Use POWER8 and POWER9 ISA enhancements to improve the performance of AES. Demonstrate why achieved performance is close to optimal for the platform. Optimized implementations in the Cryptogams repository[1] may serve as useful references. Financial bounty upon completion and community acceptance of patches.
Description
Description
Revisions and Commits
Revisions and Commits
| Status | Assigned | Task | ||
|---|---|---|---|---|
| Open | jukivili | T4460 libgcrypt performance TODOs | ||
| Resolved | jukivili | T4531 PowerPC performance improvements | ||
| Resolved | jukivili | T4529 libgcrypt: POWER AES Vector Acceleration |
Event Timeline
Comment Actions
Would the maintainers accept having perl in the repository? Linux does it.[1]
[1] https://github.com/torvalds/linux/blob/master/drivers/crypto/vmx/ghashp8-ppc.pl
Comment Actions
I don't know. That would make it a relatively easy transplant. We've also used the Cryptogams code as a reference for Golang enhancements, if that helps. I'd welcome guidance on the matter from a maintainer.
Comment Actions
I'm looking into doing a pretty epic hack of using the switch_endian syscall to speed this up.
Comment Actions
Perl would be okay for maintainer mode but not for regular builds. The reason is that perl is already used by autotools but a build shall still be possible w/o perl.
Comment Actions
Please do not change the priority back. That is a maintainer's task. I consider this along with adding replicas of issues to a bit rude.
Comment Actions
Patches for PowerPC AES acceleration sent to mailing-list, based partly on initial work by Shawn Landden (@slandden): https://lists.gnupg.org/pipermail/gcrypt-devel/2019-August/004788.html
Because there was license concerns with Cryptogams code (https://lists.gnupg.org/pipermail/gcrypt-devel/2019-July/004774.html), I decided to implemented missing parts for this myself.