Merge amd-master into release/rocm-rel-6.2 20240710

Signed-off-by: Maisam Arif <[email protected]>
Change-Id: Ieb281513769476382881c4e8186f09091d950944

.readthedocs.yaml

@@ -15,6 +15,6 @@ python:
 build:
  os: ubuntu-22.04
  tools:
- python: "3.8"
+ python: "3.10"
  apt_packages:
  - "graphviz" # For dot graphs in doxygen

CHANGELOG.md

@@ -4,6 +4,41 @@ Full documentation for rocm_smi_lib is available at [https://rocm.docs.amd.com/]
 
 ***All information listed below is for reference and subject to change.***
 
+## rocm_smi_lib for ROCm 6.2
+
+### Added
+
+- **Added Partition ID API (`rsmi_dev_partition_id_get(..)`)** 
+Previously `rsmi_dev_partition_id_get` could only be retrived by querying through `rsmi_dev_pci_id_get()`
+and parsing optional bits in our python CLI/API. We are now making this available directly through API.
+As well as added testing, in our compute partitioning tests verifing partition IDs update accordingly. 
+
+### Changed
+
+- N/A
+
+### Optimized
+
+- N/A
+
+### Fixed
+
+- **Partition ID CLI output** 
+Due to driver changes in KFD, some devices may report bits [31:28] or [2:0]. With the newly added `rsmi_dev_partition_id_get(..)`, we provided this fallback to properly retreive partition ID. We
+plan to eventually remove partition ID from the function portion of the BDF (Bus Device Function). See below for PCI ID description.
+
+ - bits [63:32] = domain
+ - bits [31:28] or bits [2:0] = partition id 
+ - bits [27:16] = reserved
+ - bits [15:8] = Bus
+ - bits [7:3] = Device
+ - bits [2:0] = Function (partition id maybe in bits [2:0]) <-- Fallback for non SPX modes
+
+### Known Issues
+
+- N/A
+
+
 ## rocm_smi_lib for ROCm 6.1.2
 
 ### Added

CMakeLists.txt

@@ -38,7 +38,7 @@ find_program (GIT NAMES git)
 
 ## Setup the package version based on git tags.
 set(PKG_VERSION_GIT_TAG_PREFIX "rsmi_pkg_ver")
-get_package_version_number("7.2.0" ${PKG_VERSION_GIT_TAG_PREFIX} GIT)
+get_package_version_number("7.3.0" ${PKG_VERSION_GIT_TAG_PREFIX} GIT)
 message("Package version: ${PKG_VERSION_STR}")
 set(${ROCM_SMI_LIBS_TARGET}_VERSION_MAJOR "${CPACK_PACKAGE_VERSION_MAJOR}")
 set(${ROCM_SMI_LIBS_TARGET}_VERSION_MINOR "${CPACK_PACKAGE_VERSION_MINOR}")

DEBIAN/postinst.in

@@ -107,7 +107,7 @@ do_ldconfig() {
 case "$1" in
  ( configure )
  do_ldconfig
- do_configureLogrotate || return 0
+ do_configureLogrotate || exit 0
  ;;
  ( abort-upgrade | abort-remove | abort-deconfigure )
  echo "$1"

RPM/post.in

@@ -107,5 +107,5 @@ do_ldconfig() {
 # post install or upgrade, $i is 1 or 2 -> do these actions
 if [ "$1" -ge 1 ]; then
  do_ldconfig
- do_configureLogrotate || return 0
+ do_configureLogrotate || exit 0
 fi

docs/sphinx/requirements.in

@@ -1 +1 @@
-rocm-docs-core[api_reference]>=0.31.0
+rocm-docs-core[api_reference]==1.4.0

