Actually, you've got it all wrong. In a synchronous system the parts have to guarantee they are done in n cycles, else things go bad. E.g. RAM in an overclocked system - the processor expects the data from the RAM to be valid after n cycles/waitstates, if the RAM is too slow - poof.
In an asynchronous system you just have to make sure that a unit signals that it's done computing to it's successor(s) in the pipeline, so they know the data is valid, and then tell its predecessor(s) that it is ready again to receive data and/or that it accepted the new data (acknowledge) - which propagates backwards through the pipe. Of course that is also the hard (because new) part of doing async, that and the logic that "knows" when a unit is ready and creates the signals.
I recently read that the cost of the (2nd) Gulf War cost $60 billion, 90% of which was paid for by several Arabic and European States. Article in German. The article claims the Pentagon got $3.8b for the first three months of the war from Congress (not including normal cost of operations nor $20b for "special measures" after 9/11).
Replying to my own post, the last sentence in peculiar.
http://www.heise.de/newsticker/data/hes-11.11.01-0 00/ - Heise Newsticker reports (in german), that the compiler switch -ipo (inter procedural optimization) can seriously mess up the compiled program. An example given (with image) is Povray under both Windows and Linux, which can tint some images.
Well, thanks for admitting you are a troll. The fact that you are comparing two systems with no common parts means you can only tell something about the whole systems. Any 4th grader would know that.
BTW, the SiS645 chip set actually beats the i850 - but you have to use the new PC2700/DDR333 RAMs.
In the latest issue (23/01) of the german computer magazin c't (article not online - www.heise.de/ct/ ), there is an article about Intel's C compiler for Linux. Testing with SPECInt2000 , they get an average increase of 20% over gcc.
P4/1.7 +26%, P3/866 +23%, Athlon/1.2 +16%, AthlonXP/1.2 +19% (due to SSE). But the boost is somewhat lower if you exclude the subtest 252.eon, which is more than 3 times as fast with icc.
Another interesting test compared scores for icc on Linux vs. Windows on the P4. Linux scores a little lower on average, but two test show huge differences: 176.gcc on Linux scores 745 vs. 529 on Windows, while for 252.eon it's 406 (L) vs. 745 (W) - gcc only scored 115. You can see that SPEC sub-scores can differ wildly on the same processor even when using the same compiler.
Mixed results for C++: 252.eon is C++, so it's obviously fast, but icc doesn't work with gcc compiled libraries (incl. most graphic toolkits).
One more thing: if you set some switches the wrong way, the resulting code may not work as intended.
Let's see, the dependance of the kernel on gcc is okay, since gcc is also cross platform - but one big use of gcc extensions in the kernel is for inline assembler? How does that go for portability?
The reason why PC users don't like Marathon is the same why they don't like the Mac: they simply don't get it. Why should I buy a computer that is easy to use, Windows 3.1 is just as good, and DOS is much more powerfull? Why buy a FPS where you have to think, the S in FPS stands for shooting, not thinking. Why would a FPS be played in 800x640x16bit, when 320x200x8bit is obviously enough for Doom?
Re:.com is just to prominent for this to work
on
.biz Open For Biz
·
· Score: 2, Funny
"No, Sir, Mr. Investor. We are not one of those worthless dotcoms, we are a dotbiz - see the difference?"
Intel's marketing ethic guidelines allow them to tell people that their processors make the Internet faster and the pictures more colorfull however. Anyway, as long as they are ahead in MHz, many people will buy them, no matter how fast they actually are.
You could, if somebody made a upgrade, which is possible, but since non of the upgrade makers have made a G4e/7450 card yet, it's unlikely they will make a G5 card in the near future (and I'm not talking Internet time).
Ahh, but the Laptop survives because it gets hot on the outside, IOW because the heat gets transfered away from the processor. If the processor doesn't get as hot, you can save money (and space, and inconvenience for the user) by not making such a big thing out of the heat transfer thingamagick.
Slashdot Mirror
Have you seen the pictures? A simple, solid state memory audio device might survive, but anything more complicated, esp. Video, would get crushed.
Well, I'd rather carry a container of methanol than an AC adapter and a really loooooong cord.
If you add all the claims about the P4, it's half RISC, half asynchronous and half fairy dust.
