Merge amd-dev into amd-master 20240405

Signed-off-by: Maisam Arif <maisarif@amd.com>
Change-Id: I7bc20ca726cb5bcd8ac166d2263074562e6e752c


[ROCm/amdsmi commit: 1171c233cf]

projects/amdsmi/CHANGELOG.md

@@ -219,7 +219,6 @@ $ amd-smi topology --json
                 "link_type": "SELF",
                 "num_hops": 0,
                 "bandwidth": "N/A",
-                "fb_sharing": "ENABLED"
             },
             {
                 "gpu": 1,
@@ -229,7 +228,6 @@ $ amd-smi topology --json
                 "link_type": "XGMI",
                 "num_hops": 1,
                 "bandwidth": "50000-100000",
-                "fb_sharing": "ENABLED"
             },
         ...
         ]

projects/amdsmi/CMakeLists.txt

@@ -28,7 +28,7 @@ find_program(GIT NAMES git)
 
 ## Setup the package version based on git tags.
 set(PKG_VERSION_GIT_TAG_PREFIX "amdsmi_pkg_ver")
-get_package_version_number("24.5.0" ${PKG_VERSION_GIT_TAG_PREFIX} GIT)
+get_package_version_number("24.5.1" ${PKG_VERSION_GIT_TAG_PREFIX} GIT)
 message("Package version: ${PKG_VERSION_STR}")
 set(${AMD_SMI_LIBS_TARGET}_VERSION_MAJOR "${CPACK_PACKAGE_VERSION_MAJOR}")
 set(${AMD_SMI_LIBS_TARGET}_VERSION_MINOR "${CPACK_PACKAGE_VERSION_MINOR}")

projects/amdsmi/amdsmi_cli/README.md

@@ -79,7 +79,7 @@ amd-smi will report the version and current platform detected when running the c
 ~$ amd-smi
 usage: amd-smi [-h]  ...
 
-AMD System Management Interface | Version: 24.5.0.0 | ROCm version: 6.1.1 | Platform: Linux Baremetal
+AMD System Management Interface | Version: 24.5.1.0 | ROCm version: 6.1.1 | Platform: Linux Baremetal
 
 options:
   -h, --help          show this help message and exit

projects/amdsmi/amdsmi_cli/amdsmi_commands.py

@@ -2782,13 +2782,11 @@ class AMDSMICommands():
             #         "gpu": GPU #
             #         "bdf": BDF identification
             #         "weight": 0 - self (current node); weight >= 0 correlated with hops (GPU-CPU, GPU-GPU, GPU-CPU-CPU-GPU, etc..)
-            #         "link_status": "ENABLED" - devices linked; "DISABLED" - devices not linked
+            #         "link_status": "ENABLED" - devices linked; "DISABLED" - devices not linked; Correlated to access
             #         "link_type": "SELF" - current node, "PCIE", "XGMI", "N/A" - no link,"UNKNOWN" - unidentified link type
             #         "num_hops": num_hops - # of hops between devices
             #         "bandwidth": numa_bw - The NUMA "minimum bandwidth-maximum bandwidth" beween src and dest nodes
             #                      "N/A" - self node or not connected devices
-            #         "fb_sharing": "ENABLED/DISABLED" - same output as defined in link_status. Devices in a hive setup should
-            #                       all have sharing enabled.
             #     }
 
             for dest_gpu_index, dest_gpu in enumerate(args.gpu):
@@ -2818,7 +2816,7 @@ class AMDSMICommands():
 
                 weight = 0
                 num_hops = 0
-                if src_gpu != dest_gpu: 
+                if src_gpu != dest_gpu:
                     weight = amdsmi_interface.amdsmi_topo_get_link_weight(src_gpu, dest_gpu)
                     num_hops = amdsmi_interface.amdsmi_topo_get_link_type(src_gpu, dest_gpu)['hops']
                 link_status = amdsmi_interface.amdsmi_is_P2P_accessible(src_gpu, dest_gpu)
@@ -2827,7 +2825,6 @@ class AMDSMICommands():
                 else:
                     link_status = "DISABLED"
 
-                # fb_sharing in BM - in a hive configuration, this is
                 # link_status = amdsmi_is_P2P_accessible(src,dest)
                 dest_gpu_links = {
                     "gpu": self.helpers.get_gpu_id_from_device_handle(dest_gpu),
@@ -2837,11 +2834,9 @@ class AMDSMICommands():
                     "link_type": link_type,
                     "num_hops": num_hops,
                     "bandwidth": numa_bw,
-                    "fb_sharing": link_status
                 }
-                if not args.access: # currently includes fb_sharing
+                if not args.access:
                     del dest_gpu_links['link_status']
-                    del dest_gpu_links['fb_sharing']
                 if not args.weight:
                     del dest_gpu_links['weight']
                 if not args.link_type:
@@ -2851,9 +2846,9 @@ class AMDSMICommands():
                 if not args.numa_bw:
                     del dest_gpu_links['bandwidth']
                 links.append(dest_gpu_links)
-                isEndOfDest = dest_gpu_index+1 == len(args.gpu)
+                dest_end = dest_gpu_index+1 == len(args.gpu)
                 isEndOfSrc = src_gpu_index+1 == len(args.gpu)
-                if isEndOfDest:
+                if dest_end:
                     topo_values[src_gpu_index]['links'] = links
                     continue
             if isEndOfSrc:

projects/amdsmi/docs/doxygen/Doxyfile

@@ -48,7 +48,7 @@ PROJECT_NAME           = AMD SMI
 # could be handy for archiving the generated documentation or if some version
 # control system is used.
 
