[llvm] [NVPTX] Add tcgen05 alloc/dealloc intrinsics (PR #124961)

[Artem Belevich via llvm-commits]

================
@@ -962,6 +962,109 @@ The ``griddepcontrol`` intrinsics allows the dependent grids and prerequisite gr
 For more information, refer 
 `PTX ISA <https://docs.nvidia.com/cuda/parallel-thread-execution/#parallel-synchronization-and-communication-instructions-griddepcontrol>`__.
 
+TCGEN05 family of Intrinsics
+----------------------------
+
+The llvm.nvvm.tcgen05.* intrinsics model the TCGEN05 family of instructions
+exposed by PTX. These intrinsics use 'Tensor Memory' (henceforth ``tmem``).
+NVPTX represents this memory using ``addrspace(6)`` and is always 32-bits.
+
+For more information, refer PTX ISA
+`<https://docs.nvidia.com/cuda/parallel-thread-execution/#tensor-memory>`_.
+
+The tensor-memory pointers may only be used with the tcgen05 intrinsics.
+There are specialized load/store instructions provided (tcgen05.ld/st) to
+work with tensor-memory.
+
+For more information on tensor-memory load/store instructions, refer
----------------
Artem-B wrote:

Edit: "For more information ..., "  "see" or "refer to".

https://github.com/llvm/llvm-project/pull/124961