fix: [SWDEV-442525] [rocm/amd_smi_lib]

Fixes gpu_process_list

Code changes related to the following:
  * amdsmi_get_gpu_process_list()
  * CLI
  * Examples
  * Unit tests
  * Changelog
  * Readme
  * rocm_smi_lib commit: 677433b367

Change-Id: I9210fbca7a5da92d0a8b472b72ca82597c8e4fb5
Signed-off-by: Oliveira, Daniel <daniel.oliveira@amd.com>

py-interface/README.md

@@ -882,13 +882,24 @@ except AmdSmiException as e:
 
 ### amdsmi_get_gpu_process_list
 
-Description: Returns the list of processes for the given GPU
+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.
 
 Input parameters:
 
 * `processor_handle` device which to query
 
-Output: List of process handles found
+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>
 
 Exceptions that can be thrown by `amdsmi_get_gpu_process_list` function:
 
@@ -906,48 +917,11 @@ try:
     else:
         for device in devices:
             processes = amdsmi_get_gpu_process_list(device)
-            print(processes)
-except AmdSmiException as e:
-    print(e)
-```
-
-### amdsmi_get_gpu_process_info
-
-Description: Returns the info for the given process
-
-Input parameters:
-
-* `processor_handle` device which to query
-* `process_handle` process 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)
-            for process in processes:
-                print(amdsmi_get_gpu_process_info(device, process))
+            if len(processes) == 0:
+                print("No processes running on this GPU")
+            else:
+                for process in processes:
+                    print(process)
 except AmdSmiException as e:
     print(e)
 ```

py-interface/amdsmi_interface.py

@@ -1923,15 +1923,16 @@ def amdsmi_get_gpu_ras_block_features_enabled(
 
 def amdsmi_get_gpu_process_list(
     processor_handle: amdsmi_wrapper.amdsmi_processor_handle,
-) -> List[amdsmi_wrapper.amdsmi_process_handle_t]:
+) -> List[amdsmi_wrapper.amdsmi_proc_info_t]:
     if not isinstance(processor_handle, amdsmi_wrapper.amdsmi_processor_handle):
         raise AmdSmiParameterException(
             processor_handle, amdsmi_wrapper.amdsmi_processor_handle
         )
 
+    # This will get populated with the number of processes found
     max_processes = ctypes.c_uint32(MAX_NUM_PROCESSES)
 
-    process_list = (amdsmi_wrapper.amdsmi_process_handle_t *
+    process_list = (amdsmi_wrapper.amdsmi_proc_info_t *
                     max_processes.value)()
     _check_res(
         amdsmi_wrapper.amdsmi_get_gpu_process_list(
@@ -1939,42 +1940,37 @@ def amdsmi_get_gpu_process_list(
         )
     )
 
-    return [amdsmi_wrapper.amdsmi_process_handle_t(process_list[x])\
-    for x in range(0, max_processes.value)]
+    result = []
+    for index in range(max_processes.value):
+        result.append(process_list[index])
+    return result
 
 
 def amdsmi_get_gpu_process_info(
     processor_handle: amdsmi_wrapper.amdsmi_processor_handle,
-    process: amdsmi_wrapper.amdsmi_process_handle_t,
+    process: amdsmi_wrapper.amdsmi_proc_info_t,
 ) -> Dict[str, Any]:
     if not isinstance(processor_handle, amdsmi_wrapper.amdsmi_processor_handle):
         raise AmdSmiParameterException(
             processor_handle, amdsmi_wrapper.amdsmi_processor_handle
         )
 
-    if not isinstance(process, amdsmi_wrapper.amdsmi_process_handle_t):
+    if not isinstance(process, amdsmi_wrapper.amdsmi_proc_info_t):
         raise AmdSmiParameterException(
-            process, amdsmi_wrapper.amdsmi_process_handle_t)
-
-    info = amdsmi_wrapper.amdsmi_proc_info_t()
-    _check_res(
-        amdsmi_wrapper.amdsmi_get_gpu_process_info(
-            processor_handle, process, ctypes.byref(info)
-        )
-    )
+            process, amdsmi_wrapper.amdsmi_proc_info_t)
 
     return {
-        "name": info.name.decode("utf-8"),
-        "pid": info.pid,
-        "mem": info.mem,
+        "name": process.name.decode("utf-8"),
+        "pid": process.pid,
+        "mem": process.mem,
         "engine_usage": {
-            "gfx": info.engine_usage.gfx,
-            "enc": info.engine_usage.enc
+            "gfx": process.engine_usage.gfx,
+            "enc": process.engine_usage.enc
         },
         "memory_usage": {
-            "gtt_mem": info.memory_usage.gtt_mem,
-            "cpu_mem": info.memory_usage.cpu_mem,
-            "vram_mem": info.memory_usage.vram_mem,
+            "gtt_mem": process.memory_usage.gtt_mem,
+            "cpu_mem": process.memory_usage.cpu_mem,
+            "vram_mem": process.memory_usage.vram_mem,
         },
     }
 

py-interface/amdsmi_wrapper.py

@@ -2212,10 +2212,7 @@ amdsmi_get_gpu_vram_usage.restype = amdsmi_status_t
 amdsmi_get_gpu_vram_usage.argtypes = [amdsmi_processor_handle, ctypes.POINTER(struct_amdsmi_vram_usage_t)]
 amdsmi_get_gpu_process_list = _libraries['libamd_smi.so'].amdsmi_get_gpu_process_list
 amdsmi_get_gpu_process_list.restype = amdsmi_status_t
-amdsmi_get_gpu_process_list.argtypes = [amdsmi_processor_handle, ctypes.POINTER(ctypes.c_uint32), ctypes.POINTER(ctypes.c_uint32)]
-amdsmi_get_gpu_process_info = _libraries['libamd_smi.so'].amdsmi_get_gpu_process_info
-amdsmi_get_gpu_process_info.restype = amdsmi_status_t
-amdsmi_get_gpu_process_info.argtypes = [amdsmi_processor_handle, amdsmi_process_handle_t, ctypes.POINTER(struct_amdsmi_proc_info_t)]
+amdsmi_get_gpu_process_list.argtypes = [amdsmi_processor_handle, ctypes.POINTER(ctypes.c_uint32), ctypes.POINTER(struct_amdsmi_proc_info_t)]
 amdsmi_get_gpu_total_ecc_count = _libraries['libamd_smi.so'].amdsmi_get_gpu_total_ecc_count
 amdsmi_get_gpu_total_ecc_count.restype = amdsmi_status_t
 amdsmi_get_gpu_total_ecc_count.argtypes = [amdsmi_processor_handle, ctypes.POINTER(struct_amdsmi_error_count_t)]
@@ -2580,7 +2577,7 @@ __all__ = \
     'amdsmi_get_gpu_pci_throughput', 'amdsmi_get_gpu_perf_level',
     'amdsmi_get_gpu_pm_metrics_info',
     'amdsmi_get_gpu_power_profile_presets',
-    'amdsmi_get_gpu_process_info', 'amdsmi_get_gpu_process_list',
+    'amdsmi_get_gpu_process_list',
     'amdsmi_get_gpu_ras_block_features_enabled',
     'amdsmi_get_gpu_ras_feature_info',
     'amdsmi_get_gpu_reg_table_info', 'amdsmi_get_gpu_revision',