Monk Posted September 1, 2011 Share Posted September 1, 2011 I've been messing with CUDA support by offloading some functions for games into the GPU of a video card. So far, I've been able to manipulate some instructions by creating a virtual machine to directly call CUDA instructions for certian floating point operations, ie foobar() -> cpu_foobar ? : 0 : 1 -> gpu_foobar() I have a test CSS server that I've been screwing with, but when you exit the server it crashes. Another cool trick is using a video cards onboard memory for maps and temporary files, which is a factor of 30 faster than normal system memory I'll take some screenshots when it isn't so messy. If I can move the core sleep functions into the GPU, it will be more accurate than any hardware timers due to the sheer speed and no latency.. Link to comment Share on other sites More sharing options...
icekohl Posted September 1, 2011 Share Posted September 1, 2011 Thread bookmarked. I've got to see this. Link to comment Share on other sites More sharing options...
Monk Posted October 11, 2011 Author Share Posted October 11, 2011 Almost done with it. I'll post screenshots soon. Link to comment Share on other sites More sharing options...
tbrown7552 Posted October 14, 2011 Share Posted October 14, 2011 subscribed. Link to comment Share on other sites More sharing options...
KOhosting Posted February 11, 2012 Share Posted February 11, 2012 Did it work? Is it functional? Link to comment Share on other sites More sharing options...
Monk Posted February 15, 2012 Author Share Posted February 15, 2012 Yea, it works. I gave up on it though because it's just something I wrote for older games. I'm pretty much out of this field. Link to comment Share on other sites More sharing options...
Recommended Posts
Archived
This topic is now archived and is closed to further replies.