Implement device_gemm_universal_preshuffle_instance for RDNA4 (#3429)
* add device_gemm_wmma_cshuffle_v3_b_preshuffle.hpp * add examples * add instances to test * remove duplicate code between examples
Y
Yung-sheng Tu committed
6df2d70143c0c8934f3dd08ec7086d5fdff16499
Parent: e302079
Committed by GitHub <noreply@github.com>
on 1/15/2026, 3:19:31 PM