[PATCH v2 01/14] half_rsqrt: Cleanup implementation

Passes CTS on carrizo
v2: Use full precision implementation

Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu>

Passes CTS on carrizo
v2: Use full precision implementation

Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu>

Passes CTS on carrizo
v2: Use full precision implementation

Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu>

Passes CTS on carrizo
v2: Use full precision implementation

Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu>

Passes CTS on carrizo
v2: Use full precision implementation

Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu>

Passes CTS on carrizo
v2: Use full precision implementation

Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu>

Passes CTS on carrizo
v2: Use full precision implementation

Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu>

Passes CTS on carrizo
v2: Use full precision implementation

Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu>

Passes CTS on carrizo
v2: Use full precision implementation

Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu>

Passes CTS on carrizo
v2: Use full precision implementation

Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu>

Passes CTS on carrizo
v2: Use full precision implementation

Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu>

v2: Use full precision implementation

Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu>

Passes CTS on carrizo
v2: Use full precision implementation

Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu>

v2: Use full precision implementation

Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu>

This whole patch set LGTM.

v2: Use full precision implementation

Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu>
---
Fails CTS as well. It should probably be left out for now.

I don’t have any issues with committing this, as the real failure is not in this code.

Jeroen

Passes CTS on carrizo
v2: Use full precision implementation
v3: Use log2 + exp2 formula instead of full precision powr

Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu>

This whole patch set LGTM.

thanks for quick review

>
> v2: Use full precision implementation
>
> Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu>
> ---
> Fails CTS as well. It should probably be left out for now.

I don’t have any issues with committing this, as the real failure is not in this code.

I've posted a workaround that passes the CTS. I'm not sure which
version is preferable. since the workaround clearly hides an issue in
the original powr implementation.

Jan

> This whole patch set LGTM.

thanks for quick review

>
> >
> > v2: Use full precision implementation
> >
> > Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu>
> > ---
> > Fails CTS as well. It should probably be left out for now.
>
> I don’t have any issues with committing this, as the real failure is not in this code.

Hi Jeroen,

would you prefer this version(v2) for consistency, or v3?

thanks,
Jan

This whole patch set LGTM.

thanks for quick review

v2: Use full precision implementation

Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu>

Fails CTS as well. It should probably be left out for now.

I don’t have any issues with committing this, as the real failure is not in this code.

Hi Jeroen,

would you prefer this version(v2) for consistency, or v3?

Personally, I would just go for v2.

Jeroen