Re: Fix PEELING_FOR_NITERS calculation (PR 87288)

2018-09-20 Thread Richard Biener
On Thu, Sep 20, 2018 at 1:44 PM Richard Sandiford wrote: > > PEELING_FOR_GAPS now means "peel one iteration for the epilogue", > in much the same way that PEELING_FOR_ALIGNMENT > 0 means > "peel that number of iterations for the prologue". We weren't > taking this into account when deciding wheth

Fix PEELING_FOR_NITERS calculation (PR 87288)

2018-09-20 Thread Richard Sandiford
PEELING_FOR_GAPS now means "peel one iteration for the epilogue", in much the same way that PEELING_FOR_ALIGNMENT > 0 means "peel that number of iterations for the prologue". We weren't taking this into account when deciding whether we needed to peel further scalar iterations beyond the iterations