Kiko Rigatti
12-02-2004, 15:49:20
"Essa afirmação é do Gabe Newell da Valve Software. Em entrevista ao HalfLife2Net, ele afirma que o game rodará lento em CPUs Hyper threaded. Já em sistema de 64-bits o jogo( confrontando os dois sistemas) é 30% superior. Isso é uma ótima notícia para a AMD e muito mais para os compradores de seus produtos...não esqueçam que a Intel pretende lançar o suporte ao 64 bits agora em Fevereiro no IDF. A tecnologia chamada agora "CT" deveria fazer parte dos Prescotts, mas só após maiores detalhes da Intel é que será possível saber quando a empresa começará a usar o referido suporte. Vejamos a transcrição da entrevista:
Will Half-Life 2 support Hyper-Threaded CPU's?
Gabe Newell: Hyper threaded CPUs attempt to extract thread-level parallelism, as opposed to traditional pipelined architectures which attempt to take advantage of instruction level parallelism. Hyper threading can be somewhat unpredictable in terms of the performance impact, as you can, in some cases, run slower.
Implementing and maintaining a "deeply" multi-threaded version of Source would be a pain (i.e. multi-threading the renderer). Implementing a hacky version (e.g. having a discreet physics thread or running the client and server in different threads) is something we may do depending upon how much bandwidth we have before we ship. Right now we don't get nearly as much bang for the buck working on hyper threading as we do on other optimizations. That may change as we run out of things to optimize.
64-bits, in contrast, is a one-time cost and is fairly simple to take advantage of. It's a huge win for tools as it not only gets more work done per instruction, but it also gets us past the current memory limitations, which are a problem for us today on tools.
Distributed computing is harder than hyper threading but it has the potential to increase performance by a huge amount (8X on our tools) as opposed to hyper threading (30%). All of our tools are going to a distributed approach.
So the taxonomy looks like this:
- general algorithmic optimization (general good thing to do)
- DX9 optimization (big gains, long term direction)
- 64-bits (not that hard, solves memory problem as well as performance gains)
- hyper threading (hard initial cost, on-going code maintenance cost, limited unpredictable performance gains, benefits in multiprocessor environments as well)
- distributed computing (hardest to do, biggest potential gains, great for tools, may be great for servers, not sure how it works with clients)
FONTE:Neofighters
Will Half-Life 2 support Hyper-Threaded CPU's?
Gabe Newell: Hyper threaded CPUs attempt to extract thread-level parallelism, as opposed to traditional pipelined architectures which attempt to take advantage of instruction level parallelism. Hyper threading can be somewhat unpredictable in terms of the performance impact, as you can, in some cases, run slower.
Implementing and maintaining a "deeply" multi-threaded version of Source would be a pain (i.e. multi-threading the renderer). Implementing a hacky version (e.g. having a discreet physics thread or running the client and server in different threads) is something we may do depending upon how much bandwidth we have before we ship. Right now we don't get nearly as much bang for the buck working on hyper threading as we do on other optimizations. That may change as we run out of things to optimize.
64-bits, in contrast, is a one-time cost and is fairly simple to take advantage of. It's a huge win for tools as it not only gets more work done per instruction, but it also gets us past the current memory limitations, which are a problem for us today on tools.
Distributed computing is harder than hyper threading but it has the potential to increase performance by a huge amount (8X on our tools) as opposed to hyper threading (30%). All of our tools are going to a distributed approach.
So the taxonomy looks like this:
- general algorithmic optimization (general good thing to do)
- DX9 optimization (big gains, long term direction)
- 64-bits (not that hard, solves memory problem as well as performance gains)
- hyper threading (hard initial cost, on-going code maintenance cost, limited unpredictable performance gains, benefits in multiprocessor environments as well)
- distributed computing (hardest to do, biggest potential gains, great for tools, may be great for servers, not sure how it works with clients)
FONTE:Neofighters