It seems that -O3 might be causing intermittent problems with the f2c'ed packed and banded code. -O3 is retained for kernel code. Fixes#341 and fixes#342.
Updates and fixes to power9 subconfig.
Details:
- Register s,c,z reference gemm and trsm ukernels that assume elements
of B have been broadcast.
- Added prototypes for level-3 ukernels that assume elements of B have
been broadcast. Also added prototype for an spackm function that
employs a duplication/broadcast factor of 4.
- Register virtual gemmtrsm ukernels that work with broadcasting of B.
- Disable right-side hemm, symm, trmm, and trmm3 in bli_family_power9.h.
- Thanks to Nicholai Tukanov for providing these updates.
Implemented and registered power9 dgemm ukernel.
Details:
- Implemented 12x6 dgemm microkernel for power9. This microkernel
assumes that elements of B have been duplicated/broadcast during the
packing step. The microkernel uses a column orientation for its
microtile vector registers and thus implements column storage and
general stride IO cases. (A row storage IO case via in-register
transposition may be added at a future date.) It should be noted that
we recommend using this microkernel with gcc and *not* xlc, as issues
with the latter cropped up during development, including but not
limited to slightly incompatible vector register mnemonics in the GNU
extended inline assembly clobber list.
Formally registered power9 sub-configuration.
Details:
- Added and registered power9 sub-configuration into the build system.
Thanks to Nicholai Tukanov and Devangi Parikh for these contributions.
- Note: The sub-configuration does not yet have a corresponding
architecture-specific kernel set registered, and so for now the
sub-config is using the generic kernel set.
