search for: getschedulingpreference

...cies are considered only if the node as an ILP scheduling > preference (the default in TargetLowering.h is None): > bool LStall = (!checkPref || left->SchedulingPref == Sched::ILP) && > BUHasStall(left, LHeight, SPQ); > ... > > and the PPC backend does not override getSchedulingPreference. > Right, even with sched=hybrid, the scheduler will fall back to register pressure scheduling unless the target implements TargetLowering::getSchedulingPreference. I forgot that piece of the puzzle. You could try simply returning Sched::ILP from PPCTargetLowering::getSchedulingPreference. If...

...etLatency()); but the latencies are considered only if the node as an ILP scheduling preference (the default in TargetLowering.h is None): bool LStall = (!checkPref || left->SchedulingPref == Sched::ILP) && BUHasStall(left, LHeight, SPQ); ... and the PPC backend does not override getSchedulingPreference. -Hal > > In addition, the stall computation is done using BUHasStall, and that > function only checks the current cycle. Without looking forward, I don't > understand how it could know how long the pipeline hazard will last. > > It looks like this may have something to d...

On Mon, 2011-12-19 at 23:20 -0800, Andrew Trick wrote: > > On Dec 19, 2011, at 10:53 PM, Hal Finkel wrote: > > > Here's my "thought experiment" (from PR11589): I have a bunch of > > load-fadd-store chains to schedule. A store takes two cycles to > > clear > > its last pipeline stage. The fadd takes longer to compute its result > > (say 5