SWDEV-335697- Add support for dynamic partitioning

Original updates:
    * Added .gitignore to help with future commits
    * Updated/added copyrights on modified or added files
    * Updated rocm_smi.h/.cc
      - Added 3 new SMI API functions:
          rsmi_dev_compute_partition_set &
          rsmi_dev_compute_partition_get
      - Added helpful maps/enums used in
        new get/set compute_partition API calls
    * Updated rocm_smi.py
      - Added --showcomputepartition
      - Added --setcomputepartition
      - Fixed a few mistypes
    * Updated rsmiBindings.py - added helpful class/dict/list
    * Updated rocm_smi_example.cc
      - Added helpful MACRO to detect if api is not supported.
      - Added current_compute_partition set/get rocm lib calls
      - Added helpful macro to discover future RSMI errors
      - Commented out test_set_freq, was having permission issues
        on a Navi21
    * Updated rocm_smi_main.cc
      - Added helpful map to debug API calls, left in for future use
      - Added comment to better understand a non-class function returns
    * Added computepartition_read_write.cc/.h
      - Added get/set compute partition API test calls
      - Confirmed on devices that do not support the API calls, tests pass
    * Updated rocm_smi_test/main.cc
      - Calls new compute partition gtests

Added following updates from review feedback:
   * Updated rocm_smi.h/cc
       - Removed C++ API calls, adding support for both C/C++
         API calls could cause confusion and adds extra work for us
       - rsmi_dev_compute_partition_get -> Fixed an edge case where
         user gives a small buffer length size (smaller than data
         received), but does not receive the partial buffer back.
         google Tests are updated to reflect this find.
   * Updated rocm_smi_example.cc
       - Fixed test_set_freq, issue was that file was not writable.
         We now indicate this warning, so prior errors make sense.
       - General test code cleanup. Removed extra code,
         by creating loops for tests.
   * Updated rocm_smi_main.cc
     - Moved and got rid of an external reference to a map used
       for debugging RSMI enums, now is a const public reference.
   * Updated rocm_smi.py
     - Updated python code to identify NOT_SUPPORTED due to
       (currently) only a few GPU support the feature

Change-Id: I4a567acbb59d6771fb64df08d19175fe3604fd1b

.gitignore

@@ -0,0 +1,124 @@
+#
+# NOTE! Don't add files that are generated in specific
+# subdirectories here. Add them in the ".gitignore" file
+# in that subdirectory instead.
+#
+# NOTE! Please use 'git ls-files -i --exclude-standard'
+# command after changing this file, to see if there are
+# any tracked files which get ignored after the change.
+#
+# Normal rules
+#
+.*
+*.o
+*.o.*
+*.a
+*.s
+*.ko
+*.so
+*.so.dbg
+*.mod.c
+*.i
+*.lst
+*.symtypes
+*.order
+modules.builtin
+*.elf
+*.bin
+*.gz
+*.bz2
+*.lzma
+*.xz
+*.lzo
+#*.patch
+*.gcno
+*.pyc
+*current_compute_partition
+
+#
+# Top-level generic files/folders
+#
+/[Bb][Ui][Ll][Dd]
+*/[Bb][Ui][Ll][Dd]
+/build
+*/build
+/[Gg][Tt][Ee][Ss][Tt][Ss]
+*/[Gg][Tt][Ee][Ss][Tt][Ss]
+/tags
+/TAGS
+/linux
+/vmlinux
+/vmlinuz
+/System.map
+/Module.markers
+Module.symvers
+
+#
+# Debian directory (make deb-pkg)
+#
+/debian/
+
+#
+# git files that we don't want to ignore even it they are dot-files
+#
+!.gitignore
+!.mailmap
+
+### VisualStudioCode ###
+!.vscode/settings.json
+
+#
+# Generated include files
+#
+include/config
+include/linux/version.h
+include/generated
+arch/*/include/generated
+
+# git generated dirs
+patches-*
+
+# quilt's files
+patches
+series
+
+# cscope files
+cscope.*
+ncscope.*
+
+# gnu global files
+GPATH
+GRTAGS
+GSYMS
+GTAGS
+
+*.orig
+*~
+\#*#
+
+#
+# Leavings from module signing
+#
+extra_certificates
+signing_key.priv
+signing_key.x509
+x509.genkey
+
+#cmake files
+CMakeLists.txt.user
+CMakeCache.txt
+CMakeFiles
+CMakeScripts
+Testing
+Makefile
+cmake_install.cmake
+install_manifest.txt
+compile_commands.json
+CTestTestfile.cmake
+_deps
+
+#
+# ROCm files
+# Removes generated config headers like rocmsmi64Config.h & oamConfig.h
+#
+*Config.h

include/rocm_smi/rocm_smi.h

@@ -3,7 +3,7 @@
  * The University of Illinois/NCSA
  * Open Source License (NCSA)
  *
- * Copyright (c) 2017, Advanced Micro Devices, Inc.
+ * Copyright (c) 2017-2023, Advanced Micro Devices, Inc.
  * All rights reserved.
  *
  * Developed by:
@@ -352,6 +352,26 @@ typedef enum {
 typedef rsmi_clk_type_t rsmi_clk_type;
 /// \endcond
 
