On Thu, Feb 14, 2019 at 1:30 PM Jason Ekstrand wrote:
>
> On Fri, Jan 18, 2019 at 6:09 PM Francisco Jerez wrote:
>>
>> Strides up to 32B can be implemented for the source regions of most
>> instructions by leveraging either the vertical or the horizontal
>> stride of the hardware Align1 region.
Jason Ekstrand writes:
> On Fri, Jan 18, 2019 at 6:09 PM Francisco Jerez
> wrote:
>
>> Strides up to 32B can be implemented for the source regions of most
>> instructions by leveraging either the vertical or the horizontal
>> stride of the hardware Align1 region. The main motivation for this
On Fri, Jan 18, 2019 at 6:09 PM Francisco Jerez
wrote:
> Strides up to 32B can be implemented for the source regions of most
> instructions by leveraging either the vertical or the horizontal
> stride of the hardware Align1 region. The main motivation for this is
> that currently the
Strides up to 32B can be implemented for the source regions of most
instructions by leveraging either the vertical or the horizontal
stride of the hardware Align1 region. The main motivation for this is
that currently the lower_integer_multiplication() pass will happily
double the stride of one