The last time I read about clockless computing, the chip simply ran slower when it was hotter, and faster when it was colder.
In an asynchronous system you just have to make sure that a unit signals that it's done computing to it's successor(s) in the pipeline, so they know the data is valid, and then tell its predecessor(s) that it is ready again to receive data and/or that it accepted the new data (acknowledge) - which propagates backwards through the pipe. Of course that is also the hard (because new) part of doing async, that and the logic that "knows" when a unit is ready and creates the signals.
I recently read that the cost of the (2nd) Gulf War cost $60 billion, 90% of which was paid for by several Arabic and European States. Article in German. The article claims the Pentagon got $3.8b for the first three months of the war from Congress (not including normal cost of operations nor $20b for "special measures" after 9/11).
The world population grew from 3.7 billion in 1970 to 6 billion in 2000. All that despite famine, Chinas one child policy and diseases like AIDS.
Bruce and Robert played together in "Maniac Cop" 1&2. MC2) also stars Robert Davi and Charles Napier - Chin Fest!
http://www.bruce-campbell.com/evil/evil-rumors.htm l
http://www.heise.de/newsticker/data/hes-11.11.01-0 00/ - Heise Newsticker reports (in german), that the compiler switch -ipo (inter procedural optimization) can seriously mess up the compiled program. An example given (with image) is Povray under both Windows and Linux, which can tint some images.
BTW, the SiS645 chip set actually beats the i850 - but you have to use the new PC2700/DDR333 RAMs.
You can say a lot against RAMBUS, but it's not slow. Check any benchmark comparing Pentium4 systems with RDRAM against P4s with DDR-SDRAM.
P4/1.7 +26%, P3/866 +23%, Athlon/1.2 +16%, AthlonXP/1.2 +19% (due to SSE). But the boost is somewhat lower if you exclude the subtest 252.eon, which is more than 3 times as fast with icc.
Another interesting test compared scores for icc on Linux vs. Windows on the P4. Linux scores a little lower on average, but two test show huge differences: 176.gcc on Linux scores 745 vs. 529 on Windows, while for 252.eon it's 406 (L) vs. 745 (W) - gcc only scored 115. You can see that SPEC sub-scores can differ wildly on the same processor even when using the same compiler.
Mixed results for C++: 252.eon is C++, so it's obviously fast, but icc doesn't work with gcc compiled libraries (incl. most graphic toolkits).
One more thing: if you set some switches the wrong way, the resulting code may not work as intended.
Let's see, the dependance of the kernel on gcc is okay, since gcc is also cross platform - but one big use of gcc extensions in the kernel is for inline assembler? How does that go for portability?
The reason why PC users don't like Marathon is the same why they don't like the Mac: they simply don't get it. Why should I buy a computer that is easy to use, Windows 3.1 is just as good, and DOS is much more powerfull? Why buy a FPS where you have to think, the S in FPS stands for shooting, not thinking. Why would a FPS be played in 800x640x16bit, when 320x200x8bit is obviously enough for Doom?
"No, Sir, Mr. Investor. We are not one of those worthless dotcoms, we are a dotbiz - see the difference?"
More like a 50-50 ratio. Now where do you think Adobe concentrates its efforts? Right, where they get fast code the easy way.
Who is going to fly them? NASA astronauts or people from the corporation?
Photoshop is at least as optimized for x86 (by Intel engineers no less) as for PPC.
Intel's marketing ethic guidelines allow them to tell people that their processors make the Internet faster and the pictures more colorfull however. Anyway, as long as they are ahead in MHz, many people will buy them, no matter how fast they actually are.
No, it doesn't. The Itanium has.
You could, if somebody made a upgrade, which is possible, but since non of the upgrade makers have made a G4e/7450 card yet, it's unlikely they will make a G5 card in the near future (and I'm not talking Internet time).
He probably used IE's Link Click Wizard ;-)
Ahh, but the Laptop survives because it gets hot on the outside, IOW because the heat gets transfered away from the processor. If the processor doesn't get as hot, you can save money (and space, and inconvenience for the user) by not making such a big thing out of the heat transfer thingamagick.
"Just like we planned" said Mr. Anonymous Coward from CRC Publishing.