Re: Vyznam dual core
Parada, Eagle, prave jsi nam vysvetlil, ze se 67% (je to porad alfa) narust vykonu pri enkodovani do Xvidu stejne nevyplati. V tom s tebou asi moc lidi souhlasit nebude.
Jak se vyjadris na ten muj minuly post, kde jsem hodil par uryvku z toho clanku?
Mam na mysli konkretne schema pipeline toho jejich noveho MT source engine:
1. Construct scene rendering lists for multiple scenes in parallel (world, water reflections, and TV monitors)
2. Overlap graphics simulations
3. Compute character skeletal transformations for all characters in all scenes in parallel
4. Compute shadows for all characters in parallel
5. Allow multiple threads to draw in parallel (this required a rewrite of the graphics libraries that live directly above Direct3D)
A uplne nejvic me zajima, co reknes na toto:
The end results of Valve's efforts were even better than they had initially hoped. Not only was the speedup on the four-core Kentsfield chips nearly linear in most cases (an average of 3.2 times over a single core) but having four CPUs instead of two made it possible to do things that simply couldn't be done with fewer cores.
Jsem zvedav, jak budes takovou hru hrat na SC.
http://enthusiast.hardocp.com/articl...50aHVzaWFzdA== :
Brian Jacobson from Valve had a very good comment on threading in the Source Engine. He noted that Valve’s experience with Half-Life 2 had the game being CPU bound much more often than it was GPU bound. “Multi-core CPU’s and multi-threading will help relieve the pressure that is being put on CPU’s.” He goes on to say that “Fundamentally, games are about what you do and not what you see… about the stuff that is done on your CPU.” He points out that Valve can now make people look photo-realistic in games, but that we are nowhere near making them act like real people. He says that with multi-threading and multi-core processors we’ll finally be able to have the computational power to make the people, the environment, the physics, the AI, and the game, in general, more immersive.
