Fix links

ROCm · Dec 11, 2024 · aa33268 · aa33268
1 parent 1d412e1
commit aa33268
Show file tree

Hide file tree

Showing 3 changed files with 5 additions and 5 deletions.
diff --git a/docs/faq.rst b/docs/faq.rst
@@ -77,7 +77,7 @@ HIP offers several benefits over OpenCL:
 * Porting from CUDA to HIP is significantly easier than from CUDA to OpenCL.
 * HIP uses development tools specialized for each platform: :doc:`amdclang++ <llvm-project:index>`
   for AMD GPUs or `nvcc <https://docs.nvidia.com/cuda/cuda-compiler-driver-nvcc/index.html>`_
-  for NVIDIA GPUs, and profilers like :doc:`omniperf <omniperf:index>` or
+  for NVIDIA GPUs, and profilers like :doc:`ROCm Compute Profiler <rocprofiler-compute:index>` or
   `Nsight Systems <https://developer.nvidia.com/nsight-systems>`_.
 * HIP provides
   * pointers and host-side pointer arithmetic.

diff --git a/docs/how-to/hip_runtime_api/memory_management/unified_memory.rst b/docs/how-to/hip_runtime_api/memory_management/unified_memory.rst
@@ -121,7 +121,7 @@ Unified memory allocators
 
 Support for the different unified memory allocators depends on the GPU
 architecture and on the system. For more information, see :ref:`unified memory
-system requirements` and :ref:`checking unified memory management support`.
+system requirements` and :ref:`checking unified memory support`.
 
 - **HIP allocated managed memory and variables**
 
@@ -227,14 +227,14 @@ functions on ROCm and CUDA, both with and without HMM support.
         - pinned host
         - zero copy [zc]_
 
-.. _checking unified memory support:
-
 .. [zc] Zero copy is a feature, where the memory is pinned to either the device
         or the host, and won't be transferred when accessed by another device or
         the host. Instead only the requested memory is transferred, without
         making an explicit copy, like a normal memory access, hence the term
         "zero copy".
 
+.. _checking unified memory support:
+
 Checking unified memory support
 --------------------------------------------------------------------------------
 

diff --git a/docs/reference/cpp_language_extensions.rst b/docs/reference/cpp_language_extensions.rst
@@ -97,7 +97,7 @@ When using ``hipLaunchKernelGGL``, your first five parameters must be:
   * ``size_t dynamicShared``: The amount of additional shared memory that you want to allocate
     when launching the kernel (see :ref:`shared-variable-type`).
   * ``hipStream_t``: The stream where you want to run the kernel. A value of ``0`` corresponds to the
-    NULL stream (see :ref:`synchronization functions`).
+    NULL stream (see :ref:`synchronization_functions`).
 
 You can include your kernel arguments after these parameters.