Re: [PATCH] Avoid epilogue peeling for x264 vectorization in x264_pixel_sad_x4_8x8

2019-05-06 Thread Richard Biener
On Mon, 6 May 2019, Jakub Jelinek wrote: > On Fri, May 03, 2019 at 12:47:39PM +0200, Richard Biener wrote: > > On Wed, Dec 12, 2018 at 11:54 AM Richard Biener wrote: > > > > > > > > > The following improves x264 vectorization by avoiding peeling for gaps > > > noticing that when the upper half of

Re: [PATCH] Avoid epilogue peeling for x264 vectorization in x264_pixel_sad_x4_8x8

2019-05-06 Thread Jakub Jelinek
On Fri, May 03, 2019 at 12:47:39PM +0200, Richard Biener wrote: > On Wed, Dec 12, 2018 at 11:54 AM Richard Biener wrote: > > > > > > The following improves x264 vectorization by avoiding peeling for gaps > > noticing that when the upper half of a vector is unused we can > > load the lower part onl

Re: [PATCH] Avoid epilogue peeling for x264 vectorization in x264_pixel_sad_x4_8x8

2019-05-03 Thread Richard Biener
On Wed, Dec 12, 2018 at 11:54 AM Richard Biener wrote: > > > The following improves x264 vectorization by avoiding peeling for gaps > noticing that when the upper half of a vector is unused we can > load the lower part only (and fill the upper half with zeros - this > is what x86 does automaticall

[PATCH] Avoid epilogue peeling for x264 vectorization in x264_pixel_sad_x4_8x8

2018-12-12 Thread Richard Biener
The following improves x264 vectorization by avoiding peeling for gaps noticing that when the upper half of a vector is unused we can load the lower part only (and fill the upper half with zeros - this is what x86 does automatically, GIMPLE doesn't allow us to leave the upper half undefined as RT