From e70f622798e08ccf9149766d41b6f405f39b4aa8 Mon Sep 17 00:00:00 2001
From: Bernhard Manfred Gruber <bernhardmgruber@gmail.com>
Date: Thu, 25 Apr 2024 17:09:03 +0200
Subject: [PATCH] Document NVTX ranges in CUB device algorithms

---
 cub/docs/developer_overview.rst | 13 +++++++++++++
 1 file changed, 13 insertions(+)

diff --git a/cub/docs/developer_overview.rst b/cub/docs/developer_overview.rst
index 106c51cd4f4..dc97b3854e1 100644
--- a/cub/docs/developer_overview.rst
+++ b/cub/docs/developer_overview.rst
@@ -744,3 +744,16 @@ contains hidden visibility attribute.
 
 To satisfy (3), CUB symbols are placed inside an inline namespace containing the set of
 GPU architectures for which the TU is being compiled.
+
+
+NVTX
+************************************
+
+The `NVIDIA Tools Extension SDK (NVTX) <https://nvidia.github.io/NVTX/>`_ is a cross-platform API
+for annotating source code to provide contextual information to developer tools.
+All device-scope algorithms in CUB are annotated with NVTX ranges,
+allowing their start and stop to be visualized in profilers
+like `NVIDIA Nsight Systems <https://developer.nvidia.com/nsight-systems>`_.
+Only the public APIs available in the ``<cub/device/device_xxx.cuh>`` headers are annotated,
+excluding direct calls to the dispatch layer.
+NVTX annotations can be disabled by defining ``NVTX_DISABLE`` during compilation.