Fix metric type error output + re-align with ROCm SMI metrics

Changes:
* [CLI] Provide fix for "/opt/rocm/bin/amd-smi metric
TypeError: '>' not supported between instances of 'str' and 'i"
--> Python API was updated, CLI needed to reflect these changes
* [API] Updated amdsmi.h's with ROCm SMI
--> Incorrectly added mem_bandwidth_acc & mem_max_bandwidth
--> Realigned wrapper with updates
* [Test] Added metrics not shown in gpu_metrics_read.cc

Change-Id: Ia3a172377fd5a582254dd5a46d81dbec7e763cd9
Signed-off-by: Charis Poag <Charis.Poag@amd.com>

py-interface/README.md

@@ -2136,8 +2136,6 @@ Output: Dictionary with fields
 `current_socclks` | List of current soc clock frequencies | MHz
 `current_vclk0s` | List of current v0 clock frequencies | MHz
 `current_dclk0s` | List of current d0 clock frequencies | MHz
-`mem_bandwidth_acc` | Memory bandwidth usage accumulated | GB/s
-`mem_max_bandwidth` | Maximum memory bandwidth usage accumulated  | GB/s
 `pcie_nak_sent_count_acc` | PCIe NAC sent count accumulated |
 `pcie_nak_rcvd_count_acc` | PCIe NAC received count accumulated |
 `jpeg_activity` | List of JPEG engine activity | %

py-interface/amdsmi_interface.py

@@ -3290,8 +3290,6 @@ def amdsmi_get_gpu_metrics_info(
         "current_socclks": list(gpu_metrics.current_socclks),
         "current_vclk0s": list(gpu_metrics.current_vclk0s),
         "current_dclk0s": list(gpu_metrics.current_dclk0s),
-        "mem_bandwidth_acc": gpu_metrics.mem_bandwidth_acc,
-        "mem_max_bandwidth": gpu_metrics.mem_max_bandwidth,
         "pcie_nak_sent_count_acc": gpu_metrics.pcie_nak_sent_count_acc,
         "pcie_nak_rcvd_count_acc": gpu_metrics.pcie_nak_rcvd_count_acc,
         "jpeg_activity": list(gpu_metrics.jpeg_activity),
@@ -3313,8 +3311,7 @@ def amdsmi_get_gpu_metrics_info(
         if gpu_metrics_output[value] == 0xFFFF:
             gpu_metrics_output[value] = "N/A"
 
-    uint_32_values = ['gfx_activity_acc', 'mem_activity_acc', 'mem_max_bandwidth',
-                      'pcie_nak_sent_count_acc', 'pcie_nak_rcvd_count_acc']
+    uint_32_values = ['gfx_activity_acc','mem_activity_acc', 'pcie_nak_sent_count_acc', 'pcie_nak_rcvd_count_acc']
 
     for value in uint_32_values:
         if gpu_metrics_output[value] == 0xFFFFFFFF:
@@ -3323,7 +3320,7 @@ def amdsmi_get_gpu_metrics_info(
     uint_64_values = ['energy_accumulator', 'system_clock_counter', 'firmware_timestamp',
                       'pcie_bandwidth_acc', 'pcie_bandwidth_inst',
                       'pcie_l0_to_recov_count_acc', 'pcie_replay_count_acc',
-                      'pcie_replay_rover_count_acc', 'mem_bandwidth_acc']
+                      'pcie_replay_rover_count_acc']
 
     for value in uint_64_values:
         if gpu_metrics_output[value] == 0xFFFFFFFFFFFFFFFF:
@@ -3345,7 +3342,7 @@ def amdsmi_get_gpu_metrics_info(
         gpu_metrics_output['indep_throttle_status'] = bool(gpu_metrics_output['indep_throttle_status'])
 
     for idx, activity in enumerate(gpu_metrics_output['vcn_activity']):
-        if activity == 0xFFFF:
+        if activity == 0xFFFF or activity > 100:
             gpu_metrics_output['vcn_activity'][idx] = "N/A"
 
     if gpu_metrics_output['gfxclk_lock_status'] == 0xFFFFFFFF:
@@ -3378,7 +3375,7 @@ def amdsmi_get_gpu_metrics_info(
             gpu_metrics_output['current_dclk0s'][idx] = "N/A"
 
     for idx, activity in enumerate(gpu_metrics_output['jpeg_activity']):
-        if activity == 0xFFFF:
+        if activity == 0xFFFF or activity > 100:
             gpu_metrics_output['jpeg_activity'][idx] = "N/A"
 
     return gpu_metrics_output

py-interface/amdsmi_wrapper.py

@@ -1620,11 +1620,8 @@ struct_amdsmi_gpu_metrics_t._fields_ = [
     ('current_vclk0s', ctypes.c_uint16 * 4),
     ('current_dclk0s', ctypes.c_uint16 * 4),
     ('jpeg_activity', ctypes.c_uint16 * 32),
-    ('mem_bandwidth_acc', ctypes.c_uint64),
-    ('mem_max_bandwidth', ctypes.c_uint32),
     ('pcie_nak_sent_count_acc', ctypes.c_uint32),
     ('pcie_nak_rcvd_count_acc', ctypes.c_uint32),
-    ('PADDING_4', ctypes.c_ubyte * 4),
 ]
 
 amdsmi_gpu_metrics_t = struct_amdsmi_gpu_metrics_t