps Bill's real problem is that universities teach Computer Science mainly on Unix-like operating systems which are free beer, free speech, open-source, ubiquitous and readily available. There is a whole spectrum of implementations to study and compare.
There is only one Windows. It is full of faults. It gets viruses. It costs money. It is closed source. It only runs on x86 (no, itanic doesn't count and neither do archaic implementations on Alpha and MIPS). It is not well implemented. For research it is of little value.
Correct. And the Great Unwashed will think that BSD/Linux/MacOS are technologically inferior than Windows simply because they "can't play back expensive, high-quality content."
These same people are allowed to vote for governments and serve on juries...
itanium (itanic) is a poor design for anything other than numbercrunching. It is a relic of theoretical supercomputer designs that were popular in the late 1970s. itanic shines on floating-point benchmarks, and is mediocre at best on everything else.
Since the late 1970s, we have had RISC and then superscalar RISC, some now with elements of VLIW. This provides better real-world (general-purpose) performance using substantially less power and fewer transistors than itanic.
Modern RISC processors (including x86 which are RISC internally) can reschedule execution of instructions dynamically (i.e. at run time). itanic can not. It relies on the compiler to schdule the code. It is only possible to schedule code well at compile time for very well-defined problem sets i.e. floating-point maths intensive programs like numerical simulations. NASA currently owns 5% of the world's itanic processors (in a single machine).
itanic was intel's attempt to kill the 64-bit RISC market, putting all of its competitors out of business. Like all great megalomaniacal plans, it has failed. It was a marketing-driven processor, and a failure.
It can't compete with clunky old UltraSPARC IV on server-oriented workloads. Even that market, which isn't big enough to sustain Sun and its processors, is orders of magnitude bigger than the market in which itanic has any relevance.
For big servers nowadays, you have a choice between Opteron and POWER.
In science and engineering, you're often better with something like Opteron, POWER or something fancy from Cray, NEC or Fujitsu. itanic runs hot and consumes too much electricity.
Has anyone ever seen one? I haven't. There was one at a show once on the Red Hat stand, but they wouldn't let me performance test it... and they wouldn't even let me see it because it had over-heated.
itanic is about the most expensive turkey in computing history.
On the Underground? At the right time of day you'll be worrying more about the risk of being crushed by the bodies around you than thinking about who's touching whom.
Being squased like sardines in amongst a bunch of smelly people doesn't count.
How can that possibly compare to a consenting handful of naked female breast? My original question still stands.
What do you get if you cross a Woodcrest with a Conroe? A Concrest?
* (Or young men dressed up as ladies.)
Nice try, Mr. Troll, but I've actually written some 3DNow! assembly language routines so I think I know a little bit more than you.
...Unless you had an AMD K6-2 or K6/III which had 3DNow! which could do it in 1 to 3 clock cycles in hardware depending on the accuracy you needed.
Q3 ran a treat on my K6-2/500 with nVidia TNT2 Ultra. There were all kinds of 3DNow! optimisations in there.
Too bad they continue to waste hundreds of millions of dollars on a dead-end CPU architecture (i.e. SPARC).
The application stack's all written in Java, right? So who the heck needs expensive SPARC when Opteron does the job faster at a fraction of the price?
Who needs Solaris when Linux is catching up so fast?
Who needs Sun, again?
...and Evolution is "only a theory!"
Next you can write a cross-platform Direct X library that uses OpenGL as a back end. That would be very useful indeed.
Excellent.
AMD already has 4-core Opterons up its sleeve. I'm really looking forward to the next couple of years.
I was only about 10-12 years old at the time, but the gist of it was, they were "processing the audio signal using a computer to remove the unimportant information and store only the important information on the disk."
I seem to remember they had a man playing the trumpet in the studio and they recorded him playing. On the computer they showed the signal and maybe some Fourier Transforms of it to demonstrate what was being stored and discarded.
Then, of course, they played back the recording.
It recently occurred to me that it was a form of lossy audio compression, and very likely related to things like MP3 and Ogg/Vorbis.
Many years ago (>5) Linux was starting to become a useful kernel on SMP machines. FreeBSD had no or little SMP support. Have they fixed that yet?
It used to be a project to develop a Free clone of QT back in the day.
Sun does allow Linux distributions to distribute Java. For example, Slackware comes with the Java SDK as standard.
You should (if you're lucky) get enough to cover your work costs (transport, clothes etc.), pay your rent/morgage and buy enough food to eat. If you're luckier, you might have some disposable income.
I vowed never to work for an unreasonable employer ever again after I quite my part-time potato-arranging job at Safeway when I was 17. I've been lucky so far.
The world doesn't owe you a living.
Toilet seat.
Which marriage? First, second or third?
Come to think of it, no. Bring on the guns and bombs.
We have the intarweb now. We can work for anyone, anywhere, at any time.
There is only one Windows. It is full of faults. It gets viruses. It costs money. It is closed source. It only runs on x86 (no, itanic doesn't count and neither do archaic implementations on Alpha and MIPS). It is not well implemented. For research it is of little value.
Sour grapes, Mr Gates?
Funk is responsible for your mood. You can score it any day on Radio W.E.F.U.N.K.
Maybe the US could donate its stockpile from Gitmo? It must be expensive keeping people locked up for years.
Correct. And the Great Unwashed will think that BSD/Linux/MacOS are technologically inferior than Windows simply because they "can't play back expensive, high-quality content."
These same people are allowed to vote for governments and serve on juries...
I truly completely and utterly despair.
Yes, but Chitty Chitty Bang Bang had magic powers.
itanium (itanic) is a poor design for anything other than numbercrunching. It is a relic of theoretical supercomputer designs that were popular in the late 1970s. itanic shines on floating-point benchmarks, and is mediocre at best on everything else.
Since the late 1970s, we have had RISC and then superscalar RISC, some now with elements of VLIW. This provides better real-world (general-purpose) performance using substantially less power and fewer transistors than itanic.
Modern RISC processors (including x86 which are RISC internally) can reschedule execution of instructions dynamically (i.e. at run time). itanic can not. It relies on the compiler to schdule the code. It is only possible to schedule code well at compile time for very well-defined problem sets i.e. floating-point maths intensive programs like numerical simulations. NASA currently owns 5% of the world's itanic processors (in a single machine).
itanic was intel's attempt to kill the 64-bit RISC market, putting all of its competitors out of business. Like all great megalomaniacal plans, it has failed. It was a marketing-driven processor, and a failure.
It can't compete with clunky old UltraSPARC IV on server-oriented workloads. Even that market, which isn't big enough to sustain Sun and its processors, is orders of magnitude bigger than the market in which itanic has any relevance.
For big servers nowadays, you have a choice between Opteron and POWER.
In science and engineering, you're often better with something like Opteron, POWER or something fancy from Cray, NEC or Fujitsu. itanic runs hot and consumes too much electricity.
Has anyone ever seen one? I haven't. There was one at a show once on the Red Hat stand, but they wouldn't let me performance test it... and they wouldn't even let me see it because it had over-heated.
itanic is about the most expensive turkey in computing history.
Being squased like sardines in amongst a bunch of smelly people doesn't count.
How can that possibly compare to a consenting handful of naked female breast? My original question still stands.
You can already see those for free as in beer on the Intarweb.
What you can't do, in either case, is touch.
So please explain how this is progress?