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.
the only way to do large scale and wide testing is to write code that performs the tests. Be they runtime or libraries at compile time, that task is best left to a machine. If you are turking those tests out I would even argue you are bad at your job.
I mean the compiler binary itself, though after reading some other comments it appears that the compiler toolchain itself may be compromised of 64 bit binaries, anyway.
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.
Amazon won't directly sell internal hard drives anymore? I always seem to have to get them from a third party Amazon storefront, prime or not. Why are they so reluctant to house and store hard drives themselves anymore?
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.
a proposal for something that decreases the reliability of mechanical disks even more. I don't want higher bit rates to deal with in addition to the stream of other unpredictable failure modes associated with these things.
Sandisk has an mlc based SSD of an identical $/capacity price point. The title is a bit misleading as it implies OCZ is somehow the first flash manufacturer to do this.
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.
Yeah seriously 10 watts isn't bad for an appliance like that, I'd be willing to bet a TV display on standby is in the same ballpark or more. If it were sipping from a battery I'd consider this bad but it isn't a laptop or a phone.
sells the steam box, as most non console games can be driven at any arbitrary resolution supported by your display. Sure textures may be crappy at that scale, but texture filtering and up sampling can go a decent way there.
This fact is especially interesting when you look at the V8 source code, a lot of which makes use of SIMD by either inline asm or separate asm files for things like jpeg rendering. A lot of this is pulled from libjpeg turbo and other libraries, but there is a fair bit of that going on.
Solaris "solved" the 32 / 64 bit issue the same way OS X did: a 64 bit kernel with an entirely 32 bit userland. OS X doesn't do this anymore but OpenSolaris did for quite a while. I haven't checked if this is still the case in the most recent OpenIndianas. So the seamlessness that you are referring to is simply a matter of adopting one as opposed to the other. This also limits the total address space for any given process to be the 4 GB limit. This can be problematic for something like a CAD or 3D rendering package, in which consuming 5 or 6 GB even with just memory mapped IO is the norm.
And for what it's worth, all the people saying that chrome is 32 bit only, that is likely the case only for windows:
file/usr/lib64/chromium-browser/chrome/usr/lib64/chromium-browser/chrome: ELF 64-bit LSB shared object, x86-64, version 1 (SYSV), dynamically linked (uses shared libs), for GNU/Linux 2.6.16, stripped
Even with all of the asm included in the chromium source code it can still be built cleanly as 64 bit. Of course the same can be said about the Linux versions of Firefox, I suppose. I too am baffled why 64 bit windows support is this complicated. When developing for Windows I find all sorts of weirdness between their 64 bit and 32 bit compilers. I found the 64 bit C compiler strict about where declaring string buffers (had to be at the beginning or it wouldn't compile). The 32 bit compiler of the same version of Visual C compiled and ran the code just fine.
Yeah and somehow products only officially supported with redhat rpms don't work on Slackware and the likes.../s Ubuntu is close enough, ABI compatibility and packed shared libs are all we really need to ensure it works on another distro.
Why do they need more revenue, isn't Mark Shuttleworth a multimillionaire still? I thought he was about philanthropy not profits. Why couldn't they just generate ad revenue from their web page or their built in Ubuntu One music store or something? This just seems wrong.
Following up here's just one example of one of his comments from a 1997.plan file:
Linux I consider linux the second most important platform after win32 for id. From a biz standpoint it would be ludicrous to place it even on par with mac or os/2, but for our types of games that are designed to be hacked, linux has a big plus: the highest hacker to user ratio of any os. I don't personally develop on linux, because I do my unixy things with NEXTSTEP, but I have a lot of technical respect for it.
for me to see my childhood hero throw FUD about market viability for my platform. John Carmack was once an open minded individual who cared about technical feats and versatility in the engine (read some of his former.plan files about comments to the portability of the OpenGL API and his efforts to port to other ISAs). This is the same man who once witnessed the leak of the quake source code, saw that a user had submitted fixes and made it compile for Linux, and then later went on to publish that user's same work as the official Id copy.
John Carmack used to be a man of principle and not cater to tempestuous marketing. With all of his influence now he says this garbage that has the potential to destroy the momentum that Valve has been generating toward a formerly unsuccessful effort? Developing games for Linux, even if it isn't a marketable success it will be a technical success and a step forward for games. When software development firms can work this closely with hardware developers and inspect EVERY piece of the stack games have the potential for more efficient hardware utilization and smoother effects.
Slashdot Mirror
Redundant summary is redundant
Lenovo x series have phenomenal battery life, my x240 gets over the advertised 13 hours depending on how I use it.
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.
the only way to do large scale and wide testing is to write code that performs the tests. Be they runtime or libraries at compile time, that task is best left to a machine. If you are turking those tests out I would even argue you are bad at your job.