-PROJECT_NUMBER         = "24.5.0.0"
+PROJECT_NUMBER         = "24.5.1.0"
 
 # Using the PROJECT_BRIEF tag one can provide an optional one line description
 # for a project that appears at the top of each page and should give viewer a

projects/amdsmi/include/amd_smi/amdsmi.h

@@ -154,7 +154,7 @@ typedef enum {
 #define AMDSMI_LIB_VERSION_MAJOR 5
 
 //! Minor version should be updated for each API change, but without changing headers
-#define AMDSMI_LIB_VERSION_MINOR 0
+#define AMDSMI_LIB_VERSION_MINOR 1
 
 //! Release version should be set to 0 as default and can be updated by the PMs for each CSP point release
 #define AMDSMI_LIB_VERSION_RELEASE 0

projects/amdsmi/py-interface/README.md

@@ -882,24 +882,13 @@ except AmdSmiException as e:
 
 ### amdsmi_get_gpu_process_list
 
-Description: Returns the list of processes for the given GPU.
-The list is of type `amdsmi_proc_info_t` and holds information about the running process.
+Description: Returns the list of processes running on the target GPU.
 
 Input parameters:
 
 * `processor_handle` device which to query
 
-Output: List of process processes with fields
-
-Output: Dictionary with fields
-
-Field | Description
----|---
-`name` | Name of process
-`pid` | Process ID
-`mem` | Process memory usage
-`engine_usage` | <table><thead><tr> <th> Subfield </th> <th> Description</th> </tr></thead><tbody><tr><td>`gfx`</td><td>GFX engine usage in ns</td></tr><tr><td>`enc`</td><td>Encode engine usage in ns</td></tr></tbody></table>
-`memory_usage` | <table><thead><tr> <th> Subfield </th> <th> Description</th> </tr></thead><tbody><tr><td>`gtt_mem`</td><td>GTT memory usage</td></tr><tr><td>`cpu_mem`</td><td>CPU memory usage</td></tr><tr><td>`vram_mem`</td><td>VRAM memory usage</td></tr> </tbody></table>
+Output: List of `amdsmi_proc_info_t` process objects running on the target GPU; can be empty
 
 Exceptions that can be thrown by `amdsmi_get_gpu_process_list` function:
 
@@ -921,7 +910,50 @@ try:
                 print("No processes running on this GPU")
             else:
                 for process in processes:
-                    print(process)
+                    print(amdsmi_get_gpu_process_info(device, process))
+except AmdSmiException as e:
+    print(e)
+```
+
+### amdsmi_get_gpu_process_info
+
+Description: Returns info about process given the target GPU and the corresponding `amdsmi_proc_info_t` object
+
+Input parameters:
+
+* `processor_handle` device which to query
+
+Output: Dictionary with fields
+
+Field | Description
+---|---
+`name` | Name of process
+`pid` | Process ID
+`mem` | Process memory usage
+`engine_usage` | <table><thead><tr> <th> Subfield </th> <th> Description</th> </tr></thead><tbody><tr><td>`gfx`</td><td>GFX engine usage in ns</td></tr><tr><td>`enc`</td><td>Encode engine usage in ns</td></tr></tbody></table>
+`memory_usage` | <table><thead><tr> <th> Subfield </th> <th> Description</th> </tr></thead><tbody><tr><td>`gtt_mem`</td><td>GTT memory usage</td></tr><tr><td>`cpu_mem`</td><td>CPU memory usage</td></tr><tr><td>`vram_mem`</td><td>VRAM memory usage</td></tr> </tbody></table
+
+Exceptions that can be thrown by `amdsmi_get_gpu_process_info` function:
+
+* `AmdSmiLibraryException`
+* `AmdSmiRetryException`
+* `AmdSmiParameterException`
+
+Example:
+
+```python
+try:
+    devices = amdsmi_get_processor_handles()
+    if len(devices) == 0:
+        print("No GPUs on machine")
+    else:
+        for device in devices:
+            processes = amdsmi_get_gpu_process_list(device)
+            if len(processes) == 0:
+                print("No processes running on this GPU")
+            else:
+                for process in processes:
+                    print(amdsmi_get_gpu_process_info(device, process))
 except AmdSmiException as e:
     print(e)
 ```