| Commit message (Collapse) | Author | Age |
| |
|
| |
|
| |
|
| |
|
| |
|
| |
|
| |
|
| |
|
| |
|
| |
|
| |
|
| |
|
| |
|
| |
|
| |
|
| |
|
| |
|
| |
|
| |
|
| |
|
|\ |
|
| |
| |
| |
| | |
timings are getting bad
|
| | |
|
| | |
|
| | |
|
| | |
|
| | |
|
| |
| |
| |
| | |
in L1 (allows to keep packed rhs in L1)
|
| |
| |
| |
| |
| |
| | |
- permit to recompute a subset of changesets
- update changeset list
- add a few more cases
|
| |
| |
| |
| |
| |
| | |
by a more general one:
It consists in increasing the actual number of rows of lhs's micro horizontal panel for small depth such that L1 cache is fully exploited.
|
|/ |
|
|
|
|
| |
to that.
|
| |
|
|
|
|
| |
memory accesses to the destination matrix in the case of K-rank-update like products, i.e., for products of the kind: "large x small" * "small x large"
|
|
|
|
| |
instead of acos.
|
| |
|
| |
|
|
|
|
| |
and expected for consistency with other methods.
|
|\ |
|
| | |
|
| |
| |
| |
| | |
outer-index insertion strategies (bug #974)
|
| | |
|
| | |
|
| | |
|
| | |
|
| | |
|
| | |
|
| |
| |
| |
| | |
This is can be useful for non-floating point scalars, where choosing the biggest element is generally not the best choice.
|
|/ |
|
|
|
|
| |
intrinsics.
|