docs/sphinx/requirements.txt

@@ -1,130 +1,126 @@
 #
-# This file is autogenerated by pip-compile with Python 3.8
+# This file is autogenerated by pip-compile with Python 3.10
 # by the following command:
 #
 # pip-compile requirements.in
 #
-accessible-pygments==0.0.4
+accessible-pygments==0.0.5
  # via pydata-sphinx-theme
-alabaster==0.7.13
+alabaster==0.7.16
  # via sphinx
-babel==2.12.1
+babel==2.15.0
  # via
  # pydata-sphinx-theme
  # sphinx
-beautifulsoup4==4.12.2
+beautifulsoup4==4.12.3
  # via pydata-sphinx-theme
-breathe==4.34.0
+breathe==4.35.0
  # via rocm-docs-core
-certifi==2022.12.7
+certifi==2024.6.2
  # via requests
-cffi==1.15.1
+cffi==1.16.0
  # via
  # cryptography
  # pynacl
-charset-normalizer==3.1.0
+charset-normalizer==3.3.2
  # via requests
-click==8.1.3
+click==8.1.7
  # via
  # click-log
  # doxysphinx
  # sphinx-external-toc
 click-log==0.4.0
  # via doxysphinx
-cryptography==40.0.2
+cryptography==42.0.8
  # via pyjwt
-deprecated==1.2.13
+deprecated==1.2.14
  # via pygithub
-docutils==0.16
+docutils==0.21.2
  # via
  # breathe
  # myst-parser
  # pydata-sphinx-theme
  # sphinx
-doxysphinx==3.3.7
+doxysphinx==3.3.8
  # via rocm-docs-core
-fastjsonschema==2.18.0
+fastjsonschema==2.19.1
  # via rocm-docs-core
-gitdb==4.0.10
+gitdb==4.0.11
  # via gitpython
-gitpython==3.1.31
+gitpython==3.1.43
  # via rocm-docs-core
-idna==3.4
+idna==3.7
  # via requests
 imagesize==1.4.1
  # via sphinx
-importlib-metadata==6.4.1
- # via sphinx
-importlib-resources==5.10.4
- # via rocm-docs-core
-jinja2==3.1.2
+jinja2==3.1.4
  # via
  # myst-parser
  # sphinx
 libsass==0.22.0
  # via doxysphinx
-lxml==4.9.2
+lxml==4.9.4
  # via doxysphinx
-markdown-it-py==2.2.0
+markdown-it-py==3.0.0
  # via
  # mdit-py-plugins
  # myst-parser
-markupsafe==2.1.2
+markupsafe==2.1.5
  # via jinja2
-mdit-py-plugins==0.3.5
+mdit-py-plugins==0.4.1
  # via myst-parser
 mdurl==0.1.2
  # via markdown-it-py
-mpire==2.8.0
+mpire==2.10.2
  # via doxysphinx
-myst-parser==1.0.0
+myst-parser==3.0.1
  # via rocm-docs-core
-packaging==23.1
+numpy==1.26.4
+ # via doxysphinx
+packaging==24.1
  # via
  # pydata-sphinx-theme
  # sphinx
-pycparser==2.21
+pycparser==2.22
  # via cffi
-pydata-sphinx-theme==0.13.3
+pydata-sphinx-theme==0.15.3
  # via
  # rocm-docs-core
  # sphinx-book-theme
-pygithub==1.58.1
+pygithub==2.3.0
  # via rocm-docs-core
-pygments==2.15.0
+pygments==2.18.0
  # via
  # accessible-pygments
  # mpire
  # pydata-sphinx-theme
  # sphinx
-pyjson5==1.6.4
+pyjson5==1.6.6
  # via doxysphinx
-pyjwt[crypto]==2.6.0
+pyjwt[crypto]==2.8.0
  # via pygithub
 pynacl==1.5.0
  # via pygithub
-pyparsing==3.0.9
+pyparsing==3.1.2
  # via doxysphinx
-pytz==2023.3.post1
- # via babel
-pyyaml==6.0
+pyyaml==6.0.1
  # via
  # myst-parser
  # rocm-docs-core
  # sphinx-external-toc
-requests==2.28.2
+requests==2.32.3
  # via
  # pygithub
  # sphinx
-rocm-docs-core[api_reference]>=0.31.0
+rocm-docs-core[api-reference]==1.4.0
  # via -r requirements.in
-smmap==5.0.0
+smmap==5.0.1
  # via gitdb
 snowballstemmer==2.2.0
  # via sphinx
-soupsieve==2.4.1
+soupsieve==2.5
  # via beautifulsoup4
-sphinx==5.3.0
+sphinx==7.3.7
  # via
  # breathe
  # myst-parser
@@ -135,37 +131,39 @@ sphinx==5.3.0
  # sphinx-design
  # sphinx-external-toc
  # sphinx-notfound-page
-sphinx-book-theme==1.0.1
+sphinx-book-theme==1.1.3
  # via rocm-docs-core
-sphinx-copybutton==0.5.1
+sphinx-copybutton==0.5.2
  # via rocm-docs-core
-sphinx-design==0.3.0
+sphinx-design==0.6.0
  # via rocm-docs-core
-sphinx-external-toc==0.3.1
+sphinx-external-toc==1.0.1
  # via rocm-docs-core
-sphinx-notfound-page==0.8.3
+sphinx-notfound-page==1.0.2
  # via rocm-docs-core
-sphinxcontrib-applehelp==1.0.4
+sphinxcontrib-applehelp==1.0.8
  # via sphinx
-sphinxcontrib-devhelp==1.0.2
+sphinxcontrib-devhelp==1.0.6
  # via sphinx
-sphinxcontrib-htmlhelp==2.0.1
+sphinxcontrib-htmlhelp==2.0.5
  # via sphinx
 sphinxcontrib-jsmath==1.0.1
  # via sphinx
-sphinxcontrib-qthelp==1.0.3
+sphinxcontrib-qthelp==1.0.7
  # via sphinx
-sphinxcontrib-serializinghtml==1.1.5
+sphinxcontrib-serializinghtml==1.1.10
  # via sphinx
-tqdm==4.66.1
+tomli==2.0.1
+ # via sphinx
+tqdm==4.66.4
  # via mpire
-typing-extensions==4.5.0
- # via pydata-sphinx-theme
-urllib3==1.26.18
- # via requests
-wrapt==1.15.0
- # via deprecated
-zipp==3.17.0
+typing-extensions==4.12.2
+ # via
+ # pydata-sphinx-theme
+ # pygithub
+urllib3==2.2.1
  # via
- # importlib-metadata
- # importlib-resources
+ # pygithub
+ # requests
+wrapt==1.16.0
+ # via deprecated