+/**
+ * Compute Partition types
+ */
+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
+                                      //!< together with shared memory
+  RSMI_COMPUTE_PARTITION_TPX,         //!< Triple GPU mode (TPX)- One-third XCCs
+                                      //!< work together with shared memory
+  RSMI_COMPUTE_PARTITION_QPX,         //!< Quad GPU mode (QPX)- Quarter XCCs
+                                      //!< work together with shared memory
+} rsmi_compute_partition_type_t;
+/// \cond Ignore in docs.
+typedef rsmi_compute_partition_type_t rsmi_compute_partition_type;
+/// \endcond
+
 /**
  * @brief Temperature Metrics.  This enum is used to identify various
  * temperature metrics. Corresponding values will be in millidegress
@@ -3470,6 +3490,70 @@ rsmi_is_P2P_accessible(uint32_t dv_ind_src, uint32_t dv_ind_dst,
 
 /** @} */  // end of HWTopo
 
+/*****************************************************************************/
+/** @defgroup ComputePartition Compute Partition Functions
+ *  These functions are used to configure and query the device's
+ *  compute parition setting.
+ *  @{
+ */
+
+/**
+ *  @brief Retrieves the current compute partitioning for a desired device
+ *
+ *  @details
+ *  Given a device index @p dv_ind and a string @p compute_partition ,
+ *  and uint32 @p len , this function will attempt to obtain the device's
+ *  current compute partition setting string. Upon successful retreival,
+ *  the obtained device's compute partition settings string shall be stored in
+ *  the passed @p compute_partition char string variable.
+ *
+ *  @param[in] dv_ind a device index
+ *
+ *  @param[inout] compute_partition a pointer to a char string variable,
+ *  which the device's current compute partition will be written to.
+ *
+ * @param[in] len the length of the caller provided buffer @p compute_partition
+ *
+ *  @retval ::RSMI_STATUS_SUCCESS call was successful
+ *  @retval ::RSMI_STATUS_INVALID_ARGS the provided arguments are not valid
+ *  @retval ::RSMI_STATUS_UNEXPECTED_DATA data provided to function is not valid
+ *  @retval ::RSMI_STATUS_NOT_SUPPORTED installed software or hardware does not
+ *  support this function with the given arguments
+ *  @retval ::RSMI_STATUS_INSUFFICIENT_SIZE is returned if @p len bytes is not
+ *  large enough to hold the entire compute partition value. In this case,
+ *  only @p len bytes will be written.
+ *
+ */
+rsmi_status_t
+rsmi_dev_compute_partition_get(uint32_t dv_ind, char *compute_partition,
+                               uint32_t len);
+
+/**
+ *  @brief Modifies a selected device's compute partition setting.
+ *
+ *  @details Given a device index @p dv_ind, a type of compute partition
+ *  @p compute_partition, this function will attempt to update the selected
+ *  device's compute partition setting.
+ *
+ *  @param[in] dv_ind a device index
+ *
+ *  @param[inout] compute_partition using enum ::rsmi_copmpute_partition_type_t,
+ *  define what the selected device's compute partition setting should be
+ *  updated to.
+ *
+ *  @retval ::RSMI_STATUS_SUCCESS call was successful
+ *  @retval ::RSMI_STATUS_PERMISSION function requires root access
+ *  @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 with the given arguments
+ *
+ */
+rsmi_status_t
+rsmi_dev_compute_partition_set(uint32_t dv_ind,
+                               rsmi_compute_partition_type_t compute_partition);
+
+/** @} */  // end of ComputePartition
+
 /*****************************************************************************/
 /** @defgroup APISupport Supported Functions
  *  API function support varies by both GPU type and the version of the

include/rocm_smi/rocm_smi_device.h

@@ -3,7 +3,7 @@
  * The University of Illinois/NCSA
  * Open Source License (NCSA)
  *
- * Copyright (c) 2017, Advanced Micro Devices, Inc.
+ * Copyright (c) 2017-2023, Advanced Micro Devices, Inc.
  * All rights reserved.
  *
  * Developed by:
@@ -161,7 +161,8 @@ enum DevInfoTypes {
   kDevMemPageBad,
   kDevNumaNode,
   kDevGpuMetrics,
-  kDevGpuReset
+  kDevGpuReset,
+  kDevComputePartition
 };
 
 typedef struct {

include/rocm_smi/rocm_smi_main.h

@@ -113,6 +113,7 @@ class RocmSMI {
                            uint64_t *weight);
     int get_node_index(uint32_t dv_ind, uint32_t *node_ind);
     const RocmSMI_env_vars& getEnv(void);
+    static const std::map<amd::smi::DevInfoTypes, std::string> devInfoTypesStrings;
 
  private:
     std::vector<std::shared_ptr<Device>> devices_;