Field G. Van Zee df80acf517 Fixed computation of b_next in L3 macro-kernels. ...

Details:
- Restructured herk_l and herk_u macro-kernels in the imagine of trmm
  and trsm, in that the edge cases are captured by the main loop, rather
  than trying to have "cleanup" sections that result in four distinct
  parts (interior, bottom edge, right edge, bottom-right edge) of the
  code.
- Fixed the way b_next was being computed in the non-gemm level-3
  macro-kernels (herk, trmm, trsm). The way they are computed now matches
  that of gemm.

2013-04-23 19:43:23 -05:00

..

0

Fixed overzealous type-checking in bli_getsc().

2013-04-16 11:24:03 -05:00

1

Allow ldim of packed micro-panels != MR, NR.

2013-04-21 15:00:24 -05:00

1d

Migrated 'bl2' prefix to 'bli'.

2013-03-24 20:01:49 -05:00

1f

Migrated 'bl2' prefix to 'bli'.

2013-03-24 20:01:49 -05:00

1m

Allow ldim of packed micro-panels != MR, NR.

2013-04-21 15:00:24 -05:00

2

Formatting change to mods in previous commit.

2013-04-15 14:40:31 -05:00

3

Fixed computation of b_next in L3 macro-kernels.

2013-04-23 19:43:23 -05:00

base

Added code for backward edge-case blocking.

2013-04-23 11:12:33 -05:00

cntl

Migrated 'bl2' prefix to 'bli'.

2013-03-24 20:01:49 -05:00

compat

Fixed bug in compatibility layer (her2k/syr2k).

2013-04-19 15:26:29 -05:00

include

Added a_next, b_next arguments to micro-kernels.

2013-04-23 16:00:18 -05:00

util

Updated dupl implementation to use PACKNR and NR.

2013-04-22 19:00:43 -05:00