include/rocm_smi/rocm_smi.h

@@ -367,8 +367,6 @@ typedef rsmi_clk_type_t rsmi_clk_type;
  */
 typedef enum {
  RSMI_COMPUTE_PARTITION_INVALID = 0,
- RSMI_COMPUTE_PARTITION_CPX, //!< Core mode (CPX)- Per-chip XCC with
- //!< shared memory
  RSMI_COMPUTE_PARTITION_SPX, //!< Single GPU mode (SPX)- All XCCs work
  //!< together with shared memory
  RSMI_COMPUTE_PARTITION_DPX, //!< Dual GPU mode (DPX)- Half XCCs work
@@ -377,6 +375,8 @@ typedef enum {
  //!< work together with shared memory
  RSMI_COMPUTE_PARTITION_QPX, //!< Quad GPU mode (QPX)- Quarter XCCs
  //!< work together with shared memory
+ RSMI_COMPUTE_PARTITION_CPX //!< Core mode (CPX)- Per-chip XCC with
+ //!< shared memory
 } rsmi_compute_partition_type_t;
 /// \cond Ignore in docs.
 typedef rsmi_compute_partition_type_t rsmi_compute_partition_type;
@@ -4053,6 +4053,30 @@ rsmi_dev_compute_partition_set(uint32_t dv_ind,
  */
 rsmi_status_t rsmi_dev_compute_partition_reset(uint32_t dv_ind);
 
+/**
+ * @brief Retrieves the partition_id for a desired device
+ *
+ * @details
+ * Given a device index @p dv_ind and a uint32_t pointer @p partition_id ,
+ * this function will attempt to obtain the device's partition ID.
+ * Upon successful retreival, the obtained device's partition will be stored
+ * in the passed @p partition_id uint32_t variable. If device does
+ * not support partitions or is in SPX, a @p partition_id ID of 0 shall
+ * be returned.
+ *
+ * @param[in] dv_ind a device index
+ *
+ * @param[inout] partition_id a uint32_t variable,
+ * which the device's partition_id will be written to.
+ *
+ * @retval ::RSMI_STATUS_SUCCESS call was successful
+ * @retval ::RSMI_STATUS_INVALID_ARGS the provided arguments are not valid
+ * @retval ::RSMI_STATUS_NOT_SUPPORTED installed software or hardware does not
+ * support this function
+ *
+ */
+rsmi_status_t rsmi_dev_partition_id_get(uint32_t dv_ind, uint32_t *partition_id);
+
 /** @} */ // end of ComputePartition
 
 /*****************************************************************************/

include/rocm_smi/rocm_smi_utils.h

@@ -240,7 +240,7 @@ class ScopeGuard {
  __forceinline ~ScopeGuard() {
  if (!dismiss_) release_();
  }
- __forceinline ScopeGuard& operator=(const ScopeGuard& rhs) {
+ __forceinline ScopeGuard& operator=(ScopeGuard& rhs) {
  dismiss_ = rhs.dismiss_;
  release_ = rhs.release_;
  rhs.dismiss_ = true;