Closed daniel-hu-arm closed 2 years ago
This patch optimize the sm3-mb algorithm using the SVE feature of aarch64. SVE is optional feature for ARM v8
Tested on modern micro-architecture, it shows an 39% uplift in performance over neon
Signed-off-by: Daniel Hu Daniel.Hu@arm.com
Is there more of these coming?
yes, will have more. but perhaps we will hold until the pending PRs are cleared.
integrated
This patch optimize the sm3-mb algorithm using the SVE feature of aarch64. SVE is optional feature for ARM v8
Tested on modern micro-architecture, it shows an 39% uplift in performance over neon
Signed-off-by: Daniel Hu Daniel.Hu@arm.com