Skip to content

[S390x] Optimize Poly1305 based on radix 2^44 with fat build support

Maamoun TK requested to merge mamonet/nettle:s390x-poly into master

This patch optimizes Poly1305 for s390x architecture by utilizing Z14-specific instruction vmslg for full 64-bit multiplication applied on 4-blocks at parallel based on radix 2^44

testsuite passes all tests of this patch.

Benchmark of poly1305 update using nettle-benchmark on z15

C This patch
656.83 Mbyte/s 5852.57 Mbyte/s
Edited by Maamoun TK

Merge request reports