Messages in this thread |  | | | From | bofh@snoopy ... | | Date | Fri, 25 Apr 97 15:26:01 +1100 | | Subject | Re: Cyrix M2 |
| |
>> > I remember a big discussion about MMX that happened not >> > too long ago. The conclusion was that the penalty to switch >> > between FP & MMX was too great for a true multitasking OS. >[SNIPPED] >> >> (Cyrix had to use FP registers for MMX to be at all compatible >> with Intel. I don't think they liked having to do it :-). Intel >> did it to save the cost of engineering their silicon to hold a >> few more registers.) >> >[SNIPPED] >It isn't a cost issue! Sources at Cyrix say they had to have a way for an >unknown operating system to be able to save and restore the new registers >without having to rewrite all the operating systems that use >Cytix/Pentiums/ix86/etc.
>It was presumed that, during a context switch FSAVE and FRSTOR will be >executed to save/restore the state of the FP Unit. If executed, these >instructions should automatically save and restore the MMX register(s) >also. I don't know if they have to extend the buffer length for this >operation. If so, the point is moot because the operating systems will >have to be rewritten to provide this additional storage.
It wouldn't be difficult to add a feature to a new CPU which had to be explicitely enabled from ring 0 before it could be used. Then if the OS had allocated enough space for saving the registers it could enable the feature. I expect that most OSs would quickly get patched to support a feature such as MMX if it was added in that way.
Russell Coker
|  |