Re: [PATCH] Fix PR90332 by extending half size vector mode

2020-03-19 Thread Segher Boessenkool
Hi! On Thu, Mar 19, 2020 at 09:18:06AM +0100, Richard Biener wrote: > On Wed, Mar 18, 2020 at 8:34 PM Segher Boessenkool > wrote: > > We don't have ops on short integer types, either, for similar reasons. > > How do you represent two vector input shuffles? The usual > way is (vec_select

Re: [PATCH] Fix PR90332 by extending half size vector mode

2020-03-19 Thread Richard Biener via Gcc-patches
On Wed, Mar 18, 2020 at 8:34 PM Segher Boessenkool wrote: > > On Wed, Mar 18, 2020 at 10:12:00PM +0800, Kewen.Lin wrote: > > > Btw, why not implement the neccessary vector init patterns? > > > > Power doesn't support 64bit vector size, it looks a bit hacky and > > confusing to introduce this kind

Re: [PATCH] Fix PR90332 by extending half size vector mode

2020-03-18 Thread Segher Boessenkool
On Wed, Mar 18, 2020 at 10:12:00PM +0800, Kewen.Lin wrote: > > Btw, why not implement the neccessary vector init patterns? > > Power doesn't support 64bit vector size, it looks a bit hacky and > confusing to introduce this kind of mode just for some optab requirement, > but I admit the optab hack

Re: [PATCH] Fix PR90332 by extending half size vector mode

2020-03-18 Thread Richard Biener via Gcc-patches
On Wed, Mar 18, 2020 at 2:56 PM Kewen.Lin wrote: > > Hi Richi, > > Thanks for your comments. > > on 2020/3/18 下午6:39, Richard Biener wrote: > > On Wed, Mar 18, 2020 at 11:06 AM Kewen.Lin wrote: > >> > >> Hi, > >> > >> As PR90332 shows, the current scalar epilogue peeling for gaps > >>

Re: [PATCH] Fix PR90332 by extending half size vector mode

2020-03-18 Thread Kewen.Lin via Gcc-patches
on 2020/3/18 下午6:40, Richard Biener wrote: > On Wed, Mar 18, 2020 at 11:39 AM Richard Biener > wrote: >> >> On Wed, Mar 18, 2020 at 11:06 AM Kewen.Lin wrote: >>> >>> Hi, >>> >>> As PR90332 shows, the current scalar epilogue peeling for gaps >>> elimination requires expected vec_init optab with

Re: [PATCH] Fix PR90332 by extending half size vector mode

2020-03-18 Thread Kewen.Lin via Gcc-patches
Hi Richi, Thanks for your comments. on 2020/3/18 下午6:39, Richard Biener wrote: > On Wed, Mar 18, 2020 at 11:06 AM Kewen.Lin wrote: >> >> Hi, >> >> As PR90332 shows, the current scalar epilogue peeling for gaps >> elimination requires expected vec_init optab with two half size >> vector mode.

Re: [PATCH] Fix PR90332 by extending half size vector mode

2020-03-18 Thread Richard Biener via Gcc-patches
On Wed, Mar 18, 2020 at 11:39 AM Richard Biener wrote: > > On Wed, Mar 18, 2020 at 11:06 AM Kewen.Lin wrote: > > > > Hi, > > > > As PR90332 shows, the current scalar epilogue peeling for gaps > > elimination requires expected vec_init optab with two half size > > vector mode. On Power, we don't

Re: [PATCH] Fix PR90332 by extending half size vector mode

2020-03-18 Thread Richard Biener via Gcc-patches
On Wed, Mar 18, 2020 at 11:06 AM Kewen.Lin wrote: > > Hi, > > As PR90332 shows, the current scalar epilogue peeling for gaps > elimination requires expected vec_init optab with two half size > vector mode. On Power, we don't support vector mode like V8QI, > so can't support optab like

[PATCH] Fix PR90332 by extending half size vector mode

2020-03-18 Thread Kewen.Lin via Gcc-patches
Hi, As PR90332 shows, the current scalar epilogue peeling for gaps elimination requires expected vec_init optab with two half size vector mode. On Power, we don't support vector mode like V8QI, so can't support optab like vec_initv16qiv8qi. But we want to leverage existing scalar mode like DI