Sync HIP documentation 2025-10-20 (#1258)

* Add examples to tools folder
* Correct P2P memory access section
* Sync poriting guide
* Add HIP Graph tutorial
* Add hint about using amdgpu-dkms for IPC API
* Add a few more env variables

projects/hip/docs/reference/env_variables/debug_hip_env.rst

@@ -27,7 +27,7 @@ and :doc:`GPU isolation <rocm:conceptual/gpu-isolation>`.
       -
 
     * - | ``AMD_LOG_MASK``
-        | Specifies HIP log filters. Here is the ` complete list of log masks <https://github.com/ROCm/clr/blob/develop/rocclr/utils/debug.hpp#L40>`_.
+        | Specifies HIP log filters. Here is the `complete list of log masks <https://github.com/ROCm/rocm-systems/blob/develop/projects/clr/rocclr/utils/debug.hpp#L48>`_.
       - ``0x7FFFFFFF``
       - | 0x1: Log API calls.
         | 0x2: Kernel and copy commands and barriers.
@@ -49,8 +49,16 @@ and :doc:`GPU isolation <rocm:conceptual/gpu-isolation>`.
         | 0x20000: Memory allocation.
         | 0x40000: Memory pool allocation, including memory in graphs.
         | 0x80000: Timestamp details.
+        | 0x100000: Comgr path information print.
         | 0xFFFFFFFF: Log always even mask flag is zero.
 
+    * - | ``HIP_FORCE_DEV_KERNARG``
+        | Forces kernel arguments to be stored in device memory to reduce latency.
+        | Can improve performance by 2-3 µs for some kernels.
+      - ``1``
+      - | 0: Disable
+        | 1: Enable
+
     * - | ``HIP_LAUNCH_BLOCKING``
         | Used for serialization on kernel execution.
       - ``0``

projects/hip/docs/reference/env_variables/gpu_isolation_hip_env.rst

@@ -14,7 +14,7 @@ environment variables in HIP are collected in the following table.
     * - | ``ROCR_VISIBLE_DEVICES``
         | A list of device indices or UUIDs that will be exposed to applications.
       - :doc:`GPU isolation <rocm:conceptual/gpu-isolation>`, :doc:`Setting the number of compute units <rocm:how-to/setting-cus>`
-      - Example: ``0,GPU-DEADBEEFDEADBEEF``
+      - Example: ``0,GPU-4b2c1a9f-8d3e-6f7a-b5c9-2e4d8a1f6c3b``
 
     * - | ``GPU_DEVICE_ORDINAL``
         | Devices indices exposed to OpenCL and HIP applications.
@@ -25,3 +25,11 @@ environment variables in HIP are collected in the following table.
         | Device indices exposed to HIP applications.
       - :doc:`GPU isolation <rocm:conceptual/gpu-isolation>`, :doc:`HIP debugging <hip:how-to/debugging>`
       - Example: ``0,2``
+
+.. admonition:: Recommendation
+
+  * On Linux, use ``ROCR_VISIBLE_DEVICES``.
+
+  * On Windows, use ``HIP_VISIBLE_DEVICES``.
+
+  * For portability across different vendors, use ``CUDA_VISIBLE_DEVICES``.

projects/hip/docs/reference/env_variables/memory_management_hip_env.rst

@@ -55,6 +55,12 @@ pages:
       - | 0: Disable
         | 1: Enable
 
+    * - | ``GPU_SINGLE_ALLOC_PERCENT``
+        | Limits the maximum size of a single memory allocation as a percentage of GPU memory.
+      - ``100``
+      - | Unit: Percentage
+        | Prevents single allocations from consuming all available GPU memory.
+
     * - | ``GPU_MAX_HEAP_SIZE``
         | Set maximum size of the GPU heap to % of board memory.
       - ``100``

projects/hip/docs/reference/env_variables/miscellaneous_hip_env.rst

@@ -16,19 +16,19 @@ different features in HIP.
       - ``--gpu-architecture=gfx906:sramecc+:xnack``, ``-fgpu-rdc``
 
     * - | ``AMD_COMGR_SAVE_TEMPS``
-        | Controls the deletion of temporary files generated during the compilation of COMGR. These files do not appear in the current working directory, but are instead left in a platform-specific temporary directory.
+        | Controls the deletion of temporary files generated during the compilation of Comgr. These files do not appear in the current working directory, but are instead left in a platform-specific temporary directory.
       - Unset by default.
       - | 0: Temporary files are deleted automatically.
         | Non zero integer: Turn off the temporary files deletion.
 
     * - | ``AMD_COMGR_EMIT_VERBOSE_LOGS``
-        | Sets logging of COMGR to include additional Comgr-specific informational messages.
+        | Sets logging of Comgr to include additional Comgr-specific informational messages.
       - Unset by default.
       - | 0: Verbose log disabled.
         | Non zero integer: Verbose log enabled.
 
     * - | ``AMD_COMGR_REDIRECT_LOGS``
-        | Controls redirect logs of COMGR.
+        | Controls redirect logs of Comgr.
       - Unset by default.
       - | `stdout` / `-`: Redirected to the standard output.
         | `stderr`: Redirected to the error stream.