Slashdot is powered by your submissions, so send in your scoop

 



Forgot your password?
typodupeerror

Comment Hopefully this doesn't result in (Score 3, Interesting) 72

removing the BTB entirely. I've seen libraries rip out faster routines or add some nondeterminism to the latency just so that it could mask such a "hot cache" vulnerability. It seems a bit backward to rip out a performance enhancing capability in the architecture just because of ASLR bypass.

Comment Couldn't the compiler... (Score 1) 359

ultimately benefit from being 64 bit as it allows for things like better vectorized string comparisons? I mean if anything it'd be a measurable improvement in speed. You get more GPRs and larger/wider vector registers. And it wouldn't shock me if a templated piece of c++ managed to make the compiler, optimizer, preprocessor and linker manage to consume a fair bit of that 32 bit address space for a given single compile process.

Comment Re: Here's a solution... (Score 1) 251

Nonredundant power supplies I'd agree is kind of a showstopper, but honestly the other two things you mentioned wouldn't have been relevant then or today. Architecture doesn't much matter for a server app built on Posix APIs that isn't FLOPs critical or GPU dependent. And software raid really hasn't been a hamper to performance or reliability since 2001 or so.

I do believe that they made Intel xserves toward the end of the lifespan of the product.

Comment Re: CPU not compatible (Score 1) 187

That is a somewhat harsh requirement but probably a commendable one. I guess this also means ASLR may be turned on by default for their binaries. The stack protection is probably well worth the performance hit. It also means though that the a third party little utility I wrote to inspect values at specified memory addresses for a certain game will probably no longer work once it's recompiled.

Slashdot Top Deals

I think there's a world market for about five computers. -- attr. Thomas J. Watson (Chairman of the Board, IBM), 1943

Working...