[clang] [flang] [llvm] [Clang][AMDGPU] Expose buffer load lds as a clang builtin (PR #132048)

[Matt Arsenault via llvm-commits]

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/132048 at github.com>


================
@@ -162,6 +162,8 @@ BUILTIN(__builtin_amdgcn_raw_buffer_load_b64, "V2UiQbiiIi", "n")
 BUILTIN(__builtin_amdgcn_raw_buffer_load_b96, "V3UiQbiiIi", "n")
 BUILTIN(__builtin_amdgcn_raw_buffer_load_b128, "V4UiQbiiIi", "n")
 
+TARGET_BUILTIN(__builtin_amdgcn_raw_ptr_buffer_load_lds, "vQbv*3IUiiiIiIi", "t", "lds-buffer-load-insts")
----------------
arsenm wrote:

Does this only support specific sizes on specific targets? Does the feature need to be split by size? 

https://github.com/llvm/llvm-project/pull/132048