[Bug] Numeric error happens only at few lines and wg1

[120L021326]

No description provided.

[120L021326]

kernel name: mla_decode_latent_sharedZ_ws_dim2_2K_txl_change

[deciding]

1. "An mbarrier object is used to synchronize threads and asynchronous memory operations."
   use named barrier otherwise
   see cp.async (can be in syntax or separate), wgmma.async, st.async
   ref
2. if the compiler not aware of a smem change before wgmma, we must manually add fence
   "...fence.proxy.async operation to make the generic proxy operations visible to the async proxy."
   ref