We are running a survey to help us improve the experience for all of our members. If you see the survey appear, please take the time to tell us about your experience if you can.
Hi
I am porting an example code from neno intrinsic to helium intrinsic, it used the Transpose related intrinsic like (vtrn_u32/ vtrn_u8), how can do the transpose operation in helium, as there is no related intrinsic in helium.
Thanks.
Helium MVE (Matrix Vector Extension) is a microarchitecture extension to the CM85 and CM55 kernels on the Armv8.1-M architecture. Similar to Neon technology in Cortex-A devices, Helium provides a set of SIMD-like instructions.
Would you please tell me which helium intrinsic can do the transpose? thanks.
Have you seen this documentation?
https://developer.arm.com/documentation/102107a/0100/Floating-point-4x4-matrix-transposition
https://developer.arm.com/documentation/102107a/0100/Integer-8-bit-4x4-matrix-transposition