ngkong@oregon.uoregon.edu (04/16/91)
Hi, I noticed that one of the IBM 55SX runs window much faster, than the other. Both machines have the exact configuration, except the faster ones has a co-processor installed. I don't mean running programs that definitely benefits from co-processor (eg, Excel), but the general window routines (re-drawing screan, open/close files, etc). I also know that in theory, Win 3 doesn't support a co-processor. But on 55SX, which is a fairly slow machines, the difference in speed is fairly significant. The hypothesis we come up with is that the c-compiled code used in Win 3.0 indirectly benefits from the presence of the co-processor, as it would skip some instructions related to soft-emulation of co-processor. Is there any documented evidence that anyone knows? Comments/experience/discussion welcomes. Casey