[clang] [Clang][AMDGPU] Add __builtin_amdgcn_s_buffer_load_<T> (PR #203352)

[Shilei Tian via cfe-commits]

================
@@ -676,3 +676,42 @@ def DocTensorStoreFromLDS_GFX1250 : Documentation {
 Asynchronously copies a tensor from LDS into global memory.
 }];
 }
+
+//===----------------------------------------------------------------------===//
+// S-Buffer Load Builtins
+//===----------------------------------------------------------------------===//
+
+def DocCatSBufferLoad : DocumentationCategory<"S-Buffer Load Builtins"> {
+  let Content = [{
+These builtins lower to ``llvm.amdgcn.s.buffer.load`` and issue an
+``s_buffer_load`` when the byte offset is uniform across the wavefront.
+When the offset is divergent, the backend may lower to a ``buffer_load``.
----------------
shiltian wrote:

FWIW, reStructuredText has its own way for warning.

https://github.com/llvm/llvm-project/pull/203352