Announcement

Collapse
No announcement yet.

Multi-Core Support for Source Unveiled

Collapse
This topic is closed.
X
X
 
  • Filter
  • Time
  • Show
Clear All
new posts

  • Multi-Core Support for Source Unveiled

    Bit-Tech had the good fortune to take the first look at the future of the Source engine and its support of multi-core processors. The future is looking mighty nice indeed.
    Having gotten some ideas of the mechanics behind the Source engine's transition to multi-core, we were keen to find out what had really motivated this move. Yes, there's new hardware arriving in the form of Kentsfield, but other development houses are not moving as quickly as Valve is when it comes to embracing the technology.



    Gabe Newell has a fairly easy answer. "If we're right, other people are going to take a long time to get the multi-threaded versions of their engines out. If we're right with the approach we've taken - which is to iterate and build on top of Source - we can get there a couple of years ahead of where they could be." In other words, Source can be at the cutting edge of engine technology, which makes it very attractive both to consumers and licensees.
    Included in the six page preview are two videos that show just a tiny hint of what the Source engine with multi-core support can truly do, a few screenshots taken from the videos, a benchmark graph, and plenty of juicy details about the future of Source and Half-Life 3 (maybe). The rain looks oh so pretty.

  • #2
    Oh man. That rain would add for some really nice dramatic, scary places. =)

    Comment


    • #3

      Comment


      • #4
        Sounds good.

        Comment


        • #5
          I'm interested in how this will improve the complexity of Bot AI, server-side. Hopefully once they can offload some of that state machine code to helper threads, the AIs can become far more complex. I guess someone still has to write all that logic, though.

          Comment


          • #6
            Very good news.. The CPU has always been a bottleneck in Source games.. Taking advantage of multi-core will give a big performance boost..

            Comment


            • #7
              Sweet, that $2000 I spent on my computer will finally go to use.

              Comment


              • #8
                I like the rain effects, but I'm more interested on how much Valve can take advantage of multi-core processors.

                Comment


                • #9
                  I like red, but I'm more interested in colors.



                  *blink*



                  What?

                  Comment


                  • #10
                    "If we're right with the approach we've taken - which is to iterate and build on top of Source - we can get there a couple of years ahead of where they could be."



                    Or, Unreal Engine 3 and Cry Engine 2 can already be farther ahead, and engines in development right now can be even further, without having to worry about codebase written years ago.

                    Comment


                    • #11
                      FightingChance wrote..

                      Or, Unreal Engine 3 and Cry Engine 2 can already be farther ahead, and engines in development right now can be even further, without having to worry about codebase written years ago.
                      well said.

                      Comment


                      • #12
                        Yes, Valve should just trash the whole source engine, and create a new one in order to top those engines. It wont be so bad, we will only have to wait another 5 years for portal and TF2.

                        Comment


                        • #13

                          Comment


                          • #14
                            Looking good.

                            Comment


                            • #15
                              FightingChance wrote..

                              "If we're right with the approach we've taken - which is to iterate and build on top of Source - we can get there a couple of years ahead of where they could be."



                              Or, Unreal Engine 3 and Cry Engine 2 can already be farther ahead, and engines in development right now can be even further, without having to worry about codebase written years ago.
                              Notice the first three words of the Valve quote: "If we're right". They obviously don't know if they'll be able to take advantage of their head start or not. Only time will tell.



                              Also, you're quick to trash the HL2 engine's codebase, but I wonder if mod developers would do the same? Perhaps Valve thinks they have a winning hand partly because of all the mods for the HL2 engine, and the coders' familiarity with its APIs. Were Valve to trash it all and start anew, developers would have to as well--and they might just decide to do it in UT2007 or something that's out right then and there. Right now, those coders can feel confident in their working code, the ubiquity of the HL2 engine on users' computers, and users' computers' capability to run the HL2 engine well. Can you say the same for the newer engines still being written?

                              Comment

                              Working...
                              X