> But the required are often dependent on variables that are not> known at > compile time, for example load/store delays, or branches> taken/not taken. > Run time interlocks deal with the actual conflicts> as they occur, while > compiler or programmer conflict avoidance> has to use the worst case > scenarios. The observation that interlocks are not needed when the delay isknown and predictable, but are needed when the delay is varialbehas been around since the beginning. The ENIAC didn't haveinterlocks for the multiplier or function tables, but did for the divider/square rooter and the card reader. (The card punch had whatamounted to a completion signal that enforced the timing.) BLS
- [cctalk] early microprocessor limited pipelin... CAREY SCHUG via cctalk
- [cctalk] Re: early microprocessor limited pip... Adrian Godwin via cctalk
- [cctalk] Delay slots, was: Re: Re: early micr... Christian Kennedy via cctalk
- [cctalk] Re: Delay slots, was: Re: Re: early ... Jonathan Stone via cctalk
- [cctalk] Re: Delay slots, was: Re: Re: early ... Maciej W. Rozycki via cctalk
- [cctalk] Re: Delay slots, was: Re: Re: early ... Jonathan Stone via cctalk
- [cctalk] Re: Delay slots, was: Re: Re: early ... Henry Bent via cctalk
- [cctalk] Re: Delay slots, was: Re: Re: early ... Maciej W. Rozycki via cctalk
- [cctalk] Re: Delay slots, was: Re: Re: early ... Maciej W. Rozycki via cctalk
- [cctalk] Re: Delay slots, was: Re: Re: early ... Paul Koning via cctalk
- [cctalk] Re: Delay slots, was: Re: Re: early ... Brian L. Stuart via cctalk
- [cctalk] Re: Delay slots, was: Re: Re: early ... Gavin Scott via cctalk
- [cctalk] Re: Delay slots, was: Re: Re: early ... Chuck Guzis via cctalk
- [cctalk] Re: Delay slots, was: Re: Re: early ... Paul Koning via cctalk
- [cctalk] Re: Delay slots, was: Re: Re: early ... Chuck Guzis via cctalk
- [cctalk] Re: early microprocessor limited pip... Paul Koning via cctalk
- [cctalk] Re: early microprocessor limited pip... Maciej W. Rozycki via cctalk
- [cctalk] Re: early microprocessor limited pip... Eric Smith via cctalk
- [cctalk] Re: early microprocessor limited pip... Eric Smith via cctalk
- [cctalk] Re: early microprocessor limited pip... emanuel stiebler via cctalk
- [cctalk] Re: Intel 8086 - 46 yrs. ago Mike Katz via cctalk