[all-commits] [llvm/llvm-project] 332b73: [AMDGPU] Revert wide LDS DMA support.

[Stanislav Mekhanoshin via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: 332b73fe12c6b383168e03eddd92020d38bc7583
      https://github.com/llvm/llvm-project/commit/332b73fe12c6b383168e03eddd92020d38bc7583
  Author: Stanislav Mekhanoshin <Stanislav.Mekhanoshin at amd.com>
  Date:   2022-05-16 (Mon, 16 May 2022)

  Changed paths:
    M llvm/lib/Target/AMDGPU/BUFInstructions.td
    M llvm/test/MC/AMDGPU/mubuf.s

  Log Message:
  -----------
  [AMDGPU] Revert wide LDS DMA support.

This reverts ffbee7acdcaaf, see also bug 37653 which it was fixing.
The bug claims this is an undocumented feature which actually works.
In the reality it is documented as not working for a good reason.
It likely does something, but it is useless anyway. These instructions
write into the LDS. The LDS address is:

M0 + inst_offset + (TIDinWave * 4).

For a store wider than a DWORD neighboring lanes will overwrite each
other.

Differential Revision: https://reviews.llvm.org/D125409