On Tue, 30 Jun 2020, Richard Sandiford wrote:
> Richard Biener writes:
> >> Another thing we'd like for SVE in general is to allow vectors *with*
> >> gaps throughout the SLP graph, since with predication it's simple to
> >> ignore any inactive element where necessary. This is often much cheaper
Richard Biener writes:
>> Another thing we'd like for SVE in general is to allow vectors *with*
>> gaps throughout the SLP graph, since with predication it's simple to
>> ignore any inactive element where necessary. This is often much cheaper
>> than packing the active elements together to remove
On Tue, 30 Jun 2020, Richard Sandiford wrote:
> Sorry for the slow reponse…
No problem.
> Richard Biener writes:
> > This splits SLP load nodes with load permutation into a SLP
> > load node (with load "permutation" removing gaps) and a
> > lane permutation node. The first and foremost goal of
Sorry for the slow reponse…
Richard Biener writes:
> This splits SLP load nodes with load permutation into a SLP
> load node (with load "permutation" removing gaps) and a
> lane permutation node. The first and foremost goal of this
> is to be able to have a single SLP node for each load group
>
