In an former article about this case, it was said the reason why the judge made M$ responsible, was that M$ is claiming the rights for all stuff that is published in the MSN forum. There is some legel stuff in the rules for the use of the forum that any content published goes over to M$. And of course, if it is yours, you are responsible.
There was a company in germany that had kind of a
earth turning device to remove mines. It shuffled all the earth in and shreddered it, either destroying or letting explode (it was armored) the mines.
The problem with these maschines seem always to be anti tank mines. Anti personal mines can be blocked by armor, but if you hit exidentally an AT mine, it will probably blow whatever machine you have.
I have testet serveral compilers on a heavy numerical code (simplex algorithm) and it's
about 15% faster the gcc.
BUT icc has a long tradtion on generating incorrect code. Years ago on SCO UNIX it compile TeX somewhat inccorect with all optimization on, and it did the same with our code now. But even with the rest it is faster then gcc.
But the same goes for the Compaq Compiler on Alpha, the Sun Compiler on Sparc and the HP Compiler on HPPA. But only one Compiler of them is free and runs everywhere! GCC.
icc is obviously tunes towards SPEC benchmarks and will give best results there.
So the effect it gives will allways overestimated.
We have P4 1.7 here and if you really give them work, the CPU overheat feature sometimes starts to slow down the CPU. So the 1.7 is more like a peak speed when idle.
And besides, the memory and bus etc. are all the old speed. There was an interesting report from Cray about the number of idle steps when a cache miss occurs. That was several hundred ticks a few years ago and will now be in the thousends.
So what you really achive with higher clocks is a CPU that idles faster.
Slashdot Mirror
In an former article about this case, it was said the reason why the judge made M$ responsible, was that M$ is claiming the rights for all stuff that is published in the MSN forum.
There is some legel stuff in the rules for the use of the forum that any content published goes over to M$.
And of course, if it is yours, you are responsible.
earth turning device to remove mines. It shuffled all the earth in and shreddered it, either destroying or letting explode (it was armored) the mines.
The problem with these maschines seem always to be anti tank mines. Anti personal mines can be blocked by armor, but if you hit exidentally an AT mine, it will probably blow whatever machine you have.
I have testet serveral compilers on a heavy numerical code (simplex algorithm) and it's about 15% faster the gcc.
BUT icc has a long tradtion on generating incorrect code. Years ago on SCO UNIX it compile TeX somewhat inccorect with all optimization on, and it did the same with our code now. But even with the rest it is faster then gcc.
But the same goes for the Compaq Compiler on Alpha, the Sun Compiler on Sparc and the HP Compiler on HPPA. But only one Compiler of them is free and runs everywhere! GCC.
icc is obviously tunes towards SPEC benchmarks and will give best results there. So the effect it gives will allways overestimated.
We have P4 1.7 here and if you really give them work, the CPU overheat feature sometimes starts to slow down the CPU. So the 1.7 is more like a peak speed when idle. And besides, the memory and bus etc. are all the old speed. There was an interesting report from Cray about the number of idle steps when a cache miss occurs. That was several hundred ticks a few years ago and will now be in the thousends. So what you really achive with higher clocks is a CPU that idles faster.