Hi Chen,
Thanks for the feedback. Will do the possible changes.
On Thu, Mar 7, 2019 at 4:37 PM Niranjankumar Balasubramanian <
niran...@multicorewareinc.com> wrote:
> Hi Chen,
> Thanks for your suggestions. Your feedback is noted.
>
> On Thu, Mar 7, 2019 at 3:41 PM chen wrote:
>
>> Just say it
Hi Chen,
Thanks for your suggestions. Your feedback is noted.
On Thu, Mar 7, 2019 at 3:41 PM chen wrote:
> Just say it works.
>
> First at all,
> The expect algorithm is square of (x >> shift)
> It is 8 bits (I assume we talk with 8bpp, the 16bpp are similar) multiple
> of 8-bits and result is
Just say it works.
First at all,
The expect algorithm is square of (x >> shift)
It is 8 bits (I assume we talk with 8bpp, the 16bpp are similar) multiple of
8-bits and result is 16 bits.
The function works on CU-level, the blockSize is up to 64 only, or call 6-bits.
So, we can decide the
# HG changeset patch
# User Akil Ayyappan
# Date 1551693998 -19800
# Mon Mar 04 15:36:38 2019 +0530
# Node ID 19f27e0c8a6f8250af5e2f7c7984dc3b57bea7e4
# Parent d12a4caf7963fd47d646040689ad5f02754ad879
x86: normFactor primitive
This patch adds AVX2 assembly for this primitive.
Pushed to
# HG changeset patch
# User Akil Ayyappan
# Date 1551693998 -19800
# Mon Mar 04 15:36:38 2019 +0530
# Node ID 19f27e0c8a6f8250af5e2f7c7984dc3b57bea7e4
# Parent d12a4caf7963fd47d646040689ad5f02754ad879
x86: normFactor primitive
This patch adds AVX2 assembly for this primitive.
