[llvm] [AMDGPU][GFX12] Restrict scalar subword loads to PAL (PR #117576)
Matt Arsenault via llvm-commits
llvm-commits at lists.llvm.org
Tue Nov 26 07:21:01 PST 2024
Juan Manuel Martinez =?utf-8?q?Caamaño?= <juamarti at amd.com>,
Juan Manuel Martinez =?utf-8?q?Caamaño?= <juamarti at amd.com>,
Juan Manuel Martinez =?utf-8?q?Caamaño?= <juamarti at amd.com>
Message-ID:
In-Reply-To: <llvm.org/llvm/llvm-project/pull/117576 at github.com>
arsenm wrote:
The backend should only reason about IR and we have an intrinsic to produce a buffer descriptor. You also could always produce the buffer-as-vector elements
https://github.com/llvm/llvm-project/pull/117576
More information about the llvm-commits
mailing list