[clang] [llvm] [AMDGPU] Asynchronous loads from global/buffer to LDS on pre-GFX12 (PR #180466)

Sameer Sahasrabuddhe via cfe-commits cfe-commits at lists.llvm.org
Mon Feb 9 02:05:54 PST 2026


================
@@ -0,0 +1,238 @@
+.. _amdgpu-async-operations:
+
+===============================
+ AMDGPU Asynchronous Operations
+===============================
+
+.. contents::
+   :local:
+
+Introduction
+============
+
+Asynchronous operations are memory transfers (usually between the global memory
+and LDS) that are completed independently at an unspecified scope. A thread that
----------------
ssahasra wrote:

These async operations are truly independent of each other as well, and not just the issuing thread. The current text deliberately specifies as little as possible.

https://github.com/llvm/llvm-project/pull/180466


More information about the cfe-commits mailing list