Field G. Van Zee 3f02af0905 Row storage optimizations to zen dotxf kernels. ...

Details:
- Split the main loop bodies of zen's [sd]dotxf kernels into two cases:
  one to handle a column-stored matrix A and one to handle a row-stored
  matrix A. This allows vector instructions to be employed even if A is
  stored by rows (and A^T appears stored as columns). Both storage cases
  use a common edge case loop. Thanks to Devin Matthews for this idea
  and for prototyping the change needed for sdotxf kernel.

2018-03-26 17:40:04 -05:00

..

1

Removed vzeroupper intrinsics from zen kenels.

2018-03-23 12:53:48 -05:00

1f

Row storage optimizations to zen dotxf kernels.

2018-03-26 17:40:04 -05:00

3

Applied 34b72a3 to non-active/unused microkernels.

2018-02-23 17:38:19 -06:00

bli_kernels_zen.h

Merge branch 'amd' into rt

2018-02-21 17:43:32 -06:00