I mean the compiler binary itself, though after reading some other comments it appears that the compiler toolchain itself may be compromised of 64 bit binaries, anyway.
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.
Amazon won't directly sell internal hard drives anymore? I always seem to have to get them from a third party Amazon storefront, prime or not. Why are they so reluctant to house and store hard drives themselves anymore?
You must be new to Slashdot, that was tradition pretty much forever.
stranger than fiction. Except for the Google part.
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.
a proposal for something that decreases the reliability of mechanical disks even more. I don't want higher bit rates to deal with in addition to the stream of other unpredictable failure modes associated with these things.
Sandisk has an mlc based SSD of an identical $/capacity price point. The title is a bit misleading as it implies OCZ is somehow the first flash manufacturer to do this.
that fits this bill. Code that I swore up and down covered all corner cases for input but with enough fuzzing could be coaxed into crashing.
has some weird psychological warfare going on there.
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.
Yeah seriously 10 watts isn't bad for an appliance like that, I'd be willing to bet a TV display on standby is in the same ballpark or more. If it were sipping from a battery I'd consider this bad but it isn't a laptop or a phone.
This is not exactly what apache does anymore. Since apache 2.x it has served multiple processes of apache that dispatch new threads.
When if ever will 10gigE be affordable. Is the asic design on those switches really that insane?
sells the steam box, as most non console games can be driven at any arbitrary resolution supported by your display. Sure textures may be crappy at that scale, but texture filtering and up sampling can go a decent way there.
This fact is especially interesting when you look at the V8 source code, a lot of which makes use of SIMD by either inline asm or separate asm files for things like jpeg rendering. A lot of this is pulled from libjpeg turbo and other libraries, but there is a fair bit of that going on.
Solaris "solved" the 32 / 64 bit issue the same way OS X did: a 64 bit kernel with an entirely 32 bit userland. OS X doesn't do this anymore but OpenSolaris did for quite a while. I haven't checked if this is still the case in the most recent OpenIndianas. So the seamlessness that you are referring to is simply a matter of adopting one as opposed to the other. This also limits the total address space for any given process to be the 4 GB limit. This can be problematic for something like a CAD or 3D rendering package, in which consuming 5 or 6 GB even with just memory mapped IO is the norm.
And for what it's worth, all the people saying that chrome is 32 bit only, that is likely the case only for windows:
file /usr/lib64/chromium-browser/chrome /usr/lib64/chromium-browser/chrome: ELF 64-bit LSB shared object, x86-64, version 1 (SYSV), dynamically linked (uses shared libs), for GNU/Linux 2.6.16, stripped
Even with all of the asm included in the chromium source code it can still be built cleanly as 64 bit. Of course the same can be said about the Linux versions of Firefox, I suppose. I too am baffled why 64 bit windows support is this complicated. When developing for Windows I find all sorts of weirdness between their 64 bit and 32 bit compilers. I found the 64 bit C compiler strict about where declaring string buffers (had to be at the beginning or it wouldn't compile). The 32 bit compiler of the same version of Visual C compiled and ran the code just fine.
Yeah and somehow products only officially supported with redhat rpms don't work on Slackware and the likes... /s
Ubuntu is close enough, ABI compatibility and packed shared libs are all we really need to ensure it works on another distro.
Why do they need more revenue, isn't Mark Shuttleworth a multimillionaire still? I thought he was about philanthropy not profits. Why couldn't they just generate ad revenue from their web page or their built in Ubuntu One music store or something? This just seems wrong.
Following up here's just one example of one of his comments from a 1997 .plan file:
Linux
I consider linux the second most important platform after win32 for id. From a biz standpoint it would be ludicrous to place it even on par with mac or os/2, but for our types of games that are designed to be hacked, linux has a big plus: the highest hacker to user ratio of any os. I don't personally develop on linux, because I do my unixy things with NEXTSTEP, but I have a lot of technical respect for it.
What happened to you, John?
for me to see my childhood hero throw FUD about market viability for my platform. John Carmack was once an open minded individual who cared about technical feats and versatility in the engine (read some of his former .plan files about comments to the portability of the OpenGL API and his efforts to port to other ISAs). This is the same man who once witnessed the leak of the quake source code, saw that a user had submitted fixes and made it compile for Linux, and then later went on to publish that user's same work as the official Id copy.
John Carmack used to be a man of principle and not cater to tempestuous marketing. With all of his influence now he says this garbage that has the potential to destroy the momentum that Valve has been generating toward a formerly unsuccessful effort? Developing games for Linux, even if it isn't a marketable success it will be a technical success and a step forward for games. When software development firms can work this closely with hardware developers and inspect EVERY piece of the stack games have the potential for more efficient hardware utilization and smoother effects.