brooks@maddog.llnl.gov (05/19/89)
Has anyone with suitable experience with GCC internals considered the difficulty of adding a "loop unrolling" feature to GCC? It would be portable and with a suitable pipeline scheduling strategy would be a big win for some of the modern pipelined processors. Anyone know where you would start on this one? brooks@maddog.llnl.gov, brooks@maddog.uucp
bunda@cs.utexas.edu (John Bunda) (05/23/89)
In article <25539@lll-winken.LLNL.GOV>, brooks@maddog.llnl.gov writes: > Has anyone with suitable experience with GCC internals considered > the difficulty of adding a "loop unrolling" feature to GCC? yes. it isn't trivial, but I am looking into this in conjuction with my work in pipeline scheduling, as a matter of fact. Watch this space, but it will be a while. -John > Anyone know where you would start on this one? > > brooks@maddog.llnl.gov, brooks@maddog.uucp -- ................................... John Bunda UT CS Dept. bunda@cs.utexas.edu Austin, Texas